zeaslity/ProjectAGiPrompt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: zeaslity:a02ac144818bba1cd833c14b1b1a46c6dc3dfe64
Branches Tags
zeaslity:master
..
compare: zeaslity:master
Branches Tags
zeaslity:master

2 Commits
a02ac14481 ... master

Author SHA1 Message Date
zeaslity
ed945abdf1 大量更新 2026-03-18 16:16:47 +08:00
zeaslity
8efefcc230 超大量更新 2026-03-18 16:16:40 +08:00
140 changed files with 28383 additions and 22 deletions
Expand all files Collapse all files

2
1-AgentSkills/coding-go-gin-gorm/SKILL.md → .agents/skills/backend-go-gin-gorm/SKILL.md
View File

@@ -1,5 +1,5 @@
---
name: developing-go-gin-gorm wdd-后端开发
name: backend-go-gin-gorm
description: >
使用 Gin + GORM 生成、编写、修改、评审 production-ready 的 Go 后端代码（Generate & Review Go backend code with Gin/GORM）。

0
1-AgentSkills/coding-go-gin-gorm/examples/dao-example.go → .agents/skills/backend-go-gin-gorm/examples/dao-example.go
View File

0
1-AgentSkills/coding-go-gin-gorm/examples/handler-example.go → .agents/skills/backend-go-gin-gorm/examples/handler-example.go
View File

0
1-AgentSkills/coding-go-gin-gorm/examples/service-example.go → .agents/skills/backend-go-gin-gorm/examples/service-example.go
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/api-design-spec.md → .agents/skills/backend-go-gin-gorm/reference/api-design-spec.md
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/api-response-spec.md → .agents/skills/backend-go-gin-gorm/reference/api-response-spec.md
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/coding-standards.md → .agents/skills/backend-go-gin-gorm/reference/coding-standards.md
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/error-codes.go → .agents/skills/backend-go-gin-gorm/reference/error-codes.go
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/framework-usage.md → .agents/skills/backend-go-gin-gorm/reference/framework-usage.md
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/logging-standards.md → .agents/skills/backend-go-gin-gorm/reference/logging-standards.md
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/project-structure.md → .agents/skills/backend-go-gin-gorm/reference/project-structure.md
View File

0
1-AgentSkills/coding-go-gin-gorm/reference/time-handling.md → .agents/skills/backend-go-gin-gorm/reference/time-handling.md
View File

0
1-AgentSkills/coding-go-gin-gorm/scripts/validate-structure.sh → .agents/skills/backend-go-gin-gorm/scripts/validate-structure.sh
View File

391
.agents/skills/dds-to-skill/SKILL.md Normal file
View File

@@ -0,0 +1,391 @@
---
name: dds-to-skill
description: >
将 DDS（详细设计说明书）/ PRD / 架构文档转换为一套可落地的 Claude Code Agent Skills（Converts DDS/PRD/Architecture docs into production-ready Agent Skills）。
包含系统级 Skill、模块级 Skills、横切 Skills 的完整生成流程，涵盖设计细节抽取、reference 分层、frontmatter 规范、质量自检。
触发场景 Trigger: 当用户需要将 DDS 文档转为 Skills / 需要从架构设计文档生成开发指导 Skill / 需要批量创建模块级 Skill 套件。
关键词 Keywords: DDS, PRD, 架构说明, 设计文档, skill 生成, skill 套件, agent skill, 模块拆分, reference 抽取, 契约, API, 状态机, 事件, Schema。
argument-hint: "<dds-file-path> [--output-dir <skills-output-dir>] [--project-name <name>]"
allowed-tools:
- Read
- Write
- Edit
- Glob
- Grep
- Bash
---
# DDS-to-Skill：从设计文档生成 Agent Skills
本 Skill 指导你将一份 DDS（Detailed Design Specification）或 PRD / 架构说明文档，转换为一套**可落地、含设计细节**的 Claude Code Agent Skills 套件。
> **核心理念**：生成的不是"空洞的工作流提示词"，而是**绑定了 DDS 设计细节**、能指导真实开发/审查的 Skill 套件。
---
## Phase 0：读取与理解 DDS
### 0.1 动态注入读取（必须执行）
```bash
# 动态注入：查看源文档目录上下文
!`ls -la $(dirname "$ARGUMENTS")`
# 动态注入：读取 DDS 正文（至少 3 段，覆盖全文）
!`sed -n '1,150p' "$ARGUMENTS"`
!`sed -n '150,300p' "$ARGUMENTS"`
!`sed -n '300,500p' "$ARGUMENTS"`
# 动态注入：抽取章节标题（构建 TOC）
!`grep -nE '^(#{1,6}\s+|[0-9]+(\.[0-9]+){0,3}\s+|第[一二三四五六七八九十]+章|第[0-9]+章)' "$ARGUMENTS" | head -n 80`
```
### 0.2 设计要素定向扫描（至少执行 3 项）
```bash
# API/接口
!`grep -nE "API|接口|路径|路由|request|response|错误码|error|handler" "$ARGUMENTS" | head -n 60`
# 事件/消息/Topic
!`grep -nE "事件|event|MQTT|topic|outbox|消息|payload|幂等|retry|publish|subscribe" "$ARGUMENTS" | head -n 60`
# 数据库/Schema
!`grep -nE "表|schema|字段|索引|unique|constraint|migration|DDL|PostgreSQL|MySQL|GORM" "$ARGUMENTS" | head -n 60`
# 状态机/流程
!`grep -nE "状态机|state|transition|流转|工单|workflow|回调|补偿|lifecycle" "$ARGUMENTS" | head -n 60`
# 安全/授权
!`grep -nE "RBAC|DAC|鉴权|JWT|claim|授权|TOTP|权限|auth|token|session" "$ARGUMENTS" | head -n 60`
# 模块/服务/依赖
!`grep -nE "模块|module|service|微服务|依赖|dependency|import|gateway" "$ARGUMENTS" | head -n 60`
```
### 0.3 无法读取时的降级
若无法读取文件，**必须停止**，输出"继续所需的最小信息清单"：
1. 系统模块列表（名称 + 职责 + 关键技术）
2. 每个模块的接口/API 列表
3. 事件/Topic 定义
4. 数据库表结构
5. 状态机/流程定义
6. 授权模型
7. 模块间依赖关系
**禁止在缺少源文档的情况下臆造设计细节。**
---
## Phase 1：分析与规划
### 1.1 模块识别
从 DDS 中识别所有业务模块，生成模块清单表：
| 模块名 | 职责概述 | 关键技术 | Skill 类型 |
|--------|---------|---------|-----------|
| *从 DDS 抽取* | *从 DDS 抽取* | *从 DDS 抽取* | 系统级/模块级/横切 |
### 1.2 Skill 三层架构规划
必须生成 3 类 Skills：
**A) 系统级 Skill（1 个）**
- 跨模块一致性、依赖规则、全局变更流程
- 命名：`developing-<system-name>-system`
**B) 模块级 Skills（N 个，每模块 1 个）**
- 高频开发指导：实现步骤 + 依赖影响检查
- 命名：`developing-<module-name>`
**C) 横切 Skills（≥ 3 个）**
- 基于 DDS 内容选择，常见横切关注点：
| 横切主题 | 适用场景 | 参考命名 |
|---------|---------|---------|
| API/事件/Schema 契约 | 有跨模块接口定义 | `designing-contracts` |
| 数据库迁移 | 有 DB Schema 定义 | `managing-db-migrations` |
| 可观测性/审计 | 有日志/监控/审计需求 | `managing-observability` |
| 安全/认证 | 有 RBAC/JWT/授权体系 | `implementing-auth` |
| 前端开发规范 | 有前端架构设计 | `frontend-<framework>` |
| 后端编码规范 | 有后端技术栈规范 | `backend-<framework>` |
| 部署/运维 | 有 K8S/Docker/CI 设计 | `deploying-<target>` |
> 实际横切 Skills 必须根据 DDS 内容动态决定，不可少于 3 个。
### 1.3 Name 候选与确认
为每个 Skill 提供 2~3 个命名候选，从中选择 1 个并说明理由。命名规则：
- 动名词形式（如 `developing-*`、`managing-*`、`implementing-*`）
- 小写字母 + 数字 + 连字符
- ≤ 64 字符
- 包含模块名或领域名
---
## Phase 2：DDS 设计细节抽取
### 2.1 章节提取与 reference 目录构建
> **详细规则见** `reference/dds-extraction-guide.md`
从 DDS 章节标题构建 `reference/` 分层目录：
```
<skill-name>/reference/
├── 01-<section-slug>/
│ ├── apis.md
│ ├── db-schema.md
│ └── events-topics.md
├── 02-<section-slug>/
│ └── state-machine.md
└── 03-<section-slug>/
└── security-model.md
```
**目录命名规范**：
- 有序前缀 `01-`、`02-`... + slug
- slug：全小写，非字母数字字符替换为 `-`，连续 `-` 合并，≤ 48 字符
### 2.2 六类设计要素抽取（必须覆盖）
每个模块级 Skill 的 reference/ 必须覆盖**至少 3 类**：
| 要素类型 | 抽取内容 | reference 文件名 |
|---------|---------|-----------------|
| **API/接口** | 路径、方法、请求/响应字段、错误码 | `apis.md` |
| **事件/Topic** | 字段、版本、幂等键、重试语义 | `events-topics.md` |
| **DB Schema** | 字段、索引、约束、迁移策略 | `db-schema.md` |
| **状态机/流程** | 状态、转移、守卫条件、回调、补偿 | `state-machine.md` |
| **授权模型** | JWT claims、RBAC/DAC、权限层级 | `security-model.md` |
| **依赖关系** | 跨模块调用链路、协议、集成点 | `dependencies.md` |
### 2.3 reference 条目格式（强制）
每条 reference 必须包含溯源信息：
```markdown
## <设计要素名称>
- **DDS-Section**: <章节标题原文>
- **DDS-Lines**: L120-L168（或近似行号）
### Extract
<结构化内容：表格/列表/代码块>
```
### 2.4 TBD 标注
如果 DDS 中某个设计要素写得不清楚或缺失：
- **必须标注 `[TBD]`**
- 输出"最小补充信息清单"
- **禁止脑补细节**
---
## Phase 3：逐个生成 SKILL.md
### 3.1 SKILL.md 结构模板
> **详细模板见** `reference/skill-templates.md`
每个 SKILL.md 必须包含以下结构：
```markdown
---
name: <skill-name>
description: <单行，< 1024 字符，中英文混合，第三人称，含功能+触发场景+关键词>
argument-hint: "<参数格式说明>"
allowed-tools:
- Read
- Write # 按需
- Edit # 按需
- Glob
- Grep
- Bash # 按需
---
# <Skill 标题>
<一段话概述本 Skill 的用途和适用范围>
## Quick Context
<动态注入命令，至少 2 处 !`command`>
## Plan
### 产物清单
### 决策点
## Verify
<按类别组织的 Checklist，可勾选>
## Execute
<分步骤的可操作指令>
## Pitfalls
<3~8 条与该模块/主题强相关的常见坑，至少 2 条引用 reference>
## Related References
<指向 reference/ 的链接列表，说明何时查阅>
```
### 3.2 Frontmatter 编写规则
> **详细规范见** `reference/frontmatter-spec.md`
**关键要点**：
- `description` **必须单行**，否则 skill 触发会失败
- 必须中英文混合，确保中文和英文查询都能命中
- 必须包含：功能说明 + 触发场景 + 关键词（含模块名）
- `allowed-tools` 遵循最小授权原则
### 3.3 内容编写原则
1. **删除常识**：只保留 DDS 特有设计与可操作步骤
2. **解释 Why**：对重要约束解释原因，不要堆砌 MUST/ALWAYS
3. **可执行动作**：禁止空话（如"检查 API 兼容"），必须写成具体审查动作
4. **设计细节绑定**：Pitfalls 和 Verify 中至少 2 处引用 `reference/` 的具体内容
5. **行数限制**：SKILL.md 主体 < 500 行
**示例 — 空话 vs 可执行动作**：
```
❌ "检查事件一致性"
✅ "在 reference/events-topics.md 找到 topic 列表，对照仓库 grep 出 publish/subscribe 点"
❌ "验证 JWT 安全"
✅ "校验 JWT claims 是否包含 tenant_id/project_id/role（来自 reference/security-model.md）"
❌ "检查 migration 可回滚"
✅ "migration 必须包含 down SQL；verify.sh grep 检查 `-- +migrate Down` 或回滚段落存在"
```
---
## Phase 4：生成 Supporting Files
### 4.1 目录结构
每个 Skill 遵循标准目录模板：
```
<skill-name>/
├── SKILL.md # 主文件（< 500 行）
├── reference/ # 设计细节（按章节分层）
│ ├── 01-<section>/
│ │ ├── apis.md
│ │ ├── db-schema.md
│ │ └── ...
│ └── 02-<section>/
│ └── ...
├── examples/ # 骨架代码示例
│ └── ...
└── scripts/ # 验证脚本
└── verify.sh # 必须提供
```
### 4.2 verify.sh 编写要求
每个 Skill 必须至少包含 1 个 `verify.sh`：
```bash
#!/bin/bash
# verify.sh - <skill-name> Skill 结构与内容验证
set -e
PASS=0; FAIL=0
check() {
if eval "$2"; then
echo "✅ PASS: $1"; ((PASS++))
else
echo "❌ FAIL: $1"; ((FAIL++))
fi
}
SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"
# 结构检查
check "SKILL.md 存在" "test -f '$SKILL_DIR/SKILL.md'"
check "reference/ 目录存在" "test -d '$SKILL_DIR/reference'"
check "SKILL.md < 500 行" "[ $(wc -l < '$SKILL_DIR/SKILL.md') -lt 500 ]"
# 内容检查
check "frontmatter 包含 name" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^name:'"
check "frontmatter 包含 description" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^description:'"
check "包含 Plan 章节" "grep -q '## Plan' '$SKILL_DIR/SKILL.md'"
check "包含 Verify 章节" "grep -q '## Verify' '$SKILL_DIR/SKILL.md'"
check "包含 Execute 章节" "grep -q '## Execute' '$SKILL_DIR/SKILL.md'"
check "包含 Pitfalls 章节" "grep -q '## Pitfalls' '$SKILL_DIR/SKILL.md'"
# reference 检查
check "reference 有章节子目录" "find '$SKILL_DIR/reference' -maxdepth 1 -type d -name '0*' | grep -q ."
check "reference 文件含 DDS-Section" "grep -rq 'DDS-Section:' '$SKILL_DIR/reference/' 2>/dev/null"
echo ""
echo "=== 结果: $PASS PASS / $FAIL FAIL ==="
[ $FAIL -eq 0 ] && exit 0 || exit 1
```
### 4.3 examples/ 编写要求
- 只放**骨架与关键接口签名**，不放完整实现
- 与模块职责强相关
- 注释说明关键设计决策
---
## Phase 5：全局自检
### 5.1 输出顺序（必须遵守）
1. **Skills 清单表**：系统级 / 模块级 / 横切，含最终 name 与理由
2. **总目录树**：Unix 路径风格
3. **每个 SKILL.md**：完整内容
4. **Supporting files**：按 `文件路径 → 文件内容` 逐个输出
5. **全局自检结果**：逐条 PASS/FAIL + 修复建议
### 5.2 自检 Checklist
按以下维度逐条检查：
**结构完整性**
- [ ] 系统级 Skill 存在（1 个）
- [ ] 模块级 Skills 数量 = 模块数
- [ ] 横切 Skills ≥ 3 个
- [ ] 每个 Skill 都有 SKILL.md + reference/ + scripts/verify.sh
**Frontmatter 规范**
- [ ] description 为单行
- [ ] description < 1024 字符
- [ ] 中英文混合
- [ ] 包含触发场景和关键词
- [ ] allowed-tools 最小授权
**内容质量**
- [ ] SKILL.md < 500 行
- [ ] 包含 Plan/Verify/Execute/Pitfalls 四个章节
- [ ] ≥ 2 处 `!command` 动态注入
- [ ] Pitfalls ≥ 2 条引用 reference
- [ ] 无空话（"检查 XX 一致性"这类无具体动作的描述）
**Reference 质量**
- [ ] 每个模块 Skill 覆盖 ≥ 3 类设计要素
- [ ] reference 有章节分层目录（非扁平）
- [ ] 每条 reference 含 DDS-Section + DDS-Lines 溯源
- [ ] DDS 缺失内容标注 [TBD]
- [ ] 无脑补设计细节
---
## Quick Reference
| 需要了解... | 查阅... |
|------------|--------|
| DDS 抽取的详细方法 | `reference/dds-extraction-guide.md` |
| SKILL.md 模板（系统/模块/横切） | `reference/skill-templates.md` |
| Frontmatter 详细规范 | `reference/frontmatter-spec.md` |
| 质量自检的完整清单 | `reference/quality-checklist.md` |
| 成功案例的目录结构 | `examples/` |

137
.agents/skills/dds-to-skill/examples/conversion-example-multi-module.md Normal file
View File

@@ -0,0 +1,137 @@
# DDS-to-Skill 转换实例：完整系统（多模块）
本文展示将一个包含多模块的 DDS 文档转换为完整 Skill 套件的过程。
---
## 1. 系统概述（模拟 DDS）
```
系统名称：ProjectMoneyX（个人财务管理系统）
技术栈：Go + Gin + GORM / Vue3 + TypeScript + Vuetify3
模块列表：
- 账单导入模块（bill-import）
- 多维分析模块（analysis）
- 预算管理模块（budget）
- 账户管理模块（account）
- 规则引擎模块（rules）
```
---
## 2. Skill 套件规划
### 2.1 Skills 清单
| 类型 | Skill Name | 职责 |
|------|-----------|------|
| 系统级 | `developing-moneyx-system` | 跨模块架构、技术栈规范、依赖管理 |
| 模块级 | `developing-bill-import` | 账单导入 ETL 流水线 |
| 模块级 | `developing-analysis` | 多维财务分析与图表 |
| 模块级 | `developing-budget` | 预算创建与跟踪 |
| 模块级 | `developing-account` | 账户 CRUD 与余额同步 |
| 模块级 | `developing-rules` | 分类规则引擎 |
| 横切 | `designing-contracts` | API/DTO 契约规范 |
| 横切 | `managing-db-migrations` | 数据库迁移策略 |
| 横切 | `managing-observability` | 日志、错误追踪 |
### 2.2 总目录树
```
1-AgentSkills/
├── developing-moneyx-system/
│ ├── SKILL.md
│ ├── reference/
│ │ ├── 01-architecture/
│ │ │ └── dependencies.md
│ │ └── 02-tech-stack/
│ │ └── conventions.md
│ └── scripts/
│ └── verify.sh
├── developing-bill-import/
│ ├── SKILL.md
│ ├── reference/
│ │ ├── 01-etl-pipeline/
│ │ │ └── pipeline-design.md
│ │ ├── 02-api-design/
│ │ │ └── apis.md
│ │ └── 03-data-model/
│ │ └── db-schema.md
│ ├── examples/
│ │ └── etl-processor.go
│ └── scripts/
│ └── verify.sh
├── developing-analysis/
│ ├── ...（同上结构）
├── developing-budget/
│ ├── ...
├── developing-account/
│ ├── ...
├── developing-rules/
│ ├── ...
├── designing-contracts/
│ ├── SKILL.md
│ ├── reference/
│ │ └── api-response-spec.md
│ └── scripts/
│ └── verify.sh
├── managing-db-migrations/
│ ├── SKILL.md
│ ├── reference/
│ │ └── migration-conventions.md
│ └── scripts/
│ └── verify.sh
└── managing-observability/
├── SKILL.md
├── reference/
│ └── logging-standards.md
└── scripts/
└── verify.sh
```
---
## 3. 关键转换决策
### 3.1 模块边界划分
> **决策依据**：DDS 中每个"章节"对应一个业务域，每个业务域生成一个模块级 Skill。
### 3.2 横切关注点识别
从 DDS 全文 grep 识别跨模块使用的技术点：
```bash
# 发现所有模块都用了统一响应格式 → designing-contracts
grep -c "ResponseError\|ResponseSuccess" *.go
# 发现多个模块有 migration 文件 → managing-db-migrations
find . -name "*migration*" -o -name "*migrate*"
# 发现多个模块有日志调用 → managing-observability
grep -rn "log\.\(Info\|Error\|Debug\)" --include="*.go" | wc -l
```
### 3.3 Reference 深度决策
| 要素 | 模块 | DDS 覆盖度 | reference 策略 |
|------|------|-----------|---------------|
| API | bill-import | 完整 | 全量抽取到 apis.md |
| DB Schema | budget | 部分 | 抽取已有 + [TBD] 标注缺失 |
| 事件 | analysis | 无 | 跳过，无需创建事件 reference |
| 状态机 | bill-import | 完整 | ETL 状态流转到 state-machine.md |
---
## 4. 输出示例：系统级 Skill
```yaml
---
name: developing-moneyx-system
description: >
指导 ProjectMoneyX 个人财务管理系统的全局架构决策与跨模块一致性（Guides system-level architecture for ProjectMoneyX personal finance system）。
包含：模块注册、技术栈规范、依赖管理、响应格式统一。
触发场景 Trigger: 新增模块 / 跨模块变更 / 架构决策 / 技术栈选型。
关键词 Keywords: moneyx, system, architecture, 架构, 财务, finance, 模块, cross-module。
---
```

95
.agents/skills/dds-to-skill/examples/conversion-example-workflow.md Normal file
View File

@@ -0,0 +1,95 @@
# DDS-to-Skill 转换实例：工单流程模块
本文展示了一个从 DDS 片段到完整 Skill 的转换过程。
---
## 1. DDS 原文片段（模拟）
```markdown
## 5. 工单管理模块（rmdc-work-procedure）
### 5.1 模块职责
负责工单生命周期管理，包括创建、审批、执行、完成等流转。
### 5.2 数据库设计
#### workflows 主表
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | BIGINT | PK, AUTO_INCREMENT | 工单ID |
| type | VARCHAR(50) | NOT NULL | 工单类型 |
| status | VARCHAR(30) | NOT NULL, DEFAULT 'pending' | 当前状态 |
| creator_id | BIGINT | NOT NULL, FK → users.id | 创建人 |
| assignee_id | BIGINT | FK → users.id | 处理人 |
| version | INT | NOT NULL, DEFAULT 1 | 乐观锁版本号 |
### 5.3 状态机
- pending → submitted → under_review → approved/rejected
- submitted → revoked（创建人可撤销）
- 终态：approved, rejected, revoked, closed
### 5.4 API 接口
- POST /api/workflow/create - 创建工单
- POST /api/workflow/transition - 状态转换
- POST /api/workflow/callback - 业务回调
- POST /api/workflow/list - 工单列表
```
---
## 2. 转换步骤演示
### 步骤 1：模块识别
| 模块 | 职责 | 技术 | Skill 类型 |
|------|------|------|-----------|
| rmdc-work-procedure | 工单生命周期管理 | Go + Gin + PostgreSQL | 模块级 |
### 步骤 2：设计要素抽取
从 DDS 中识别到 4 类要素：
- ✅ API/接口 → 4 个 API 端点
- ✅ DB Schema → workflows 主表
- ✅ 状态机 → 5 个状态 + 转换规则
- ❌ 事件/Topic → DDS 未提及 → 标注 [TBD]
- ❌ 授权模型 → DDS 未提及 → 标注 [TBD]
- ✅ 依赖关系 → 业务模块回调
### 步骤 3：reference 文件生成
```
reference/
├── 01-data-model/
│ └── db-schema.md # workflows 表结构
├── 02-api-design/
│ └── apis.md # 4 个 API 定义
├── 03-workflow-engine/
│ └── state-machine.md # 状态机定义
└── 04-integration/
└── dependencies.md # 回调接口
```
### 步骤 4：SKILL.md 关键段落
```markdown
## Pitfalls
1. **版本号遗漏**: 更新工单时忘记传递 `version` 字段，导致乐观锁失效
（参考 `reference/01-data-model/db-schema.md` 中 workflows.version 字段定义）
2. **终态误转换**: 对 approved/rejected/revoked/closed 状态尝试非法转换
（参考 `reference/03-workflow-engine/state-machine.md` 中的终态定义）
3. **事件推送遗漏**: 状态变更后忘记通知相关方 [TBD - DDS 未定义事件机制]
```
---
## 3. 自检结果
| # | 检查项 | 结果 | 说明 |
|---|-------|------|------|
| S4 | SKILL.md 存在 | ✅ PASS | |
| R1 | 设计要素 ≥ 3 类 | ✅ PASS | API + DB + 状态机 + 依赖 = 4 类 |
| R5 | TBD 标注 | ✅ PASS | 事件和授权标注了 [TBD] |
| C7 | Pitfalls 引用 reference | ✅ PASS | 2 条引用了 reference 路径 |
| R6 | 无脑补 | ✅ PASS | 缺失内容均标注 [TBD] |

260
.agents/skills/dds-to-skill/reference/dds-extraction-guide.md Normal file
View File

@@ -0,0 +1,260 @@
# DDS 设计细节抽取指南
本文档详细说明如何从 DDS（详细设计说明书）中抽取设计细节，并组织到 reference/ 目录中。
---
## 1. 章节标题提取
### 1.1 标题识别规则（按优先级）
| 优先级 | 格式 | 示例 |
|-------|------|------|
| 1 | Markdown 标题 | `# 系统架构`、`## 接口设计` |
| 2 | 编号标题 | `1 概述`、`2.3 数据库设计` |
| 3 | 中文章标题 | `第一章 总体设计`、`第3章` |
| 4 | 中文小节 | `一、系统概述`、`（二）接口规范` |
### 1.2 提取命令
```bash
# 综合提取（推荐首选）
grep -nE '^(#{1,6}\s+|[0-9]+(\.[0-9]+){0,3}\s+|第[一二三四五六七八九十]+章|第[0-9]+章|[一二三四五六七八九十]+、)' "$DDS_FILE" | head -n 120
# 如果上面匹配不足，尝试更宽松的模式
sed -n '1,200p' "$DDS_FILE" | nl -ba | sed -n '1,120p'
```
### 1.3 降级策略
当标题提取不足（少于 3 个）或 DDS 格式混乱时：
```
reference/00-unknown/
├── 01-apis/
├── 02-events/
├── 03-db/
├── 04-state-machine/
└── 05-security/
```
同时在自检中标记 FAIL：
- **原因**：DDS 标题结构不可识别
- **建议**：提供 Markdown 标题 / 章节目录 / md 格式导出版本
---
## 2. 六类设计要素抽取方法
### 2.1 API/接口
**扫描关键词**：
```bash
grep -nE "API|接口|路径|路由|request|response|错误码|error|handler|endpoint|method" "$DDS_FILE" | head -n 80
```
**抽取内容**：
| 字段 | 说明 |
|------|------|
| 路径 | `/api/v1/users/list` |
| 方法 | POST / GET 等 |
| 请求字段 | 字段名、类型、是否必须、校验规则 |
| 响应字段 | 字段名、类型、说明 |
| 错误码 | code + message + 触发场景 |
| 鉴权要求 | JWT / API Key / 公开 |
**输出格式**：
```markdown
## POST /api/v1/users/list
- **DDS-Section**: 3.2 用户管理接口
- **DDS-Lines**: L120-L168
### Request
| 字段 | 类型 | 必须 | 说明 |
|------|------|------|------|
| page | int | N | 页码，默认 1 |
| page_size | int | N | 每页数量，默认 20 |
### Response
| 字段 | 类型 | 说明 |
|------|------|------|
| list | []User | 用户列表 |
| total | int | 总数 |
### 错误码
| code | message | 触发场景 |
|------|---------|---------|
| 1001 | 参数校验失败 | 字段格式错误 |
```
### 2.2 事件/Topic/消息
**扫描关键词**：
```bash
grep -nE "事件|event|MQTT|topic|outbox|消息|payload|幂等|retry|publish|subscribe|Kafka|RabbitMQ" "$DDS_FILE" | head -n 80
```
**抽取内容**：
| 字段 | 说明 |
|------|------|
| Topic/Queue 名 | `cmii/rmdc/{project_id}/command` |
| 方向 | Publish / Subscribe |
| Payload 字段 | 字段名、类型、说明 |
| QoS / 可靠性 | At-least-once / Exactly-once |
| 幂等键 | 用于去重的唯一标识字段 |
| 重试策略 | 重试间隔、最大次数、死信队列 |
### 2.3 数据库/Schema
**扫描关键词**：
```bash
grep -nE "表|schema|字段|索引|unique|constraint|migration|DDL|PostgreSQL|MySQL|GORM|column|CREATE TABLE" "$DDS_FILE" | head -n 80
```
**抽取内容**：
| 字段 | 说明 |
|------|------|
| 表名 | `users`、`workflows` |
| 字段定义 | 名称、类型、约束、默认值 |
| 索引 | 类型（唯一/普通/组合）、字段 |
| 外键关系 | 引用表、级联策略 |
| 迁移策略 | 向前兼容 / 字段演进方案 |
### 2.4 状态机/流程
**扫描关键词**：
```bash
grep -nE "状态机|state|transition|流转|工单|workflow|回调|补偿|lifecycle|FSM|guard" "$DDS_FILE" | head -n 80
```
**抽取内容**：
| 字段 | 说明 |
|------|------|
| 状态枚举 | 名称、值、描述 |
| 转换规则 | from → to、触发动作、守卫条件 |
| 角色权限 | 谁可以触发哪些转换 |
| 回调/副作用 | 状态变更后执行的操作 |
| 补偿机制 | 转换失败时的回滚策略 |
### 2.5 授权模型
**扫描关键词**：
```bash
grep -nE "RBAC|DAC|鉴权|JWT|claim|授权|TOTP|权限|auth|token|session|role|permission" "$DDS_FILE" | head -n 80
```
**抽取内容**：
| 字段 | 说明 |
|------|------|
| 认证方式 | JWT / Session / OAuth |
| JWT Claims | 包含的字段（tenant_id, role 等） |
| 角色定义 | 角色名、权限描述 |
| 权限矩阵 | 角色 × 资源 × 操作 |
| 层级设计 | 一级授权 / 二级授权 |
### 2.6 依赖关系
**扫描关键词**：
```bash
grep -nE "模块|module|service|依赖|dependency|import|gateway|调用|集成|protocol" "$DDS_FILE" | head -n 80
```
**抽取内容**：
| 字段 | 说明 |
|------|------|
| 源模块 | 调用方 |
| 目标模块 | 被调用方 |
| 协议 | HTTP / gRPC / MQTT / 内部调用 |
| 关键接口 | 跨模块调用的接口清单 |
| 失败处理 | 超时、重试、熔断策略 |
---
## 3. reference 目录组织
### 3.1 命名规范
```
reference/
├── 01-architecture-overview/ # 章节序号 + slug
│ └── dependencies.md
├── 02-api-design/
│ ├── apis.md
│ └── error-codes.md
├── 03-data-model/
│ └── db-schema.md
├── 04-message-system/
│ └── events-topics.md
├── 05-workflow-engine/
│ └── state-machine.md
└── 06-security/
└── security-model.md
```
**Slug 生成规则**：
1. 全小写
2. 非字母数字字符替换为 `-`
3. 连续 `-` 合并为单个
4. 截断到 48 字符以内
5. 序号来自 DDS 中的章节顺序
### 3.2 SKILL.md 中的引用方式
```markdown
## Pitfalls
1. **MQTT Topic 命名冲突**：新增 topic 前必须检查
`reference/04-message-system/events-topics.md` 中的 topic 清单
## Related References
| 需要了解... | 查阅... |
|------------|--------|
| API 完整定义 | `reference/02-api-design/apis.md` |
| 数据库表结构 | `reference/03-data-model/db-schema.md` |
```
### 3.3 扁平化兼容
当 DDS 章节结构不明显时，也可以采用扁平 reference，但需在自检中说明：
```
reference/
├── apis.md
├── db-schema.md
├── events-topics.md
├── state-machine.md
├── security-model.md
└── dependencies.md
```
---
## 4. TBD 标注规范
当 DDS 中某个设计要素不完整或不清晰时：
```markdown
## 消息重试策略
- **DDS-Section**: 4.3 消息可靠性
- **DDS-Lines**: L245-L260
### Extract
| 配置项 | 值 |
|-------|---|
| 最大重试次数 | [TBD - DDS 未明确指定] |
| 重试间隔 | [TBD - DDS 未明确指定] |
| 死信队列 | [TBD - DDS 仅提及概念，未给出配置] |
### 最小补充信息清单
1. 重试次数上限（建议 3~5 次）
2. 重试间隔策略（固定 / 指数退避）
3. 死信队列名称与消费策略
```

162
.agents/skills/dds-to-skill/reference/frontmatter-spec.md Normal file
View File

@@ -0,0 +1,162 @@
# Frontmatter 编写规范
Frontmatter 是 Skill 的"身份证"，决定了 Skill 何时被触发、是否被正确识别。编写不当会导致 Skill 永远不会被使用。
---
## 1. 必须字段
### 1.1 name
**规则**：
- 小写字母 + 数字 + 连字符（`-`）
- 动名词形式开头（`developing-`、`managing-`、`implementing-`、`designing-`）
- ≤ 64 字符
- 包含模块名或领域名
**常用前缀**：
| 前缀 | 适用场景 |
|------|---------|
| `developing-` | 模块开发、功能实现 |
| `managing-` | 管理类操作（DB、配置、部署） |
| `implementing-` | 特定技术方案实现 |
| `designing-` | 设计阶段的规范和契约 |
| `writing-` | 编写文档、脚本、测试 |
**示例**：
```yaml
# ✅ 正确
name: developing-work-procedure
name: managing-db-migrations
name: implementing-totp-auth
# ❌ 错误
name: WorkProcedure # 不能大写
name: work_procedure # 不能用下划线
name: wp # 太短，无法触发
```
### 1.2 description
**这是最关键的字段** —— 决定 Skill 是否能被正确触发。
**硬性规则**：
1. **必须单行**（不换行） —— 换行会导致 YAML 解析出错，Skill 静默失败
2. **< 1024 字符**
3. **第三人称**描述
4. **中英文混合** —— 确保中文和英文查询都能命中
5. **包含触发场景**（Trigger）和**关键词**（Keywords）
**结构模板**：
```
<功能概述（中英文）>。包含：<具体能力列表>。触发场景 Trigger: <场景列表>。关键词 Keywords: <关键词列表>。
```
**示例**：
```yaml
# ✅ 正确（单行，中英文混合，包含触发场景和关键词）
description: 指导 rmdc-work-procedure 工单流程模块的开发（Guides development of rmdc-work-procedure workflow module）。包含：状态机实现、工单 CRUD、并发控制、WebSocket 事件。触发场景 Trigger: 修改工单表 / 添加工单类型 / 变更状态转换 / 实现工单 API。关键词 Keywords: workflow, work-procedure, state-machine, 工单, 状态机, 流转。
# ❌ 错误 - 多行（会静默失败！）
description: |
指导工单模块开发。
包含状态机实现。
# ❌ 错误 - 太短，无关键词
description: 工单模块开发指导
# ❌ 错误 - 纯英文，中文查询无法命中
description: Guides the development of workflow module with state machine
```
**推动触发的技巧**：
- Claude 有"不触发"的倾向，所以 description 应该稍微"激进"一些
- 多列出触发场景，覆盖用户可能的表述方式
- 包含同义词（如：工单/workflow/ticket）
### 1.3 argument-hint
**规则**：
- 说明 `$ARGUMENTS` 的期望格式
- 给出 2~3 个具体示例
**示例**：
```yaml
argument-hint: "<action> <target> - e.g., 'create handler user', 'add api /workflow/create', 'update schema workflows'"
```
---
## 2. 可选字段
### 2.1 allowed-tools
**原则**：最小授权 —— 只声明 Skill 真正需要的工具。
| 工具 | 适用场景 |
|------|---------|
| `Read` | 读取文件（几乎总是需要） |
| `Glob` | 搜索文件（几乎总是需要） |
| `Grep` | 搜索文件内容（几乎总是需要） |
| `Bash` | 执行 shell 命令（按需） |
| `Write` | 创建新文件（开发类 Skill 需要） |
| `Edit` | 编辑现有文件（开发类 Skill 需要） |
**示例**：
```yaml
# 只读 Skill（审查/分析类）
allowed-tools:
- Read
- Glob
- Grep
# 开发 Skill（需要写文件）
allowed-tools:
- Read
- Write
- Edit
- Glob
- Grep
- Bash
```
---
## 3. YAML 格式注意事项
### 3.1 多行 description 的安全写法
如果 description 确实很长，使用 `>` 折叠块语法（注意：这仍然会被解析为单行）：
```yaml
description: >
指导 rmdc-work-procedure 工单流程模块的开发。
包含状态机实现、工单 CRUD、并发控制。
触发场景 Trigger: 修改工单表、添加工单类型。
```
> ⚠️ 使用 `>` 时，YAML 会将换行替换为空格，最终合并为单行。这是安全的。
> ❌ 绝不要使用 `|`（保留换行块语法），那会导致多行 description。
### 3.2 特殊字符转义
```yaml
# 包含冒号时用引号包裹
argument-hint: "<action>: <target>"
# 包含 # 时用引号
description: "指导 C# 项目开发"
```
---
## 4. 自检清单
- [ ] `name` 为动名词形式、小写连字符、≤ 64 字符
- [ ] `description` 在最终 YAML 中为单行
- [ ] `description` < 1024 字符
- [ ] `description` 包含中文和英文
- [ ] `description` 包含触发场景（Trigger）
- [ ] `description` 包含关键词（Keywords）
- [ ] `argument-hint` 有具体示例
- [ ] `allowed-tools` 遵循最小授权

114
.agents/skills/dds-to-skill/reference/quality-checklist.md Normal file
View File

@@ -0,0 +1,114 @@
# 全局质量自检清单
DDS-to-Skill 转换完成后，必须按以下清单逐条检查。每条标记 PASS 或 FAIL，FAIL 必须附修复建议。
---
## 1. 结构完整性
| # | 检查项 | PASS 条件 |
|---|-------|----------|
| S1 | 系统级 Skill 存在 | 恰好 1 个 `developing-*-system` Skill |
| S2 | 模块级 Skills 数量 | = DDS 中识别的模块数 |
| S3 | 横切 Skills 数量 | ≥ 3 个 |
| S4 | 每个 Skill 有 SKILL.md | 所有 Skill 目录下存在 SKILL.md |
| S5 | 每个 Skill 有 reference/ | 所有 Skill 目录下存在 reference/ |
| S6 | 每个 Skill 有 verify.sh | 所有 Skill 的 scripts/ 下存在 verify.sh |
| S7 | 目录命名规范 | 全小写、连字符、动名词形式 |
---
## 2. Frontmatter 规范
| # | 检查项 | PASS 条件 |
|---|-------|----------|
| F1 | description 单行 | YAML 解析后 description 为单行字符串 |
| F2 | description 长度 | < 1024 字符 |
| F3 | description 中英文 | 同时包含中文和英文描述 |
| F4 | description 含触发场景 | 包含 "触发场景" 或 "Trigger" 关键词 |
| F5 | description 含关键词 | 包含 "关键词" 或 "Keywords" |
| F6 | name 格式 | 小写字母 + 数字 + 连字符，动名词开头 |
| F7 | argument-hint 存在 | frontmatter 中包含 argument-hint 字段 |
| F8 | allowed-tools 最小授权 | 只读 Skill 不包含 Write/Edit |
---
## 3. 内容质量
| # | 检查项 | PASS 条件 |
|---|-------|----------|
| C1 | SKILL.md 行数 | < 500 行 |
| C2 | 包含 Plan 章节 | grep 到 `## Plan` |
| C3 | 包含 Verify 章节 | grep 到 `## Verify` |
| C4 | 包含 Execute 章节 | grep 到 `## Execute` |
| C5 | 包含 Pitfalls 章节 | grep 到 `## Pitfalls` |
| C6 | 动态注入 | ≥ 2 处 `!` + 反引号命令 |
| C7 | Pitfalls 引用 reference | ≥ 2 条 Pitfall 中出现 `reference/` 路径 |
| C8 | 无空话 | 不含"检查 XX 一致性"这类无具体动作的描述 |
| C9 | 无常识内容 | 不含 Claude 已知的通用知识（如 HTTP 状态码定义） |
| C10 | 术语一致 | 同一概念在所有 Skill 中使用相同术语 |
---
## 4. Reference 质量
| # | 检查项 | PASS 条件 |
|---|-------|----------|
| R1 | 设计要素覆盖率 | 每个模块 Skill 覆盖 ≥ 3 类（API/事件/DB/状态机/权限/依赖） |
| R2 | 章节分层 | reference/ 下存在 `01-*` 等编号目录（或使用扁平+说明） |
| R3 | DDS 溯源 | 每条 reference 含 `DDS-Section:` 字段 |
| R4 | DDS 行号 | 每条 reference 含 `DDS-Lines:` 字段 |
| R5 | TBD 标注 | DDS 缺失内容标注 `[TBD]`，附最小补充清单 |
| R6 | 无脑补 | 所有设计细节可溯源到 DDS 原文 |
| R7 | 内容充分 | reference 包含足够的结构化数据（表格/列表/代码块） |
---
## 5. 跨 Skill 一致性
| # | 检查项 | PASS 条件 |
|---|-------|----------|
| X1 | 模块名一致 | 所有 Skill 中模块名拼写相同 |
| X2 | 错误码不冲突 | 相同错误码在不同 Skill 中含义相同 |
| X3 | API 路径不冲突 | 不同模块的 API 路径无重叠 |
| X4 | 事件/Topic 定义一致 | 同一 Topic 在发布方和订阅方 Skill 中定义相同 |
| X5 | 授权模型一致 | JWT Claims、角色定义在所有 Skill 中一致 |
---
## 6. 自检输出格式
```markdown
# 全局自检结果
## 结构完整性
- ✅ S1 PASS: 系统级 Skill `developing-xxx-system` 存在
- ✅ S2 PASS: 模块级 Skills 数量 = 5（匹配 DDS 中的 5 个模块）
- ❌ S3 FAIL: 横切 Skills 仅 2 个，少于要求的 3 个
- **修复**: 从 DDS 中识别出缓存策略章节，建议增加 `managing-cache` Skill
- ✅ S4 PASS: 所有 Skill 目录下存在 SKILL.md
## Frontmatter 规范
- ✅ F1 PASS: 所有 description 为单行
- ❌ F2 FAIL: `developing-core` 的 description 超过 1024 字符（1156 字符）
- **修复**: 精简触发场景描述，移除重复关键词
## 内容质量
- ✅ C1 PASS: 所有 SKILL.md < 500 行
- ❌ C8 FAIL: `developing-gateway` 中 Verify 包含"检查 API 一致性"
- **修复**: 改为"对照 reference/02-api-design/apis.md 中的接口清单，grep 仓库中的 handler 注册点，确认路径和方法一致"
## 总计: XX PASS / YY FAIL
```
---
## 7. 常见 FAIL 及修复方案
| FAIL 类型 | 常见原因 | 修复方案 |
|----------|---------|---------|
| description 多行 | 使用了 `\|` 语法 | 改用 `>` 或单行字符串 |
| reference 不足 | DDS 内容被遗漏 | 重新扫描 DDS，补充缺失要素 |
| 空话 | 直接复制 DDS 原文 | 转化为可执行的审查动作 |
| 脑补 | DDS 未提及的细节 | 标注 [TBD] 并列出补充清单 |
| 横切不足 | 未充分分析 DDS | 从 DDS 中识别更多跨模块关注点 |

255
.agents/skills/dds-to-skill/reference/skill-templates.md Normal file
View File

@@ -0,0 +1,255 @@
# SKILL.md 模板库
本文档包含系统级 Skill、模块级 Skill、横切 Skill 的 SKILL.md 模板，供 DDS-to-Skill 转换时参照。
---
## 1. 系统级 Skill 模板
```markdown
---
name: developing-<system>-system
description: >
指导 <系统名> 系统级开发决策与跨模块一致性（Guides system-level development for <system>）。
包含：架构总览、模块注册、依赖规则、全局变更流程、版本兼容策略、技术栈规范。
触发场景 Trigger: 新增模块 / 跨模块变更 / 全局架构决策 / 技术栈选型。
关键词 Keywords: <system>, system, architecture, 架构, 模块, 依赖, 兼容, cross-module。
argument-hint: "<module-name|change-type> - 指定涉及的模块名或变更类型"
allowed-tools:
- Read
- Glob
- Grep
- Bash
---
# Developing <System> System
<一段话描述系统整体架构、技术栈、模块组成>
## Quick Context
```bash
# 动态注入：查看系统模块结构
!`ls -la <project-root>/`
# 动态注入：搜索模块间依赖
!`grep -rnE "import|module|service" <project-root>/ | head -30`
```
## Architecture Overview
<ASCII 架构图或层次说明>
## Module Registry
| 模块 | 职责 | 技术 | Skill |
|------|------|------|-------|
| ... | ... | ... | `developing-<module>` |
## Plan
### 产物清单
- [ ] 确定变更涉及的模块列表
- [ ] 确认是否涉及跨模块通信
- [ ] 确认是否涉及契约变更
- [ ] 确认是否需要数据库迁移
### 决策点
1. 变更是否影响多个模块？
2. 是否需要版本兼容处理？
3. 是否需要全局配置变更？
## Verify
- [ ] 模块间依赖无循环
- [ ] 共享契约版本一致
- [ ] 全局配置项完整
- [ ] 技术栈版本对齐
## Execute
### 添加新模块
1. 在项目根目录创建模块目录...
2. 注册到路由/网关...
3. 更新模块依赖图...
### 跨模块变更
1. 列出所有受影响模块...
2. 按依赖顺序逐个修改...
3. 运行集成测试...
## Pitfalls
1. **循环依赖**: 模块间禁止直接 import，必须通过共享接口定义
2. **版本不一致**: 修改共享结构需同步更新所有消费方
3. ...
## Related References
- [模块依赖关系](reference/dependencies.md)
- [技术栈规范](reference/tech-stack.md)
```
---
## 2. 模块级 Skill 模板
```markdown
---
name: developing-<module>
description: >
指导 <module> 模块的开发（Guides development of <module> module）。
包含：<模块职责概述>、API 实现、数据库操作、状态管理、安全校验。
触发场景 Trigger: 开发/修改 <module> 相关功能 / <模块特定场景>。
关键词 Keywords: <module>, <技术关键词>, <业务关键词>。
argument-hint: "<action> <target> - e.g., 'create handler', 'add api', 'update schema'"
allowed-tools:
- Read
- Write
- Edit
- Glob
- Grep
- Bash
---
# Developing <Module>
<一段话描述模块职责、技术栈、在系统中的位置>
## Quick Context
```bash
# 动态注入：查看模块结构
!`find . -name "*.go" -path "*/<module>/*" | head -20`
# 动态注入：查看现有接口
!`grep -rn "func.*Handler\|func.*Service" ./<module>/ | head -20`
```
## Plan
### 产物清单
- [ ] <根据 DDS 列出具体产物>
### 决策点
1. <从 DDS 抽取的关键决策>
2. ...
## Verify
### <验证类别 1>
- [ ] <具体检查项，引用 reference>
### <验证类别 2>
- [ ] <具体检查项>
## Execute
### 1. <步骤标题>
```bash
# 具体操作命令
```
### 2. <步骤标题>
```go
// 关键代码骨架
```
## Pitfalls
1. **<坑名>**: <描述>（参考 `reference/<file>.md`）
2. ...（至少 3 条，至少 2 条引用 reference）
## Related References
- [API 定义](reference/01-<section>/apis.md)
- [数据库 Schema](reference/02-<section>/db-schema.md)
```
---
## 3. 横切 Skill 模板
```markdown
---
name: <crosscut-skill-name>
description: >
<横切关注点>的统一规范与实现指导（Guides <crosscut concern> across all modules）。
包含：<具体内容列表>。
触发场景 Trigger: <触发场景列表>。
关键词 Keywords: <关键词列表>。
argument-hint: "<module-name|file-path> - 指定要应用规范的模块或文件"
allowed-tools:
- Read
- Glob
- Grep
- Bash
---
# <横切 Skill 标题>
<描述这个横切关注点在系统中的重要性和适用范围>
## Quick Context
```bash
# 动态注入
!`<扫描所有模块中与该横切主题相关的文件>`
```
## Plan
### 产物清单
- [ ] <横切维度的产物>
### 决策点
1. <跨模块的统一决策>
2. ...
## Verify
- [ ] <跨模块一致性检查>
- [ ] <规范合规检查>
- [ ] ...
## Execute
### 全局规范
<适用于所有模块的规则>
### 模块适配
<各模块的特殊处理>
## Pitfalls
1. **<跨模块一致性问题>**: <描述>
2. ...
## Related References
- [全局规范定义](reference/<global-spec>.md)
```
---
## 4. 模板使用注意事项
### 4.1 必须自定义的部分
- `<尖括号>` 中的所有占位符
- Plan 的产物清单和决策点必须来自 DDS
- Verify 的检查项必须与模块设计细节对应
- Pitfalls 必须与模块/主题强相关，不可用通用建议填充
### 4.2 禁止照搬模板
模板是结构参考，不是内容来源。以下行为将导致自检 FAIL：
- 产物清单中出现模板占位符
- Pitfalls 与模块无关（如：在前端 Skill 中出现数据库 Pitfall）
- Verify 中没有引用任何 reference
### 4.3 按 DDS 内容增减
- 如果 DDS 中没有状态机，模块 Skill 可以不包含状态机相关 Verify
- 如果 DDS 中有额外的关注点（如性能优化、缓存策略），应增加对应章节
- 横切 Skill 的数量和主题必须由 DDS 内容决定

214
.agents/skills/dds-to-skill/scripts/verify-skill-output.sh Normal file
View File

@@ -0,0 +1,214 @@
#!/bin/bash
# verify-skill-output.sh
# 验证 DDS-to-Skill 转换输出的完整性和质量
#
# 用法：./verify-skill-output.sh <skills-output-dir>
# 示例：./verify-skill-output.sh /path/to/1-AgentSkills
#
# 依赖：bash, grep, sed, find, wc
set -e
SKILLS_DIR="${1:-.}"
PASS=0
FAIL=0
WARN=0
# 颜色输出
GREEN='\033[0;32m'
RED='\033[0;31m'
YELLOW='\033[0;33m'
NC='\033[0m' # No Color
pass() {
echo -e "${GREEN}✅ PASS${NC}: $1"
((PASS++))
}
fail() {
echo -e "${RED}❌ FAIL${NC}: $1"
echo -e " ${RED}修复${NC}: $2"
((FAIL++))
}
warn() {
echo -e "${YELLOW}⚠️ WARN${NC}: $1"
((WARN++))
}
echo "============================================"
echo " DDS-to-Skill 输出质量验证"
echo " 目标目录: $SKILLS_DIR"
echo "============================================"
echo ""
# ============================================
# 1. 结构完整性检查
# ============================================
echo "--- 1. 结构完整性 ---"
# S1: 检查是否有系统级 Skill
SYSTEM_SKILLS=$(find "$SKILLS_DIR" -maxdepth 1 -type d -name "*-system*" 2>/dev/null | wc -l)
if [ "$SYSTEM_SKILLS" -ge 1 ]; then
pass "S1: 存在系统级 Skill ($SYSTEM_SKILLS 个)"
else
warn "S1: 未找到系统级 Skill（名称包含 '-system'）"
fi
# S4: 每个 Skill 都有 SKILL.md
SKILL_DIRS=$(find "$SKILLS_DIR" -maxdepth 1 -type d ! -name "$(basename "$SKILLS_DIR")" 2>/dev/null)
MISSING_SKILLMD=0
for dir in $SKILL_DIRS; do
if [ ! -f "$dir/SKILL.md" ]; then
fail "S4: $dir 缺少 SKILL.md" "创建该目录下的 SKILL.md"
((MISSING_SKILLMD++))
fi
done
if [ "$MISSING_SKILLMD" -eq 0 ]; then
pass "S4: 所有 Skill 目录都有 SKILL.md"
fi
# S5: 每个 Skill 都有 reference/
MISSING_REF=0
for dir in $SKILL_DIRS; do
if [ ! -d "$dir/reference" ]; then
warn "S5: $dir 缺少 reference/ 目录"
((MISSING_REF++))
fi
done
if [ "$MISSING_REF" -eq 0 ]; then
pass "S5: 所有 Skill 目录都有 reference/"
fi
echo ""
# ============================================
# 2. Frontmatter 规范检查
# ============================================
echo "--- 2. Frontmatter 规范 ---"
for dir in $SKILL_DIRS; do
SKILL_FILE="$dir/SKILL.md"
[ ! -f "$SKILL_FILE" ] && continue
SKILL_NAME=$(basename "$dir")
# F1: name 字段
if head -20 "$SKILL_FILE" | grep -q '^name:'; then
pass "F1 [$SKILL_NAME]: frontmatter 包含 name"
else
fail "F1 [$SKILL_NAME]: 缺少 name 字段" "在 frontmatter 中添加 name 字段"
fi
# F2: description 字段
if head -20 "$SKILL_FILE" | grep -q '^description:'; then
pass "F2 [$SKILL_NAME]: frontmatter 包含 description"
else
fail "F2 [$SKILL_NAME]: 缺少 description 字段" "在 frontmatter 中添加 description 字段"
fi
# C1: 行数 < 500
LINE_COUNT=$(wc -l < "$SKILL_FILE")
if [ "$LINE_COUNT" -lt 500 ]; then
pass "C1 [$SKILL_NAME]: SKILL.md = $LINE_COUNT 行 (< 500)"
else
fail "C1 [$SKILL_NAME]: SKILL.md = $LINE_COUNT 行 (>= 500)" "将冗长内容移到 reference/ 中"
fi
done
echo ""
# ============================================
# 3. 内容质量检查
# ============================================
echo "--- 3. 内容质量 ---"
for dir in $SKILL_DIRS; do
SKILL_FILE="$dir/SKILL.md"
[ ! -f "$SKILL_FILE" ] && continue
SKILL_NAME=$(basename "$dir")
# C2-C5: 必须章节
for section in "Plan" "Verify" "Execute" "Pitfalls"; do
if grep -q "## $section" "$SKILL_FILE"; then
pass "C [$SKILL_NAME]: 包含 ## $section"
else
warn "C [$SKILL_NAME]: 缺少 ## $section 章节"
fi
done
# C6: 动态注入
INJECT_COUNT=$(grep -c '!`' "$SKILL_FILE" 2>/dev/null || echo 0)
if [ "$INJECT_COUNT" -ge 2 ]; then
pass "C6 [$SKILL_NAME]: $INJECT_COUNT 处动态注入 (>= 2)"
else
warn "C6 [$SKILL_NAME]: 仅 $INJECT_COUNT 处动态注入 (建议 >= 2)"
fi
# C7: Pitfalls 引用 reference
REF_IN_PITFALLS=$(sed -n '/## Pitfalls/,/## /p' "$SKILL_FILE" | grep -c 'reference/' 2>/dev/null || echo 0)
if [ "$REF_IN_PITFALLS" -ge 2 ]; then
pass "C7 [$SKILL_NAME]: Pitfalls 中 $REF_IN_PITFALLS 处引用 reference (>= 2)"
else
warn "C7 [$SKILL_NAME]: Pitfalls 中仅 $REF_IN_PITFALLS 处引用 reference (建议 >= 2)"
fi
done
echo ""
# ============================================
# 4. Reference 质量检查
# ============================================
echo "--- 4. Reference 质量 ---"
for dir in $SKILL_DIRS; do
[ ! -d "$dir/reference" ] && continue
SKILL_NAME=$(basename "$dir")
# R2: 章节分层
SECTION_DIRS=$(find "$dir/reference" -maxdepth 1 -type d -name '0*' 2>/dev/null | wc -l)
if [ "$SECTION_DIRS" -ge 1 ]; then
pass "R2 [$SKILL_NAME]: reference 有 $SECTION_DIRS 个章节子目录"
else
warn "R2 [$SKILL_NAME]: reference 无章节子目录（使用扁平结构）"
fi
# R3: DDS 溯源
DDS_SECTION_COUNT=$(grep -r 'DDS-Section:' "$dir/reference/" 2>/dev/null | wc -l)
if [ "$DDS_SECTION_COUNT" -ge 1 ]; then
pass "R3 [$SKILL_NAME]: $DDS_SECTION_COUNT 处 DDS-Section 溯源"
else
warn "R3 [$SKILL_NAME]: 无 DDS-Section 溯源标记"
fi
# R5: TBD 标注
TBD_COUNT=$(grep -r '\[TBD' "$dir/reference/" 2>/dev/null | wc -l)
if [ "$TBD_COUNT" -ge 0 ]; then
pass "R5 [$SKILL_NAME]: $TBD_COUNT 处 [TBD] 标注"
fi
# R1: 设计要素类型数
REF_FILES=$(find "$dir/reference" -name "*.md" 2>/dev/null | wc -l)
if [ "$REF_FILES" -ge 3 ]; then
pass "R1 [$SKILL_NAME]: $REF_FILES 个 reference 文件 (>= 3)"
else
warn "R1 [$SKILL_NAME]: 仅 $REF_FILES 个 reference 文件 (建议 >= 3)"
fi
done
echo ""
# ============================================
# 总结
# ============================================
echo "============================================"
echo " 验证完成"
echo " ✅ PASS: $PASS"
echo " ❌ FAIL: $FAIL"
echo " ⚠️ WARN: $WARN"
echo "============================================"
if [ "$FAIL" -gt 0 ]; then
exit 1
else
exit 0
fi

60
.agents/skills/dds-to-skill/scripts/verify.sh Normal file
View File

@@ -0,0 +1,60 @@
#!/bin/bash
# verify.sh - dds-to-skill Skill 自身结构验证
#
# 验证本 Skill 的文件结构和内容完整性
# 用法：cd dds-to-skill && ./scripts/verify.sh
set -e
PASS=0; FAIL=0
check() {
if eval "$2"; then
echo "✅ PASS: $1"; ((PASS++))
else
echo "❌ FAIL: $1"; ((FAIL++))
fi
}
SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"
echo "=== dds-to-skill Skill 自检 ==="
echo "目录: $SKILL_DIR"
echo ""
# 结构检查
check "SKILL.md 存在" "test -f '$SKILL_DIR/SKILL.md'"
check "reference/ 目录存在" "test -d '$SKILL_DIR/reference'"
check "examples/ 目录存在" "test -d '$SKILL_DIR/examples'"
check "scripts/ 目录存在" "test -d '$SKILL_DIR/scripts'"
# SKILL.md 内容检查
check "SKILL.md < 500 行" "[ \$(wc -l < '$SKILL_DIR/SKILL.md') -lt 500 ]"
check "包含 name 字段" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^name:'"
check "包含 description 字段" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^description:'"
check "包含 argument-hint" "head -20 '$SKILL_DIR/SKILL.md' | grep -q 'argument-hint:'"
# 阶段结构检查
check "包含 Phase 0（读取）" "grep -q 'Phase 0' '$SKILL_DIR/SKILL.md'"
check "包含 Phase 1（分析）" "grep -q 'Phase 1' '$SKILL_DIR/SKILL.md'"
check "包含 Phase 2（抽取）" "grep -q 'Phase 2' '$SKILL_DIR/SKILL.md'"
check "包含 Phase 3（生成）" "grep -q 'Phase 3' '$SKILL_DIR/SKILL.md'"
check "包含 Phase 4（支撑文件）" "grep -q 'Phase 4' '$SKILL_DIR/SKILL.md'"
check "包含 Phase 5（自检）" "grep -q 'Phase 5' '$SKILL_DIR/SKILL.md'"
# Reference 文件检查
check "dds-extraction-guide.md 存在" "test -f '$SKILL_DIR/reference/dds-extraction-guide.md'"
check "skill-templates.md 存在" "test -f '$SKILL_DIR/reference/skill-templates.md'"
check "frontmatter-spec.md 存在" "test -f '$SKILL_DIR/reference/frontmatter-spec.md'"
check "quality-checklist.md 存在" "test -f '$SKILL_DIR/reference/quality-checklist.md'"
# Examples 检查
check "至少 1 个转换示例" "find '$SKILL_DIR/examples' -name '*.md' | grep -q ."
# 动态注入检查
INJECT_COUNT=$(grep -c '!\`' "$SKILL_DIR/SKILL.md" 2>/dev/null || echo 0)
check "SKILL.md 包含动态注入 (>= 2 处)" "[ $INJECT_COUNT -ge 2 ]"
echo ""
echo "=== 结果: $PASS PASS / $FAIL FAIL ==="
[ $FAIL -eq 0 ] && exit 0 || exit 1

267
.agents/skills/developing-projectmoneyx/SKILL.md Normal file
View File

@@ -0,0 +1,267 @@
---
name: developing-projectmoneyx
description: >
指导 ProjectMoneyX 多源账单数据治理系统的全栈开发（Guides full-stack development of ProjectMoneyX bill data governance system）。
包含：ETL Pipeline 编排（Parse → Normalize → Dedup → Link → Rule → Export）、插件化解析器对接、三层去重策略、规则引擎映射、Firefly III 适配、SQLite 数据模型、审计追溯。
触发场景 Trigger: 开发/修改 ProjectMoneyX 的 Parser / Pipeline / 去重 / 规则 / 导入导出 / 审计 / 前端页面 / API 接口。
关键词 Keywords: ProjectMoneyX, 账单, bill, ETL, parser, dedup, 去重, 链路合并, transfer link, rule engine, 规则引擎, Firefly III, 导入, import, export, audit, 审计, SQLite, GORM, GIN, Vue3, Vuetify。
argument-hint: "<action> <target>" 例如/ e.g.:
"add parser for ccb", "implement dedup scorer", "create rule handler",
"update transaction schema", "build import preview page"
allowed-tools:
- Read
- Write
- Edit
- Glob
- Grep
- Bash
---
# Developing ProjectMoneyX
ProjectMoneyX 是 Firefly III 生态的**本地化多源账单数据治理中间件**，技术栈为 Go (GIN + GORM) + Vue3 (TypeScript + Vuetify) + SQLite。系统核心是一条 ETL Pipeline：`Parse → Normalize → Dedup → Link → Rule → Export`，将支付宝/微信/银行账单标准化后推送至 Firefly III。
> **架构关键词**：DDD 分层 · 插件化 Adapter · 三层去重 · 规则可解释 · 全链路审计
## Quick Context
```bash
# 动态注入：后端项目结构
!`find projectmoneyx-server/internal -type f -name "*.go" | head -40`
# 动态注入：前端项目结构
!`find projectmoneyx-web/src -type f -name "*.ts" -o -name "*.vue" | head -30`
# 动态注入：数据库表定义
!`grep -rn "TableName\|func.*TableName" projectmoneyx-server/internal/ | head -20`
# 动态注入：API 路由注册
!`grep -rn "Group\|GET\|POST\|PUT\|DELETE" projectmoneyx-server/internal/handler/ | head -30`
```
## Architecture Overview
```
┌─────────────────────────────────────────────────────┐
│ 展现层: Vue3 + TypeScript + Vuetify │
│ 导入中心 / 清洗预览 / 去重处理 / 规则管理 / 导入任务 / 审计 │
├─────────────────────────────────────────────────────┤
│ 接入层: GIN RESTful API (/api/v1/*) │
│ import / transactions / dedup / rules / export / audit │
├─────────────────────────────────────────────────────┤
│ 应用服务层: Pipeline 编排 │
│ ImportBatchService → PipelineService │
├─────────────────────────────────────────────────────┤
│ 业务逻辑层 (ETL Core Domain) │
│ Parser(插件) → Normalize → Match → Link → Rule → Export │
├─────────────────────────────────────────────────────┤
│ 数据持久层: GORM + SQLite (WAL) │
│ 11 张核心表，分阶段事务 │
└─────────────────────────────────────────────────────┘
```
**分层依赖规则**：handler → service → domain（entity/repository）← dao。Parser/Matcher/Linker/Rule/Exporter 为独立可测试组件。
## Module Registry
| 模块 | 包路径 | 职责 | 优先级 |
|------|--------|------|--------|
| 导入中心 | `handler/import` + `service/import_batch` | 文件上传、批次管理 | P0 |
| 解析引擎 | `parser/` | 插件化平台解析器 | P0 |
| 标准化引擎 | `normalize/` | 异构字段 → 统一 Transaction 模型 | P0 |
| 去重引擎 | `matcher/` | 严格去重 + 模糊去重(P1) | P0/P1 |
| 链路引擎 | `linker/` | 转账闭环 + 订单链路合并 | P0 |
| 规则引擎 | `rule/` | 6 类规则按序执行 | P0/P1 |
| 导出引擎 | `exporter/` | Firefly API/CSV 导出 | P0 |
| 审计中心 | `service/audit` | 全链路追溯 | P0 |
| 系统设置 | `handler/settings` + `config/` | Firefly 连接、阈值参数 | P1 |
## Plan
### 产物清单
| 动作 | 产物 |
|------|------|
| `add parser` | `parser/<platform>/<platform>_parser.go` — 实现 `BillParser` 接口 |
| `create handler` | `handler/<resource>_handler.go` — GIN Handler |
| `create service` | `service/<resource>_service.go` — 应用服务 |
| `create dao` | `dao/<resource>_dao.go` — GORM 数据访问 |
| `create entity` | `domain/entity/<resource>.go` — 领域实体 |
| `add rule type` | `rule/<type>_mapper.go` — 规则映射器 |
| `scaffold module` | 上述全部 + DTO + repository 接口 |
### 决策点
1. **Parser 选择**：先检查 `parser/registry.go` 中已注册的解析器，确认目标平台是否已有实现
2. **去重层级**：严格去重(P0) vs 模糊去重(P1) — 新功能默认只实现严格去重
3. **规则执行顺序**：必须遵守 6 步固定顺序（`reference/04-rule-engine/rule-execution.md`）
4. **事务边界**：ETL 每阶段独立事务，禁止跨阶段长事务
5. **SQLite 约束**：单写连接 `MaxOpenConns=1`，启用 WAL 模式
---
## Execute
### 1. 新增平台解析器
```go
// 1. 实现 BillParser 接口 (parser/<platform>/<platform>_parser.go)
type Parser struct{}
func (p *Parser) Platform() string { return "<platform>" }
func (p *Parser) Detect(meta FileMeta, header []string) bool {
// 基于文件名/表头特征判定
}
func (p *Parser) Parse(ctx context.Context, reader io.Reader) ([]RawBillRecord, error) {
// 逐行读取 → 填充 RawBillRecord.RawFields
// 必须设置 SourcePlatform, SourceRecordID, RowNo, RowFingerprint
}
// 2. 注册到 Registry (parser/registry.go)
r.Register(&<platform>.Parser{})
```
**字段映射要求**（参考 `reference/02-parser-engine/field-mappings.md`）：
- `trade_time`：统一 UTC+8，`time.Time`
- `amount`：去除货币符号，正数 `decimal(18,6)`
- `direction`：`income` / `expense` / `transfer` / `refund` / `fee` / `other`
- `category_raw`：保留原始分类，不在 Parser 中做映射
- `order_id`：去除空格，作为唯一标识
### 2. ETL Pipeline 阶段开发
每个阶段必须：
1. 接收 `context.Context` + 数据切片
2. 返回处理后切片 + error
3. 在独立事务中持久化（`db.Transaction`，每批 500 条 `CreateInBatches`）
4. 更新批次状态
```go
// 阶段签名模式
func (s *StageService) Execute(ctx context.Context, txns []*Transaction) ([]*Transaction, error)
```
### 3. 规则引擎扩展
新增规则类型时：
1. 在 `rule/engine.go` 的 `executionOrder` 中确认位置
2. 实现 `MatchConditions(txn)` 和 `ApplyActions(txn)` 方法
3. 确保 `RuleHit` 记录命中日志（含 `BeforeValue` / `AfterValue`）
4. 规则条件 JSON 存储，参考 `reference/04-rule-engine/rule-conditions.md`
### 4. API 开发
遵循统一响应格式：
```go
type Response struct {
Code int `json:"code"` // 0=成功
Message string `json:"message"`
Data interface{} `json:"data"`
}
```
路由分组：`/api/v1/import/*`、`/api/v1/transactions/*`、`/api/v1/dedup/*`、`/api/v1/rules/*`、`/api/v1/export/*`、`/api/v1/audit/*`、`/api/v1/settings/*`
### 5. 前端页面开发
7 个核心页面，全部使用 Vue3 + Composition API + TypeScript：
- 导入中心：`FileUploader.vue` + 拖拽上传 + 进度条
- 清洗预览：`TransactionTable.vue` + `v-data-table` + 行展开对比
- 去重处理：`DedupCompare.vue` + 左右分栏 + 评分因子展开
- 规则管理：`RuleEditor.vue` + 条件构建器 + 测试预览
- 导入任务：统计概览 + 失败列表 + 单条/批量重试
- 审计追溯：`AuditTimeline.vue` + `v-timeline` + 快照展开
- 系统设置：Firefly 连接配置 + 测试连接 + 去重参数配置
---
## Verify
### 架构层级检查
- [ ] handler 层不包含业务逻辑，仅做参数绑定 + 调用 service + 返回响应
- [ ] service 层不直接操作 `*gorm.DB`，通过 repository 接口访问数据
- [ ] domain/entity 不依赖 handler/service
- [ ] 无循环依赖（handler → service → domain ← dao）
### Parser 检查
- [ ] 新增 Parser 实现了 `BillParser` 接口的全部 3 个方法（`Platform()`, `Detect()`, `Parse()`）
- [ ] 已注册到 `parser/registry.go`（`reference/02-parser-engine/parser-interface.md`）
- [ ] 字段映射覆盖了所有原始字段（对照 `reference/02-parser-engine/field-mappings.md`）
- [ ] `amount` 为正数，`direction` 独立表达收支方向
- [ ] `RowFingerprint` 使用 SHA256 生成（`reference/03-dedup-engine/fingerprint.md`）
### 去重与链路检查
- [ ] 严格去重判定键按优先级 3 级执行（`reference/03-dedup-engine/strict-dedup.md`）
- [ ] 模糊去重评分因子 6 项，阈值可配置（`reference/03-dedup-engine/fuzzy-dedup.md`）
- [ ] 转账闭环 5 条件全部满足才匹配（`reference/03-dedup-engine/transfer-link.md`）
- [ ] 疑似重复（60-84 分）进入 `PENDING_REVIEW` 人工确认队列
### 规则引擎检查
- [ ] 6 类规则按固定顺序执行：对手方归一 → 商户归一 → 分类 → 账户 → 标签 → Firefly（`reference/04-rule-engine/rule-execution.md`）
- [ ] 同类型内按 `priority` 升序执行，首条命中即停止
- [ ] 每条命中记录 `RuleHit`，含 `BeforeValue` / `AfterValue`
- [ ] 规则条件 JSON 结构正确（`reference/04-rule-engine/rule-conditions.md`）
### 数据库检查
- [ ] 表结构 11 张表齐全（`reference/05-database/db-schema.md`）
- [ ] 关键索引已创建（`reference/05-database/indexes.md`）
- [ ] SQLite 配置：`MaxOpenConns=1`, WAL 模式, `cache_size=-64000`
- [ ] ETL 每阶段独立事务，`CreateInBatches` 每批 500 条
### API 检查
- [ ] 路由路径遵循 `reference/06-api-design/api-catalog.md`
- [ ] 统一 `Response` / `PageResponse` 结构
- [ ] 导入前 6 项校验完整（`reference/07-export-engine/import-validation.md`）
### 前端检查
- [ ] 所有页面使用 `<script setup lang="ts">` + Composition API
- [ ] 数据表格使用 `v-data-table` + `fixed-header`
- [ ] 处理三种 UI 状态：加载中（skeleton）、空数据（empty-state）、错误（snackbar + 重试）
- [ ] 路由定义匹配 `reference/08-frontend/routes.md`
---
## Pitfalls
1. **支付宝分类是全局基准字典**：系统使用支付宝 22 种分类作为统一标准。微信/银行等平台必须映射到此分类枚举，不要在 Parser 中创造新的分类值体系（参考 `reference/02-parser-engine/field-mappings.md` 中的分类枚举表）
2. **微信分类需要"交易类型 + 商品"联合推断**：微信的"交易类型"是支付动作（商户消费/转账/红包），不是消费语义。必须结合"商品"字段做关键词推断，未命中的归入"其他"并记录。不要直接把微信交易类型当作分类使用（参考 `reference/02-parser-engine/field-mappings.md` 中的微信推断规则流程图）
3. **规则执行顺序不可变**：6 类规则的执行顺序是固定的（对手方归一 → 商户归一 → 分类 → 账户 → 标签 → Firefly），先归一再分类可提升命中率。修改顺序会导致规则相互依赖断裂（参考 `reference/04-rule-engine/rule-execution.md`）
4. **SQLite 单写连接**：`MaxOpenConns` 必须设为 1，SQLite 不支持多写。ETL Pipeline 已通过分阶段事务避免超长锁定。如果遇到 `database is locked` 错误，检查是否有未关闭的事务（参考 `reference/05-database/db-schema.md` 中的 SQLite 配置）
5. **转账闭环需 5 条件全部满足**：金额一致 + 方向互补 + 时间窗口内 + 不同平台 + 非退款/手续费。漏掉任何一项都会导致误合并。特别注意退款交易（direction=refund）不应参与转账闭环（参考 `reference/03-dedup-engine/transfer-link.md`）
6. **行指纹是分钟粒度**：`GenerateRowFingerprint` 使用 `2006-01-02 15:04` 格式（分钟级），不是秒级。这是为了容忍不同平台对同一交易记录的秒级时间差异（参考 `reference/03-dedup-engine/fingerprint.md`）
7. **批次状态机严格受控**：批次状态只能按 `CREATED → UPLOADED → PARSING → ... → IMPORT_SUCCESS` 的线性路径推进，不可跳跃。失败时只能回退至上一可重试状态（参考 `reference/01-architecture/batch-state-machine.md`）
---
## Related References
| 需要了解... | 查阅... |
|------------|--------|
| 系统架构与模块依赖 | `reference/01-architecture/system-overview.md` |
| 批次状态机定义 | `reference/01-architecture/batch-state-machine.md` |
| Parser 接口与注册 | `reference/02-parser-engine/parser-interface.md` |
| 平台字段映射规则 | `reference/02-parser-engine/field-mappings.md` |
| 严格去重判定键 | `reference/03-dedup-engine/strict-dedup.md` |
| 模糊去重评分模型 | `reference/03-dedup-engine/fuzzy-dedup.md` |
| 转账闭环识别规则 | `reference/03-dedup-engine/transfer-link.md` |
| 行指纹生成算法 | `reference/03-dedup-engine/fingerprint.md` |
| 规则条件 JSON 格式 | `reference/04-rule-engine/rule-conditions.md` |
| 规则执行顺序与可解释性 | `reference/04-rule-engine/rule-execution.md` |
| 数据库 11 张表结构 | `reference/05-database/db-schema.md` |
| 关键索引设计 | `reference/05-database/indexes.md` |
| API 接口目录 | `reference/06-api-design/api-catalog.md` |
| 统一响应与错误码 | `reference/06-api-design/response-format.md` |
| Firefly 导出适配 | `reference/07-export-engine/firefly-mapping.md` |
| 导入前校验清单 | `reference/07-export-engine/import-validation.md` |
| 前端路由与页面 | `reference/08-frontend/routes.md` |
| 前端组件交互 | `reference/08-frontend/components.md` |
| 非功能设计要求 | `reference/09-nonfunctional/performance.md` |
| 部署与安全 | `reference/09-nonfunctional/deployment.md` |

57
.agents/skills/developing-projectmoneyx/reference/01-architecture/batch-state-machine.md Normal file
View File

@@ -0,0 +1,57 @@
## 批次状态机
- **DDS-Section**: 5.2 批次状态机
- **DDS-Lines**: L362-L387
### Extract
#### 状态枚举
| 状态 | 说明 | 备注 |
|------|------|------|
| `CREATED` | 批次已创建 | 初始状态 |
| `UPLOADED` | 文件上传完成 | |
| `PARSING` | 正在解析 | |
| `PARSED` | 解析完成 | |
| `NORMALIZING` | 正在标准化 | |
| `NORMALIZED` | 标准化完成 | |
| `MATCHING` | 正在去重/链路合并 | |
| `MATCHED` | 去重/链路完成 | |
| `RULE_APPLYING` | 正在应用规则 | |
| `PREVIEW_READY` | 规则映射完成，可预览 | 用户可在此阶段查看预览结果、人工确认去重 |
| `IMPORTING` | 正在导入 | 用户确认后触发 |
| `IMPORT_SUCCESS` | 全部导入成功 | 终态 |
| `PARTIAL_FAILED` | 部分失败 | 可重试 |
| `IMPORT_FAILED` | 全部失败 | 可重试 |
| `RETRYING` | 重试中 | |
#### 状态转换规则
```
[*] → CREATED: 创建批次
CREATED → UPLOADED: 文件上传完成
UPLOADED → PARSING: 触发解析
PARSING → PARSED: 解析完成
PARSING → UPLOADED: 解析失败（回退）
PARSED → NORMALIZING: 触发标准化
NORMALIZING → NORMALIZED: 标准化完成
NORMALIZED → MATCHING: 触发去重/链路
MATCHING → MATCHED: 去重/链路完成
MATCHED → RULE_APPLYING: 触发规则映射
RULE_APPLYING → PREVIEW_READY: 规则映射完成
PREVIEW_READY → IMPORTING: 用户确认导入
IMPORTING → IMPORT_SUCCESS: 全部成功
IMPORTING → PARTIAL_FAILED: 部分失败
IMPORTING → IMPORT_FAILED: 全部失败
PARTIAL_FAILED → RETRYING: 用户重试
IMPORT_FAILED → RETRYING: 用户重试
RETRYING → IMPORT_SUCCESS: 重试成功
RETRYING → PARTIAL_FAILED: 仍有失败
```
#### 实现要点
- 解析失败时状态回退至 `UPLOADED`，记录错误信息
- `PREVIEW_READY` 是用户交互节点，用户可查看预览结果和人工确认去重
- 失败状态支持重试，不需要整批重做
- 状态变更必须记录到 `audit_logs` 表

113
.agents/skills/developing-projectmoneyx/reference/01-architecture/system-overview.md Normal file
View File

@@ -0,0 +1,113 @@
## 系统架构总览
- **DDS-Section**: 3. 总体架构设计
- **DDS-Lines**: L77-L164
### Extract
#### 分层架构
| 层级 | 技术选型 | 核心职责 |
|------|----------|----------|
| **展现层** | Vue3 + TS + Vuetify | 上传文件、批次管理、预览确认、规则配置、人工确认、导入结果展示 |
| **接入层** | GIN Framework | RESTful 接口，统一参数校验、错误处理、响应封装 |
| **应用服务层** | Go Service | 编排完整业务流程（ETL Pipeline），不承载具体解析规则 |
| **Adapter 层** | Go Plugin Interface | 按平台解析原始文件，输出平台原始记录 DTO |
| **Normalize 层** | Go Service | 统一字段、金额、方向、时间、分类原始值 |
| **Match 层** | Go Service | 严格去重、模糊去重（多因子评分） |
| **Link 层** | Go Service | 转账闭环、订单链路聚合 |
| **Rule 层** | Go Service | 分类、账户、对手方、标签映射 |
| **Export 层** | Go Service | 适配 Firefly III / Data Importer API 或 CSV/JSON |
| **Repository 层** | GORM | 隔离数据库访问，面向领域对象持久化 |
| **数据持久层** | SQLite | 本地数据库，存储全量数据与审计链路 |
#### 数据流转拓扑
```
多源账单导入 → 解析器(Parser) → 标准化入库 → 去重与链路合并 → 规则映射 → 导出/推送
(文件上传) (Adapter层) (SQLite) (Dedup+Link) (Rule Engine) (API/CSV)
```
#### 后端包结构
```
projectmoneyx-server/
├── cmd/server/main.go # 程序入口
├── internal/
│ ├── config/ # 配置管理
│ ├── handler/ # GIN Handler（接入层）
│ ├── middleware/ # 中间件
│ ├── service/ # 应用服务层
│ ├── domain/ # 领域层
│ │ ├── entity/ # 领域实体
│ │ ├── valueobject/ # 值对象
│ │ └── repository/ # 仓储接口
│ ├── parser/ # Adapter 解析层（插件化）
│ ├── normalize/ # 标准化引擎
│ ├── matcher/ # 去重引擎
│ ├── linker/ # 链路合并引擎
│ ├── rule/ # 规则引擎
│ ├── exporter/ # 导出引擎
│ ├── dao/ # 数据访问层（GORM 实现）
│ └── dto/ # 数据传输对象
├── migrations/ # 数据库迁移
├── web/ # 前端打包产物
└── go.mod
```
#### 前端项目结构
```
projectmoneyx-web/
├── src/
│ ├── api/ # API 调用封装
│ ├── views/ # 页面视图 (8 个核心页面)
│ ├── components/ # 可复用组件
│ ├── stores/ # Pinia 状态管理
│ ├── types/ # TypeScript 类型定义
│ ├── router/ # Vue Router
│ ├── plugins/ # Vuetify 等插件
│ ├── App.vue
│ └── main.ts
├── package.json
├── tsconfig.json
└── vite.config.ts
```
#### 模块清单
| 模块 | 包名 | 职责 | 优先级 |
|------|------|------|--------|
| 导入中心 | `import-center` | 文件上传、批次管理、来源识别 | P0 |
| 解析引擎 | `parser-engine` | 平台解析器注册、装载与执行 | P0 |
| 标准化引擎 | `normalize-engine` | 统一模型转换 | P0 |
| 去重引擎 | `dedup-engine` | 严格去重与模糊去重 | P0/P1 |
| 链路引擎 | `link-engine` | 转账闭环与订单链路合并 | P0 |
| 规则引擎 | `rule-engine` | 分类/账户/标签/商户归一化 | P0/P1 |
| 导入编排 | `import-orchestrator` | 导入预览、执行、重试 | P0 |
| 审计中心 | `audit-center` | 审计日志、处理链追溯 | P0 |
| 系统设置 | `settings-center` | Firefly 配置、阈值参数 | P1 |
#### 核心 Service 清单
```go
type ImportBatchService struct { ... } // 批次管理
type PipelineService struct { ... } // ETL 流水线编排
type ParserRegistry struct { ... } // 解析器注册中心
type TransactionNormalizeService struct { ... } // 标准化服务
type DedupMatchService struct { ... } // 去重匹配服务
type TransferLinkService struct { ... } // 转账链路合并服务
type RuleApplyService struct { ... } // 规则应用服务
type FireflyExportService struct { ... } // Firefly 导出服务
type AuditTraceService struct { ... } // 审计追溯服务
```
#### 关键设计约束
| # | 约束 | 说明 |
|---|------|------|
| 1 | 本地优先 | 财务数据敏感，必须本地部署 |
| 2 | 插件化解析器 | 平台格式变化频繁，适配逻辑隔离在 Adapter 层 |
| 3 | 统一交易模型稳定 | 避免下游 Firefly 或上游平台格式污染核心域模型 |
| 4 | 支付宝分类为标准 | 支付宝 22 种分类最丰富，其他平台映射到此体系 |
| 5 | 微信分类需推断 | 微信"交易类型"粗粒度，结合"商品"字段推断分类 |

156
.agents/skills/developing-projectmoneyx/reference/02-parser-engine/field-mappings.md Normal file
View File

@@ -0,0 +1,156 @@
## 平台字段映射规则
- **DDS-Section**: 6.3 支付宝解析规则 + 6.4 微信解析规则 + 6.5 统一交易模型
- **DDS-Lines**: L500-L668
### Extract
#### 支付宝原始字段
```
交易时间 | 交易分类 | 交易对方 | 对方账号 | 商品说明 | 收/支 | 金额 | 收/付款方式 | 交易状态 | 交易订单号 | 商家订单号 | 备注
```
#### 支付宝字段映射表
| 原字段 | 目标字段 | 映射说明 |
|--------|----------|----------|
| 交易时间 | `trade_time` | 解析为 `time.Time`，统一 UTC+8 |
| 交易分类 | `category_raw` | 直接作为原始分类（22 种标准分类） |
| 交易对方 | `counterparty` | 交易对手名称 |
| 对方账号 | `counterparty_account` | 存入扩展字段 |
| 商品说明 | `merchant_name` / `note` | 优先作为商户名，辅助作为备注 |
| 收/支 | `direction` | "收入" → income, "支出" → expense, "其他" → other |
| 金额 | `amount` | 去除 ¥ 符号，解析为 Decimal 正数 |
| 收/付款方式 | `payment_method` | 存入扩展字段，可用于账户映射 |
| 交易状态 | `trade_status` | "交易成功" / "退款成功" 等 |
| 交易订单号 | `source_record_id` / `order_id` | 去除空格，作为唯一标识 |
| 商家订单号 | `merchant_order_id` / `parent_order_id` | 可用于链路关联 |
| 备注 | `note` | 补充备注 |
#### 支付宝标准分类枚举（22 类）— 全局统一基准
| 编号 | 分类名称 | 编号 | 分类名称 |
|------|----------|------|----------|
| 1 | 餐饮美食 | 12 | 退款 |
| 2 | 投资理财 | 13 | 教育培训 |
| 3 | 日用百货 | 14 | 住房物业 |
| 4 | 数码电器 | 15 | 酒店旅游 |
| 5 | 交通出行 | 16 | 文化休闲 |
| 6 | 充值缴费 | 17 | 运动户外 |
| 7 | 信用借还 | 18 | 爱车养车 |
| 8 | 转账红包 | 19 | 商业服务 |
| 9 | 生活服务 | 20 | 母婴亲子 |
| 10 | 家居家装 | 21 | 收入 |
| 11 | 医疗健康 | 22 | 其他 |
> **关键设计决策**：支付宝拥有最丰富的 22 种交易分类，系统将其作为**全局统一分类基准字典**。所有其他平台的交易分类最终都应映射到此套分类枚举。
#### 微信原始字段
```
交易时间 | 交易类型 | 交易对方 | 商品 | 收/支 | 金额(元) | 支付方式 | 当前状态 | 交易单号 | 商户单号 | 备注
```
#### 微信字段映射表
| 原字段 | 目标字段 | 映射说明 |
|--------|----------|----------|
| 交易时间 | `trade_time` | 解析为 `time.Time`，统一 UTC+8 |
| 交易类型 | `category_raw` | 存储原始类型，需通过推断映射到标准分类 |
| 交易对方 | `counterparty` | 交易对手名称 |
| 商品 | `merchant_name` / `product_desc` | **关键字段**，用于推断实际消费分类 |
| 收/支 | `direction` | "收入" → income, "支出" → expense |
| 金额(元) | `amount` | 去除 ¥ 符号，解析为 Decimal 正数 |
| 支付方式 | `payment_method` | 存入扩展字段 |
| 当前状态 | `trade_status` | "支付成功" / "已退款" 等 |
| 交易单号 | `source_record_id` / `order_id` | 去除空格 |
| 商户单号 | `merchant_order_id` / `parent_order_id` | 链路关联 |
| 备注 | `note` | 补充备注 |
#### 微信分类推断规则
微信"交易类型"多为支付动作（商户消费、扫二维码付款、转账、红包等），无实际消费语义。推断流程：
1. **交易类型 = 转账** → 转账红包
2. **交易类型 = 微信红包** → 转账红包
3. **交易类型含 "退款"** → 退款
4. **交易类型 = 商户消费/扫二维码付款** → 基于"商品"字段关键词推断：
| 微信交易类型 | 商品关键词 | 推断标准分类 |
|-------------|-----------|-------------|
| 商户消费 | 美团 / 外卖 / 餐厅 / 咖啡 / 面包 | 餐饮美食 |
| 商户消费 | 滴滴 / 打车 / 地铁 / 高铁 / 加油 | 交通出行 |
| 商户消费 | 京东 / 超市 / 便利店 / 百货 | 日用百货 |
| 商户消费 | 电费 / 水费 / 话费 / 燃气 | 充值缴费 |
| 商户消费 | 医院 / 药店 / 体检 | 医疗健康 |
| 商户消费 | 电影 / 游戏 / 书籍 | 文化休闲 |
| 商户消费 | 酒店 / 景点 / 旅行 | 酒店旅游 |
| 商户消费 | 无法识别 | 其他（待人工补充） |
> **设计原则**：若商品内容无法识别关键词，先落入"其他"分类，并允许用户通过规则管理补充映射。系统应记录未命中规则的记录，便于后续规则完善。
#### 统一交易模型 (Transaction)
```go
type Transaction struct {
ID string
TransactionID string // 业务唯一 ID
BatchID string
SourcePlatform string
SourceRecordID string
TradeTime time.Time
Amount decimal.Decimal // 正数，方向独立表达
Currency string // 默认 CNY
Direction string // income/expense/transfer/refund/fee/other
Counterparty string
MerchantName string
CategoryRaw string // 原始分类（来自平台）
CategoryMapped string // 映射后分类（规则引擎填充）
AccountMapped string // 映射账户
Tags string // 逗号分隔
OrderID string
ParentOrderID string
PaymentMethod string
Note string
RawPayload string // 原始记录完整 JSON 快照
RowFingerprint string
Status string // PENDING_CLEAN → CLEANED → ... → IMPORTED
FireflyTxnID string
}
```
#### 标准化规则
| 规则项 | 说明 |
|--------|------|
| 时间 | 统一存储为 `Asia/Shanghai (UTC+8)` |
| 金额 | 统一使用正数（`decimal(18,6)`），方向独立用 `direction` 表达 |
| 币种 | 默认 `CNY` |
| 状态 | 初始为 `PENDING_CLEAN` |
| 原始快照 | 完整写入 `raw_payload`（JSON），确保审计可追溯 |
| 指纹 | 对关键字段做 SHA256，用于严格去重 |
#### Direction 枚举
| 值 | 说明 |
|----|------|
| `INCOME` | 收入 |
| `EXPENSE` | 支出 |
| `TRANSFER` | 内部转账 |
| `REFUND` | 退款 |
| `FEE` | 手续费 |
| `OTHER` | 其他 |
#### TransactionStatus 枚举
| 值 | 说明 |
|----|------|
| `PENDING_CLEAN` | 待清洗（标准化完成） |
| `CLEANED` | 已清洗 |
| `PENDING_REVIEW` | 待人工确认（模糊去重疑似） |
| `READY_TO_IMPORT` | 可导入 |
| `IMPORTING` | 导入中 |
| `IMPORTED` | 已导入 |
| `FAILED` | 导入失败 |
| `DUPLICATE` | 重复记录 |

90
.agents/skills/developing-projectmoneyx/reference/02-parser-engine/parser-interface.md Normal file
View File

@@ -0,0 +1,90 @@
## 解析器接口设计
- **DDS-Section**: 6.1 解析器接口设计 + 6.2 解析器注册中心
- **DDS-Lines**: L438-L498
### Extract
#### BillParser 接口
```go
// BillParser 是所有平台解析器必须实现的接口
type BillParser interface {
// Platform 返回平台标识符，如 "alipay", "wechat", "ccb"
Platform() string
// Detect 根据文件元信息和表头判断是否为本平台文件
Detect(fileMeta FileMeta, header []string) bool
// Parse 解析指定文件，返回原始记录列表
Parse(ctx context.Context, reader io.Reader) ([]RawBillRecord, error)
}
```
#### FileMeta 文件元信息
```go
type FileMeta struct {
FileName string
FileType string // csv, xlsx, txt
FileHash string
FileSize int64
}
```
#### RawBillRecord 原始账单记录
```go
type RawBillRecord struct {
SourcePlatform string
SourceRecordID string
RawFields map[string]string // 原始 K-V 字段
RowNo int
RowFingerprint string
}
```
#### Registry 解析器注册中心
```go
type Registry struct {
parsers []BillParser
}
func NewRegistry() *Registry {
r := &Registry{}
// 注册所有解析器
r.Register(&alipay.Parser{})
r.Register(&wechat.Parser{})
r.Register(&ccb.Parser{})
r.Register(&icbc.Parser{})
return r
}
// Detect 自动检测文件对应的解析器
func (r *Registry) Detect(meta FileMeta, header []string) (BillParser, error) {
for _, p := range r.parsers {
if p.Detect(meta, header) {
return p, nil
}
}
return nil, ErrUnknownPlatform
}
```
#### 新增解析器步骤
1. 在 `parser/<platform>/` 目录下创建 `<platform>_parser.go`
2. 实现 `BillParser` 接口的 3 个方法
3. 在 `parser/registry.go` 的 `NewRegistry()` 中调用 `r.Register()`
4. `Detect()` 方法基于文件名特征或 CSV 表头关键词判定
5. `Parse()` 逐行读取文件，填充 `RawBillRecord.RawFields`
#### V1.0 支持的平台
| 平台 | 标识符 | 文件格式 | 优先级 |
|------|--------|----------|--------|
| 支付宝 | `alipay` | CSV | P0（优先） |
| 微信支付 | `wechat` | CSV | P0（优先） |
| 建设银行 | `ccb` | CSV/Excel | P1（次优先） |
| 工商银行 | `icbc` | CSV/Excel | P1（次优先） |

41
.agents/skills/developing-projectmoneyx/reference/03-dedup-engine/fingerprint.md Normal file
View File

@@ -0,0 +1,41 @@
## 行指纹生成算法
- **DDS-Section**: 7.2 严格去重 — 行指纹算法
- **DDS-Lines**: L709-L726
### Extract
#### 指纹生成函数
```go
func GenerateRowFingerprint(t *Transaction) string {
raw := fmt.Sprintf("%s|%s|%s|%s|%s|%s",
t.TradeTime.Format("2006-01-02 15:04"), // 分钟粒度（非秒级）
t.Amount.String(),
t.Direction,
normalizeString(t.Counterparty),
normalizeString(t.MerchantName),
t.OrderID,
)
hash := sha256.Sum256([]byte(raw))
return hex.EncodeToString(hash[:])
}
```
#### 关键设计决策
- **分钟粒度**：使用 `2006-01-02 15:04` 格式（精确到分钟），不是 `15:04:05`（秒级）
- **原因**：不同平台对同一交易的记录时间可能有秒级差异（如支付宝记录 10:30:15，微信记录 10:30:22），分钟粒度可以容忍这种差异
- **normalizeString** 处理：去除前后空格、全角转半角、统一大小写
- **SHA256 输出**：64 字符的十六进制字符串
#### 参与指纹的字段
| 字段 | 处理方式 |
|------|----------|
| `TradeTime` | `Format("2006-01-02 15:04")` — 分钟粒度 |
| `Amount` | `Decimal.String()` — 标准化数字字符串 |
| `Direction` | 原值：income/expense/... |
| `Counterparty` | `normalizeString()` — 去空格、标准化 |
| `MerchantName` | `normalizeString()` — 去空格、标准化 |
| `OrderID` | 原值（已在 Parser 中去除空格） |

85
.agents/skills/developing-projectmoneyx/reference/03-dedup-engine/fuzzy-dedup.md Normal file
View File

@@ -0,0 +1,85 @@
## 模糊去重（多因子评分 — P1 阶段）
- **DDS-Section**: 7.3 模糊去重（多因子评分 — P1 阶段）
- **DDS-Lines**: L755-L818
### Extract
#### 多因子评分模型
| 因子 | 分值 | 评分说明 |
|------|------|----------|
| 时间在 ±5 分钟内 | 30 | 时间差越小得分越高，超出窗口直接 0 分 |
| 金额精确一致 | 30 | 金额一致得满分，差额在手续费容差内得部分分(20分) |
| 交易方向一致 | 10 | 方向相同得满分 |
| 订单号相同/相近 | 15 | 完全一致 15 分，包含关系 10 分 |
| 对手方相似 | 10 | Levenshtein 相似度 + contains 判定 |
| 来源关联规则命中 | 5 | 预配置的平台关联规则 |
**总分 = 100 分**
#### 判定阈值（可配置）
| 分值范围 | 判定结果 | 处理方式 |
|----------|----------|----------|
| ≥ 85 | 自动判定重复 | 自动标记 DUPLICATE |
| 60 ~ 84 | 疑似重复 | 标记 PENDING_REVIEW，进入人工确认队列 |
| < 60 | 不判定重复 | 保留独立交易 |
#### 评分算法骨架
```go
type FuzzyScorer struct {
TimeWindow time.Duration // 默认 5 分钟
AmountEpsilon float64 // 金额容差（手续费）
}
func (s *FuzzyScorer) Score(a, b *Transaction) int {
score := 0
// 时间因子 (30分) — 线性衰减
timeDiff := math.Abs(a.TradeTime.Sub(b.TradeTime).Minutes())
if timeDiff <= s.TimeWindow.Minutes() {
score += int(30 * (1 - timeDiff/s.TimeWindow.Minutes()))
}
// 金额因子 (30分)
if a.Amount.Equal(b.Amount) {
score += 30
} else if a.Amount.Sub(b.Amount).Abs().LessThan(decimal.NewFromFloat(s.AmountEpsilon)) {
score += 20
}
// 方向因子 (10分)
if a.Direction == b.Direction { score += 10 }
// 订单号因子 (15分)
if a.OrderID != "" && a.OrderID == b.OrderID {
score += 15
} else if strings.Contains(a.OrderID, b.OrderID) || strings.Contains(b.OrderID, a.OrderID) {
score += 10
}
// 对手方因子 (10分) — Levenshtein 相似度
score += int(10 * counterpartySimilarity(a.Counterparty, b.Counterparty))
// 来源规则因子 (5分)
if s.platformLinked(a.SourcePlatform, b.SourcePlatform) { score += 5 }
return score
}
```
#### 配置项
| 配置键 | 默认值 | 说明 |
|--------|--------|------|
| `fuzzy_time_window` | 5 | 模糊匹配时间窗口（分钟） |
| `fuzzy_threshold_high` | 85 | 自动判定重复阈值 |
| `fuzzy_threshold_low` | 60 | 疑似重复阈值 |
| `amount_epsilon` | 0.01 | 金额容差（手续费） |
#### 性能优化
- 按 `trade_time` 时间分桶，避免全表 O(N²) 扫描
- 使用索引 `idx_txn_trade_time` 加速时间范围查询

48
.agents/skills/developing-projectmoneyx/reference/03-dedup-engine/strict-dedup.md Normal file
View File

@@ -0,0 +1,48 @@
## 严格去重（精确匹配）
- **DDS-Section**: 7.2 严格去重（基础去重 — 精确匹配）
- **DDS-Lines**: L697-L753
### Extract
#### 三级唯一性判定键（按优先级）
| 优先级 | 判定键 | 适用场景 |
|--------|--------|----------|
| 1 | `source_platform` + `source_record_id` | 同一平台重复导入 |
| 2 | `source_file_hash` + `row_fingerprint` | 同一文件重复上传 |
| 3 | `order_id`（若可信） | 跨批次订单号匹配 |
#### 执行流程
```go
func (s *StrictDedup) Execute(ctx context.Context, txns []*Transaction) ([]*Transaction, error) {
var result []*Transaction
for _, txn := range txns {
// 判定键 1: platform + record_id
exists, existingID := s.repo.FindByPlatformAndRecordID(
ctx, txn.SourcePlatform, txn.SourceRecordID)
if exists {
s.createDedupRelation(ctx, txn.ID, existingID, "strict", 100)
txn.Status = "DUPLICATE"
continue
}
// 判定键 2: file_hash + fingerprint
exists, existingID = s.repo.FindByFingerprint(ctx, txn.RowFingerprint)
if exists {
s.createDedupRelation(ctx, txn.ID, existingID, "strict", 100)
txn.Status = "DUPLICATE"
continue
}
result = append(result, txn)
}
return result, nil
}
```
#### 实现要点
- 命中时创建 `dedup_relation`（relation_type=`strict`, confidence=100）
- 被判重的交易 status 设为 `DUPLICATE`
- 只返回未命中的交易进入下一阶段
- 使用数据库索引 `idx_txn_platform_record` 和 `idx_txn_fingerprint` 加速查询

78
.agents/skills/developing-projectmoneyx/reference/03-dedup-engine/transfer-link.md Normal file
View File

@@ -0,0 +1,78 @@
## 转账闭环识别
- **DDS-Section**: 7.4 链路合并（转账闭环 + 订单链路）
- **DDS-Lines**: L820-L871
### Extract
#### 典型场景
银行卡支出 1000 元（流向支付宝），支付宝收入 1000 元 → 合并为一笔内部转账。
#### 转账闭环识别规则（5 项全部满足）
| # | 条件 | 说明 |
|---|------|------|
| 1 | 金额一致 | `a.Amount.Equal(b.Amount)` |
| 2 | 方向互补 | 一条 expense + 一条 income |
| 3 | 时间窗口内 | 默认 ±30 分钟（`transfer_time_window` 可配置） |
| 4 | 不同平台 | `a.SourcePlatform != b.SourcePlatform` |
| 5 | 非退款/手续费 | `direction` 不是 `refund` 或 `fee` |
#### 实现骨架
```go
func (l *TransferLinker) Detect(a, b *Transaction) *LinkResult {
// 条件 1: 金额一致
if !a.Amount.Equal(b.Amount) { return nil }
// 条件 2: 方向互补
if !((a.Direction == "expense" && b.Direction == "income") ||
(a.Direction == "income" && b.Direction == "expense")) { return nil }
// 条件 3: 时间窗口
if math.Abs(a.TradeTime.Sub(b.TradeTime).Minutes()) > l.TimeWindow { return nil }
// 条件 4: 不同平台
if a.SourcePlatform == b.SourcePlatform { return nil }
// 条件 5: 非退款/手续费
if a.Direction == "refund" || b.Direction == "refund" { return nil }
if a.Direction == "fee" || b.Direction == "fee" { return nil }
return &LinkResult{
ParentTransactionID: selectPrimary(a, b).ID,
ChildTransactionID: selectSecondary(a, b).ID,
LinkType: "transfer",
FromAccount: mapToAccount(getExpenseSide(a, b)),
ToAccount: mapToAccount(getIncomeSide(a, b)),
}
}
```
#### 订单链路合并
**典型场景**：京东订单 + 微信支付，一笔真实消费产生多条流水。
**合并策略**：
- 保留更完整的业务记录为主交易（优先保留有商品详情的记录）
- 其他记录挂为关联来源
- 形成 `parent_order_id` 聚合链路
#### LinkResult 数据结构
```go
type LinkResult struct {
ParentTransactionID string
ChildTransactionID string
LinkType string // transfer / order / refund / fee
FromAccount string
ToAccount string
}
```
#### 配置项
| 配置键 | 默认值 | 说明 |
|--------|--------|------|
| `transfer_time_window` | 30 | 转账闭环时间窗口（分钟） |

63
.agents/skills/developing-projectmoneyx/reference/04-rule-engine/rule-conditions.md Normal file
View File

@@ -0,0 +1,63 @@
## 规则条件 JSON 格式
- **DDS-Section**: 8.2 规则匹配条件
- **DDS-Lines**: L938-L967
### Extract
#### 条件匹配维度
| 条件类型 | 字段 | 说明 | 示例 |
|----------|------|------|------|
| 平台过滤 | `platform` | 指定生效平台 | `"alipay"` |
| 原始分类 | `category_raw` | 原始分类匹配 | `"餐饮美食"` |
| 关键词 | `keywords` | 商品/商户名关键词 | `["美团", "外卖"]` |
| 正则 | `regex` | 正则表达式匹配 | `"^滴滴.*出行$"` |
| 金额范围 | `amount_range` | [min, max] | `[0, 50]` |
| 方向 | `direction` | 收支方向 | `"expense"` |
| 对手方 | `counterparty` | 对手方包含 | `"支付宝"` |
#### JSON 结构示例
```json
{
"platform": "wechat",
"conditions": {
"category_raw": "商户消费",
"keywords": ["美团", "外卖", "饿了么"],
"direction": "expense"
},
"actions": {
"category_mapped": "餐饮美食",
"merchant_normalized": "外卖平台"
}
}
```
#### Rule 数据模型
```go
type Rule struct {
ID string // UUID
RuleType string // 规则类型枚举
Priority int // 优先级（越小越高）
PlatformScope string // 平台范围：all / alipay / wechat
ConditionsJSON string // 条件 JSON
ActionsJSON string // 动作 JSON
Enabled bool // 是否启用
Description string // 规则描述
CreatedAt time.Time
UpdatedAt time.Time
}
```
#### RuleType 枚举
| 类型 | 说明 |
|------|------|
| `COUNTERPARTY_NORMALIZE` | 对手方归一化 |
| `MERCHANT_NORMALIZE` | 商户名归一化 |
| `CATEGORY_MAPPING` | 分类映射 |
| `ACCOUNT_MAPPING` | 账户映射 |
| `TAG_MAPPING` | 标签映射 |
| `FIREFLY_FIELD_MAPPING` | Firefly 字段映射 |

89
.agents/skills/developing-projectmoneyx/reference/04-rule-engine/rule-execution.md Normal file
View File

@@ -0,0 +1,89 @@
## 规则执行顺序与可解释性
- **DDS-Section**: 8.3 规则执行顺序 + 8.4 规则引擎核心实现 + 8.5 可解释性设计
- **DDS-Lines**: L969-L1045
### Extract
#### 固定执行顺序（不可变）
```
1. 对手方归一化 (COUNTERPARTY_NORMALIZE)
↓
2. 商户归一化 (MERCHANT_NORMALIZE)
↓
3. 分类映射 (CATEGORY_MAPPING)
↓
4. 账户映射 (ACCOUNT_MAPPING)
↓
5. 标签映射 (TAG_MAPPING)
↓
6. Firefly 字段映射 (FIREFLY_FIELD_MAPPING)
```
**设计原因**：先做归一再做分类，可提升规则命中率与稳定性。例如先将"美团外卖-北京"归一为"美团外卖"，再匹配分类规则"美团 → 餐饮美食"。
#### 执行原则
- 同一类型内按 `priority` 升序执行（数字越小优先级越高）
- **首条命中即停止**（同类型中第一个匹配的规则生效，后续不再匹配）
- 每条交易记录所有命中的规则 ID 和前后字段对比
#### 规则引擎核心实现
```go
type Engine struct {
ruleRepo repository.RuleRepo
hitRepo repository.RuleHitRepo
}
func (e *Engine) Apply(ctx context.Context, txns []*Transaction) error {
ruleGroups := e.loadRulesGroupByType(ctx)
executionOrder := []string{
"COUNTERPARTY_NORMALIZE",
"MERCHANT_NORMALIZE",
"CATEGORY_MAPPING",
"ACCOUNT_MAPPING",
"TAG_MAPPING",
"FIREFLY_FIELD_MAPPING",
}
for _, txn := range txns {
for _, ruleType := range executionOrder {
rules := ruleGroups[ruleType]
for _, rule := range rules {
if !rule.MatchPlatform(txn.SourcePlatform) { continue }
if rule.MatchConditions(txn) {
before := txn.Snapshot()
rule.ApplyActions(txn)
after := txn.Snapshot()
e.hitRepo.Save(ctx, &RuleHit{
TransactionID: txn.ID,
RuleID: rule.ID,
MatchedCondition: rule.ConditionsJSON,
BeforeValue: before,
AfterValue: after,
})
break // 同类型首条命中即停止
}
}
}
}
return nil
}
```
#### 可解释性设计 — RuleHit 审计
每条交易保留完整的规则命中记录：
| 信息项 | 说明 |
|--------|------|
| 命中规则 ID | 关联 rules 表 |
| 命中条件摘要 | 匹配的具体关键词/正则 |
| 变更前值 | 规则执行前的字段值 |
| 变更后值 | 规则执行后的字段值 |
| 命中时间 | 规则执行时间戳 |
用于前端"为何被分到餐饮/交通"的解释展示。

252
.agents/skills/developing-projectmoneyx/reference/05-database/db-schema.md Normal file
View File

@@ -0,0 +1,252 @@
## 数据库表结构设计
- **DDS-Section**: 10. 数据库详细设计（SQLite + GORM）
- **DDS-Lines**: L1135-L1347
### Extract
#### ER 关系总览
```
IMPORT_BATCHES ──1:N──> SOURCE_FILES ──1:N──> RAW_RECORDS
IMPORT_BATCHES ──1:N──> TRANSACTIONS
RAW_RECORDS ──1:1──> TRANSACTIONS (normalizes_to)
TRANSACTIONS ──1:N──> DEDUP_RELATIONS
TRANSACTIONS ──1:N──> LINK_RELATIONS
TRANSACTIONS ──1:N──> RULE_HITS
RULES ──1:N──> RULE_HITS
IMPORT_BATCHES ──1:N──> IMPORT_TASKS ──1:N──> IMPORT_RESULTS
TRANSACTIONS ──1:N──> AUDIT_LOGS
```
共 **11 张核心表**。
#### 表结构定义
##### 1. IMPORT_BATCHES — 导入批次
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| status | varchar(32) | | 批次状态 |
| total_files | int | | 文件总数 |
| total_records | int | | 记录总数 |
| success_count | int | | 成功数 |
| failed_count | int | | 失败数 |
| duplicate_count | int | | 重复数 |
| created_at | datetime | | 创建时间 |
| updated_at | datetime | | 更新时间 |
##### 2. SOURCE_FILES — 源文件
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| batch_id | varchar(36) | FK | 批次 ID |
| file_name | varchar(255) | | 原始文件名 |
| file_hash | varchar(64) | INDEX | 文件 SHA256 哈希 |
| source_platform | varchar(32) | | 来源平台 |
| file_type | varchar(16) | | csv/xlsx/txt |
| file_size | int | | 文件大小(bytes) |
| uploaded_at | datetime | | 上传时间 |
##### 3. RAW_RECORDS — 原始记录
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| source_file_id | varchar(36) | FK | 来源文件 ID |
| row_no | int | | 行号 |
| source_platform | varchar(32) | | 平台 |
| source_record_id | varchar(128) | | 原始流水号 |
| row_fingerprint | varchar(64) | INDEX | 行指纹 SHA256 |
| raw_payload | text | | 原始 JSON 快照 |
| parse_status | varchar(32) | | 解析状态 |
| parse_error | text | | 错误信息 |
##### 4. TRANSACTIONS — 统一交易记录（核心表）
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| transaction_id | varchar(64) | UNIQUE | 业务唯一 ID |
| batch_id | varchar(36) | INDEX | 导入批次 |
| raw_record_id | varchar(36) | | 原始记录 ID |
| source_platform | varchar(32) | INDEX(组合) | 来源平台 |
| source_record_id | varchar(128) | INDEX(组合) | 原始记录号 |
| trade_time | datetime | INDEX, NOT NULL | 交易时间 |
| amount | decimal(18,6) | NOT NULL | 金额 |
| currency | varchar(16) | DEFAULT 'CNY' | 币种 |
| direction | varchar(16) | NOT NULL | 方向 |
| counterparty | varchar(255) | | 对手方 |
| merchant_name | varchar(255) | | 商户名 |
| category_raw | varchar(128) | | 原始分类 |
| category_mapped | varchar(128) | | 映射分类 |
| account_mapped | varchar(128) | | 映射账户 |
| tags | varchar(512) | | 标签(逗号分隔) |
| order_id | varchar(128) | INDEX | 订单号 |
| parent_order_id | varchar(128) | | 父链路号 |
| payment_method | varchar(128) | | 支付方式 |
| note | text | | 备注 |
| raw_payload | text | | 原始记录 JSON |
| row_fingerprint | varchar(64) | INDEX | 行指纹 |
| status | varchar(32) | INDEX, DEFAULT 'PENDING_CLEAN' | 状态 |
| firefly_txn_id | varchar(128) | | Firefly 交易 ID |
| imported_at | datetime | | 导入时间 |
| created_at | datetime | | 创建时间 |
| updated_at | datetime | | 更新时间 |
##### 5. DEDUP_RELATIONS — 去重关系
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| src_transaction_id | varchar(36) | FK, INDEX | 原交易 ID |
| target_transaction_id | varchar(36) | FK | 目标交易 ID |
| relation_type | varchar(16) | | strict/fuzzy |
| confidence | int | | 置信度 0-100 |
| status | varchar(16) | | auto/confirmed/rejected |
| reason_json | text | | 判定依据 JSON |
| created_at | datetime | | 创建时间 |
##### 6. LINK_RELATIONS — 链路关系
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| parent_transaction_id | varchar(36) | FK | 主交易 ID |
| child_transaction_id | varchar(36) | FK | 子交易 ID |
| link_type | varchar(16) | | transfer/order/refund/fee |
| reason_json | text | | 关联依据 JSON |
| created_at | datetime | | 创建时间 |
##### 7. RULES — 规则定义
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| rule_type | varchar(32) | INDEX(组合) | 规则类型 |
| priority | int | INDEX(组合) | 优先级 |
| platform_scope | varchar(32) | | 平台范围 |
| conditions_json | text | | 条件 JSON |
| actions_json | text | | 动作 JSON |
| enabled | boolean | | 是否启用 |
| description | varchar(255) | | 规则描述 |
| created_at | datetime | | 创建时间 |
| updated_at | datetime | | 更新时间 |
##### 8. RULE_HITS — 规则命中记录
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| transaction_id | varchar(36) | FK | 交易 ID |
| rule_id | varchar(36) | FK | 规则 ID |
| matched_condition | text | | 命中条件摘要 |
| before_value | text | | 变更前值 |
| after_value | text | | 变更后值 |
| created_at | datetime | | 执行时间 |
##### 9. IMPORT_TASKS — 导入任务
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| batch_id | varchar(36) | FK | 批次 ID |
| export_mode | varchar(16) | | api/csv |
| status | varchar(32) | | pending/running/success/partial_failed/failed |
| total_count | int | | 总记录数 |
| success_count | int | | 成功数 |
| failed_count | int | | 失败数 |
| started_at | datetime | | 开始时间 |
| finished_at | datetime | | 完成时间 |
##### 10. IMPORT_RESULTS — 导入结果
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| task_id | varchar(36) | FK | 任务 ID |
| transaction_id | varchar(36) | FK | 交易 ID |
| status | varchar(16) | | success/failed |
| error_code | varchar(32) | | 错误码 |
| error_message | text | | 错误描述 |
| firefly_txn_id | varchar(128) | | Firefly 返回 ID |
| retry_count | int | | 重试次数 |
| created_at | datetime | | 创建时间 |
##### 11. AUDIT_LOGS — 审计日志
| 字段 | 类型 | 约束 | 说明 |
|------|------|------|------|
| id | varchar(36) | PK | UUID 主键 |
| entity_type | varchar(64) | | 实体类型 |
| entity_id | varchar(36) | | 实体 ID |
| action | varchar(32) | | 操作类型 |
| before_snapshot | text | | 变更前快照 |
| after_snapshot | text | | 变更后快照 |
| operator | varchar(64) | | 操作者 |
| created_at | datetime | | 操作时间 |
#### GORM Model 示例（Transaction）
```go
type Transaction struct {
ID string `gorm:"primaryKey;type:varchar(36)"`
TransactionID string `gorm:"uniqueIndex;type:varchar(64)"`
BatchID string `gorm:"index;type:varchar(36)"`
RawRecordID string `gorm:"type:varchar(36)"`
SourcePlatform string `gorm:"type:varchar(32);index:idx_platform_record"`
SourceRecordID string `gorm:"type:varchar(128);index:idx_platform_record"`
TradeTime time.Time `gorm:"index;not null"`
Amount decimal.Decimal `gorm:"type:decimal(18,6);not null"`
Currency string `gorm:"type:varchar(16);default:'CNY'"`
Direction string `gorm:"type:varchar(16);not null"`
Counterparty string `gorm:"type:varchar(255)"`
MerchantName string `gorm:"type:varchar(255)"`
CategoryRaw string `gorm:"type:varchar(128)"`
CategoryMapped string `gorm:"type:varchar(128)"`
AccountMapped string `gorm:"type:varchar(128)"`
Tags string `gorm:"type:varchar(512)"`
OrderID string `gorm:"index;type:varchar(128)"`
ParentOrderID string `gorm:"type:varchar(128)"`
PaymentMethod string `gorm:"type:varchar(128)"`
Note string `gorm:"type:text"`
RawPayload string `gorm:"type:text"`
RowFingerprint string `gorm:"index;type:varchar(64)"`
Status string `gorm:"index;type:varchar(32);default:'PENDING_CLEAN'"`
FireflyTxnID string `gorm:"type:varchar(128)"`
ImportedAt *time.Time
CreatedAt time.Time
UpdatedAt time.Time
}
func (Transaction) TableName() string { return "transactions" }
```
#### SQLite 性能配置
```go
func initDB(dbPath string) *gorm.DB {
db, _ := gorm.Open(sqlite.Open(dbPath), &gorm.Config{})
sqlDB, _ := db.DB()
sqlDB.SetMaxOpenConns(1) // SQLite 单写
sqlDB.SetMaxIdleConns(10)
db.Exec("PRAGMA journal_mode=WAL")
db.Exec("PRAGMA synchronous=NORMAL")
db.Exec("PRAGMA cache_size=-64000") // 64MB cache
return db
}
```
#### 事务边界设计
```
事务 1: 文件入库 + 原始记录入库
事务 2: 标准化结果落库
事务 3: 去重/链路关系落库
事务 4: 规则命中落库
事务 5: 导入结果落库
```
每阶段独立事务，使用 `CreateInBatches` 每批 500 条。

25
.agents/skills/developing-projectmoneyx/reference/05-database/indexes.md Normal file
View File

@@ -0,0 +1,25 @@
## 关键索引设计
- **DDS-Section**: 10.2 关键索引设计
- **DDS-Lines**: L1296-L1310
### Extract
| 表名 | 索引名 | 索引列 | 用途 |
|------|--------|--------|------|
| `transactions` | `idx_txn_platform_record` | `source_platform, source_record_id` | 严格去重判定键 1 |
| `transactions` | `idx_txn_fingerprint` | `row_fingerprint` | 严格去重判定键 2 |
| `transactions` | `idx_txn_batch` | `batch_id` | 批次查询 |
| `transactions` | `idx_txn_trade_time` | `trade_time` | 模糊去重时间分桶 |
| `transactions` | `idx_txn_order` | `order_id` | 订单号匹配 |
| `transactions` | `idx_txn_status` | `status` | 状态过滤 |
| `source_files` | `idx_sf_hash` | `file_hash` | 文件重复上传拦截 |
| `raw_records` | `idx_rr_fingerprint` | `row_fingerprint` | 行级去重 |
| `rules` | `idx_rule_type_priority` | `rule_type, priority` | 规则执行顺序 |
| `dedup_relations` | `idx_dedup_src` | `src_transaction_id` | 去重关系查询 |
#### 性能说明
- `idx_txn_platform_record` 是严格去重最频繁命中的索引，组合索引比两个单列索引效率更高
- `idx_txn_trade_time` 用于模糊去重的时间分桶，避免全表 O(N²) 扫描
- `idx_rule_type_priority` 确保规则按类型分组、按优先级有序加载

87
.agents/skills/developing-projectmoneyx/reference/06-api-design/api-catalog.md Normal file
View File

@@ -0,0 +1,87 @@
## API 接口目录
- **DDS-Section**: 11. API 接口设计（GIN RESTful）
- **DDS-Lines**: L1350-L1451
### Extract
#### 导入中心 API
| 方法 | 路径 | 说明 |
|------|------|------|
| `POST` | `/api/v1/import/batches` | 上传账单文件，创建批次（multipart/form-data） |
| `GET` | `/api/v1/import/batches` | 获取批次列表 |
| `GET` | `/api/v1/import/batches/:batchId` | 获取批次详情 |
| `POST` | `/api/v1/import/batches/:batchId/process` | 触发解析与清洗流水线 |
| `GET` | `/api/v1/import/batches/:batchId/preview` | 获取清洗预览结果 |
| `DELETE` | `/api/v1/import/batches/:batchId` | 删除批次 |
##### 上传文件接口详情
```
POST /api/v1/import/batches
Content-Type: multipart/form-data
参数:
- files[] (必填) 账单文件
- sourcePlatform (可选) 指定来源平台: "alipay", "wechat"
- autoDetect (可选) 是否自动识别, 默认 true
响应:
{
"code": 0,
"message": "ok",
"data": {
"batchId": "550e8400-e29b-41d4-a716-446655440000",
"status": "UPLOADED",
"filesCount": 2,
"detectedPlatforms": ["alipay", "wechat"]
}
}
```
#### 交易记录 API
| 方法 | 路径 | 说明 |
|------|------|------|
| `GET` | `/api/v1/transactions` | 分页查询交易记录 |
| `GET` | `/api/v1/transactions/:id` | 获取交易详情（含规则命中记录） |
| `GET` | `/api/v1/transactions/:id/trace` | 获取交易完整处理链路 |
#### 去重确认 API
| 方法 | 路径 | 说明 |
|------|------|------|
| `GET` | `/api/v1/dedup/reviews` | 获取疑似重复列表 |
| `GET` | `/api/v1/dedup/reviews/:reviewId` | 获取重复详情（含评分因子） |
| `POST` | `/api/v1/dedup/reviews/:reviewId/confirm` | 确认合并 |
| `POST` | `/api/v1/dedup/reviews/:reviewId/reject` | 拒绝合并 |
#### 规则管理 API
| 方法 | 路径 | 说明 |
|------|------|------|
| `GET` | `/api/v1/rules` | 获取规则列表（支持类型/平台过滤） |
| `POST` | `/api/v1/rules` | 创建规则 |
| `PUT` | `/api/v1/rules/:id` | 更新规则 |
| `DELETE` | `/api/v1/rules/:id` | 删除规则 |
| `POST` | `/api/v1/rules/evaluate` | 重新评估规则（修改规则后触发） |
| `POST` | `/api/v1/rules/:id/test` | 测试规则命中预览 |
#### 导入/导出 API
| 方法 | 路径 | 说明 |
|------|------|------|
| `POST` | `/api/v1/import/tasks` | 创建导入任务（确认导入到 Firefly） |
| `GET` | `/api/v1/import/tasks/:taskId` | 获取导入任务详情 |
| `POST` | `/api/v1/import/tasks/:taskId/retry` | 重试失败项 |
| `GET` | `/api/v1/export/csv/:batchId` | 导出批次为 CSV 文件 |
#### 审计与系统 API
| 方法 | 路径 | 说明 |
|------|------|------|
| `GET` | `/api/v1/audit/logs` | 获取操作日志列表 |
| `GET` | `/api/v1/settings` | 获取系统配置 |
| `PUT` | `/api/v1/settings` | 更新系统配置（Firefly 连接等） |
| `POST` | `/api/v1/settings/test-connection` | 测试 Firefly III 连接 |

57
.agents/skills/developing-projectmoneyx/reference/06-api-design/response-format.md Normal file
View File

@@ -0,0 +1,57 @@
## 统一响应格式与错误码
- **DDS-Section**: 11.1 统一响应格式 + 14.4 错误处理策略
- **DDS-Lines**: L1352-L1369, L1787-L1816
### Extract
#### 统一响应结构
```go
// 普通响应
type Response struct {
Code int `json:"code"` // 0=成功, 非0=错误码
Message string `json:"message"` // 成功/错误说明
Data interface{} `json:"data"` // 业务数据
}
// 分页响应
type PageResponse struct {
Code int `json:"code"`
Message string `json:"message"`
Data interface{} `json:"data"`
Total int64 `json:"total"`
Page int `json:"page"`
Size int `json:"size"`
}
```
#### 错误码定义
| 错误码 | 常量名 | 说明 |
|--------|--------|------|
| 0 | `ErrCodeSuccess` | 成功 |
| 40000 | `ErrCodeBadRequest` | 通用参数错误 |
| 40001 | `ErrCodeFileParseError` | 文件解析失败 |
| 40002 | `ErrCodeUnknownPlatform` | 未识别的平台来源 |
| 40003 | `ErrCodeDuplicateFile` | 重复上传文件 |
| 40004 | `ErrCodeRuleInvalid` | 规则定义无效 |
| 40005 | `ErrCodeExportFailed` | 导出/推送失败 |
| 50000 | `ErrCodeInternal` | 服务器内部错误 |
#### 全局错误处理中间件
```go
func ErrorHandler() gin.HandlerFunc {
return func(c *gin.Context) {
c.Next()
if len(c.Errors) > 0 {
err := c.Errors.Last()
c.JSON(http.StatusOK, Response{
Code: mapErrorCode(err),
Message: err.Error(),
})
}
}
}
```

65
.agents/skills/developing-projectmoneyx/reference/07-export-engine/firefly-mapping.md Normal file
View File

@@ -0,0 +1,65 @@
## Firefly III 导出适配
- **DDS-Section**: 9. Firefly III / Data Importer 适配设计
- **DDS-Lines**: L1048-L1132
### Extract
#### 两段式规则映射策略
**第一阶段 — ProjectMoneyX 负责**：
1. 字段级映射：异构字段 → 统一模型
2. 业务分类映射：对手方/描述 → 分类/标签
3. 商户名归一化：别名 → 统一名称
**第二阶段 — Firefly III 负责**：
1. 最后一层字段适配
2. 临时补充规则
3. 导入格式兼容
#### 导出模式
##### 模式 A：API 推送模式（优先）
```
Export Engine → Data Importer (POST /api/v1/import) → Firefly III
↓
返回成功/失败明细 → 更新 import_results 表
```
##### 模式 B：中间文件导出模式
- 生成完全符合 Data Importer 规范的标准 CSV / JSON
- 用户手动下载后在 Data Importer 中执行导入
- 适合 API 不可用或权限受限场景
#### Firefly 交易类型映射
| 内部 Direction | Firefly Type | 说明 |
|----------------|--------------|------|
| `expense` | `withdrawal` | 支出 |
| `income` | `deposit` | 收入 |
| `transfer` | `transfer` | 内部转账 |
| `refund` | `deposit` | 退款（作为收入处理） |
| `fee` | `withdrawal` | 手续费（作为支出处理） |
#### ImportResult 数据结构
```go
type ImportResult struct {
TaskID string
TransactionID string
Status string // success / failed
ErrorCode string
ErrorMessage string
FireflyTxnID string // Firefly III 返回的交易 ID
RetryCount int
CreatedAt time.Time
}
```
#### 导入后反馈
- 导入成功/失败数量统计
- 失败原因分类展示（字段缺失、格式错误、账户不存在等）
- 失败记录可单独重试（无需整批重做）

24
.agents/skills/developing-projectmoneyx/reference/07-export-engine/import-validation.md Normal file
View File

@@ -0,0 +1,24 @@
## 导入前校验清单
- **DDS-Section**: 9.4 导入前校验清单
- **DDS-Lines**: L1103-L1112
### Extract
#### 6 项必须校验
| # | 校验项 | 说明 | 失败处理 |
|---|--------|------|----------|
| 1 | 必填字段完整性 | `amount`, `trade_time`, `direction` 不可为空 | 标记为 FAILED，记录具体缺失字段 |
| 2 | 金额格式合法性 | 必须为正数，精度不超过 6 位小数 | 标记为 FAILED |
| 3 | 时间格式合法性 | 必须为有效日期时间 | 标记为 FAILED |
| 4 | 账户映射完整性 | 来源平台必须有对应的 Firefly 账户映射 | 标记为 FAILED，提示配置账户映射 |
| 5 | 重复导入拦截 | 检查 `transaction_id` 是否已在 Firefly III 中存在 | 跳过并标记 |
| 6 | 未确认记录检查 | 是否存在 `PENDING_REVIEW` 状态的疑似重复记录 | 阻断导入，提示先处理待确认记录 |
#### 校验实现要点
- 校验在 Export Engine 的 `validate()` 方法中统一执行
- 校验失败的记录不参与推送，但不影响其他记录
- 校验结果写入 `import_results` 表，前端可展示失败原因
- 第 6 项（未确认记录）为全局阻断性校验，有未确认记录时整批不可导入

82
.agents/skills/developing-projectmoneyx/reference/08-frontend/components.md Normal file
View File

@@ -0,0 +1,82 @@
## 前端核心组件与交互
- **DDS-Section**: 12.2 页面职责与交互说明
- **DDS-Lines**: L1489-L1572
### Extract
#### 核心可复用组件
| 组件 | 文件 | 用途 |
|------|------|------|
| 文件上传器 | `FileUploader.vue` | 拖拽 + 点击上传，进度条，平台自动检测 |
| 交易表格 | `TransactionTable.vue` | `v-data-table` + 行展开 + 批量操作 |
| 规则编辑器 | `RuleEditor.vue` | 条件构建器 + 动作配置 + 测试预览 |
| 去重对比 | `DedupCompare.vue` | 左右分栏对比 + 评分因子 + 差异高亮 |
| 审计时间线 | `AuditTimeline.vue` | `v-timeline` + 快照展开 |
#### 1. FileUploader.vue
- 使用 Vuetify `v-file-input` + 自定义拖拽区域
- 文件选择后立即调用 `POST /api/v1/import/batches`
- 上传进度条实时展示
- 自动检测文件来源平台，允许手动修改
- 批量文件列表显示文件名、大小、检测到的平台
#### 2. TransactionTable.vue
- 使用 Vuetify `v-data-table` 实现分页排序
- 行展开（`expanded`）显示详情面板：原始字段 vs 标准字段对比
- 规则命中说明显示该条交易命中的具体规则
- 状态标记：以颜色标签区分 待清洗/已清洗/重复/待确认
- 筛选器：支持按来源平台、分类、方向、状态过滤
- 必须 `fixed-header` + 列宽显式指定
#### 3. DedupCompare.vue
- 左右分栏对比布局
- 差异字段高亮显示
- 评分因子可展开查看（6 项因子各自得分）
- 操作按钮：确认合并 / 拒绝合并 / 暂时跳过
- 链路视图展示已识别的转账闭环和订单链路
#### 4. RuleEditor.vue
- 条件构建器：支持多条件 AND/OR 组合
- 使用 Vuetify `v-select`、`v-text-field`、`v-chip` 构建
- 按类型分组展示规则列表，支持拖拽排序优先级
- 测试按钮触发 `POST /api/v1/rules/:id/test`
- 启用/禁用一键切换
#### 5. AuditTimeline.vue
- 使用 Vuetify `v-timeline` 组件
- 每个节点可展开查看详细快照数据
- 处理链路：原始文件 → 原始记录 → 标准化 → 规则命中 → 导入结果
#### Pinia Store 清单
| Store | 文件 | 管理的状态 |
|-------|------|-----------|
| Import Store | `importStore.ts` | 批次列表、上传状态、处理进度 |
| Transaction Store | `transactionStore.ts` | 交易记录分页、筛选条件、详情 |
| Rule Store | `ruleStore.ts` | 规则列表、编辑表单、测试结果 |
#### API 模块清单
| 模块 | 文件 | 封装的 API 组 |
|------|------|-------------|
| Import API | `api/import.ts` | 批次上传、列表、详情、处理 |
| Transaction API | `api/transaction.ts` | 交易查询、详情、链路 |
| Dedup API | `api/dedup.ts` | 去重列表、确认、拒绝 |
| Rule API | `api/rule.ts` | 规则 CRUD、测试、评估 |
| Export API | `api/export.ts` | 导入任务、重试、CSV 导出 |
| Audit API | `api/audit.ts` | 审计日志查询 |
#### TypeScript 类型清单
| 文件 | 定义的类型 |
|------|-----------|
| `types/transaction.ts` | Transaction, Direction, TransactionStatus, RawRecord |
| `types/rule.ts` | Rule, RuleType, RuleCondition, RuleHit |
| `types/common.ts` | Response, PageResponse, ImportBatch, SourceFile, ImportTask |

95
.agents/skills/developing-projectmoneyx/reference/08-frontend/routes.md Normal file
View File

@@ -0,0 +1,95 @@
## 前端路由与页面
- **DDS-Section**: 12.3 前端路由设计 + 12.1 信息架构与导航
- **DDS-Lines**: L1454-L1628
### Extract
#### 信息架构
```
侧边导航栏 → 导入中心
→ 数据清洗
→ 去重处理
→ 规则管理
→ 导入任务
→ 数据审计
→ 系统设置
导入中心 → 文件上传页 / 批次列表页 / 批次详情页
数据清洗 → 清洗结果预览页
去重处理 → 重复记录处理页
规则管理 → 规则列表页 / 规则编辑页
导入任务 → 导入任务列表页 / 导入结果详情页
数据审计 → 审计追溯页 / 交易处理链路页
系统设置 → Firefly 连接配置 / 去重参数配置
```
#### 路由定义
```typescript
const routes = [
{ path: '/', redirect: '/import' },
{
path: '/import',
name: 'ImportCenter',
component: () => import('@/views/ImportCenterView.vue'),
meta: { title: '导入中心', icon: 'mdi-upload' }
},
{
path: '/import/batch/:batchId',
name: 'BatchDetail',
component: () => import('@/views/BatchDetailView.vue'),
meta: { title: '批次详情' }
},
{
path: '/preview/:batchId',
name: 'Preview',
component: () => import('@/views/PreviewView.vue'),
meta: { title: '清洗预览' }
},
{
path: '/dedup',
name: 'DedupReview',
component: () => import('@/views/DedupReviewView.vue'),
meta: { title: '去重处理', icon: 'mdi-content-duplicate' }
},
{
path: '/rules',
name: 'RuleConfig',
component: () => import('@/views/RuleConfigView.vue'),
meta: { title: '规则管理', icon: 'mdi-cog-outline' }
},
{
path: '/tasks',
name: 'ImportTask',
component: () => import('@/views/ImportTaskView.vue'),
meta: { title: '导入任务', icon: 'mdi-export' }
},
{
path: '/audit',
name: 'AuditTrace',
component: () => import('@/views/AuditTraceView.vue'),
meta: { title: '数据审计', icon: 'mdi-history' }
},
{
path: '/settings',
name: 'Settings',
component: () => import('@/views/SettingsView.vue'),
meta: { title: '系统设置', icon: 'mdi-tune' }
}
]
```
#### 页面文件清单
| 页面 | 文件 | 用途 |
|------|------|------|
| 导入中心 | `ImportCenterView.vue` | 文件上传 + 批次列表 |
| 批次详情 | `BatchDetailView.vue` | 单批次详情 |
| 清洗预览 | `PreviewView.vue` | 标准化结果预览 |
| 去重处理 | `DedupReviewView.vue` | 疑似重复确认 |
| 规则配置 | `RuleConfigView.vue` | 规则 CRUD |
| 导入任务 | `ImportTaskView.vue` | 导入结果展示 |
| 审计追溯 | `AuditTraceView.vue` | 全链路追溯 |
| 系统设置 | `SettingsView.vue` | Firefly 配置 |

86
.agents/skills/developing-projectmoneyx/reference/09-nonfunctional/deployment.md Normal file
View File

@@ -0,0 +1,86 @@
## 部署与安全设计
- **DDS-Section**: 13.2 安全设计 + 13.5 部署架构
- **DDS-Lines**: L1663-L1732
### Extract
#### 安全措施
| 安全措施 | 说明 |
|----------|------|
| 本地部署 | 默认本地运行，敏感账单数据不上传云端 |
| API Token 加密 | Firefly III API Token 使用 AES 加密存储 |
| 审计日志脱敏 | 日志中账号、订单号局部遮罩（如 `138****1234`） |
| 文件安全 | 上传文件限制类型和大小（默认最大 50MB） |
| CORS 配置 | 仅允许本地来源访问 API |
#### 部署架构
```
Docker 容器 / 本地部署
├── 前端静态资源 (Vue3 Build → /web)
├── 后端服务 (Go Binary :8080)
└── SQLite 数据库 (/data/projectmoneyx.db)
外部依赖（可选）
├── Firefly III (API 推送)
└── Data Importer (API 推送)
```
#### 部署方式
1. **Docker 部署**（推荐）：单容器包含前后端 + SQLite
2. **二进制部署**：交叉编译为单体可执行文件，前端资源使用 Go `embed` 嵌入
#### Dockerfile 示例
```dockerfile
FROM golang:1.21-alpine AS builder
WORKDIR /app
COPY . .
RUN go build -o projectmoneyx ./cmd/server
FROM alpine:latest
WORKDIR /app
COPY --from=builder /app/projectmoneyx .
COPY --from=builder /app/web ./web
VOLUME /data
EXPOSE 8080
CMD ["./projectmoneyx", "--db", "/data/projectmoneyx.db"]
```
#### 配置管理
```go
type Config struct {
Server ServerConfig `yaml:"server"`
Database DatabaseConfig `yaml:"database"`
Firefly FireflyConfig `yaml:"firefly"`
Dedup DedupConfig `yaml:"dedup"`
}
type ServerConfig struct {
Port int `yaml:"port" default:"8080"`
Mode string `yaml:"mode" default:"release"`
}
type DatabaseConfig struct {
Path string `yaml:"path" default:"./data/projectmoneyx.db"`
}
type FireflyConfig struct {
BaseURL string `yaml:"base_url"`
APIToken string `yaml:"api_token"` // AES 加密存储
ImporterURL string `yaml:"importer_url"`
Enabled bool `yaml:"enabled"`
}
type DedupConfig struct {
FuzzyTimeWindow int `yaml:"fuzzy_time_window" default:"5"`
FuzzyThresholdHigh int `yaml:"fuzzy_threshold_high" default:"85"`
FuzzyThresholdLow int `yaml:"fuzzy_threshold_low" default:"60"`
TransferTimeWindow int `yaml:"transfer_time_window" default:"30"`
AmountEpsilon float64 `yaml:"amount_epsilon" default:"0.01"`
}
```

55
.agents/skills/developing-projectmoneyx/reference/09-nonfunctional/performance.md Normal file
View File

@@ -0,0 +1,55 @@
## 性能设计
- **DDS-Section**: 13.1 性能设计 + 13.3 可维护性设计
- **DDS-Lines**: L1632-L1681
### Extract
#### 性能目标
单次导入 1 万条记录在主流程内完成解析与清洗，去重计算应在 30 秒内完成。
#### 优化策略
| 策略 | 说明 |
|------|------|
| 批量插入 | `raw_records` 和 `transactions` 使用 GORM `CreateInBatches`，每批 500 条 |
| 关键索引 | `source_platform + source_record_id`、`batch_id`、`trade_time`、`order_id` |
| 模糊去重分桶 | 按 `trade_time` 时间分桶，避免全表扫描 |
| 规则预筛选 | 按平台和启用状态预加载规则，减少无效匹配 |
| 异步处理 | ETL Pipeline 使用 goroutine 异步执行，前端轮询状态 |
| 连接池 | SQLite 使用 WAL 模式提升并发读写性能 |
#### SQLite 性能配置
```go
func initDB(dbPath string) *gorm.DB {
db, _ := gorm.Open(sqlite.Open(dbPath), &gorm.Config{})
sqlDB, _ := db.DB()
sqlDB.SetMaxOpenConns(1) // SQLite 单写
sqlDB.SetMaxIdleConns(10)
db.Exec("PRAGMA journal_mode=WAL")
db.Exec("PRAGMA synchronous=NORMAL")
db.Exec("PRAGMA cache_size=-64000") // 64MB cache
return db
}
```
#### 可维护性设计
| 原则 | 说明 |
|------|------|
| 解析器插件化 | 新增平台只需实现 `BillParser` 接口并注册 |
| 规则条件 JSON 化 | 规则存储为 JSON，灵活扩展匹配条件 |
| 导入器解耦 | Export 层独立，可替换下游目标 |
| 分层 DTO/VO/Entity | Handler → DTO → Service → Entity → DAO |
| 事务分阶段 | 每个 ETL 阶段独立事务，避免超长事务 |
#### 可追溯性设计
| 追溯能力 | 实现方式 |
|----------|----------|
| 任一导入结果 → 原始文件 | `transaction.raw_record_id → raw_record.source_file_id → source_file` |
| 任一规则命中 → 解释说明 | `rule_hits` 表记录命中条件和前后字段值对比 |
| 任一合并操作 → 判定依据 | `dedup_relations.reason_json` 和 `link_relations.reason_json` |
| 任一操作 → 操作日志 | `audit_logs` 表记录实体变更和操作者信息 |

101
.agents/skills/developing-projectmoneyx/scripts/verify.sh Normal file
View File

@@ -0,0 +1,101 @@
#!/bin/bash
# verify.sh - developing-projectmoneyx Skill 结构与内容验证
set -e
PASS=0; FAIL=0
check() {
if eval "$2"; then
echo "✅ PASS: $1"; ((PASS++))
else
echo "❌ FAIL: $1"; ((FAIL++))
fi
}
SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"
# ========================
# 结构完整性检查
# ========================
check "SKILL.md 存在" "test -f '$SKILL_DIR/SKILL.md'"
check "reference/ 目录存在" "test -d '$SKILL_DIR/reference'"
check "scripts/ 目录存在" "test -d '$SKILL_DIR/scripts'"
check "SKILL.md < 500 行" "[ $(wc -l < '$SKILL_DIR/SKILL.md') -lt 500 ]"
# ========================
# Frontmatter 检查
# ========================
check "frontmatter 包含 name" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^name:'"
check "frontmatter 包含 description" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^description:'"
check "frontmatter 包含 argument-hint" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^argument-hint:'"
check "frontmatter 包含 allowed-tools" "head -20 '$SKILL_DIR/SKILL.md' | grep -q '^allowed-tools:'"
# ========================
# 章节检查
# ========================
check "包含 Quick Context 章节" "grep -q '## Quick Context' '$SKILL_DIR/SKILL.md'"
check "包含 Plan 章节" "grep -q '## Plan' '$SKILL_DIR/SKILL.md'"
check "包含 Verify 章节" "grep -q '## Verify' '$SKILL_DIR/SKILL.md'"
check "包含 Execute 章节" "grep -q '## Execute' '$SKILL_DIR/SKILL.md'"
check "包含 Pitfalls 章节" "grep -q '## Pitfalls' '$SKILL_DIR/SKILL.md'"
check "包含 Related References 章节" "grep -q '## Related References' '$SKILL_DIR/SKILL.md'"
# ========================
# 动态注入检查
# ========================
check "包含至少 2 处动态注入命令" "[ $(grep -c '!\`' '$SKILL_DIR/SKILL.md') -ge 2 ]"
# ========================
# Pitfalls 引用 reference 检查
# ========================
check "Pitfalls 引用 reference/ 至少 2 处" "[ $(grep -A 100 '## Pitfalls' '$SKILL_DIR/SKILL.md' | grep -c 'reference/') -ge 2 ]"
# ========================
# reference 目录结构检查
# ========================
check "reference 有 01-architecture 子目录" "test -d '$SKILL_DIR/reference/01-architecture'"
check "reference 有 02-parser-engine 子目录" "test -d '$SKILL_DIR/reference/02-parser-engine'"
check "reference 有 03-dedup-engine 子目录" "test -d '$SKILL_DIR/reference/03-dedup-engine'"
check "reference 有 04-rule-engine 子目录" "test -d '$SKILL_DIR/reference/04-rule-engine'"
check "reference 有 05-database 子目录" "test -d '$SKILL_DIR/reference/05-database'"
check "reference 有 06-api-design 子目录" "test -d '$SKILL_DIR/reference/06-api-design'"
check "reference 有 07-export-engine 子目录" "test -d '$SKILL_DIR/reference/07-export-engine'"
check "reference 有 08-frontend 子目录" "test -d '$SKILL_DIR/reference/08-frontend'"
check "reference 有 09-nonfunctional 子目录" "test -d '$SKILL_DIR/reference/09-nonfunctional'"
# ========================
# reference 内容检查
# ========================
check "reference 文件含 DDS-Section 溯源" "grep -rq 'DDS-Section:' '$SKILL_DIR/reference/' 2>/dev/null"
check "reference 文件含 DDS-Lines 溯源" "grep -rq 'DDS-Lines:' '$SKILL_DIR/reference/' 2>/dev/null"
# ========================
# 关键 reference 文件存在检查
# ========================
check "system-overview.md 存在" "test -f '$SKILL_DIR/reference/01-architecture/system-overview.md'"
check "batch-state-machine.md 存在" "test -f '$SKILL_DIR/reference/01-architecture/batch-state-machine.md'"
check "parser-interface.md 存在" "test -f '$SKILL_DIR/reference/02-parser-engine/parser-interface.md'"
check "field-mappings.md 存在" "test -f '$SKILL_DIR/reference/02-parser-engine/field-mappings.md'"
check "strict-dedup.md 存在" "test -f '$SKILL_DIR/reference/03-dedup-engine/strict-dedup.md'"
check "fuzzy-dedup.md 存在" "test -f '$SKILL_DIR/reference/03-dedup-engine/fuzzy-dedup.md'"
check "transfer-link.md 存在" "test -f '$SKILL_DIR/reference/03-dedup-engine/transfer-link.md'"
check "fingerprint.md 存在" "test -f '$SKILL_DIR/reference/03-dedup-engine/fingerprint.md'"
check "rule-conditions.md 存在" "test -f '$SKILL_DIR/reference/04-rule-engine/rule-conditions.md'"
check "rule-execution.md 存在" "test -f '$SKILL_DIR/reference/04-rule-engine/rule-execution.md'"
check "db-schema.md 存在" "test -f '$SKILL_DIR/reference/05-database/db-schema.md'"
check "indexes.md 存在" "test -f '$SKILL_DIR/reference/05-database/indexes.md'"
check "api-catalog.md 存在" "test -f '$SKILL_DIR/reference/06-api-design/api-catalog.md'"
check "response-format.md 存在" "test -f '$SKILL_DIR/reference/06-api-design/response-format.md'"
check "firefly-mapping.md 存在" "test -f '$SKILL_DIR/reference/07-export-engine/firefly-mapping.md'"
check "import-validation.md 存在" "test -f '$SKILL_DIR/reference/07-export-engine/import-validation.md'"
echo ""
echo "=== 结果: $PASS PASS / $FAIL FAIL ==="
[ $FAIL -eq 0 ] && exit 0 || exit 1

2
1-AgentSkills/coding-vue3-vuetify/SKILL.md → .agents/skills/frontend-vue3-vuetify/SKILL.md
View File

@@ -1,5 +1,5 @@
---
name: coding-vue3-vuetify
name: frontend-vue3-vuetify
description: Build production-grade Vue 3 + TypeScript + Vuetify 3 interfaces with architectural rigor. 构建生产级 Vue 3 + TypeScript + Vuetify 3 界面。Use when creating Vue components, pages, layouts, Pinia stores, or API modules. 用于创建 Vue 组件、页面、布局、Pinia 状态管理或 API 模块。Enforces strict typing, Composition API patterns, Material Design 3 aesthetics, and bulletproof data handling.
---

0
1-AgentSkills/coding-vue3-vuetify/examples/api-module.ts → .agents/skills/frontend-vue3-vuetify/examples/api-module.ts
View File

0
1-AgentSkills/coding-vue3-vuetify/examples/data-table-page.vue → .agents/skills/frontend-vue3-vuetify/examples/data-table-page.vue
View File

0
1-AgentSkills/coding-vue3-vuetify/examples/page-layout.vue → .agents/skills/frontend-vue3-vuetify/examples/page-layout.vue
View File

0
1-AgentSkills/coding-vue3-vuetify/reference/api-patterns.md → .agents/skills/frontend-vue3-vuetify/reference/api-patterns.md
View File

0
1-AgentSkills/coding-vue3-vuetify/reference/layout-patterns.md → .agents/skills/frontend-vue3-vuetify/reference/layout-patterns.md
View File

0
1-AgentSkills/coding-vue3-vuetify/reference/typescript-rules.md → .agents/skills/frontend-vue3-vuetify/reference/typescript-rules.md
View File

0
1-AgentSkills/coding-vue3-vuetify/reference/ui-interaction.md → .agents/skills/frontend-vue3-vuetify/reference/ui-interaction.md
View File

202
.agents/skills/skill-creator/LICENSE.txt Normal file
View File

@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

479
.agents/skills/skill-creator/SKILL.md Normal file
View File

@@ -0,0 +1,479 @@
---
name: skill-creator
description: Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
---
# Skill Creator
A skill for creating new skills and iteratively improving them.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run claude-with-access-to-the-skill on them
- Help the user evaluate the results both qualitatively and quantitatively
- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
- Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics
- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
- Repeat until you're satisfied
- Expand the test set and try again at larger scale
Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.
On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.
Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.
Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.
Cool? Cool.
## Communicating with the user
The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:
- "evaluation" and "benchmark" are borderline, but OK
- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them
It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.
---
## Creating a skill
### Capture Intent
Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step.
1. What should this skill enable Claude to do?
2. When should this skill trigger? (what user phrases/contexts)
3. What's the expected output format?
4. Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide.
### Interview and Research
Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies. Wait to write test prompts until you've got this part ironed out.
Check available MCPs - if useful for research (searching docs, finding similar skills, looking up best practices), research in parallel via subagents if available, otherwise inline. Come prepared with context to reduce burden on the user.
### Write the SKILL.md
Based on the user interview, fill in these components:
- **name**: Skill identifier
- **description**: When to trigger, what it does. This is the primary triggering mechanism - include both what the skill does AND specific contexts for when to use it. All "when to use" info goes here, not in the body. Note: currently Claude has a tendency to "undertrigger" skills -- to not use them when they'd be useful. To combat this, please make the skill descriptions a little bit "pushy". So for instance, instead of "How to build a simple fast dashboard to display internal Anthropic data.", you might write "How to build a simple fast dashboard to display internal Anthropic data. Make sure to use this skill whenever the user mentions dashboards, data visualization, internal metrics, or wants to display any kind of company data, even if they don't explicitly ask for a 'dashboard.'"
- **compatibility**: Required tools, dependencies (optional, rarely needed)
- **the rest of the skill :)**
### Skill Writing Guide
#### Anatomy of a Skill
```
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter (name, description required)
│ └── Markdown instructions
└── Bundled Resources (optional)
├── scripts/ - Executable code for deterministic/repetitive tasks
├── references/ - Docs loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts)
```
#### Progressive Disclosure
Skills use a three-level loading system:
1. **Metadata** (name + description) - Always in context (~100 words)
2. **SKILL.md body** - In context whenever skill triggers (<500 lines ideal)
3. **Bundled resources** - As needed (unlimited, scripts can execute without loading)
These word counts are approximate and you can feel free to go longer if needed.
**Key patterns:**
- Keep SKILL.md under 500 lines; if you're approaching this limit, add an additional layer of hierarchy along with clear pointers about where the model using the skill should go next to follow up.
- Reference files clearly from SKILL.md with guidance on when to read them
- For large reference files (>300 lines), include a table of contents
**Domain organization**: When a skill supports multiple domains/frameworks, organize by variant:
```
cloud-deploy/
├── SKILL.md (workflow + selection)
└── references/
├── aws.md
├── gcp.md
└── azure.md
```
Claude reads only the relevant reference file.
#### Principle of Lack of Surprise
This goes without saying, but skills must not contain malware, exploit code, or any content that could compromise system security. A skill's contents should not surprise the user in their intent if described. Don't go along with requests to create misleading skills or skills designed to facilitate unauthorized access, data exfiltration, or other malicious activities. Things like a "roleplay as an XYZ" are OK though.
#### Writing Patterns
Prefer using the imperative form in instructions.
**Defining output formats** - You can do it like this:
```markdown
## Report structure
ALWAYS use this exact template:
# [Title]
## Executive summary
## Key findings
## Recommendations
```
**Examples pattern** - It's useful to include examples. You can format them like this (but if "Input" and "Output" are in the examples you might want to deviate a little):
```markdown
## Commit message format
**Example 1:**
Input: Added user authentication with JWT tokens
Output: feat(auth): implement JWT-based authentication
```
### Writing Style
Try to explain to the model why things are important in lieu of heavy-handed musty MUSTs. Use theory of mind and try to make the skill general and not super-narrow to specific examples. Start by writing a draft and then look at it with fresh eyes and improve it.
### Test Cases
After writing the skill draft, come up with 2-3 realistic test prompts — the kind of thing a real user would actually say. Share them with the user: [you don't have to use this exact language] "Here are a few test cases I'd like to try. Do these look right, or do you want to add more?" Then run them.
Save test cases to `evals/evals.json`. Don't write assertions yet — just the prompts. You'll draft assertions in the next step while the runs are in progress.
```json
{
"skill_name": "example-skill",
"evals": [
{
"id": 1,
"prompt": "User's task prompt",
"expected_output": "Description of expected result",
"files": []
}
]
}
```
See `references/schemas.md` for the full schema (including the `assertions` field, which you'll add later).
## Running and evaluating test cases
This section is one continuous sequence — don't stop partway through. Do NOT use `/skill-test` or any other testing skill.
Put results in `<skill-name>-workspace/` as a sibling to the skill directory. Within the workspace, organize results by iteration (`iteration-1/`, `iteration-2/`, etc.) and within that, each test case gets a directory (`eval-0/`, `eval-1/`, etc.). Don't create all of this upfront — just create directories as you go.
### Step 1: Spawn all runs (with-skill AND baseline) in the same turn
For each test case, spawn two subagents in the same turn — one with the skill, one without. This is important: don't spawn the with-skill runs first and then come back for baselines later. Launch everything at once so it all finishes around the same time.
**With-skill run:**
```
Execute this task:
- Skill path: <path-to-skill>
- Task: <eval prompt>
- Input files: <eval files if any, or "none">
- Save outputs to: <workspace>/iteration-<N>/eval-<ID>/with_skill/outputs/
- Outputs to save: <what the user cares about — e.g., "the .docx file", "the final CSV">
```
**Baseline run** (same prompt, but the baseline depends on context):
- **Creating a new skill**: no skill at all. Same prompt, no skill path, save to `without_skill/outputs/`.
- **Improving an existing skill**: the old version. Before editing, snapshot the skill (`cp -r <skill-path> <workspace>/skill-snapshot/`), then point the baseline subagent at the snapshot. Save to `old_skill/outputs/`.
Write an `eval_metadata.json` for each test case (assertions can be empty for now). Give each eval a descriptive name based on what it's testing — not just "eval-0". Use this name for the directory too. If this iteration uses new or modified eval prompts, create these files for each new eval directory — don't assume they carry over from previous iterations.
```json
{
"eval_id": 0,
"eval_name": "descriptive-name-here",
"prompt": "The user's task prompt",
"assertions": []
}
```
### Step 2: While runs are in progress, draft assertions
Don't just wait for the runs to finish — you can use this time productively. Draft quantitative assertions for each test case and explain them to the user. If assertions already exist in `evals/evals.json`, review them and explain what they check.
Good assertions are objectively verifiable and have descriptive names — they should read clearly in the benchmark viewer so someone glancing at the results immediately understands what each one checks. Subjective skills (writing style, design quality) are better evaluated qualitatively — don't force assertions onto things that need human judgment.
Update the `eval_metadata.json` files and `evals/evals.json` with the assertions once drafted. Also explain to the user what they'll see in the viewer — both the qualitative outputs and the quantitative benchmark.
### Step 3: As runs complete, capture timing data
When each subagent task completes, you receive a notification containing `total_tokens` and `duration_ms`. Save this data immediately to `timing.json` in the run directory:
```json
{
"total_tokens": 84852,
"duration_ms": 23332,
"total_duration_seconds": 23.3
}
```
This is the only opportunity to capture this data — it comes through the task notification and isn't persisted elsewhere. Process each notification as it arrives rather than trying to batch them.
### Step 4: Grade, aggregate, and launch the viewer
Once all runs are done:
1. **Grade each run** — spawn a grader subagent (or grade inline) that reads `agents/grader.md` and evaluates each assertion against the outputs. Save results to `grading.json` in each run directory. The grading.json expectations array must use the fields `text`, `passed`, and `evidence` (not `name`/`met`/`details` or other variants) — the viewer depends on these exact field names. For assertions that can be checked programmatically, write and run a script rather than eyeballing it — scripts are faster, more reliable, and can be reused across iterations.
2. **Aggregate into benchmark** — run the aggregation script from the skill-creator directory:
```bash
python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name <name>
```
This produces `benchmark.json` and `benchmark.md` with pass_rate, time, and tokens for each configuration, with mean ± stddev and the delta. If generating benchmark.json manually, see `references/schemas.md` for the exact schema the viewer expects.
Put each with_skill version before its baseline counterpart.
3. **Do an analyst pass** — read the benchmark data and surface patterns the aggregate stats might hide. See `agents/analyzer.md` (the "Analyzing Benchmark Results" section) for what to look for — things like assertions that always pass regardless of skill (non-discriminating), high-variance evals (possibly flaky), and time/token tradeoffs.
4. **Launch the viewer** with both qualitative outputs and quantitative data:
```bash
nohup python <skill-creator-path>/eval-viewer/generate_review.py \
<workspace>/iteration-N \
--skill-name "my-skill" \
--benchmark <workspace>/iteration-N/benchmark.json \
> /dev/null 2>&1 &
VIEWER_PID=$!
```
For iteration 2+, also pass `--previous-workspace <workspace>/iteration-<N-1>`.
**Cowork / headless environments:** If `webbrowser.open()` is not available or the environment has no display, use `--static <output_path>` to write a standalone HTML file instead of starting a server. Feedback will be downloaded as a `feedback.json` file when the user clicks "Submit All Reviews". After download, copy `feedback.json` into the workspace directory for the next iteration to pick up.
Note: please use generate_review.py to create the viewer; there's no need to write custom HTML.
5. **Tell the user** something like: "I've opened the results in your browser. There are two tabs — 'Outputs' lets you click through each test case and leave feedback, 'Benchmark' shows the quantitative comparison. When you're done, come back here and let me know."
### What the user sees in the viewer
The "Outputs" tab shows one test case at a time:
- **Prompt**: the task that was given
- **Output**: the files the skill produced, rendered inline where possible
- **Previous Output** (iteration 2+): collapsed section showing last iteration's output
- **Formal Grades** (if grading was run): collapsed section showing assertion pass/fail
- **Feedback**: a textbox that auto-saves as they type
- **Previous Feedback** (iteration 2+): their comments from last time, shown below the textbox
The "Benchmark" tab shows the stats summary: pass rates, timing, and token usage for each configuration, with per-eval breakdowns and analyst observations.
Navigation is via prev/next buttons or arrow keys. When done, they click "Submit All Reviews" which saves all feedback to `feedback.json`.
### Step 5: Read the feedback
When the user tells you they're done, read `feedback.json`:
```json
{
"reviews": [
{"run_id": "eval-0-with_skill", "feedback": "the chart is missing axis labels", "timestamp": "..."},
{"run_id": "eval-1-with_skill", "feedback": "", "timestamp": "..."},
{"run_id": "eval-2-with_skill", "feedback": "perfect, love this", "timestamp": "..."}
],
"status": "complete"
}
```
Empty feedback means the user thought it was fine. Focus your improvements on the test cases where the user had specific complaints.
Kill the viewer server when you're done with it:
```bash
kill $VIEWER_PID 2>/dev/null
```
---
## Improving the skill
This is the heart of the loop. You've run the test cases, the user has reviewed the results, and now you need to make the skill better based on their feedback.
### How to think about improvements
1. **Generalize from the feedback.** The big picture thing that's happening here is that we're trying to create skills that can be used a million times (maybe literally, maybe even more who knows) across many different prompts. Here you and the user are iterating on only a few examples over and over again because it helps move faster. The user knows these examples in and out and it's quick for them to assess new outputs. But if the skill you and the user are codeveloping works only for those examples, it's useless. Rather than put in fiddly overfitty changes, or oppressively constrictive MUSTs, if there's some stubborn issue, you might try branching out and using different metaphors, or recommending different patterns of working. It's relatively cheap to try and maybe you'll land on something great.
2. **Keep the prompt lean.** Remove things that aren't pulling their weight. Make sure to read the transcripts, not just the final outputs — if it looks like the skill is making the model waste a bunch of time doing things that are unproductive, you can try getting rid of the parts of the skill that are making it do that and seeing what happens.
3. **Explain the why.** Try hard to explain the **why** behind everything you're asking the model to do. Today's LLMs are *smart*. They have good theory of mind and when given a good harness can go beyond rote instructions and really make things happen. Even if the feedback from the user is terse or frustrated, try to actually understand the task and why the user is writing what they wrote, and what they actually wrote, and then transmit this understanding into the instructions. If you find yourself writing ALWAYS or NEVER in all caps, or using super rigid structures, that's a yellow flag — if possible, reframe and explain the reasoning so that the model understands why the thing you're asking for is important. That's a more humane, powerful, and effective approach.
4. **Look for repeated work across test cases.** Read the transcripts from the test runs and notice if the subagents all independently wrote similar helper scripts or took the same multi-step approach to something. If all 3 test cases resulted in the subagent writing a `create_docx.py` or a `build_chart.py`, that's a strong signal the skill should bundle that script. Write it once, put it in `scripts/`, and tell the skill to use it. This saves every future invocation from reinventing the wheel.
This task is pretty important (we are trying to create billions a year in economic value here!) and your thinking time is not the blocker; take your time and really mull things over. I'd suggest writing a draft revision and then looking at it anew and making improvements. Really do your best to get into the head of the user and understand what they want and need.
### The iteration loop
After improving the skill:
1. Apply your improvements to the skill
2. Rerun all test cases into a new `iteration-<N+1>/` directory, including baseline runs. If you're creating a new skill, the baseline is always `without_skill` (no skill) — that stays the same across iterations. If you're improving an existing skill, use your judgment on what makes sense as the baseline: the original version the user came in with, or the previous iteration.
3. Launch the reviewer with `--previous-workspace` pointing at the previous iteration
4. Wait for the user to review and tell you they're done
5. Read the new feedback, improve again, repeat
Keep going until:
- The user says they're happy
- The feedback is all empty (everything looks good)
- You're not making meaningful progress
---
## Advanced: Blind comparison
For situations where you want a more rigorous comparison between two versions of a skill (e.g., the user asks "is the new version actually better?"), there's a blind comparison system. Read `agents/comparator.md` and `agents/analyzer.md` for the details. The basic idea is: give two outputs to an independent agent without telling it which is which, and let it judge quality. Then analyze why the winner won.
This is optional, requires subagents, and most users won't need it. The human review loop is usually sufficient.
---
## Description Optimization
The description field in SKILL.md frontmatter is the primary mechanism that determines whether Claude invokes a skill. After creating or improving a skill, offer to optimize the description for better triggering accuracy.
### Step 1: Generate trigger eval queries
Create 20 eval queries — a mix of should-trigger and should-not-trigger. Save as JSON:
```json
[
{"query": "the user prompt", "should_trigger": true},
{"query": "another prompt", "should_trigger": false}
]
```
The queries must be realistic and something a Claude Code or Claude.ai user would actually type. Not abstract requests, but requests that are concrete and specific and have a good amount of detail. For instance, file paths, personal context about the user's job or situation, column names and values, company names, URLs. A little bit of backstory. Some might be in lowercase or contain abbreviations or typos or casual speech. Use a mix of different lengths, and focus on edge cases rather than making them clear-cut (the user will get a chance to sign off on them).
Bad: `"Format this data"`, `"Extract text from PDF"`, `"Create a chart"`
Good: `"ok so my boss just sent me this xlsx file (its in my downloads, called something like 'Q4 sales final FINAL v2.xlsx') and she wants me to add a column that shows the profit margin as a percentage. The revenue is in column C and costs are in column D i think"`
For the **should-trigger** queries (8-10), think about coverage. You want different phrasings of the same intent — some formal, some casual. Include cases where the user doesn't explicitly name the skill or file type but clearly needs it. Throw in some uncommon use cases and cases where this skill competes with another but should win.
For the **should-not-trigger** queries (8-10), the most valuable ones are the near-misses — queries that share keywords or concepts with the skill but actually need something different. Think adjacent domains, ambiguous phrasing where a naive keyword match would trigger but shouldn't, and cases where the query touches on something the skill does but in a context where another tool is more appropriate.
The key thing to avoid: don't make should-not-trigger queries obviously irrelevant. "Write a fibonacci function" as a negative test for a PDF skill is too easy — it doesn't test anything. The negative cases should be genuinely tricky.
### Step 2: Review with user
Present the eval set to the user for review using the HTML template:
1. Read the template from `assets/eval_review.html`
2. Replace the placeholders:
- `__EVAL_DATA_PLACEHOLDER__` → the JSON array of eval items (no quotes around it — it's a JS variable assignment)
- `__SKILL_NAME_PLACEHOLDER__` → the skill's name
- `__SKILL_DESCRIPTION_PLACEHOLDER__` → the skill's current description
3. Write to a temp file (e.g., `/tmp/eval_review_<skill-name>.html`) and open it: `open /tmp/eval_review_<skill-name>.html`
4. The user can edit queries, toggle should-trigger, add/remove entries, then click "Export Eval Set"
5. The file downloads to `~/Downloads/eval_set.json` — check the Downloads folder for the most recent version in case there are multiple (e.g., `eval_set (1).json`)
This step matters — bad eval queries lead to bad descriptions.
### Step 3: Run the optimization loop
Tell the user: "This will take some time — I'll run the optimization loop in the background and check on it periodically."
Save the eval set to the workspace, then run in the background:
```bash
python -m scripts.run_loop \
--eval-set <path-to-trigger-eval.json> \
--skill-path <path-to-skill> \
--model <model-id-powering-this-session> \
--max-iterations 5 \
--verbose
```
Use the model ID from your system prompt (the one powering the current session) so the triggering test matches what the user actually experiences.
While it runs, periodically tail the output to give the user updates on which iteration it's on and what the scores look like.
This handles the full optimization loop automatically. It splits the eval set into 60% train and 40% held-out test, evaluates the current description (running each query 3 times to get a reliable trigger rate), then calls Claude with extended thinking to propose improvements based on what failed. It re-evaluates each new description on both train and test, iterating up to 5 times. When it's done, it opens an HTML report in the browser showing the results per iteration and returns JSON with `best_description` — selected by test score rather than train score to avoid overfitting.
### How skill triggering works
Understanding the triggering mechanism helps design better eval queries. Skills appear in Claude's `available_skills` list with their name + description, and Claude decides whether to consult a skill based on that description. The important thing to know is that Claude only consults skills for tasks it can't easily handle on its own — simple, one-step queries like "read this PDF" may not trigger a skill even if the description matches perfectly, because Claude can handle them directly with basic tools. Complex, multi-step, or specialized queries reliably trigger skills when the description matches.
This means your eval queries should be substantive enough that Claude would actually benefit from consulting a skill. Simple queries like "read file X" are poor test cases — they won't trigger skills regardless of description quality.
### Step 4: Apply the result
Take `best_description` from the JSON output and update the skill's SKILL.md frontmatter. Show the user before/after and report the scores.
---
### Package and Present (only if `present_files` tool is available)
Check whether you have access to the `present_files` tool. If you don't, skip this step. If you do, package the skill and present the .skill file to the user:
```bash
python -m scripts.package_skill <path/to/skill-folder>
```
After packaging, direct the user to the resulting `.skill` file path so they can install it.
---
## Claude.ai-specific instructions
In Claude.ai, the core workflow is the same (draft → test → review → improve → repeat), but because Claude.ai doesn't have subagents, some mechanics change. Here's what to adapt:
**Running test cases**: No subagents means no parallel execution. For each test case, read the skill's SKILL.md, then follow its instructions to accomplish the test prompt yourself. Do them one at a time. This is less rigorous than independent subagents (you wrote the skill and you're also running it, so you have full context), but it's a useful sanity check — and the human review step compensates. Skip the baseline runs — just use the skill to complete the task as requested.
**Reviewing results**: If you can't open a browser (e.g., Claude.ai's VM has no display, or you're on a remote server), skip the browser reviewer entirely. Instead, present results directly in the conversation. For each test case, show the prompt and the output. If the output is a file the user needs to see (like a .docx or .xlsx), save it to the filesystem and tell them where it is so they can download and inspect it. Ask for feedback inline: "How does this look? Anything you'd change?"
**Benchmarking**: Skip the quantitative benchmarking — it relies on baseline comparisons which aren't meaningful without subagents. Focus on qualitative feedback from the user.
**The iteration loop**: Same as before — improve the skill, rerun the test cases, ask for feedback — just without the browser reviewer in the middle. You can still organize results into iteration directories on the filesystem if you have one.
**Description optimization**: This section requires the `claude` CLI tool (specifically `claude -p`) which is only available in Claude Code. Skip it if you're on Claude.ai.
**Blind comparison**: Requires subagents. Skip it.
**Packaging**: The `package_skill.py` script works anywhere with Python and a filesystem. On Claude.ai, you can run it and the user can download the resulting `.skill` file.
---
## Cowork-Specific Instructions
If you're in Cowork, the main things to know are:
- You have subagents, so the main workflow (spawn test cases in parallel, run baselines, grade, etc.) all works. (However, if you run into severe problems with timeouts, it's OK to run the test prompts in series rather than parallel.)
- You don't have a browser or display, so when generating the eval viewer, use `--static <output_path>` to write a standalone HTML file instead of starting a server. Then proffer a link that the user can click to open the HTML in their browser.
- For whatever reason, the Cowork setup seems to disincline Claude from generating the eval viewer after running the tests, so just to reiterate: whether you're in Cowork or in Claude Code, after running tests, you should always generate the eval viewer for the human to look at examples before revising the skill yourself and trying to make corrections, using `generate_review.py` (not writing your own boutique html code). Sorry in advance but I'm gonna go all caps here: GENERATE THE EVAL VIEWER *BEFORE* evaluating inputs yourself. You want to get them in front of the human ASAP!
- Feedback works differently: since there's no running server, the viewer's "Submit All Reviews" button will download `feedback.json` as a file. You can then read it from there (you may have to request access first).
- Packaging works — `package_skill.py` just needs Python and a filesystem.
- Description optimization (`run_loop.py` / `run_eval.py`) should work in Cowork just fine since it uses `claude -p` via subprocess, not a browser, but please save it until you've fully finished making the skill and the user agrees it's in good shape.
---
## Reference files
The agents/ directory contains instructions for specialized subagents. Read them when you need to spawn the relevant subagent.
- `agents/grader.md` — How to evaluate assertions against outputs
- `agents/comparator.md` — How to do blind A/B comparison between two outputs
- `agents/analyzer.md` — How to analyze why one version beat another
The references/ directory has additional documentation:
- `references/schemas.md` — JSON structures for evals.json, grading.json, etc.
---
Repeating one more time the core loop here for emphasis:
- Figure out what the skill is about
- Draft or edit the skill
- Run claude-with-access-to-the-skill on test prompts
- With the user, evaluate the outputs:
- Create benchmark.json and run `eval-viewer/generate_review.py` to help the user review them
- Run quantitative evals
- Repeat until you and the user are satisfied
- Package the final skill and return it to the user.
Please add steps to your TodoList, if you have such a thing, to make sure you don't forget. If you're in Cowork, please specifically put "Create evals JSON and run `eval-viewer/generate_review.py` so human can review test cases" in your TodoList to make sure it happens.
Good luck!

274
.agents/skills/skill-creator/agents/analyzer.md Normal file
View File

@@ -0,0 +1,274 @@
# Post-hoc Analyzer Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
## Role
After the blind comparator determines a winner, the Post-hoc Analyzer "unblids" the results by examining the skills and transcripts. The goal is to extract actionable insights: what made the winner better, and how can the loser be improved?
## Inputs
You receive these parameters in your prompt:
- **winner**: "A" or "B" (from blind comparison)
- **winner_skill_path**: Path to the skill that produced the winning output
- **winner_transcript_path**: Path to the execution transcript for the winner
- **loser_skill_path**: Path to the skill that produced the losing output
- **loser_transcript_path**: Path to the execution transcript for the loser
- **comparison_result_path**: Path to the blind comparator's output JSON
- **output_path**: Where to save the analysis results
## Process
### Step 1: Read Comparison Result
1. Read the blind comparator's output at comparison_result_path
2. Note the winning side (A or B), the reasoning, and any scores
3. Understand what the comparator valued in the winning output
### Step 2: Read Both Skills
1. Read the winner skill's SKILL.md and key referenced files
2. Read the loser skill's SKILL.md and key referenced files
3. Identify structural differences:
- Instructions clarity and specificity
- Script/tool usage patterns
- Example coverage
- Edge case handling
### Step 3: Read Both Transcripts
1. Read the winner's transcript
2. Read the loser's transcript
3. Compare execution patterns:
- How closely did each follow their skill's instructions?
- What tools were used differently?
- Where did the loser diverge from optimal behavior?
- Did either encounter errors or make recovery attempts?
### Step 4: Analyze Instruction Following
For each transcript, evaluate:
- Did the agent follow the skill's explicit instructions?
- Did the agent use the skill's provided tools/scripts?
- Were there missed opportunities to leverage skill content?
- Did the agent add unnecessary steps not in the skill?
Score instruction following 1-10 and note specific issues.
### Step 5: Identify Winner Strengths
Determine what made the winner better:
- Clearer instructions that led to better behavior?
- Better scripts/tools that produced better output?
- More comprehensive examples that guided edge cases?
- Better error handling guidance?
Be specific. Quote from skills/transcripts where relevant.
### Step 6: Identify Loser Weaknesses
Determine what held the loser back:
- Ambiguous instructions that led to suboptimal choices?
- Missing tools/scripts that forced workarounds?
- Gaps in edge case coverage?
- Poor error handling that caused failures?
### Step 7: Generate Improvement Suggestions
Based on the analysis, produce actionable suggestions for improving the loser skill:
- Specific instruction changes to make
- Tools/scripts to add or modify
- Examples to include
- Edge cases to address
Prioritize by impact. Focus on changes that would have changed the outcome.
### Step 8: Write Analysis Results
Save structured analysis to `{output_path}`.
## Output Format
Write a JSON file with this structure:
```json
{
"comparison_summary": {
"winner": "A",
"winner_skill": "path/to/winner/skill",
"loser_skill": "path/to/loser/skill",
"comparator_reasoning": "Brief summary of why comparator chose winner"
},
"winner_strengths": [
"Clear step-by-step instructions for handling multi-page documents",
"Included validation script that caught formatting errors",
"Explicit guidance on fallback behavior when OCR fails"
],
"loser_weaknesses": [
"Vague instruction 'process the document appropriately' led to inconsistent behavior",
"No script for validation, agent had to improvise and made errors",
"No guidance on OCR failure, agent gave up instead of trying alternatives"
],
"instruction_following": {
"winner": {
"score": 9,
"issues": [
"Minor: skipped optional logging step"
]
},
"loser": {
"score": 6,
"issues": [
"Did not use the skill's formatting template",
"Invented own approach instead of following step 3",
"Missed the 'always validate output' instruction"
]
}
},
"improvement_suggestions": [
{
"priority": "high",
"category": "instructions",
"suggestion": "Replace 'process the document appropriately' with explicit steps: 1) Extract text, 2) Identify sections, 3) Format per template",
"expected_impact": "Would eliminate ambiguity that caused inconsistent behavior"
},
{
"priority": "high",
"category": "tools",
"suggestion": "Add validate_output.py script similar to winner skill's validation approach",
"expected_impact": "Would catch formatting errors before final output"
},
{
"priority": "medium",
"category": "error_handling",
"suggestion": "Add fallback instructions: 'If OCR fails, try: 1) different resolution, 2) image preprocessing, 3) manual extraction'",
"expected_impact": "Would prevent early failure on difficult documents"
}
],
"transcript_insights": {
"winner_execution_pattern": "Read skill -> Followed 5-step process -> Used validation script -> Fixed 2 issues -> Produced output",
"loser_execution_pattern": "Read skill -> Unclear on approach -> Tried 3 different methods -> No validation -> Output had errors"
}
}
```
## Guidelines
- **Be specific**: Quote from skills and transcripts, don't just say "instructions were unclear"
- **Be actionable**: Suggestions should be concrete changes, not vague advice
- **Focus on skill improvements**: The goal is to improve the losing skill, not critique the agent
- **Prioritize by impact**: Which changes would most likely have changed the outcome?
- **Consider causation**: Did the skill weakness actually cause the worse output, or is it incidental?
- **Stay objective**: Analyze what happened, don't editorialize
- **Think about generalization**: Would this improvement help on other evals too?
## Categories for Suggestions
Use these categories to organize improvement suggestions:
| Category | Description |
|----------|-------------|
| `instructions` | Changes to the skill's prose instructions |
| `tools` | Scripts, templates, or utilities to add/modify |
| `examples` | Example inputs/outputs to include |
| `error_handling` | Guidance for handling failures |
| `structure` | Reorganization of skill content |
| `references` | External docs or resources to add |
## Priority Levels
- **high**: Would likely change the outcome of this comparison
- **medium**: Would improve quality but may not change win/loss
- **low**: Nice to have, marginal improvement
---
# Analyzing Benchmark Results
When analyzing benchmark results, the analyzer's purpose is to **surface patterns and anomalies** across multiple runs, not suggest skill improvements.
## Role
Review all benchmark run results and generate freeform notes that help the user understand skill performance. Focus on patterns that wouldn't be visible from aggregate metrics alone.
## Inputs
You receive these parameters in your prompt:
- **benchmark_data_path**: Path to the in-progress benchmark.json with all run results
- **skill_path**: Path to the skill being benchmarked
- **output_path**: Where to save the notes (as JSON array of strings)
## Process
### Step 1: Read Benchmark Data
1. Read the benchmark.json containing all run results
2. Note the configurations tested (with_skill, without_skill)
3. Understand the run_summary aggregates already calculated
### Step 2: Analyze Per-Assertion Patterns
For each expectation across all runs:
- Does it **always pass** in both configurations? (may not differentiate skill value)
- Does it **always fail** in both configurations? (may be broken or beyond capability)
- Does it **always pass with skill but fail without**? (skill clearly adds value here)
- Does it **always fail with skill but pass without**? (skill may be hurting)
- Is it **highly variable**? (flaky expectation or non-deterministic behavior)
### Step 3: Analyze Cross-Eval Patterns
Look for patterns across evals:
- Are certain eval types consistently harder/easier?
- Do some evals show high variance while others are stable?
- Are there surprising results that contradict expectations?
### Step 4: Analyze Metrics Patterns
Look at time_seconds, tokens, tool_calls:
- Does the skill significantly increase execution time?
- Is there high variance in resource usage?
- Are there outlier runs that skew the aggregates?
### Step 5: Generate Notes
Write freeform observations as a list of strings. Each note should:
- State a specific observation
- Be grounded in the data (not speculation)
- Help the user understand something the aggregate metrics don't show
Examples:
- "Assertion 'Output is a PDF file' passes 100% in both configurations - may not differentiate skill value"
- "Eval 3 shows high variance (50% ± 40%) - run 2 had an unusual failure that may be flaky"
- "Without-skill runs consistently fail on table extraction expectations (0% pass rate)"
- "Skill adds 13s average execution time but improves pass rate by 50%"
- "Token usage is 80% higher with skill, primarily due to script output parsing"
- "All 3 without-skill runs for eval 1 produced empty output"
### Step 6: Write Notes
Save notes to `{output_path}` as a JSON array of strings:
```json
[
"Assertion 'Output is a PDF file' passes 100% in both configurations - may not differentiate skill value",
"Eval 3 shows high variance (50% ± 40%) - run 2 had an unusual failure",
"Without-skill runs consistently fail on table extraction expectations",
"Skill adds 13s average execution time but improves pass rate by 50%"
]
```
## Guidelines
**DO:**
- Report what you observe in the data
- Be specific about which evals, expectations, or runs you're referring to
- Note patterns that aggregate metrics would hide
- Provide context that helps interpret the numbers
**DO NOT:**
- Suggest improvements to the skill (that's for the improvement step, not benchmarking)
- Make subjective quality judgments ("the output was good/bad")
- Speculate about causes without evidence
- Repeat information already in the run_summary aggregates

202
.agents/skills/skill-creator/agents/comparator.md Normal file
View File

@@ -0,0 +1,202 @@
# Blind Comparator Agent
Compare two outputs WITHOUT knowing which skill produced them.
## Role
The Blind Comparator judges which output better accomplishes the eval task. You receive two outputs labeled A and B, but you do NOT know which skill produced which. This prevents bias toward a particular skill or approach.
Your judgment is based purely on output quality and task completion.
## Inputs
You receive these parameters in your prompt:
- **output_a_path**: Path to the first output file or directory
- **output_b_path**: Path to the second output file or directory
- **eval_prompt**: The original task/prompt that was executed
- **expectations**: List of expectations to check (optional - may be empty)
## Process
### Step 1: Read Both Outputs
1. Examine output A (file or directory)
2. Examine output B (file or directory)
3. Note the type, structure, and content of each
4. If outputs are directories, examine all relevant files inside
### Step 2: Understand the Task
1. Read the eval_prompt carefully
2. Identify what the task requires:
- What should be produced?
- What qualities matter (accuracy, completeness, format)?
- What would distinguish a good output from a poor one?
### Step 3: Generate Evaluation Rubric
Based on the task, generate a rubric with two dimensions:
**Content Rubric** (what the output contains):
| Criterion | 1 (Poor) | 3 (Acceptable) | 5 (Excellent) |
|-----------|----------|----------------|---------------|
| Correctness | Major errors | Minor errors | Fully correct |
| Completeness | Missing key elements | Mostly complete | All elements present |
| Accuracy | Significant inaccuracies | Minor inaccuracies | Accurate throughout |
**Structure Rubric** (how the output is organized):
| Criterion | 1 (Poor) | 3 (Acceptable) | 5 (Excellent) |
|-----------|----------|----------------|---------------|
| Organization | Disorganized | Reasonably organized | Clear, logical structure |
| Formatting | Inconsistent/broken | Mostly consistent | Professional, polished |
| Usability | Difficult to use | Usable with effort | Easy to use |
Adapt criteria to the specific task. For example:
- PDF form → "Field alignment", "Text readability", "Data placement"
- Document → "Section structure", "Heading hierarchy", "Paragraph flow"
- Data output → "Schema correctness", "Data types", "Completeness"
### Step 4: Evaluate Each Output Against the Rubric
For each output (A and B):
1. **Score each criterion** on the rubric (1-5 scale)
2. **Calculate dimension totals**: Content score, Structure score
3. **Calculate overall score**: Average of dimension scores, scaled to 1-10
### Step 5: Check Assertions (if provided)
If expectations are provided:
1. Check each expectation against output A
2. Check each expectation against output B
3. Count pass rates for each output
4. Use expectation scores as secondary evidence (not the primary decision factor)
### Step 6: Determine the Winner
Compare A and B based on (in priority order):
1. **Primary**: Overall rubric score (content + structure)
2. **Secondary**: Assertion pass rates (if applicable)
3. **Tiebreaker**: If truly equal, declare a TIE
Be decisive - ties should be rare. One output is usually better, even if marginally.
### Step 7: Write Comparison Results
Save results to a JSON file at the path specified (or `comparison.json` if not specified).
## Output Format
Write a JSON file with this structure:
```json
{
"winner": "A",
"reasoning": "Output A provides a complete solution with proper formatting and all required fields. Output B is missing the date field and has formatting inconsistencies.",
"rubric": {
"A": {
"content": {
"correctness": 5,
"completeness": 5,
"accuracy": 4
},
"structure": {
"organization": 4,
"formatting": 5,
"usability": 4
},
"content_score": 4.7,
"structure_score": 4.3,
"overall_score": 9.0
},
"B": {
"content": {
"correctness": 3,
"completeness": 2,
"accuracy": 3
},
"structure": {
"organization": 3,
"formatting": 2,
"usability": 3
},
"content_score": 2.7,
"structure_score": 2.7,
"overall_score": 5.4
}
},
"output_quality": {
"A": {
"score": 9,
"strengths": ["Complete solution", "Well-formatted", "All fields present"],
"weaknesses": ["Minor style inconsistency in header"]
},
"B": {
"score": 5,
"strengths": ["Readable output", "Correct basic structure"],
"weaknesses": ["Missing date field", "Formatting inconsistencies", "Partial data extraction"]
}
},
"expectation_results": {
"A": {
"passed": 4,
"total": 5,
"pass_rate": 0.80,
"details": [
{"text": "Output includes name", "passed": true},
{"text": "Output includes date", "passed": true},
{"text": "Format is PDF", "passed": true},
{"text": "Contains signature", "passed": false},
{"text": "Readable text", "passed": true}
]
},
"B": {
"passed": 3,
"total": 5,
"pass_rate": 0.60,
"details": [
{"text": "Output includes name", "passed": true},
{"text": "Output includes date", "passed": false},
{"text": "Format is PDF", "passed": true},
{"text": "Contains signature", "passed": false},
{"text": "Readable text", "passed": true}
]
}
}
}
```
If no expectations were provided, omit the `expectation_results` field entirely.
## Field Descriptions
- **winner**: "A", "B", or "TIE"
- **reasoning**: Clear explanation of why the winner was chosen (or why it's a tie)
- **rubric**: Structured rubric evaluation for each output
- **content**: Scores for content criteria (correctness, completeness, accuracy)
- **structure**: Scores for structure criteria (organization, formatting, usability)
- **content_score**: Average of content criteria (1-5)
- **structure_score**: Average of structure criteria (1-5)
- **overall_score**: Combined score scaled to 1-10
- **output_quality**: Summary quality assessment
- **score**: 1-10 rating (should match rubric overall_score)
- **strengths**: List of positive aspects
- **weaknesses**: List of issues or shortcomings
- **expectation_results**: (Only if expectations provided)
- **passed**: Number of expectations that passed
- **total**: Total number of expectations
- **pass_rate**: Fraction passed (0.0 to 1.0)
- **details**: Individual expectation results
## Guidelines
- **Stay blind**: DO NOT try to infer which skill produced which output. Judge purely on output quality.
- **Be specific**: Cite specific examples when explaining strengths and weaknesses.
- **Be decisive**: Choose a winner unless outputs are genuinely equivalent.
- **Output quality first**: Assertion scores are secondary to overall task completion.
- **Be objective**: Don't favor outputs based on style preferences; focus on correctness and completeness.
- **Explain your reasoning**: The reasoning field should make it clear why you chose the winner.
- **Handle edge cases**: If both outputs fail, pick the one that fails less badly. If both are excellent, pick the one that's marginally better.

223
.agents/skills/skill-creator/agents/grader.md Normal file
View File

@@ -0,0 +1,223 @@
# Grader Agent
Evaluate expectations against an execution transcript and outputs.
## Role
The Grader reviews a transcript and output files, then determines whether each expectation passes or fails. Provide clear evidence for each judgment.
You have two jobs: grade the outputs, and critique the evals themselves. A passing grade on a weak assertion is worse than useless — it creates false confidence. When you notice an assertion that's trivially satisfied, or an important outcome that no assertion checks, say so.
## Inputs
You receive these parameters in your prompt:
- **expectations**: List of expectations to evaluate (strings)
- **transcript_path**: Path to the execution transcript (markdown file)
- **outputs_dir**: Directory containing output files from execution
## Process
### Step 1: Read the Transcript
1. Read the transcript file completely
2. Note the eval prompt, execution steps, and final result
3. Identify any issues or errors documented
### Step 2: Examine Output Files
1. List files in outputs_dir
2. Read/examine each file relevant to the expectations. If outputs aren't plain text, use the inspection tools provided in your prompt — don't rely solely on what the transcript says the executor produced.
3. Note contents, structure, and quality
### Step 3: Evaluate Each Assertion
For each expectation:
1. **Search for evidence** in the transcript and outputs
2. **Determine verdict**:
- **PASS**: Clear evidence the expectation is true AND the evidence reflects genuine task completion, not just surface-level compliance
- **FAIL**: No evidence, or evidence contradicts the expectation, or the evidence is superficial (e.g., correct filename but empty/wrong content)
3. **Cite the evidence**: Quote the specific text or describe what you found
### Step 4: Extract and Verify Claims
Beyond the predefined expectations, extract implicit claims from the outputs and verify them:
1. **Extract claims** from the transcript and outputs:
- Factual statements ("The form has 12 fields")
- Process claims ("Used pypdf to fill the form")
- Quality claims ("All fields were filled correctly")
2. **Verify each claim**:
- **Factual claims**: Can be checked against the outputs or external sources
- **Process claims**: Can be verified from the transcript
- **Quality claims**: Evaluate whether the claim is justified
3. **Flag unverifiable claims**: Note claims that cannot be verified with available information
This catches issues that predefined expectations might miss.
### Step 5: Read User Notes
If `{outputs_dir}/user_notes.md` exists:
1. Read it and note any uncertainties or issues flagged by the executor
2. Include relevant concerns in the grading output
3. These may reveal problems even when expectations pass
### Step 6: Critique the Evals
After grading, consider whether the evals themselves could be improved. Only surface suggestions when there's a clear gap.
Good suggestions test meaningful outcomes — assertions that are hard to satisfy without actually doing the work correctly. Think about what makes an assertion *discriminating*: it passes when the skill genuinely succeeds and fails when it doesn't.
Suggestions worth raising:
- An assertion that passed but would also pass for a clearly wrong output (e.g., checking filename existence but not file content)
- An important outcome you observed — good or bad — that no assertion covers at all
- An assertion that can't actually be verified from the available outputs
Keep the bar high. The goal is to flag things the eval author would say "good catch" about, not to nitpick every assertion.
### Step 7: Write Grading Results
Save results to `{outputs_dir}/../grading.json` (sibling to outputs_dir).
## Grading Criteria
**PASS when**:
- The transcript or outputs clearly demonstrate the expectation is true
- Specific evidence can be cited
- The evidence reflects genuine substance, not just surface compliance (e.g., a file exists AND contains correct content, not just the right filename)
**FAIL when**:
- No evidence found for the expectation
- Evidence contradicts the expectation
- The expectation cannot be verified from available information
- The evidence is superficial — the assertion is technically satisfied but the underlying task outcome is wrong or incomplete
- The output appears to meet the assertion by coincidence rather than by actually doing the work
**When uncertain**: The burden of proof to pass is on the expectation.
### Step 8: Read Executor Metrics and Timing
1. If `{outputs_dir}/metrics.json` exists, read it and include in grading output
2. If `{outputs_dir}/../timing.json` exists, read it and include timing data
## Output Format
Write a JSON file with this structure:
```json
{
"expectations": [
{
"text": "The output includes the name 'John Smith'",
"passed": true,
"evidence": "Found in transcript Step 3: 'Extracted names: John Smith, Sarah Johnson'"
},
{
"text": "The spreadsheet has a SUM formula in cell B10",
"passed": false,
"evidence": "No spreadsheet was created. The output was a text file."
},
{
"text": "The assistant used the skill's OCR script",
"passed": true,
"evidence": "Transcript Step 2 shows: 'Tool: Bash - python ocr_script.py image.png'"
}
],
"summary": {
"passed": 2,
"failed": 1,
"total": 3,
"pass_rate": 0.67
},
"execution_metrics": {
"tool_calls": {
"Read": 5,
"Write": 2,
"Bash": 8
},
"total_tool_calls": 15,
"total_steps": 6,
"errors_encountered": 0,
"output_chars": 12450,
"transcript_chars": 3200
},
"timing": {
"executor_duration_seconds": 165.0,
"grader_duration_seconds": 26.0,
"total_duration_seconds": 191.0
},
"claims": [
{
"claim": "The form has 12 fillable fields",
"type": "factual",
"verified": true,
"evidence": "Counted 12 fields in field_info.json"
},
{
"claim": "All required fields were populated",
"type": "quality",
"verified": false,
"evidence": "Reference section was left blank despite data being available"
}
],
"user_notes_summary": {
"uncertainties": ["Used 2023 data, may be stale"],
"needs_review": [],
"workarounds": ["Fell back to text overlay for non-fillable fields"]
},
"eval_feedback": {
"suggestions": [
{
"assertion": "The output includes the name 'John Smith'",
"reason": "A hallucinated document that mentions the name would also pass — consider checking it appears as the primary contact with matching phone and email from the input"
},
{
"reason": "No assertion checks whether the extracted phone numbers match the input — I observed incorrect numbers in the output that went uncaught"
}
],
"overall": "Assertions check presence but not correctness. Consider adding content verification."
}
}
```
## Field Descriptions
- **expectations**: Array of graded expectations
- **text**: The original expectation text
- **passed**: Boolean - true if expectation passes
- **evidence**: Specific quote or description supporting the verdict
- **summary**: Aggregate statistics
- **passed**: Count of passed expectations
- **failed**: Count of failed expectations
- **total**: Total expectations evaluated
- **pass_rate**: Fraction passed (0.0 to 1.0)
- **execution_metrics**: Copied from executor's metrics.json (if available)
- **output_chars**: Total character count of output files (proxy for tokens)
- **transcript_chars**: Character count of transcript
- **timing**: Wall clock timing from timing.json (if available)
- **executor_duration_seconds**: Time spent in executor subagent
- **total_duration_seconds**: Total elapsed time for the run
- **claims**: Extracted and verified claims from the output
- **claim**: The statement being verified
- **type**: "factual", "process", or "quality"
- **verified**: Boolean - whether the claim holds
- **evidence**: Supporting or contradicting evidence
- **user_notes_summary**: Issues flagged by the executor
- **uncertainties**: Things the executor wasn't sure about
- **needs_review**: Items requiring human attention
- **workarounds**: Places where the skill didn't work as expected
- **eval_feedback**: Improvement suggestions for the evals (only when warranted)
- **suggestions**: List of concrete suggestions, each with a `reason` and optionally an `assertion` it relates to
- **overall**: Brief assessment — can be "No suggestions, evals look solid" if nothing to flag
## Guidelines
- **Be objective**: Base verdicts on evidence, not assumptions
- **Be specific**: Quote the exact text that supports your verdict
- **Be thorough**: Check both transcript and output files
- **Be consistent**: Apply the same standard to each expectation
- **Explain failures**: Make it clear why evidence was insufficient
- **No partial credit**: Each expectation is pass or fail, not partial

146
.agents/skills/skill-creator/assets/eval_review.html Normal file
View File

@@ -0,0 +1,146 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Eval Set Review - __SKILL_NAME_PLACEHOLDER__</title>
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
<style>
* { box-sizing: border-box; margin: 0; padding: 0; }
body { font-family: 'Lora', Georgia, serif; background: #faf9f5; padding: 2rem; color: #141413; }
h1 { font-family: 'Poppins', sans-serif; margin-bottom: 0.5rem; font-size: 1.5rem; }
.description { color: #b0aea5; margin-bottom: 1.5rem; font-style: italic; max-width: 900px; }
.controls { margin-bottom: 1rem; display: flex; gap: 0.5rem; }
.btn { font-family: 'Poppins', sans-serif; padding: 0.5rem 1rem; border: none; border-radius: 6px; cursor: pointer; font-size: 0.875rem; font-weight: 500; }
.btn-add { background: #6a9bcc; color: white; }
.btn-add:hover { background: #5889b8; }
.btn-export { background: #d97757; color: white; }
.btn-export:hover { background: #c4613f; }
table { width: 100%; max-width: 1100px; border-collapse: collapse; background: white; border-radius: 6px; overflow: hidden; box-shadow: 0 1px 3px rgba(0,0,0,0.08); }
th { font-family: 'Poppins', sans-serif; background: #141413; color: #faf9f5; padding: 0.75rem 1rem; text-align: left; font-size: 0.875rem; }
td { padding: 0.75rem 1rem; border-bottom: 1px solid #e8e6dc; vertical-align: top; }
tr:nth-child(even) td { background: #faf9f5; }
tr:hover td { background: #f3f1ea; }
.section-header td { background: #e8e6dc; font-family: 'Poppins', sans-serif; font-weight: 500; font-size: 0.8rem; color: #141413; text-transform: uppercase; letter-spacing: 0.05em; }
.query-input { width: 100%; padding: 0.4rem; border: 1px solid #e8e6dc; border-radius: 4px; font-size: 0.875rem; font-family: 'Lora', Georgia, serif; resize: vertical; min-height: 60px; }
.query-input:focus { outline: none; border-color: #d97757; box-shadow: 0 0 0 2px rgba(217,119,87,0.15); }
.toggle { position: relative; display: inline-block; width: 44px; height: 24px; }
.toggle input { opacity: 0; width: 0; height: 0; }
.toggle .slider { position: absolute; inset: 0; background: #b0aea5; border-radius: 24px; cursor: pointer; transition: 0.2s; }
.toggle .slider::before { content: ""; position: absolute; width: 18px; height: 18px; left: 3px; bottom: 3px; background: white; border-radius: 50%; transition: 0.2s; }
.toggle input:checked + .slider { background: #d97757; }
.toggle input:checked + .slider::before { transform: translateX(20px); }
.btn-delete { background: #c44; color: white; padding: 0.3rem 0.6rem; border: none; border-radius: 4px; cursor: pointer; font-size: 0.75rem; font-family: 'Poppins', sans-serif; }
.btn-delete:hover { background: #a33; }
.summary { margin-top: 1rem; color: #b0aea5; font-size: 0.875rem; }
</style>
</head>
<body>
<h1>Eval Set Review: <span id="skill-name">__SKILL_NAME_PLACEHOLDER__</span></h1>
<p class="description">Current description: <span id="skill-desc">__SKILL_DESCRIPTION_PLACEHOLDER__</span></p>
<div class="controls">
<button class="btn btn-add" onclick="addRow()">+ Add Query</button>
<button class="btn btn-export" onclick="exportEvalSet()">Export Eval Set</button>
</div>
<table>
<thead>
<tr>
<th style="width:65%">Query</th>
<th style="width:18%">Should Trigger</th>
<th style="width:10%">Actions</th>
</tr>
</thead>
<tbody id="eval-body"></tbody>
</table>
<p class="summary" id="summary"></p>
<script>
const EVAL_DATA = __EVAL_DATA_PLACEHOLDER__;
let evalItems = [...EVAL_DATA];
function render() {
const tbody = document.getElementById('eval-body');
tbody.innerHTML = '';
// Sort: should-trigger first, then should-not-trigger
const sorted = evalItems
.map((item, origIdx) => ({ ...item, origIdx }))
.sort((a, b) => (b.should_trigger ? 1 : 0) - (a.should_trigger ? 1 : 0));
let lastGroup = null;
sorted.forEach(item => {
const group = item.should_trigger ? 'trigger' : 'no-trigger';
if (group !== lastGroup) {
const headerRow = document.createElement('tr');
headerRow.className = 'section-header';
headerRow.innerHTML = `<td colspan="3">${item.should_trigger ? 'Should Trigger' : 'Should NOT Trigger'}</td>`;
tbody.appendChild(headerRow);
lastGroup = group;
}
const idx = item.origIdx;
const tr = document.createElement('tr');
tr.innerHTML = `
<td><textarea class="query-input" onchange="updateQuery(${idx}, this.value)">${escapeHtml(item.query)}</textarea></td>
<td>
<label class="toggle">
<input type="checkbox" ${item.should_trigger ? 'checked' : ''} onchange="updateTrigger(${idx}, this.checked)">
<span class="slider"></span>
</label>
<span style="margin-left:8px;font-size:0.8rem;color:#b0aea5">${item.should_trigger ? 'Yes' : 'No'}</span>
</td>
<td><button class="btn-delete" onclick="deleteRow(${idx})">Delete</button></td>
`;
tbody.appendChild(tr);
});
updateSummary();
}
function escapeHtml(text) {
const div = document.createElement('div');
div.textContent = text;
return div.innerHTML;
}
function updateQuery(idx, value) { evalItems[idx].query = value; updateSummary(); }
function updateTrigger(idx, value) { evalItems[idx].should_trigger = value; render(); }
function deleteRow(idx) { evalItems.splice(idx, 1); render(); }
function addRow() {
evalItems.push({ query: '', should_trigger: true });
render();
const inputs = document.querySelectorAll('.query-input');
inputs[inputs.length - 1].focus();
}
function updateSummary() {
const trigger = evalItems.filter(i => i.should_trigger).length;
const noTrigger = evalItems.filter(i => !i.should_trigger).length;
document.getElementById('summary').textContent =
`${evalItems.length} queries total: ${trigger} should trigger, ${noTrigger} should not trigger`;
}
function exportEvalSet() {
const valid = evalItems.filter(i => i.query.trim() !== '');
const data = valid.map(i => ({ query: i.query.trim(), should_trigger: i.should_trigger }));
const blob = new Blob([JSON.stringify(data, null, 2)], { type: 'application/json' });
const url = URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = 'eval_set.json';
document.body.appendChild(a);
a.click();
document.body.removeChild(a);
URL.revokeObjectURL(url);
}
render();
</script>
</body>
</html>

471
.agents/skills/skill-creator/eval-viewer/generate_review.py Normal file
View File

@@ -0,0 +1,471 @@
#!/usr/bin/env python3
"""Generate and serve a review page for eval results.
Reads the workspace directory, discovers runs (directories with outputs/),
embeds all output data into a self-contained HTML page, and serves it via
a tiny HTTP server. Feedback auto-saves to feedback.json in the workspace.
Usage:
python generate_review.py <workspace-path> [--port PORT] [--skill-name NAME]
python generate_review.py <workspace-path> --previous-feedback /path/to/old/feedback.json
No dependencies beyond the Python stdlib are required.
"""
import argparse
import base64
import json
import mimetypes
import os
import re
import signal
import subprocess
import sys
import time
import webbrowser
from functools import partial
from http.server import HTTPServer, BaseHTTPRequestHandler
from pathlib import Path
# Files to exclude from output listings
METADATA_FILES = {"transcript.md", "user_notes.md", "metrics.json"}
# Extensions we render as inline text
TEXT_EXTENSIONS = {
".txt", ".md", ".json", ".csv", ".py", ".js", ".ts", ".tsx", ".jsx",
".yaml", ".yml", ".xml", ".html", ".css", ".sh", ".rb", ".go", ".rs",
".java", ".c", ".cpp", ".h", ".hpp", ".sql", ".r", ".toml",
}
# Extensions we render as inline images
IMAGE_EXTENSIONS = {".png", ".jpg", ".jpeg", ".gif", ".svg", ".webp"}
# MIME type overrides for common types
MIME_OVERRIDES = {
".svg": "image/svg+xml",
".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
".pptx": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
}
def get_mime_type(path: Path) -> str:
ext = path.suffix.lower()
if ext in MIME_OVERRIDES:
return MIME_OVERRIDES[ext]
mime, _ = mimetypes.guess_type(str(path))
return mime or "application/octet-stream"
def find_runs(workspace: Path) -> list[dict]:
"""Recursively find directories that contain an outputs/ subdirectory."""
runs: list[dict] = []
_find_runs_recursive(workspace, workspace, runs)
runs.sort(key=lambda r: (r.get("eval_id", float("inf")), r["id"]))
return runs
def _find_runs_recursive(root: Path, current: Path, runs: list[dict]) -> None:
if not current.is_dir():
return
outputs_dir = current / "outputs"
if outputs_dir.is_dir():
run = build_run(root, current)
if run:
runs.append(run)
return
skip = {"node_modules", ".git", "__pycache__", "skill", "inputs"}
for child in sorted(current.iterdir()):
if child.is_dir() and child.name not in skip:
_find_runs_recursive(root, child, runs)
def build_run(root: Path, run_dir: Path) -> dict | None:
"""Build a run dict with prompt, outputs, and grading data."""
prompt = ""
eval_id = None
# Try eval_metadata.json
for candidate in [run_dir / "eval_metadata.json", run_dir.parent / "eval_metadata.json"]:
if candidate.exists():
try:
metadata = json.loads(candidate.read_text())
prompt = metadata.get("prompt", "")
eval_id = metadata.get("eval_id")
except (json.JSONDecodeError, OSError):
pass
if prompt:
break
# Fall back to transcript.md
if not prompt:
for candidate in [run_dir / "transcript.md", run_dir / "outputs" / "transcript.md"]:
if candidate.exists():
try:
text = candidate.read_text()
match = re.search(r"## Eval Prompt\n\n([\s\S]*?)(?=\n##|$)", text)
if match:
prompt = match.group(1).strip()
except OSError:
pass
if prompt:
break
if not prompt:
prompt = "(No prompt found)"
run_id = str(run_dir.relative_to(root)).replace("/", "-").replace("\\", "-")
# Collect output files
outputs_dir = run_dir / "outputs"
output_files: list[dict] = []
if outputs_dir.is_dir():
for f in sorted(outputs_dir.iterdir()):
if f.is_file() and f.name not in METADATA_FILES:
output_files.append(embed_file(f))
# Load grading if present
grading = None
for candidate in [run_dir / "grading.json", run_dir.parent / "grading.json"]:
if candidate.exists():
try:
grading = json.loads(candidate.read_text())
except (json.JSONDecodeError, OSError):
pass
if grading:
break
return {
"id": run_id,
"prompt": prompt,
"eval_id": eval_id,
"outputs": output_files,
"grading": grading,
}
def embed_file(path: Path) -> dict:
"""Read a file and return an embedded representation."""
ext = path.suffix.lower()
mime = get_mime_type(path)
if ext in TEXT_EXTENSIONS:
try:
content = path.read_text(errors="replace")
except OSError:
content = "(Error reading file)"
return {
"name": path.name,
"type": "text",
"content": content,
}
elif ext in IMAGE_EXTENSIONS:
try:
raw = path.read_bytes()
b64 = base64.b64encode(raw).decode("ascii")
except OSError:
return {"name": path.name, "type": "error", "content": "(Error reading file)"}
return {
"name": path.name,
"type": "image",
"mime": mime,
"data_uri": f"data:{mime};base64,{b64}",
}
elif ext == ".pdf":
try:
raw = path.read_bytes()
b64 = base64.b64encode(raw).decode("ascii")
except OSError:
return {"name": path.name, "type": "error", "content": "(Error reading file)"}
return {
"name": path.name,
"type": "pdf",
"data_uri": f"data:{mime};base64,{b64}",
}
elif ext == ".xlsx":
try:
raw = path.read_bytes()
b64 = base64.b64encode(raw).decode("ascii")
except OSError:
return {"name": path.name, "type": "error", "content": "(Error reading file)"}
return {
"name": path.name,
"type": "xlsx",
"data_b64": b64,
}
else:
# Binary / unknown — base64 download link
try:
raw = path.read_bytes()
b64 = base64.b64encode(raw).decode("ascii")
except OSError:
return {"name": path.name, "type": "error", "content": "(Error reading file)"}
return {
"name": path.name,
"type": "binary",
"mime": mime,
"data_uri": f"data:{mime};base64,{b64}",
}
def load_previous_iteration(workspace: Path) -> dict[str, dict]:
"""Load previous iteration's feedback and outputs.
Returns a map of run_id -> {"feedback": str, "outputs": list[dict]}.
"""
result: dict[str, dict] = {}
# Load feedback
feedback_map: dict[str, str] = {}
feedback_path = workspace / "feedback.json"
if feedback_path.exists():
try:
data = json.loads(feedback_path.read_text())
feedback_map = {
r["run_id"]: r["feedback"]
for r in data.get("reviews", [])
if r.get("feedback", "").strip()
}
except (json.JSONDecodeError, OSError, KeyError):
pass
# Load runs (to get outputs)
prev_runs = find_runs(workspace)
for run in prev_runs:
result[run["id"]] = {
"feedback": feedback_map.get(run["id"], ""),
"outputs": run.get("outputs", []),
}
# Also add feedback for run_ids that had feedback but no matching run
for run_id, fb in feedback_map.items():
if run_id not in result:
result[run_id] = {"feedback": fb, "outputs": []}
return result
def generate_html(
runs: list[dict],
skill_name: str,
previous: dict[str, dict] | None = None,
benchmark: dict | None = None,
) -> str:
"""Generate the complete standalone HTML page with embedded data."""
template_path = Path(__file__).parent / "viewer.html"
template = template_path.read_text()
# Build previous_feedback and previous_outputs maps for the template
previous_feedback: dict[str, str] = {}
previous_outputs: dict[str, list[dict]] = {}
if previous:
for run_id, data in previous.items():
if data.get("feedback"):
previous_feedback[run_id] = data["feedback"]
if data.get("outputs"):
previous_outputs[run_id] = data["outputs"]
embedded = {
"skill_name": skill_name,
"runs": runs,
"previous_feedback": previous_feedback,
"previous_outputs": previous_outputs,
}
if benchmark:
embedded["benchmark"] = benchmark
data_json = json.dumps(embedded)
return template.replace("/*__EMBEDDED_DATA__*/", f"const EMBEDDED_DATA = {data_json};")
# ---------------------------------------------------------------------------
# HTTP server (stdlib only, zero dependencies)
# ---------------------------------------------------------------------------
def _kill_port(port: int) -> None:
"""Kill any process listening on the given port."""
try:
result = subprocess.run(
["lsof", "-ti", f":{port}"],
capture_output=True, text=True, timeout=5,
)
for pid_str in result.stdout.strip().split("\n"):
if pid_str.strip():
try:
os.kill(int(pid_str.strip()), signal.SIGTERM)
except (ProcessLookupError, ValueError):
pass
if result.stdout.strip():
time.sleep(0.5)
except subprocess.TimeoutExpired:
pass
except FileNotFoundError:
print("Note: lsof not found, cannot check if port is in use", file=sys.stderr)
class ReviewHandler(BaseHTTPRequestHandler):
"""Serves the review HTML and handles feedback saves.
Regenerates the HTML on each page load so that refreshing the browser
picks up new eval outputs without restarting the server.
"""
def __init__(
self,
workspace: Path,
skill_name: str,
feedback_path: Path,
previous: dict[str, dict],
benchmark_path: Path | None,
*args,
**kwargs,
):
self.workspace = workspace
self.skill_name = skill_name
self.feedback_path = feedback_path
self.previous = previous
self.benchmark_path = benchmark_path
super().__init__(*args, **kwargs)
def do_GET(self) -> None:
if self.path == "/" or self.path == "/index.html":
# Regenerate HTML on each request (re-scans workspace for new outputs)
runs = find_runs(self.workspace)
benchmark = None
if self.benchmark_path and self.benchmark_path.exists():
try:
benchmark = json.loads(self.benchmark_path.read_text())
except (json.JSONDecodeError, OSError):
pass
html = generate_html(runs, self.skill_name, self.previous, benchmark)
content = html.encode("utf-8")
self.send_response(200)
self.send_header("Content-Type", "text/html; charset=utf-8")
self.send_header("Content-Length", str(len(content)))
self.end_headers()
self.wfile.write(content)
elif self.path == "/api/feedback":
data = b"{}"
if self.feedback_path.exists():
data = self.feedback_path.read_bytes()
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(data)))
self.end_headers()
self.wfile.write(data)
else:
self.send_error(404)
def do_POST(self) -> None:
if self.path == "/api/feedback":
length = int(self.headers.get("Content-Length", 0))
body = self.rfile.read(length)
try:
data = json.loads(body)
if not isinstance(data, dict) or "reviews" not in data:
raise ValueError("Expected JSON object with 'reviews' key")
self.feedback_path.write_text(json.dumps(data, indent=2) + "\n")
resp = b'{"ok":true}'
self.send_response(200)
except (json.JSONDecodeError, OSError, ValueError) as e:
resp = json.dumps({"error": str(e)}).encode()
self.send_response(500)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(resp)))
self.end_headers()
self.wfile.write(resp)
else:
self.send_error(404)
def log_message(self, format: str, *args: object) -> None:
# Suppress request logging to keep terminal clean
pass
def main() -> None:
parser = argparse.ArgumentParser(description="Generate and serve eval review")
parser.add_argument("workspace", type=Path, help="Path to workspace directory")
parser.add_argument("--port", "-p", type=int, default=3117, help="Server port (default: 3117)")
parser.add_argument("--skill-name", "-n", type=str, default=None, help="Skill name for header")
parser.add_argument(
"--previous-workspace", type=Path, default=None,
help="Path to previous iteration's workspace (shows old outputs and feedback as context)",
)
parser.add_argument(
"--benchmark", type=Path, default=None,
help="Path to benchmark.json to show in the Benchmark tab",
)
parser.add_argument(
"--static", "-s", type=Path, default=None,
help="Write standalone HTML to this path instead of starting a server",
)
args = parser.parse_args()
workspace = args.workspace.resolve()
if not workspace.is_dir():
print(f"Error: {workspace} is not a directory", file=sys.stderr)
sys.exit(1)
runs = find_runs(workspace)
if not runs:
print(f"No runs found in {workspace}", file=sys.stderr)
sys.exit(1)
skill_name = args.skill_name or workspace.name.replace("-workspace", "")
feedback_path = workspace / "feedback.json"
previous: dict[str, dict] = {}
if args.previous_workspace:
previous = load_previous_iteration(args.previous_workspace.resolve())
benchmark_path = args.benchmark.resolve() if args.benchmark else None
benchmark = None
if benchmark_path and benchmark_path.exists():
try:
benchmark = json.loads(benchmark_path.read_text())
except (json.JSONDecodeError, OSError):
pass
if args.static:
html = generate_html(runs, skill_name, previous, benchmark)
args.static.parent.mkdir(parents=True, exist_ok=True)
args.static.write_text(html)
print(f"\n Static viewer written to: {args.static}\n")
sys.exit(0)
# Kill any existing process on the target port
port = args.port
_kill_port(port)
handler = partial(ReviewHandler, workspace, skill_name, feedback_path, previous, benchmark_path)
try:
server = HTTPServer(("127.0.0.1", port), handler)
except OSError:
# Port still in use after kill attempt — find a free one
server = HTTPServer(("127.0.0.1", 0), handler)
port = server.server_address[1]
url = f"http://localhost:{port}"
print(f"\n Eval Viewer")
print(f" ─────────────────────────────────")
print(f" URL: {url}")
print(f" Workspace: {workspace}")
print(f" Feedback: {feedback_path}")
if previous:
print(f" Previous: {args.previous_workspace} ({len(previous)} runs)")
if benchmark_path:
print(f" Benchmark: {benchmark_path}")
print(f"\n Press Ctrl+C to stop.\n")
webbrowser.open(url)
try:
server.serve_forever()
except KeyboardInterrupt:
print("\nStopped.")
server.server_close()
if __name__ == "__main__":
main()

1325
.agents/skills/skill-creator/eval-viewer/viewer.html Normal file
View File

File diff suppressed because it is too large Load Diff

430
.agents/skills/skill-creator/references/schemas.md Normal file
View File

@@ -0,0 +1,430 @@
# JSON Schemas
This document defines the JSON schemas used by skill-creator.
---
## evals.json
Defines the evals for a skill. Located at `evals/evals.json` within the skill directory.
```json
{
"skill_name": "example-skill",
"evals": [
{
"id": 1,
"prompt": "User's example prompt",
"expected_output": "Description of expected result",
"files": ["evals/files/sample1.pdf"],
"expectations": [
"The output includes X",
"The skill used script Y"
]
}
]
}
```
**Fields:**
- `skill_name`: Name matching the skill's frontmatter
- `evals[].id`: Unique integer identifier
- `evals[].prompt`: The task to execute
- `evals[].expected_output`: Human-readable description of success
- `evals[].files`: Optional list of input file paths (relative to skill root)
- `evals[].expectations`: List of verifiable statements
---
## history.json
Tracks version progression in Improve mode. Located at workspace root.
```json
{
"started_at": "2026-01-15T10:30:00Z",
"skill_name": "pdf",
"current_best": "v2",
"iterations": [
{
"version": "v0",
"parent": null,
"expectation_pass_rate": 0.65,
"grading_result": "baseline",
"is_current_best": false
},
{
"version": "v1",
"parent": "v0",
"expectation_pass_rate": 0.75,
"grading_result": "won",
"is_current_best": false
},
{
"version": "v2",
"parent": "v1",
"expectation_pass_rate": 0.85,
"grading_result": "won",
"is_current_best": true
}
]
}
```
**Fields:**
- `started_at`: ISO timestamp of when improvement started
- `skill_name`: Name of the skill being improved
- `current_best`: Version identifier of the best performer
- `iterations[].version`: Version identifier (v0, v1, ...)
- `iterations[].parent`: Parent version this was derived from
- `iterations[].expectation_pass_rate`: Pass rate from grading
- `iterations[].grading_result`: "baseline", "won", "lost", or "tie"
- `iterations[].is_current_best`: Whether this is the current best version
---
## grading.json
Output from the grader agent. Located at `<run-dir>/grading.json`.
```json
{
"expectations": [
{
"text": "The output includes the name 'John Smith'",
"passed": true,
"evidence": "Found in transcript Step 3: 'Extracted names: John Smith, Sarah Johnson'"
},
{
"text": "The spreadsheet has a SUM formula in cell B10",
"passed": false,
"evidence": "No spreadsheet was created. The output was a text file."
}
],
"summary": {
"passed": 2,
"failed": 1,
"total": 3,
"pass_rate": 0.67
},
"execution_metrics": {
"tool_calls": {
"Read": 5,
"Write": 2,
"Bash": 8
},
"total_tool_calls": 15,
"total_steps": 6,
"errors_encountered": 0,
"output_chars": 12450,
"transcript_chars": 3200
},
"timing": {
"executor_duration_seconds": 165.0,
"grader_duration_seconds": 26.0,
"total_duration_seconds": 191.0
},
"claims": [
{
"claim": "The form has 12 fillable fields",
"type": "factual",
"verified": true,
"evidence": "Counted 12 fields in field_info.json"
}
],
"user_notes_summary": {
"uncertainties": ["Used 2023 data, may be stale"],
"needs_review": [],
"workarounds": ["Fell back to text overlay for non-fillable fields"]
},
"eval_feedback": {
"suggestions": [
{
"assertion": "The output includes the name 'John Smith'",
"reason": "A hallucinated document that mentions the name would also pass"
}
],
"overall": "Assertions check presence but not correctness."
}
}
```
**Fields:**
- `expectations[]`: Graded expectations with evidence
- `summary`: Aggregate pass/fail counts
- `execution_metrics`: Tool usage and output size (from executor's metrics.json)
- `timing`: Wall clock timing (from timing.json)
- `claims`: Extracted and verified claims from the output
- `user_notes_summary`: Issues flagged by the executor
- `eval_feedback`: (optional) Improvement suggestions for the evals, only present when the grader identifies issues worth raising
---
## metrics.json
Output from the executor agent. Located at `<run-dir>/outputs/metrics.json`.
```json
{
"tool_calls": {
"Read": 5,
"Write": 2,
"Bash": 8,
"Edit": 1,
"Glob": 2,
"Grep": 0
},
"total_tool_calls": 18,
"total_steps": 6,
"files_created": ["filled_form.pdf", "field_values.json"],
"errors_encountered": 0,
"output_chars": 12450,
"transcript_chars": 3200
}
```
**Fields:**
- `tool_calls`: Count per tool type
- `total_tool_calls`: Sum of all tool calls
- `total_steps`: Number of major execution steps
- `files_created`: List of output files created
- `errors_encountered`: Number of errors during execution
- `output_chars`: Total character count of output files
- `transcript_chars`: Character count of transcript
---
## timing.json
Wall clock timing for a run. Located at `<run-dir>/timing.json`.
**How to capture:** When a subagent task completes, the task notification includes `total_tokens` and `duration_ms`. Save these immediately — they are not persisted anywhere else and cannot be recovered after the fact.
```json
{
"total_tokens": 84852,
"duration_ms": 23332,
"total_duration_seconds": 23.3,
"executor_start": "2026-01-15T10:30:00Z",
"executor_end": "2026-01-15T10:32:45Z",
"executor_duration_seconds": 165.0,
"grader_start": "2026-01-15T10:32:46Z",
"grader_end": "2026-01-15T10:33:12Z",
"grader_duration_seconds": 26.0
}
```
---
## benchmark.json
Output from Benchmark mode. Located at `benchmarks/<timestamp>/benchmark.json`.
```json
{
"metadata": {
"skill_name": "pdf",
"skill_path": "/path/to/pdf",
"executor_model": "claude-sonnet-4-20250514",
"analyzer_model": "most-capable-model",
"timestamp": "2026-01-15T10:30:00Z",
"evals_run": [1, 2, 3],
"runs_per_configuration": 3
},
"runs": [
{
"eval_id": 1,
"eval_name": "Ocean",
"configuration": "with_skill",
"run_number": 1,
"result": {
"pass_rate": 0.85,
"passed": 6,
"failed": 1,
"total": 7,
"time_seconds": 42.5,
"tokens": 3800,
"tool_calls": 18,
"errors": 0
},
"expectations": [
{"text": "...", "passed": true, "evidence": "..."}
],
"notes": [
"Used 2023 data, may be stale",
"Fell back to text overlay for non-fillable fields"
]
}
],
"run_summary": {
"with_skill": {
"pass_rate": {"mean": 0.85, "stddev": 0.05, "min": 0.80, "max": 0.90},
"time_seconds": {"mean": 45.0, "stddev": 12.0, "min": 32.0, "max": 58.0},
"tokens": {"mean": 3800, "stddev": 400, "min": 3200, "max": 4100}
},
"without_skill": {
"pass_rate": {"mean": 0.35, "stddev": 0.08, "min": 0.28, "max": 0.45},
"time_seconds": {"mean": 32.0, "stddev": 8.0, "min": 24.0, "max": 42.0},
"tokens": {"mean": 2100, "stddev": 300, "min": 1800, "max": 2500}
},
"delta": {
"pass_rate": "+0.50",
"time_seconds": "+13.0",
"tokens": "+1700"
}
},
"notes": [
"Assertion 'Output is a PDF file' passes 100% in both configurations - may not differentiate skill value",
"Eval 3 shows high variance (50% ± 40%) - may be flaky or model-dependent",
"Without-skill runs consistently fail on table extraction expectations",
"Skill adds 13s average execution time but improves pass rate by 50%"
]
}
```
**Fields:**
- `metadata`: Information about the benchmark run
- `skill_name`: Name of the skill
- `timestamp`: When the benchmark was run
- `evals_run`: List of eval names or IDs
- `runs_per_configuration`: Number of runs per config (e.g. 3)
- `runs[]`: Individual run results
- `eval_id`: Numeric eval identifier
- `eval_name`: Human-readable eval name (used as section header in the viewer)
- `configuration`: Must be `"with_skill"` or `"without_skill"` (the viewer uses this exact string for grouping and color coding)
- `run_number`: Integer run number (1, 2, 3...)
- `result`: Nested object with `pass_rate`, `passed`, `total`, `time_seconds`, `tokens`, `errors`
- `run_summary`: Statistical aggregates per configuration
- `with_skill` / `without_skill`: Each contains `pass_rate`, `time_seconds`, `tokens` objects with `mean` and `stddev` fields
- `delta`: Difference strings like `"+0.50"`, `"+13.0"`, `"+1700"`
- `notes`: Freeform observations from the analyzer
**Important:** The viewer reads these field names exactly. Using `config` instead of `configuration`, or putting `pass_rate` at the top level of a run instead of nested under `result`, will cause the viewer to show empty/zero values. Always reference this schema when generating benchmark.json manually.
---
## comparison.json
Output from blind comparator. Located at `<grading-dir>/comparison-N.json`.
```json
{
"winner": "A",
"reasoning": "Output A provides a complete solution with proper formatting and all required fields. Output B is missing the date field and has formatting inconsistencies.",
"rubric": {
"A": {
"content": {
"correctness": 5,
"completeness": 5,
"accuracy": 4
},
"structure": {
"organization": 4,
"formatting": 5,
"usability": 4
},
"content_score": 4.7,
"structure_score": 4.3,
"overall_score": 9.0
},
"B": {
"content": {
"correctness": 3,
"completeness": 2,
"accuracy": 3
},
"structure": {
"organization": 3,
"formatting": 2,
"usability": 3
},
"content_score": 2.7,
"structure_score": 2.7,
"overall_score": 5.4
}
},
"output_quality": {
"A": {
"score": 9,
"strengths": ["Complete solution", "Well-formatted", "All fields present"],
"weaknesses": ["Minor style inconsistency in header"]
},
"B": {
"score": 5,
"strengths": ["Readable output", "Correct basic structure"],
"weaknesses": ["Missing date field", "Formatting inconsistencies", "Partial data extraction"]
}
},
"expectation_results": {
"A": {
"passed": 4,
"total": 5,
"pass_rate": 0.80,
"details": [
{"text": "Output includes name", "passed": true}
]
},
"B": {
"passed": 3,
"total": 5,
"pass_rate": 0.60,
"details": [
{"text": "Output includes name", "passed": true}
]
}
}
}
```
---
## analysis.json
Output from post-hoc analyzer. Located at `<grading-dir>/analysis.json`.
```json
{
"comparison_summary": {
"winner": "A",
"winner_skill": "path/to/winner/skill",
"loser_skill": "path/to/loser/skill",
"comparator_reasoning": "Brief summary of why comparator chose winner"
},
"winner_strengths": [
"Clear step-by-step instructions for handling multi-page documents",
"Included validation script that caught formatting errors"
],
"loser_weaknesses": [
"Vague instruction 'process the document appropriately' led to inconsistent behavior",
"No script for validation, agent had to improvise"
],
"instruction_following": {
"winner": {
"score": 9,
"issues": ["Minor: skipped optional logging step"]
},
"loser": {
"score": 6,
"issues": [
"Did not use the skill's formatting template",
"Invented own approach instead of following step 3"
]
}
},
"improvement_suggestions": [
{
"priority": "high",
"category": "instructions",
"suggestion": "Replace 'process the document appropriately' with explicit steps",
"expected_impact": "Would eliminate ambiguity that caused inconsistent behavior"
}
],
"transcript_insights": {
"winner_execution_pattern": "Read skill -> Followed 5-step process -> Used validation script",
"loser_execution_pattern": "Read skill -> Unclear on approach -> Tried 3 different methods"
}
}
```

401
.agents/skills/skill-creator/scripts/aggregate_benchmark.py Normal file
View File

@@ -0,0 +1,401 @@
#!/usr/bin/env python3
"""
Aggregate individual run results into benchmark summary statistics.
Reads grading.json files from run directories and produces:
- run_summary with mean, stddev, min, max for each metric
- delta between with_skill and without_skill configurations
Usage:
python aggregate_benchmark.py <benchmark_dir>
Example:
python aggregate_benchmark.py benchmarks/2026-01-15T10-30-00/
The script supports two directory layouts:
Workspace layout (from skill-creator iterations):
<benchmark_dir>/
└── eval-N/
├── with_skill/
│ ├── run-1/grading.json
│ └── run-2/grading.json
└── without_skill/
├── run-1/grading.json
└── run-2/grading.json
Legacy layout (with runs/ subdirectory):
<benchmark_dir>/
└── runs/
└── eval-N/
├── with_skill/
│ └── run-1/grading.json
└── without_skill/
└── run-1/grading.json
"""
import argparse
import json
import math
import sys
from datetime import datetime, timezone
from pathlib import Path
def calculate_stats(values: list[float]) -> dict:
"""Calculate mean, stddev, min, max for a list of values."""
if not values:
return {"mean": 0.0, "stddev": 0.0, "min": 0.0, "max": 0.0}
n = len(values)
mean = sum(values) / n
if n > 1:
variance = sum((x - mean) ** 2 for x in values) / (n - 1)
stddev = math.sqrt(variance)
else:
stddev = 0.0
return {
"mean": round(mean, 4),
"stddev": round(stddev, 4),
"min": round(min(values), 4),
"max": round(max(values), 4)
}
def load_run_results(benchmark_dir: Path) -> dict:
"""
Load all run results from a benchmark directory.
Returns dict keyed by config name (e.g. "with_skill"/"without_skill",
or "new_skill"/"old_skill"), each containing a list of run results.
"""
# Support both layouts: eval dirs directly under benchmark_dir, or under runs/
runs_dir = benchmark_dir / "runs"
if runs_dir.exists():
search_dir = runs_dir
elif list(benchmark_dir.glob("eval-*")):
search_dir = benchmark_dir
else:
print(f"No eval directories found in {benchmark_dir} or {benchmark_dir / 'runs'}")
return {}
results: dict[str, list] = {}
for eval_idx, eval_dir in enumerate(sorted(search_dir.glob("eval-*"))):
metadata_path = eval_dir / "eval_metadata.json"
if metadata_path.exists():
try:
with open(metadata_path) as mf:
eval_id = json.load(mf).get("eval_id", eval_idx)
except (json.JSONDecodeError, OSError):
eval_id = eval_idx
else:
try:
eval_id = int(eval_dir.name.split("-")[1])
except ValueError:
eval_id = eval_idx
# Discover config directories dynamically rather than hardcoding names
for config_dir in sorted(eval_dir.iterdir()):
if not config_dir.is_dir():
continue
# Skip non-config directories (inputs, outputs, etc.)
if not list(config_dir.glob("run-*")):
continue
config = config_dir.name
if config not in results:
results[config] = []
for run_dir in sorted(config_dir.glob("run-*")):
run_number = int(run_dir.name.split("-")[1])
grading_file = run_dir / "grading.json"
if not grading_file.exists():
print(f"Warning: grading.json not found in {run_dir}")
continue
try:
with open(grading_file) as f:
grading = json.load(f)
except json.JSONDecodeError as e:
print(f"Warning: Invalid JSON in {grading_file}: {e}")
continue
# Extract metrics
result = {
"eval_id": eval_id,
"run_number": run_number,
"pass_rate": grading.get("summary", {}).get("pass_rate", 0.0),
"passed": grading.get("summary", {}).get("passed", 0),
"failed": grading.get("summary", {}).get("failed", 0),
"total": grading.get("summary", {}).get("total", 0),
}
# Extract timing — check grading.json first, then sibling timing.json
timing = grading.get("timing", {})
result["time_seconds"] = timing.get("total_duration_seconds", 0.0)
timing_file = run_dir / "timing.json"
if result["time_seconds"] == 0.0 and timing_file.exists():
try:
with open(timing_file) as tf:
timing_data = json.load(tf)
result["time_seconds"] = timing_data.get("total_duration_seconds", 0.0)
result["tokens"] = timing_data.get("total_tokens", 0)
except json.JSONDecodeError:
pass
# Extract metrics if available
metrics = grading.get("execution_metrics", {})
result["tool_calls"] = metrics.get("total_tool_calls", 0)
if not result.get("tokens"):
result["tokens"] = metrics.get("output_chars", 0)
result["errors"] = metrics.get("errors_encountered", 0)
# Extract expectations — viewer requires fields: text, passed, evidence
raw_expectations = grading.get("expectations", [])
for exp in raw_expectations:
if "text" not in exp or "passed" not in exp:
print(f"Warning: expectation in {grading_file} missing required fields (text, passed, evidence): {exp}")
result["expectations"] = raw_expectations
# Extract notes from user_notes_summary
notes_summary = grading.get("user_notes_summary", {})
notes = []
notes.extend(notes_summary.get("uncertainties", []))
notes.extend(notes_summary.get("needs_review", []))
notes.extend(notes_summary.get("workarounds", []))
result["notes"] = notes
results[config].append(result)
return results
def aggregate_results(results: dict) -> dict:
"""
Aggregate run results into summary statistics.
Returns run_summary with stats for each configuration and delta.
"""
run_summary = {}
configs = list(results.keys())
for config in configs:
runs = results.get(config, [])
if not runs:
run_summary[config] = {
"pass_rate": {"mean": 0.0, "stddev": 0.0, "min": 0.0, "max": 0.0},
"time_seconds": {"mean": 0.0, "stddev": 0.0, "min": 0.0, "max": 0.0},
"tokens": {"mean": 0, "stddev": 0, "min": 0, "max": 0}
}
continue
pass_rates = [r["pass_rate"] for r in runs]
times = [r["time_seconds"] for r in runs]
tokens = [r.get("tokens", 0) for r in runs]
run_summary[config] = {
"pass_rate": calculate_stats(pass_rates),
"time_seconds": calculate_stats(times),
"tokens": calculate_stats(tokens)
}
# Calculate delta between the first two configs (if two exist)
if len(configs) >= 2:
primary = run_summary.get(configs[0], {})
baseline = run_summary.get(configs[1], {})
else:
primary = run_summary.get(configs[0], {}) if configs else {}
baseline = {}
delta_pass_rate = primary.get("pass_rate", {}).get("mean", 0) - baseline.get("pass_rate", {}).get("mean", 0)
delta_time = primary.get("time_seconds", {}).get("mean", 0) - baseline.get("time_seconds", {}).get("mean", 0)
delta_tokens = primary.get("tokens", {}).get("mean", 0) - baseline.get("tokens", {}).get("mean", 0)
run_summary["delta"] = {
"pass_rate": f"{delta_pass_rate:+.2f}",
"time_seconds": f"{delta_time:+.1f}",
"tokens": f"{delta_tokens:+.0f}"
}
return run_summary
def generate_benchmark(benchmark_dir: Path, skill_name: str = "", skill_path: str = "") -> dict:
"""
Generate complete benchmark.json from run results.
"""
results = load_run_results(benchmark_dir)
run_summary = aggregate_results(results)
# Build runs array for benchmark.json
runs = []
for config in results:
for result in results[config]:
runs.append({
"eval_id": result["eval_id"],
"configuration": config,
"run_number": result["run_number"],
"result": {
"pass_rate": result["pass_rate"],
"passed": result["passed"],
"failed": result["failed"],
"total": result["total"],
"time_seconds": result["time_seconds"],
"tokens": result.get("tokens", 0),
"tool_calls": result.get("tool_calls", 0),
"errors": result.get("errors", 0)
},
"expectations": result["expectations"],
"notes": result["notes"]
})
# Determine eval IDs from results
eval_ids = sorted(set(
r["eval_id"]
for config in results.values()
for r in config
))
benchmark = {
"metadata": {
"skill_name": skill_name or "<skill-name>",
"skill_path": skill_path or "<path/to/skill>",
"executor_model": "<model-name>",
"analyzer_model": "<model-name>",
"timestamp": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
"evals_run": eval_ids,
"runs_per_configuration": 3
},
"runs": runs,
"run_summary": run_summary,
"notes": [] # To be filled by analyzer
}
return benchmark
def generate_markdown(benchmark: dict) -> str:
"""Generate human-readable benchmark.md from benchmark data."""
metadata = benchmark["metadata"]
run_summary = benchmark["run_summary"]
# Determine config names (excluding "delta")
configs = [k for k in run_summary if k != "delta"]
config_a = configs[0] if len(configs) >= 1 else "config_a"
config_b = configs[1] if len(configs) >= 2 else "config_b"
label_a = config_a.replace("_", " ").title()
label_b = config_b.replace("_", " ").title()
lines = [
f"# Skill Benchmark: {metadata['skill_name']}",
"",
f"**Model**: {metadata['executor_model']}",
f"**Date**: {metadata['timestamp']}",
f"**Evals**: {', '.join(map(str, metadata['evals_run']))} ({metadata['runs_per_configuration']} runs each per configuration)",
"",
"## Summary",
"",
f"| Metric | {label_a} | {label_b} | Delta |",
"|--------|------------|---------------|-------|",
]
a_summary = run_summary.get(config_a, {})
b_summary = run_summary.get(config_b, {})
delta = run_summary.get("delta", {})
# Format pass rate
a_pr = a_summary.get("pass_rate", {})
b_pr = b_summary.get("pass_rate", {})
lines.append(f"| Pass Rate | {a_pr.get('mean', 0)*100:.0f}% ± {a_pr.get('stddev', 0)*100:.0f}% | {b_pr.get('mean', 0)*100:.0f}% ± {b_pr.get('stddev', 0)*100:.0f}% | {delta.get('pass_rate', '—')} |")
# Format time
a_time = a_summary.get("time_seconds", {})
b_time = b_summary.get("time_seconds", {})
lines.append(f"| Time | {a_time.get('mean', 0):.1f}s ± {a_time.get('stddev', 0):.1f}s | {b_time.get('mean', 0):.1f}s ± {b_time.get('stddev', 0):.1f}s | {delta.get('time_seconds', '—')}s |")
# Format tokens
a_tokens = a_summary.get("tokens", {})
b_tokens = b_summary.get("tokens", {})
lines.append(f"| Tokens | {a_tokens.get('mean', 0):.0f} ± {a_tokens.get('stddev', 0):.0f} | {b_tokens.get('mean', 0):.0f} ± {b_tokens.get('stddev', 0):.0f} | {delta.get('tokens', '—')} |")
# Notes section
if benchmark.get("notes"):
lines.extend([
"",
"## Notes",
""
])
for note in benchmark["notes"]:
lines.append(f"- {note}")
return "\n".join(lines)
def main():
parser = argparse.ArgumentParser(
description="Aggregate benchmark run results into summary statistics"
)
parser.add_argument(
"benchmark_dir",
type=Path,
help="Path to the benchmark directory"
)
parser.add_argument(
"--skill-name",
default="",
help="Name of the skill being benchmarked"
)
parser.add_argument(
"--skill-path",
default="",
help="Path to the skill being benchmarked"
)
parser.add_argument(
"--output", "-o",
type=Path,
help="Output path for benchmark.json (default: <benchmark_dir>/benchmark.json)"
)
args = parser.parse_args()
if not args.benchmark_dir.exists():
print(f"Directory not found: {args.benchmark_dir}")
sys.exit(1)
# Generate benchmark
benchmark = generate_benchmark(args.benchmark_dir, args.skill_name, args.skill_path)
# Determine output paths
output_json = args.output or (args.benchmark_dir / "benchmark.json")
output_md = output_json.with_suffix(".md")
# Write benchmark.json
with open(output_json, "w") as f:
json.dump(benchmark, f, indent=2)
print(f"Generated: {output_json}")
# Write benchmark.md
markdown = generate_markdown(benchmark)
with open(output_md, "w") as f:
f.write(markdown)
print(f"Generated: {output_md}")
# Print summary
run_summary = benchmark["run_summary"]
configs = [k for k in run_summary if k != "delta"]
delta = run_summary.get("delta", {})
print(f"\nSummary:")
for config in configs:
pr = run_summary[config]["pass_rate"]["mean"]
label = config.replace("_", " ").title()
print(f" {label}: {pr*100:.1f}% pass rate")
print(f" Delta: {delta.get('pass_rate', '—')}")
if __name__ == "__main__":
main()

326
.agents/skills/skill-creator/scripts/generate_report.py Normal file
View File

@@ -0,0 +1,326 @@
#!/usr/bin/env python3
"""Generate an HTML report from run_loop.py output.
Takes the JSON output from run_loop.py and generates a visual HTML report
showing each description attempt with check/x for each test case.
Distinguishes between train and test queries.
"""
import argparse
import html
import json
import sys
from pathlib import Path
def generate_html(data: dict, auto_refresh: bool = False, skill_name: str = "") -> str:
"""Generate HTML report from loop output data. If auto_refresh is True, adds a meta refresh tag."""
history = data.get("history", [])
holdout = data.get("holdout", 0)
title_prefix = html.escape(skill_name + " \u2014 ") if skill_name else ""
# Get all unique queries from train and test sets, with should_trigger info
train_queries: list[dict] = []
test_queries: list[dict] = []
if history:
for r in history[0].get("train_results", history[0].get("results", [])):
train_queries.append({"query": r["query"], "should_trigger": r.get("should_trigger", True)})
if history[0].get("test_results"):
for r in history[0].get("test_results", []):
test_queries.append({"query": r["query"], "should_trigger": r.get("should_trigger", True)})
refresh_tag = ' <meta http-equiv="refresh" content="5">\n' if auto_refresh else ""
html_parts = ["""<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
""" + refresh_tag + """ <title>""" + title_prefix + """Skill Description Optimization</title>
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
<style>
body {
font-family: 'Lora', Georgia, serif;
max-width: 100%;
margin: 0 auto;
padding: 20px;
background: #faf9f5;
color: #141413;
}
h1 { font-family: 'Poppins', sans-serif; color: #141413; }
.explainer {
background: white;
padding: 15px;
border-radius: 6px;
margin-bottom: 20px;
border: 1px solid #e8e6dc;
color: #b0aea5;
font-size: 0.875rem;
line-height: 1.6;
}
.summary {
background: white;
padding: 15px;
border-radius: 6px;
margin-bottom: 20px;
border: 1px solid #e8e6dc;
}
.summary p { margin: 5px 0; }
.best { color: #788c5d; font-weight: bold; }
.table-container {
overflow-x: auto;
width: 100%;
}
table {
border-collapse: collapse;
background: white;
border: 1px solid #e8e6dc;
border-radius: 6px;
font-size: 12px;
min-width: 100%;
}
th, td {
padding: 8px;
text-align: left;
border: 1px solid #e8e6dc;
white-space: normal;
word-wrap: break-word;
}
th {
font-family: 'Poppins', sans-serif;
background: #141413;
color: #faf9f5;
font-weight: 500;
}
th.test-col {
background: #6a9bcc;
}
th.query-col { min-width: 200px; }
td.description {
font-family: monospace;
font-size: 11px;
word-wrap: break-word;
max-width: 400px;
}
td.result {
text-align: center;
font-size: 16px;
min-width: 40px;
}
td.test-result {
background: #f0f6fc;
}
.pass { color: #788c5d; }
.fail { color: #c44; }
.rate {
font-size: 9px;
color: #b0aea5;
display: block;
}
tr:hover { background: #faf9f5; }
.score {
display: inline-block;
padding: 2px 6px;
border-radius: 4px;
font-weight: bold;
font-size: 11px;
}
.score-good { background: #eef2e8; color: #788c5d; }
.score-ok { background: #fef3c7; color: #d97706; }
.score-bad { background: #fceaea; color: #c44; }
.train-label { color: #b0aea5; font-size: 10px; }
.test-label { color: #6a9bcc; font-size: 10px; font-weight: bold; }
.best-row { background: #f5f8f2; }
th.positive-col { border-bottom: 3px solid #788c5d; }
th.negative-col { border-bottom: 3px solid #c44; }
th.test-col.positive-col { border-bottom: 3px solid #788c5d; }
th.test-col.negative-col { border-bottom: 3px solid #c44; }
.legend { font-family: 'Poppins', sans-serif; display: flex; gap: 20px; margin-bottom: 10px; font-size: 13px; align-items: center; }
.legend-item { display: flex; align-items: center; gap: 6px; }
.legend-swatch { width: 16px; height: 16px; border-radius: 3px; display: inline-block; }
.swatch-positive { background: #141413; border-bottom: 3px solid #788c5d; }
.swatch-negative { background: #141413; border-bottom: 3px solid #c44; }
.swatch-test { background: #6a9bcc; }
.swatch-train { background: #141413; }
</style>
</head>
<body>
<h1>""" + title_prefix + """Skill Description Optimization</h1>
<div class="explainer">
<strong>Optimizing your skill's description.</strong> This page updates automatically as Claude tests different versions of your skill's description. Each row is an iteration — a new description attempt. The columns show test queries: green checkmarks mean the skill triggered correctly (or correctly didn't trigger), red crosses mean it got it wrong. The "Train" score shows performance on queries used to improve the description; the "Test" score shows performance on held-out queries the optimizer hasn't seen. When it's done, Claude will apply the best-performing description to your skill.
</div>
"""]
# Summary section
best_test_score = data.get('best_test_score')
best_train_score = data.get('best_train_score')
html_parts.append(f"""
<div class="summary">
<p><strong>Original:</strong> {html.escape(data.get('original_description', 'N/A'))}</p>
<p class="best"><strong>Best:</strong> {html.escape(data.get('best_description', 'N/A'))}</p>
<p><strong>Best Score:</strong> {data.get('best_score', 'N/A')} {'(test)' if best_test_score else '(train)'}</p>
<p><strong>Iterations:</strong> {data.get('iterations_run', 0)} | <strong>Train:</strong> {data.get('train_size', '?')} | <strong>Test:</strong> {data.get('test_size', '?')}</p>
</div>
""")
# Legend
html_parts.append("""
<div class="legend">
<span style="font-weight:600">Query columns:</span>
<span class="legend-item"><span class="legend-swatch swatch-positive"></span> Should trigger</span>
<span class="legend-item"><span class="legend-swatch swatch-negative"></span> Should NOT trigger</span>
<span class="legend-item"><span class="legend-swatch swatch-train"></span> Train</span>
<span class="legend-item"><span class="legend-swatch swatch-test"></span> Test</span>
</div>
""")
# Table header
html_parts.append("""
<div class="table-container">
<table>
<thead>
<tr>
<th>Iter</th>
<th>Train</th>
<th>Test</th>
<th class="query-col">Description</th>
""")
# Add column headers for train queries
for qinfo in train_queries:
polarity = "positive-col" if qinfo["should_trigger"] else "negative-col"
html_parts.append(f' <th class="{polarity}">{html.escape(qinfo["query"])}</th>\n')
# Add column headers for test queries (different color)
for qinfo in test_queries:
polarity = "positive-col" if qinfo["should_trigger"] else "negative-col"
html_parts.append(f' <th class="test-col {polarity}">{html.escape(qinfo["query"])}</th>\n')
html_parts.append(""" </tr>
</thead>
<tbody>
""")
# Find best iteration for highlighting
if test_queries:
best_iter = max(history, key=lambda h: h.get("test_passed") or 0).get("iteration")
else:
best_iter = max(history, key=lambda h: h.get("train_passed", h.get("passed", 0))).get("iteration")
# Add rows for each iteration
for h in history:
iteration = h.get("iteration", "?")
train_passed = h.get("train_passed", h.get("passed", 0))
train_total = h.get("train_total", h.get("total", 0))
test_passed = h.get("test_passed")
test_total = h.get("test_total")
description = h.get("description", "")
train_results = h.get("train_results", h.get("results", []))
test_results = h.get("test_results", [])
# Create lookups for results by query
train_by_query = {r["query"]: r for r in train_results}
test_by_query = {r["query"]: r for r in test_results} if test_results else {}
# Compute aggregate correct/total runs across all retries
def aggregate_runs(results: list[dict]) -> tuple[int, int]:
correct = 0
total = 0
for r in results:
runs = r.get("runs", 0)
triggers = r.get("triggers", 0)
total += runs
if r.get("should_trigger", True):
correct += triggers
else:
correct += runs - triggers
return correct, total
train_correct, train_runs = aggregate_runs(train_results)
test_correct, test_runs = aggregate_runs(test_results)
# Determine score classes
def score_class(correct: int, total: int) -> str:
if total > 0:
ratio = correct / total
if ratio >= 0.8:
return "score-good"
elif ratio >= 0.5:
return "score-ok"
return "score-bad"
train_class = score_class(train_correct, train_runs)
test_class = score_class(test_correct, test_runs)
row_class = "best-row" if iteration == best_iter else ""
html_parts.append(f""" <tr class="{row_class}">
<td>{iteration}</td>
<td><span class="score {train_class}">{train_correct}/{train_runs}</span></td>
<td><span class="score {test_class}">{test_correct}/{test_runs}</span></td>
<td class="description">{html.escape(description)}</td>
""")
# Add result for each train query
for qinfo in train_queries:
r = train_by_query.get(qinfo["query"], {})
did_pass = r.get("pass", False)
triggers = r.get("triggers", 0)
runs = r.get("runs", 0)
icon = "✓" if did_pass else "✗"
css_class = "pass" if did_pass else "fail"
html_parts.append(f' <td class="result {css_class}">{icon}<span class="rate">{triggers}/{runs}</span></td>\n')
# Add result for each test query (with different background)
for qinfo in test_queries:
r = test_by_query.get(qinfo["query"], {})
did_pass = r.get("pass", False)
triggers = r.get("triggers", 0)
runs = r.get("runs", 0)
icon = "✓" if did_pass else "✗"
css_class = "pass" if did_pass else "fail"
html_parts.append(f' <td class="result test-result {css_class}">{icon}<span class="rate">{triggers}/{runs}</span></td>\n')
html_parts.append(" </tr>\n")
html_parts.append(""" </tbody>
</table>
</div>
""")
html_parts.append("""
</body>
</html>
""")
return "".join(html_parts)
def main():
parser = argparse.ArgumentParser(description="Generate HTML report from run_loop output")
parser.add_argument("input", help="Path to JSON output from run_loop.py (or - for stdin)")
parser.add_argument("-o", "--output", default=None, help="Output HTML file (default: stdout)")
parser.add_argument("--skill-name", default="", help="Skill name to include in the report title")
args = parser.parse_args()
if args.input == "-":
data = json.load(sys.stdin)
else:
data = json.loads(Path(args.input).read_text())
html_output = generate_html(data, skill_name=args.skill_name)
if args.output:
Path(args.output).write_text(html_output)
print(f"Report written to {args.output}", file=sys.stderr)
else:
print(html_output)
if __name__ == "__main__":
main()

248
.agents/skills/skill-creator/scripts/improve_description.py Normal file
View File

@@ -0,0 +1,248 @@
#!/usr/bin/env python3
"""Improve a skill description based on eval results.
Takes eval results (from run_eval.py) and generates an improved description
using Claude with extended thinking.
"""
import argparse
import json
import re
import sys
from pathlib import Path
import anthropic
from scripts.utils import parse_skill_md
def improve_description(
client: anthropic.Anthropic,
skill_name: str,
skill_content: str,
current_description: str,
eval_results: dict,
history: list[dict],
model: str,
test_results: dict | None = None,
log_dir: Path | None = None,
iteration: int | None = None,
) -> str:
"""Call Claude to improve the description based on eval results."""
failed_triggers = [
r for r in eval_results["results"]
if r["should_trigger"] and not r["pass"]
]
false_triggers = [
r for r in eval_results["results"]
if not r["should_trigger"] and not r["pass"]
]
# Build scores summary
train_score = f"{eval_results['summary']['passed']}/{eval_results['summary']['total']}"
if test_results:
test_score = f"{test_results['summary']['passed']}/{test_results['summary']['total']}"
scores_summary = f"Train: {train_score}, Test: {test_score}"
else:
scores_summary = f"Train: {train_score}"
prompt = f"""You are optimizing a skill description for a Claude Code skill called "{skill_name}". A "skill" is sort of like a prompt, but with progressive disclosure -- there's a title and description that Claude sees when deciding whether to use the skill, and then if it does use the skill, it reads the .md file which has lots more details and potentially links to other resources in the skill folder like helper files and scripts and additional documentation or examples.
The description appears in Claude's "available_skills" list. When a user sends a query, Claude decides whether to invoke the skill based solely on the title and on this description. Your goal is to write a description that triggers for relevant queries, and doesn't trigger for irrelevant ones.
Here's the current description:
<current_description>
"{current_description}"
</current_description>
Current scores ({scores_summary}):
<scores_summary>
"""
if failed_triggers:
prompt += "FAILED TO TRIGGER (should have triggered but didn't):\n"
for r in failed_triggers:
prompt += f' - "{r["query"]}" (triggered {r["triggers"]}/{r["runs"]} times)\n'
prompt += "\n"
if false_triggers:
prompt += "FALSE TRIGGERS (triggered but shouldn't have):\n"
for r in false_triggers:
prompt += f' - "{r["query"]}" (triggered {r["triggers"]}/{r["runs"]} times)\n'
prompt += "\n"
if history:
prompt += "PREVIOUS ATTEMPTS (do NOT repeat these — try something structurally different):\n\n"
for h in history:
train_s = f"{h.get('train_passed', h.get('passed', 0))}/{h.get('train_total', h.get('total', 0))}"
test_s = f"{h.get('test_passed', '?')}/{h.get('test_total', '?')}" if h.get('test_passed') is not None else None
score_str = f"train={train_s}" + (f", test={test_s}" if test_s else "")
prompt += f'<attempt {score_str}>\n'
prompt += f'Description: "{h["description"]}"\n'
if "results" in h:
prompt += "Train results:\n"
for r in h["results"]:
status = "PASS" if r["pass"] else "FAIL"
prompt += f' [{status}] "{r["query"][:80]}" (triggered {r["triggers"]}/{r["runs"]})\n'
if h.get("note"):
prompt += f'Note: {h["note"]}\n'
prompt += "</attempt>\n\n"
prompt += f"""</scores_summary>
Skill content (for context on what the skill does):
<skill_content>
{skill_content}
</skill_content>
Based on the failures, write a new and improved description that is more likely to trigger correctly. When I say "based on the failures", it's a bit of a tricky line to walk because we don't want to overfit to the specific cases you're seeing. So what I DON'T want you to do is produce an ever-expanding list of specific queries that this skill should or shouldn't trigger for. Instead, try to generalize from the failures to broader categories of user intent and situations where this skill would be useful or not useful. The reason for this is twofold:
1. Avoid overfitting
2. The list might get loooong and it's injected into ALL queries and there might be a lot of skills, so we don't want to blow too much space on any given description.
Concretely, your description should not be more than about 100-200 words, even if that comes at the cost of accuracy.
Here are some tips that we've found to work well in writing these descriptions:
- The skill should be phrased in the imperative -- "Use this skill for" rather than "this skill does"
- The skill description should focus on the user's intent, what they are trying to achieve, vs. the implementation details of how the skill works.
- The description competes with other skills for Claude's attention — make it distinctive and immediately recognizable.
- If you're getting lots of failures after repeated attempts, change things up. Try different sentence structures or wordings.
I'd encourage you to be creative and mix up the style in different iterations since you'll have multiple opportunities to try different approaches and we'll just grab the highest-scoring one at the end.
Please respond with only the new description text in <new_description> tags, nothing else."""
response = client.messages.create(
model=model,
max_tokens=16000,
thinking={
"type": "enabled",
"budget_tokens": 10000,
},
messages=[{"role": "user", "content": prompt}],
)
# Extract thinking and text from response
thinking_text = ""
text = ""
for block in response.content:
if block.type == "thinking":
thinking_text = block.thinking
elif block.type == "text":
text = block.text
# Parse out the <new_description> tags
match = re.search(r"<new_description>(.*?)</new_description>", text, re.DOTALL)
description = match.group(1).strip().strip('"') if match else text.strip().strip('"')
# Log the transcript
transcript: dict = {
"iteration": iteration,
"prompt": prompt,
"thinking": thinking_text,
"response": text,
"parsed_description": description,
"char_count": len(description),
"over_limit": len(description) > 1024,
}
# If over 1024 chars, ask the model to shorten it
if len(description) > 1024:
shorten_prompt = f"Your description is {len(description)} characters, which exceeds the hard 1024 character limit. Please rewrite it to be under 1024 characters while preserving the most important trigger words and intent coverage. Respond with only the new description in <new_description> tags."
shorten_response = client.messages.create(
model=model,
max_tokens=16000,
thinking={
"type": "enabled",
"budget_tokens": 10000,
},
messages=[
{"role": "user", "content": prompt},
{"role": "assistant", "content": text},
{"role": "user", "content": shorten_prompt},
],
)
shorten_thinking = ""
shorten_text = ""
for block in shorten_response.content:
if block.type == "thinking":
shorten_thinking = block.thinking
elif block.type == "text":
shorten_text = block.text
match = re.search(r"<new_description>(.*?)</new_description>", shorten_text, re.DOTALL)
shortened = match.group(1).strip().strip('"') if match else shorten_text.strip().strip('"')
transcript["rewrite_prompt"] = shorten_prompt
transcript["rewrite_thinking"] = shorten_thinking
transcript["rewrite_response"] = shorten_text
transcript["rewrite_description"] = shortened
transcript["rewrite_char_count"] = len(shortened)
description = shortened
transcript["final_description"] = description
if log_dir:
log_dir.mkdir(parents=True, exist_ok=True)
log_file = log_dir / f"improve_iter_{iteration or 'unknown'}.json"
log_file.write_text(json.dumps(transcript, indent=2))
return description
def main():
parser = argparse.ArgumentParser(description="Improve a skill description based on eval results")
parser.add_argument("--eval-results", required=True, help="Path to eval results JSON (from run_eval.py)")
parser.add_argument("--skill-path", required=True, help="Path to skill directory")
parser.add_argument("--history", default=None, help="Path to history JSON (previous attempts)")
parser.add_argument("--model", required=True, help="Model for improvement")
parser.add_argument("--verbose", action="store_true", help="Print thinking to stderr")
args = parser.parse_args()
skill_path = Path(args.skill_path)
if not (skill_path / "SKILL.md").exists():
print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
sys.exit(1)
eval_results = json.loads(Path(args.eval_results).read_text())
history = []
if args.history:
history = json.loads(Path(args.history).read_text())
name, _, content = parse_skill_md(skill_path)
current_description = eval_results["description"]
if args.verbose:
print(f"Current: {current_description}", file=sys.stderr)
print(f"Score: {eval_results['summary']['passed']}/{eval_results['summary']['total']}", file=sys.stderr)
client = anthropic.Anthropic()
new_description = improve_description(
client=client,
skill_name=name,
skill_content=content,
current_description=current_description,
eval_results=eval_results,
history=history,
model=args.model,
)
if args.verbose:
print(f"Improved: {new_description}", file=sys.stderr)
# Output as JSON with both the new description and updated history
output = {
"description": new_description,
"history": history + [{
"description": current_description,
"passed": eval_results["summary"]["passed"],
"failed": eval_results["summary"]["failed"],
"total": eval_results["summary"]["total"],
"results": eval_results["results"],
}],
}
print(json.dumps(output, indent=2))
if __name__ == "__main__":
main()

136
.agents/skills/skill-creator/scripts/package_skill.py Normal file
View File

@@ -0,0 +1,136 @@
#!/usr/bin/env python3
"""
Skill Packager - Creates a distributable .skill file of a skill folder
Usage:
python utils/package_skill.py <path/to/skill-folder> [output-directory]
Example:
python utils/package_skill.py skills/public/my-skill
python utils/package_skill.py skills/public/my-skill ./dist
"""
import fnmatch
import sys
import zipfile
from pathlib import Path
from scripts.quick_validate import validate_skill
# Patterns to exclude when packaging skills.
EXCLUDE_DIRS = {"__pycache__", "node_modules"}
EXCLUDE_GLOBS = {"*.pyc"}
EXCLUDE_FILES = {".DS_Store"}
# Directories excluded only at the skill root (not when nested deeper).
ROOT_EXCLUDE_DIRS = {"evals"}
def should_exclude(rel_path: Path) -> bool:
"""Check if a path should be excluded from packaging."""
parts = rel_path.parts
if any(part in EXCLUDE_DIRS for part in parts):
return True
# rel_path is relative to skill_path.parent, so parts[0] is the skill
# folder name and parts[1] (if present) is the first subdir.
if len(parts) > 1 and parts[1] in ROOT_EXCLUDE_DIRS:
return True
name = rel_path.name
if name in EXCLUDE_FILES:
return True
return any(fnmatch.fnmatch(name, pat) for pat in EXCLUDE_GLOBS)
def package_skill(skill_path, output_dir=None):
"""
Package a skill folder into a .skill file.
Args:
skill_path: Path to the skill folder
output_dir: Optional output directory for the .skill file (defaults to current directory)
Returns:
Path to the created .skill file, or None if error
"""
skill_path = Path(skill_path).resolve()
# Validate skill folder exists
if not skill_path.exists():
print(f"❌ Error: Skill folder not found: {skill_path}")
return None
if not skill_path.is_dir():
print(f"❌ Error: Path is not a directory: {skill_path}")
return None
# Validate SKILL.md exists
skill_md = skill_path / "SKILL.md"
if not skill_md.exists():
print(f"❌ Error: SKILL.md not found in {skill_path}")
return None
# Run validation before packaging
print("🔍 Validating skill...")
valid, message = validate_skill(skill_path)
if not valid:
print(f"❌ Validation failed: {message}")
print(" Please fix the validation errors before packaging.")
return None
print(f"✅ {message}\n")
# Determine output location
skill_name = skill_path.name
if output_dir:
output_path = Path(output_dir).resolve()
output_path.mkdir(parents=True, exist_ok=True)
else:
output_path = Path.cwd()
skill_filename = output_path / f"{skill_name}.skill"
# Create the .skill file (zip format)
try:
with zipfile.ZipFile(skill_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
# Walk through the skill directory, excluding build artifacts
for file_path in skill_path.rglob('*'):
if not file_path.is_file():
continue
arcname = file_path.relative_to(skill_path.parent)
if should_exclude(arcname):
print(f" Skipped: {arcname}")
continue
zipf.write(file_path, arcname)
print(f" Added: {arcname}")
print(f"\n✅ Successfully packaged skill to: {skill_filename}")
return skill_filename
except Exception as e:
print(f"❌ Error creating .skill file: {e}")
return None
def main():
if len(sys.argv) < 2:
print("Usage: python utils/package_skill.py <path/to/skill-folder> [output-directory]")
print("\nExample:")
print(" python utils/package_skill.py skills/public/my-skill")
print(" python utils/package_skill.py skills/public/my-skill ./dist")
sys.exit(1)
skill_path = sys.argv[1]
output_dir = sys.argv[2] if len(sys.argv) > 2 else None
print(f"📦 Packaging skill: {skill_path}")
if output_dir:
print(f" Output directory: {output_dir}")
print()
result = package_skill(skill_path, output_dir)
if result:
sys.exit(0)
else:
sys.exit(1)
if __name__ == "__main__":
main()

103
.agents/skills/skill-creator/scripts/quick_validate.py Normal file
View File

@@ -0,0 +1,103 @@
#!/usr/bin/env python3
"""
Quick validation script for skills - minimal version
"""
import sys
import os
import re
import yaml
from pathlib import Path
def validate_skill(skill_path):
"""Basic validation of a skill"""
skill_path = Path(skill_path)
# Check SKILL.md exists
skill_md = skill_path / 'SKILL.md'
if not skill_md.exists():
return False, "SKILL.md not found"
# Read and validate frontmatter
content = skill_md.read_text()
if not content.startswith('---'):
return False, "No YAML frontmatter found"
# Extract frontmatter
match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
if not match:
return False, "Invalid frontmatter format"
frontmatter_text = match.group(1)
# Parse YAML frontmatter
try:
frontmatter = yaml.safe_load(frontmatter_text)
if not isinstance(frontmatter, dict):
return False, "Frontmatter must be a YAML dictionary"
except yaml.YAMLError as e:
return False, f"Invalid YAML in frontmatter: {e}"
# Define allowed properties
ALLOWED_PROPERTIES = {'name', 'description', 'license', 'allowed-tools', 'metadata', 'compatibility'}
# Check for unexpected properties (excluding nested keys under metadata)
unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES
if unexpected_keys:
return False, (
f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}. "
f"Allowed properties are: {', '.join(sorted(ALLOWED_PROPERTIES))}"
)
# Check required fields
if 'name' not in frontmatter:
return False, "Missing 'name' in frontmatter"
if 'description' not in frontmatter:
return False, "Missing 'description' in frontmatter"
# Extract name for validation
name = frontmatter.get('name', '')
if not isinstance(name, str):
return False, f"Name must be a string, got {type(name).__name__}"
name = name.strip()
if name:
# Check naming convention (kebab-case: lowercase with hyphens)
if not re.match(r'^[a-z0-9-]+$', name):
return False, f"Name '{name}' should be kebab-case (lowercase letters, digits, and hyphens only)"
if name.startswith('-') or name.endswith('-') or '--' in name:
return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens"
# Check name length (max 64 characters per spec)
if len(name) > 64:
return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters."
# Extract and validate description
description = frontmatter.get('description', '')
if not isinstance(description, str):
return False, f"Description must be a string, got {type(description).__name__}"
description = description.strip()
if description:
# Check for angle brackets
if '<' in description or '>' in description:
return False, "Description cannot contain angle brackets (< or >)"
# Check description length (max 1024 characters per spec)
if len(description) > 1024:
return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters."
# Validate compatibility field if present (optional)
compatibility = frontmatter.get('compatibility', '')
if compatibility:
if not isinstance(compatibility, str):
return False, f"Compatibility must be a string, got {type(compatibility).__name__}"
if len(compatibility) > 500:
return False, f"Compatibility is too long ({len(compatibility)} characters). Maximum is 500 characters."
return True, "Skill is valid!"
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python quick_validate.py <skill_directory>")
sys.exit(1)
valid, message = validate_skill(sys.argv[1])
print(message)
sys.exit(0 if valid else 1)

310
.agents/skills/skill-creator/scripts/run_eval.py Normal file
View File

@@ -0,0 +1,310 @@
#!/usr/bin/env python3
"""Run trigger evaluation for a skill description.
Tests whether a skill's description causes Claude to trigger (read the skill)
for a set of queries. Outputs results as JSON.
"""
import argparse
import json
import os
import select
import subprocess
import sys
import time
import uuid
from concurrent.futures import ProcessPoolExecutor, as_completed
from pathlib import Path
from scripts.utils import parse_skill_md
def find_project_root() -> Path:
"""Find the project root by walking up from cwd looking for .claude/.
Mimics how Claude Code discovers its project root, so the command file
we create ends up where claude -p will look for it.
"""
current = Path.cwd()
for parent in [current, *current.parents]:
if (parent / ".claude").is_dir():
return parent
return current
def run_single_query(
query: str,
skill_name: str,
skill_description: str,
timeout: int,
project_root: str,
model: str | None = None,
) -> bool:
"""Run a single query and return whether the skill was triggered.
Creates a command file in .claude/commands/ so it appears in Claude's
available_skills list, then runs `claude -p` with the raw query.
Uses --include-partial-messages to detect triggering early from
stream events (content_block_start) rather than waiting for the
full assistant message, which only arrives after tool execution.
"""
unique_id = uuid.uuid4().hex[:8]
clean_name = f"{skill_name}-skill-{unique_id}"
project_commands_dir = Path(project_root) / ".claude" / "commands"
command_file = project_commands_dir / f"{clean_name}.md"
try:
project_commands_dir.mkdir(parents=True, exist_ok=True)
# Use YAML block scalar to avoid breaking on quotes in description
indented_desc = "\n ".join(skill_description.split("\n"))
command_content = (
f"---\n"
f"description: |\n"
f" {indented_desc}\n"
f"---\n\n"
f"# {skill_name}\n\n"
f"This skill handles: {skill_description}\n"
)
command_file.write_text(command_content)
cmd = [
"claude",
"-p", query,
"--output-format", "stream-json",
"--verbose",
"--include-partial-messages",
]
if model:
cmd.extend(["--model", model])
# Remove CLAUDECODE env var to allow nesting claude -p inside a
# Claude Code session. The guard is for interactive terminal conflicts;
# programmatic subprocess usage is safe.
env = {k: v for k, v in os.environ.items() if k != "CLAUDECODE"}
process = subprocess.Popen(
cmd,
stdout=subprocess.PIPE,
stderr=subprocess.DEVNULL,
cwd=project_root,
env=env,
)
triggered = False
start_time = time.time()
buffer = ""
# Track state for stream event detection
pending_tool_name = None
accumulated_json = ""
try:
while time.time() - start_time < timeout:
if process.poll() is not None:
remaining = process.stdout.read()
if remaining:
buffer += remaining.decode("utf-8", errors="replace")
break
ready, _, _ = select.select([process.stdout], [], [], 1.0)
if not ready:
continue
chunk = os.read(process.stdout.fileno(), 8192)
if not chunk:
break
buffer += chunk.decode("utf-8", errors="replace")
while "\n" in buffer:
line, buffer = buffer.split("\n", 1)
line = line.strip()
if not line:
continue
try:
event = json.loads(line)
except json.JSONDecodeError:
continue
# Early detection via stream events
if event.get("type") == "stream_event":
se = event.get("event", {})
se_type = se.get("type", "")
if se_type == "content_block_start":
cb = se.get("content_block", {})
if cb.get("type") == "tool_use":
tool_name = cb.get("name", "")
if tool_name in ("Skill", "Read"):
pending_tool_name = tool_name
accumulated_json = ""
else:
return False
elif se_type == "content_block_delta" and pending_tool_name:
delta = se.get("delta", {})
if delta.get("type") == "input_json_delta":
accumulated_json += delta.get("partial_json", "")
if clean_name in accumulated_json:
return True
elif se_type in ("content_block_stop", "message_stop"):
if pending_tool_name:
return clean_name in accumulated_json
if se_type == "message_stop":
return False
# Fallback: full assistant message
elif event.get("type") == "assistant":
message = event.get("message", {})
for content_item in message.get("content", []):
if content_item.get("type") != "tool_use":
continue
tool_name = content_item.get("name", "")
tool_input = content_item.get("input", {})
if tool_name == "Skill" and clean_name in tool_input.get("skill", ""):
triggered = True
elif tool_name == "Read" and clean_name in tool_input.get("file_path", ""):
triggered = True
return triggered
elif event.get("type") == "result":
return triggered
finally:
# Clean up process on any exit path (return, exception, timeout)
if process.poll() is None:
process.kill()
process.wait()
return triggered
finally:
if command_file.exists():
command_file.unlink()
def run_eval(
eval_set: list[dict],
skill_name: str,
description: str,
num_workers: int,
timeout: int,
project_root: Path,
runs_per_query: int = 1,
trigger_threshold: float = 0.5,
model: str | None = None,
) -> dict:
"""Run the full eval set and return results."""
results = []
with ProcessPoolExecutor(max_workers=num_workers) as executor:
future_to_info = {}
for item in eval_set:
for run_idx in range(runs_per_query):
future = executor.submit(
run_single_query,
item["query"],
skill_name,
description,
timeout,
str(project_root),
model,
)
future_to_info[future] = (item, run_idx)
query_triggers: dict[str, list[bool]] = {}
query_items: dict[str, dict] = {}
for future in as_completed(future_to_info):
item, _ = future_to_info[future]
query = item["query"]
query_items[query] = item
if query not in query_triggers:
query_triggers[query] = []
try:
query_triggers[query].append(future.result())
except Exception as e:
print(f"Warning: query failed: {e}", file=sys.stderr)
query_triggers[query].append(False)
for query, triggers in query_triggers.items():
item = query_items[query]
trigger_rate = sum(triggers) / len(triggers)
should_trigger = item["should_trigger"]
if should_trigger:
did_pass = trigger_rate >= trigger_threshold
else:
did_pass = trigger_rate < trigger_threshold
results.append({
"query": query,
"should_trigger": should_trigger,
"trigger_rate": trigger_rate,
"triggers": sum(triggers),
"runs": len(triggers),
"pass": did_pass,
})
passed = sum(1 for r in results if r["pass"])
total = len(results)
return {
"skill_name": skill_name,
"description": description,
"results": results,
"summary": {
"total": total,
"passed": passed,
"failed": total - passed,
},
}
def main():
parser = argparse.ArgumentParser(description="Run trigger evaluation for a skill description")
parser.add_argument("--eval-set", required=True, help="Path to eval set JSON file")
parser.add_argument("--skill-path", required=True, help="Path to skill directory")
parser.add_argument("--description", default=None, help="Override description to test")
parser.add_argument("--num-workers", type=int, default=10, help="Number of parallel workers")
parser.add_argument("--timeout", type=int, default=30, help="Timeout per query in seconds")
parser.add_argument("--runs-per-query", type=int, default=3, help="Number of runs per query")
parser.add_argument("--trigger-threshold", type=float, default=0.5, help="Trigger rate threshold")
parser.add_argument("--model", default=None, help="Model to use for claude -p (default: user's configured model)")
parser.add_argument("--verbose", action="store_true", help="Print progress to stderr")
args = parser.parse_args()
eval_set = json.loads(Path(args.eval_set).read_text())
skill_path = Path(args.skill_path)
if not (skill_path / "SKILL.md").exists():
print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
sys.exit(1)
name, original_description, content = parse_skill_md(skill_path)
description = args.description or original_description
project_root = find_project_root()
if args.verbose:
print(f"Evaluating: {description}", file=sys.stderr)
output = run_eval(
eval_set=eval_set,
skill_name=name,
description=description,
num_workers=args.num_workers,
timeout=args.timeout,
project_root=project_root,
runs_per_query=args.runs_per_query,
trigger_threshold=args.trigger_threshold,
model=args.model,
)
if args.verbose:
summary = output["summary"]
print(f"Results: {summary['passed']}/{summary['total']} passed", file=sys.stderr)
for r in output["results"]:
status = "PASS" if r["pass"] else "FAIL"
rate_str = f"{r['triggers']}/{r['runs']}"
print(f" [{status}] rate={rate_str} expected={r['should_trigger']}: {r['query'][:70]}", file=sys.stderr)
print(json.dumps(output, indent=2))
if __name__ == "__main__":
main()

332
.agents/skills/skill-creator/scripts/run_loop.py Normal file
View File

@@ -0,0 +1,332 @@
#!/usr/bin/env python3
"""Run the eval + improve loop until all pass or max iterations reached.
Combines run_eval.py and improve_description.py in a loop, tracking history
and returning the best description found. Supports train/test split to prevent
overfitting.
"""
import argparse
import json
import random
import sys
import tempfile
import time
import webbrowser
from pathlib import Path
import anthropic
from scripts.generate_report import generate_html
from scripts.improve_description import improve_description
from scripts.run_eval import find_project_root, run_eval
from scripts.utils import parse_skill_md
def split_eval_set(eval_set: list[dict], holdout: float, seed: int = 42) -> tuple[list[dict], list[dict]]:
"""Split eval set into train and test sets, stratified by should_trigger."""
random.seed(seed)
# Separate by should_trigger
trigger = [e for e in eval_set if e["should_trigger"]]
no_trigger = [e for e in eval_set if not e["should_trigger"]]
# Shuffle each group
random.shuffle(trigger)
random.shuffle(no_trigger)
# Calculate split points
n_trigger_test = max(1, int(len(trigger) * holdout))
n_no_trigger_test = max(1, int(len(no_trigger) * holdout))
# Split
test_set = trigger[:n_trigger_test] + no_trigger[:n_no_trigger_test]
train_set = trigger[n_trigger_test:] + no_trigger[n_no_trigger_test:]
return train_set, test_set
def run_loop(
eval_set: list[dict],
skill_path: Path,
description_override: str | None,
num_workers: int,
timeout: int,
max_iterations: int,
runs_per_query: int,
trigger_threshold: float,
holdout: float,
model: str,
verbose: bool,
live_report_path: Path | None = None,
log_dir: Path | None = None,
) -> dict:
"""Run the eval + improvement loop."""
project_root = find_project_root()
name, original_description, content = parse_skill_md(skill_path)
current_description = description_override or original_description
# Split into train/test if holdout > 0
if holdout > 0:
train_set, test_set = split_eval_set(eval_set, holdout)
if verbose:
print(f"Split: {len(train_set)} train, {len(test_set)} test (holdout={holdout})", file=sys.stderr)
else:
train_set = eval_set
test_set = []
client = anthropic.Anthropic()
history = []
exit_reason = "unknown"
for iteration in range(1, max_iterations + 1):
if verbose:
print(f"\n{'='*60}", file=sys.stderr)
print(f"Iteration {iteration}/{max_iterations}", file=sys.stderr)
print(f"Description: {current_description}", file=sys.stderr)
print(f"{'='*60}", file=sys.stderr)
# Evaluate train + test together in one batch for parallelism
all_queries = train_set + test_set
t0 = time.time()
all_results = run_eval(
eval_set=all_queries,
skill_name=name,
description=current_description,
num_workers=num_workers,
timeout=timeout,
project_root=project_root,
runs_per_query=runs_per_query,
trigger_threshold=trigger_threshold,
model=model,
)
eval_elapsed = time.time() - t0
# Split results back into train/test by matching queries
train_queries_set = {q["query"] for q in train_set}
train_result_list = [r for r in all_results["results"] if r["query"] in train_queries_set]
test_result_list = [r for r in all_results["results"] if r["query"] not in train_queries_set]
train_passed = sum(1 for r in train_result_list if r["pass"])
train_total = len(train_result_list)
train_summary = {"passed": train_passed, "failed": train_total - train_passed, "total": train_total}
train_results = {"results": train_result_list, "summary": train_summary}
if test_set:
test_passed = sum(1 for r in test_result_list if r["pass"])
test_total = len(test_result_list)
test_summary = {"passed": test_passed, "failed": test_total - test_passed, "total": test_total}
test_results = {"results": test_result_list, "summary": test_summary}
else:
test_results = None
test_summary = None
history.append({
"iteration": iteration,
"description": current_description,
"train_passed": train_summary["passed"],
"train_failed": train_summary["failed"],
"train_total": train_summary["total"],
"train_results": train_results["results"],
"test_passed": test_summary["passed"] if test_summary else None,
"test_failed": test_summary["failed"] if test_summary else None,
"test_total": test_summary["total"] if test_summary else None,
"test_results": test_results["results"] if test_results else None,
# For backward compat with report generator
"passed": train_summary["passed"],
"failed": train_summary["failed"],
"total": train_summary["total"],
"results": train_results["results"],
})
# Write live report if path provided
if live_report_path:
partial_output = {
"original_description": original_description,
"best_description": current_description,
"best_score": "in progress",
"iterations_run": len(history),
"holdout": holdout,
"train_size": len(train_set),
"test_size": len(test_set),
"history": history,
}
live_report_path.write_text(generate_html(partial_output, auto_refresh=True, skill_name=name))
if verbose:
def print_eval_stats(label, results, elapsed):
pos = [r for r in results if r["should_trigger"]]
neg = [r for r in results if not r["should_trigger"]]
tp = sum(r["triggers"] for r in pos)
pos_runs = sum(r["runs"] for r in pos)
fn = pos_runs - tp
fp = sum(r["triggers"] for r in neg)
neg_runs = sum(r["runs"] for r in neg)
tn = neg_runs - fp
total = tp + tn + fp + fn
precision = tp / (tp + fp) if (tp + fp) > 0 else 1.0
recall = tp / (tp + fn) if (tp + fn) > 0 else 1.0
accuracy = (tp + tn) / total if total > 0 else 0.0
print(f"{label}: {tp+tn}/{total} correct, precision={precision:.0%} recall={recall:.0%} accuracy={accuracy:.0%} ({elapsed:.1f}s)", file=sys.stderr)
for r in results:
status = "PASS" if r["pass"] else "FAIL"
rate_str = f"{r['triggers']}/{r['runs']}"
print(f" [{status}] rate={rate_str} expected={r['should_trigger']}: {r['query'][:60]}", file=sys.stderr)
print_eval_stats("Train", train_results["results"], eval_elapsed)
if test_summary:
print_eval_stats("Test ", test_results["results"], 0)
if train_summary["failed"] == 0:
exit_reason = f"all_passed (iteration {iteration})"
if verbose:
print(f"\nAll train queries passed on iteration {iteration}!", file=sys.stderr)
break
if iteration == max_iterations:
exit_reason = f"max_iterations ({max_iterations})"
if verbose:
print(f"\nMax iterations reached ({max_iterations}).", file=sys.stderr)
break
# Improve the description based on train results
if verbose:
print(f"\nImproving description...", file=sys.stderr)
t0 = time.time()
# Strip test scores from history so improvement model can't see them
blinded_history = [
{k: v for k, v in h.items() if not k.startswith("test_")}
for h in history
]
new_description = improve_description(
client=client,
skill_name=name,
skill_content=content,
current_description=current_description,
eval_results=train_results,
history=blinded_history,
model=model,
log_dir=log_dir,
iteration=iteration,
)
improve_elapsed = time.time() - t0
if verbose:
print(f"Proposed ({improve_elapsed:.1f}s): {new_description}", file=sys.stderr)
current_description = new_description
# Find the best iteration by TEST score (or train if no test set)
if test_set:
best = max(history, key=lambda h: h["test_passed"] or 0)
best_score = f"{best['test_passed']}/{best['test_total']}"
else:
best = max(history, key=lambda h: h["train_passed"])
best_score = f"{best['train_passed']}/{best['train_total']}"
if verbose:
print(f"\nExit reason: {exit_reason}", file=sys.stderr)
print(f"Best score: {best_score} (iteration {best['iteration']})", file=sys.stderr)
return {
"exit_reason": exit_reason,
"original_description": original_description,
"best_description": best["description"],
"best_score": best_score,
"best_train_score": f"{best['train_passed']}/{best['train_total']}",
"best_test_score": f"{best['test_passed']}/{best['test_total']}" if test_set else None,
"final_description": current_description,
"iterations_run": len(history),
"holdout": holdout,
"train_size": len(train_set),
"test_size": len(test_set),
"history": history,
}
def main():
parser = argparse.ArgumentParser(description="Run eval + improve loop")
parser.add_argument("--eval-set", required=True, help="Path to eval set JSON file")
parser.add_argument("--skill-path", required=True, help="Path to skill directory")
parser.add_argument("--description", default=None, help="Override starting description")
parser.add_argument("--num-workers", type=int, default=10, help="Number of parallel workers")
parser.add_argument("--timeout", type=int, default=30, help="Timeout per query in seconds")
parser.add_argument("--max-iterations", type=int, default=5, help="Max improvement iterations")
parser.add_argument("--runs-per-query", type=int, default=3, help="Number of runs per query")
parser.add_argument("--trigger-threshold", type=float, default=0.5, help="Trigger rate threshold")
parser.add_argument("--holdout", type=float, default=0.4, help="Fraction of eval set to hold out for testing (0 to disable)")
parser.add_argument("--model", required=True, help="Model for improvement")
parser.add_argument("--verbose", action="store_true", help="Print progress to stderr")
parser.add_argument("--report", default="auto", help="Generate HTML report at this path (default: 'auto' for temp file, 'none' to disable)")
parser.add_argument("--results-dir", default=None, help="Save all outputs (results.json, report.html, log.txt) to a timestamped subdirectory here")
args = parser.parse_args()
eval_set = json.loads(Path(args.eval_set).read_text())
skill_path = Path(args.skill_path)
if not (skill_path / "SKILL.md").exists():
print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
sys.exit(1)
name, _, _ = parse_skill_md(skill_path)
# Set up live report path
if args.report != "none":
if args.report == "auto":
timestamp = time.strftime("%Y%m%d_%H%M%S")
live_report_path = Path(tempfile.gettempdir()) / f"skill_description_report_{skill_path.name}_{timestamp}.html"
else:
live_report_path = Path(args.report)
# Open the report immediately so the user can watch
live_report_path.write_text("<html><body><h1>Starting optimization loop...</h1><meta http-equiv='refresh' content='5'></body></html>")
webbrowser.open(str(live_report_path))
else:
live_report_path = None
# Determine output directory (create before run_loop so logs can be written)
if args.results_dir:
timestamp = time.strftime("%Y-%m-%d_%H%M%S")
results_dir = Path(args.results_dir) / timestamp
results_dir.mkdir(parents=True, exist_ok=True)
else:
results_dir = None
log_dir = results_dir / "logs" if results_dir else None
output = run_loop(
eval_set=eval_set,
skill_path=skill_path,
description_override=args.description,
num_workers=args.num_workers,
timeout=args.timeout,
max_iterations=args.max_iterations,
runs_per_query=args.runs_per_query,
trigger_threshold=args.trigger_threshold,
holdout=args.holdout,
model=args.model,
verbose=args.verbose,
live_report_path=live_report_path,
log_dir=log_dir,
)
# Save JSON output
json_output = json.dumps(output, indent=2)
print(json_output)
if results_dir:
(results_dir / "results.json").write_text(json_output)
# Write final HTML report (without auto-refresh)
if live_report_path:
live_report_path.write_text(generate_html(output, auto_refresh=False, skill_name=name))
print(f"\nReport: {live_report_path}", file=sys.stderr)
if results_dir and live_report_path:
(results_dir / "report.html").write_text(generate_html(output, auto_refresh=False, skill_name=name))
if results_dir:
print(f"Results saved to: {results_dir}", file=sys.stderr)
if __name__ == "__main__":
main()

47
.agents/skills/skill-creator/scripts/utils.py Normal file
View File

@@ -0,0 +1,47 @@
"""Shared utilities for skill-creator scripts."""
from pathlib import Path
def parse_skill_md(skill_path: Path) -> tuple[str, str, str]:
"""Parse a SKILL.md file, returning (name, description, full_content)."""
content = (skill_path / "SKILL.md").read_text()
lines = content.split("\n")
if lines[0].strip() != "---":
raise ValueError("SKILL.md missing frontmatter (no opening ---)")
end_idx = None
for i, line in enumerate(lines[1:], start=1):
if line.strip() == "---":
end_idx = i
break
if end_idx is None:
raise ValueError("SKILL.md missing frontmatter (no closing ---)")
name = ""
description = ""
frontmatter_lines = lines[1:end_idx]
i = 0
while i < len(frontmatter_lines):
line = frontmatter_lines[i]
if line.startswith("name:"):
name = line[len("name:"):].strip().strip('"').strip("'")
elif line.startswith("description:"):
value = line[len("description:"):].strip()
# Handle YAML multiline indicators (>, |, >-, |-)
if value in (">", "|", ">-", "|-"):
continuation_lines: list[str] = []
i += 1
while i < len(frontmatter_lines) and (frontmatter_lines[i].startswith(" ") or frontmatter_lines[i].startswith("\t")):
continuation_lines.append(frontmatter_lines[i].strip())
i += 1
description = " ".join(continuation_lines)
continue
else:
description = value.strip('"').strip("'")
i += 1
return name, description, content

6
.idea/data_source_mapping.xml generated
View File

@@ -1,6 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="DataSourcePerFileMappings">
<file url="file://$PROJECT_DIR$/101-数据库学习/3-SQLite/9-题目/SQLite基础考察.sql" value="33bcd8d4-0085-46de-8fa2-dfc09570882c" />
</component>
</project>

48
14-2026年2月11日-XAwindows转发/2026年2月11日-代理图.md Normal file
View File

@@ -0,0 +1,48 @@
```mermaid
---
config:
layout: dagre
---
flowchart LR
subgraph Internet["☁️ 公网环境 (Internet)"]
direction TB
HostA["🖥️ 主机 A (Linux)<br>IP: 144.7.97.70"]
end
subgraph GostService["⚙️ Gost Service (gost.yaml)"]
direction TB
Listener1["Listen 内网:39000"]
Listener2["Listen 内网:1999"]
Listener3["Listen 公网:1998"]
end
subgraph Middle["🛡️ 中转跳板 (主机 B)"]
direction TB
HostB["🖥️ 主机 B (Windows Server)<br>公网: 144.7.88.50<br>内网: 192.168.10.1"]
GostService
end
subgraph Intranet["🏠 局域网环境 (Intranet)"]
direction TB
HostC["💻 主机 C (Windows PC)<br>IP: 192.168.10.2"]
end
HostC -- "1. TCP 请求<br>目标: 192.168.10.1:39000" --> Listener1
Listener1 -. "转发 (Forward)<br>目标: 144.7.97.70:39000" .-> HostA
HostC -- "2. HTTP 请求<br>目标: 192.168.10.1:1999" --> Listener2
Listener2 -. "转发 (Forward)<br>目标: 144.7.97.70:1999" .-> HostA
HostA -- "3. HTTP 请求<br>目标: 144.7.88.50:1998" --> Listener3
Listener3 -. "转发 (Forward)<br>目标: 192.168.10.2:1998" .-> HostC
HostA:::linux
Listener1:::gostBox
Listener2:::gostBox
Listener3:::gostBox
HostB:::windows
HostC:::windows
classDef linux fill:#e1f5fe,stroke:#01579b,stroke-width:2px,color:#000
classDef windows fill:#e8f5e9,stroke:#2e7d32,stroke-width:2px,color:#000
classDef gostBox fill:#fff3e0,stroke:#ef6c00,stroke-width:2px,stroke-dasharray: 5 5,color:#000
linkStyle 0 stroke:#1976D2,stroke-width:2px,fill:none
linkStyle 1 stroke:#1976D2,stroke-width:2px,fill:none
linkStyle 2 stroke:#1976D2,stroke-width:2px,fill:none
linkStyle 3 stroke:#1976D2,stroke-width:2px,fill:none
linkStyle 4 stroke:#D32F2F,stroke-width:2px,fill:none
linkStyle 5 stroke:#D32F2F,stroke-width:2px,fill:none
```

287
14-2026年2月11日-XAwindows转发/2026年2月11日-代理方案.md Normal file
View File

@@ -0,0 +1,287 @@
完全正确！既然主机B可以直接访问主机C（同局域网），那么**只需要在主机B上配置端口转发**即可，无需在主机A和主机C上安装任何软件。 [github](https://github.com/ginuerzh/gost/issues/1027)
## 简化方案：仅配置主机B
### 场景重新分析
主机B作为中转枢纽，提供三个端口转发服务：
1. 内网端口 → 主机A:39000（供主机C使用）
2. 内网端口 → 主机A:1999（供主机C使用）
3. 公网端口 → 主机C:1998（供主机A使用）
### 主机B完整配置（Windows Server）
#### 1. 下载Gost
```bash
# 从 https://github.com/go-gost/gost/releases 下载Windows版本
# 解压到 C:\gost\
```
#### 2. 创建配置文件
在 `C:\gost\` 目录创建 `gost.yaml`：
```yaml
services:
# 服务1: 主机C访问主机A的39000端口（TCP）
# 主机C连接 192.168.10.1:39000
- name: forward-c-to-a-39000
addr: 192.168.10.1:39000
handler:
type: tcp
listener:
type: tcp
forwarder:
nodes:
- name: host-a-39000
addr: 144.7.97.70:39000
# 服务2: 主机C访问主机A的1999端口（HTTP）
# 主机C连接 192.168.10.1:1999 或 http://192.168.10.1:1999
- name: forward-c-to-a-1999
addr: 192.168.10.1:1999
handler:
type: tcp
listener:
type: tcp
forwarder:
nodes:
- name: host-a-1999
addr: 144.7.97.70:1999
# 服务3: 主机A访问主机C的1998端口（HTTP）
# 主机A连接 144.7.8.50:11998 或 http://144.7.8.50:11998
- name: forward-a-to-c-1998
addr: 144.7.8.50:11998
handler:
type: tcp
listener:
type: tcp
forwarder:
nodes:
- name: host-c-1998
addr: 192.168.10.2:1998
```
#### 3. 测试配置
```bash
# 在PowerShell或CMD中测试运行
cd C:\gost
.\gost.exe -C gost.yaml
# 观察输出，确认没有错误
# 看到类似以下输出表示成功：
# 2026/02/11 11:26:00 forward-c-to-a-39000: listening on 192.168.10.1:39000
# 2026/02/11 11:26:00 forward-c-to-a-1999: listening on 192.168.10.1:1999
# 2026/02/11 11:26:00 forward-a-to-c-1998: listening on 144.7.8.50:11998
```
如果测试正常，按 `Ctrl+C` 停止，继续下一步。
#### 4. 使用NSSM注册为Windows服务
```bash
# 下载NSSM: http://www.nssm.cc/download
# 解压到 C:\nssm\
# 以管理员身份打开CMD或PowerShell
cd C:\nssm\win64
# 安装服务
nssm.exe install GostService
# 在弹出的NSSM窗口中配置：
# Application标签页：
# Path: C:\gost\gost.exe
# Startup directory: C:\gost
# Arguments: -C gost.yaml
#
# Details标签页：
# Display name: Gost Port Forwarding Service
# Description: Gost端口转发服务
#
# 点击 Install service
```
#### 5. 启动服务
```bash
# 启动服务
nssm start GostService
# 查看服务状态
nssm status GostService
# 如果需要，可以查看服务是否在运行
sc query GostService
```
#### 6. 服务管理命令
```bash
# 启动服务
nssm start GostService
# 停止服务
nssm stop GostService
# 重启服务（修改配置后使用）
nssm restart GostService
# 查看服务状态
nssm status GostService
# 编辑服务配置
nssm edit GostService
# 查看服务日志（在服务属性中可配置日志输出路径）
nssm edit GostService
# 在I/O标签页可以设置：
# Output (stdout): C:\gost\logs\gost.log
# Error (stderr): C:\gost\logs\gost-error.log
# 删除服务（如果需要重新配置）
nssm stop GostService
nssm remove GostService confirm
```
### 防火墙配置
在主机B的Windows防火墙中添加入站规则：
```powershell
# 以管理员身份运行PowerShell
# 允许39000端口（内网访问）
New-NetFirewallRule -DisplayName "Gost-39000" -Direction Inbound -LocalPort 39000 -Protocol TCP -Action Allow
# 允许1999端口（内网访问）
New-NetFirewallRule -DisplayName "Gost-1999" -Direction Inbound -LocalPort 1999 -Protocol TCP -Action Allow
# 允许11998端口（公网访问）
New-NetFirewallRule -DisplayName "Gost-11998" -Direction Inbound -LocalPort 11998 -Protocol TCP -Action Allow
```
或者通过图形界面：
1. 打开 `Windows Defender 防火墙` → `高级设置`
2. 点击 `入站规则` → `新建规则`
3. 选择 `端口` → `TCP` → 输入端口号 `39000,1999,11998`
4. 选择 `允许连接` → 完成
## 使用方式
### 需求1：主机C访问主机A的39000端口（TCP）
在主机C上：
```bash
# 连接到主机B的内网IP
telnet 192.168.10.1 39000
# 或使用你的应用程序连接
# 目标地址: 192.168.10.1:39000
```
### 需求2：主机C访问主机A的1999端口（HTTP）
在主机C上：
```bash
# 浏览器访问
http://192.168.10.1:1999
# 或使用curl
curl http://192.168.10.1:1999
# 或使用你的应用程序
# 目标地址: 192.168.10.1:1999
```
### 需求3：主机A访问主机C的1998端口（HTTP）
在主机A上：
```bash
# 访问主机B的公网IP
curl http://144.7.8.50:11998
# 或使用浏览器
http://144.7.8.50:11998
# 实际流量路径：主机A → 144.7.8.50:11998 → 192.168.10.2:1998
```
## 验证配置
### 在主机B上验证服务是否运行
```powershell
# 查看Gost进程
tasklist | findstr gost
# 查看监听端口
netstat -ano | findstr "39000"
netstat -ano | findstr "1999"
netstat -ano | findstr "11998"
# 应该能看到类似输出：
# TCP 192.168.10.1:39000 0.0.0.0:0 LISTENING [PID]
# TCP 192.168.10.1:1999 0.0.0.0:0 LISTENING [PID]
# TCP 144.7.8.50:11998 0.0.0.0:0 LISTENING [PID]
```
### 测试连通性
在主机B上进行本地测试：
```powershell
# 测试到主机A的连接（需要确保主机A的服务在运行）
Test-NetConnection -ComputerName 144.7.97.70 -Port 39000
Test-NetConnection -ComputerName 144.7.97.70 -Port 1999
# 测试到主机C的连接（需要确保主机C的1998端口服务在运行）
Test-NetConnection -ComputerName 192.168.10.2 -Port 1998
```
## 配置优化建议
如果需要添加日志功能，可以修改配置文件：
```yaml
log:
level: info
format: json
output: C:\gost\logs\gost.log
services:
# ... 其他配置保持不变
```
## 故障排查
如果遇到问题：
1. **检查Gost服务状态**：
```bash
nssm status GostService
```
2. **查看Gost日志**（如果配置了日志输出）：
```bash
type C:\gost\logs\gost.log
type C:\gost\logs\gost-error.log
```
3. **手动运行查看错误**：
```bash
cd C:\gost
.\gost.exe -C gost.yaml -L debug
```
4. **检查端口占用冲突**：
```powershell
netstat -ano | findstr "39000"
netstat -ano | findstr "1999"
netstat -ano | findstr "11998"
```
这个简化方案只需要在主机B上操作，维护更简单，性能也更好！ [nephen](https://www.nephen.cn/posts/4669df2a/)

45
14-2026年2月11日-XAwindows转发/gost.yaml Normal file
View File

@@ -0,0 +1,45 @@
log:
level: info
format: json
output: C:\gost\logs\gost.log
services:
# 服务1: 主机C访问主机A的39000端口（TCP）
# 主机C连接 192.168.10.1:39000
- name: forward-c-to-a-39000
addr: 192.168.10.1:39000
handler:
type: tcp
listener:
type: tcp
forwarder:
nodes:
- name: host-a-39000
addr: 144.7.97.70:39000
# 服务2: 主机C访问主机A的1999端口（HTTP）
# 主机C连接 192.168.10.1:1999 或 http://192.168.10.1:1999
- name: forward-c-to-a-1999
addr: 192.168.10.1:1999
handler:
type: tcp
listener:
type: tcp
forwarder:
nodes:
- name: host-a-1999
addr: 144.7.97.70:1999
# 服务3: 主机A访问主机C的59014端口（HTTP）
# 主机A连接 144.7.8.50:59014 或 http://144.7.8.50:59014
- name: forward-a-to-c-59014
addr: 144.7.8.50:59014
handler:
type: tcp
listener:
type: tcp
forwarder:
nodes:
- name: host-c-59014
addr: 192.168.10.2:59014

22
14-2026年2月11日-XAwindows转发/网络代理工具.md Normal file
View File

@@ -0,0 +1,22 @@
你是一名精通网络的专家，熟练掌握各种网络代理工具，包括但不限于Gost、V2Ray、Xray、3proxy、Traefik、Nginx、Windows Netsh等。
你的第一参考来源应该是 https://gost.run/
我有如下的场景
### 主机介绍
1. 主机A，是一台LINUX服务器，公网IP地址是144.7.97.70
2. 主机B，是一台windows服务器，公网IP地址是144.7.88.50，内网IP地址是 192.168.10.1
3. 主机C，是一台windows电脑，内网IP地址是 192.168.10.2 无法访问公网 但是与主机B在同一个局域网内
### 需求
1. 主机C需要通过主机B访问主机A的39000端口 TCP协议
2. 主机C需要通过主机B访问主机A的1999端口 HTTP协议
3. 主机A需要通过主机B访问主机C的1998端口 HTTP协议
请你使用Gost工具，分析并给出主机B上面的 代理配置方案
### 要求
1. 最好使用配置文件的形式
2. Gost代理需要持久化运行，最好有守护进程
3. 给出详细的配置步骤和命令

61
14-2026年2月11日-XAwindows转发/网路代理工具-综述.md Normal file
View File

@@ -0,0 +1,61 @@
在Windows系统中，要实现同时支持HTTP（7层）和TCP（4层）的网络代理与转发，有多种不同定位的工具可供选择。根据您的技术背景，以下将其分为**专业代理工具**（最推荐）、**通用反向代理服务器**和**轻量级/内置工具**三类。
### 1. 专业多协议代理工具（推荐）
这类工具专门为复杂的网络隧道和多协议代理设计，通常单文件运行，配置灵活，非常适合需要同时处理HTTP和TCP流量的场景。
* **Gost (GO Simple Tunnel)**
* **特点**：基于Go语言编写，无依赖单文件。它专为代理设计，支持多级转发和几乎所有主流协议（HTTP/HTTPS/HTTP2/SOCKS5/TCP/UDP）。
* **L7 (HTTP) 功能**：直接开启HTTP/SOCKS5代理端口。
* **L4 (TCP) 功能**：支持端口转发（Port Forwarding）和透明代理。
* **适用场景**：构建复杂的代理链路、穿透防火墙或简单的本地端口映射 。 [gost](https://gost.run/en/concepts/proxy/)
* **示例**：
```bash
# 开启一个监听8080端口的代理，同时支持HTTP和SOCKS5
gost -L :8080
# 将本地8080端口的TCP流量转发到192.168.1.1的80端口
gost -L tcp://:8080/192.168.1.1:80
```
* **V2Ray / Xray (Project V)**
* **特点**：虽然常被称为“翻墙”工具，但其实质是强大的网络平台。其核心功能就是灵活的路由（Routing）和协议转换。
* **功能**：通过配置`inbounds`（入站）和`outbounds`（出站），可以精确控制HTTP请求（基于域名/路径的7层路由）和TCP连接（基于IP/端口的4层转发）。
* **优势**：在处理复杂的流量分流（如国内流量直连，国外流量代理）方面表现最优。
* **3proxy**
* **特点**：极轻量级的代理服务器，资源占用极低。
* **功能**：通过配置文件可以同时开启`proxy`（HTTP代理，默认端口3128）和`tcppm`（TCP端口映射）服务 。 [proxyrack](https://www.proxyrack.com/blog/setup-basic-3proxy-configuration/)
* **适用场景**：老旧机器或对资源极其敏感的环境。
### 2. 通用反向代理服务器
这类通常用于Web服务架构，但同样具备强大的代理能力。
* **Traefik**
* **特点**：云原生反向代理，同样基于Go，在Windows上作为单个exe运行非常方便。
* **L7 & L4**：原生支持HTTP和TCP路由（Routers）。它通过`EntryPoints`监听端口，利用`Routers`区分是HTTP请求还是纯TCP流，非常现代化 。 [cloudbees](https://www.cloudbees.com/blog/setting-up-traefik-as-a-reverse-proxy-for-asp-net-applications)
* **配置**：支持动态配置（文件/Docker标签），比Nginx更易于实现自动发现。
* **Nginx (Windows版)**
* **L7 (HTTP)**：行业标准，通过`http { ... }`块配置 `proxy_pass` 实现。
* **L4 (TCP)**：通过`stream { ... }`模块实现。
* **注意**：Windows官方预编译版本的Nginx有时不包含`stream`模块（需确认版本或自行编译），且性能不如Linux版 。如果必须在Windows使用TCP转发，建议优先考虑Traefik或Gost。 [nginx](https://nginx.org/en/docs/stream/ngx_stream_proxy_module.html)
### 3. 系统内置与轻量级工具
* **Windows Netsh (仅L4)**
* **特点**：Windows系统自带的命令行工具，无需安装任何软件。
* **功能**：仅支持TCP端口转发（PortProxy），不支持HTTP协议分析或修改。
* **命令示例** ： [woshub](https://woshub.com/port-forwarding-in-windows/)
```powershell
netsh interface portproxy add v4tov4 listenport=8080 connectaddress=192.168.1.5 connectport=80
```
### 总结对比表
| 工具 | 协议支持 | 部署难度 | 典型用途 | 推荐指数 |
| :--- | :--- | :--- | :--- | :--- |
| **Gost** | HTTP/SOCKS/TCP/UDP | 低 (单文件) | 隧道搭建、多级代理 | ⭐⭐⭐⭐⭐ |
| **Traefik** | HTTP/TCP/UDP | 中 | 微服务网关、Web服务反代 | ⭐⭐⭐⭐ |
| **Nginx** | HTTP/TCP | 中 | 高性能Web服务器 | ⭐⭐⭐ |
| **Netsh** | TCP (无HTTP) | 极低 (内置) | 简单的端口映射 | ⭐⭐ |
如果您需要快速实现代理功能且不依赖复杂环境，建议首选 **Gost**；如果是为了搭建Web服务并顺带转发TCP流量，**Traefik** 体验会优于 Windows 版 Nginx。

135
15-CICD工具选型/1-开源工具选型.md Normal file
View File

@@ -0,0 +1,135 @@
我现在想要深入的调研 每年构建数量在10万次左右的CICD工具，要求集成性能较强
1. 构建能力
1. 对多语言构建的要求较强
2. 多版本的node
3. 多版本的Java构建
4. 支持maven并发构建
5. 构建缓存支持较好
6. 支持多分支构建
6. 至此gravvl vm构建
2. 灵活的构建参数
3. 灵活的服务器调度
4. 需要又灵活的集成策略
1. 构建信息需要向外传递
5. 主流的脚本语法
6. 良好的文档、生态支持
7. 有接口暴露API，能够进行二次开发
8. 支持私有化部署
最好是开源免费的CI CD工具，也可以对比付费的构建工具 如TeamCity等, 我们现在使用的是Jenkins工具。
请你根据我的上述实际需求，整理一份精确且丰富的调研需求prompt，用于发起提问
## CI/CD 选型调研 Prompt（10万次/年构建规模，偏私有化与强集成）
请你以“企业级 CI/CD 平台架构师 + DevOps 专家”的视角，针对**每年约 10 万次构建**（约 270 次/天，峰值可能更高）的场景，输出一份**可落地的 CI/CD 工具选型调研报告**与建议清单。我们当前使用 **Jenkins**，希望对比开源与商业方案（如 TeamCity 等），并特别关注**性能、扩展性、构建缓存、调度能力与二次开发能力**。
### 1) 背景与目标
* 当前：Jenkins（请默认我们已有大量 Pipeline/Shared Library/插件依赖）
* 目标：评估下一代 CI/CD 工具是否能在**性能、稳定性、可维护性、可扩展性、集成与安全**上显著优于 Jenkins，或给出 Jenkins 体系增强路线（如分层、控制面/执行面拆分、缓存体系改造等）。
* 部署要求：**必须支持私有化部署**（IDC / 私有云 / K8s 均可能）
### 2) 必须满足的构建能力（重点逐条对比）
请对每个候选工具给出“是否支持/成熟度/实现方式/限制/最佳实践/替代方案”。
**多语言与多版本**
* Node：支持多版本 Node（例如 nvm/asdf/容器镜像/工具链管理），并能在流水线内灵活切换
* Java：支持多版本 JDK（8/11/17/21 等），并可与 Maven/Gradle 协作
* Maven：支持 **Maven 并发构建**（并行 stage、并行 module、分布式构建），并说明常见瓶颈与优化方式
**多分支与规模化**
* 支持多分支构建（多分支流水线/PR 构建/分支策略），并说明分支规模增大后的性能与资源开销
* 支持大规模并发：请给出在 10万次/年构建规模下的参考架构（控制面、执行面、队列、弹性伸缩、隔离模型）
**构建缓存（强诉求）**
* 支持高质量缓存体系：依赖缓存（npm/maven）、构建产物缓存、远程缓存（如 Bazel/Gradle build cache 类似能力）
* 缓存可共享、可清理、可审计、可多租户隔离
* 请说明：缓存命中率提升策略、缓存一致性/污染处理、典型落地方式（PVC/NFS/S3/MinIO/远程 cache 服务）
**分布式/虚拟化执行**
* 支持 “可扩展的执行节点/Agent”，以及基于 **K8s** 或 VM 的动态调度
* 我们有 “**Gravvl VM 构建**”（按你理解：可视为“特定 VM/镜像/硬件架构环境的构建需求”，例如需要在 VM 内执行、或需要特定内核/驱动/安全基线）。请给出：如何接入、如何做资源隔离、如何做镜像管理与复用、如何控制成本。
### 3) 灵活的构建参数与触发模型
* 参数化构建：动态参数、级联参数、环境矩阵（OS/Arch/版本）、手动触发与 API 触发
* 触发源：Git Push/PR/MR、Tag、定时、Webhook、外部事件（消息队列/工单/发布平台）
* 复杂流水线编排：条件执行、审批/人工确认、并行/扇出、失败重试与补偿
### 4) 灵活的服务器调度与资源治理
请说明调度能力是否“内置/需集成/依赖 K8s/需商业组件”：
* 队列与优先级：不同项目/团队配额、优先级、抢占/限流
* 弹性：基于队列长度/资源水位自动扩缩容
* 隔离：多租户隔离、Runner/Agent 隔离、网络隔离、凭据隔离
* 成本：资源利用率、峰谷策略、冷启动/预热策略
### 5) 集成策略与对外传递（强诉求）
* “构建信息需要向外传递”：请给出可落地的事件模型与集成方式
* 构建开始/成功/失败/产物信息/制品元数据/测试报告/覆盖率/安全扫描结果
* 事件投递方式：Webhook、消息队列（Kafka/NATS/RabbitMQ）、事件总线、回调、API 拉取
* 幂等、重试、可观测（Trace/Log/Metric）与审计
### 6) 脚本语法与可维护性
* 主流脚本语法：YAML（GitLab CI/GHA 风格）、Groovy（Jenkinsfile）、Kotlin DSL、声明式 pipeline 等
* 复用机制：模板、模块化、共享库、Pipeline as Code 的最佳实践
* 可读性/可维护性/可测试性（pipeline 单元测试、lint、review 工作流）
### 7) 文档、生态与社区成熟度
* 官方文档质量、学习曲线、社区活跃度
* 插件/扩展生态（SCM、制品库、SonarQube、安全扫描、通知、K8s、云厂商等）
* 企业支持能力：升级策略、兼容性、长期维护版本（LTS）
### 8) API 暴露与二次开发能力（必须）
* 是否提供完整 API（REST/GraphQL/gRPC）、Webhook、SDK
* RBAC/权限模型与 API 鉴权（Token/OAuth/OIDC/SAML）
* 自定义插件/扩展点：能否开发自定义步骤、Runner、调度策略、UI 扩展
* 审计与合规：操作审计、凭据管理、密钥轮换、最小权限
### 9) 私有化部署与运维
* 支持在 K8s/VM/裸机部署；高可用；备份恢复；灾备
* 数据存储：数据库依赖、状态存储、配置管理
* 升级与回滚策略（零停机/灰度）
* 监控与告警：Prometheus 指标、日志、审计、链路追踪
### 10) 输出要求（你必须这样输出）
请你输出以下结构化内容，越具体越好：
1. **候选工具清单**（开源优先 + 商业对照），并说明为何入选
* 例如：Jenkins（对照）、GitLab CI、GitHub Actions Enterprise、Tekton、Argo Workflows、Buildkite、TeamCity、CircleCI Server、GoCD 等（你可自行增减，但要给理由）
2. **对比矩阵表**（必须包含上面 1-9 所有维度）
* 每项给：支持程度（原生/依赖集成/不支持）、成熟度（高/中/低）、落地复杂度（低/中/高）、风险点
3. **推荐 Top 3 方案**
* 分别给出：适用场景、参考架构（控制面/执行面/缓存/制品/队列/可观测）、迁移路径（从 Jenkins 迁移的策略）
4. **性能与规模化建议**（针对 10万次/年构建）
* 并发模型、缓存策略、Runner/Agent 伸缩、队列治理、构建隔离
5. **二次开发与集成方案**
* 构建事件对外传递的实现建议（Webhook/MQ/事件总线）与接口设计要点
6. **风险清单与验证计划（PoC）**
* 给出 2~4 周 PoC 验证项：缓存命中率、并发吞吐、稳定性、迁移成本、安全合规、可观测性等
* 明确要收集的指标与验收标准（例如：平均排队时间、构建成功率、缓存命中率、单构建成本等）
> 注意：请基于“私有化部署 + 高并发构建 + 强缓存 + 强集成 + 可二开”的目标，不要只给概念描述，要给可执行的工程落地建议与对比依据。

290
15-CICD工具选型/2-gemi-选型说明.md Normal file
View File

@@ -0,0 +1,290 @@
---
title: 企业级 CI／CD 平台架构演进与选型深度研究报告
date: 2026-02-04T16:08:48Z
lastmod: 2026-02-04T16:08:55Z
---
# 企业级 CI／CD 平台架构演进与选型深度研究报告
## 1. 执行摘要与架构背景
### 1.1 研究背景与战略意义
　　在当前企业数字化转型的深水区，持续集成与持续交付（CI/CD）平台已不再仅仅是自动化脚本的执行器，而是软件供应链的核心生产线。针对本企业年均 ​**10 万次构建**​（日均约 270 次，峰值可能突破 1000 次/日）的规模，现有的 Jenkins 架构正面临着从“工具级”向“平台级”跨越的临界点。当前的 Jenkins 体系虽然通过大量 Shared Library 和插件维持运转，但在面对​**GraalVM 原生镜像构建的高资源消耗**​、**Maven/Node 复杂依赖的缓存瓶颈**以及**企业级数据总线（Event Bus）的强集成需求**时，表现出了明显的架构疲态。
　　本报告站在“企业级架构师”与“DevOps 专家”的双重视角，对私有化部署场景下的主流 CI/CD 解决方案进行了穷尽式的深度剖析。我们的目标不仅是选出一款工具，更是为了构建一套能够在未来 3-5 年内支撑业务倍增、保障构建性能与安全、且具备高度二次开发能力的工程化底座。
### 1.2 核心挑战分析：10 万次构建的规模效应
　　10 万次/年的构建量级是一个关键的分水岭。在此规模之下，简单的脚本编排尚可应付；而一旦跨越此量级，一系列隐性的架构瓶颈将集中爆发：
- **I/O 吞吐风暴（I/O Throttling）：** Java (Maven/Gradle) 和 Node.js (npm/yarn) 生态系统的构建高度依赖网络 I/O。假设单次“净构建”需下载 200MB 依赖，若无高效缓存，10 万次构建将产生 **20TB** 的无效网络流量。这不仅会导致构建排队，甚至可能阻塞 IDC 的出口带宽 ^^。
- **控制面与执行面的资源竞争：** 传统的 Jenkins 主从架构（Master-Slave）在处理高并发（如峰值 50+ 并发流水线）时，Controller 节点的 JVM 堆内存压力剧增，导致 UI 卡顿甚至宕机。特别是当 GraalVM 等 CPU/内存密集型任务混跑在共享集群时，“吵闹邻居”（Noisy Neighbor）效应将严重影响稳定性 ^^。
- **集成架构的脆弱性：** 当前“强集成”需求要求构建状态实时向外投递。依赖 Jenkins 插件进行点对点（Point-to-Point）通知的方式在插件升级或 API 变更时极易断裂。架构必须向\*\*事件驱动架构（EDA）\*\*转型，将 CI 平台作为标准的事件生产者（Producer）接入 Kafka 等消息总线 ^^。
### 1.3 评估范围与方法论
　　本报告严格遵循“私有化部署”的红线要求，剔除纯 SaaS 方案（如 CircleCI Cloud、GitHub Actions Cloud），重点考察以下核心维度：
1. **性能密度：** 单位资源下的并发吞吐能力。
2. **缓存工程：** 多级缓存体系（本地/远程/分布式）的实现机制。
3. **异构计算支持：** 对 K8s 动态节点与 GraalVM 专用静态节点的混合调度能力。
4. **开放性：** API 完备度与事件总线集成能力。
---
## 2. 候选工具生态格局与入围清单
　　在私有化部署（Self-Hosted）领域，市场格局呈现出“一超多强”的态势。基于技术栈匹配度（Java/Node/K8s）与企业级特性，我们将以下工具列入深度评估清单：
### 2.1 核心候选者
#### **1. Jenkins (基准对照组)**
- **入选理由：** 现有的存量资产，拥有全球最大的插件生态。
- **当前定位：** 传统的自动化服务器。虽然通过 Jenkins X 和 Kubernetes Plugin 尝试现代化，但其核心架构仍基于 Servlet 容器，积重难返。
- **关键挑战：** “插件地狱”（Plugin Hell）与单点故障风险。维护一个高可用的 Jenkins 集群往往需要专门的运维团队 ^^。
#### **2. TeamCity (工程化首选)**
- **入选理由：** JetBrains 出品，专为复杂工程设计。在 Java/Kotlin 生态中拥有统治级的构建优化能力（智能并行、构建链优化）。
- **架构特点：** 采用强类型的 Kotlin DSL 配置，Server-Agent 架构极其成熟，原生支持构建队列的智能调度 ^^。
- **适用性：** 极度适合 Maven 多模块与 Gradle 构建场景，对 GraalVM 等重型构建有优秀的资源隔离管理。
#### **3. GitLab CI/CD (DevOps 一体化首选)**
- **入选理由：** 云原生时代的标杆。与其源码管理（SCM）深度绑定，实现了“代码即流水线”的闭环。
- **架构特点：** 核心组件（Coordinator）与执行组件（Runner）完全解耦。GitLab Runner 基于 Go 语言开发，极其轻量且稳定，完美契合 Kubernetes 环境 ^^。
- **适用性：** 适合追求工具链统一、容器化程度高的团队。
#### **4. Buildkite (混合云架构对照)**
- **入选理由：** 以“高并发”和“混合云”著称。虽然其控制面（Control Plane）通常为 SaaS，但其 Agent 必须部署在私有环境。
- **特别说明：** 尽管它是 SaaS 控制面，但对于拥有极高并发需求且希望零维护控制面的团队，Buildkite 提供了一种独特的思路。如果企业的安全合规允许构建元数据（Metadata）上云，而代码和产物留在本地，Buildkite 是极具竞争力的“黑马” ^^。
- *在本报告中，Buildkite 将作为架构设计的参考标杆，用于对比极致的 Agent 调度能力。*
#### **5. Tekton / Argo Workflows (云原生纯粹派)**
- **入选理由：** Kubernetes 原生（CRD-based）的流水线引擎。
- **落选深度评估理由：** 尽管它们是底层引擎的未来，但缺乏企业级 CI 所需的用户界面（UI）、权限管理（RBAC）和插件生态。通常作为底层执行器被上层平台（如 OpenShift Pipelines）集成，直接作为企业级 CI 平台使用二次开发成本过高 ^^。
---
## 3. 核心能力深度对比矩阵与解析
　　本章节将针对您的具体需求，对 Jenkins、TeamCity 和 GitLab CI 进行“像素级”的横向评测。
### 3.1 性能核心：多语言版本管理与并发构建
　　**需求分析：** 企业内部存在多版本 Node.js (Legacy/Modern) 和 Java (JDK 8/11/17/21) 共存的现状。Maven 构建的并发效率直接决定了开发者的等待时间。
|**功能维度**|**Jenkins (现有)**|**TeamCity (JetBrains)**|**GitLab CI (Runner)**|**架构师点评与风险提示**||||||
| --| -------------------------------------------------------------------------------------------------------------------------------| ---------------------------------------------------------------------------------------------------------------------------------------------------------| ---------------------------------------------------------------------------------------------------------------------| ------------------------------------------------------------------------------------------------------------------------------------------------------| --| --| --| --| --|
|**多版本环境切换**|**依赖插件/脚本**<br /><br />通常需在 Global Tools 中配置多个 JDK/Node 路径，或在 Shell 中手动 source nvm。容易产生环境污染（Dirty Agent）。|**原生参数化**<br /><br />Agent 自动汇报环境能力（Capabilities）。通过构建参数直接选择 JDK 版本。支持在同一 Agent 上通过 Docker Wrapper 隔离运行不同步骤。|**容器镜像驱动（最佳实践）** <br /><br />每一个 Job 都在指定的 Docker 镜像中运行（如`image: maven:3.8-jdk-11`）。切换版本只需修改 YAML 中的 image 标签，完全隔离。|​**GitLab 胜出**。<br /><br />Jenkins 的环境管理是运维噩梦；TeamCity 的 Agent 管理虽然智能但仍依赖物理/虚拟机环境配置；GitLab 的“容器即环境”彻底解决了版本冲突问题^^。||||||
|**Maven 并发构建**|**弱/依赖插件**<br /><br />Groovy 的`parallel`​语法可并行 Stage，但同一 Agent 上的并行 Maven 进程可能导致`.m2`​仓库锁冲突。跨节点并行需频繁`stash/unstash`产物，I/O 开销巨大。|**卓越（构建链）** <br /><br />原生解析 Maven POM 依赖图，自动拆分为独立的构建链（Build Chain）。支持“快照依赖”，智能调度模块并行构建，且仅重构建修改模块（Incremental Build）。|**中等（手动拆分）** <br /><br />支持`parallel: matrix`​和 DAG (`needs`) 关键字。需手动定义模块间的依赖关系，不如 TeamCity 智能。|​**TeamCity 胜出**。<br /><br />对于大型 Maven Monorepo，TeamCity 的增量构建与依赖分析能力可减少 40%-60% 的无用构建时间^^。||||||
|**GraalVM 原生构建**|**资源黑洞风险**<br /><br />若调度到常规 K8s Pod，极易因 OOM 被杀。需配置特定的 Label 绑定到大内存节点。|**专用 Agent 池**<br /><br />将 GraalVM 任务路由到专属的物理机/大内存 Agent 池。支持细粒度的 CPU/内存配额管理。|**Tag 路由机制**<br /><br />通过`tags: [graalvm]`将任务调度到特定的 Runner（如 Bare-metal Runner）。K8s 执行器支持为特定 Job 设置 hugepages 和资源 limit。|​**平局**。<br /><br />关键在于基础设施层的隔离。TeamCity 的 Agent Pool 可视化管理更优；GitLab 的 Runner配置更灵活^^。||||||
### 3.2 规模化扩展：队列治理与弹性伸缩
　　**需求分析：** 10 万次/年的构建意味着峰值期间（如发版日）会有大量任务堆积。如何处理优先级（Hotfix 插队）和资源抢占是关键。
#### 3.2.1 队列与优先级模型
- **TeamCity：** 拥有业界最先进的​**构建队列优化器（Optimizer）** 。它不仅支持基于优先级的插队（Priority Class），还能自动合并队列中的冗余构建（例如：在构建 A 等待期间，代码库又有新提交，TeamCity 可以自动取消构建 A 直接运行包含最新代码的构建 B）。这对节省 10 万次规模下的资源至关重要 ^^。
- **GitLab CI：** 本质上是 FIFO（先进先出）队列。虽然可以通过设置 Runner 的并发限制来管理，但在同一个 Runner 实例内部很难实现“让 Hotfix 构建立即抢占正在运行的 CI 构建”的逻辑，通常需要预留专用的 Runner 资源，造成浪费。
- **Jenkins：** 依赖 `Priority Sorter Plugin`，配置繁琐且容易失效。在高负载下，Jenkins Master 的调度线程本身可能成为瓶颈。
#### 3.2.2 弹性伸缩架构（Elasticity）
- **GitLab CI (Kubernetes Executor)：** 真正的云原生弹性。Runner 作为一个轻量级 Agent，仅在需要时向 K8s API 申请 Pod。构建结束后 Pod 立即销毁。这种\*\*“用完即焚”\*\*（Ephemeral）模式完美契合 10 万次构建的动态波动特性，资源利用率最高 ^^。
- **TeamCity：** 支持“云代理”（Cloud Agents）。可以对接 K8s 或 AWS EC2，按需启动 Agent。但 TeamCity 的 Agent 是有状态连接（Bi-directional communication），启动和握手速度通常慢于 GitLab 的无状态 Runner。
### 3.3 构建缓存体系：性能决胜点
　　**需求分析：** “强诉求”——缓存必须可共享、可清理。Maven 和 Node 的依赖下载是性能杀手。
#### **架构方案 A：GitLab CI 的分布式缓存（S3/MinIO 后端）**
　　GitLab 采用“压缩-上传-下载-解压”的缓存机制。
- **机制：** Job 开始时，Runner 从 MinIO 下载 `cache.zip`​ 并解压；Job 结束时，压缩 `node_modules` 并上传。
- **瓶颈：** 对于 `node_modules` 动辄 1GB 的情况，压缩和网络传输的时间可能超过下载依赖本身的时间。
- **优化策略：** 必须使用 **Docker Layer Caching** 或 ​**PVC 挂载**​。在私有化 K8s 环境中，推荐使用 `hostPath`​ 或高性能网络存储（如 CephFS）挂载到 Runner Pod 中作为全局缓存，通过 `KANIKO_CACHE_ARGS` 实现构建层缓存 ^^。
#### **架构方案 B：TeamCity 的本地持久化缓存**
　　TeamCity 倾向于使用持久化 Agent。
- **机制：** Agent 是长期运行的。Maven 的 `.m2` 仓库直接存储在 Agent 的本地磁盘上。
- **优势：** 二次构建速度极快（零网络开销）。
- **风险：** 缓存污染。如果两个并行构建修改同一个本地依赖，可能导致构建失败。TeamCity 通过“共享资源锁”（Shared Resources）机制来解决此问题，但这会降低并发度 ^^。
- **推荐方案：** 结合 ​**Remote Build Cache**（如 Gradle Enterprise 或 Bazel Remote Cache）。不依赖 CI 工具本身的缓存，而是让构建工具直接连接局域网内的 Nginx/Redis 缓存服务。
---
## 4. 推荐方案 Top 3 与架构设计
　　基于“私有化 + 高并发 + 强集成”的目标，我们给出明确的选型建议。
### 推荐一：GitLab CI/CD（DevOps 平台化转型的战略首选）
　　**适用场景：**
- 希望实现从代码管理到部署的​**全链路闭环**。
- 运维团队具备较强的 **Kubernetes** 运维能力。
- 追求​**配置即代码**（YAML）和不可变基础设施。
　　**参考架构（针对 10 万次/年规模）：**
- **控制面（Control Plane）：** 部署 GitLab HA 集群（3 节点），配置高性能 Redis 集群用于作业队列缓冲，外接 PostgreSQL 数据库。
- **执行面（Data Plane）：**
- **通用池：** Kubernetes Executor，配置 HPA（水平自动伸缩），承载 80% 的 Java/Node 构建。
- **专用池：** 3-5 台高配置裸金属服务器（Bare Metal），安装 Shell Executor 或 Docker Executor，专门用于 **GraalVM Native Image** 构建，避免 K8s OOM 风险 ^^。
- **缓存策略：** 部署私有化 MinIO 集群作为 Distributed Cache 后端。同时在 K8s Runner 中开启 `PVC` 挂载，将 Maven/NPM 缓存挂载为 ReadWriteMany 卷（需底层存储支持，如 NAS），实现“热缓存”。
- **迁移路径：** 利用 GitLab 的 `include`​ 机制，将 Jenkins Shared Library 中的逻辑重构为通用的 `.gitlab-ci.yml` 模板库（Templates），供各个项目引用。
### 推荐二：TeamCity（工程效能极致优化的战术首选）
　　**适用场景：**
- 核心业务为复杂的 ​**Java Monorepo**，对依赖管理极其敏感。
- 需要极度精细的**构建队列管理**和资源抢占能力。
- 可以接受独立的 SCM 和 CI 工具分离，且预算允许购买 Agent 授权。
　　**参考架构：**
- **控制面：** 单节点 TeamCity Server（配备高性能 NVMe SSD 存储数据库和 Artifacts），因 TeamCity Server 架构难以水平扩展，需垂直扩展（Vertical Scaling）以支撑高并发 API 请求。
- **执行面：**
- **Agent Pool A (Cloud):** 对接 K8s 集群，用于运行轻量级 Docker 任务。
- **Agent Pool B (Persistent):** 部署在物理机上的持久化 Agent，用于 Maven 增量构建和 GraalVM 构建。利用本地磁盘 I/O 优势。
- **集成：** 开发自定义 Java 插件监听构建事件，推送到 Kafka。
### 推荐三：Jenkins Modernization（存量资产保护的折衷方案）
　　**适用场景：**
- 存量 Pipeline 逻辑过于复杂（数万行 Groovy 代码），重写成本不可接受。
- 预算极其有限，无法承担 TeamCity 许可或 GitLab Premium 费用。
　　**增强路线（Survival Strategy）：**
- **彻底的控制/执行分离：** 禁止在 Master 节点执行任何 Job。所有构建强制下发到 K8s Pod。
- **配置即代码（JCasC）：** 使用 Jenkins Configuration as Code 插件管理 Master 配置，杜绝手动 UI 修改。
- **事件总线改造：** 编写一个全局的 Shared Library (`GlobalPipelineListener`​)，在 `pipeline`​ 的 `post { always {... } }` 块中注入 Kafka 发送逻辑，强制所有构建接入事件总线。
---
## 5. 深度专题：二次开发与集成方案（事件总线）
　　**需求：** “构建信息向外传递”是强诉求。我们需要从“轮询查询”转向“事件驱动”。
### 5.1 数据模型设计（CloudEvents 标准化）
　　建议采用 **CloudEvents** 规范定义构建事件，确保 Kafka 消息的通用性。
　　**Kafka Topic:** `cicd.build.events`
　　**Schema (Avro/JSON) 示例：**
　　JSON
```
{
"specversion": "1.0",
"type": "com.company.cicd.build.finished",
"source": "/gitlab/project/1234",
"id": "a1b2c3d4",
"time": "2026-02-04T10:00:00Z",
"datacontenttype": "application/json",
"data": {
"pipeline_id": "998877",
"status": "failed",
"duration_ms": 45000,
"initiator": "devops-user",
"commit_sha": "7f8a9b...",
"artifacts": [
{"name": "app.jar", "size": 102400, "url": "s3://builds/app.jar"}
],
"environment": {
"os": "linux",
"arch": "amd64",
"graalvm_version": "21.3"
}
}
}
```
### 5.2 集成实现方案对比
|**方案**|**Jenkins 实现**|**GitLab CI 实现**|**TeamCity 实现**|**推荐度**||||||
| --| ---------------------------------------------------------------------------------------| -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| ------------------------------------------------------------------------------------------------------------------------------------------| --------------------------------------------------------------| --| --| --| --| --|
|**Webhook 桥接**|**使用 Notification Plugin**<br /><br />配置 Webhook URL 指向一个中间件（Kafka Bridge）。<br /><br />*缺点：* 插件可靠性一般，重试机制弱。|**使用 System Hooks**<br /><br />在 Admin 层级配置全局 System Hook，将所有 Pipeline Event 推送到 Kafka Bridge 服务（如用 Go 编写的轻量级转换器）。<br /><br />*优点：* 全局生效，无需修改.gitlab-ci.yml，官方支持，极为稳定^^。|**Custom Webhook Plugin**<br /><br />安装 Webhook 插件配置 Payload 模板。<br /><br />*缺点：* 需手动配置每个项目或继承模板。|**GitLab (High)** <br /><br />原生 System Hooks 覆盖面最全。||||||
|**原生插件/监听器**|**Groovy Shared Library**<br /><br />在库中封装`KafkaProducer`。每次构建必须引用该库。<br /><br />*缺点：* 侵入性强，依赖 Jenkins 类加载器。|**不可行**<br /><br />GitLab SaaS/Omnibus 不允许注入自定义代码到核心 Rails 进程中。只能通过 Webhook 异步处理。|**Server-Side Plugin (Java)** <br /><br />利用 TeamCity Open API 编写 Java 插件，实现`BuildServerAdapter`​接口。在`buildFinished`方法中直接调用 Kafka SDK 发送消息。<br /><br />*优点：* 性能最高，可靠性最强（事务级保障）^^。|**TeamCity (High)** <br /><br />如果追求“强集成”且有 Java 开发能力，这是最完美的方案。||||||
　　**集成建议：**
　　若选型 ​**GitLab**​，请开发一个 **"Webhook-to-Kafka Gateway"** 微服务。该服务接收 GitLab 的 HTTP POST 请求，验证 `X-Gitlab-Token`，将 JSON 转换为 Avro，并投递到 Kafka。这种解耦架构最符合云原生设计原则。
---
## 6. 性能与规模化落地建议（10万次/年）
　　针对年均 10 万次构建（日均峰值可能达 1000+），必须在架构层面进行针对性优化。
### 6.1 并发模型计算与容量规划
- **吞吐量估算：** 假设日均 270 次，峰值系数 5 倍（集中在上午 10 点和下午 3 点），即峰值每小时约 60-100 次构建。假设平均构建时长 10 分钟。
- **并发需求：** \$\\text{并发数} \= \\text{每小时构建数} \\times \\text{构建时长(小时)} \\approx 100 \\times (10/60) \\approx 16.6\$。考虑到排队冗余，需预留 ​**30-50 个并发执行槽位（Executors/Runners）** 。
- **硬件建议：**
- **K8s Cluster:** 至少 3 个 Worker 节点，每节点 32C/64G（用于通用构建）。
- **GraalVM 专用池:** 2 台高频 CPU（4GHz+）、大内存（128G+）的裸金属服务器。GraalVM 构建不仅吃内存，极其依赖 CPU 单核主频来缩短 Native Compile 时间 ^^。
### 6.2 GraalVM 构建的特殊隔离策略
　　GraalVM Native Image 构建过程极其霸道，会瞬间占满宿主机的所有可用 CPU 和内存。
- **策略 1：Taints &amp; Tolerations (K8s)**
为 GraalVM 专用节点打上污点 `kubectl taint nodes node-graalvm dedicated=graalvm:NoSchedule`​。在 CI Job 中添加对应的容忍度（Tolerations），确保只有 GraalVM 任务调度到这些节点，且**绝对禁止**普通 Java/Node 任务抢占这些资源。
- **策略 2：CPU Pinning (绑核)**
为了保证构建时间的稳定性，建议在 K8s Pod 中通过 CPU Manager Policy 设置为 `static`，独占 CPU 核心，防止上下文切换带来的性能损耗。
### 6.3 镜像管理与复用（Docker Layer Caching）
- **问题：** 每次构建都 `docker build` 会产生大量重复层。
- **解法：** 使用 **Kaniko** 或 ​**BuildKit**。
- **最佳实践：** 搭建私有的 Harbor 镜像仓库，并配置为 **Proxy Cache** 模式代理 Docker Hub。在内网环境中，Runner 拉取基础镜像（如 `openjdk:17-slim`）的速度应达到 Gigabit 线速。
---
## 7. 风险清单与验证计划（PoC）
　　建议开展为期 4 周的概念验证（PoC），以数据驱动决策。
### 7.1 PoC 验证关键指标（KPIs）
|**验证项**|**关键指标 (Metric)**|**验收标准 (Acceptance Criteria)**|**测试方法**|||||
| --| -----------------------------| ---------------------------------------------------------| -----------------------------------------------------------------------------------| --| --| --| --|
|**Maven 并发构建效率**|缓存命中率 (Cache Hit Rate)|\> 90% 的依赖直接从本地/局域网缓存获取|清空 Runner，运行构建，记录耗时；再次运行，耗时应减少 60% 以上。|||||
|**GraalVM 隔离性**|邻居干扰度 (Interference)|GraalVM 构建期间，同节点其他 Pod 响应延迟增加 \< 10%|在同一节点并发运行 Native Build 和 API 压测，监控 CPU Steal 和 Memory Thrashing。|||||
|**事件总线集成**|事件延迟 (E2E Latency)|Build 结束到 Kafka 收到消息 \< 500ms|触发构建，对比 CI 日志时间戳与 Kafka 消息时间戳。|||||
|**弹性伸缩**|冷启动时间 (Cold Start)|新 Runner Pod 启动并接手任务 \< 30s|模拟突发流量（一次性触发 50 个构建），观察 K8s HPA 响应速度。|||||
### 7.2 迁移风险与应对
- **风险：** **Groovy 脚本黑盒化。** 现有的 Shared Library 包含大量未文档化的业务逻辑（如特定的发包逻辑、通知逻辑）。
- **应对：** 在 PoC 阶段，选取最复杂的 3 个 Pipeline 进行“翻译”。如果是 GitLab，尝试用 Template 复现；如果是 TeamCity，用 Kotlin DSL 复现。如果复现成本过高，说明 Jenkins 锁定效应（Vendor Lock-in）极强，需重新评估迁移 ROI。
---
## 8. 结论
　　面对 10 万次/年的构建规模与私有化强集成的需求：
1. **若追求架构的先进性与运维的标准化：** 请选择 ​**GitLab CI/CD**。它用“容器化一切”的理念解决了环境版本管理难题，用 System Hooks 解决了集成难题，是云原生时代的最佳实践。
2. **若受困于超复杂的 Java 构建逻辑与性能瓶颈：** 请选择 ​**TeamCity**。它是构建工程领域的特种兵，能榨干每一分硬件性能，特别是在 GraalVM 和大型 Monorepo 场景下表现无可匹敌。
3. **Jenkins** 只有在经过彻底的“云原生化改造”（JCasC + K8s）后才值得保留，否则它将成为 DevOps 效能提升的最大阻碍。
　　**建议下一步：** 立即搭建 GitLab HA 环境与 Kafka Bridge 进行 PoC，实测 Maven 分布式缓存与 System Hooks 的连通性。

856
15-CICD工具选型/3-per-选型说明.md Normal file
View File

@@ -0,0 +1,856 @@
---
## 1️⃣ 候选工具清单（开源 + 商业对照）
基于你的需求（私有化部署、高并发、强缓存、可二开），以下工具入选：
## 🟢 **开源方案**
1. **Jenkins**（对照基准）- 插件生态最成熟，但架构老旧
2. **GitLab CI + Runner** - 一体化 DevOps 平台，私有化首选
3. **Tekton** - K8s-native，云原生架构，高度可扩展
4. **Argo Workflows** - K8s-native，适合复杂 DAG 编排
5. **Drone** - 轻量级容器化，适合中小规模
6. **GoCD** - 管道可视化强，但社区活跃度下降
## 🟡 **商业/混合方案**
7. **Buildkite** - BYOC 模式，控制面托管 + Agent 自管理
8. **CircleCI Server** - 私有化部署版本，但价格较高
9. **TeamCity** - JetBrains 出品，Java 生态友好，商业授权
10. **Harness** - AI 驱动的 CD 平台，侧重部署编排
## ❌ **未入选原因**
- **GitHub Actions**：虽支持自托管 Runner，但控制面必须依赖 GitHub.com[fuyuan7+1](https://www.fuyuan7.com/post-1172.html)
- **Travis CI**：商业化转型后口碑下降，私有化支持弱
- **Bamboo**：Atlassian 已停止活跃开发
---
## 2️⃣ 对比矩阵表（9 大维度 × 10 个工具）
| **维度/工具** | **Jenkins** | **GitLab CI** | **Tekton** | **Argo Workflows** | **Drone** | **Buildkite** | **TeamCity** | **CircleCI Server** | **GoCD** |
| -- | ----------------------- | ----------------------------- | ---------------------- | ---------------------- | ----------------- | ---------------------- | ----------------- | --------------------- | -------------------- |
| **多语言支持** | ✅ 原生插件 | ✅ Docker 执行器 | ✅ Task 容器化 | ✅ 容器化 | ✅ 容器化 | ✅ 脚本驱动 | ✅ 原生支持 | ✅ 容器化 | ✅ 原生支持 |
| **多版本管理（Node/JDK）** | 🟡 插件 + 容器 | ✅ 镜像 + image 字段 | ✅ 容器镜像 | ✅ 容器镜像 | ✅ 容器镜像 | ✅ 自定义脚本 | ✅ 内置版本管理 | ✅ 容器镜像 | 🟡 手动配置 |
| **Maven 并发构建** | ✅ 插件 + 并行 stage | ✅ 并行 job | ✅ 并行 Task | ✅ 并行 Step | 🟡 基础并行 | ✅ 并行 step | ✅ 并行构建 | ✅ 并行 workflow | ✅ 并行 pipeline |
| **多分支/PR 构建** | ✅ Multibranch Plugin | ✅ 原生支持 | 🟡 需 Triggers 集成 | 🟡 需 Events 集成 | ✅ 原生支持 | ✅ 动态管道 | ✅ 原生支持 | ✅ 原生支持 | ✅ 原生支持 |
| **构建缓存（成熟度）** | 🟡 插件 + 自建 | ✅ 分布式缓存（S3/MinIO）[[cnblogs](https://www.cnblogs.com/Sol-wang/p/16775377.html)] | 🟡 需自建 PVC/S3 | 🟡 需自建 | 🟡 Volume 缓存 | ✅ 插件 + S3 | ✅ 内置缓存 | ✅ 原生缓存 | 🟡 工件缓存 |
| **远程缓存（Gradle/Bazel）** | ⚠️ 手动集成 | ✅ 支持（需配置）[[youtube](https://www.youtube.com/watch?v=zOu3WOKNUcc)][[bitrise](https://bitrise.io/blog/post/bitrise-build-cache-reduces-circleci-build-times)] | ✅ 支持 | ✅ 支持 | ⚠️ 手动集成 | ✅ 支持 | ✅ 支持 | ✅ 支持 | ⚠️ 手动集成 |
| **K8s 动态调度** | 🟡 K8s Plugin | ✅ Runner K8s executor[[gitlab](https://gitlab.cn/docs/runner/fleet_scaling/_index/)] | ✅ 原生 K8s | ✅ 原生 K8s | 🟡 需手动配置 | ✅ Agent K8s 集成 | 🟡 Cloud Agent | ✅ K8s 执行器 | 🟡 弹性 Agent |
| **VM/特定环境构建** | ✅ Docker Machine | ✅ Docker Machine[[gitlab](https://gitlab.cn/docs/runner/configuration/autoscale/)] | 🟡 需自建 | 🟡 需自建 | 🟡 需自建 | ✅ Agent 自定义 | ✅ Cloud Agent | ✅ Machine executor | 🟡 弹性 Agent |
| **队列与优先级** | ✅ Priority Sorter | ✅ resource\_group[[gitlab](https://gitlab.cn/docs/runner/fleet_scaling/_index/)] | 🟡 K8s PriorityClass | 🟡 K8s PriorityClass | ⚠️ 基础队列 | ✅ 高级队列 | ✅ 内置队列 | ✅ 队列管理 | ✅ Pipeline 优先级 |
| **多租户隔离** | 🟡 Folder + Role | ✅ Group/Project 隔离 | ✅ Namespace 隔离 | ✅ Namespace 隔离 | 🟡 Org 隔离 | ✅ Org/Team 隔离 | ✅ Project 隔离 | ✅ Context 隔离 | 🟡 Pipeline Group |
| **事件/Webhook 输出** | ✅ 插件丰富 | ✅ 原生 Webhook | ✅ CloudEvents | ✅ Argo Events | ✅ 原生 Webhook | ✅ Webhook + GraphQL | ✅ Notification | ✅ Webhook | 🟡 通知插件 |
| **API 能力** | ✅ REST API | ✅ REST + GraphQL | ✅ K8s API | ✅ K8s API | ✅ REST API | ✅ GraphQL[[slant](https://www.slant.co/versus/2482/2485/~gitlab-ci_vs_buildkite)] | ✅ REST API | ✅ REST API | ✅ REST API |
| **脚本语法** | Groovy（复杂） | YAML（简洁）[[cnblogs](https://www.cnblogs.com/Sol-wang/p/16775377.html)] | YAML（K8s CRD） | YAML（Workflow） | YAML（简洁）[[juejin](https://juejin.cn/post/7380694342744932390)] | YAML（灵活） | Kotlin DSL | YAML | 声明式 |
| **共享库/模板** | ✅ Shared Library[[blog.csdn](https://blog.csdn.net/weixin_33628677/article/details/150154969)] | ✅ include/extends | ✅ Task Catalog | ✅ Template 库 | 🟡 基础复用 | ✅ 动态模板 | ✅ 模板系统 | ✅ Orb（限 Cloud） | 🟡 模板管道 |
| **插件生态** | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐ |
| **文档质量** | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐ |
| **私有化部署** | ✅ 完全支持 | ✅ 完全支持 | ✅ 完全支持 | ✅ 完全支持 | ✅ 完全支持 | 🟡 BYOC 混合 | ✅ 完全支持 | ✅ 完全支持 | ✅ 完全支持 |
| **高可用（HA）** | 🟡 需 CloudBees | ✅ 多节点 + LB | ✅ K8s 原生 | ✅ K8s 原生 | 🟡 需自建 | ✅ SaaS 控制面 | ✅ 主从模式 | ✅ 集群模式 | 🟡 需手动配置 |
| **学习曲线** | 陡峭（Groovy） | 平缓（YAML） | 中等（K8s） | 中等（K8s） | 平缓 | 平缓 | 中等 | 平缓 | 中等 |
| **成本（10万次/年）** | 低（基础设施） | 低（开源/EE 可选） | 低（仅 K8s） | 低（仅 K8s） | 低（开源） | 高（按用户） | 中（授权费） | 高（企业版） | 低（开源） |
**图例**：
- ✅ 原生支持/成熟度高
- 🟡 需集成/配置/成熟度中
- ⚠️ 需手动实现/风险较高
- ❌ 不支持
---
## 3️⃣ 推荐 Top 3 方案
## 🥇 **方案 1：GitLab CI + K8s Runner（综合最优）**
## **适用场景**
- 需要完整 DevOps 平台（SCM + CI/CD + 制品库 + 安全扫描）
- 团队已有 GitLab 使用经验或愿意投入学习
- 私有化部署 + 高并发构建 + 强缓存需求
## **参考架构**
```
┌─────────────────────────────────────────────────────────┐
│ GitLab Instance（控制面） │
│ ├─ Postgres（元数据） │
│ ├─ Redis（队列/缓存） │
│ └─ Gitaly（Git 存储） │
└─────────────────────────────────────────────────────────┘
↓ gRPC
┌─────────────────────────────────────────────────────────┐
│ GitLab Runner（执行面）- K8s Executor │
│ ├─ Runner Manager（Job 调度） │
│ ├─ Kubernetes Cluster │
│ │ ├─ Build Pod（动态创建/销毁） │
│ │ ├─ PVC（共享缓存：npm/maven/gradle） │
│ │ └─ Pod Priority Class（优先级调度） │
│ └─ Auto-scaling（HPA + Cluster Autoscaler） │
└─────────────────────────────────────────────────────────┘
↓ Webhook/API
┌─────────────────────────────────────────────────────────┐
│ 外部集成 │
│ ├─ 制品库（Nexus/Harbor） │
│ ├─ 消息队列（Kafka - 构建事件） │
│ ├─ 监控（Prometheus + Grafana） │
│ └─ 远程缓存（MinIO/S3 - Gradle/Bazel cache） │
└─────────────────────────────────────────────────────────┘
```
## **构建缓存策略**
1. **依赖缓存**：`.gitlab-ci.yml` 中配置 `cache` 字段，存储到 S3/MinIO[[cnblogs](https://www.cnblogs.com/Sol-wang/p/16775377.html)]
2. **远程构建缓存**：Gradle 配置 `--build-cache`，指向 MinIO endpoint[[youtube](https://www.youtube.com/watch?v=zOu3WOKNUcc)]
3. **Docker 层缓存**：使用 `kaniko` 或 `buildkit` 与 Registry 集成
4. **缓存命中率目标**：60-80%（通过合理的缓存 key 策略）[[bitrise](https://bitrise.io/blog/post/bitrise-build-cache-reduces-circleci-build-times)]
## **从 Jenkins 迁移路径**
1. **Phase 1（2周）** ：
- 部署 GitLab + Runner 测试环境
- 选取 3-5 个简单项目试点（Java/Node）
- Pipeline 脚本从 Jenkinsfile 转换为 `.gitlab-ci.yml`
2. **Phase 2（4周）** ：
- 迁移 20% 项目（优先选择构建频率低的）
- 构建 Shared Template 库（替代 Jenkins Shared Library）
- 配置缓存体系（MinIO + GitLab Cache）
3. **Phase 3（8周）** ：
- 批量迁移剩余项目
- Jenkins 保留特殊场景（如复杂 Groovy 逻辑）
- 双轨运行 3 个月后评估下线 Jenkins
## **风险与限制**
- **Groovy 转换成本**：复杂 Shared Library 需重写为 YAML + 脚本[[blog.csdn](https://blog.csdn.net/weixin_33628677/article/details/150154969)]
- **插件依赖**：部分 Jenkins 插件无对应 GitLab 功能（需自建或接受功能差异）
- **学习曲线**：团队需熟悉 GitLab Runner 的 executor 模型[[gitlab](https://gitlab.cn/docs/runner/fleet_scaling/_index/)]
---
## 🥈 **方案 2：Tekton + Argo Workflows（云原生最佳）**
## **适用场景**
- 已有 K8s 基础设施，团队熟悉 K8s 生态
- 需要极致的可扩展性和定制化（CI/CD as Code）
- 不需要一体化 SCM 平台（Git 使用 GitHub/Gitea 等）
## **参考架构**
```
┌─────────────────────────────────────────────────────────┐
│ Git 仓库（GitHub/Gitea/GitLab） │
└─────────────────────────────────────────────────────────┘
↓ Webhook
┌─────────────────────────────────────────────────────────┐
│ Tekton Triggers（事件监听） │
│ ├─ EventListener（接收 Webhook） │
│ ├─ TriggerBinding（参数提取） │
│ └─ TriggerTemplate（Pipeline 实例化） │
└─────────────────────────────────────────────────────────┘
↓ K8s API
┌─────────────────────────────────────────────────────────┐
│ Tekton Pipelines（核心引擎） │
│ ├─ Task（构建单元：npm install/mvn test） │
│ ├─ Pipeline（编排多个 Task） │
│ ├─ PipelineRun（执行实例） │
│ └─ Workspace（PVC 共享工作区 + 缓存） │
└─────────────────────────────────────────────────────────┘
↓ 并行编排
┌─────────────────────────────────────────────────────────┐
│ Argo Workflows（复杂 DAG） │
│ ├─ Workflow Template（复用逻辑） │
│ ├─ Workflow（复杂依赖关系） │
│ └─ Argo Events（高级事件源：Kafka/SQS） │
└─────────────────────────────────────────────────────────┘
↓ CloudEvents
┌─────────────────────────────────────────────────────────┐
│ 可观测与集成 │
│ ├─ Tekton Dashboard（Web UI） │
│ ├─ Prometheus（指标） │
│ ├─ Elasticsearch（日志） │
│ └─ 消息队列（构建事件 → Kafka） │
└─────────────────────────────────────────────────────────┘
```
## **构建缓存策略**
1. **PVC 共享缓存**：定义 Workspace 指向 RWX PVC（存储 npm cache/maven .m2）
2. **远程缓存**：Task 中配置 Gradle/Bazel remote cache 参数
3. **镜像层缓存**：使用 Tekton Catalog 中的 `buildah`/`kaniko` Task
## **从 Jenkins 迁移路径**
1. **Phase 1（4周）** ：
- 部署 Tekton + Dashboard + Triggers
- 创建 Task Catalog（npm-build、maven-test、docker-build 等）
- 试点 5 个项目，编写 Pipeline YAML
2. **Phase 2（6周）** ：
- 编写 Tekton → Kafka 的事件适配器（自定义 Task）
- 集成 Argo Workflows 处理复杂分支逻辑
- 迁移 30% 项目
3. **Phase 3（8周）** ：
- 批量迁移，建立 Pipeline 模板库
- Jenkins 逐步退役
## **风险与限制**
- **学习成本高**：团队需深入理解 K8s CRD、RBAC、PVC 等概念[[wangsen](https://wangsen.site/2024/12/13/Argo-v-s-Tekton/)]
- **UI 弱**：Tekton Dashboard 功能基础，缺少 Jenkins 级别的可视化[[juejin](https://juejin.cn/post/7209839016966914085)]
- **调试困难**：Pipeline 失败时需通过 `kubectl logs` 查看日志
- **社区分裂**：Tekton vs Argo 社区存在竞争，需选择主导工具[reddit+1](https://www.reddit.com/r/devops/comments/vfpnc8/community_feedback_on_argo_workflows_cd_events_vs/)
---
## 🥉 **方案 3：Buildkite（混合云最佳，但成本高）**
## **适用场景**
- 需要极致的构建性能和无限并发
- 愿意接受"控制面 SaaS + 执行面私有化"的混合模式
- 预算充足（按用户月费，不按分钟计费）
## **参考架构**
```
┌─────────────────────────────────────────────────────────┐
│ Buildkite SaaS（控制面 - 托管） │
│ ├─ Pipeline 管理 │
│ ├─ 队列调度 │
│ ├─ GraphQL API │
│ └─ Webhook 集成 │
└─────────────────────────────────────────────────────────┘
↓ 轮询/WebSocket
┌─────────────────────────────────────────────────────────┐
│ Buildkite Agent（执行面 - 私有化） │
│ ├─ K8s 集群（Agent DaemonSet/StatefulSet） │
│ ├─ Elastic CI Stack（AWS/自建） │
│ ├─ 自定义 Agent（VM/容器/裸机） │
│ └─ 无限并发（按 Agent 数量扩展） │
└─────────────────────────────────────────────────────────┘
↓ 插件系统
┌─────────────────────────────────────────────────────────┐
│ 插件生态 │
│ ├─ Docker Plugin（容器构建） │
│ ├─ S3 Cache Plugin（构建缓存） │
│ ├─ Artifacts（制品存储） │
│ └─ 自定义插件（Shell/Go/Ruby） │
└─────────────────────────────────────────────────────────┘
```
## **构建缓存策略**
1. **S3 Cache Plugin**：自动缓存目录到 S3/MinIO
2. **Docker Layer Cache**：Agent 本地缓存 + Registry 缓存
3. **自定义缓存逻辑**：通过插件或脚本实现 Gradle/Bazel 远程缓存
## **从 Jenkins 迁移路径**
1. **Phase 1（2周）** ：
- 注册 Buildkite 账户，部署 Agent 到测试环境
- 转换 3-5 个 Jenkinsfile 为 `pipeline.yml`
2. **Phase 2（4周）** ：
- 配置 Webhook + 队列策略
- 迁移 20% 项目
3. **Phase 3（6周）** ：
- 批量迁移，逐步下线 Jenkins
## **风险与限制**
- **成本高**：按用户收费（如 50 用户 × \$15/月 \= \$9000/年），但无限并发[[slant](https://www.slant.co/versus/2482/2485/~gitlab-ci_vs_buildkite)]
- **控制面依赖**：必须依赖 Buildkite SaaS，无法完全私有化
- **数据主权**：元数据存储在 Buildkite 云端（需评估合规风险）
- **供应商锁定**：Pipeline 语法专有，迁移出去成本高
---
## 4️⃣ 性能与规模化建议（10万次/年构建）
## **并发模型计算**
**假设条件**：
- 平均每次构建时间：15 分钟
- 每日构建：270 次（平均）
- 峰值时段（工作日 9:00-18:00）：每小时 50 次
**并发需求**：
- 平均并发：`270 次/天 ÷ 24 小时 ÷ 4 (每小时平均) = 11.25 并发`
- 峰值并发：`50 次/小时 ÷ 4 (15分钟) = 12.5 → **约 15 并发**`
**资源配置建议**：
```
# GitLab Runner K8s Executor 示例
[[runners]]
name = "k8s-runner"
limit = 20 # 最大并发 Job
[runners.kubernetes]
namespace = "gitlab-runner"
cpu_request = "2"
cpu_limit = "4"
memory_request = "4Gi"
memory_limit = "8Gi"
# 动态 Pod，构建后自动销毁
```
## **缓存策略（关键性能优化）**
## **三层缓存体系**
1. **L1 本地缓存（Runner/Agent 本地）**
- **适用**：npm cache、maven .m2、gradle cache
- **存储**：Agent 本地磁盘 / K8s hostPath
- **命中率**：80-90%（同 Agent 复用）
- **风险**：Agent 重启丢失
2. **L2 分布式缓存（共享存储）**
- **适用**：多 Runner 共享依赖
- **存储**：NFS / K8s RWX PVC / MinIO
- **命中率**：60-75%
- **实现**：GitLab Cache 配置[[cnblogs](https://www.cnblogs.com/Sol-wang/p/16775377.html)]
```
cache:
key: ${CI_COMMIT_REF_SLUG}
paths:
- node_modules/
- .m2/repository/
policy: pull-push
```
3. **L3 远程构建缓存（Gradle/Bazel Remote Cache）**
- **适用**：增量编译、Monorepo
- **存储**：专用缓存服务（HTTP/gRPC）
- **命中率**：50-70%
- **性能提升**：60-83% 构建加速[[youtube](https://www.youtube.com/watch?v=zOu3WOKNUcc)][[bitrise](https://bitrise.io/blog/post/bitrise-build-cache-reduces-circleci-build-times)]
- **实现**：
```
# Gradle 配置
buildCache {
remote(HttpBuildCache) {
url = 'http://minio.internal:9000/build-cache/'
push = true
}
}
```
## **缓存一致性与污染处理**
**问题**：缓存 key 冲突导致错误复用
**解决方案**：
- **精细化 key**：`${OS}-${ARCH}-${COMPILER_VERSION}-${DEPS_HASH}`
- **定期清理**：每周清理 \>30 天未访问缓存
- **分支隔离**：`master` 与 `feature/*` 使用不同缓存 namespace
- **审计日志**：记录缓存写入/读取，排查污染源
## **队列治理**
**GitLab 示例**：
```
build:
resource_group: production # 同一时间只允许 1 个该组 Job
script: mvn clean package
test:
resource_group: test-pool # 限制测试并发
script: npm test
```
**K8s 示例（Tekton）** ：
```
apiVersion: scheduling.k8s.io/v1
kind: PriorityClass
metadata:
name: high-priority-build
value: 1000 # 高优先级（Hotfix/Release）
---
apiVersion: tekton.dev/v1beta1
kind: PipelineRun
spec:
podTemplate:
priorityClassName: high-priority-build
```
## **Runner/Agent 伸缩策略**
**GitLab Runner HPA（K8s）** ：
```
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: gitlab-runner
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: gitlab-runner
minReplicas: 3
maxReplicas: 20
metrics:
- type: Pods
pods:
metric:
name: gitlab_runner_jobs_queue
target:
type: AverageValue
averageValue: "5" # 每个 Runner 队列 >5 时扩容
```
**Cluster Autoscaler**：
- K8s 节点池自动扩展（AWS EKS / 阿里云 ACK）
- 冷启动时间：3-5 分钟（需预热策略）
## **构建隔离（安全与稳定）**
**三层隔离模型**：
1. **网络隔离**：
- K8s NetworkPolicy：限制 Pod 出站访问
- 构建 Pod 仅允许访问制品库、缓存服务
2. **资源隔离**：
- CPU/内存配额（LimitRange + ResourceQuota）
- 磁盘 I/O 限制（StorageClass QoS）
3. **凭据隔离**：
- K8s Secret + RBAC（每个项目独立 ServiceAccount）
- HashiCorp Vault 动态密钥（构建后自动吊销）
---
## 5️⃣ 二次开发与集成方案
## **构建事件对外传递实现**
## **场景需求**
将构建开始/成功/失败/产物信息传递给：
- 内部发布平台
- 消息通知（钉钉/企业微信）
- 质量分析平台（SonarQube、测试报告）
- 可观测系统（Grafana Dashboard）
## **方案 1：Webhook Push（推荐 - 简单场景）**
**GitLab CI 示例**：
```
stages:
- build
- notify
build:
stage: build
script: mvn clean package
after_script:
- |
curl -X POST https://internal-api.company.com/builds \
-H "Content-Type: application/json" \
-d '{
"project": "'$CI_PROJECT_NAME'",
"commit": "'$CI_COMMIT_SHA'",
"status": "'$CI_JOB_STATUS'",
"artifacts": "'$CI_JOB_URL'/artifacts"
}'
```
**Buildkite 插件**：
```
steps:
- label: ":package: Build"
command: npm run build
plugins:
- artifacts#v1.5.0:
upload: "dist/*"
- webhook-notify#v1.0.0: # 自定义插件
url: https://internal-api.company.com/builds
payload:
build_id: ${BUILDKITE_BUILD_ID}
status: ${BUILDKITE_BUILD_STATUS}
```
**优点**：实现简单，延迟低
**缺点**：无重试机制，目标服务故障导致丢失
---
## **方案 2：消息队列（推荐 - 高可靠场景）**
**架构**：
```
CI/CD 工具 → Kafka Topic (build-events) → 消费者（发布平台/通知服务）
```
**Tekton 自定义 Task**：
```
apiVersion: tekton.dev/v1beta1
kind: Task
metadata:
name: kafka-notify
spec:
params:
- name: event-type
type: string
- name: build-status
type: string
steps:
- name: send
image: confluentinc/cp-kafka:7.3.0
script: |
echo '{
"event": "$(params.event-type)",
"status": "$(params.build-status)",
"timestamp": "'$(date -Iseconds)'"
}' | kafka-console-producer \
--broker-list kafka.internal:9092 \
--topic build-events
```
**Jenkins 插件**（假设使用 Kafka Plugin）：
```
pipeline {
agent any
stages {
stage('Build') {
steps {
sh 'mvn clean package'
}
}
}
post {
always {
kafkaPublish(
topic: 'build-events',
message: """
{
"project": "${env.JOB_NAME}",
"build": "${env.BUILD_NUMBER}",
"status": "${currentBuild.result}"
}
"""
)
}
}
}
```
**优点**：
- 高可靠（持久化、重试）
- 解耦（消费者异步处理）
- 可审计（事件日志）
**缺点**：
- 需维护 Kafka 集群
- 复杂度增加
---
## **方案 3：API 轮询（补充方案）**
**场景**：外部系统主动拉取构建状态
**GitLab API**：
```
# 获取最新 Pipeline 状态
curl -H "PRIVATE-TOKEN: <token>" \
"https://gitlab.company.com/api/v4/projects/123/pipelines/latest"
```
**Buildkite GraphQL**：
```
query {
pipeline(slug: "company/repo") {
builds(first: 10) {
edges {
node {
number
state
createdAt
url
}
}
}
}
}
```
**优点**：无需 CI/CD 工具配置
**缺点**：实时性差，API 调用频率限制
---
## **接口设计要点（事件 Schema）**
**标准化事件结构**（参考 CloudEvents 规范）：
```
{
"specversion": "1.0",
"type": "build.completed",
"source": "gitlab-ci/project/123",
"id": "a3b7c8d9-1234-5678-90ab-cdef12345678",
"time": "2026-02-04T15:30:00Z",
"datacontenttype": "application/json",
"data": {
"project": "backend-service",
"branch": "main",
"commit": "abc123def456",
"build_number": 4567,
"status": "success",
"duration_seconds": 320,
"artifacts": [
{
"name": "backend-service.jar",
"url": "https://nexus.company.com/repository/releases/backend-service-1.2.3.jar",
"checksum": "sha256:abcdef1234567890..."
}
],
"test_results": {
"total": 1523,
"passed": 1520,
"failed": 3
},
"metadata": {
"triggered_by": "user@company.com",
"cache_hit_rate": 0.78
}
}
}
```
**幂等性设计**：
- 事件 ID 唯一（UUID）
- 消费者端去重（Redis/数据库记录已处理事件 ID）
---
## 6️⃣ 风险清单与验证计划（PoC）
## **PoC 周期：2-4 周**
## **Week 1-2：基础功能验证**
| **验证项** | **成功标准** | **测试方法** |
| -- | ------------------------------------- | ------------------------------- |
| **多语言构建** | Node 16/18/20、JDK 8/11/17 构建成功 | 创建包含多版本矩阵的 Pipeline |
| **Maven 并行构建** | 构建时间缩短 \>30% | 对比单线程 vs 多模块并行 |
| **多分支触发** | PR/MR 自动触发构建，状态回写 Git | 提交 PR 测试 |
| **缓存基础功能** | npm/maven 依赖缓存命中率 \>50% | 连续两次构建对比时间 |
| **K8s 动态调度** | Pod 自动创建/销毁，资源隔离有效 | `kubectl top pods`监控资源 |
## **Week 3：性能与规模测试**
| **验证项** | **成功标准** | **测试方法** |
| -- | -------------------------------------- | ------------------------------- |
| **并发吞吐** | 15 并发构建，队列时间 \<2 分钟 | JMeter/自定义脚本触发并发构建 |
| **缓存命中率** | 二次构建缓存命中率 \>60% | 分析构建日志 |
| **弹性伸缩** | Runner 自动扩展至 15 个，缩容至 3 个 | 模拟峰谷流量 |
| **稳定性** | 连续运行 100 次构建，成功率 \>99% | 批量触发构建，记录失败率 |
## **Week 4：集成与可观测性**
| **验证项** | **成功标准** | **测试方法** |
| -- | ----------------------------------------- | ------------------------ |
| **事件传递** | 构建事件 100% 发送至 Kafka/Webhook | 检查消息队列消费日志 |
| **API 调用** | GraphQL/REST API 响应时间 \<500ms | Postman/curl 测试 |
| **监控指标** | Prometheus 采集到构建时长、成功率等指标 | Grafana Dashboard 验证 |
| **日志审计** | 所有构建操作可追溯（用户、时间、参数） | 查询审计日志 |
| **凭据安全** | Secret 不泄漏到日志，仅授权项目可访问 | 安全扫描 + 权限测试 |
## **关键指标收集**
**性能指标**：
```
- 平均排队时间（Queue Time）：目标 <2 分钟
- 平均构建时间（Build Time）：目标缩短 20%（相比 Jenkins）
- 缓存命中率（Cache Hit Rate）：目标 60-80%
- P99 构建时长：目标 <25 分钟
```
**成本指标**：
```
- 单次构建成本（计算资源）：
= (vCPU 小时数 × CPU 单价 + 内存 GB·小时 × 内存单价) / 构建次数
目标：<Jenkins 成本的 70%（通过缓存 + 资源优化）
- 人力成本（运维工时/月）：
目标：<5 人天/月（相比 Jenkins 的 10 人天/月）
```
**稳定性指标**：
```
- 构建成功率（Build Success Rate）：>99%
- 系统可用性（Uptime）：>99.5%
- 故障恢复时间（MTTR）：<30 分钟
```
## **迁移成本评估**
**技术债务清单**：
1. **Pipeline 脚本数量**：统计现有 Jenkinsfile 总数
2. **Shared Library 依赖**：分析哪些可复用、哪些需重写
3. **插件依赖**：列出关键插件，找对应替代方案
4. **定制化逻辑**：识别硬编码在 Groovy 中的业务逻辑
**迁移时间估算**（假设 100 个项目）：
```
- 简单项目（标准 npm/maven）：0.5 天/项目 = 50 天
- 中等项目（多 stage、缓存依赖）：1 天/项目 = 50 天
- 复杂项目（Groovy 重逻辑）：3 天/项目 = 150 天
总计：250 人天 ≈ 2-3 人团队 × 4 个月
```
---
## 7️⃣ 最终建议与决策树
## **决策树**
```
开始
│
├─ 是否已有 K8s 基础设施？
│ ├─ 是 → 团队对 K8s 熟悉度？
│ │ ├─ 高 → **Tekton + Argo** (云原生最佳)
│ │ └─ 中/低 → **GitLab CI + K8s Runner**
│ └─ 否 → 是否愿意引入 K8s？
│ ├─ 是 → **GitLab CI + K8s Runner** (平滑过渡)
│ └─ 否 → **GitLab CI + Docker Executor** 或 **Jenkins 优化**
│
├─ 是否需要完整 DevOps 平台（SCM + CI/CD）？
│ ├─ 是 → **GitLab** (All-in-One)
│ └─ 否 → 已有 Git 服务 → **Buildkite / Tekton / Drone**
│
├─ 预算情况？
│ ├─ 充足 → **Buildkite / TeamCity** (商业支持)
│ └─ 有限 → **GitLab CI / Tekton** (开源)
│
└─ 迁移风险承受度？
├─ 低（稳健迁移）→ **GitLab CI** (与 Jenkins 差异小)
└─ 高（激进重构）→ **Tekton** (云原生架构)
```
## **综合推荐（基于你的场景）**
**场景回顾**：
- ✅ 10 万次/年构建（中等规模）
- ✅ 私有化部署
- ✅ 强缓存需求（Maven/Gradle/npm）
- ✅ 可二次开发（API + 事件集成）
- ✅ 从 Jenkins 迁移
**最佳选择**：**GitLab CI + K8s Runner**
**理由**：
1. **功能完整**：覆盖 SCM + CI/CD + 制品库，减少工具碎片化
2. **迁移成本适中**：YAML 语法接近 Jenkinsfile，学习曲线平缓[[cnblogs](https://www.cnblogs.com/Sol-wang/p/16775377.html)]
3. **缓存成熟**：原生支持分布式缓存 + Gradle/Bazel 远程缓存[[youtube](https://www.youtube.com/watch?v=zOu3WOKNUcc)]
4. **可扩展性强**：K8s Runner 支持动态伸缩，满足 10 万次/年需求[[gitlab](https://gitlab.cn/docs/runner/fleet_scaling/_index/)]
5. **API 丰富**：REST + GraphQL，易于集成外部系统
6. **社区活跃**：文档完善，问题快速解决
7. **成本低**：开源社区版免费，企业版功能可选
**替代选择**：
- 如果团队 K8s 专家充足 → **Tekton**（更灵活，但学习成本高）
- 如果预算充足且追求极致性能 → **Buildkite**（无限并发，但成本高）
---
## 8️⃣ 下一步行动项
## **立即行动（本周）**
1. ✅ 确定 PoC 团队（2-3 人）
2. ✅ 准备 K8s 测试环境（或利用现有）
3. ✅ 部署 GitLab CE + GitLab Runner（K8s Executor）
4. ✅ 选取 3 个试点项目（简单 + 中等 + 复杂各 1 个）
## **第 1-2 周：基础验证**
1. 转换试点项目的 Jenkinsfile → `.gitlab-ci.yml`
2. 配置分布式缓存（MinIO）
3. 测试多语言、多分支构建
## **第 3 周：性能测试**
1. 并发压测（15 并发）
2. 缓存命中率优化
3. 监控指标采集（Prometheus + Grafana）
## **第 4 周：集成测试**
1. 配置 Webhook → Kafka
2. API 集成测试（获取构建状态）
3. 编写 PoC 报告，决策是否全面推广
## **第 2-6 月：全面迁移**
1. 批量迁移项目（分批次）
2. 培训团队（GitLab CI 最佳实践）
3. 建立 Shared Template 库
4. Jenkins 逐步下线（保留 6 个月作为备份）
---
## 📚 参考资料
- GitLab Runner 自动扩缩容文档[gitlab+1](https://gitlab.cn/docs/runner/configuration/autoscale/)
- GitLab CI/CD 私有化部署指南[[cnblogs](https://www.cnblogs.com/Sol-wang/p/16775377.html)]
- Bazel/Gradle 远程缓存性能分析[[bitrise](https://bitrise.io/blog/post/bitrise-build-cache-reduces-circleci-build-times)][[youtube](https://www.youtube.com/watch?v=zOu3WOKNUcc)]
- Tekton vs Argo Workflows 对比[wangsen+1](https://wangsen.site/2024/12/13/Argo-v-s-Tekton/)
- 高并发 CI/CD 架构设计[csdn+1](https://blog.csdn.net/sinat_28461591/article/details/148729218)
- Jenkins Shared Library 迁移策略[[blog.csdn](https://blog.csdn.net/weixin_33628677/article/details/150154969)]
---
**报告生成时间**：2026 年 2 月 4 日
**有效期**：建议 3 个月内复核（CI/CD 工具演进快）
如有具体技术细节需要深入（如某个工具的配置示例、成本计算模型、PoC 脚本等），请随时追问！
添加到后续问题
检查来源

21
16-ProjectMoneyM-转FireFlyIII/1-原始需求/0-产品经理-prompt.md Normal file
View File

@@ -0,0 +1,21 @@
你现在是一名策略产品经理，你擅长进行市场研究和竞品分析，以制定产品策略。你能把握行业趋势，了解用户需求，并在此基础上优化产品功能和用户体验。请在这个角色下为我解答以下问题。
----
你是一名出色的产品经理，能够根据用户的初始需求，理解用户需求的真实需求意图，改善客户不够完善的需求，形成专业、简练的需求文档。并且能够在基础需求上优化产品的额设计和功能
请根据要求,进行深度的思考，优化[1-初始需求稿.md]，直接给出优化后的PRD
注意及要求如下
1. 括号内的内容需要关注,需要根据括号内的内容进行修改,是你需要给出建议的内容,正式文档中应该去掉括号及内容
2. 必要时候应该联网搜索,查询开源的项目实现等
----
你是一名出色的产品经理，请你根据[1-初始需求稿.md]客户的原始需求,审查[2-优化产品需求文档PRD.md],检查PRD文档是否完全满足原始需求;如果有更加优秀的设计方案,请给出修改建议
----
你是一名出色的产品经理，能够根据用户的初始需求，理解用户需求的真实需求意图，改善客户不够完善的需求，形成专业、简练的需求文档。并且能够在基础需求上优化产品的额设计和功能
你之前根据[1-初始需求稿.md]输出了[2-优化产品需求文档PRD.md], 目前初始需求有一些更新,见[1.1-初始需求稿.md],请你详细对比[1.1-初始需求稿.md]和[1-初始需求稿.md]之间的差异, 修改[2-优化产品需求文档PRD.md],得到新的需求文档

83
16-ProjectMoneyM-转FireFlyIII/1-原始需求/1-初始需求稿.md Normal file
View File

@@ -0,0 +1,83 @@
# 个人财务分析系统
``` 项目名称: ProjectMoneyM ```
``` 项目版本: v1.0 ```
``` 项目编制日期: 2026-02-26 ```
## 数据来源
1. 数据来源
| 数据来源 | 最长周期 | 文件格式 | 说明 | 数据维度 |
| --- | --- | --- | --- | --- |
| 支付宝账单 | 1年 | csv | 第一来源 | 最全 |
| 微信账单 | 3个月 | csv | 第二来源 | 第二全 |
| 招商银行 | 1年 | pdf | 第三来源 | 第三全 |
| 京东商城 | 1年 | pdf | 第四来源 | 第四全 |
2. 数据解析工具
1. 能够读取不同格式的账单来源
2. 能够通过OCR的方式解析特定的收入数据
## 数据清洗及标准化
1. 时间维度清洗
1. 需要统一时间维度,统一为东八区时间,格式为yyyy-MM-dd HH:mm:ss
2. 数据展示环节 需要能够通过时间段进行筛选查询收支数据
2. 支付项目清洗
1. 需要过滤重复的支付项
2. 需要明确支付途径和支付卡
3. 例如,一笔支出,银行账单会记录支出,支付宝或者微信会记录支出,需要将这些重复的支付项合并
4. 支付途径为: 支付宝,微信,云闪付,京东,美团,拼多多
5. 实际支付卡为: 信用卡,借记卡,余额宝,微信钱包,支付宝钱包
6. 支出项目的账本归类
1. 一笔支出可以归于一个或者多个账本
2. 一笔支出需要在日常开支中进行分析,也需要在过年支出这种特殊的账本中进行分析
3. 支付金额清洗
1. 需要统一为标准的数据格式
4. 支出去向清洗
1. 需要将支出进行分类
2. 请参考支付宝的支出分类
## 收支情况 展示内容
```此部分重要使用前端图表工具进行绘图展示```
### 收支分析(请给出能够展示的图形类型)
1. 需要直观的看出结余情况, 收入大于支出,支出大于收入的对比
2. 时间维度为,月度,季度,年度,重点展示月度收支情况
3. 收支的最小维度为月度
### 收入分析(请给出能够展示的图形类型)
#### 收入趋势
1. 能够根据不同的时间维度进行收入的对比
2. 能够直观的展示收入的趋势
#### 收入总览
1. 收入来源占比分析
2. 时间维度,重点展示年度收入,季度收入
3. 收入的最小维度为月度
#### 收入
### 支出分析(请给出能够展示的图形类型)
#### 支出趋势
1. 能够根据不同的时间维度进行支出的对比
2. 能够直观的展示支出的趋势
#### 支出总览
1. 支出去向占比分析
2. 时间维度,重点展示年度支出,季度支出
3. 支出的最小维度为月度
### 展示内容导出
1. 支持将展示内容导出为图片
2. 支持将展示内容导出为PDF文件
## 技术栈
1. Golang
2. Vue
3. TypeScript
4. SQLite
5. ECharts(寻找适合的图表工具,不限于ECharts)

106
16-ProjectMoneyM-转FireFlyIII/1-原始需求/2-1-优化产品需求文档PRD.md Normal file
View File

@@ -0,0 +1,106 @@
# 产品需求文档 (PRD): ProjectMoneyX 个人全景财务分析系统
| 文档属性 | 详情 |
| --- | --- |
| **项目名称** | ProjectMoneyX |
| **版本号** | v1.2 (基于开源 ETL 架构优化版) |
| **编制日期** | 2026-02-26 |
| **文档状态** | 进行中 |
## 1. 项目背景与目标
### 1.1 项目背景
随着移动支付的普及，个人财务数据分散在支付宝、微信、各家银行及电商平台中。用户面临“账单碎片化”、“流水重复记录”等痛点。传统的记账软件通常依赖手动记录或单一的账单导入，缺乏灵活的规则引擎来处理复杂的跨账户对账。
### 1.2 项目目标
构建一套自动化、高精度的个人财务分析系统。借鉴开源社区成熟的双轨制记账流转架构，通过引入 `Provider` 解析器与 `Translate` 规则引擎，实现多源数据的标准化转换（IR），并利用算法解决跨账户流水重复问题，提供多维度的收支分析与预算管理功能。
---
## 2. 核心系统架构：ETL 数据工作流
参考业内成熟方案，系统底层采用高度解耦的管道架构，确保后续极强的可扩展性：
**数据流转路径：** `原始账单 (Raw Files) -> 提供方解析 (Provider) -> 中间表示 (IR) -> 规则转换 (Translate) -> 数据库标准账单`
* **Provider 层：** 专注于“读”。屏蔽不同账单格式（CSV, PDF, Excel）的差异。
* **IR 层 (Intermediate Representation)：** 统一的数据结构协议，作为 Provider 和 Translate 的桥梁。
* **Translate 层：** 专注于“洗”。基于 YAML/JSON 规则配置，执行分类映射、时间标准化与账户归属。
---
## 3. 数据采集与 Provider 模块 (Data Ingestion)
针对不同来源的账单，建立独立的 Provider 适配器。当某银行账单格式更新时，仅需修改或新增对应的 Provider，不影响系统核心逻辑。
| 提供方 (Provider) | 原始格式 | 核心提取字段 | 数据权重 | 提取说明 |
| --- | --- | --- | --- | --- |
| **Alipay (支付宝)** | CSV | 订单号、商户、商品明细、金额 | **L1 (最高)** | 标准 CSV 解析，作为消费类主数据。 |
| **WeChat (微信支付)** | CSV | 交易单号、交易对方、交易类型 | **L2** | 预处理跳过表头，提取转账与红包标记。 |
| **Banks (招商/工行等)** | PDF/XLS | 交易日、交易摘要、收支金额 | **L3** | 作为资金实际扣款核对依据 (Reconciliation)。 |
| **JD/Meituan (电商)** | PDF/CSV | 订单明细、支付通道 | **L3** | 重点关注白条/月付等信用支付记录。 |
---
## 4. 数据转换与清洗逻辑 (Translate & Cleaning)
Translate 层是数据质量的核心把控者，负责将 IR 数据转换为最终的财务记录，并解决数据冲突。
### 4.1 Translate 规则引擎
建立基于配置文件的映射规则，实现自动化数据归位：
* **时间与时区标准化：** 统一转换为 ISO 8601 格式，所有国内交易归一化为东八区时间。
* **账户路由 (Account Routing)：** * *规则示例：* 当 Provider 为 `Alipay`，且原始数据中的支付方式为“招商银行信用卡”时，资金来源（Funding Source）自动映射至用户的“招行信用卡”实体账户。
* **智能分类映射 (Category Mapping)：**
* 根据交易对方 (Peer) 或 商品说明 (Item) 进行正则匹配。
* *规则示例：* `Peer` 包含“星巴克”或“瑞幸” -> 映射分类为 [餐饮-咖啡]。
### 4.2 交易链路合并与去重算法 (De-duplication)
同一笔交易会在支付平台（如微信）和资金源（如银行卡）各产生一条流水。系统通过**时间窗与金额双重校验**进行链路合并，而非粗暴删除。
**核心算法逻辑：**
设高权重账单记录为 $T_{primary}$（如支付宝），低权重账单记录为 $T_{secondary}$（如银行卡）。
当同时满足以下条件时，判定为同一条交易链路：
$$| Time(T_{primary}) - Time(T_{secondary}) | \le \Delta t \quad (\text{建议 } \Delta t = 120s)$$
$$Amount(T_{primary}) = Amount(T_{secondary})$$
**处理策略：**
1. 将两条记录在底层数据库建立关联（Parent-Child 或 LinkID）。
2. 前端展示时，**合并为一笔记录**。保留 $T_{primary}$ 的丰富消费明细（如分类、商户名），将 $T_{secondary}$ 的账户信息作为该笔消费的资金出处。
---
## 5. 核心功能模块详述
### 5.1 全景仪表盘 (Dashboard)
* **资产负债表：** 实时聚合各账户总资产、总负债（信用卡/白条），计算净资产。
* **现金流概览：** 本月总收入 vs 总支出，环比上月 (MoM) 增减百分比。
### 5.2 账单查询与多维分析
* **组合漏斗筛选：** 支持时间范围、金额区间、支付渠道、资金账户、交易分类的多条件交叉查询。
* **可视化图表：**
* **消费结构：** 饼图展示各大类的支出占比。
* **资金流向 (Sankey Diagram)：** 桑基图直观展示“收入源 -> 资金池 (账户) -> 支出分类”的完整链路。
### 5.3 预算管理
* **精细化限额：** 支持全局预算和分类预算（例如：设定“交通”每月额度 1000 元）。
* **阈值预警：** 当分类支出进度达到 80% 和 100% 时，系统触发视觉高亮预警。
---
## 6. 非功能需求 (NFR)
* **数据隐私 (Local-First)：** 财务数据极其敏感，系统解析 (Provider) 和转换 (Translate) 过程应优先在客户端（本地环境）执行，拒绝未经加密的云端明文传输。

139
16-ProjectMoneyM-转FireFlyIII/1-原始需求/2-优化产品需求文档PRD.md Normal file
View File

@@ -0,0 +1,139 @@
# 产品需求文档 (PRD): ProjectMoneyX 个人全景财务分析系统
| 文档属性 | 详情 |
| --- | --- |
| **项目名称** | ProjectMoneyX |
| **版本号** | v1.1 (优化版) |
| **编制日期** | 2026-02-26 |
## 1. 项目背景与目标
### 1.1 项目背景
随着移动支付的普及，个人财务数据分散在支付宝、微信、各家银行APP及电商平台中。用户难以通过单一平台获取全景财务状况，面临“账单碎片化”、“流水重复记录”、“统计维度单一”等痛点。
### 1.2 项目目标
构建一套自动化、高精度的个人财务分析系统。通过ETL（抽取、转换、加载）技术整合多源数据，利用算法解决跨账户流水重复问题，提供多维度的收支分析、资产趋势及预算管理功能，帮助用户实现“上帝视角”的财务管控。
---
## 2. 数据源与采集规范 (Data Ingestion)
系统需支持多格式、多来源的账单导入，并建立可扩展的解析适配器模式。
| 数据来源 | 原始格式 | 数据周期 | 解析策略 | 数据权重 | 备注 |
| --- | --- | --- | --- | --- | --- |
| **支付宝** | CSV | 1年 | Pandas直接读取 | **L1 (最高)** | 包含商品明细，作为消费类主数据 |
| **微信支付** | CSV | 3个月 | Pandas预处理 (表头清洗) | **L2** | 包含转账与社交红包，需特殊标记 |
| **招商银行** | PDF | 1年 | 文本流解析 (pdfplumber) | **L3** | 作为资金来源核对依据 (Reconciliation) |
| **京东金融** | PDF/XLS | 1年 | 文本流解析 / OCR辅助 | **L3** | 重点关注“白条”类信贷数据 |
| **云闪付** | PDF/CSV | 1年 | 适配器解析 | **L3** | 银联通道补充数据 |
**功能要求：**
* **适配器模式（Adapter Pattern）：** 针对不同来源开发独立的解析类（Parser Class），当银行账单格式变更时，仅需更新对应解析器。
* **OCR 增强解析：** 针对图片格式的账单或非标准的扫描版PDF，集成 OCR 引擎（如 PaddleOCR）进行关键字段（日期、金额、商户）提取。
---
## 3. 数据清洗与核心逻辑 (Data Cleaning & Logic)
这是本系统的核心壁垒，重点解决多渠道数据冲突与标准化问题。
### 3.1 时间维度标准化
* **存储标准：** 所有交易时间戳统一转换为 **ISO 8601** 格式存储。
* **时区处理：** 统一归一化为 `UTC+8`。若涉及跨国交易（如外币信用卡），需保留原始交易币种和时间，并记录当期汇率。
* **查询支持：** 数据库层需支持基于时间窗口（Time Window）的聚合查询（如：`BETWEEN '2026-02-01' AND '2026-02-28'`）。
### 3.2 交易去重与链路合并 (De-duplication & Linkage)
初始需求中提到的“重复项”实际上是“同一笔交易在不同账户的映射”。系统不应简单删除，而应建立**交易链路（Transaction Linkage）**。
**核心算法逻辑：**
设支付宝账单记录为 $T_{ali}$，银行账单记录为 $T_{bank}$。
当满足以下条件时，判定为同一笔交易：
$$| Time(T_{ali}) - Time(T_{bank}) | \le \Delta t \quad (\text{建议 } \Delta t = 120s)$$
$$Amount(T_{ali}) = Amount(T_{bank})$$
**处理策略：**
1. **合并展示：** 将两条记录关联。
* **主记录（保留）：** 支付宝/微信记录（因其包含具体的商户名、商品名、消费分类）。
* **辅记录（隐藏/标记）：** 银行卡记录标记为“资金划转（Transfer）”或“支付源扣款”。
2. **账户归属明确：**
* **支付渠道（Payment Channel）：** 支付宝、微信、云闪付、美团。
* **资金账户（Funding Source）：** 招商银行信用卡、工商银行储蓄卡、京东白条、余额宝。
* *示例：* 用户在淘宝买衣服，用支付宝绑定的招行卡支付。系统记录为：**支出 200元 (分类:服饰)**，支付渠道：**支付宝**，资金来源：**招行信用卡**。
### 3.3 智能分类 (Smart Categorization)
* **多级分类体系：**
* 一级分类：餐饮、交通、购物、居住、娱乐、医疗、金融。
* 二级分类：早餐/正餐、地铁/打车、数码/服饰、房租/水电。
* **关键词映射：** 建立 `Merchant_Keyword_Map` 表。
* 例：包含“星巴克”、“瑞幸” -> 自动归类为 [餐饮-咖啡]。
* 例：包含“中国石油” -> 自动归类为 [交通-加油]。
* **人工修正与学习：** 用户手动修改某一笔交易分类后，系统询问“是否将该商户后续交易默认应用此分类”。
---
## 4. 功能模块详述
### 4.1 仪表盘 (Dashboard)
* **全景资产卡片：** 显示总资产、总负债（信用卡+白条+花呗）、净资产。
* **本月收支概览：** * 当月支出 vs 上月同期环比 (MoM)。
* 预算执行进度条（如：本月预算剩余 30%）。
* **收支趋势图：** 折线图展示近12个月的收支波动。
### 4.2 账单查询与分析
* **高级筛选器：** 支持组合条件筛选：
* 时间范围（自定义/本周/本月/本年）。
* 金额区间（如：> 1000元的大额支出）。
* 支付渠道 & 资金账户。
* 交易分类。
* 关键词搜索（如：“京东”）。
* **多维图表：**
* [饼图] 消费结构分析（哪类钱花得最多）。
* [堆叠柱状图] 支付渠道依赖度分析。
* [桑基图 (Sankey Diagram)] 资金流向可视化（从收入 -> 账户 -> 支出类别）。
### 4.3 预算与预警
* **预算设置：** 支持总预算及分分类预算（如：“餐饮”每月限额 3000元）。
* **超支预警：** 当某一类别支出达到预算的 80% 时，界面高亮提示。
---
## 5. 非功能需求 (NFR)
### 5.1 数据隐私与安全
* **本地优先（Local-First）：** 鉴于财务数据极度敏感，建议所有数据解析、清洗、存储默认在用户本地电脑中完成。
---
## 技术栈
1. Golang
2. Vue
3. TypeScript
4. SQLite
5. ECharts(寻找适合的图表工具,不限于ECharts)

33
16-ProjectMoneyM-转FireFlyIII/2-概要详细设计/0-概要设计prompt.md Normal file
View File

@@ -0,0 +1,33 @@
你是一名资深的软件系统架构师，具备以下核心职责与能力，绘图请使用mermaid语言：
## 需求分析与理解
- 深度解读产品需求文档（PRD），识别业务目标、功能需求与非功能性需求
- 分析需求间的依赖关系与优先级，识别潜在的技术风险与挑战
## 架构设计与规划
- 设计高可用、可扩展、高性能的系统架构，确保系统健壮性与安全性
- 制定技术选型方案，包括开发语言、框架、中间件、数据库等关键技术栈
- 绘制多层次架构图（系统架构图、数据流图、组件交互图）
- 定义模块划分、接口规范、数据模型与核心算法策略
- 规划系统分层结构（展现层、业务层、数据层），明确各层职责边界
## 方案设计与输出
- 针对核心需求点提供详细的技术解决方案，包含实现路径与备选方案
- 设计关键业务流程的时序图与状态机，确保逻辑清晰完整
- 输出规范化的《系统详细设计说明书》，包含架构设计、接口定义、数据库设计等完整文档
## 技术栈说明
- 后端开发技术栈 Golang GROM GIN
- 前端开发技术栈 Vue3 TypeScript Vuetify
## 参考项目
- 项目有非常完善的数据清洗工具，基本满足了数据读取部分，可以摘取此项目的数据translate provider部分代码 [double-entry-generator](https://github.com/deb-sig/double-entry-generator)
请根据[2-优化产品需求文档PRD.md]，按照上述的要求，输出系统详细设计说明书
你之前根据[2-优化产品需求文档PRD.md]输出了[3-详细设计说明书.md], 目前PRD需求有一些更新,见[2.1-优化产品需求文档PRD.md],请你详细对比[2.1-优化产品需求文档PRD.md]和[2-优化产品需求文档PRD.md]之间的差异, 修改[3-详细设计说明书.md],得到新的需求文档.要求尽量不改动[3-详细设计说明书.md]的初始设计,只改动差异化部分的设计

1785
16-ProjectMoneyM-转FireFlyIII/2-概要详细设计/3-详细设计说明书.md Normal file
View File

File diff suppressed because it is too large Load Diff

106
16-ProjectMoneyM-转FireFlyIII/3-实现详细稿/1-ProjectMoneyM-PRD.md Normal file
View File

@@ -0,0 +1,106 @@
# 产品需求文档 (PRD): ProjectMoneyX 个人全景财务分析系统
| 文档属性 | 详情 |
| --- | --- |
| **项目名称** | ProjectMoneyX |
| **版本号** | v1.2 (基于开源 ETL 架构优化版) |
| **编制日期** | 2026-02-26 |
| **文档状态** | 进行中 |
## 1. 项目背景与目标
### 1.1 项目背景
随着移动支付的普及，个人财务数据分散在支付宝、微信、各家银行及电商平台中。用户面临“账单碎片化”、“流水重复记录”等痛点。传统的记账软件通常依赖手动记录或单一的账单导入，缺乏灵活的规则引擎来处理复杂的跨账户对账。
### 1.2 项目目标
构建一套自动化、高精度的个人财务分析系统。借鉴开源社区成熟的双轨制记账流转架构，通过引入 `Provider` 解析器与 `Translate` 规则引擎，实现多源数据的标准化转换（IR），并利用算法解决跨账户流水重复问题，提供多维度的收支分析与预算管理功能。
---
## 2. 核心系统架构：ETL 数据工作流
参考业内成熟方案，系统底层采用高度解耦的管道架构，确保后续极强的可扩展性：
**数据流转路径：** `原始账单 (Raw Files) -> 提供方解析 (Provider) -> 中间表示 (IR) -> 规则转换 (Translate) -> 数据库标准账单`
* **Provider 层：** 专注于“读”。屏蔽不同账单格式（CSV, PDF, Excel）的差异。
* **IR 层 (Intermediate Representation)：** 统一的数据结构协议，作为 Provider 和 Translate 的桥梁。
* **Translate 层：** 专注于“洗”。基于 YAML/JSON 规则配置，执行分类映射、时间标准化与账户归属。
---
## 3. 数据采集与 Provider 模块 (Data Ingestion)
针对不同来源的账单，建立独立的 Provider 适配器。当某银行账单格式更新时，仅需修改或新增对应的 Provider，不影响系统核心逻辑。
| 提供方 (Provider) | 原始格式 | 核心提取字段 | 数据权重 | 提取说明 |
| --- | --- | --- | --- | --- |
| **Alipay (支付宝)** | CSV | 订单号、商户、商品明细、金额 | **L1 (最高)** | 标准 CSV 解析，作为消费类主数据。 |
| **WeChat (微信支付)** | CSV | 交易单号、交易对方、交易类型 | **L2** | 预处理跳过表头，提取转账与红包标记。 |
| **Banks (招商/工行等)** | PDF/XLS | 交易日、交易摘要、收支金额 | **L3** | 作为资金实际扣款核对依据 (Reconciliation)。 |
| **JD/Meituan (电商)** | PDF/CSV | 订单明细、支付通道 | **L3** | 重点关注白条/月付等信用支付记录。 |
---
## 4. 数据转换与清洗逻辑 (Translate & Cleaning)
Translate 层是数据质量的核心把控者，负责将 IR 数据转换为最终的财务记录，并解决数据冲突。
### 4.1 Translate 规则引擎
建立基于配置文件的映射规则，实现自动化数据归位：
* **时间与时区标准化：** 统一转换为 ISO 8601 格式，所有国内交易归一化为东八区时间。
* **账户路由 (Account Routing)：** * *规则示例：* 当 Provider 为 `Alipay`，且原始数据中的支付方式为“招商银行信用卡”时，资金来源（Funding Source）自动映射至用户的“招行信用卡”实体账户。
* **智能分类映射 (Category Mapping)：**
* 根据交易对方 (Peer) 或 商品说明 (Item) 进行正则匹配。
* *规则示例：* `Peer` 包含“星巴克”或“瑞幸” -> 映射分类为 [餐饮-咖啡]。
### 4.2 交易链路合并与去重算法 (De-duplication)
同一笔交易会在支付平台（如微信）和资金源（如银行卡）各产生一条流水。系统通过**时间窗与金额双重校验**进行链路合并，而非粗暴删除。
**核心算法逻辑：**
设高权重账单记录为 $T_{primary}$（如支付宝），低权重账单记录为 $T_{secondary}$（如银行卡）。
当同时满足以下条件时，判定为同一条交易链路：
$$| Time(T_{primary}) - Time(T_{secondary}) | \le \Delta t \quad (\text{建议 } \Delta t = 120s)$$
$$Amount(T_{primary}) = Amount(T_{secondary})$$
**处理策略：**
1. 将两条记录在底层数据库建立关联（Parent-Child 或 LinkID）。
2. 前端展示时，**合并为一笔记录**。保留 $T_{primary}$ 的丰富消费明细（如分类、商户名），将 $T_{secondary}$ 的账户信息作为该笔消费的资金出处。
---
## 5. 核心功能模块详述
### 5.1 全景仪表盘 (Dashboard)
* **资产负债表：** 实时聚合各账户总资产、总负债（信用卡/白条），计算净资产。
* **现金流概览：** 本月总收入 vs 总支出，环比上月 (MoM) 增减百分比。
### 5.2 账单查询与多维分析
* **组合漏斗筛选：** 支持时间范围、金额区间、支付渠道、资金账户、交易分类的多条件交叉查询。
* **可视化图表：**
* **消费结构：** 饼图展示各大类的支出占比。
* **资金流向 (Sankey Diagram)：** 桑基图直观展示“收入源 -> 资金池 (账户) -> 支出分类”的完整链路。
### 5.3 预算管理
* **精细化限额：** 支持全局预算和分类预算（例如：设定“交通”每月额度 1000 元）。
* **阈值预警：** 当分类支出进度达到 80% 和 100% 时，系统触发视觉高亮预警。
---
## 6. 非功能需求 (NFR)
* **数据隐私 (Local-First)：** 财务数据极其敏感，系统解析 (Provider) 和转换 (Translate) 过程应优先在客户端（本地环境）执行，拒绝未经加密的云端明文传输。

951
16-ProjectMoneyM-转FireFlyIII/3-实现详细稿/2-ProjectMoneyM-DDS.md Normal file
View File

@@ -0,0 +1,951 @@
# 系统详细设计说明书 (DDS): ProjectMoneyX 个人全景财务分析系统
| 文档属性 | 详情 |
| --- | --- |
| **项目名称** | ProjectMoneyX |
| **版本号** | v1.0 |
| **编制日期** | 2026-02-26 |
| **文档状态** | 初稿 |
| **技术栈** | Golang (Gin + GORM) / Vue3 + TypeScript + Vuetify / ECharts |
| **参考项目** | [double-entry-generator](https://github.com/deb-sig/double-entry-generator) |
---
## 1. 系统总体架构
### 1.1 架构概览
系统采用前后端分离的 B/S 架构，后端以 Golang Gin 框架提供 RESTful API，前端以 Vue3 + Vuetify 构建 SPA 应用。核心数据处理流程借鉴 `double-entry-generator` 的 **Provider → IR → Translate** 管道模式，将其从命令行工具改造为 Web 服务。
```mermaid
graph TB
subgraph Frontend["前端 (Vue3 + Vuetify + ECharts)"]
UI_Upload["账单上传"]
UI_Dashboard["全景仪表盘"]
UI_Query["账单查询与分析"]
UI_Budget["预算管理"]
UI_Account["账户管理"]
UI_Rule["规则配置"]
end
subgraph Backend["后端 (Golang Gin)"]
API["RESTful API Layer (Gin Router)"]
SVC["Service Layer"]
ETL["ETL Pipeline"]
subgraph ETL_Detail["ETL 管道"]
Provider["Provider 解析层"]
IR["IR 中间表示层"]
Translate["Translate 规则引擎"]
Dedup["去重引擎"]
end
REPO["Repository Layer (GORM)"]
end
subgraph Storage["数据存储"]
DB["SQLite / MySQL"]
FileStore["本地文件存储"]
end
Frontend -->|HTTP/JSON| API
API --> SVC
SVC --> ETL
ETL_Detail --> REPO
SVC --> REPO
REPO --> DB
Provider --> FileStore
```
### 1.2 分层架构说明
| 层级 | 职责 | 技术选择 |
| --- | --- | --- |
| **展现层 (Presentation)** | UI 渲染、用户交互、数据可视化 | Vue3 + Vuetify + ECharts |
| **API 层 (API Gateway)** | 路由分发、参数校验、认证鉴权、响应封装 | Gin Framework |
| **业务层 (Service)** | 核心业务逻辑编排、ETL 流程调度 | Go Service |
| **数据处理层 (ETL Pipeline)** | Provider 解析、IR 转换、Translate 规则、去重合并 | Go (参考 double-entry-generator) |
| **数据访问层 (Repository)** | ORM 映射、数据库 CRUD | GORM |
| **数据存储层 (Storage)** | 持久化存储 | SQLite (默认, Local-First) / MySQL (可选) |
---
## 2. 后端详细设计
### 2.1 项目目录结构
```
projectmoneyx-server/
├── main.go # 程序入口
├── config/
│ └── config.go # 配置加载 (YAML)
├── internal/
│ ├── api/ # API 层 (Gin Handler)
│ │ ├── router.go # 路由注册
│ │ ├── middleware/ # 中间件 (CORS, Logger, Auth)
│ │ ├── handler/
│ │ │ ├── bill_handler.go
│ │ │ ├── account_handler.go
│ │ │ ├── budget_handler.go
│ │ │ ├── dashboard_handler.go
│ │ │ ├── category_handler.go
│ │ │ └── rule_handler.go
│ │ └── dto/ # 请求/响应 DTO
│ │ ├── request.go
│ │ └── response.go
│ ├── service/ # 业务层
│ │ ├── bill_service.go
│ │ ├── account_service.go
│ │ ├── budget_service.go
│ │ ├── dashboard_service.go
│ │ └── import_service.go # ETL 编排
│ ├── etl/ # ETL 管道 (核心)
│ │ ├── pipeline.go # 管道编排器
│ │ ├── provider/ # Provider 层 (参考 double-entry-generator)
│ │ │ ├── interface.go # Provider 接口定义
│ │ │ ├── alipay/
│ │ │ │ ├── alipay.go
│ │ │ │ └── parse.go
│ │ │ ├── wechat/
│ │ │ │ ├── wechat.go
│ │ │ │ └── parse.go
│ │ │ └── bank/
│ │ │ ├── cmb.go # 招商银行
│ │ │ └── icbc.go # 工商银行
│ │ ├── ir/ # IR 中间表示
│ │ │ └── ir.go
│ │ ├── translate/ # Translate 规则引擎
│ │ │ ├── engine.go
│ │ │ ├── category.go
│ │ │ └── account.go
│ │ └── dedup/ # 去重引擎
│ │ └── dedup.go
│ ├── model/ # GORM 数据模型
│ │ ├── bill.go
│ │ ├── account.go
│ │ ├── category.go
│ │ ├── budget.go
│ │ └── rule.go
│ └── repository/ # 数据访问层
│ ├── bill_repo.go
│ ├── account_repo.go
│ └── budget_repo.go
├── configs/
│ ├── app.yaml # 应用配置
│ └── rules/ # Translate 规则配置
│ ├── category_rules.yaml
│ └── account_rules.yaml
└── uploads/ # 上传文件临时存储
```
### 2.2 ETL 管道核心设计
#### 2.2.1 Provider 接口定义
借鉴 `double-entry-generator` 的 Provider 模式，定义统一接口：
```go
// internal/etl/provider/interface.go
package provider
import "projectmoneyx/internal/etl/ir"
// Provider 定义账单解析器的通用接口
type Provider interface {
// Translate 将原始账单文件解析为 IR 中间表示
Translate(filename string) (*ir.IR, error)
// Name 返回 Provider 名称
Name() string
// SupportedFormats 返回支持的文件格式
SupportedFormats() []string
}
// ProviderFactory Provider 工厂，根据类型创建对应 Provider
func NewProvider(providerType string) (Provider, error) {
switch providerType {
case "alipay":
return alipay.New(), nil
case "wechat":
return wechat.New(), nil
case "cmb":
return bank.NewCMB(), nil
default:
return nil, fmt.Errorf("unsupported provider: %s", providerType)
}
}
```
#### 2.2.2 IR 中间表示结构
参考 `double-entry-generator` 的 `ir.Order` 结构，针对个人财务场景扩展：
```go
// internal/etl/ir/ir.go
package ir
import "time"
// IR 中间表示，作为 Provider 与 Translate 的桥梁
type IR struct {
Orders []Order `json:"orders"`
}
// Order 统一的订单中间表示
type Order struct {
// --- 基础字段 (对齐 double-entry-generator) ---
Peer string `json:"peer"` // 交易对方
Item string `json:"item"` // 商品说明
Category string `json:"category"` // 原始分类
Money float64 `json:"money"` // 交易金额
PayTime time.Time `json:"pay_time"` // 支付时间 (ISO 8601)
Type TxType `json:"type"` // 收/支/其他
TypeOriginal string `json:"type_original"` // 原始交易类型文本
Method string `json:"method"` // 支付方式
MerchantOrderID string `json:"merchant_order_id"` // 商户订单号
OrderID string `json:"order_id"` // 交易单号
Status string `json:"status"` // 交易状态
Note string `json:"note"` // 备注
// --- ProjectMoneyX 扩展字段 ---
ProviderName string `json:"provider_name"` // 来源 Provider
DataWeight int `json:"data_weight"` // 数据权重 (L1=1, L2=2, L3=3)
Currency string `json:"currency"` // 币种，默认 CNY
Metadata map[string]string `json:"metadata"` // 扩展元数据
}
// TxType 交易方向
type TxType string
const (
TxTypeSend TxType = "Send" // 支出
TxTypeRecv TxType = "Recv" // 收入
TxTypeUnknown TxType = "Unknown" // 未知
)
```
#### 2.2.3 Translate 规则引擎
```go
// internal/etl/translate/engine.go
package translate
// TranslateEngine 规则引擎核心
type TranslateEngine struct {
CategoryRules []CategoryRule `yaml:"category_rules"`
AccountRules []AccountRule `yaml:"account_rules"`
}
// CategoryRule 分类映射规则
type CategoryRule struct {
Match MatchCondition `yaml:"match"`
Category string `yaml:"category"` // 目标分类 (如 "餐饮-咖啡")
Priority int `yaml:"priority"` // 规则优先级
}
// AccountRule 账户路由规则
type AccountRule struct {
Provider string `yaml:"provider"` // Provider 名称 (如 "alipay")
MethodMatch string `yaml:"method_match"` // 支付方式正则
AccountID uint `yaml:"account_id"` // 目标账户 ID
}
// MatchCondition 匹配条件
type MatchCondition struct {
Field string `yaml:"field"` // 匹配字段: peer / item / category
Pattern string `yaml:"pattern"` // 正则表达式
}
// Apply 对 IR 应用规则转换
func (e *TranslateEngine) Apply(irData *ir.IR) ([]model.Bill, error) {
// 1. 时间标准化 (ISO 8601, UTC+8)
// 2. 遍历每条 Order，匹配 CategoryRules 进行分类
// 3. 遍历每条 Order，匹配 AccountRules 进行账户路由
// 4. 转换为 model.Bill 结构
}
```
#### 2.2.4 去重引擎
```go
// internal/etl/dedup/dedup.go
package dedup
import "time"
const DefaultTimeDelta = 120 * time.Second // 默认时间窗口 120 秒
// DedupEngine 交易链路去重引擎
type DedupEngine struct {
TimeDelta time.Duration
}
// Process 执行去重合并
// 算法: 按 DataWeight 升序排列，低权重记录尝试匹配高权重记录
// 匹配条件: |Time(Tp) - Time(Ts)| <= Δt AND Amount(Tp) == Amount(Ts)
func (d *DedupEngine) Process(bills []model.Bill) []model.Bill {
// 1. 按 DataWeight 分组: primary (L1) vs secondary (L2, L3)
// 2. 双层循环匹配: 时间窗 + 金额精确匹配
// 3. 匹配成功: 建立 LinkID 关联, 标记 secondary 为 linked
// 4. 返回合并后的结果集
}
```
#### 2.2.5 Pipeline 编排
```go
// internal/etl/pipeline.go
package etl
// Pipeline ETL 管道编排器
type Pipeline struct {
providerRegistry map[string]provider.Provider
translateEngine *translate.TranslateEngine
dedupEngine *dedup.DedupEngine
}
// Run 执行完整 ETL 流程
func (p *Pipeline) Run(providerType, filePath string) (*ImportResult, error) {
// Step 1: Provider 解析 -> IR
prov, err := provider.NewProvider(providerType)
irData, err := prov.Translate(filePath)
// Step 2: Translate 规则转换 -> []Bill
bills, err := p.translateEngine.Apply(irData)
// Step 3: Dedup 去重合并
mergedBills := p.dedupEngine.Process(bills)
// Step 4: 持久化入库
return p.save(mergedBills)
}
```
```mermaid
sequenceDiagram
participant U as 用户
participant FE as 前端
participant API as Gin API
participant SVC as ImportService
participant P as Provider
participant T as Translate
participant D as DedupEngine
participant DB as Database
U->>FE: 上传账单文件 + 选择来源类型
FE->>API: POST /api/v1/bills/import (multipart)
API->>SVC: ImportBill(providerType, file)
SVC->>P: Translate(filePath)
P-->>SVC: IR (中间表示)
SVC->>T: Apply(IR)
T-->>SVC: []Bill (标准账单)
SVC->>D: Process([]Bill)
D->>DB: 查询已有账单 (时间窗)
DB-->>D: 存量数据
D-->>SVC: 去重后 []Bill
SVC->>DB: 批量写入
DB-->>SVC: 写入结果
SVC-->>API: ImportResult(成功/跳过/失败数)
API-->>FE: JSON Response
FE-->>U: 导入结果报告
```
### 2.3 数据模型设计 (GORM)
#### 2.3.1 ER 关系图
```mermaid
erDiagram
USER ||--o{ ACCOUNT : owns
USER ||--o{ BUDGET : sets
ACCOUNT ||--o{ BILL : "fund_source"
CATEGORY ||--o{ BILL : classifies
CATEGORY ||--o{ BUDGET : limits
BILL ||--o| BILL_LINK : linked
CATEGORY ||--o{ CATEGORY : "parent-child"
USER ||--o{ TRANSLATE_RULE : configures
USER {
uint id PK
string username
string password_hash
timestamp created_at
}
ACCOUNT {
uint id PK
uint user_id FK
string name
string type "debit/credit/ewallet"
float64 balance
string currency
bool is_active
}
BILL {
uint id PK
uint user_id FK
uint account_id FK
uint category_id FK
string provider_name
string order_id UK
string merchant_order_id
string peer
string item
float64 amount
string tx_type "income/expense/transfer"
string method
string status
string note
string link_id
int data_weight
timestamp pay_time
timestamp created_at
}
CATEGORY {
uint id PK
uint parent_id FK
string name
string icon
int sort_order
string type "income/expense"
}
BUDGET {
uint id PK
uint user_id FK
uint category_id FK "nullable, null=全局"
float64 amount
string period "monthly/yearly"
string month "2026-02"
}
BILL_LINK {
uint id PK
string link_id UK
uint primary_bill_id FK
uint secondary_bill_id FK
}
TRANSLATE_RULE {
uint id PK
uint user_id FK
string rule_type "category/account"
string match_field
string match_pattern
string target_value
int priority
bool is_active
}
```
#### 2.3.2 核心 Model 定义
```go
// internal/model/bill.go
package model
import (
"time"
"gorm.io/gorm"
)
type Bill struct {
gorm.Model
UserID uint `gorm:"index;not null" json:"user_id"`
AccountID uint `gorm:"index" json:"account_id"`
CategoryID uint `gorm:"index" json:"category_id"`
ProviderName string `gorm:"size:32" json:"provider_name"`
OrderID string `gorm:"size:128;uniqueIndex" json:"order_id"`
MerchantOrderID string `gorm:"size:128" json:"merchant_order_id"`
Peer string `gorm:"size:256" json:"peer"`
Item string `gorm:"size:512" json:"item"`
Amount float64 `gorm:"type:decimal(12,2);not null" json:"amount"`
TxType string `gorm:"size:16;not null" json:"tx_type"`
Method string `gorm:"size:64" json:"method"`
Status string `gorm:"size:32" json:"status"`
Note string `gorm:"size:512" json:"note"`
LinkID string `gorm:"size:64;index" json:"link_id"`
DataWeight int `gorm:"default:1" json:"data_weight"`
PayTime time.Time `gorm:"index;not null" json:"pay_time"`
// 关联
Account Account `gorm:"foreignKey:AccountID" json:"account,omitempty"`
Category Category `gorm:"foreignKey:CategoryID" json:"category,omitempty"`
}
// internal/model/account.go
type Account struct {
gorm.Model
UserID uint `gorm:"index;not null" json:"user_id"`
Name string `gorm:"size:128;not null" json:"name"`
Type string `gorm:"size:32;not null" json:"type"` // debit/credit/ewallet
Balance float64 `gorm:"type:decimal(14,2);default:0" json:"balance"`
Currency string `gorm:"size:8;default:CNY" json:"currency"`
IsActive bool `gorm:"default:true" json:"is_active"`
}
// internal/model/category.go
type Category struct {
gorm.Model
ParentID *uint `gorm:"index" json:"parent_id"`
Name string `gorm:"size:64;not null" json:"name"`
Icon string `gorm:"size:64" json:"icon"`
SortOrder int `gorm:"default:0" json:"sort_order"`
Type string `gorm:"size:16" json:"type"` // income/expense
Children []Category `gorm:"foreignKey:ParentID" json:"children,omitempty"`
}
// internal/model/budget.go
type Budget struct {
gorm.Model
UserID uint `gorm:"index;not null" json:"user_id"`
CategoryID *uint `gorm:"index" json:"category_id"` // nil = 全局预算
Amount float64 `gorm:"type:decimal(12,2);not null" json:"amount"`
Period string `gorm:"size:16;default:monthly" json:"period"`
Month string `gorm:"size:8;not null" json:"month"` // "2026-02"
}
```
### 2.4 API 接口设计
#### 2.4.1 接口总表
| 模块 | Method | Path | 描述 |
| --- | --- | --- | --- |
| **账单导入** | POST | `/api/v1/bills/import` | 上传并导入账单文件 |
| | GET | `/api/v1/bills/import-history` | 导入历史记录 (导入质量图数据) |
| **账单管理** | GET | `/api/v1/bills` | 多条件查询账单列表 |
| | GET | `/api/v1/bills/:id` | 查询账单详情 |
| | PUT | `/api/v1/bills/:id` | 修改账单 (手动调整分类等) |
| | DELETE | `/api/v1/bills/:id` | 删除账单 |
| **仪表盘** | GET | `/api/v1/dashboard/summary` | 资产负债 + 现金流概览 |
| | GET | `/api/v1/dashboard/trend` | 收支趋势 + 净资产趋势 (按月) |
| | GET | `/api/v1/dashboard/asset-composition` | 各账户资产构成 (堆叠图数据) |
| **分析** | GET | `/api/v1/analysis/category` | 分类占比 (饼图, 支持 type=income/expense) |
| | GET | `/api/v1/analysis/sankey` | 资金流向 (桑基图数据) |
| | GET | `/api/v1/analysis/heatmap` | 日消费热力图数据 |
| | GET | `/api/v1/analysis/category-trend` | 分类支出趋势 (多折线图数据) |
| **账户** | GET | `/api/v1/accounts` | 账户列表 |
| | POST | `/api/v1/accounts` | 创建账户 |
| | PUT | `/api/v1/accounts/:id` | 修改账户 |
| | DELETE | `/api/v1/accounts/:id` | 删除账户 |
| | GET | `/api/v1/accounts/:id/waterfall` | 账户收支瀑布图数据 |
| **预算** | GET | `/api/v1/budgets` | 预算列表 (含执行进度) |
| | POST | `/api/v1/budgets` | 创建/更新预算 |
| | DELETE | `/api/v1/budgets/:id` | 删除预算 |
| **分类** | GET | `/api/v1/categories` | 分类树 |
| | POST | `/api/v1/categories` | 新增分类 |
| **规则** | GET | `/api/v1/rules` | 规则列表 |
| | POST | `/api/v1/rules` | 新增规则 |
| | PUT | `/api/v1/rules/:id` | 修改规则 |
| | DELETE | `/api/v1/rules/:id` | 删除规则 |
#### 2.4.2 核心接口详细定义
**POST /api/v1/bills/import — 账单导入**
```
Request: multipart/form-data
- file: 账单文件 (CSV/XLS/PDF)
- provider: string ("alipay" | "wechat" | "cmb" | "icbc" | "jd" | "meituan")
Response 200:
{
"code": 0,
"data": {
"total": 150, // 解析总条数
"imported": 132, // 新导入条数
"duplicated": 15, // 去重跳过条数
"linked": 3, // 链路合并条数
"failed": 0 // 失败条数
}
}
```
**GET /api/v1/bills — 账单查询**
```
Query Params:
- start_date: string (2026-01-01)
- end_date: string (2026-01-31)
- min_amount: float64
- max_amount: float64
- tx_type: string (income/expense)
- category_id: uint
- account_id: uint
- provider: string
- keyword: string (模糊搜索 peer/item)
- page: int (default 1)
- page_size: int (default 20)
Response 200:
{
"code": 0,
"data": {
"total": 500,
"items": [ { ...Bill } ]
}
}
```
**GET /api/v1/dashboard/summary — 仪表盘概览**
```
Query Params:
- month: string (2026-02, 默认当月)
Response 200:
{
"code": 0,
"data": {
"total_assets": 125000.00,
"total_liabilities": 8500.00,
"net_worth": 116500.00,
"month_income": 15000.00,
"month_expense": 8200.00,
"income_mom_pct": 5.2,
"expense_mom_pct": -3.1,
"accounts": [ { "name": "招行储蓄卡", "balance": 80000.00, "type": "debit" } ]
}
}
```
**GET /api/v1/analysis/sankey — 桑基图数据**
```
Query Params:
- start_date / end_date
Response 200:
{
"code": 0,
"data": {
"nodes": [
{ "name": "工资" }, { "name": "招行储蓄卡" }, { "name": "餐饮" }
],
"links": [
{ "source": "工资", "target": "招行储蓄卡", "value": 15000 },
{ "source": "招行储蓄卡", "target": "餐饮", "value": 3200 }
]
}
}
```
---
## 3. 前端详细设计
### 3.1 页面结构与路由
```mermaid
graph LR
subgraph Layout["AppLayout"]
Sidebar["侧边导航栏"]
Header["顶部栏"]
Main["主内容区"]
end
Main --> Dashboard["/dashboard 仪表盘"]
Main --> Bills["/bills 账单管理"]
Main --> Import["/import 账单导入"]
Main --> Accounts["/accounts 账户管理"]
Main --> Budgets["/budgets 预算管理"]
Main --> Analysis["/analysis 多维分析"]
Main --> Rules["/rules 规则配置"]
```
### 3.2 前端项目结构
```
projectmoneyx-web/
├── src/
│ ├── main.ts
│ ├── App.vue
│ ├── router/
│ │ └── index.ts
│ ├── api/ # Axios 接口封装
│ │ ├── request.ts # Axios 实例 + 拦截器
│ │ ├── bill.ts
│ │ ├── account.ts
│ │ ├── dashboard.ts
│ │ ├── analysis.ts
│ │ ├── budget.ts
│ │ └── rule.ts
│ ├── views/
│ │ ├── DashboardView.vue # 全景仪表盘
│ │ ├── BillListView.vue # 账单查询
│ │ ├── ImportView.vue # 账单导入
│ │ ├── AccountView.vue # 账户管理
│ │ ├── BudgetView.vue # 预算管理
│ │ ├── AnalysisView.vue # 多维分析 (桑基图/饼图)
│ │ └── RuleView.vue # 规则配置
│ ├── components/
│ │ ├── charts/
│ │ │ ├── NetWorthTrendChart.vue # 图表1: 净资产趋势折线图
│ │ │ ├── CashFlowBarChart.vue # 图表2: 现金流对比柱状图
│ │ │ ├── AssetCompositionChart.vue # 图表3: 资产构成堆叠图
│ │ │ ├── ExpensePieChart.vue # 图表4: 支出结构环形图
│ │ │ ├── CalendarHeatmap.vue # 图表5: 收支日历热力图
│ │ │ ├── CategoryTrendChart.vue # 图表6: 分类支出趋势折线图
│ │ │ ├── SankeyChart.vue # 图表7: 资金流向桑基图
│ │ │ ├── IncomePieChart.vue # 图表8: 收入来源环形图
│ │ │ ├── BudgetGauge.vue # 图表9: 预算进度仪表盘
│ │ │ ├── BudgetCompareChart.vue # 图表10: 预算vs实际对比图
│ │ │ ├── AccountWaterfallChart.vue # 图表11: 账户收支瀑布图
│ │ │ └── ImportQualityChart.vue # 图表12: 导入质量统计图
│ │ ├── BillFilterPanel.vue # 账单筛选面板
│ │ ├── ImportUploader.vue # 文件上传组件
│ │ └── AccountCard.vue # 账户卡片
│ ├── stores/ # Pinia 状态管理
│ │ ├── bill.ts
│ │ ├── account.ts
│ │ └── dashboard.ts
│ └── types/ # TypeScript 类型定义
│ ├── bill.d.ts
│ ├── account.d.ts
│ └── api.d.ts
```
### 3.3 核心页面设计
#### 3.3.1 全景仪表盘 (DashboardView)
* **资产负债表：** 实时聚合各账户总资产、总负债（信用卡/白条），计算净资产。
* **现金流概览：** 本月总收入 vs 总支出，环比上月 (MoM) 增减百分比。
```
┌─────────────────────────────────────────────────────────┐
│ [净资产卡片] [本月收入卡片] [本月支出卡片] │
│ ¥116,500 ¥15,000 ↑5.2% ¥8,200 ↓3.1% │
├──────────────────────────┬──────────────────────────────┤
│ 收支趋势折线图 (ECharts) │ 消费结构饼图 (ECharts) │
│ (近12个月) │ (本月各分类占比) │
├──────────────────────────┴──────────────────────────────┤
│ 各账户余额一栏表 (v-data-table) │
│ 招行储蓄卡 ¥80,000 | 支付宝余额 ¥5,000 | ... │
└─────────────────────────────────────────────────────────┘
```
#### 3.3.2 账单导入页 (ImportView)
```
┌─────────────────────────────────────────────────────────┐
│ Step 1: 选择来源 ○ 支付宝 ○ 微信 ○ 招商银行 ... │
├─────────────────────────────────────────────────────────┤
│ Step 2: 上传文件 [拖拽区域 / 点击选择文件] │
├─────────────────────────────────────────────────────────┤
│ Step 3: 导入结果 │
│ ✅ 解析 150 条 | 导入 132 条 | 去重 15 条 | 合并 3 条 │
└─────────────────────────────────────────────────────────┘
```
#### 3.3.3 多维分析页 (AnalysisView)
* **组合漏斗筛选：** 支持时间范围、金额区间、支付渠道、资金账户、交易分类的多条件交叉查询。
* **可视化图表：**
* **消费结构：** 饼图展示各大类的支出占比。
* **资金流向 (Sankey Diagram)：** 桑基图直观展示“收入源 -> 资金池 (账户) -> 支出分类”的完整链路。
桑基图核心配置：
```typescript
// components/charts/SankeyChart.vue
const option: EChartsOption = {
series: [{
type: 'sankey',
data: nodes, // [{ name: '工资' }, { name: '招行卡' }, { name: '餐饮' }]
links: links, // [{ source: '工资', target: '招行卡', value: 15000 }]
emphasis: { focus: 'adjacency' },
lineStyle: { color: 'gradient', curveness: 0.5 },
label: { position: 'right' }
}]
}
```
---
## 4. 关键业务流程
### 4.1 账单导入全流程状态机
```mermaid
stateDiagram-v2
[*] --> FileUploaded: 用户上传文件
FileUploaded --> Parsing: 开始解析
Parsing --> ParseSuccess: Provider 解析成功
Parsing --> ParseFailed: 格式错误/文件损坏
ParseSuccess --> Translating: 规则引擎转换
Translating --> TranslateSuccess: 转换完成
TranslateSuccess --> Deduplicating: 去重处理
Deduplicating --> ImportComplete: 写入数据库
ImportComplete --> [*]: 返回导入报告
ParseFailed --> [*]: 返回错误信息
```
### 4.2 预算预警触发流程
```mermaid
sequenceDiagram
participant SVC as BudgetService
participant DB as Database
participant FE as 前端
Note over SVC: 每次账单写入后触发
SVC->>DB: 查询本月已用 (SUM by category)
DB-->>SVC: 已用金额
SVC->>DB: 查询预算限额
DB-->>SVC: 预算配置
alt 已用 >= 100% 限额
SVC-->>FE: 超支预警 (红色标记)
else 已用 >= 80% 限额
SVC-->>FE: 临近预警 (橙色标记)
else 正常
SVC-->>FE: 正常状态 (绿色)
end
```
---
## 5. Translate 规则配置规范
### 5.1 分类规则配置示例 (YAML)
```yaml
# configs/rules/category_rules.yaml
category_rules:
# --- 餐饮 ---
- match: { field: "peer", pattern: "星巴克|瑞幸|Luckin" }
category: "餐饮-咖啡"
priority: 10
- match: { field: "peer", pattern: "美团|饿了么|美团外卖" }
category: "餐饮-外卖"
priority: 10
- match: { field: "item", pattern: "早餐|午餐|晚餐|堂食" }
category: "餐饮-正餐"
priority: 5
# --- 交通 ---
- match: { field: "peer", pattern: "滴滴|高德打车|T3出行" }
category: "交通-打车"
priority: 10
- match: { field: "peer", pattern: "12306|铁路" }
category: "交通-火车"
priority: 10
# --- 购物 ---
- match: { field: "peer", pattern: "淘宝|天猫|拼多多" }
category: "购物-电商"
priority: 3
# --- 兜底规则 ---
- match: { field: "peer", pattern: ".*" }
category: "其他-未分类"
priority: 0
```
### 5.2 账户路由配置示例 (YAML)
```yaml
# configs/rules/account_rules.yaml
account_rules:
- provider: "alipay"
method_match: "招商银行信用卡"
account_name: "招行信用卡"
- provider: "alipay"
method_match: "花呗"
account_name: "花呗"
- provider: "alipay"
method_match: "余额宝|账户余额"
account_name: "支付宝余额"
- provider: "wechat"
method_match: "零钱"
account_name: "微信零钱"
- provider: "wechat"
method_match: "招商银行"
account_name: "招行储蓄卡"
```
---
## 6. 非功能性设计
### 6.1 数据隐私 (Local-First)
| 设计要点 | 实现方式 |
| --- | --- |
| 本地部署 | 默认使用 SQLite，单一二进制文件部署，无需外部数据库 |
| 文件处理 | 上传的原始账单文件仅在本地解析后即删除，不持久存储原始文件 |
| 无远程调用 | ETL 管道全过程本地执行，不依赖任何云端 API |
| 可选 MySQL | 如需多端访问，可配置切换到 MySQL，但建议内网部署 |
### 6.2 性能设计
| 场景 | 指标 | 措施 |
| --- | --- | --- |
| 账单导入 | 1000 条/秒 | GORM 批量插入 (CreateInBatches) |
| 账单列表查询 | < 200ms | 复合索引 (user_id, pay_time, category_id) |
| 仪表盘聚合 | < 500ms | 数据库聚合查询 + 前端缓存 (Pinia) |
| 去重匹配 | O(n·m) | 按时间窗口分桶预排序，减少比较次数 |
### 6.3 可扩展性设计
- **新增 Provider**：实现 `provider.Provider` 接口，注册到工厂即可
- **新增规则**：YAML 配置热加载，无需重启
- **新增图表**：ECharts 组件化封装，新图表只需新建 Vue 组件
---
## 7. 参考项目代码复用说明
### 7.1 从 double-entry-generator 复用的部分
| 模块 | 源路径 | 复用说明 |
| --- | --- | --- |
| IR 结构 | `pkg/ir/ir.go` | 复用 `Order` 结构体核心字段，扩展 `ProviderName`、`DataWeight` 等字段 |
| Alipay Provider | `pkg/provider/alipay/` | 复用 CSV 解析、GBK 编码处理、字段映射逻辑 |
| WeChat Provider | `pkg/provider/wechat/` | 复用 CSV/XLSX 解析、跳过表头逻辑 |
| 退款后处理 | `alipay.postProcess()` | 复用退款订单匹配和交易关闭处理逻辑 |
### 7.2 需要新增/改造的部分
| 模块 | 改造说明 |
| --- | --- |
| Provider 接口 | 从直接函数调用改为 Web API 触发，增加文件上传处理 |
| Translate 层 | 原项目的 Compiler 输出 Beancount 文本，改为输出数据库 Model |
| 去重引擎 | 原项目不涉及，需完全新写 |
| 规则配置 | 原项目配置固定，改为数据库存储 + YAML 双模式，支持用户自定义 |
---
## 8. 部署架构
```mermaid
graph LR
subgraph Local["本地部署 (推荐)"]
Binary["Go 单体二进制"]
SQLite["SQLite 数据库文件"]
StaticFiles["Vue 前端静态文件 (embed)"]
Binary --> SQLite
Binary --> StaticFiles
end
subgraph Docker["Docker 部署 (可选)"]
Container["Docker Container"]
Volume["Data Volume"]
Container --> Volume
end
User["浏览器"] -->|http://localhost:8080| Binary
User -->|http://host:8080| Container
```
> **推荐部署方式**：使用 Go 的 `embed` 包将编译后的 Vue 前端静态资源嵌入后端二进制文件，实现**单文件部署**，配合 SQLite 达到真正的 Local-First 体验。

637
16-ProjectMoneyM-转FireFlyIII/3-实现详细稿/3-DataGrip-DDS.md Normal file
View File

@@ -0,0 +1,637 @@
# ProjectMoneyX 数据可视化详细设计说明书
| 文档属性 | 详情 |
| --- | --- |
| **所属系统** | ProjectMoneyX 个人全景财务分析系统 |
| **关联文档** | [2-ProjectMoneyX-DDS.md](./2-ProjectMoneyX-DDS.md) §3 前端详细设计 |
| **技术框架** | ECharts 5.x + Vue3 Composition API + TypeScript |
| **编制日期** | 2026-02-26 |
---
## 0. 图表总览与需求覆盖矩阵
下表将 PRD 中的核心分析需求映射到具体图表实现，确保**多维度全覆盖**：
| PRD 需求 | 分析维度 | 实现图表 | 所在页面 |
|---|---|---|---|
| 资产负债表 | 总资产/负债/净资产趋势 | 图表1: 净资产趋势折线图 | Dashboard |
| 现金流概览 (MoM) | 月度收入 vs 支出对比 | 图表2: 现金流对比柱状图 | Dashboard |
| 各账户资产构成 | 账户维度的资金分布 | 图表3: 资产构成堆叠图 | Dashboard |
| 消费结构 (饼图) | 分类维度的支出占比 | 图表4: 支出结构环形图 | Analysis |
| 消费规律识别 | 时间维度的消费强度 | 图表5: 收支日历热力图 | Analysis |
| 分类趋势对比 | 分类×时间交叉分析 | 图表6: 分类支出趋势折线图 | Analysis |
| 资金流向 (Sankey) | 收入→账户→支出全链路 | 图表7: 资金流向桑基图 ⭐ | Analysis |
| 收入结构分析 | 收入来源维度的占比 | 图表8: 收入来源环形图 | Analysis |
| 预算管理 (阈值预警) | 预算执行进度 | 图表9: 预算进度仪表盘 | Budget |
| 预算执行趋势 | 预算 vs 实际的偏差跟踪 | 图表10: 预算 vs 实际对比图 | Budget |
| 账户交易分析 | 单账户维度的流水趋势 | 图表11: 账户收支瀑布图 | Account |
| 去重链路可视化 | ETL 导入质量监控 | 图表12: 导入质量统计图 | Import |
### 图表与页面分布
```mermaid
graph TB
subgraph Dashboard["仪表盘 (DashboardView)"]
C1["图表1: 净资产趋势折线图"]
C2["图表2: 现金流对比柱状图"]
C3["图表3: 资产构成堆叠图"]
end
subgraph Analysis["多维分析 (AnalysisView)"]
C4["图表4: 支出结构环形图"]
C5["图表5: 收支日历热力图"]
C6["图表6: 分类支出趋势折线图"]
C7["图表7: 资金流向桑基图 ⭐"]
C8["图表8: 收入来源环形图"]
end
subgraph Budget["预算管理 (BudgetView)"]
C9["图表9: 预算进度仪表盘"]
C10["图表10: 预算 vs 实际对比图"]
end
subgraph Account["账户管理 (AccountView)"]
C11["图表11: 账户收支瀑布图"]
end
subgraph Import["账单导入 (ImportView)"]
C12["图表12: 导入质量统计图"]
end
```
---
## 1. 仪表盘总览区 (DashboardView)
### 图表1：净资产趋势折线图
**图表类型：** `ECharts Line Chart`（面积折线图，Area Line）
**用途：** 展示净资产随时间的增长趋势，是资产健康度的核心指标。
| 配置项 | 说明 |
|---|---|
| `xAxis.type` | `'category'`，数据为月份标签 `['2024-06', ..., '2026-02']` |
| `yAxis.type` | `'value'`，单位 CNY，开启 `scale: true` 避免从0开始压缩曲线 |
| `series.type` | `'line'`，开启 `areaStyle` 填充半透明渐变区域 |
| `series.smooth` | `true`，平滑曲线更符合财务趋势感 |
| 关键数据字段 | `{ month: string, netWorth: number, totalAssets: number, totalLiabilities: number }[]` |
| 多线配置 | 叠加三条线：净资产（主线蓝 `#4F6EF7`）、总资产（绿虚线 `#10B981`）、总负债（红虚线 `#EF4444`），用 `markLine` 标注最高/最低点 |
**ECharts 高级能力：** 使用 `visualMap` 组件，当净资产低于某阈值时自动将线段变红预警。
**后端接口：** `GET /api/v1/dashboard/trend?range=12m`
```json
// Response
{
"code": 0,
"data": {
"months": ["2025-03", "2025-04", "..."],
"net_worth": [98000, 101000, "..."],
"total_assets": [120000, 125000, "..."],
"total_liabilities": [22000, 24000, "..."]
}
}
```
---
### 图表2：月度现金流对比柱状图
**图表类型：** `ECharts Bar Chart`（分组柱 + 折线混合）
**用途：** 直观对比每月收入/支出，突出结余（净现金流）。
| 配置项 | 说明 |
|---|---|
| `xAxis` | 近12个月，`type: 'category'` |
| `series[0]` | 收入柱，`barMaxWidth: 20`，颜色 `#10B981`（绿） |
| `series[1]` | 支出柱，同组排列，颜色 `#EF4444`（红） |
| `series[2]` | 结余折线（叠加 `type: 'line'`），颜色 `#4F6EF7`（蓝），`z: 10` 置于顶层 |
| `tooltip.formatter` | 自定义：同时显示收入、支出、结余、环比变化（MoM%） |
| `markArea` | 标记亏损月（收入 < 支出）的柱背景为浅红色区域 |
**后端接口：** 复用 `GET /api/v1/dashboard/trend?range=12m`，数据中应增加 `month_income[]` 和 `month_expense[]` 数组。
---
### 图表3：资产构成堆叠柱 / 堆叠面积图
**图表类型：** `ECharts Bar Chart (stack)` 或 `Line Chart (stack + areaStyle)`
**用途：** 展示各账户资产随时间的构成变化，如活期、基金、信用卡负债各占比的演变。
| 配置项 | 说明 |
|---|---|
| `series[n].stack` | 统一设为 `'total'`，触发堆叠模式 |
| 账户数据字段 | `{ month, accounts: { name: string, balance: number }[] }[]` |
| `series` 中负债处理 | 负债账户（信用卡/白条）使用负值，自动向下延伸，形成正负对称的资产负债视图 |
| `legend` | 开启可点击切换，方便单独聚焦某账户 |
**后端接口：** `GET /api/v1/dashboard/asset-composition?range=12m`
```json
// Response
{
"code": 0,
"data": {
"months": ["2025-03", "2025-04"],
"series": [
{ "name": "招行储蓄卡", "type": "debit", "data": [80000, 82000] },
{ "name": "支付宝余额", "type": "ewallet", "data": [5000, 4500] },
{ "name": "招行信用卡", "type": "credit", "data": [-8000, -7500] }
]
}
}
```
---
## 2. 支出分析区 (AnalysisView - Tab1: 支出)
### 图表4：支出结构环形图（Donut）
**图表类型：** `ECharts Pie Chart`（`radius: ['40%', '70%']` 环形）
**用途：** 展示选定时间段内各消费分类占比，支持二级下钻。
| 配置项 | 说明 |
|---|---|
| `series.radius` | `['40%', '70%']` 形成环形，中心显示总支出金额 |
| `series.label` | 外侧显示分类名 + 百分比，`labelLine` 引导线 |
| `graphic`（中心文字） | 使用 ECharts `graphic` 组件在环心渲染「总支出 / ¥9,820」 |
| `series.emphasis` | 鼠标悬停时扇区放大 `scaleSize: 10`，联动下方账单表格筛选 |
| 数据字段 | `{ name: string, value: number, percentage: number }[]` |
| 二级下钻 | 点击一级分类（餐饮）→ 触发 `series.data` 替换为二级分类（外卖/堂食/咖啡），配合 Vue3 `ref` 响应式切换，面包屑导航返回上级 |
**后端接口：** `GET /api/v1/analysis/category?type=expense&start_date=&end_date=&parent_id=`
```json
// Response
{
"code": 0,
"data": {
"total": 9820.50,
"items": [
{ "category_id": 1, "name": "餐饮", "value": 3200, "percentage": 32.6, "has_children": true },
{ "category_id": 2, "name": "购物", "value": 2500, "percentage": 25.5, "has_children": true },
{ "category_id": 3, "name": "交通", "value": 1200, "percentage": 12.2, "has_children": false }
]
}
}
```
---
### 图表5：收支日历热力图
**图表类型：** `ECharts HeatMap`（日历坐标系）
**用途：** 以日历形式展示每日消费强度，快速识别高消费日/周期性支出规律（如固定还款日、周末消费高峰）。
| 配置项 | 说明 |
|---|---|
| `calendar.range` | 设置为当前选中月份或全年，如 `'2026'` 或 `'2026-02'` |
| `series.coordinateSystem` | `'calendar'`，与 `calendar` 组件绑定 |
| `series.data` | `[['2026-02-15', 420], ['2026-02-16', 85], ...]`（日期 + 消费金额） |
| `visualMap` | 连续型，从浅绿（低消费 `#E8F5E9`）到深红（高消费 `#C62828`）渐变，阈值按数据自适应 |
| `tooltip` | 显示该日消费总额和前3笔最大账单 |
**后端接口：** `GET /api/v1/analysis/heatmap?year=2026&type=expense`
```json
// Response
{
"code": 0,
"data": [
["2026-02-01", 156.50],
["2026-02-02", 320.00],
["2026-02-14", 899.00]
]
}
```
---
### 图表6：分类支出趋势多折线图
**图表类型：** `ECharts Line Chart`（多系列）
**用途：** 对比各支出分类（餐饮、购物、交通）近 N 个月的趋势，找出异常增长的分类。
| 配置项 | 说明 |
|---|---|
| `legend` | 开启可交互，默认只显示前5大分类，其余折叠于 `legend.selector` |
| `xAxis` | 月份，近12个月 |
| 每条 `series` | 对应一个支出分类，最多显示 6 条线，其余归入"其他" |
| `dataZoom` | 开启 X 轴缩放 (`type: 'slider'`)，支持拖拽查看任意时间段 |
| 颜色规范 | 自定义 10 色 palette，**与环形图(图表4)保持颜色一致**保证跨图表认知一致性 |
| `markPoint` | 自动标注各分类的月度最大值 (`type: 'max'`) |
**后端接口：** `GET /api/v1/analysis/category-trend?type=expense&range=12m&top=6`
```json
// Response
{
"code": 0,
"data": {
"months": ["2025-03", "2025-04", "..."],
"series": [
{ "name": "餐饮", "data": [3200, 2800, "..."] },
{ "name": "购物", "data": [2500, 3100, "..."] },
{ "name": "交通", "data": [1200, 1100, "..."] }
]
}
}
```
---
## 3. 资金流向区 (AnalysisView - Tab2: 流向)
### 图表7：资金流向桑基图（Sankey）⭐ 核心图
**图表类型：** `ECharts Sankey Diagram`
**用途：** 唯一能完整展示「收入源 → 资金池(账户) → 支出分类」全链路的图表，是个人收支系统最有价值的可视化。
```typescript
// 核心数据结构（TypeScript）
interface SankeyNode {
name: string // 节点名称
itemStyle?: { color: string }
depth?: number // 强制分层: 0=收入源, 1=账户, 2=支出分类
}
interface SankeyLink {
source: string // 来源节点 name
target: string // 目标节点 name
value: number // 流量金额（CNY）
}
// 三列节点分组示例
const nodes: SankeyNode[] = [
// 收入源（左列, depth=0）
{ name: '工资薪酬', itemStyle: { color: '#10B981' }, depth: 0 },
{ name: '兼职收入', itemStyle: { color: '#34D399' }, depth: 0 },
{ name: '投资收益', itemStyle: { color: '#6EE7B7' }, depth: 0 },
// 账户池（中列, depth=1）
{ name: '招行储蓄', itemStyle: { color: '#4F6EF7' }, depth: 1 },
{ name: '支付宝', itemStyle: { color: '#818CF8' }, depth: 1 },
{ name: '微信钱包', itemStyle: { color: '#A5B4FC' }, depth: 1 },
// 支出分类（右列, depth=2）
{ name: '餐饮', itemStyle: { color: '#EF4444' }, depth: 2 },
{ name: '购物', itemStyle: { color: '#F97316' }, depth: 2 },
{ name: '居住', itemStyle: { color: '#F59E0B' }, depth: 2 },
{ name: '储蓄/投资',itemStyle: { color: '#10B981' }, depth: 2 },
]
```
| 关键配置项 | 说明 |
|---|---|
| `series.type` | `'sankey'` |
| `series.layout` | `'none'`（禁用自动布局），通过 `depth` 属性手动控制三列分层 |
| `series.nodeGap` | `12`（节点间距） |
| `series.nodeWidth` | `20`（节点宽度） |
| `series.lineStyle.color` | `'gradient'`（从源到目标渐变色，ECharts 内置支持） |
| `series.lineStyle.opacity` | `0.4`，悬停时 `emphasis.lineStyle.opacity: 0.8` |
| `series.emphasis.focus` | `'adjacency'`（高亮相邻节点和链接，淡化其他） |
| `series.label.position` | 左列 `'left'`，右列 `'right'`，中列 `'inside'` |
| `tooltip.formatter` | 自定义显示：节点→`账户名: 总额 ¥X,XXX`；链接→`源 → 目标: ¥X,XXX（占XX%）` |
**后端接口：** `GET /api/v1/analysis/sankey?start_date=&end_date=`（已在 DDS 中定义）
---
## 4. 收入分析区 (AnalysisView - Tab3: 收入)
### 图表8：收入来源环形图
**图表类型：** `ECharts Pie Chart`（`radius: ['40%', '70%']` 环形）
**用途：** 展示选定时间段内各收入来源占比（如：工资、兼职、理财收益、转账收款等），与支出环形图(图表4)形成对称分析。
| 配置项 | 说明 |
|---|---|
| `series.radius` | `['40%', '70%']` 形成环形，中心显示总收入金额 |
| `series.color` | 使用绿色系 palette（与支出红色系区分），如 `['#10B981', '#34D399', '#6EE7B7', '#A7F3D0']` |
| `graphic`（中心文字） | 在环心渲染「总收入 / ¥15,000」 |
| `series.emphasis` | 悬停扇区放大，tooltip 显示收入来源明细 |
| 数据字段 | `{ name: string, value: number, percentage: number }[]` |
**后端接口：** 复用 `GET /api/v1/analysis/category?type=income&start_date=&end_date=`
> **设计说明：** PRD 原文重点描述了支出维度的分析，但收入来源的结构分析是完整财务画像不可缺少的一环。用户需要了解"钱从哪来"的占比分布，才能做出更好的财务规划决策。
---
## 5. 预算管理区 (BudgetView)
### 图表9：预算进度仪表盘（多量规阵列）
**图表类型：** `ECharts Gauge Chart`（多个仪表盘组成阵列）
**用途：** 直观展示每个预算分类的执行进度百分比，配合 DDS 中定义的 80%/100% 阈值预警逻辑。
| 配置项 | 说明 |
|---|---|
| `series.type` | `'gauge'` |
| `series.progress.show` | `true`，显示进度弧 |
| `series.axisLine.lineStyle.color` | 三段式渐变：`[[0.8, '#10B981'], [1.0, '#F59E0B'], [1.0+, '#EF4444']]`（绿→橙→红） |
| `series.detail.formatter` | `'{value}%'`，中心显示百分比 |
| `series.title.text` | 分类名称（如"餐饮"、"交通"） |
| `series.data` | `[{ value: 75, name: '餐饮' }]`，表示已用 75% |
| 布局 | 使用 `v-row` + `v-col` 阵列，每个分类一个小仪表盘，全局预算用大号仪表盘 |
**阈值预警联动（对齐 DDS §4.2）：**
- `0% ~ 79%` → 绿色弧 `#10B981` + 正常文字
- `80% ~ 99%` → 橙色弧 `#F59E0B` + 橙色警告徽章
- `≥ 100%` → 红色弧 `#EF4444` + 红色超支提示 + 弧度超出刻度线
```typescript
// BudgetGauge.vue 核心 option
const getGaugeOption = (budget: BudgetItem): EChartsOption => ({
series: [{
type: 'gauge',
startAngle: 200,
endAngle: -20,
min: 0,
max: 100,
progress: { show: true, width: 12 },
pointer: { show: false },
axisLine: {
lineStyle: {
width: 12,
color: [[0.8, '#10B981'], [1, '#F59E0B'], [1.2, '#EF4444']] // 允许超出100%
}
},
axisTick: { show: false },
splitLine: { show: false },
axisLabel: { show: false },
detail: {
valueAnimation: true,
formatter: `{value}%\n¥${budget.used} / ¥${budget.limit}`,
fontSize: 14
},
title: { text: budget.categoryName, offsetCenter: [0, '80%'] },
data: [{ value: Math.round((budget.used / budget.limit) * 100) }]
}]
})
```
**后端接口：** `GET /api/v1/budgets?month=2026-02`（已在 DDS 中定义），响应需扩展：
```json
// Response
{
"code": 0,
"data": [
{
"id": 1, "category_name": "全局", "category_id": null,
"limit": 10000, "used": 8200, "percentage": 82,
"status": "warning"
},
{
"id": 2, "category_name": "餐饮", "category_id": 1,
"limit": 3000, "used": 2400, "percentage": 80,
"status": "warning"
},
{
"id": 3, "category_name": "交通", "category_id": 3,
"limit": 1000, "used": 650, "percentage": 65,
"status": "normal"
}
]
}
```
---
### 图表10：预算 vs 实际对比柱状图
**图表类型：** `ECharts Bar Chart`（分组柱状图）
**用途：** 对比各分类的预算限额与实际支出，直观发现超支和节省的分类，辅助下月预算调整。
| 配置项 | 说明 |
|---|---|
| `xAxis` | 各预算分类名称 `type: 'category'` |
| `series[0]` | 预算限额柱，颜色 `#93C5FD`（浅蓝），`barMaxWidth: 24` |
| `series[1]` | 实际支出柱，颜色动态：未超支 `#10B981`（绿），超支 `#EF4444`（红） |
| `series[1].itemStyle.color` | 使用 `function(params)` 回调，根据是否超支动态着色 |
| `markLine` | 在 100% 预算位置画水平参考线 |
| `tooltip` | 显示：`分类名 | 预算: ¥X | 实际: ¥Y | 差额: ±¥Z (XX%)` |
**后端接口：** 复用 `GET /api/v1/budgets?month=2026-02`
---
## 6. 账户管理区 (AccountView)
### 图表11：账户收支瀑布图
**图表类型：** `ECharts Bar Chart`（瀑布图，使用透明柱实现）
**用途：** 展示选定账户在某月内余额的逐日/逐笔变化过程，帮助用户理解"钱是怎么花没的"。
| 配置项 | 说明 |
|---|---|
| 实现方式 | 使用 ECharts 堆叠柱模拟瀑布：底部透明柱 (`itemStyle.color: 'transparent'`) + 上方有色柱 |
| `xAxis` | 日期或交易序号 |
| 颜色逻辑 | 收入笔→绿色柱向上增长，支出笔→红色柱向下减少，最终柱→蓝色(期末余额) |
| `tooltip` | 显示：`日期 | 交易对方 | ±金额 | 余额` |
| `series.label` | 在柱体上方/下方显示金额增减 |
**后端接口：** `GET /api/v1/accounts/:id/waterfall?month=2026-02`
```json
// Response
{
"code": 0,
"data": {
"account_name": "招行储蓄卡",
"opening_balance": 80000,
"closing_balance": 82500,
"transactions": [
{ "date": "2026-02-01", "peer": "工资", "amount": 15000, "type": "income", "balance": 95000 },
{ "date": "2026-02-03", "peer": "房租", "amount": -5500, "type": "expense", "balance": 89500 },
{ "date": "2026-02-05", "peer": "美团外卖", "amount": -35, "type": "expense", "balance": 89465 }
]
}
}
```
---
## 7. 导入质量区 (ImportView)
### 图表12：导入质量统计图
**图表类型：** `ECharts Bar Chart`（堆叠柱状图）
**用途：** 每次导入后展示本次及历史导入的数据质量分布（新增/去重/链路合并/失败），帮助用户监控 ETL 管道健康度。
| 配置项 | 说明 |
|---|---|
| `xAxis` | 导入批次（按时间倒序，最近 10 次） |
| `series[0]` | 新导入数，颜色 `#10B981`（绿），`stack: 'total'` |
| `series[1]` | 去重跳过数，颜色 `#F59E0B`（橙），`stack: 'total'` |
| `series[2]` | 链路合并数，颜色 `#4F6EF7`（蓝），`stack: 'total'` |
| `series[3]` | 失败数，颜色 `#EF4444`（红），`stack: 'total'` |
| `tooltip` | 显示各类明细和总解析条数 |
**后端接口：** `GET /api/v1/bills/import-history?limit=10`
```json
// Response
{
"code": 0,
"data": [
{
"batch_id": "20260226-001",
"provider": "alipay",
"imported_at": "2026-02-26T19:30:00+08:00",
"total": 150, "imported": 132, "duplicated": 15, "linked": 3, "failed": 0
}
]
}
```
---
## 8. 全局设计规范
### 8.1 统一色彩系统
为保证跨图表的**视觉一致性**和**认知连贯性**，所有图表使用统一的语义化色板：
| 语义 | 色值 | 用途场景 |
|---|---|---|
| **收入/正向/安全** | `#10B981` (Emerald-500) | 收入柱、正常进度、储蓄类 |
| **支出/负向/危险** | `#EF4444` (Red-500) | 支出柱、超支预警、失败 |
| **警告/临近阈值** | `#F59E0B` (Amber-500) | 80% 预算警告、去重跳过 |
| **中性/信息** | `#4F6EF7` (Indigo-500) | 结余线、链路合并、账户主色 |
| **辅助蓝** | `#818CF8` (Violet-400) | 辅助信息、次要指标 |
| **背景辅助** | `#F8FAFC` (Slate-50) | 图表背景、空白区域 |
**分类色板**（饼图/折线图/桑基图多分类通用，共 10 色循环）：
```typescript
const CATEGORY_PALETTE = [
'#4F6EF7', '#10B981', '#F59E0B', '#EF4444', '#8B5CF6',
'#EC4899', '#06B6D4', '#F97316', '#84CC16', '#6366F1'
]
```
### 8.2 ECharts 公共配置封装
```typescript
// composables/useECharts.ts
import * as echarts from 'echarts/core'
import { ref, onMounted, onUnmounted, watch } from 'vue'
export function useECharts(containerRef: Ref<HTMLElement | null>) {
const chartInstance = ref<echarts.ECharts | null>(null)
let resizeObserver: ResizeObserver | null = null
onMounted(() => {
if (containerRef.value) {
chartInstance.value = echarts.init(containerRef.value)
// 响应式 resize
resizeObserver = new ResizeObserver(() => {
chartInstance.value?.resize()
})
resizeObserver.observe(containerRef.value)
}
})
onUnmounted(() => {
resizeObserver?.disconnect()
chartInstance.value?.dispose()
})
const setOption = (option: echarts.EChartsOption) => {
chartInstance.value?.setOption(option, { notMerge: true })
}
return { chartInstance, setOption }
}
```
### 8.3 图表联动设计
12 张图在 Vue3 中的协作方式：
```mermaid
graph LR
Store["Pinia: dateRangeStore"] -->|watch dateRange| C1["图表1~3 (Dashboard)"]
Store -->|watch dateRange| C4["图表4~8 (Analysis)"]
Store -->|watch month| C9["图表9~10 (Budget)"]
C4 -->|"emit('category-filter')"| BillTable["账单列表表格"]
C4 -->|"emit('category-filter')"| C7["图表7: 桑基图高亮"]
C9 -->|"点击分类仪表盘"| C10["图表10: 对应分类高亮"]
```
| 联动机制 | 实现方式 |
|---|---|
| **全局时间筛选器** | Pinia store 存储 `dateRange`，所有图表 `watch` 该变量触发 API 重新请求并刷新 |
| **分类联动** | 点击环形图扇区 → `emits('category-filter', categoryId)` → 账单表格过滤 + 桑基图高亮对应节点 |
| **图表 resize** | 统一在 `useECharts` composable 中使用 `ResizeObserver` 处理，配合 Vuetify 响应式断点 |
| **数据懒加载** | 桑基图和热力图数据量较大，使用 `defineAsyncComponent` 延迟渲染，进入视口后加载 |
| **颜色同步** | 跨图表的相同分类使用 `CATEGORY_PALETTE` 通过 `categoryId % 10` 索引取色，保证颜色映射一致 |
### 8.4 ECharts 组件注册清单
采用 ECharts 按需引入，减少打包体积：
```typescript
// plugins/echarts.ts
import * as echarts from 'echarts/core'
import {
LineChart, // 图表1, 6
BarChart, // 图表2, 3, 10, 11, 12
PieChart, // 图表4, 8
HeatmapChart, // 图表5
SankeyChart, // 图表7
GaugeChart, // 图表9
} from 'echarts/charts'
import {
TitleComponent, TooltipComponent, LegendComponent,
GridComponent, DataZoomComponent, VisualMapComponent,
CalendarComponent, MarkLineComponent, MarkPointComponent,
MarkAreaComponent, GraphicComponent, ToolboxComponent
} from 'echarts/components'
import { CanvasRenderer } from 'echarts/renderers'
echarts.use([
LineChart, BarChart, PieChart, HeatmapChart, SankeyChart, GaugeChart,
TitleComponent, TooltipComponent, LegendComponent,
GridComponent, DataZoomComponent, VisualMapComponent,
CalendarComponent, MarkLineComponent, MarkPointComponent,
MarkAreaComponent, GraphicComponent, ToolboxComponent,
CanvasRenderer
])
export default echarts
```
### 8.5 前端组件与后端 API 完整映射
| Vue 组件 | ECharts 图表类型 | 后端 API |
|---|---|---|
| `NetWorthTrendChart.vue` | Line (Area) | `GET /api/v1/dashboard/trend` |
| `CashFlowBarChart.vue` | Bar + Line (混合) | `GET /api/v1/dashboard/trend` |
| `AssetCompositionChart.vue` | Bar (Stack) | `GET /api/v1/dashboard/asset-composition` |
| `ExpensePieChart.vue` | Pie (Donut) | `GET /api/v1/analysis/category?type=expense` |
| `CalendarHeatmap.vue` | Heatmap (Calendar) | `GET /api/v1/analysis/heatmap` |
| `CategoryTrendChart.vue` | Line (Multi) | `GET /api/v1/analysis/category-trend` |
| `SankeyChart.vue` | Sankey | `GET /api/v1/analysis/sankey` |
| `IncomePieChart.vue` | Pie (Donut) | `GET /api/v1/analysis/category?type=income` |
| `BudgetGauge.vue` | Gauge | `GET /api/v1/budgets` |
| `BudgetCompareChart.vue` | Bar (Grouped) | `GET /api/v1/budgets` |
| `AccountWaterfallChart.vue` | Bar (Waterfall) | `GET /api/v1/accounts/:id/waterfall` |
| `ImportQualityChart.vue` | Bar (Stack) | `GET /api/v1/bills/import-history` |

566
16-ProjectMoneyM-转FireFlyIII/3-实现详细稿/4-DDS-to-Stitch-Prompt-Guide.md Normal file
View File

@@ -0,0 +1,566 @@
# DDS 文档 → Google Stitch UI 设计 Prompt 转换指南
> 本文档提供一套系统化的方法论，用于将软件系统的 **DDS（详细设计说明书）** 转换为 **Google Stitch** 能够理解并生成高质量 UI 设计的 prompt。
---
## 一、转换方法论总览
### 核心思路：Zoom-Out → Zoom-In 分层提取
```
DDS 文档
├── 第1层：系统全局上下文（Zoom-Out） → Stitch 全局系统 prompt
├── 第2层：页面级结构提取 → Stitch 逐页设计 prompt
├── 第3层：组件级细节提取 → Stitch 组件精修 prompt
└── 第4层：交互与联动提取 → Stitch 交互追加 prompt
```
> [!IMPORTANT]
> Google Stitch 的最佳实践是**分步生成、逐步精修**，不要试图一次性生成整个系统的 UI。建议按页面逐一生成，每个页面先生成骨架，再通过迭代精修细节。
### DDS 信息提取清单
从 DDS 文档中需要提取的 UI 相关信息：
| 提取维度 | DDS 中的对应章节 | 提取要点 |
|---|---|---|
| **系统定位与目标用户** | §1 项目背景 / PRD | 产品类型、面向人群、核心价值主张 |
| **页面结构与路由** | §3.1 页面结构与路由 | 有哪些页面、层级关系、导航结构 |
| **页面布局** | §3.3 核心页面设计 | ASCII 布局图、区域划分、信息层级 |
| **图表与数据可视化** | 数据可视化 DDS | 图表类型、数据维度、色彩规范 |
| **色彩系统** | §8.1 统一色彩系统 | 语义化色板、分类色板、品牌色 |
| **组件清单** | §3.2 项目结构 | Vue 组件列表、功能定义 |
| **数据模型** | §2.3 数据模型 | 实体关系、字段定义（用于理解界面数据） |
| **API 接口** | §2.4 API 接口 | 数据结构（用于理解界面需要展示什么数据） |
---
## 二、Prompt 模板体系
### 🔹 Step 0：全局 Design Token Prompt（系统级，仅需执行一次）
> 目的：为 Stitch 建立设计系统的基础约束，后续每个页面 prompt 可引用此上下文。
```
【系统设计基调 Prompt】
我正在设计一个名为「ProjectMoneyX」的个人全景财务分析系统的 Web 端 UI。
### 产品定位
- 这是一款面向个人用户的财务数据分析工具
- 核心功能：多源账单导入（支付宝/微信/银行）→ 智能去重 → 多维可视化分析 → 预算管理
- 用户画像：25-40岁的白领/自由职业者，关注个人财务健康，有一定数据分析意识
- 使用场景：主要在桌面端浏览器使用，每周查看1-2次财务报告
### 设计风格要求
- 整体风格：现代金融科技（FinTech）风格，专业但不冰冷
- 设计语言：类似 Material Design 3 的圆角卡片式布局
- 色彩基调：
- 主色/中性蓝：#4F6EF7（Indigo-500），用于品牌调性和信息展示
- 正向/收入色：#10B981（Emerald-500），用于收入、正常状态
- 负向/支出色：#EF4444（Red-500），用于支出、超支预警
- 警告色：#F59E0B（Amber-500），用于临近阈值提醒
- 背景色：#F8FAFC（浅灰白），卡片背景白色
- 字体：使用系统字体 + Noto Sans SC（中文）
- 布局：左侧固定导航栏 + 右侧主内容区的经典 Dashboard 布局
- 深色模式支持：需要考虑暗色主题的兼容性
### 导航结构（侧边栏菜单）
1. 📊 仪表盘（Dashboard）— 默认首页
2. 📋 账单管理（Bills）
3. 📤 账单导入（Import）
4. 🏦 账户管理（Accounts）
5. 💰 预算管理（Budget）
6. 📈 多维分析（Analysis）
7. ⚙️ 规则配置（Rules）
请为这个系统设计一致的视觉风格。所有页面文字使用中文。
```
---
### 🔹 Step 1：仪表盘页面（DashboardView）
> 从 DDS §3.3.1 + 数据可视化 DDS §1 提取
```
【仪表盘页面设计 Prompt】
为「ProjectMoneyX 个人全景财务分析系统」设计仪表盘（Dashboard）页面。
### 页面目标
用户打开系统后的第一个页面，需要在一屏内快速获取个人财务健康全貌。
### 页面布局（从上到下）
**第一行：核心指标卡片区（3个等宽卡片）**
- 卡片1「净资产」：显示 ¥116,500，下方小字"较上月 ↑3.2%"，背景带有淡蓝色渐变
- 卡片2「本月收入」：显示 ¥15,000，下方 ↑5.2%（绿色箭头），图标用收入符号
- 卡片3「本月支出」：显示 ¥8,200，下方 ↓3.1%（绿色箭头表示支出减少是好事），图标用支出符号
- 每个卡片都有圆角、微弱阴影、悬停时轻微上浮动画
**第二行：图表区（2列布局，左宽右窄，比例约 6:4）**
- 左侧「净资产趋势图」：面积折线图，展示近12个月的净资产、总资产、总负债三条线
- 净资产线为实线蓝色(#4F6EF7)带半透明渐变填充
- 总资产为绿色虚线(#10B981)
- 总负债为红色虚线(#EF4444)
- 图表上方有标题"净资产趋势"和时间范围选择器（近6月/近12月/全部）
- 右侧「月度现金流对比」：柱状图+折线图混合
- 绿色柱=收入，红色柱=支出，蓝色折线=结余
- 亏损月份的柱状图背景有淡红色标记
**第三行：资产构成区（全宽）**
- 「各账户资产构成」：堆叠面积图，展示各账户余额随时间的构成变化
- 包含：招行储蓄卡、支付宝余额、微信零钱等正向资产（向上堆叠）
- 以及：招行信用卡、花呗等负债（负值向下延伸）
- 图表外框是白色卡片容器，有圆角和阴影
### 视觉要求
- 卡片之间有 16px 间距
- 图表容器统一使用白色圆角卡片（border-radius: 12px）
- 页面顶部有"仪表盘"标题和全局时间筛选器
- 所有数字使用等宽字体，金额显示千分位分隔符
- 页面内容使用中文
请生成一个专业的、现代化的仪表盘页面设计。
```
---
### 🔹 Step 2：账单导入页（ImportView）
> 从 DDS §3.3.2 + 数据可视化 DDS §7 提取
```
【账单导入页设计 Prompt】
为「ProjectMoneyX」设计账单导入页面。
### 页面目标
引导用户完成账单文件的上传和导入，展示导入结果和历史导入质量。
### 页面布局
**上半部分：导入操作区（卡片式步骤引导，Step 1-2-3 横向流程）**
- Step 1「选择来源」：
- 展示 4-6 个可选来源的图标卡片（横向排列）
- 每个卡片包含图标和名称：支付宝（蓝色）、微信支付（绿色）、招商银行（红色）、工商银行（红色）、京东（红色）、美团（黄色）
- 选中状态：卡片边框高亮 + 勾选标记
- 卡片之间 12px 间距，悬停有缩放效果
- Step 2「上传文件」：
- 大尺寸拖拽上传区域（虚线边框，中间云上传图标 + 文字"拖拽文件到此处，或点击选择"）
- 支持的格式提示文字：CSV / XLS / PDF
- 上传中显示进度条
- Step 3「导入结果」：
- 导入成功后显示统计卡片行：
- ✅ 解析 150 条（蓝色）
- ✅ 新导入 132 条（绿色）
- ⚠️ 去重跳过 15 条（橙色）
- 🔗 链路合并 3 条（蓝色）
- ❌ 失败 0 条（灰色）
**下半部分：导入历史质量图表（全宽卡片）**
- 标题：「导入质量趋势」
- 堆叠柱状图：X轴为最近10次导入批次，Y轴为条数
- 绿色段=新导入数，橙色段=去重数，蓝色段=合并数，红色段=失败数
- 图表下方有最近导入记录表格，显示时间、来源、各项统计
### 视觉要求
- 步骤之间用连接线或箭头串联，当前步骤高亮
- 未到达的步骤灰化处理
- 整体卡片式布局，白色圆角卡片 + 淡灰背景
- 页面所有文字使用中文
```
---
### 🔹 Step 3：多维分析页（AnalysisView）
> 从 DDS §3.3.3 + 数据可视化 DDS §2-4 提取
```
【多维分析页设计 Prompt】
为「ProjectMoneyX」设计多维分析页面，这是系统中数据可视化最丰富的页面。
### 页面目标
提供深度的收支分析能力，帮助用户理解"钱花在哪了"和"钱从哪来"。
### 页面结构
**顶部：全局筛选栏**
- 时间范围选择器（日期区间 picker）
- 快捷选项按钮组：本月 / 近3月 / 近6月 / 近1年 / 自定义
- 页面标题左侧显示"多维分析"
**Tab 标签页切换（3个 Tab）**
---
**Tab 1：支出分析**
- 左右两列布局（5:5）
- 左侧「支出结构环形图」：
- 大尺寸环形图（Donut），中心显示"总支出 ¥9,820"
- 外侧标签：餐饮 32.6%、购物 25.5%、交通 12.2% 等
- 支持点击某分类后下钻到二级分类（如 餐饮→外卖/堂食/咖啡）
- 下钻后顶部出现面包屑导航 "全部 > 餐饮"
- 颜色使用分类色板：#4F6EF7、#10B981、#F59E0B、#EF4444、#8B5CF6...
- 右侧「分类支出趋势折线图」：
- 多条折线，每条代表一个支出分类
- 默认展示前5大分类，其余折叠
- 底部有缩放滑块，支持拖拽查看任意时间段
- 颜色与左侧环形图一致（跨图表颜色同步）
- 下方全宽「收支日历热力图」：
- 日历格子视图，展示每日消费强度
- 颜色从浅绿(低消费)渐变到深红(高消费)
- 悬停显示该日总额和前3笔最大账单
- 支持月份/年份切换
---
**Tab 2：资金流向**
- 全宽展示「资金流向桑基图」（Sankey Diagram）⭐ 核心图表
- 三列布局：左列=收入来源（工资、兼职、投资收益），中列=资金池/账户（招行储蓄、支付宝、微信），右列=支出分类（餐饮、购物、居住、储蓄）
- 流线颜色使用源到目标的渐变色
- 悬停高亮相邻节点和链接，淡化其他
- 节点标签：左列左对齐，中列居中，右列右对齐
- 整体图表高度 500px 以上，确保信息清晰
---
**Tab 3：收入分析**
- 「收入来源环形图」：与支出环形图对称设计
- 中心显示"总收入 ¥15,000"
- 使用绿色系配色：#10B981、#34D399、#6EE7B7、#A7F3D0
- 分类：工资、兼职收入、理财收益、转账收款等
### 视觉要求
- Tab 切换使用底部指示线动画
- 所有图表统一白色卡片容器，带标题栏
- 图表标题栏右侧可放置图表操作图标（下载、全屏等）
- 页面所有文字使用中文
```
---
### 🔹 Step 4：预算管理页（BudgetView）
> 从 DDS §4.2 + 数据可视化 DDS §5 提取
```
【预算管理页设计 Prompt】
为「ProjectMoneyX」设计预算管理页面。
### 页面目标
直观展示各分类预算执行进度，快速识别超支和节省项。
### 页面布局
**顶部：月份选择器 + 操作按钮**
- 左侧：月份选择器（< 2026年2月 >），可左右切换
- 右侧：「设置预算」按钮（主色调），点击弹出预算编辑弹窗
**第一行：全局预算仪表盘（居中，大号）**
- 单个大尺寸仪表盘（Gauge），展示全局预算使用率
- 弧形进度条：0-79% 绿色 → 80-99% 橙色 → ≥100% 红色
- 中心显示百分比数字 + "¥8,200 / ¥10,000"
- 标题"全局预算"在仪表盘下方
**第二行：分类预算仪表盘阵列（网格布局，3-4列）**
- 每个分类一个小号仪表盘卡片，包含：
- 分类图标 + 分类名称
- 环形进度条（同样三段变色逻辑）
- 中心数字：82% + "¥2,400/¥3,000"
- 超支的卡片有红色边框闪烁效果
- 示例分类：餐饮(80%⚠️)、交通(65%✅)、购物(110%🔴)、居住(45%✅)、娱乐(30%✅)
**第三行：预算 vs 实际对比柱状图（全宽卡片）**
- 分组柱状图：每个分类两根柱子
- 浅蓝柱=预算限额
- 动态色柱=实际支出（未超支绿色，超支红色）
- 100% 预算位置有水平参考虚线
- tooltip 显示差额和百分比
### 视觉要求
- 仪表盘弧度动画：页面加载时从0动画填充到目标值
- 超支项有强烈的红色视觉提示（不仅是颜色，还有图标/徽章）
- 分类卡片支持悬停展开详情
- 页面所有文字使用中文
```
---
### 🔹 Step 5：账户管理页（AccountView）
> 从 DDS §3.1 + 数据可视化 DDS §6 提取
```
【账户管理页设计 Prompt】
为「ProjectMoneyX」设计账户管理页面。
### 页面目标
管理用户的所有资金账户，查看各账户余额和交易流水。
### 页面布局
**顶部：账户总览卡片行**
- 横向卡片滚动/网格，每个账户一个卡片：
- 卡片上半部分：账户图标 + 账户名称 + 账户类型标签（储蓄卡/信用卡/电子钱包）
- 卡片下半部分：当前余额（大字加粗）
- 储蓄卡类：蓝色系渐变背景
- 信用卡类：红色系渐变背景，额外显示"已用额度/总额度"
- 电子钱包类：紫色系渐变背景
- 右上角有编辑和删除小图标
- 最右侧有一个虚线框的「+ 添加账户」卡片
**下半部分：选中账户的详情区**
- 选中某个账户卡片后，下方展示该账户的详情：
- 左侧（6/10宽度）「账户收支瀑布图」：
- 瀑布柱状图，展示月内余额逐笔变化
- 起始柱（月初余额）→ 绿色向上柱（收入）→ 红色向下柱（支出）→ 蓝色终止柱（月末余额）
- 每根柱子上方/下方标注金额变化
- 月份选择器在图表标题栏
- 右侧（4/10宽度）：账户信息卡片
- 账户名称、类型、币种
- 本月收入合计 / 支出合计 / 净变化
- 最近 5 笔交易列表
### 视觉要求
- 账户卡片类似银行卡片造型，有微光泽/渐变效果
- 选中账户卡片有高亮边框 + 下方指示箭头
- 页面所有文字使用中文
```
---
### 🔹 Step 6：账单管理页（BillListView）
```
【账单管理页设计 Prompt】
为「ProjectMoneyX」设计账单管理页面。
### 页面目标
支持多维条件筛选和查看所有账单记录。
### 页面布局
**顶部：高级筛选面板（可展开/收起的卡片）**
- 第一行筛选项：时间范围（日期区间）、交易类型（收入/支出/全部 按钮组）
- 第二行筛选项：金额区间（最小~最大）、账户（下拉选择）、分类（级联选择器）、来源（支付宝/微信等 多选）
- 第三行：关键词搜索框（搜索交易对方/商品说明）+ 「查询」按钮 + 「重置」按钮
- 展开/收起按钮，默认只显示第一行
**主体：账单数据表格**
- 表头列：日期、交易对方、商品说明、金额、交易类型、分类、账户、来源
- 金额列：收入行显示绿色正数，支出行显示红色负数
- 交易类型列：使用小标签（tag），收入=绿tag，支出=红tag
- 来源列：显示对应图标（支付宝/微信等小logo）
- 每行末尾有操作列：查看详情、编辑、删除
- 表格支持列排序（点击表头）
- 底部分页器：显示总条数，每页20/50/100条切换
**表格上方工具栏**
- 左侧：显示匹配结果数"共 500 条记录"
- 右侧：导出按钮、列设置按钮
### 视觉要求
- 表格偶数行有浅灰背景（斑马纹）
- 悬停行高亮
- 支出和收入行的金额颜色区分明显
- 页面所有文字使用中文
```
---
### 🔹 Step 7：规则配置页（RuleView）
```
【规则配置页设计 Prompt】
为「ProjectMoneyX」设计规则配置页面。
### 页面目标
让用户管理自动分类映射规则和账户路由规则，控制 ETL 数据清洗行为。
### 页面布局
**Tab 切换：分类规则 / 账户路由规则**
---
**Tab 1：分类映射规则**
- 顶部：「+ 新增规则」按钮
- 规则列表（卡片式，非表格）：
- 每条规则一个卡片，显示：
- 匹配条件：标识标签 "交易对方" 或 "商品说明"，后面显示正则表达式（代码样式）
- 箭头 →
- 目标分类："餐饮-咖啡" (带分类颜色标签)
- 优先级数字徽章
- 启用/禁用切换开关
- 编辑/删除操作图标
- 规则按优先级降序排列，高优先级规则排在前面
- 支持拖拽排序调整优先级
---
**Tab 2：账户路由规则**
- 类似的卡片式列表：
- 来源标签："支付宝"（蓝色标签）
- 匹配方式：支付方式包含 "招商银行信用卡"
- 箭头 →
- 目标账户："招行信用卡" (带账户类型图标)
**新增/编辑弹窗**
- 表单弹窗：选择匹配字段、输入正则表达式、选择目标分类/账户、设置优先级
- 有"测试规则"按钮，可输入样例文本测试匹配结果
### 视觉要求
- 规则卡片之间有清晰的分隔
- 正则表达式用等宽字体 + 代码背景色展示
- 箭头使用 → 图标表达映射关系
- 页面所有文字使用中文
```
---
## 三、迭代精修 Prompt 模板
在 Stitch 生成初版设计后，使用以下追加 prompt 进行精修：
### 3.1 交互动效精修
```
请为当前设计添加以下交互效果：
1. 卡片悬停时轻微上浮（translateY: -2px）+ 阴影加深
2. 数字指标在页面加载时有从0到目标值的计数动画
3. Tab 切换时有滑动过渡效果
4. 图表区域在进入视口时有淡入+上滑的入场动画
5. 按钮点击有涟漪扩散效果（Material Design ripple）
```
### 3.2 响应式适配
```
请调整当前设计的响应式布局：
- 桌面端（≥1280px）：侧边栏固定展开 + 主内容区自适应
- 平板端（768-1279px）：侧边栏收起为图标模式，主内容区全宽
- 移动端（<768px）：侧边栏变为底部 Tab 导航，卡片竖向堆叠
- 仪表盘的三列卡片在移动端变为单列
- 图表在小屏下高度等比缩小，保持可读性
```
### 3.3 暗色模式
```
请为当前设计创建暗色模式版本：
- 背景色从 #F8FAFC 变为 #0F172A（深蓝灰）
- 卡片背景从白色变为 #1E293B
- 文字颜色从深灰变为 #E2E8F0
- 图表背景透明，网格线使用 rgba(255,255,255,0.1)
- 色彩系统中的语义色（绿/红/橙/蓝）保持不变但亮度微调
- 阴影从灰色阴影变为更深的投影
- 侧边栏背景 #1E293B，选中项高亮使用主色半透明
```
### 3.4 空状态设计
```
请为以下场景设计空状态界面：
1. 首次使用 - 仪表盘无数据：显示插画 + "开始导入您的第一份账单" + 引导按钮
2. 账单列表搜索无结果：显示搜索插画 + "未找到匹配的账单记录"
3. 预算页面未设置预算：显示图标 + "您还未设置任何预算" + "立即设置"按钮
4. 分析页面数据不足：显示图表插画 + "数据量不足，建议导入更多账单后查看分析"
```
---
## 四、高级技巧
### 4.1 使用 DDS 中的 ASCII 布局图
> DDS 中常包含 ASCII 格式的页面布局草图，可以直接转化为 Stitch 的结构描述。
**DDS 原文示例：**
```
┌─────────────────────────────────────────────────────────┐
│ [净资产卡片] [本月收入卡片] [本月支出卡片] │
│ ¥116,500 ¥15,000 ↑5.2% ¥8,200 ↓3.1% │
├──────────────────────────┬──────────────────────────────┤
│ 收支趋势折线图 (ECharts) │ 消费结构饼图 (ECharts) │
│ (近12个月) │ (本月各分类占比) │
├──────────────────────────┴──────────────────────────────┤
│ 各账户余额一栏表 (v-data-table) │
└─────────────────────────────────────────────────────────┘
```
**转化手法：** 将 ASCII 图的区块关系、比例、信息层级直接翻译为自然语言的空间描述（上/下、左/右、占比等），如上述各页面 prompt 所示。
### 4.2 从 API Response 推导界面数据
> DDS 中的 API 响应结构直接告诉我们界面需要展示哪些字段。
```json
// 从 DDS 的 API 响应结构
{
"total_assets": 125000.00, → UI: "总资产 ¥125,000"
"total_liabilities": 8500.00, → UI: "总负债 ¥8,500"
"net_worth": 116500.00, → UI: "净资产 ¥116,500"（核心指标卡片）
"income_mom_pct": 5.2, → UI: "↑5.2%"（环比增长标签）
}
```
### 4.3 从色彩系统构建 Stitch Prompt
> DDS §8.1 的色彩系统应该完整传递给 Stitch，确保生成的设计色彩一致。
**关键做法：** 在每个页面 prompt 中引用完整的语义化色彩映射（收入=绿、支出=红、警告=橙、中性=蓝），而不是仅给出色值。
### 4.4 Stitch 的 Experimental Mode 高级用法
如果你有系统的线框图或草图，可以使用 Stitch 的 **Experimental Mode**：
1. 将 DDS 中的 Mermaid 图表导出为图片
2. 将 ASCII 布局图在画图工具中绘制为简单线框
3. 配合文字 prompt 一起上传到 Stitch Experimental Mode
4. 这种图文并茂的方式能获得更精准的布局结果
---
## 五、完整工作流程
```mermaid
graph TD
A["1. 阅读 DDS 文档"] --> B["2. 提取 UI 相关信息"]
B --> C["3. 编写全局设计 Token Prompt"]
C --> D["4. 按页面逐一生成设计"]
D --> E["5. 使用迭代 Prompt 精修"]
E --> F{"6. 满意？"}
F -->|否| E
F -->|是| G["7. 导出为 Figma/HTML"]
G --> H["8. 结合 DDS 技术选型进行开发"]
```
### 推荐执行顺序
| 步骤 | Prompt | 预期产出 |
|---|---|---|
| 1 | Step 0: 设计基调 | 确定整体风格，不需要实际页面 |
| 2 | Step 1: 仪表盘 | 最重要的页面，奠定视觉基调 |
| 3 | Step 3: 多维分析 | 最复杂的页面，包含最多图表 |
| 4 | Step 4: 预算管理 | 仪表盘风格的延伸 |
| 5 | Step 2: 账单导入 | 流程导向页面 |
| 6 | Step 5: 账户管理 | 卡片+图表混合 |
| 7 | Step 6: 账单管理 | 表格导向页面 |
| 8 | Step 7: 规则配置 | 配置类页面 |
> [!TIP]
> **先攻克最重要+最复杂的页面**（仪表盘和多维分析），这两个页面的设计语言确立后，其他页面可以快速复用。

17
17-ProjectMoneyX/1-原始需求/0-产品经理-prompt.md Normal file
View File

@@ -0,0 +1,17 @@
你现在是一名策略产品经理，你擅长进行市场研究和竞品分析，以制定产品策略。你能把握行业趋势，了解用户需求，并在此基础上优化产品功能和用户体验。请在这个角色下为我解答以下问题。
----
你是一名出色的产品经理，能够根据用户的初始需求，理解用户需求的真实需求意图，改善客户不够完善的需求，形成专业、简练的需求文档。并且能够在基础需求上优化产品的额设计和功能
请根据要求,进行深度的思考，优化[1-初始需求稿.md]，直接给出优化后的PRD
----
你是一名出色的产品经理，请你根据[1-初始需求稿.md]客户的原始需求,审查[2-优化产品需求文档PRD.md],检查PRD文档是否完全满足原始需求;如果有更加优秀的设计方案,请给出修改建议
----
你是一名出色的产品经理，能够根据用户的初始需求，理解用户需求的真实需求意图，改善客户不够完善的需求，形成专业、简练的需求文档。并且能够在基础需求上优化产品的额设计和功能
你之前根据[1-初始需求稿.md]输出了[2-优化产品需求文档PRD.md], 目前初始需求有一些更新,见[1.1-初始需求稿.md],请你详细对比[1.1-初始需求稿.md]和[1-初始需求稿.md]之间的差异, 修改[2-优化产品需求文档PRD.md],得到新的需求文档

19
17-ProjectMoneyX/1-原始需求/1-初始需求稿.md Normal file
View File

@@ -0,0 +1,19 @@
# ProjectMoneyX
旨在为FireFlyIII+DataImporter提供自动化的数据清洗和导入服务
1. 最好能够通过API进行数据的导入到DataImporter
2. 本地多种来源的数据, 清洗为统一的数据格式,本地保存至sqlite数据库
3. 数据去重考虑, 本地的sqlite数据库应该存储清洗之后的数据, 通过时间窗与金额双重校验进行链路合并
4. (请考虑规则映射,本地进行数据规则映射,还是统一由DataImporter进行规则映射)
### 数据支持
1. 支付宝、微信等主流支付平台的账单导入
2. 建设银行、工商银行、中信银行、汇丰银行等主流银行账单
3. 支持美团、京东等生活服务平台的账单
4. 支持币安、ByBit等交易所的币币交易记录
### 参考项目:
1. [double-entry-generator](https://github.com/deb-sig/double-entry-generator)
2. [FireFlyIII](https://github.com/firefly-iii/firefly-iii)
3. [DataImporter](https://github.com/firefly-iii/data-importer)
4. [FireFlyIII-Docs](https://docs.firefly-iii.org/)

0
99-项目模板/3-实现详细稿/1-实现功能-prompt.md → 17-ProjectMoneyX/1-原始需求/2-优化产品需求文档PRD.md
View File

31
17-ProjectMoneyX/2-概要详细设计/0-概要设计prompt.md Normal file
View File

@@ -0,0 +1,31 @@
你是一名资深的软件系统架构师，具备以下核心职责与能力，绘图请使用mermaid语言：
## 需求分析与理解
- 深度解读产品需求文档（PRD），识别业务目标、功能需求与非功能性需求
- 分析需求间的依赖关系与优先级，识别潜在的技术风险与挑战
## 架构设计与规划
- 设计高可用、可扩展、高性能的系统架构，确保系统健壮性与安全性
- 制定技术选型方案，包括开发语言、框架、中间件、数据库等关键技术栈
- 绘制多层次架构图（系统架构图、数据流图、组件交互图）
- 定义模块划分、接口规范、数据模型与核心算法策略
- 规划系统分层结构（展现层、业务层、数据层），明确各层职责边界
## 方案设计与输出
- 针对核心需求点提供详细的技术解决方案，包含实现路径与备选方案
- 设计关键业务流程的时序图与状态机，确保逻辑清晰完整
- 输出规范化的《系统详细设计说明书》，包含架构设计、接口定义、数据库设计等完整文档
## 技术栈说明
- 后端开发技术栈 Golang GROM GIN
- 前端开发技术栈 Vue3 TypeScript Vuetify
请根据 ，按照上述的要求，输出系统详细设计说明书
你之前根据[2-优化产品需求文档PRD.md]输出了[3-详细设计说明书.md], 目前PRD需求有一些更新,见[2.1-优化产品需求文档PRD.md],请你详细对比[2.1-优化产品需求文档PRD.md]和[2-优化产品需求文档PRD.md]之间的差异, 修改[3-详细设计说明书.md],得到新的需求文档.要求尽量不改动[3-详细设计说明书.md]的初始设计,只改动差异化部分的设计

51
17-ProjectMoneyX/2-概要详细设计/bill-data-instructions.md Normal file
View File

@@ -0,0 +1,51 @@
# 支付宝的账单数据
## 数据维度
交易时间 交易分类 交易对方 对方账号 商品说明 收/支 金额 收/付款方式 交易状态 交易订单号 商家订单号 备注
## 交易类型
1. 餐饮美食
2. 投资理财
3. 日用百货
4. 数码电器
5. 交通出行
6. 充值缴费
7. 信用借还
8. 转账红包
9. 生活服务
10. 家居家装
11. 医疗健康
12. 退款
13. 教育培训
14. 住房物业
15. 酒店旅游
16. 文化休闲
17. 运动户外
18. 爱车养车
19. 商业服务
20. 母婴亲子
21. 收入
22. 其他
```支付宝的交易类型是最为丰富的，应该以此为准，其他平台的交易类型应该映射到支付宝的交易类型```
# 微信的账单数据
## 数据维度
交易时间 交易类型 交易对方 商品 收/支 金额(元) 支付方式 当前状态 交易单号 商户单号 备注
## 交易类型
商户消费
扫二维码付款
转账
微信红包（单发）
微信红包-退款
微信红包
微信红包（群红包）
美团平台商户-退款
滴滴出行-退款
腾讯云费用账户-移动支付-退款
```需要通过 商品 内容推断得到具体的交易类型```

565
17-ProjectMoneyX/2-概要详细设计/prd-claude.md Normal file
View File

@@ -0,0 +1,565 @@
# ProjectMoneyX — 产品需求文档（PRD）
> **版本**：v1.0 | **日期**：2026-03-03 | **状态**：综合定稿
---
## 1. 产品概述
### 1.1 产品名称
**ProjectMoneyX**
### 1.2 产品定位
ProjectMoneyX 是一款面向 Firefly III 生态的**本地化多源账单数据治理中间件**。
它并非简单的"导入工具"，而是 Firefly III 的前置**数据治理层**——负责将分散在支付平台、银行、生活服务及加密货币交易所的零散账单，经过标准化清洗、智能去重与链路合并后，无缝推送至 Firefly III / Data Importer，实现全资产的自动化流转与管理。
### 1.3 产品愿景
让用户可以将来自多源账单**一键汇总**为统一结构，经过规则映射与去重合并后，稳定导入 Firefly III，形成**可持续、可审计、可复用**的个人财务数据资产。
---
## 2. 背景与核心痛点
### 2.1 当前问题
| # | 痛点 | 说明 |
|---|------|------|
| 1 | **数据源分散** | 账单来源覆盖支付宝、微信、银行、生活服务平台、交易所，导出格式各异 |
| 2 | **字段不统一** | 不同平台对时间、金额、收支方向、交易类型、对手方、备注等字段定义不同 |
| 3 | **重复与链路拆分** | 同一笔真实交易可能在多个来源中出现（如银行卡转支付宝同时出现在两方账单），或在单一来源中拆成多条流水（下单、支付、退款、手续费） |
| 4 | **导入链路复杂** | Data Importer 偏重"导入"，并不擅长承担复杂的本地多源清洗编排 |
| 5 | **规则分散** | 若完全依赖 Data Importer 进行规则映射，会导致多来源规则难以统一沉淀和复用 |
### 2.2 真实需求意图
从原始需求分析，用户真正需要的是一个完整的：
- **多源账单标准化中台** — 屏蔽平台差异
- **本地清洗去重引擎** — 消除重复与链路碎片
- **可配置规则映射系统** — 沉淀长期积累的分类知识
- **面向 Firefly III 的导入适配层** — 无缝对接现有生态
---
## 3. 产品目标
### 3.1 核心目标
1. 支持多源账单文件导入并解析为**统一交易模型**
2. 支持在本地完成清洗、标准化、规则映射、去重与链路合并
3. 支持通过 API 或中间文件方式将数据导入 Data Importer / Firefly III
4. 支持将清洗后的标准交易持久化到本地 SQLite，便于追溯、重跑和校验
### 3.2 MVP 成功标准
| # | 标准 |
|---|------|
| 1 | 用户可导入至少 3 类主流账单（支付平台、银行、生活消费平台） |
| 2 | 同一批数据可在本地完成去重并输出统一交易记录 |
| 3 | 用户可完成从「上传文件 → 预览清洗结果 → 应用规则 → 导入 Firefly III」的完整闭环 |
| 4 | 导入失败可追溯到原始文件、解析结果和转换结果 |
---
## 4. 目标用户
### 4.1 核心用户画像
- 拥有多平台消费/收支记录的个人用户
- 使用 Firefly III 进行个人财务管理的进阶用户
- 有一定技术能力，希望本地掌控账单数据的用户
### 4.2 用户特征
- 注重隐私，倾向于本地部署
- 可接受文件导入而非完全自动爬取
- 关注财务统计的一致性与长期可维护性
---
## 5. 产品范围
### 5.1 本期范围（In Scope）
1. 本地账单文件导入（CSV / Excel / 常见文本格式）
2. 多来源适配器解析（插件化架构）
3. 统一交易模型转换
4. 本地规则映射（分类/账户/标签）
5. 去重与链路合并
6. SQLite 本地持久化
7. 导入结果预览与确认
8. 对接 Firefly III / Data Importer 的导入能力
9. 导入任务日志与失败重试
### 5.2 非本期范围（Out of Scope）
1. 直接登录第三方平台自动抓取账单
2. 银行/平台开放 API 的在线拉取（后续可扩展）
3. 完整 BI 分析平台
4. 替代 Firefly III 的账本能力
5. 高频实时同步（本期以"批量导入"为主）
---
## 6. 产品架构与数据流转
### 6.1 数据流转拓扑
```
┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ 多源账单导入 │ -> │ 解析器(Parser) │ -> │ 标准化入库 │ -> │ 去重与链路合并 │ -> │ 规则映射 │ -> │ 导出/推送 │
│ (文件上传) │ │ (Adapter层) │ │ (SQLite) │ │ (Dedup+Link) │ │ (Rule Engine) │ │ (API/CSV) │
└──────────────┘ └──────────────┘ └──────────────┘ └──────────────┘ └──────────────┘ └──────────────┘
```
### 6.2 规则映射策略：两段式分离
> **关键产品决策**：规则映射采用"本地为主，Data Importer 为辅"的两段式策略。
**第一阶段 — ProjectMoneyX 负责（数据对齐 + 业务分类）**：
- **字段级映射**：将各平台异构字段（如支付宝"交易对方"、银行"附言"）统一映射为标准数据字段
- **业务分类映射**：将交易对手、描述等信息映射到分类（餐饮、交通、工资等）、账户、标签
- **商户名归一化**：统一商户别名（如"美团外卖-xxx店"→ 统一商户名）
**第二阶段 — Firefly III / Data Importer 负责（兜底与补充）**：
- 最后一层字段兼容适配
- 临时补充规则
- 与 Firefly III 导入格式保持兼容
**选择本地规则映射为主的核心理由：**
1. **多源统一能力更强**：本地能先统一语义，再输出稳定格式
2. **规则可沉淀**：用户长期积累的分类规则、商户别名、账户映射，不应绑定在某个导入器实例里
3. **可解释性更高**：用户能在导入前看到"这条为何被分到餐饮/交通"
4. **迁移性更好**：即使未来不使用 Data Importer，也能复用规则引擎
### 6.3 分层架构
```
┌─────────────────────────────────────────────────────┐
│ Web UI / CLI │
├─────────────────────────────────────────────────────┤
│ Adapter 层 │ 各平台账单解析器（插件化） │
├─────────────────────────────────────────────────────┤
│ Normalize 层 │ 字段标准化、统一交易模型转换 │
├─────────────────────────────────────────────────────┤
│ Match 层 │ 去重与链路合并 │
├─────────────────────────────────────────────────────┤
│ Rule 层 │ 分类/账户/标签/对手方映射 │
├─────────────────────────────────────────────────────┤
│ Export 层 │ 导出至 Data Importer / Firefly III │
├─────────────────────────────────────────────────────┤
│ Storage 层 │ SQLite 持久化 + 审计日志 │
└─────────────────────────────────────────────────────┘
```
**设计原则：**
- 平台差异尽量收敛在 Adapter 层
- 统一模型要稳定，避免被单个平台格式污染
- 导入层与规则层解耦，便于未来替换下游系统
---
## 7. 核心功能模块
### 7.1 模块 A：数据源接入模块
负责接收和管理多来源账单文件。
**功能点：**
- 支持文件上传（CSV / Excel / 常见文本格式）
- 支持来源类型自动识别或用户手动指定
- 支持批量文件导入
- 支持记录原始文件元信息（文件名、来源、导入时间、文件哈希值）
**首批支持来源：**
| 类型 | 平台 | 备注 |
|------|------|------|
| 支付平台 | 支付宝、微信支付 | 核心优先级 |
| 传统银行 | 建设银行、工商银行、中信银行、汇丰银行 | 需考虑不同语言/地区的格式兼容 |
| 生活服务 | 美团、京东 | 用于细化支付平台的笼统账单 |
| 加密货币 | 币安(Binance)、ByBit | 优先支持现货/资金流水，衍生品后续扩展 |
> **产品建议**：电商/生活平台的账单主要用于**细化**支付平台的笼统记录。例如，将微信支付的"美团订单"替换为具体的"外卖-商家名"。
### 7.2 模块 B：解析与标准化模块
负责将不同来源账单解析为**统一交易模型**，屏蔽不同平台字段差异。
**统一交易模型核心字段：**
| 字段名 | 类型 | 说明 |
|--------|------|------|
| `transaction_id` | String | 系统内唯一 ID（自动生成） |
| `source_platform` | Enum | 来源平台（alipay/wechat/ccb/icbc/...） |
| `source_record_id` | String | 原始记录 ID / 交易流水号 |
| `trade_time` | DateTime | 交易时间（统一为本地标准时区） |
| `amount` | Decimal | 交易金额（高精度，正数） |
| `currency` | String | 币种（CNY/USD/USDT/...） |
| `direction` | Enum | 收入 / 支出 / 转账 / 退款 / 手续费 |
| `counterparty` | String | 交易对手 |
| `merchant_name` | String | 商户名 |
| `category_raw` | String | 原始分类（平台提供） |
| `category_mapped` | String | 映射后分类（规则引擎输出） |
| `order_id` | String | 订单号 |
| `parent_order_id` | String | 父链路号（用于链路合并） |
| `note` | String | 备注 |
| `raw_payload` | JSON | 原始记录快照（完整保留） |
| `import_batch_id` | String | 导入批次 |
| `status` | Enum | 待清洗 / 待导入 / 已导入 / 失败 |
**标准化规则：**
- 时间统一为本地标准时区（UTC+8）
- 金额统一为 Decimal 高精度保存
- 正负号规则统一：独立 `direction` 字段 + 正金额值
- 交易类型统一到平台无关的业务枚举
### 7.3 模块 C：去重与链路合并模块
这是本系统的**核心亮点**，负责识别重复流水与还原真实交易链路。
#### 7.3.1 去重目标
解决以下典型问题：
- 同一账单文件被重复导入
- 同一交易在多个来源重复出现（如银行卡转支付宝同时出现在两方账单）
- 同一文件中存在重复记录
#### 7.3.2 链路合并目标
解决以下典型问题：
- 一笔真实消费对应多条流水（支付、优惠、退款、手续费）
- 同一订单在不同平台产生镜像记录（如京东订单 + 微信支付流水）
- 跨账户资金流动产生的两笔独立记录
#### 7.3.3 三层去重策略
采用"**基础去重 → 模糊去重 → 链路合并**"三层递进模型：
**A. 基础去重（严格去重 — 精确匹配）**
基于以下唯一性组合进行绝对去重，确保同一份账单多次上传不会重复落库：
- 来源平台 + 原始记录 ID（`source_platform` + `source_record_id`）
- 文件哈希 + 行指纹
- 订单号 / 交易单号（若可信）
**B. 模糊去重（相似去重 — 多因子评分）**
当缺少唯一 ID 时，使用以下组合进行评分匹配：
- 时间窗（如 ±5 分钟，可配置）
- 金额精准一致（考虑手续费设置极小金额容差）
- 交易方向一致
- 对手方相似
- 订单号相同或相近
- 来源平台关联规则命中
> **多因子判定升级**：原始需求中提出"时间窗+金额双重校验"作为起点，实际应升级为**"时间窗 + 金额 + 方向 + 订单号 + 对手方 + 来源规则"的多因子判定机制**，以覆盖真实复杂场景。
**C. 链路合并（转账闭环）**
对跨账户资金流动与同一业务链路的记录进行聚合：
- **典型场景**：银行卡支出 1000 元（流向支付宝），支付宝收入 1000 元 → 合并为一笔**内部转账(Transfer)**，源账户=银行卡，目标账户=支付宝
- **主交易 + 附属事件**：消费/收入主体 + 手续费、退款、优惠抵扣、汇率损耗
#### 7.3.4 置信度与人工干预
- 高置信度记录：自动合并
- 低置信度记录：标记为"疑似重复/疑似链路"，进入人工确认队列
- 所有合并操作可回溯、可撤销
### 7.4 模块 D：规则映射模块
负责将标准化交易映射到最终记账语义。
**规则映射内容：**
| 映射类型 | 说明 | 示例 |
|----------|------|------|
| 分类映射 | 交易 → 预设分类 | "美团外卖" → 餐饮 |
| 账户映射 | 来源 → 账户名 | 微信支付 → 微信零钱 |
| 对手方映射 | 商户名标准化 | "饿了么-xxx店" → "饿了么" |
| 标签映射 | 交易 → 标签 | 可标记为：报销、家庭、订阅、投资 |
| Firefly III 字段映射 | 内部字段 → FF3 字段 | direction → type (withdrawal/deposit/transfer) |
**规则配置能力：**
- 支持基于正则、关键词、金额范围等条件的规则定义
- 支持规则优先级排序
- 规则命中结果可精确解释（每条交易展示命中的具体规则）
- 支持规则模板库，预置常见映射
### 7.5 模块 E：导入编排模块
负责将清洗后的数据导入 Firefly III 生态。
**模式 A：API 推送模式（优先）**
- 通过 Webhook 或直接调用 Data Importer / Firefly III API
- 自动发起导入任务
- "本地清洗完毕 → 自动触发 DataImporter 导入任务"的丝滑体验
- 可追踪返回结果
**模式 B：中间文件导出模式**
- 生成完全符合 Data Importer 规范的标准 CSV / JSON
- 用户手动导入
- 适合 API 不稳定或权限受限场景
**导入前校验：**
- 必填字段完整性校验
- 金额/时间格式校验
- 账户映射完整性校验
- 重复导入拦截
**导入后反馈：**
- 导入成功/失败数量统计
- 失败原因分类展示
- 失败记录可单独重试（无需整批重做）
### 7.6 模块 F：本地存储与审计模块
负责数据持久化与全链路可追溯性。
**SQLite 核心数据表：**
| 表名 | 说明 |
|------|------|
| `source_files` | 原始文件表（文件名、哈希、来源、导入时间） |
| `raw_records` | 原始解析记录表（原始数据快照） |
| `transactions` | 标准交易表（统一模型） |
| `dedup_relations` | 去重关系表（记录合并依据） |
| `rules` | 规则配置表 |
| `import_tasks` | 导入任务表 |
| `import_results` | 导入结果表 |
| `audit_logs` | 操作日志表 |
**设计目标：**
- 支持重跑：任意阶段可重新执行
- 支持审计：完整记录每条交易的处理全过程
- 支持回溯：任一交易可追溯到来源文件、来源平台、经过的规则处理链
---
## 8. 核心用户场景
### 场景 1：月度账单统一入账
用户每月从支付宝、微信、银行导出账单，批量上传后，系统自动清洗并去重，用户预览确认后一键导入 Firefly III。
### 场景 2：跨平台订单去重
用户在京东下单，通过微信支付。京东账单与微信账单均包含该笔信息。系统识别为同一订单链路，仅保留主交易并记录来源关联。
### 场景 3：跨账户转账闭环
用户从建行卡转入 1000 元到支付宝。银行账单显示"支出 1000"，支付宝账单显示"收入 1000"。系统匹配时间窗 + 金额，将两笔记录合并为一笔内部转账。
### 场景 4：交易所流水整理
用户导入币安和 ByBit 资金流水，系统将充提币、手续费、现货买卖拆分为统一的账务事件，并映射到投资类账户与标签。支持将 Crypto 交易折算为基础法币或保留原始币种。
### 场景 5：导入失败快速修复
某次批量导入中 5 条记录因账户映射缺失而失败。用户在失败列表中查看原因，补充规则后仅重试这 5 条，无需重做整批。
---
## 9. 功能优先级
### P0 — 必须有（MVP 核心）
| # | 功能 |
|---|------|
| 1 | 文件上传与批量导入 |
| 2 | 来源类型识别/选择 |
| 3 | 多来源解析器框架（插件化） |
| 4 | 统一交易模型 |
| 5 | 本地 SQLite 持久化 |
| 6 | 基础去重（严格去重） |
| 7 | 链路合并（转账闭环） |
| 8 | 基础规则映射（分类/账户） |
| 9 | 导入预览与确认 |
| 10 | API / 文件两种导入方式 |
| 11 | 导入日志与失败重试 |
### P1 — 应该有
| # | 功能 |
|---|------|
| 1 | 模糊去重（多因子评分） |
| 2 | 规则模板库 |
| 3 | 商户别名归一化 |
| 4 | 用户可配置时间窗与去重阈值 |
| 5 | 导入批次管理 |
| 6 | 手动合并/手动拆分疑似交易链路 |
| 7 | 标签映射 |
### P2 — 可以有
| # | 功能 |
|---|------|
| 1 | 自动来源识别增强（智能推断文件类型） |
| 2 | 可视化规则调试 |
| 3 | 简易统计报表（导入概览、分类占比） |
| 4 | 多账本导入支持 |
| 5 | 对账可视化（展示未匹配的"孤儿"转账记录） |
| 6 | 加密货币多币种与法币折算 |
---
## 10. 产品信息架构
### 10.1 一级模块
```
ProjectMoneyX
├── 导入中心 # 文件上传、批次管理
├── 数据清洗 # 解析结果、标准化预览
├── 去重处理 # 重复记录、链路合并、人工确认
├── 规则管理 # 分类/账户/标签/对手方规则配置
├── 导入任务 # 导入执行、结果查看、失败重试
├── 数据审计 # 全链路追溯、操作日志
└── 系统设置 # Firefly III 连接配置、时间窗参数等
```
### 10.2 关键页面
| 页面 | 说明 |
|------|------|
| 文件上传页 | 拖拽/选择文件，选择或自动识别来源类型 |
| 导入批次详情页 | 展示批次内所有记录和处理状态 |
| 清洗结果预览页 | 展示标准化后的交易列表，支持逐条查看映射详情 |
| 重复记录处理页 | 展示疑似重复/链路合并记录，支持人工确认或拒绝 |
| 规则配置页 | 可视化配置分类、账户、标签映射规则 |
| 导入结果页 | 展示导入成功/失败统计，失败可重试 |
| 审计追溯页 | 查看任一交易的完整处理链路 |
---
## 11. 关键交互原则
1. **先预览，后导入**：任何清洗结果必须允许用户确认后再执行导入
2. **规则可解释**：每条交易应展示命中的具体规则和分类依据
3. **重复可回溯**：被判定重复/合并的记录必须可查看判定依据与原始数据
4. **失败可重试**：导入失败不应要求整批重做，支持单条/选择性重试
5. **操作可逆**：合并、分类等操作均可撤销回滚
---
## 12. 非功能需求
### 12.1 安全与隐私
- **本地优先原则**：鉴于财务数据的极度敏感性，完全采用本地化部署（Docker / 本地命令行 / 本地 Web UI）
- SQLite 数据库仅存在于本地，敏感账单数据默认不上传云端
- API Token 加密存储
- 操作日志不泄露敏感字段
### 12.2 性能
- 单次导入 1 万条记录应可完成解析与清洗
- 去重计算应在合理时间内完成（建议 30 秒内完成主流程）
### 12.3 可维护性
- **插件化架构**：解析器(Parser)设计为独立模块，银行/平台格式变更时只需更新对应 Parser，无需重构主程序
- **规则引擎可扩展**：支持新增规则类型和匹配条件
- **去重策略可配置**：时间窗、金额容差、置信度阈值均可配置
### 12.4 可追溯性
- 任一导入结果必须可追溯至原始文件与原始记录
- 任一规则命中必须可解释
- 任一合并操作必须记录判定依据
---
## 13. 版本规划
### V1.0（MVP）
- 支付宝 / 微信 / 2 家银行账单支持
- 文件导入、解析、标准化
- SQLite 持久化
- 基础去重（严格去重）
- 基础规则映射（分类/账户）
- Data Importer API 导入 + CSV 导出
- 导入预览与确认
### V1.5
- 美团 / 京东账单支持
- 链路合并增强（转账闭环 + 订单链路聚合）
- 模糊去重（多因子评分）
- 批次管理与失败重试
- 手动修正与确认流程
- 商户别名归一化
### V2.0
- 币安 / ByBit 交易所流水适配
- 高级规则系统（模板库 + 可视化调试）
- 对账可视化（孤儿记录展示 + 手动干预）
- 简易统计报表（导入概览、分类占比）
- 多账本 / 多环境支持
- 加密货币多币种管理（法币折算 / 多货币对接）
---
## 14. 风险与应对策略
| # | 风险 | 影响 | 应对策略 |
|---|------|------|----------|
| 1 | 不同平台账单格式频繁变化 | 解析器失效 | 采用插件化解析器 + 版本化适配，格式变更只需更新对应 Parser |
| 2 | 去重误判（误合并/漏合并） | 数据准确性受损 | 采用"严格+模糊"分层策略；低置信度记录进人工确认队列 |
| 3 | 交易所流水语义复杂 | 解析困难 | V1 仅支持资金流水和基础现货，衍生品/复杂划转后续扩展 |
| 4 | 过度依赖 Data Importer | 耦合风险 | 核心规则与标准化能力沉淀在本地，导入器仅作为输出目标之一 |
| 5 | 加密货币汇率波动 | 金额折算不稳定 | 支持保留原始币种，汇率折算为可选项，对接 Firefly III 多货币系统 |
---
## 15. 参考项目
| 项目 | 说明 |
|------|------|
| [double-entry-generator](https://github.com/deb-sig/double-entry-generator) | 复式记账生成工具，核心参考项目 |
| [Firefly III](https://github.com/firefly-iii/firefly-iii) | 目标对接的个人财务管理系统 |
| [Data Importer](https://github.com/firefly-iii/data-importer) | Firefly III 的数据导入器 |
| [Firefly III Docs](https://docs.firefly-iii.org/) | Firefly III 官方文档 |
---
## 16. 总结
ProjectMoneyX 不是一个"简单导入工具"，而是一个面向 Firefly III 的**本地账单数据治理中台**。
其核心价值可以浓缩为：
> 1. **汇聚多源账单** — 一站式接入支付平台、银行、生活服务、交易所
> 2. **统一交易语义** — 屏蔽平台差异，建立标准化交易模型
> 3. **智能去重合并** — 消除重复，还原真实交易链路与转账闭环
> 4. **本地规则沉淀** — 分类/账户/标签映射可长期积累、可解释、可迁移
> 5. **无缝对接导入** — 丝滑推送至 Firefly III / Data Importer
**核心产品决策：**
> - **规则映射以本地为主，Data Importer 为辅**
> - **去重策略从"时间窗+金额"升级为多因子判定**
> - **SQLite 不仅是缓存，更是清洗结果与审计链路的核心数据底座**
> - **插件化架构确保可持续维护**

70
17-ProjectMoneyX/2-概要详细设计/prd-gemini.md Normal file
View File

@@ -0,0 +1,70 @@
# 产品需求文档 (PRD)：ProjectMoneyX
## 1. 产品概述
**ProjectMoneyX** 是一款专为 FireFlyIII 设计的个人财务自动化数据清洗与导入中间件。它通过统一的数据标准，将分散在支付平台、银行、生活服务及加密货币交易所的零散账单，转化为结构化的财务数据，并无缝对接至 FireFlyIII 的 DataImporter，实现全资产的自动化流转与管理。
## 2. 核心痛点与解决思路
* **痛点**：多平台账单格式各异，手动整理耗时且易错；跨账户转账（如从建行转入支付宝）容易被重复记账（一笔支出，一笔收入）。
* **解决思路 (核心价值)**：
* **标准化**：将千奇百怪的源数据映射为统一的内部数据模型（Standard Schema）。
* **智能化去重与合并**：识别跨账户转账，将单边记录闭环为完整的复式记账流（Double-Entry Journal）。
* **无缝对接**：作为前置清洗层，让 FireFlyIII 专注财务分析，而非脏数据处理。
## 3. 产品架构与数据流转规则
### 3.1 规则映射策略：两段式分离（解答您的疑问）
强烈建议**不要**在 ProjectMoneyX 中做业务类的分类映射（如“买菜”映射到“餐饮”），这会与 FireFlyIII 的 Rule Engine 功能重叠且难以维护。
* **第一阶段（ProjectMoneyX 负责 - 数据对齐）**：负责**字段级映射**。将各平台的异构字段（如支付宝的“交易对方”、银行的“附言”）统一映射为标准数据字段（Date, Amount, Payee, Description, Source Account）。
* **第二阶段（FireFlyIII 负责 - 业务分类）**：利用 FireFlyIII 本身的规则引擎，基于整理好的 Payee 和 Description，自动分配 Budget、Category 和 Tags。
### 3.2 数据流转拓扑
`多源账单导入` -> `解析器 (Parser)` -> `标准化入库 (SQLite)` -> `链路合并与去重 (Deduplication)` -> `格式化输出 (API)` -> `DataImporter / FireFlyIII`
## 4. 核心功能需求
### 4.1 多源数据接入 (Data Ingestion)
系统需支持通过插件化/模块化的方式接入各类账单文件（CSV/Excel/API）：
* **支付平台**：支付宝（Alipay）、微信支付（WeChat Pay）。
* **传统银行**：建设银行、工商银行、中信银行、汇丰银行（需考虑不同语言/地区的账单格式兼容）。
* **电商/生活平台**：美团、京东（主要用于细化支付平台的笼统账单，例如将微信支付的“美团订单”替换为具体的“外卖-商家名”）。
* **加密货币**：Binance、ByBit（需支持将 Crypto 交易折算为基础法币，或保留原始币种对接 FireFlyIII 的多货币系统，需考虑手续费剥离）。
### 4.2 本地数据清洗与存储 (Cleanse & Store)
* **统一数据模型**：所有解析后的数据写入本地 SQLite。核心字段应包含：`Original_ID`, `Platform`, `Transaction_Time`, `Amount`, `Currency`, `Transaction_Type` (入账/出账), `Opposite_Party` (交易对手), `Remark`。
* **数据幂等性校验**：基于平台提供的唯一交易流水号（Original_ID）进行绝对去重，确保同一份账单多次上传不会重复落库。
### 4.3 智能去重与链路合并 (Deduplication & Linkage)
这是本系统的**核心亮点**。针对跨账户资金流动，进行模糊匹配与链路合并：
* **时间与金额双重校验（Time-Amount Window）**：
* 设置可配的时间容差（如 $\pm 5$ 分钟）。
* 金额精准匹配（考虑可能存在的手续费，可设置极小金额容差）。
* **转账链路闭环**：
* *场景*：银行卡支出 1000 元（流向支付宝），支付宝收入 1000 元。
* *动作*：系统在 SQLite 中扫描到这两笔符合“时间窗+金额”匹配的相反流水，将其从“两笔独立的支出和收入”合并为“一笔内部转账 (Transfer)”，源账户为银行卡，目标账户为支付宝。
### 4.4 自动化导出与推送 (Export & Integration)
* **标准 CSV 生成**：基于 SQLite 中已清洗且合并的数据，生成完全符合 FireFlyIII DataImporter 规范的 CSV 文件。
* **API 推送集成**：支持通过 Webhook 或直接调用 DataImporter 的 API 接口，实现“本地清洗完毕 -> 自动触发 DataImporter 导入任务”的丝滑体验。
## 5. 非功能需求与产品设计优化建议
* **本地优先原则**：鉴于财务数据的极度敏感性，项目应完全采用本地化部署（Docker/本地命令行），SQLite 数据库仅存在于本地。
* **插件化架构**：银行和平台的账单格式随时可能变更。建议在代码架构上将“解析器(Parser)”设计为独立模块。未来当某银行格式改变时，只需更新对应 Parser 脚本，而无需重构主程序。
* **对账可视化（可选进阶）**：提供一个简单的本地 Web UI 页面，展示“未成功匹配的孤儿转账记录”，允许用户手动干预合并。

528
17-ProjectMoneyX/2-概要详细设计/prd-gpt.md Normal file
View File

@@ -0,0 +1,528 @@
# ProjectMoneyX 产品需求文档（PRD）
## 1. 产品概述
### 1.1 产品名称
**ProjectMoneyX**
### 1.2 产品定位
ProjectMoneyX 是一个面向个人财务与账务归集场景的**本地化账单清洗、去重、归一化与导入编排系统**。
其目标是为 **Firefly III + Data Importer** 提供自动化的数据预处理能力，解决多平台账单格式不统一、重复交易难识别、导入前数据质量差、分类规则分散等问题。
### 1.3 产品愿景
让用户可以将来自支付平台、银行、生活服务平台、交易所等多源账单，一键汇总为统一结构，经过规则映射与去重合并后，稳定导入 Firefly III，形成可持续、可审计、可复用的个人财务数据资产。
---
## 2. 背景与问题定义
### 2.1 当前问题
用户当前面临的核心问题包括：
1. **数据源分散**：账单来源覆盖支付宝、微信、银行、生活服务平台、交易所，导出格式各异。
2. **字段不统一**：不同平台对时间、金额、收支方向、交易类型、对手方、备注等字段定义不同。
3. **存在重复与链路拆分**：同一笔真实交易可能在多个来源中出现，或在单一来源中拆成多条流水（如下单、支付、退款、手续费）。
4. **导入链路复杂**：Firefly III 的 Data Importer 偏重“导入”，但并不擅长承担复杂的本地多源清洗编排。
5. **分类规则分散**：若完全依赖 Data Importer 进行规则映射，会导致多来源规则难以统一沉淀和复用。
### 2.2 真实需求意图
从初始需求看，用户真正需要的并不只是“导入工具”，而是一个完整的：
* **多源账单标准化中台**
* **本地清洗去重引擎**
* **可配置规则映射系统**
* **面向 Firefly III 的导入适配层**
也就是说，ProjectMoneyX 的核心不是替代 Firefly III，而是成为其前置的“数据治理层”。
---
## 3. 产品目标
### 3.1 核心目标
1. 支持多源账单文件导入并解析为统一结构。
2. 支持在本地完成清洗、标准化、规则映射、去重与链路合并。
3. 支持通过 API 或中间文件方式将数据导入 Data Importer / Firefly III。
4. 支持将清洗后的标准交易持久化到本地 SQLite，便于追溯、重跑和校验。
### 3.2 成功标准（MVP）
1. 用户可导入至少 3 类主流账单（支付平台、银行、生活消费平台）。
2. 同一批数据可在本地完成去重并输出统一交易记录。
3. 用户可完成从“上传文件 → 预览清洗结果 → 应用规则 → 导入 Firefly III”的闭环。
4. 导入失败可追溯到原始文件、解析结果和转换结果。
---
## 4. 目标用户
### 4.1 核心用户
* 有多平台消费/收支记录的个人用户
* 使用 Firefly III 进行个人财务管理的进阶用户
* 有一定技术能力，希望本地掌控账单数据的用户
### 4.2 用户特征
* 注重隐私，倾向于本地部署
* 可接受文件导入而非完全自动爬取
* 关注财务统计的一致性与长期可维护性
---
## 5. 产品范围
### 5.1 本期范围（In Scope）
1. 本地账单文件导入（CSV / Excel / 常见文本格式）
2. 多来源适配器解析
3. 统一交易模型转换
4. 本地规则映射
5. 去重与链路合并
6. SQLite 本地持久化
7. 导入结果预览
8. 对接 Firefly III / Data Importer 的导入能力
9. 导入任务日志与失败重试
### 5.2 非本期范围（Out of Scope）
1. 直接登录第三方平台自动抓取账单
2. 银行/平台开放 API 的在线拉取（后续可扩展）
3. 完整 BI 分析平台
4. 替代 Firefly III 的账本能力
5. 高频实时同步（本期以“批量导入”为主）
---
## 6. 核心产品方案
## 6.1 总体流程
**完整业务链路：**
1. 用户上传账单文件
2. 系统识别来源类型（或用户手动指定）
3. 使用对应解析器提取原始账单记录
4. 将不同来源映射为统一交易结构
5. 执行清洗规则（字段标准化、金额修正、时间格式统一、币种规范化等）
6. 执行去重与链路合并
7. 执行分类/账户/标签规则映射
8. 生成待导入数据集
9. 用户预览并确认
10. 通过 API 或导出中间格式导入 Data Importer / Firefly III
11. 写入任务结果、日志与状态
---
## 6.2 模块设计
### 模块 A：数据源接入模块
负责接收和管理多来源账单文件。
**功能点：**
* 支持文件上传
* 支持来源类型选择/自动识别
* 支持批量文件导入
* 支持记录原始文件元信息（文件名、来源、导入时间、哈希值）
**首批支持来源：**
* 支付平台：支付宝、微信
* 银行：建设银行、工商银行、中信银行、汇丰银行
* 生活服务平台：美团、京东
* 交易平台：币安、ByBit（优先支持现货/资金流水，复杂交易后续逐步扩展）
---
### 模块 B：解析与标准化模块
负责将不同来源账单解析为统一数据结构。
**目标：**
建立统一交易模型，屏蔽不同平台字段差异。
**统一交易核心字段建议：**
* transaction_id（系统内唯一 ID）
* source_type（来源类型）
* source_platform（来源平台）
* source_record_id（原始记录 ID）
* trade_time（交易时间）
* amount（金额）
* currency（币种）
* direction（收入/支出/转账/退款/手续费）
* counterparty（交易对手）
* merchant_name（商户名）
* category_raw（原始分类）
* order_id（订单号）
* parent_order_id（父链路号）
* note（备注）
* raw_payload（原始记录快照）
* import_batch_id（导入批次）
* status（待清洗/待导入/已导入/失败）
**标准化规则：**
* 时间统一为本地标准时区
* 金额统一为 decimal，高精度保存
* 正负号规则统一（支出为负/收入为正，或独立 direction + 正金额，需产品统一）
* 交易类型统一到平台无关的业务枚举
---
### 模块 C：去重与链路合并模块
负责识别重复流水与同一业务链路的多条记录。
#### 1）去重目标
解决以下问题：
* 同一账单被重复导入
* 同一交易在多个来源重复出现
* 同一文件中存在重复记录
#### 2）链路合并目标
解决以下问题：
* 一笔真实消费对应多条流水（支付、优惠、退款、手续费）
* 同一订单在不同平台产生镜像记录（如京东订单 + 微信支付流水）
#### 3）建议策略
采用“**基础去重 + 业务链路合并**”双层模型：
**A. 基础去重（严格去重）**
优先使用以下唯一性组合：
* 来源平台 + 原始记录 ID
* 文件哈希 + 行指纹
* 订单号 / 交易单号（若可信）
**B. 模糊去重（相似去重）**
当缺少唯一 ID 时，使用以下组合评分：
* 时间窗（如 ±2 分钟 / 可配置）
* 金额一致
* 交易方向一致
* 对手方相似
* 订单号相同或相近
* 来源平台关联规则命中
**C. 链路合并**
对疑似同一业务链路的记录进行聚合，形成主交易 + 附属事件：
* 主交易：消费/收入主体
* 附属事件：手续费、退款、优惠抵扣、汇率损耗等
#### 4）产品决策
初稿中提出“通过时间窗与金额双重校验进行链路合并”，这是合理起点，但不足以覆盖真实复杂场景。应升级为：
**“时间窗 + 金额 + 方向 + 订单号 + 对手方 + 来源规则”的多因子判定机制**。
---
### 模块 D：规则映射模块
负责将标准化交易映射到最终记账语义。
#### 1）规则映射内容
* 分类映射（餐饮、交通、工资、转账等）
* 账户映射（微信零钱、支付宝余额、建设银行卡等）
* 对手方映射（商户标准化）
* 标签映射（报销、家庭、订阅、投资）
* Firefly III 目标字段映射
#### 2）关键产品决策：规则应放在哪里？
针对初稿中的疑问：“本地进行数据规则映射，还是统一由 Data Importer 进行规则映射？”
**建议结论：**
> **以本地规则映射为主，Data Importer 规则映射为辅。**
#### 3）原因
1. **多源统一能力更强**：本地能先统一语义，再输出稳定格式。
2. **规则可沉淀**：用户长期积累的分类规则、商户别名、账户映射，不应绑定在某个导入器实例里。
3. **可解释性更高**：用户能在导入前看到“这条为何被分到餐饮/交通”。
4. **迁移性更好**：即使未来不使用 Data Importer，也能复用规则引擎。
#### 4）保留策略
仍保留 Data Importer 的简单映射能力，用于：
* 最后一层字段兼容
* 临时补充规则
* 与 Firefly III 导入格式保持兼容
---
### 模块 E：导入编排模块
负责将清洗后的数据导入 Firefly III 生态。
#### 1）导入方式
优先支持两种模式：
**模式 A：API 推送模式（优先）**
* 调用 Data Importer 或 Firefly III API
* 自动发起导入任务
* 可追踪返回结果
**模式 B：中间文件导出模式**
* 生成 Data Importer 可接收的标准 CSV/JSON
* 用户手动导入
* 适合 API 不稳定或权限受限场景
#### 2）导入前校验
* 必填字段校验
* 金额/时间格式校验
* 账户映射完整性校验
* 重复导入拦截
#### 3）导入后反馈
* 导入成功数量
* 失败数量
* 失败原因分类
* 可重试记录列表
---
### 模块 F：本地存储与审计模块
负责数据持久化与可追溯性。
#### 存储建议
使用 SQLite 存储以下核心数据：
1. 原始文件表
2. 原始解析记录表
3. 标准交易表
4. 去重关系表
5. 规则配置表
6. 导入任务表
7. 导入结果表
8. 操作日志表
#### 设计目标
* 支持重跑
* 支持审计
* 支持回溯某条交易来自哪个文件、哪个平台、经过哪些规则处理
---
## 7. 核心用户场景
### 场景 1：月度账单统一入账
用户每月从支付宝、微信、招商/建行导出账单，批量上传后，系统自动清洗并去重，用户确认后导入 Firefly III。
### 场景 2：跨平台订单去重
用户在京东下单，通过微信支付；京东账单与微信账单均包含该笔信息。系统识别为同一订单链路，仅保留主交易并记录来源关联。
### 场景 3：交易所流水整理
用户导入币安和 ByBit 资金流水，系统将充提币、手续费、现货买卖拆分为统一的账务事件，并映射到投资类账户与标签。
---
## 8. 功能需求清单
## 8.1 必须有（P0）
1. 文件上传与批量导入
2. 来源类型识别/选择
3. 多来源解析器框架
4. 统一交易模型
5. 本地 SQLite 存储
6. 去重机制
7. 链路合并机制
8. 规则映射（分类/账户/标签）
9. 导入预览
10. API / 文件两种导入方式
11. 导入日志与失败重试
## 8.2 应该有（P1）
1. 规则模板库
2. 商户别名归一化
3. 用户可配置时间窗与去重阈值
4. 导入批次管理
5. 手动合并/手动拆分疑似交易链路
## 8.3 可以有（P2）
1. 自动来源识别增强
2. 可视化规则调试
3. 简易统计报表（导入概览、分类占比）
4. 多账本导入支持
---
## 9. 非功能需求
### 9.1 性能
* 单次导入 1 万条记录应可完成解析与清洗
* 去重计算应可在合理时间内完成（建议 30 秒内完成主流程，视硬件而定）
### 9.2 安全
* 本地部署优先
* 敏感账单数据默认不上传云端
* API Token 加密存储
* 操作日志不泄露敏感字段
### 9.3 可维护性
* 解析器应插件化
* 规则引擎应可扩展
* 去重策略支持配置化
### 9.4 可追溯性
* 任一导入结果必须可追溯至原始文件与原始记录
* 任一规则命中必须可解释
---
## 10. 产品信息架构（建议）
### 一级模块
1. 导入中心
2. 数据清洗
3. 规则管理
4. 导入任务
5. 数据审计
6. 系统设置
### 关键页面
* 文件上传页
* 导入批次详情页
* 清洗结果预览页
* 重复记录处理页
* 规则配置页
* 导入结果页
* 错误记录页
---
## 11. 关键交互原则
1. **先预览，后导入**：任何清洗结果必须允许用户确认。
2. **规则可解释**：每条交易应展示命中的规则。
3. **重复可回溯**：被判定重复/合并的记录必须可查看判定依据。
4. **失败可重试**：导入失败不应要求整批重做。
---
## 12. 技术与架构建议（产品层约束）
### 12.1 架构建议
采用分层设计：
* **Adapter 层**：各平台账单解析器
* **Normalize 层**：字段标准化
* **Match 层**：去重与链路合并
* **Rule 层**：分类/账户/标签映射
* **Export 层**：导出至 Data Importer / Firefly III
* **Storage 层**：SQLite 持久化
### 12.2 设计原则
* 平台差异尽量收敛在 Adapter 层
* 统一模型要稳定，避免被单个平台格式污染
* 导入层与规则层解耦，便于未来替换 Firefly III
---
## 13. 版本规划
### V1（MVP）
* 支付宝 / 微信 / 2 家银行账单支持
* 文件导入、解析、标准化
* SQLite 持久化
* 基础去重
* 基础规则映射
* Data Importer 导入
### V1.5
* 美团 / 京东支持
* 链路合并增强
* 批次管理与失败重试
* 手工修正与确认流程
### V2
* 币安 / ByBit 流水适配增强
* 高级规则系统
* 可视化统计与导入质量分析
* 多账本/多环境支持
---
## 14. 风险与产品决策说明
### 风险 1：不同平台账单格式频繁变化
**应对：** 采用插件化解析器 + 版本化适配
### 风险 2：去重误判
**应对：**
* 采用“严格去重 + 模糊去重”分层策略
* 引入人工确认队列处理低置信度记录
### 风险 3：交易所流水语义复杂
**应对：**
V1 仅支持资金流水和基础现货场景，衍生品/复杂划转后续扩展
### 风险 4：过度依赖 Data Importer
**应对：**
将核心规则与标准化能力沉淀在本地，导入器仅作为输出目标之一
---
## 15. 最终产品结论（精炼版）
ProjectMoneyX 不是一个“简单导入工具”，而是一个面向 Firefly III 的**本地账单数据治理中台**。
它的核心价值在于：
* 汇聚多源账单
* 统一交易语义
* 去重并还原真实交易链路
* 在本地完成规则映射沉淀
* 稳定输出到 Firefly III / Data Importer
其中最关键的产品决策是：
> **规则映射应以本地为主，Data Importer 为辅；去重策略应从“时间窗 + 金额”升级为多因子判定；SQLite 不仅是缓存，更是清洗结果与审计链路的核心数据底座。**

19
17-ProjectMoneyX/2-概要详细设计/prd-origin.md Normal file
View File

@@ -0,0 +1,19 @@
# ProjectMoneyX
旨在为FireFlyIII+DataImporter提供自动化的数据清洗和导入服务
1. 最好能够通过API进行数据的导入到DataImporter
2. 本地多种来源的数据, 清洗为统一的数据格式,本地保存至sqlite数据库
3. 数据去重考虑, 本地的sqlite数据库应该存储清洗之后的数据, 通过时间窗与金额双重校验进行链路合并
4. (请考虑规则映射,本地进行数据规则映射,还是统一由DataImporter进行规则映射)
### 数据支持
1. 支付宝、微信等主流支付平台的账单导入
2. 建设银行、工商银行、中信银行、汇丰银行等主流银行账单
3. 支持美团、京东等生活服务平台的账单
4. 支持币安、ByBit等交易所的币币交易记录
### 参考项目:
1. [double-entry-generator](https://github.com/deb-sig/double-entry-generator)
2. [FireFlyIII](https://github.com/firefly-iii/firefly-iii)
3. [DataImporter](https://github.com/firefly-iii/data-importer)
4. [FireFlyIII-Docs](https://docs.firefly-iii.org/)

BIN
17-ProjectMoneyX/2-概要详细设计/微信支付账单流水文件(20250101-20250331)_20260202151120.xlsx Normal file
View File

Binary file not shown.

717
17-ProjectMoneyX/2-概要详细设计/支付宝交易明细(20250101-20251231).csv Normal file
View File

@@ -0,0 +1,717 @@
------------------------------------------------------------------------------------
<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϣ<EFBFBD><EFBFBD>
<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
֧<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD>18802881074
<EFBFBD><EFBFBD>ʼʱ<EFBFBD>䣺[2025-01-01 00:00:00] <20><>ֹʱ<D6B9>䣺[2025-12-31 23:59:59]
<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͣ<EFBFBD>[ȫ<><C8AB>]
<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʱ<EFBFBD>䣺[2026-02-02 15:22:48]
<EFBFBD><EFBFBD>692<EFBFBD>ʼ<EFBFBD>¼
<EFBFBD><EFBFBD><EFBFBD>룺11<EFBFBD><EFBFBD> 15310.80Ԫ
֧<EFBFBD><EFBFBD><EFBFBD><EFBFBD>273<EFBFBD><EFBFBD> 47685.82Ԫ
<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD>408<EFBFBD><EFBFBD> 35070.55Ԫ
<EFBFBD>ر<EFBFBD><EFBFBD><EFBFBD>ʾ<EFBFBD><EFBFBD>
1.<2E><><EFBFBD>ص<EFBFBD><D8B5><EFBFBD><EFBFBD>ݿɱ<DDBF><C9B1><EFBFBD>֧<EFBFBD><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ӧ֧<D3A6><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>룬<EFBFBD><EBA3AC>ϵͳԭ<CDB3><D4AD><EFBFBD><EFBFBD>ͨѶ<CDA8><D1B6><EFBFBD>ϵ<EFBFBD>ż<EFBFBD><C5BC><EFBFBD><EFBFBD><EFBFBD>ص<EFBFBD><D8B5>±<EFBFBD><C2B1>ص<EFBFBD><D8B5><EFBFBD>ʵ<EFBFBD>ʽ<EFBFBD><CABD>׽<EFBFBD><D7BD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʱ<EFBFBD><CAB1><EFBFBD><EFBFBD>ʵ<EFBFBD>ʽ<EFBFBD><CABD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϊ׼<CEAA><D7BC>
2.<2E><><EFBFBD>𽫱<EFBFBD><F0BDABB1>ص<EFBFBD><D8B5><EFBFBD>Ϊ<EFBFBD>տ<D5BF><EEB7BD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƾ<EFBFBD><C6BE>ʹ<EFBFBD>ã<EFBFBD><C3A3><EFBFBD><EFBFBD><EFBFBD>֤<EFBFBD>˻<EFBFBD>ʵ<EFBFBD>ʵ<EFBFBD><CAB5><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ٽ<EFBFBD><D9BD>з<EFBFBD><D0B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
3.֧<><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD><D6A7><EFBFBD>ȷ<EFBFBD><C8B7><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD><D6A7><EFBFBD><EFBFBD>ʽ<EFBFBD><CABD><EFBFBD>ܼȲ<DCBC><C8B2><EFBFBD>֧<EFBFBD><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ҳͬ<D2B2><CDAC><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>н<EFBFBD><D0BD>ף<EFBFBD><D7A3><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʹ<EFBFBD>ñ<EFBFBD><C3B1>ص<EFBFBD><D8B5><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ظ<EFBFBD><D8B8><EFBFBD><EFBFBD>ˣ<EFBFBD>
4.<2E><><EFBFBD>ص<EFBFBD><D8B5>羭<EFBFBD>κ<EFBFBD>Ϳ<EFBFBD>ġ<EFBFBD><C4A1><EFBFBD><EFBFBD>죬<EFBFBD><ECA3AC><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʧȥЧ<C8A5><D0A7><EFBFBD><EFBFBD>
5.<2E><><EFBFBD><EFBFBD><EFBFBD>˵<EFBFBD><CBB5>磺<EFBFBD><E7A3BA>ֵ<EFBFBD><D6B5><EFBFBD>֡<EFBFBD><D6A1>˻<EFBFBD>ת<EFBFBD><D7AA><EFBFBD><EFBFBD><EFBFBD>߸<EFBFBD><DFB8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD>Ȳ<EFBFBD><C8B2><EFBFBD><EFBFBD><EFBFBD>Ϊ<EFBFBD><CEAA><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϊ<EFBFBD><CEAA><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD>ࣻ
6.<2E><>ͳ<EFBFBD><CDB3><EFBFBD>߼<EFBFBD><DFBC><EFBFBD>ͬ<EFBFBD><CDAC><EFBFBD><EFBFBD>ϸ<EFBFBD><CFB8><EFBFBD><EFBFBD>ֱ<EFBFBD><D6B1><EFBFBD>ۼӺ󣬿<D3BA><F3A3ACBF>ܻ<EFBFBD><DCBB><EFBFBD><EFBFBD>·<EFBFBD>ͳ<EFBFBD>ƽ<EFBFBD><C6BD>һ<EEB2BB>£<EFBFBD><C2A3><EFBFBD><EFBFBD><EFBFBD>ʵ<EFBFBD>ʽ<EFBFBD><CABD>׽<EFBFBD><D7BD><EFBFBD>Ϊ׼<CEAA><D7BC>
7.<2E><>ֹ<EFBFBD><D6B9><EFBFBD><EFBFBD><EFBFBD>ص<EFBFBD><D8B5><EFBFBD><EFBFBD>ڷǷ<DAB7><C7B7><EFBFBD>;<EFBFBD><CDBE>
8.<2E><><EFBFBD><EFBFBD>ϸ<EFBFBD><CFB8>չʾ<D5B9><CABE>ǰ<EFBFBD>˵<EFBFBD><CBB5>еĽ<D0B5><C4BD>ף<EFBFBD><D7A3><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɾ<EFBFBD><C9BE><EFBFBD>ļ<EFBFBD>¼<EFBFBD><C2BC>
9.<2E><><EFBFBD><EFBFBD>ϸ<EFBFBD><CFB8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˶<EFBFBD><CBB6><EFBFBD>ʹ<EFBFBD>á<EFBFBD>
------------------------֧<><D6A7><EFBFBD><EFBFBD>֧<EFBFBD><D6A7><EFBFBD>Ƽ<EFBFBD><C6BC><EFBFBD><EFBFBD>޹<EFBFBD>˾ <20><><EFBFBD>ӿͻ<D3BF><CDBB>ص<EFBFBD>------------------------
<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʱ<EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׷<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׶Է<EFBFBD>,<EFBFBD>Է<EFBFBD><EFBFBD>˺<EFBFBD>,<EFBFBD><EFBFBD>Ʒ˵<EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>/֧,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>/<2F><><EFBFBD>ʽ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>״̬,<EFBFBD><EFBFBD><EFBFBD>׶<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>̼Ҷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>ע,
2025-12-31 15:23:29,ҽ<EFBFBD>ƽ<EFBFBD><EFBFBD><EFBFBD>,ŵ<EFBFBD><EFBFBD>ҽҩ,/,С<EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,229.43,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025123122001422381414647277 ,54201909036686325711511767165809224747777 ,,
2025-12-31 12:18:14,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ۻ<EFBFBD><EFBFBD><EFBFBD>,sm1***@163.com,<EFBFBD><EFBFBD><EFBFBD>ܻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>_<EFBFBD><EFBFBD><EFBFBD>¿<EFBFBD><EFBFBD><EFBFBD>500ml_<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʱ<EFBFBD><EFBFBD>:2025-12-31 12:17:42,֧<EFBFBD><EFBFBD>,4.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025123122001422381416747354 ,visionpayF57BB9C6233414B0866670B4 ,,
2025-12-31 10:54:16,ҽ<EFBFBD>ƽ<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҽԺ,/,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҽԺ,֧<EFBFBD><EFBFBD>,30.19,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025123122001422381414649487 ,822017092208872157041304100318000042512310744625 ,,
2025-12-31 09:53:57,ҽ<EFBFBD>ƽ<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҽԺ,/,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҽԺ,֧<EFBFBD><EFBFBD>,324.47,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025123122001422381416098850 ,122017092208872157041304100318000072512310739415 ,,
2025-12-31 03:21:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251231394401585381 , ,,
2025-12-30 18:54:06,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,һ<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD>(<28><><EFBFBD><EFBFBD>Ƽ),523***@qq.com,ת<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,2000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251230200040011100380015625389 , ,,
2025-12-30 14:03:27,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,173******20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,2000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251230200040011100150022443155 , ,,
2025-12-30 03:04:51,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.31,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251230385911475381 , ,,
2025-12-29 20:43:37,<EFBFBD>ҾӼ<EFBFBD>װ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʒ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ݣ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ι<EFBFBD>˾,/,<EFBFBD><EFBFBD>ά<EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.10,<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122922001422381409339128 ,21P2088721085226061W03_ZENNa251229204329 ,,
2025-12-29 09:35:35,<EFBFBD>ҾӼ<EFBFBD>װ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,lh9***@163.com,<EFBFBD><EFBFBD><EFBFBD>Ӳ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ּ<EFBFBD>ͷ<EFBFBD><EFBFBD>ͷ<EFBFBD><EFBFBD><EFBFBD>ӵ<EFBFBD><EFBFBD>ӳ<EFBFBD>ר<EFBFBD><EFBFBD><EFBFBD>ֹ<EFBFBD><EFBFBD>߾<EFBFBD><EFBFBD>ܷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ά<EFBFBD><EFBFBD>ʵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,2.90,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122922001122381402234167 ,T200P4975554097188367849 ,,
2025-12-29 09:35:35,<EFBFBD>ҾӼ<EFBFBD>װ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,186***@163.com,iFixes-iCF6<46>ֻ<EFBFBD>ά<EFBFBD><CEAC><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ȳ<EFBFBD><C8B2><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֻ<EFBFBD><D6BB><EFBFBD>Ļ<EFBFBD><C4BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>𿪲<EFBFBD><F0BFAAB2><EFBFBD> <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,126.91,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049)&<26>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122922001122381403067739 ,T200P4975554097179367849 ,,
2025-12-29 09:35:35,<EFBFBD>ҾӼ<EFBFBD>װ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**Ӫ,wen***@163.com,<EFBFBD>ֻ<EFBFBD>ר<EFBFBD>ò<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>С<EFBFBD><EFBFBD>ά<EFBFBD><EFBFBD><EFBFBD><EFBFBD>˿<EFBFBD><EFBFBD><EFBFBD><EFBFBD>װ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƻ<EFBFBD><EFBFBD>iPhone<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,14.79,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049)&<26>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122922001122381403632712 ,T200P4975554097185367849 ,,
2025-12-29 09:35:35,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,tb**4,189******32,ԭ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ˮ<EFBFBD><EFBFBD>iPhone <20><><EFBFBD><EFBFBD>ƻ<EFBFBD><C6BB>X/Xr/11/12/13/14 Pro Max <20><>Ļ<EFBFBD>ܷ⽺ <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,12.59,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049)&<26>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122922001122381404571152 ,T200P4975554097182367849 ,,
2025-12-29 03:56:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251229382170809381 , ,,
2025-12-28 17:28:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>̷<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>̷<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,49.00,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122822001422381400643272 ,2620161017022043782025122800112000100283133324 ,,
2025-12-28 17:19:53,ҽ<EFBFBD>ƽ<EFBFBD><EFBFBD><EFBFBD>,ŵ<EFBFBD><EFBFBD>ҽҩ,/,С<EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,23.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122822001422381400655692 ,92201909036686325713511766913586906226523 ,,
2025-12-28 10:04:40,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD>ݳ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>¼<EFBFBD>ʳƷ<EFBFBD><EFBFBD>(<28><><EFBFBD>幤<EFBFBD>̻<EFBFBD>),֧<EFBFBD><EFBFBD>,2.90,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122822001422381400702300 ,36106600004857000220251228MMhlshuk ,,
2025-12-28 03:20:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251228375131448381 , ,,
2025-12-27 18:44:22,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>յ<EFBFBD>,fpp***@163.com,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,17.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122722001422381400354038 ,17668322619112300022388 ,,
2025-12-27 02:42:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251227368730128381 , ,,
2025-12-26 03:45:41,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.36,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251226362901285381 , ,,
2025-12-25 18:31:28,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,pin***@service.alibaba.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ի<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,0.10,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122522001122381448883487 ,13180600725122588190968809923 ,,
2025-12-25 18:31:28,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѡ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ţ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>԰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,11.49,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122522001122381449569644 ,13180600725122588190967809923 ,,
2025-12-25 13:40:31,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ž<EFBFBD>ͨ<EFBFBD><EFBFBD>˾,icb***@126.com,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122522001422381443926599 ,041347890001000542512250121663 ,,
2025-12-25 12:51:59,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD><EFBFBD>ɭ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,ecp***@bj.lawson-china.com,LAWSON<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ǵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,21.30,<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122522001422381443744478 ,712031479688 ,,
2025-12-25 03:31:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251225356323552381 , ,,
2025-12-24 10:37:15,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,3.25,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025122400003001380069515828 , ,,
2025-12-24 03:10:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.36,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251224349461635381 , ,,
2025-12-23 18:33:37,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,15.39,<EFBFBD><EFBFBD><EFBFBD>&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122322001422381436957517 ,17664860174112300022388 ,,
2025-12-23 18:24:48,<EFBFBD>˿<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,njq***@163.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD>Żݼۡ<DDBC><DBA1><EFBFBD>Я<EFBFBD><D0AF>֧<EFBFBD><D6A7><EFBFBD><EFBFBD>ʾ<EFBFBD><CABE><EFBFBD>ʼDZ<CABC><C7B1><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>չswitch<63><68><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ת<EFBFBD><D7AA><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ߵ<EFBFBD><DFB5><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,30.16,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025122322001122381439744858_4963878291803367849 ,T200P4963878291803367849 ,,
2025-12-23 18:24:35,<EFBFBD>˿<EFBFBD>,cu**<2A><>,cuk***@cuktech.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD>Żݼۡ<DDBC><DBA1><EFBFBD>iPhone17<31><37><EFBFBD>¡<EFBFBD>CUKTECH<43><48>̬<EFBFBD>ƴ<EFBFBD><C6B4><EFBFBD><EFBFBD><EFBFBD>֯<EFBFBD><D6AF><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Type-c<><63><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƻ<EFBFBD><C6BB>iPhone17Pro <20>ȶ<EFBFBD><C8B6><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,17.15,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025122322001122381436088949_4963878291805367849 ,T200P4963878291804367849 ,,
2025-12-23 18:23:43,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,cu**<2A><>,cuk***@cuktech.com,<EFBFBD><EFBFBD>iPhone17<EFBFBD>»<EFBFBD><EFBFBD><EFBFBD>ѡ<EFBFBD><EFBFBD>CUKTECH<EFBFBD><EFBFBD>̬<EFBFBD><EFBFBD>10<EFBFBD>ų<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ܳ<EFBFBD>ultra<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>س<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>17ProMax<EFBFBD><EFBFBD><EFBFBD><EFBFBD>120W<EFBFBD><EFBFBD> <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,121.23,<EFBFBD><EFBFBD><EFBFBD>&<26>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122322001122381435665575 ,T200P4963878291807367849 ,,
2025-12-23 18:23:43,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,cu**<2A><>,cuk***@cuktech.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD><EFBFBD><EFBFBD>iPhone17<EFBFBD><EFBFBD><EFBFBD>¡<EFBFBD>CUKTECH<EFBFBD><EFBFBD>̬<EFBFBD>ƴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֯<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Type-c<><63><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƻ<EFBFBD><C6BB>iPhone17Pro <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,17.15,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025122322001122381436088949 ,T200P4963878291804367849 ,,
2025-12-23 18:23:43,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,njq***@163.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD><EFBFBD><EFBFBD>Я<EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʾ<EFBFBD><EFBFBD><EFBFBD>ʼDZ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>չswitch<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ת<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ߵ<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,30.16,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025122322001122381439744858 ,T200P4963878291803367849 ,,
2025-12-23 03:24:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251223343356797381 , ,,
2025-12-22 03:33:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.28,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251222336941406381 , ,,
2025-12-21 11:08:04,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD>˹͡<EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݶ<EFBFBD><DDB6><EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,21.40,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025122122001122381420688816 ,13110600725122158123868809923 ,,
2025-12-21 03:18:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.28,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251221330257238381 , ,,
2025-12-20 03:46:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251220323930866381 , ,,
2025-12-19 03:27:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251219317192067381 , ,,
2025-12-18 16:25:06,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,331***@qq.com,ţ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ר<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ϴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƭģ<EFBFBD><EFBFBD>Բ<EFBFBD><EFBFBD><EFBFBD>μӺ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.14,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8050)&<26><>ͨ<EFBFBD><CDA8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121822001122381410132890 ,T200P4952909919714367849 ,,
2025-12-18 16:23:31,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**˾,c2m***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƭ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƭ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ţ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,26.87,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121822001122381407912458 ,T200P4953202488331367849 ,,
2025-12-18 02:42:48,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251218305981168381 , ,,
2025-12-17 03:28:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.34,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251217305329068381 , ,,
2025-12-16 22:45:41,ҽ<EFBFBD>ƽ<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ĵ<EFBFBD><EFBFBD><EFBFBD>ѧ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҽԺ,/,ҽ<EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD>(<28><><EFBFBD><EFBFBD><EFBFBD>Է<EFBFBD>),֧<EFBFBD><EFBFBD>,0.00,,֧<EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,20251216223820293264 ,0202512162245400689 ,,
2025-12-16 03:26:15,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.40,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251216398646960381 , ,,
2025-12-15 02:43:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251215387752822381 , ,,
2025-12-14 11:54:45,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>ϳɶ<EFBFBD>ð<EFBFBD><EFBFBD>Ѽ(<28><>ʳ<EFBFBD>ǵ<EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,12.70,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7571)&ƽ<><C6BD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD>֧<EFBFBD><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121422001122381452508741 ,13110600725121401692891809923 ,,
2025-12-14 03:13:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251214385758976381 , ,,
2025-12-13 17:16:17,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,pin***@service.alibaba.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ի<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,0.09,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7571)&<26>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121322001122381445546677 ,13170600725121305726226809923 ,,
2025-12-13 17:16:17,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD>˹͡<EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ݶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,19.53,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7571)&<26>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121322001122381446540391 ,13170600725121305726225809923 ,,
2025-12-13 12:10:27,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD>꣩<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.50,Mastercard(7567)&<26><><EFBFBD><EFBFBD>֧<EFBFBD><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȯ,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121322001422381446137885 ,161266000048250000705832856804251213 ,,
2025-12-13 03:27:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.39,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251213379575231381 , ,,
2025-12-12 03:31:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251212373708843381 , ,,
2025-12-11 18:10:47,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,18.50,Mastercard(7567)&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121122001422381438348818 ,17654478471112300022388 ,,
2025-12-11 12:12:07,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>籥<EFBFBD><EFBFBD>¿<EFBFBD><EFBFBD>,/,<EFBFBD>籥<EFBFBD><EFBFBD>¿<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121122001422381434025652 ,20P2088521461085192W03_2025121140000009995125500200008 ,,
2025-12-11 03:09:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.45,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251211367336130381 , ,,
2025-12-10 18:12:22,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,18.50,Mastercard(7567)&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121022001422381432588043 ,17653615420112300022388 ,,
2025-12-10 12:35:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ݳǵ꣩,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>909700207282780640,֧<EFBFBD><EFBFBD>,107.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025121023001422381431996011 ,4620180330024764010461368606249654884309045 ,,
2025-12-10 02:43:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.39,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251210360943162381 , ,,
2025-12-09 18:28:00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120922001422381427570425 ,17652760805112300022388 ,,
2025-12-09 18:25:51,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.50,Mastercard(7567)&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120922001422381428426849 ,17652759511112300022388 ,,
2025-12-09 03:15:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.37,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251209354791074381 , ,,
2025-12-08 18:24:38,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,24.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120822001422381424047124 ,17651894783112300022388 ,,
2025-12-08 03:19:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.26,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251208348041260381 , ,,
2025-12-07 20:53:53,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>926625<EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>926625<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.70,Mastercard(7567)&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120722001422381416172487 ,091266000048180000144445902722125120720535343868 ,,
2025-12-07 03:25:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.26,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251207337946641381 , ,,
2025-12-06 18:42:36,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120622001122381414440471 ,13180600725120608925039809923 ,,
2025-12-06 03:18:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.37,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251206336007386381 , ,,
2025-12-05 12:30:12,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD>꣩<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,18.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120522001422381403216231 ,361266000048250000705660664362251205 ,,
2025-12-05 03:34:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.26,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251205330117052381 , ,,
2025-12-04 18:14:20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɨ<EFBFBD><EFBFBD><EFBFBD>㵥<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,176******32,<EFBFBD><EFBFBD>Ӫ<EFBFBD>뽻<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,19.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025120422001422381402074365 ,17648432606112300022388 ,,
2025-12-04 03:08:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.46,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251204322257518381 , ,,
2025-12-03 02:50:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.26,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251203315921033381 , ,,
2025-12-03 00:54:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.10,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251203019130101000380080263813 ,20251203009130501000380068762173 ,,
2025-12-02 11:46:05,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD>Ա<EFBFBD><EFBFBD>Ű<EFBFBD>ũ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֽ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,0.10,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251202020070011530380099063337 ,FP301_7731034505290370 ,,
2025-12-02 02:42:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.12.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.40,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251202309981239381 , ,,
2025-12-01 03:18:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.27,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251201399424385381 , ,,
2025-11-30 02:45:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.27,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251130395423120381 , ,,
2025-11-29 03:04:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251129391526990381 , ,,
2025-11-28 02:49:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.28,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251128383717400381 , ,,
2025-11-27 03:23:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.40,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251127376195372381 , ,,
2025-11-26 08:59:43,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***8,186******04,wps<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ա4<EFBFBD>꿨WPS<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Լ<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,233.41,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025112622001122381416406740 ,T200P4905702325718367849 ,,
2025-11-26 02:41:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251126368342303381 , ,,
2025-11-25 03:11:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.36,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251125362373331381 , ,,
2025-11-24 03:05:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.26,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251124352826609381 , ,,
2025-11-23 10:56:49,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD>˹͡<EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ݶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,21.70,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025112322001122381454281008 ,13100600725112393832796809923 ,,
2025-11-23 10:56:49,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȥ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>е<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,7.60,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025112322001122381456680562 ,13100600725112393832797809923 ,,
2025-11-23 03:05:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.26,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251123343532227381 , ,,
2025-11-22 11:10:02,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,pin***@service.alibaba.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ի<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,0.10,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025112222001122381450926996 ,13110600725112204792227809923 ,,
2025-11-22 11:10:02,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>跹<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƥ<EFBFBD><EFBFBD><EFBFBD>׷<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,15.38,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025112222001122381451157347 ,13110600725112204792226809923 ,,
2025-11-22 03:05:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.34,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251122341284188381 , ,,
2025-11-21 02:33:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.37,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251121330455266381 , ,,
2025-11-20 20:20:20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.90,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025112022001122381437258390 ,13200600725112074416431809923 ,,
2025-11-20 03:21:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.27,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251120323591502381 , ,,
2025-11-19 03:38:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.47,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251119322435717381 , ,,
2025-11-18 11:09:49,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.20,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025111822001122381422440272 ,13110600725111850434483809923 ,,
2025-11-18 02:57:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.38,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251118314974430381 , ,,
2025-11-17 03:09:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.28,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251117302968810381 , ,,
2025-11-16 03:31:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.28,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251116300094016381 , ,,
2025-11-15 17:41:13,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.40,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025111522001122381407472253 ,13170600725111507286877809923 ,,
2025-11-15 02:39:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.40,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251115395272527381 , ,,
2025-11-14 03:13:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251114388354289381 , ,,
2025-11-13 03:06:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251113376570250381 , ,,
2025-11-12 02:42:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.37,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251112375168063381 , ,,
2025-11-11 19:37:38,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,zxp***@meituan.com,<EFBFBD><EFBFBD><EFBFBD>Ŷ<EFBFBD><EFBFBD><EFBFBD>-25111111100300001307570380598513,֧<EFBFBD><EFBFBD>,164.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025111122001422381440160624 ,20251111193728U94546423358573308 ,,
2025-11-11 03:18:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.37,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251111362145355381 , ,,
2025-11-10 22:52:56,<EFBFBD>˿<EFBFBD>,ac**<2A><>,wan***@acasis.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD>Żݼۡ<DDBC><DBA1><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˹macmini<6E><69>չ<EFBFBD><D5B9>M2<4D><32>̬Ӳ<CCAC><D3B2>40Gbps<70><73><EFBFBD><EFBFBD><EFBFBD><EFBFBD>չ<EFBFBD><D5B9>usb<73><62><EFBFBD>ӿڵ<D3BF><DAB5><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,412.32,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(7049)&<26>Ż<EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025111022001122381434028780_4872624230728367849 ,T200P4872624230728367849 ,,
2025-11-10 22:49:06,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ac**<2A><>,wan***@acasis.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˹macmini<EFBFBD><EFBFBD>չ<EFBFBD><EFBFBD>M2<EFBFBD><EFBFBD>̬Ӳ<EFBFBD><EFBFBD>40Gbps<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>չ<EFBFBD><EFBFBD>usb<EFBFBD><EFBFBD><EFBFBD>ӿڵ<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,412.32,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(7049) 6<><36>&<26><><EFBFBD><EFBFBD><EFBFBD>ۿ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025111022001122381434028780 ,T200P4872624230728367849 ,,
2025-11-10 22:45:39,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ac**<2A><>,wan***@acasis.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˹macmini<EFBFBD><EFBFBD>չ<EFBFBD><EFBFBD>M2<EFBFBD><EFBFBD>̬Ӳ<EFBFBD><EFBFBD>40Gbps<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>չ<EFBFBD><EFBFBD>usb<EFBFBD><EFBFBD><EFBFBD>ӿڵ<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,449.10,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025111022001122381436550331 ,T200P4872983148238367849 ,,
2025-11-10 03:26:13,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251110356730844381 , ,,
2025-11-09 17:07:20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,15.90,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110922001122381430346936 ,13170600725110948174744809923 ,,
2025-11-09 11:14:35,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,Ҽ¯<EFBFBD><EFBFBD>¯<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,7.32,<EFBFBD>ʴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(8058)&<26>ʴ<EFBFBD><CAB4><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110922001122381425293395 ,13110600725110917875770809923 ,,
2025-11-09 02:39:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251109350024316381 , ,,
2025-11-08 17:25:46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD>˹͡<EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ݶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,14.90,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110822001122381421060475 ,13170600725110806755069809923 ,,
2025-11-08 17:25:46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,pin***@service.alibaba.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,0.10,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110822001122381422389675 ,13170600725110806755070809923 ,,
2025-11-08 13:47:24,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Զ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>-2025<32><35>11<31><31><EFBFBD>˵<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,114.80,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025110829020999380178839157 , ,,
2025-11-08 11:11:56,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.08,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110822001122381421865127 ,13110600725110887801616809923 ,,
2025-11-08 03:54:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.40,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251108348091974381 , ,,
2025-11-07 21:23:47,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD>ƶ<EFBFBD>,z97***@service.aliyun.com,Ϊ19801981923<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,100.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110722001422381411992435 ,2025110700003100003859878386 ,,
2025-11-07 03:16:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251107336132155381 , ,,
2025-11-06 14:35:45,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,13.23,<EFBFBD>ʴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(8058)&<26>ʴ<EFBFBD><CAB4><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025110600003001380064190393 , ,,
2025-11-06 11:11:06,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.08,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110622001122381401444190 ,13110600725110679684448809923 ,,
2025-11-06 02:35:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251106329424173381 , ,,
2025-11-05 03:48:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251105322918113381 , ,,
2025-11-04 12:08:47,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>**,tmc***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD>ӯͨRX9070XT16Gӣͫˮ<EFBFBD><EFBFBD>AtlantisOC<EFBFBD><EFBFBD>Ƶ<EFBFBD><EFBFBD>7<EFBFBD>ȹ<EFBFBD>ARGB<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>Կ<EFBFBD>,֧<EFBFBD><EFBFBD>,3179.55,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8676)&<26>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110422001122381448541895 ,T200P4857594229507367849 ,,
2025-11-04 12:06:59,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD>è<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,tmc***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD>Կ<EFBFBD>1088Ԫ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӿ<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,1086.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9080)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110422001122381449774819 ,T200P4857663240208367849 ,,
2025-11-04 03:28:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.50,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251104315296861381 , ,,
2025-11-03 23:07:08,<EFBFBD>˿<EFBFBD>,as**<2A><>,nby***@126.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD>Żݼۡ<DDBC>amd 9700x/7800x3d/9800x3d<33><64>u<EFBFBD>˶x870/b850<35><30>ѩ<EFBFBD><D1A9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>cpu,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2668.99,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(7049)&<26>Ż<EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025110322001122381450503122_4856302441057367849 ,T200P4856302441057367849 ,,
2025-11-03 19:03:30,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,as**<2A><>,nby***@126.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD>amd 9700x/7800x3d/9800x3d<33><64>u<EFBFBD>˶x870/b850<35><30>ѩ<EFBFBD><D1A9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>cpu,֧<EFBFBD><EFBFBD>,2668.99,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(7049) 12<31><32>&<26><><EFBFBD><EFBFBD><EFBFBD>ۿ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025110322001122381450503122 ,T200P4856302441057367849 ,,
2025-11-03 19:02:07,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,as**<2A><>,nby***@126.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD>amd 9700x/7800x3d/9800x3d<33><64>u<EFBFBD>˶x870/b850<35><30>ѩ<EFBFBD><D1A9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>cpu,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2809.46,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025110322001122381451742666 ,T200P4855996622357367849 ,,
2025-11-03 18:59:41,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,as**<2A><>,nby***@126.com,<EFBFBD><EFBFBD><EFBFBD>Żݼۡ<EFBFBD>amd 9700x/7800x3d/9800x3d<33><64>u<EFBFBD>˶x870/b850<35><30>ѩ<EFBFBD><D1A9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>cpu,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2809.46,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025110322001122381448618984 ,T200P4856375952362367849 ,,
2025-11-03 02:36:48,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251103314420750381 , ,,
2025-11-02 11:09:41,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,it_***@meituan.com,<EFBFBD><EFBFBD>˹͡<EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݶ<EFBFBD><DDB6><EFBFBD>)-<2D><><EFBFBD><EFBFBD>App-25110211100300001306095593206513,֧<EFBFBD><EFBFBD>,31.30,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110222001422381438405632 ,20251102110936U01537119355913714 ,,
2025-11-02 03:04:15,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.11.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251102307891869381 , ,,
2025-11-01 23:05:04,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,dzq***@chinatelecom-ec.com.cn,Ϊ17329730418<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,50.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110123001422381433819826 ,2025110100003100003859192912 ,,
2025-11-01 11:04:26,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>ϵ»<EFBFBD>լ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD>ݵ<EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,44.90,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025110122001122381428541138 ,13110600725110120727517809923 ,,
2025-11-01 03:22:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.31-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.33,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251101301347734381 , ,,
2025-10-31 08:35:00,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,90.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(9683)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025103100003001380063090623 ,1300787791955 ,,
2025-10-31 02:40:36,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251031394273762381 , ,,
2025-10-30 11:05:03,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,7.90,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9924)&<26>й<EFBFBD><D0B9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025103022001122381416673112 ,13110600725103050251102809923 ,,
2025-10-30 03:26:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.30,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251030387864269381 , ,,
2025-10-29 03:10:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.42,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251029375835438381 , ,,
2025-10-28 11:23:07,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>跹<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƥ<EFBFBD><EFBFBD><EFBFBD>׷<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,11.30,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102822001122381403783940 ,13110600725102877580724809923 ,,
2025-10-28 09:24:14,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,1.31,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025102800003001380062855089 , ,,
2025-10-28 03:28:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.39,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251028374004236381 , ,,
2025-10-27 16:08:34,<EFBFBD>˿<EFBFBD>,tb**8,mfx***@163.com,<EFBFBD>˿<EFBFBD>-ԭװ<D4AD><D7B0>Ʒ<EFBFBD>û<EFBFBD><C3BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>N<EFBFBD><4E><EFBFBD><EFBFBD><EFBFBD>仪ǿ<E4BBAA><C7BF><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>1571AM<41><4D><EFBFBD><EFBFBD>air4<72><34><EFBFBD><EFBFBD>pro2 <20>ȶ<EFBFBD><C8B6><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,258.83,<EFBFBD><EFBFBD><EFBFBD>·<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025102122001122381420376235_4824071642359367849 ,T200P4824071642358367849 ,,
2025-10-27 03:29:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251027362723067381 , ,,
2025-10-26 13:36:35,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,z97***@service.aliyun.com,Ϊ19267221762<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,200.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102622001422381447777457 ,2025102600003100003858660078 ,,
2025-10-26 13:34:19,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,z97***@service.aliyun.com,Ϊ19267221762<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,100.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102622001422381453957081 ,2025102600003100003858664261 ,,
2025-10-26 11:03:18,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,14.50,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102622001122381453375880 ,13110600725102677591029809923 ,,
2025-10-26 02:55:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251026355808285381 , ,,
2025-10-25 11:41:03,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,14.50,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102522001122381444160600 ,13110600725102593152689809923 ,,
2025-10-25 03:11:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251025349174034381 , ,,
2025-10-24 14:21:00,<EFBFBD>˿<EFBFBD>,tb**8,158******61,<EFBFBD>˿<EFBFBD>-<2D><>ʪ<EFBFBD>ȼ<EFBFBD><C8BC><EFBFBD><EFBFBD>ڼ<EFBFBD><DABC>þ<EFBFBD>׼<EFBFBD>߾<EFBFBD><DFBE>ȵ<EFBFBD><C8B5><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Աڹ<D4B1>ʽӤ<CABD><D3A4><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʪ<EFBFBD>¶ȱ<C2B6>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,3.80,Mastercard(7567),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025102422001122381438633442_4832446968600367849 ,T200P4832446968600367849 ,,
2025-10-24 14:20:19,<EFBFBD>ҾӼ<EFBFBD>װ,tb**8,158******61,<EFBFBD><EFBFBD>ʪ<EFBFBD>ȼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ڼ<EFBFBD><EFBFBD>þ<EFBFBD>׼<EFBFBD>߾<EFBFBD><EFBFBD>ȵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Աڹ<EFBFBD>ʽӤ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʪ<EFBFBD>¶ȱ<EFBFBD>,֧<EFBFBD><EFBFBD>,3.80,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025102422001122381438633442 ,T200P4832446968600367849 ,,
2025-10-24 14:20:19,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,tb**8,mfx***@163.com,ԭװ<EFBFBD><EFBFBD>Ʒ<EFBFBD>û<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>N<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>仪ǿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>1571AM<EFBFBD><EFBFBD><EFBFBD><EFBFBD>air4<EFBFBD><EFBFBD><EFBFBD><EFBFBD>pro2 <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,193.20,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102422001122381440910085 ,T200P4832446968596367849 ,,
2025-10-24 03:16:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251024342331988381 , ,,
2025-10-23 03:06:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251023340337743381 , ,,
2025-10-22 11:13:44,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,14.40,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102222001122381425233242 ,13110600725102236962908809923 ,,
2025-10-22 02:58:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.36,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251022333867010381 , ,,
2025-10-21 11:14:04,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,tb**8,mfx***@163.com,ԭװ<EFBFBD><EFBFBD>Ʒ<EFBFBD>û<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>N<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>仪ǿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>1571AM<EFBFBD><EFBFBD><EFBFBD><EFBFBD>air4<EFBFBD><EFBFBD><EFBFBD><EFBFBD>pro2 <20>ȶ<EFBFBD><C8B6><EFBFBD>,֧<EFBFBD><EFBFBD>,258.83,<EFBFBD><EFBFBD><EFBFBD>·<EFBFBD><EFBFBD><EFBFBD>(3<><33>),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025102122001122381420376235 ,T200P4824071642358367849 ,,
2025-10-21 11:11:04,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,Ҽ¯<EFBFBD><EFBFBD>¯<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,8.29,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102122001122381418859426 ,13110600725102178897340809923 ,,
2025-10-21 02:41:18,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.47,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251021321395527381 , ,,
2025-10-20 11:09:04,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʿ<EFBFBD><EFBFBD>ȫ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݵ<EFBFBD><DDB5><EFBFBD>·<EFBFBD><C2B7>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.10,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025102022001122381412627729 ,13110600725102070779003809923 ,,
2025-10-20 03:22:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251020320495597381 , ,,
2025-10-19 17:00:43,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̡<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><><EFBFBD>й㳡<D0B9><E3B3A1>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,15.20,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101922001122381408876241 ,13170600725101982374461809923 ,,
2025-10-19 11:18:59,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,8.98,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101922001122381405850597 ,13110600725101996577750809923 ,,
2025-10-19 03:03:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251019313664191381 , ,,
2025-10-18 14:45:21,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ele***@service.aliyun.com,ʰ<EFBFBD>ݿ<EFBFBD>24H<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ı<EFBFBD><C4B1>ֵ<EFBFBD>),֧<EFBFBD><EFBFBD>,12.01,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101822001122381459190594 ,13140600725101820240590809923 ,,
2025-10-18 03:04:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.29,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251018306928696381 , ,,
2025-10-17 18:03:18,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,hxj***@aliyun.com,<EFBFBD>Զ<EFBFBD><EFBFBD>ϵ<EFBFBD> <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֵ綯<D6B5><E7B6AF><EFBFBD>綯<EFBFBD><E7B6AF><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>48V60V72V<32><56><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>糵ͨ<E7B3B5><CDA8>,֧<EFBFBD><EFBFBD>,14.29,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101722001122381454077495 ,T200P4815036612399367849 ,,
2025-10-17 03:29:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.36,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251017300041361381 , ,,
2025-10-16 03:11:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.33,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251016393782017381 , ,,
2025-10-15 11:26:04,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,Ҽ¯<EFBFBD><EFBFBD>¯<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,5.32,<EFBFBD>ʴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(8058)&<26>ʴ<EFBFBD><CAB4><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101522001122381441017813 ,13110600725101540808669809923 ,,
2025-10-15 11:23:26,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**P,p-s***@service.taobao.com,88VIP<EFBFBD><EFBFBD><EFBFBD><EFBFBD>꿨,֧<EFBFBD><EFBFBD>,88.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101522001122381441531490 ,T200P4809083223258367849 ,,
2025-10-15 03:11:45,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251015386769605381 , ,,
2025-10-14 18:24:29,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ele***@service.aliyun.com,ʰ<EFBFBD>ݿ<EFBFBD>24H<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ı<EFBFBD><C4B1>ֵ<EFBFBD>),֧<EFBFBD><EFBFBD>,12.51,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101422001122381431329168 ,13180600725101463801312809923 ,,
2025-10-14 02:50:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.31,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251014379863715381 , ,,
2025-10-13 02:58:14,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.31,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251013373415404381 , ,,
2025-10-12 17:12:29,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,8.88,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101222001122381420808770 ,13170600725101229967579809923 ,,
2025-10-12 17:10:44,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><><EFBFBD>й㳡<D0B9><E3B3A1>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,9.20,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101222001122381420939593 ,13170600725101202462584809923 ,,
2025-10-12 14:57:00,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,38.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101222001422381422375834 ,M2025101290390194 ,,
2025-10-12 03:26:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.31,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251012362055809381 , ,,
2025-10-11 02:50:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.32,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251011356131235381 , ,,
2025-10-10 22:09:31,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ϻ<EFBFBD>**<2A><>,asl***@service.taobao.com,<EFBFBD><EFBFBD>Ʊ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{8706255300978|1_2_2025000452573738738},֧<EFBFBD><EFBFBD>,899.51,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025101022001122381410076228 ,T1400P4799769050580367849 ,,
2025-10-10 03:02:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251010348031380381 , ,,
2025-10-09 04:16:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251009347928864381 , ,,
2025-10-08 13:55:58,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Զ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>-2025<32><35>10<31><30><EFBFBD>˵<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,118.46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025100829020999380190836580 , ,,
2025-10-08 02:21:45,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251008335245733381 , ,,
2025-10-08 01:28:54,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,10000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251008019130101000380031629339 ,20251008009130501000380028951419 ,,
2025-10-07 17:07:36,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,һ<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD>,523***@qq.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,10000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251007200040011100660097997901 , ,,
2025-10-07 03:47:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251007333762924381 , ,,
2025-10-06 20:07:13,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ٵ<EFBFBD>(<28>û<EFBFBD><C3BB><EFBFBD><EFBFBD><EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,11.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100622001122381442676080 ,13200600725100634999189809923 ,,
2025-10-06 19:34:35,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ͯ***<2A><>,176******46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ת<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100622001322381442411685 ,T3900P4790789138737367849 ,,
2025-10-06 16:23:59,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ι<EFBFBD>˾,156***@qq.com,534·-<2D><><EFBFBD><EFBFBD>00048092-<2D>˳<EFBFBD>ʱ<EFBFBD><CAB1>2025-10-06 16:23:58,֧<EFBFBD><EFBFBD>,2.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100622001422381439600261 ,20251006162358000976918352278619 ,,
2025-10-06 16:23:54,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ι<EFBFBD>˾,156***@qq.com,534·-<2D><><EFBFBD><EFBFBD>00048092-<2D>˳<EFBFBD>ʱ<EFBFBD><CAB1>2025-10-06 16:23:53,֧<EFBFBD><EFBFBD>,2.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100622001422381439639071 ,20251006162353000819156361506463 ,,
2025-10-06 14:49:09,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ι<EFBFBD>˾,156***@qq.com,13·-<2D><><EFBFBD><EFBFBD>00058112-<2D>˳<EFBFBD>ʱ<EFBFBD><CAB1>2025-10-06 14:49:08,֧<EFBFBD><EFBFBD>,2.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100622001422381437706520 ,20251006144908000999975505079807 ,,
2025-10-06 14:49:05,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ι<EFBFBD>˾,156***@qq.com,13·-<2D><><EFBFBD><EFBFBD>00058112-<2D>˳<EFBFBD>ʱ<EFBFBD><CAB1>2025-10-06 14:49:04,֧<EFBFBD><EFBFBD>,2.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100622001422381441377049 ,20251006144904000541184004915602 ,,
2025-10-06 03:13:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251006322636270381 , ,,
2025-10-05 17:35:23,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,һ<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD>(<28><><EFBFBD><EFBFBD>Ƽ),523***@qq.com,ת<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10000.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251005200040011100380070264908 , ,,
2025-10-05 04:10:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251005321378546381 , ,,
2025-10-04 09:45:22,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,19.63,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025100400003001380060301738 , ,,
2025-10-04 04:19:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251004314999079381 , ,,
2025-10-03 03:34:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251003307689168381 , ,,
2025-10-02 16:56:31,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,414.66,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025100200003001380060048995 , ,,
2025-10-02 04:55:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.10.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251002302701924381 , ,,
2025-10-01 11:34:17,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ,syc***@163.com,<EFBFBD>˳<EFBFBD>ʱ<EFBFBD>䣺2025-10-01 11:34:14,֧<EFBFBD><EFBFBD>,2.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100122001422381404238545 ,0016_86012179_20251001113414_65773 ,,
2025-10-01 09:54:33,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ,syc***@163.com,<EFBFBD>˳<EFBFBD>ʱ<EFBFBD>䣺2025-10-01 09:54:31,֧<EFBFBD><EFBFBD>,2.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025100122001422381406626033 ,0016_86012256_20251001095431_63752 ,,
2025-10-01 03:31:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20251001392894855381 , ,,
2025-09-30 22:56:39,<EFBFBD>˿<EFBFBD>,ͯ***<2A><>,176******46,<EFBFBD>˿<EFBFBD>-<2D><>ʤ<EFBFBD><CAA4>79Ԫ<39><D4AA>ֵ6<D6B5><36><EFBFBD><EFBFBD> <20><><EFBFBD><EFBFBD>Сʳ<D0A1><CAB3>Ʒ<EFBFBD>ײ<EFBFBD>˫<EFBFBD><CBAB><EFBFBD><EFBFBD>˫<EFBFBD><CBAB><EFBFBD><EFBFBD><EFBFBD>ײ<EFBFBD><D7B2><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,74.00,Mastercard(7567),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025093022001122381459367194_4778829794028367849 ,T200P4778829794028367849 ,,
2025-09-30 16:48:32,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̼<EFBFBD>,cds***@bytedance.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>6<EFBFBD><EFBFBD><EFBFBD>ϵ»<EFBFBD>Ԫ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,40.90,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025093022001422381455223137 ,2001052509300102448288487934 ,,
2025-09-30 16:27:57,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,ͯ***<2A><>,176******46,<EFBFBD><EFBFBD>ʤ<EFBFBD><EFBFBD>79Ԫ<EFBFBD><EFBFBD>ֵ6<EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20><><EFBFBD><EFBFBD>Сʳ<D0A1><CAB3>Ʒ<EFBFBD>ײ<EFBFBD>˫<EFBFBD><CBAB><EFBFBD><EFBFBD>˫<EFBFBD><CBAB><EFBFBD><EFBFBD><EFBFBD>ײ<EFBFBD><D7B2><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,148.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025093022001122381457237875 ,T200P4779138492817367849 ,,
2025-09-30 16:05:14,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,ͯ***<2A><>,176******46,<EFBFBD><EFBFBD>ʤ<EFBFBD><EFBFBD>79Ԫ<EFBFBD><EFBFBD>ֵ6<EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20><><EFBFBD><EFBFBD>Сʳ<D0A1><CAB3>Ʒ<EFBFBD>ײ<EFBFBD>˫<EFBFBD><CBAB><EFBFBD><EFBFBD>˫<EFBFBD><CBAB><EFBFBD><EFBFBD><EFBFBD>ײ<EFBFBD><D7B2><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,74.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025093022001122381459367194 ,T200P4778829794028367849 ,,
2025-09-30 03:07:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250930382909273381 , ,,
2025-09-29 03:40:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250929376639863381 , ,,
2025-09-28 11:06:36,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ȼ<EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD>Ȼ<EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD>(9293),֧<EFBFBD><EFBFBD>,9.80,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092822001422381437175823 ,30P2088501249387791W03_20250928D116CCerfc7p58980301000 ,,
2025-09-28 11:06:13,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ȼ<EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD>Ȼ<EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD>(2444),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,4.70,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025092822001422381441105479 ,10P2088501249387791W03_20250928D116CCerq1im29720100103 ,,
2025-09-28 11:06:07,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ȼ<EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD>Ȼ<EFBFBD>ʹ<EFBFBD><EFBFBD><EFBFBD>(6432),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,4.40,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025092822001422381438827825 ,10P2088501249387791W03_20250928D116CCer7og575480100003 ,,
2025-09-28 03:14:36,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250928375100368381 , ,,
2025-09-27 11:10:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,16.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092722001122381429859795 ,13110600725092720047056809923 ,,
2025-09-27 03:10:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250927362642454381 , ,,
2025-09-26 03:00:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250926361547276381 , ,,
2025-09-25 11:06:51,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>Ͻְ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,8.99,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092522001122381418988180 ,13110600725092517783897809923 ,,
2025-09-25 03:03:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250925349076342381 , ,,
2025-09-24 18:09:30,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ele***@service.aliyun.com,ʰ<EFBFBD>ݿ<EFBFBD>24H<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ı<EFBFBD><C4B1>ֵ<EFBFBD>),֧<EFBFBD><EFBFBD>,7.90,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092422001122381414422713 ,13180600725092491701863809923 ,,
2025-09-24 03:19:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250924342098358381 , ,,
2025-09-23 16:55:03,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ele***@service.aliyun.com,ʰ<EFBFBD>ݿ<EFBFBD>24H<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ı<EFBFBD><C4B1>ֵ<EFBFBD>),֧<EFBFBD><EFBFBD>,13.85,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8050)&<26><>ͨ<EFBFBD><CDA8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092322001122381407151523 ,13160600725092383589350809923 ,,
2025-09-23 02:36:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250923334898725381 , ,,
2025-09-22 16:53:59,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ele***@service.aliyun.com,ʰ<EFBFBD>ݿ<EFBFBD>24H<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ı<EFBFBD><C4B1>ֵ<EFBFBD>),֧<EFBFBD><EFBFBD>,13.40,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092222001122381456935724 ,13160600725092274001909809923 ,,
2025-09-22 03:45:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250922328821573381 , ,,
2025-09-21 03:12:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250921317692171381 , ,,
2025-09-20 11:09:18,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,14.50,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025092022001122381445453695 ,13110600725092080014994809923 ,,
2025-09-20 03:12:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250920315811278381 , ,,
2025-09-19 11:12:26,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʦ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>е<EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,8.70,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091922001122381435021156 ,13110600725091919883735809923 ,,
2025-09-19 03:39:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250919309211758381 , ,,
2025-09-18 11:23:00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ<EFBFBD>跹<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.19,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091822001122381429381602 ,13110600725091802792971809923 ,,
2025-09-18 04:08:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250918302648664381 , ,,
2025-09-17 18:48:21,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ele***@service.aliyun.com,H.+<2B>ݶ<EFBFBD><DDB6>೬<EFBFBD><E0B3AC>(<28><><EFBFBD>е<EFBFBD>),֧<EFBFBD><EFBFBD>,5.60,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091722001122381426039807 ,13180600725091783703837809923 ,,
2025-09-17 04:20:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250917396314409381 , ,,
2025-09-16 03:32:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250916383194185381 , ,,
2025-09-15 03:48:13,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250915382170851381 , ,,
2025-09-14 17:01:32,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,zxp***@meituan.com,<EFBFBD>ۼ<EFBFBD><EFBFBD>տ<EFBFBD><EFBFBD><EFBFBD>-<2D><><EFBFBD><EFBFBD>App-25091411100300001308432887524513,֧<EFBFBD><EFBFBD>,183.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091422001422381404109972 ,20250914170126U16915646628473623 ,,
2025-09-14 17:00:39,<EFBFBD>˿<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,zxp***@meituan.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD>Ŷ<EFBFBD><C5B6><EFBFBD>-25091411100300001308434164447513,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,163.00,Mastercard(7567),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025091422001422381400154130_20250914170039R14546788680653514 ,20250914165416U98850402059403514 ,,
2025-09-14 16:54:23,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,zxp***@meituan.com,<EFBFBD><EFBFBD><EFBFBD>Ŷ<EFBFBD><EFBFBD><EFBFBD>-25091411100300001308434164447513,֧<EFBFBD><EFBFBD>,163.60,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091422001422381400154130 ,20250914165416U98850402059403514 ,,
2025-09-14 03:18:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250914375953025381 , ,,
2025-09-13 11:34:08,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ճ¼Ұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.67,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091322001122381455921098 ,13110600725091321787496809923 ,,
2025-09-13 03:40:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250913364839447381 , ,,
2025-09-13 01:10:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,49.70,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250913019130101000380011178987 ,20250913009130501000380010980838 ,,
2025-09-12 21:45:22,<EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϣ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,xys***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>-<2D><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(4728162674678780409)<29>ۿ<EFBFBD>,֧<EFBFBD><EFBFBD>,0.30,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091210032004150267985192 , ,,
2025-09-12 03:01:18,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250912362483510381 , ,,
2025-09-11 17:54:49,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,x***4,187******89,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƴ<EFBFBD>š<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD> <20><><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD><C5A1><EFBFBD><EFBFBD>ڲ<EFBFBD><DAB2><EFBFBD>ƴ<EFBFBD>ţ<EFBFBD>,֧<EFBFBD><EFBFBD>,2.82,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091122001122381447051715 ,T200P4736005959805367849 ,,
2025-09-11 17:54:23,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,x***4,187******89,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƴ<EFBFBD>š<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD> <20><><EFBFBD><EFBFBD><EFBFBD>š<EFBFBD><C5A1><EFBFBD><EFBFBD>ڲ<EFBFBD><DAB2><EFBFBD>ƴ<EFBFBD>ţ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,1.00,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025091122001122381447349654 ,T200P4735817174475367849 ,,
2025-09-11 03:13:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250911356903776381 , ,,
2025-09-10 11:27:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʦ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>е<EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,9.60,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025091022001122381437400638 ,13110600725091044593132809923 ,,
2025-09-10 03:18:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250910350130083381 , ,,
2025-09-09 18:41:30,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,ttw***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ļ<EFBFBD>-<2D>ļ<EFBFBD><C4BC><EFBFBD>_1858364978_LP00758467960213,֧<EFBFBD><EFBFBD>,25.50,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090922001422381434337487 ,CN_V1_602217969737300959 ,,
2025-09-09 04:22:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250909338859440381 , ,,
2025-09-08 12:21:24,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,****6,173******20,32<EFBFBD><EFBFBD> wsy<73><79>ʾ<EFBFBD><CABE> 2025<32><35>6<EFBFBD>¹<EFBFBD><C2B9><EFBFBD> <20>dz<EFBFBD><C7B3><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,50.00,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090822001133151414964530 ,T200P4728162674678780409 ,,
2025-09-08 05:37:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250908337964632381 , ,,
2025-09-07 20:59:17,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD>ƶ<EFBFBD>,z97***@service.aliyun.com,Ϊ19801981923<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,49.04,<EFBFBD>ʴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(8058)&<26>ʴ<EFBFBD><CAB4><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090722001422381417260873 ,2025090700003100003855175487 ,,
2025-09-07 18:49:15,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>εγ<EFBFBD><EFBFBD><EFBFBD>,chu***@didichuxing.com,<EFBFBD>ػݿ쳵<EFBFBD><EFBFBD><EFBFBD><EFBFBD>-<2D><>ʦ<EFBFBD><CAA6>-09<30><39>07<30><37><EFBFBD>г<EFBFBD>,֧<EFBFBD><EFBFBD>,20.15,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090722001422381416348388 ,212_202509078430588101785912 ,,
2025-09-07 18:47:27,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̼<EFBFBD>,cds***@bytedance.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ţ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>浥<EFBFBD><EFBFBD><EFBFBD>ײ<EFBFBD>,֧<EFBFBD><EFBFBD>,9.22,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090722001422381421976588 ,2001052509070102390544035385 ,,
2025-09-07 14:30:55,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>εγ<EFBFBD><EFBFBD><EFBFBD>,chu***@didichuxing.com,<EFBFBD>ػݿ쳵<EFBFBD><EFBFBD><EFBFBD><EFBFBD>-<2D><>ʦ<EFBFBD><CAA6>-09<30><39>07<30><37><EFBFBD>г<EFBFBD>,֧<EFBFBD><EFBFBD>,14.45,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090722001422381416152939 ,212_202509078430376001846412 ,,
2025-09-07 09:58:26,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,46.85,<EFBFBD>ʴ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(8058)&<26>ʴ<EFBFBD><CAB4><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090700003001380057548315 ,1300787791955 ,,
2025-09-07 04:03:50,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250907331405160381 , ,,
2025-09-06 16:59:08,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʦ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>۰<EFBFBD><DBB0><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>е<EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,9.40,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090622001122381411552157 ,13160600725090606378763809923 ,,
2025-09-06 02:53:37,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250906319001768381 , ,,
2025-09-05 03:33:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250905317471288381 , ,,
2025-09-04 17:04:40,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>跹<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƥ<EFBFBD><EFBFBD><EFBFBD>׷<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,12.80,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090422001122381458914643 ,13170600725090466508706809923 ,,
2025-09-04 06:02:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250904311991165381 , ,,
2025-09-03 11:05:56,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>ȼ͡<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ⷹ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,12.40,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090322001122381454517433 ,13110600725090381808990809923 ,,
2025-09-03 03:48:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250903300292465381 , ,,
2025-09-02 17:33:38,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ<EFBFBD>跹<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.69,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090222001122381451621052 ,13170600725090224234883809923 ,,
2025-09-02 09:47:30,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,414.66,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025090200003001380056655821 , ,,
2025-09-02 03:09:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.09.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250902398392051381 , ,,
2025-09-01 20:15:06,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,dzq***@chinatelecom-ec.com.cn,Ϊ17329730418<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,49.42,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090122001422381449765621 ,2025090100003100003854508158 ,,
2025-09-01 10:58:34,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ<EFBFBD>跹<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.57,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025090122001122381446946156 ,13100600725090129635381809923 ,,
2025-09-01 02:36:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.31-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250901388046757381 , ,,
2025-08-31 16:06:22,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><><EFBFBD>й㳡<D0B9><E3B3A1>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.20,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025083122001122381444785817 ,13160600725083193746470809923 ,,
2025-08-31 11:21:21,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,èѾ<EFBFBD>ס<EFBFBD><EFBFBD>񽱵ij<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݶ<EFBFBD><DDB6><EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.30,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025083122001122381444767662 ,13110600725083137101972809923 ,,
2025-08-31 04:13:37,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250831387408011381 , ,,
2025-08-30 20:10:27,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ҼƷ**<2A><>,gb3***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Żݡ<EFBFBD> Apple/ƻ<><C6BB> Mac mini ̨ʽ<CCA8><CABD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> M4/M4 ProоƬ<D0BE><C6AC><EFBFBD><EFBFBD>ʽ<EFBFBD><CABD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ż<EFBFBD>,֧<EFBFBD><EFBFBD>,2470.24,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025083022001122381440104621 ,T200P4711537692627367849 ,,
2025-08-30 19:38:20,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,ʵ***<2A><>,188******61,ƻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ż<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȫ<EFBFBD><EFBFBD><EFBFBD>˿<EFBFBD> zfb<66><62>֤,֧<EFBFBD><EFBFBD>,26.12,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025083022001122381438997910 ,T200P4711349665664367849 ,,
2025-08-30 16:20:33,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD>ϰ<EFBFBD><EFBFBD>̡<EFBFBD><EFBFBD><EFBFBD>ѡ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><><EFBFBD><EFBFBD>·<EFBFBD><C2B7>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,3.50,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025083022001122381440416921 ,13160600725083031481906809923 ,,
2025-08-30 04:15:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250830381113289381 , ,,
2025-08-29 03:44:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250829370707957381 , ,,
2025-08-28 04:17:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250828369488934381 , ,,
2025-08-27 14:05:01,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,235.70,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025082700003001380056000002 , ,,
2025-08-27 11:06:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,èѾ<EFBFBD>ס<EFBFBD><EFBFBD>񽱵ij<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݶ<EFBFBD><DDB6><EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,9.82,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082722001122381428267232 ,13110600725082710826106809923 ,,
2025-08-27 03:18:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250827362797805381 , ,,
2025-08-26 03:04:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250826357066023381 , ,,
2025-08-25 21:38:41,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,v***g,152******10,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>S10ѧϰ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>10.3Ӣ<EFBFBD><EFBFBD>īˮ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˿<EFBFBD><EFBFBD><EFBFBD>ǰ<EFBFBD>⣬<EFBFBD><EFBFBD><EFBFBD>˵<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,677.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082522001122381421271920 ,T200P4702801357739367849 ,,
2025-08-25 17:43:26,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,z97***@service.aliyun.com,Ϊ19267221762<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,10.00,Mastercard(7567),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082522001422381421790820 ,2025082500003100003853963095 ,,
2025-08-25 17:42:43,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,50.00,,<EFBFBD>ѹر<EFBFBD>,2025082500003001380055828559 ,1300787791955 ,,
2025-08-25 03:17:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250825350652232381 , ,,
2025-08-24 17:13:03,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,èѾ<EFBFBD>ס<EFBFBD><EFBFBD>񽱵ij<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݶ<EFBFBD><DDB6><EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,11.70,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082422001122381417732874 ,13170600725082449482329809923 ,,
2025-08-24 15:02:16,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,w***g,180******61,13.3<EFBFBD><EFBFBD>īˮ<EFBFBD><EFBFBD> <20><><EFBFBD><EFBFBD> 40hzˢ<7A><CBA2> <20>ֻ<EFBFBD><D6BB><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,1504.41,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9080)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082422001122381416968053 ,T200P4700379745630367849 ,,
2025-08-24 14:25:02,<EFBFBD><EFBFBD><EFBFBD>ý軹,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,36.74,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025082400003001380055706885 , ,,
2025-08-24 11:13:27,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD>ô<EFBFBD>һ<EFBFBD>롤<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ţ<EFBFBD>(<28>ݳǵ<DDB3>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,13.76,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082422001122381416391443 ,13110600725082490203741809923 ,,
2025-08-24 03:04:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.02,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250824345384659381 , ,,
2025-08-23 11:10:46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʿ<EFBFBD><EFBFBD>ȫ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ݵ<EFBFBD><DDB5><EFBFBD>·<EFBFBD><C2B7>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,19.63,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8050)&<26><>ͨ<EFBFBD><CDA8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082322001122381410880259 ,13110600725082317238191809923 ,,
2025-08-23 03:48:18,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250823339941125381 , ,,
2025-08-22 18:33:24,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,133***@163.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ڻ<EFBFBD>е<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ĻĤ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>15Pro<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Pro<EFBFBD>ʼDZ<EFBFBD><EFBFBD><EFBFBD>ĤG16<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Supe<EFBFBD><EFBFBD><EFBFBD><EFBFBD>16<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ۿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>16S/16k<36><6B><EFBFBD><EFBFBD>ĤAi,֧<EFBFBD><EFBFBD>,57.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&֧<><D6A7><EFBFBD>Ż<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082222001122381409009009 ,T200P4697285365130367849 ,,
2025-08-22 16:47:18,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,300.00,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250822200040031100380096203310 ,202508220206302182461597380007824492 ,,
2025-08-22 03:16:15,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250822333896325381 , ,,
2025-08-21 03:31:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250821328027822381 , ,,
2025-08-20 15:36:02,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>콢<EFBFBD><EFBFBD>,133***@163.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ڻ<EFBFBD>е<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ĻĤ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>15Pro<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Pro<EFBFBD>ʼDZ<EFBFBD><EFBFBD><EFBFBD>ĤG16<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Supe<EFBFBD><EFBFBD><EFBFBD><EFBFBD>16<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ۿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>16S/16k<36><6B><EFBFBD><EFBFBD>ĤAi,֧<EFBFBD><EFBFBD>,39.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082022001122381459533429 ,T200P4693788468261367849 ,,
2025-08-20 15:36:02,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ó,137******60,<EFBFBD><EFBFBD>75<EFBFBD>Ⱦƾ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʪ<EFBFBD><EFBFBD>80<EFBFBD><EFBFBD><EFBFBD>칫<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɱ<EFBFBD><EFBFBD>ר<EFBFBD><EFBFBD>ʪֽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>־<EFBFBD>,֧<EFBFBD><EFBFBD>,1.98,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025082022001122381459879423 ,T200P4693788468262367849 ,,
2025-08-20 03:21:15,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250820321933754381 , ,,
2025-08-19 10:45:42,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**<2A><>,230***@qq.com,<EFBFBD><EFBFBD><EFBFBD>û<EFBFBD>е<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҫ<EFBFBD><EFBFBD>16pro<EFBFBD><EFBFBD>Ļ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ĥ<EFBFBD>޽<EFBFBD>14<EFBFBD>ֻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>16<EFBFBD><EFBFBD><EFBFBD><EFBFBD>X<EFBFBD><EFBFBD>Ĥ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>⻤<EFBFBD><EFBFBD><EFBFBD>޽<EFBFBD>14X<EFBFBD><EFBFBD><EFBFBD>弫<EFBFBD><EFBFBD>Pro15.6<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20>ȶ<EFBFBD><C8B6><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,28.52,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025081922001122381455031759 ,T200P4691413369379367849 ,,
2025-08-19 03:08:36,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250819311442207381 , ,,
2025-08-18 03:17:36,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250818310123849381 , ,,
2025-08-17 02:59:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250817304860229381 , ,,
2025-08-16 03:12:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250816397477484381 , ,,
2025-08-15 22:53:56,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,x***1,189******93,<EFBFBD><EFBFBD>LGԭ<EFBFBD><EFBFBD>4K<EFBFBD><EFBFBD>16<EFBFBD><EFBFBD>4k60hz<EFBFBD><EFBFBD>Я<EFBFBD><EFBFBD>4K<EFBFBD><EFBFBD>Я<EFBFBD><EFBFBD>ʾ<EFBFBD><EFBFBD>swi,֧<EFBFBD><EFBFBD>,520.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025081522001122381440714523 ,T200P4686011388200367849 ,,
2025-08-15 03:13:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250815394396009381 , ,,
2025-08-14 03:11:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250814388920262381 , ,,
2025-08-13 03:08:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250813383824405381 , ,,
2025-08-12 16:48:58,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***3,183******08,<EFBFBD>й<EFBFBD><EFBFBD>ƶ<EFBFBD> <20><><EFBFBD><EFBFBD>SR1041D ˫Ƶǧ<C6B5><C7A7>·<EFBFBD><C2B7><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,28.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025081222001122381427638308 ,T200P4680666901563367849 ,,
2025-08-12 03:14:14,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250812378302151381 , ,,
2025-08-11 03:35:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250811373582207381 , ,,
2025-08-10 17:32:58,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,С<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,9.80,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025081022001122381420830718 ,13170600725081032947729809923 ,,
2025-08-10 04:05:14,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250810368418242381 , ,,
2025-08-09 12:12:11,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>Ա<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,e50***@alibaba-inc.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ<EFBFBD>跹(<28>̷<EFBFBD><CCB7><EFBFBD><EFBFBD>ĵ<EFBFBD>)<29><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,3.40,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025080922001122381414274601 ,13120600725080908838843809923 ,,
2025-08-09 03:06:37,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250809362722939381 , ,,
2025-08-08 10:38:00,<EFBFBD>Ļ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**6,132******40,PS4/PS5<53><35><EFBFBD><EFBFBD> ע<><D7A2><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ŷ PS5<53>۰汸<DBB0><E6B1B8> <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20><><EFBFBD>ݽ<EFBFBD><DDBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,5.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025080822001122381409283246 ,T200P4673272683844367849 ,,
2025-08-08 03:23:45,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250808357119063381 , ,,
2025-08-07 02:51:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250807347240236381 , ,,
2025-08-06 14:13:50,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,99.03,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025080600003001380053671496 ,1300787791955 ,,
2025-08-06 04:10:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250806340275432381 , ,,
2025-08-05 23:58:03,<EFBFBD>˿<EFBFBD>,t***2,180******73,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD><EFBFBD>ps5silm<6C>ᱡ<EFBFBD><E1B1A1><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ֱ<EFBFBD><D6B1><EFBFBD><EFBFBD>Զ<EFBFBD><D4B6><EFBFBD>99<39>£<EFBFBD><C2A3><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ڱ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2591.90,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26>Ż<EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025080422001122381458573012_4667427648402367849 ,T200P4667427648402367849 ,,
2025-08-05 04:12:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250805336915918381 , ,,
2025-08-04 20:22:16,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***2,180******73,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ps5silm<EFBFBD>ᱡ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD>ֱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Զ<EFBFBD><EFBFBD><EFBFBD>99<EFBFBD>£<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ڱ<EFBFBD>,֧<EFBFBD><EFBFBD>,2591.90,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025080422001122381458573012 ,T200P4667427648402367849 ,,
2025-08-04 18:24:23,<EFBFBD>˿<EFBFBD>,t***0,192******88,<EFBFBD>˿<EFBFBD>-<2D>۰<EFBFBD>PS5 Slim<69><6D><EFBFBD>ְ<EFBFBD><D6B0><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>1TB<54><42><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɫ<EFBFBD><C9AB><EFBFBD><EFBFBD>ȫ<EFBFBD>¡<EFBFBD><C2A1><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2800.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025080422001122381458885838_4667214924501367849 ,T200P4667214924501367849 ,,
2025-08-04 18:07:56,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***0,192******88,<EFBFBD>۰<EFBFBD>PS5 Slim<69><6D><EFBFBD>ְ<EFBFBD><D6B0><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>1TB<54><42><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɫ<EFBFBD><C9AB><EFBFBD><EFBFBD>ȫ<EFBFBD>¡<EFBFBD><C2A1><EFBFBD>,֧<EFBFBD><EFBFBD>,2800.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025080422001122381458885838 ,T200P4667214924501367849 ,,
2025-08-04 04:33:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250804331652482381 , ,,
2025-08-03 04:19:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250803326303458381 , ,,
2025-08-02 10:29:59,ҽ<EFBFBD>ƽ<EFBFBD><EFBFBD><EFBFBD>,*ΰ,151******36,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,2.34,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301)&<26><><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025080223001422381446505041 ,47541017993112300022388 ,,
2025-08-02 03:08:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.08.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250802320470551381 , ,,
2025-08-01 04:09:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.31-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250801315714401381 , ,,
2025-07-31 15:13:32,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,402.75,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025073100003001380052470433 , ,,
2025-07-31 03:24:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250731308407712381 , ,,
2025-07-30 02:48:18,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250730304661081381 , ,,
2025-07-29 03:13:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250729399432012381 , ,,
2025-07-28 10:59:10,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,207.88,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025072800003001380052168861 , ,,
2025-07-28 03:07:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250728393959428381 , ,,
2025-07-27 03:47:14,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250727389200054381 , ,,
2025-07-26 03:31:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250726384194014381 , ,,
2025-07-25 02:58:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250725378200243381 , ,,
2025-07-24 03:16:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250724373393289381 , ,,
2025-07-23 03:10:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250723368326570381 , ,,
2025-07-22 16:47:21,<EFBFBD><EFBFBD><EFBFBD>ý軹,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,46.67,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025072200003001380051622816 , ,,
2025-07-22 03:33:34,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250722362895518381 , ,,
2025-07-21 03:40:48,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250721358181762381 , ,,
2025-07-20 03:48:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250720352942396381 , ,,
2025-07-19 03:25:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250719347295506381 , ,,
2025-07-18 03:24:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250718336979163381 , ,,
2025-07-17 03:29:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250717335267177381 , ,,
2025-07-16 03:27:15,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250716329331861381 , ,,
2025-07-15 13:24:41,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,173******20,<EFBFBD><EFBFBD><EFBFBD>ŷ<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025071522001122381431450252 ,T200P4632775668334367849 ,,
2025-07-15 02:51:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250715324029955381 , ,,
2025-07-14 03:08:45,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250714318349224381 , ,,
2025-07-13 18:34:54,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̼<EFBFBD>,cds***@bytedance.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>2<EFBFBD>ο<EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,10.08,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025071322001422381423337838 ,2001052507130101916666229801 ,,
2025-07-13 04:34:45,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250713313700130381 , ,,
2025-07-12 03:09:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250712307997692381 , ,,
2025-07-11 14:49:22,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,tb**6,181******18,<EFBFBD><EFBFBD>ɫ<EFBFBD><EFBFBD>Ѽ<EFBFBD>Ҽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɫ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Կ<EFBFBD>׿ۿɰ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ǧѼɳ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,1.88,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025071122001122381415025978 ,T200P4625824539289367849 ,,
2025-07-11 14:49:22,<EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>1**8,cn9***@88.com,idea2025<EFBFBD><EFBFBD><EFBFBD><EFBFBD>pycharmרҵ<EFBFBD><EFBFBD>clion<EFBFBD><EFBFBD><EFBFBD>漤<EFBFBD><EFBFBD> jetbrainsȫ<73><C8AB>Ͱ,֧<EFBFBD><EFBFBD>,29.90,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025071122001122381416214774 ,T200P4625824539288367849 ,,
2025-07-11 03:17:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250711302917032381 , ,,
2025-07-10 03:35:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250710397217877381 , ,,
2025-07-09 14:02:16,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,99.89,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025070900003001380050128031 ,1300787791955 ,,
2025-07-09 03:28:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250709390645618381 , ,,
2025-07-08 04:04:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250708384507381381 , ,,
2025-07-07 04:42:14,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250707379478842381 , ,,
2025-07-06 04:04:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250706373787807381 , ,,
2025-07-05 03:10:53,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250705367767901381 , ,,
2025-07-04 15:55:15,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD>ƶ<EFBFBD>,z97***@service.aliyun.com,Ϊ18802881074<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,199.68,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025070422001422381445618978 ,2025070400003100003850130138 ,,
2025-07-04 03:02:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250704362536622381 , ,,
2025-07-03 03:23:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250703357377104381 , ,,
2025-07-02 03:04:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.07.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250702351319312381 , ,,
2025-07-01 02:36:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.07,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250701345879139381 , ,,
2025-06-30 03:46:49,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250630341159330381 , ,,
2025-06-29 03:33:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250629335711106381 , ,,
2025-06-28 15:58:53,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,46.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062822001422381420671443 ,M20250628235726798 ,,
2025-06-28 14:40:21,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,23.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062822001422381421449042 ,M2025062841110438 ,,
2025-06-28 02:29:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250628326925673381 , ,,
2025-06-27 17:27:34,<EFBFBD>˿<EFBFBD>,tb**8,135******99,<EFBFBD>˿<EFBFBD>-12<31><32>CPU ϣ<><CFA3>̨ʽ<CCA8><CABD><EFBFBD><EFBFBD>8G<38>ڴ<EFBFBD> 256G<36><47>̬M2 ԭ<><D4AD>i5-12400<30>Ѳ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,679.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025062722001122381415789440_4603068361462367849 ,T200P4603068361462367849 ,,
2025-06-27 17:19:14,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,tb**8,135******99,12<EFBFBD><EFBFBD>CPU ϣ<><CFA3>̨ʽ<CCA8><CABD><EFBFBD><EFBFBD>8G<38>ڴ<EFBFBD> 256G<36><47>̬M2 ԭ<><D4AD>i5-12400<30>Ѳ<EFBFBD>,֧<EFBFBD><EFBFBD>,679.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025062722001122381415789440 ,T200P4603068361462367849 ,,
2025-06-27 17:19:14,<EFBFBD>˶<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>**,176******85,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>๦<EFBFBD>ܻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ز<EFBFBD><EFBFBD><EFBFBD><EFBFBD>¼Ӻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>¶Ӫ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>¹<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,3.90,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062722001122381418403888 ,T200P4603068361463367849 ,,
2025-06-27 02:30:18,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250627324910959381 , ,,
2025-06-26 14:17:02,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ӱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>۰<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,50.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062600003001380048238864 ,1300787791955 ,,
2025-06-26 11:52:45,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,37.83,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025062600003001380048218208 , ,,
2025-06-26 11:52:26,<EFBFBD><EFBFBD><EFBFBD>ý軹,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,25.16,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025062600003001380048220960 , ,,
2025-06-26 03:07:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250626319462455381 , ,,
2025-06-25 03:25:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250625314622619381 , ,,
2025-06-24 03:03:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250624307632071381 , ,,
2025-06-24 00:52:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,10.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250624019130101000380044591796 ,20250624009130501000380063538831 ,,
2025-06-23 16:01:06,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,***<2A><>,mzi***@qq.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ת<EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,10.00,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062322001351731444631009 ,T3900P4402188108580733909 ,,
2025-06-23 03:06:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250623303988500381 , ,,
2025-06-22 17:48:34,<EFBFBD>Ļ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>ư<EFBFBD>,/,<EFBFBD>ƶ<EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,140.94,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062222001422381451824242 ,772016102002255999250622608571430520 ,,
2025-06-22 17:45:51,<EFBFBD>˿<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>ư<EFBFBD>,/,<EFBFBD>˿<EFBFBD>-<2D>ƶ<EFBFBD>֧<EFBFBD><D6A7>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,100.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025062222001422381451863311_562016102002255999250622608555130221 ,562016102002255999250622608541829957 ,,
2025-06-22 17:43:38,<EFBFBD>Ļ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>ư<EFBFBD>,/,<EFBFBD>ƶ<EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,100.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025062222001422381451863311 ,562016102002255999250622608541829957 ,,
2025-06-22 17:04:15,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD><EFBFBD>Ž<EFBFBD><EFBFBD><EFBFBD>,it_***@meituan.com,<EFBFBD><EFBFBD><EFBFBD>Ŷ<EFBFBD><EFBFBD><EFBFBD>-<2D><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>¸<EFBFBD><C2B8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>2025<32><35>6<EFBFBD><36><EFBFBD>˵<EFBFBD>,֧<EFBFBD><EFBFBD>,42.82,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062222001422381450641126 ,20250622170406U17824294339453555 ,,
2025-06-22 15:16:39,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>˹**<2A><>,asl***@service.taobao.com,<EFBFBD><EFBFBD>Ʊ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{8216068949978|1_2_2025000383259929929},֧<EFBFBD><EFBFBD>,1216.00,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(8676) 3<><33>&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025062222001122381448703365 ,T1400P4400562927905367849 ,,
2025-06-22 03:25:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250622398881910381 , ,,
2025-06-21 03:43:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250621392993957381 , ,,
2025-06-20 03:00:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250620386728126381 , ,,
2025-06-19 03:34:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250619380974263381 , ,,
2025-06-18 15:24:43,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,С***<2A><>,mzi***@qq.com,ȫ<EFBFBD><EFBFBD>32<EFBFBD><EFBFBD>2K 75Hz<48><7A>ʾ<EFBFBD><CABE>MYS 32Q75S<35><53>ɫ,֧<EFBFBD><EFBFBD>,529.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025061822001122381429924253 ,T200P4393403318241367849 ,,
2025-06-18 14:14:37,<EFBFBD>ҾӼ<EFBFBD>װ,tb**4,185******43,CM<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˿<EFBFBD><EFBFBD><EFBFBD><EFBFBD>˿<EFBFBD><EFBFBD>ĸ<EFBFBD><EFBFBD>װ<EFBFBD><EFBFBD>װ<EFBFBD><EFBFBD>еƽͷ<EFBFBD><EFBFBD>˿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>װM2M2.5M3M4M5,֧<EFBFBD><EFBFBD>,8.20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025061822001122381424331852 ,T200P4393415592853367849 ,,
2025-06-18 03:18:48,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250618371982396381 , ,,
2025-06-17 05:43:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250617371498205381 , ,,
2025-06-16 09:42:22,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**9,156***@163.com,DB<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>V2.12ȫ<EFBFBD>Զ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD><EFBFBD>˫<EFBFBD><EFBFBD>5G<EFBFBD>忨<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>13141516ϵ<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.99,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025061622001122381416130601 ,T200P4389721452158367849 ,,
2025-06-16 03:52:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250616364643274381 , ,,
2025-06-15 20:22:14,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,23.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025061522001422381415060657 ,M20250615261406386 ,,
2025-06-15 02:33:48,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250615358250179381 , ,,
2025-06-14 03:17:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250614352799424381 , ,,
2025-06-13 17:25:23,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,15.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025061322001422381400534891 ,M20250613250168182 ,,
2025-06-13 03:15:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250613346768971381 , ,,
2025-06-12 02:47:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250612341311468381 , ,,
2025-06-11 04:39:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250611336328282381 , ,,
2025-06-10 03:35:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250610329986075381 , ,,
2025-06-09 03:32:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250609324395049381 , ,,
2025-06-09 01:30:58,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,1.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250609019130101000380032036107 ,20250609009130501000380055787585 ,,
2025-06-08 14:32:47,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,****6,173******20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ת<EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,1.00,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025060822001333151450756566 ,T3900P4376733769555780409 ,,
2025-06-08 04:06:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250608318254895381 , ,,
2025-06-07 04:14:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250607312822115381 , ,,
2025-06-06 03:54:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250606307367695381 , ,,
2025-06-05 03:12:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250605300999334381 , ,,
2025-06-04 05:36:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250604395526899381 , ,,
2025-06-03 20:05:35,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,22.83,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025060322001422381408936641 ,M20250603204029029 ,,
2025-06-03 03:31:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250603388483391381 , ,,
2025-06-02 10:20:50,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,15.20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9080)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025060200003001380045459588 , ,,
2025-06-02 04:31:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.06.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250602382329067381 , ,,
2025-06-01 04:30:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.31-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250601376232407381 , ,,
2025-05-31 03:23:41,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250531369535213381 , ,,
2025-05-30 02:36:34,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250530362803136381 , ,,
2025-05-29 03:24:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250529356745225381 , ,,
2025-05-28 03:31:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250528350601780381 , ,,
2025-05-27 20:50:43,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,ts**<2A><>,156******53,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ܳ䡿DNF<EFBFBD><EFBFBD>ȯ<EFBFBD><EFBFBD><EFBFBD>ο<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>³<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD> dnf100000<30><30><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,925.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025052722001122381430770657 ,T200P4358637648693367849 ,,
2025-05-27 17:09:29,<EFBFBD>˿<EFBFBD>,yi**7,131******78,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD>»<EFBFBD><C2BB><EFBFBD><EFBFBD>ؿɳ䡿DNF<4E><46>ȯ<EFBFBD><C8AF><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>³<EFBFBD> dnf100000<30><30>ȯ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,904.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025052722001122381430579401_4358332548790367849 ,T200P4358332548790367849 ,,
2025-05-27 16:59:42,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,yi**7,131******78,<EFBFBD><EFBFBD><EFBFBD>»<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ؿɳ䡿DNF<EFBFBD><EFBFBD>ȯ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>³<EFBFBD> dnf100000<30><30>ȯ,֧<EFBFBD><EFBFBD>,904.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025052722001122381430579401 ,T200P4358332548790367849 ,,
2025-05-27 02:49:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250527336276525381 , ,,
2025-05-26 04:34:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250526330964114381 , ,,
2025-05-25 03:37:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250525324017301381 , ,,
2025-05-24 04:02:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250524318023487381 , ,,
2025-05-23 04:08:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250523311477636381 , ,,
2025-05-22 02:29:01,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250522399872574381 , ,,
2025-05-21 15:51:49,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**˶,127***@qq.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>qpe֧<EFBFBD><EFBFBD>4/5Gרҵ<D7A8><D2B5>16PM/14/13/12/XR/Xsmax/XS/8P<38><50><EFBFBD>հ<EFBFBD>,֧<EFBFBD><EFBFBD>,8.80,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025052122001122381447601859 ,T200P4349107836447367849 ,,
2025-05-21 09:53:19,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>**8,139******71,<EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>QPE<EFBFBD><EFBFBD>ƻ<EFBFBD><EFBFBD>iPhone12 13 14promax SE3<45>ƶ<EFBFBD><C6B6><EFBFBD>ͨ<EFBFBD><CDA8><EFBFBD>Ž<EFBFBD><C5BD><EFBFBD>5G,֧<EFBFBD><EFBFBD>,37.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025052122001122381447793861 ,T200P4348158337219367849 ,,
2025-05-21 09:53:19,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,in**<2A><>,inb***@163.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>С<EFBFBD><EFBFBD><EFBFBD>Ⱦ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>칫<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>usb<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>С<EFBFBD>ͼ<EFBFBD><EFBFBD>ô<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̨<EFBFBD>ȱ<EFBFBD>Я,֧<EFBFBD><EFBFBD>,4.99,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025052122001122381448024267 ,T200P4348158337220367849 ,,
2025-05-21 09:51:17,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>**8,139******71,<EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>QPE<EFBFBD><EFBFBD>ƻ<EFBFBD><EFBFBD>iPhone12 13 14promax SE3<45>ƶ<EFBFBD><C6B6><EFBFBD>ͨ<EFBFBD><CDA8><EFBFBD>Ž<EFBFBD><C5BD><EFBFBD>5G,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,37.00,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025052122001122381442338325 ,T200P4348545663969367849 ,,
2025-05-21 04:34:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250521398751097381 , ,,
2025-05-20 04:13:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250520392389469381 , ,,
2025-05-19 04:26:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250519384237568381 , ,,
2025-05-18 03:31:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250518372719235381 , ,,
2025-05-18 02:00:29,<EFBFBD>˿<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̼<EFBFBD>,cds***@bytedance.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѩ<EFBFBD><D1A9><EFBFBD><EFBFBD>ʥ<EFBFBD><CAA5>ϵ<EFBFBD><CFB5><EFBFBD><EFBFBD>ѡһ3<D2BB>ο<EFBFBD><CEBF><EFBFBD><EFBFBD><EFBFBD>֪<EFBFBD><D6AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,8.64,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025041722001422381407178511_ONP25051802001419002733186715407 ,2001052504170101399721930850 ,,
2025-05-17 03:31:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250517371769023381 , ,,
2025-05-16 22:22:13,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,173******20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025051622001122381412289299 ,T200P4341795843860367849 ,,
2025-05-16 13:41:21,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,173******20,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025051622001122381410170456 ,T200P4340654136078367849 ,,
2025-05-16 04:22:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250516365775235381 , ,,
2025-05-15 03:41:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250515359187556381 , ,,
2025-05-14 13:40:40,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,99.00,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(1074)&<26>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025051400003001380043914528 ,5100398784953 ,,
2025-05-14 02:33:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250514352255943381 , ,,
2025-05-13 03:52:25,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250513346746386381 , ,,
2025-05-12 02:57:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250512335481752381 , ,,
2025-05-11 11:53:00,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,һ<EFBFBD><EFBFBD>һ<EFBFBD><EFBFBD>(<28><><EFBFBD><EFBFBD>Ƽ),523***@qq.com,ת<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,2000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250511200040011100380091221479 , ,,
2025-05-11 11:51:28,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,173******20,ת<EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,2000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250511200040011100150019750338 , ,,
2025-05-11 03:51:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250511333912347381 , ,,
2025-05-10 03:23:17,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250510322600452381 , ,,
2025-05-09 03:05:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250509315779821381 , ,,
2025-05-08 04:14:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250508315073755381 , ,,
2025-05-07 02:51:49,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250507308093085381 , ,,
2025-05-06 15:17:08,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,22.05,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025050600003001380043062305 , ,,
2025-05-06 09:37:24,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,ts**y,ts7***@tom.com,ũ<EFBFBD><EFBFBD><EFBFBD>ո<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD≯ּӺ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ڵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>״󶹸<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,15.37,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025050622001122381402338473 ,T200P4326642253364367849 ,,
2025-05-06 04:10:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250506302629566381 , ,,
2025-05-05 16:43:45,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ,syc***@163.com,00000057-<2D><><EFBFBD>ơ<EFBFBD>00405707<30><37><EFBFBD>˳<EFBFBD>ʱ<EFBFBD>䣺2025-05-05 16:43:43,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025050522001422381401401883 ,00000057_0000000086011267_20250505164343_00059 ,,
2025-05-05 14:33:28,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ,syc***@163.com,00000008-<2D><><EFBFBD>ơ<EFBFBD>00100801<30><31><EFBFBD>˳<EFBFBD>ʱ<EFBFBD>䣺2025-05-05 14:33:26,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025050522001422381458183311 ,00000008_0000000086011036_20250505143326_00040 ,,
2025-05-05 03:47:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250505396136112381 , ,,
2025-05-04 05:48:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250504390645650381 , ,,
2025-05-03 17:53:25,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ߵ´<EFBFBD><EFBFBD><EFBFBD>,aut***@autonavi.com,<EFBFBD>ߵ´򳵶<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,15.01,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025050322001422381446465891 ,0001N202505030000000010652068649 ,,
2025-05-03 03:44:34,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250503383439139381 , ,,
2025-05-02 04:08:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.05.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250502377560317381 , ,,
2025-05-01 11:30:08,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD>ٿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֱ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><><EFBFBD><EFBFBD>·<EFBFBD><C2B7>),sky***@qq.com,846384900245105,֧<EFBFBD><EFBFBD>,159.80,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025050122001422381433276338 ,29412217460702084638490024510505 ,,
2025-05-01 03:32:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250501371362531381 , ,,
2025-04-30 09:11:59,<EFBFBD>˿<EFBFBD>,<EFBFBD>Ϻ<EFBFBD>**<2A><>,/,<EFBFBD>˿<EFBFBD>-<2D><>Ʊ<EFBFBD><C6B1><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{7965555900978|1_2_2025000348147343343},<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,485.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025041422001122381452093535*4300580667428367849_331645250760364978 ,4300580667428367849_331645250760364978 ,,
2025-04-30 03:46:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250430364987217381 , ,,
2025-04-29 22:08:05,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD><EFBFBD>Ʊ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,244.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025041622001422381459713866_M2025042969464392 ,M20250416298601972 ,,
2025-04-29 22:07:32,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD><EFBFBD>Ʊ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,317.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025042622001422381400687657_M2025042969448270 ,M20250426287256131 ,,
2025-04-29 21:59:36,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,347.50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025042922001422381427164993 ,M20250429214277630 ,,
2025-04-29 10:07:59,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,27.90,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9924)&<26>й<EFBFBD><D0B9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025042900003001380042083623 , ,,
2025-04-29 04:42:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250429358743200381 , ,,
2025-04-28 03:54:49,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250428352378605381 , ,,
2025-04-27 04:11:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250427346301836381 , ,,
2025-04-26 09:16:56,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,317.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025042622001422381400687657 ,M20250426287256131 ,,
2025-04-26 04:20:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250426340428146381 , ,,
2025-04-25 03:29:18,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250425329299878381 , ,,
2025-04-24 04:31:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250424327586472381 , ,,
2025-04-23 02:30:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250423313916117381 , ,,
2025-04-22 04:03:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250422313051138381 , ,,
2025-04-21 14:22:28,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,ts**<2A><>,156******53,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ܳ䡿DNF<EFBFBD><EFBFBD>ȯ<EFBFBD><EFBFBD><EFBFBD>ο<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>³<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD> dnf100000<30><30><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,930.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025042122001122381436118562 ,T200P4309751882748367849 ,,
2025-04-21 03:20:13,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250421301104612381 , ,,
2025-04-20 16:30:36,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ߵ´<EFBFBD><EFBFBD><EFBFBD>,aut***@autonavi.com,<EFBFBD>ߵ´򳵶<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,82.69,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025042022001422381427335351 ,0001N202504200000000010497225517 ,,
2025-04-20 03:43:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250420399952807381 , ,,
2025-04-19 02:40:32,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250419393363541381 , ,,
2025-04-18 19:15:06,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>ҳ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,151******48,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,84.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025041822001422381415881370 ,47449749062112300022388 ,,
2025-04-18 04:18:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250418382757845381 , ,,
2025-04-17 19:55:52,<EFBFBD>Ļ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̼<EFBFBD>,cds***@bytedance.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʥ<EFBFBD><EFBFBD>ϵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѡһ3<EFBFBD>ο<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֪<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,12.31,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301)&֧<><D6A7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025041722001422381407178511 ,2001052504170101399721930850 ,,
2025-04-17 19:55:37,<EFBFBD>Ļ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>̼<EFBFBD>,cds***@bytedance.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѩ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʥ<EFBFBD><EFBFBD>ϵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѡһ3<EFBFBD>ο<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֪<EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,12.97,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025041722001422381408597715 ,2001052504170101400901930850 ,,
2025-04-17 05:59:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250417382899825381 , ,,
2025-04-16 09:02:28,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,244.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025041622001422381459713866 ,M20250416298601972 ,,
2025-04-16 04:01:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250416374499641381 , ,,
2025-04-15 03:10:52,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250415368364079381 , ,,
2025-04-14 23:01:01,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ͼ<EFBFBD>΢<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD>ƶ<EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025041422001422381452336884 ,12126600004802000039A250414610210508273471250 ,,
2025-04-14 21:17:54,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ͼ<EFBFBD>΢<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD>ƶ<EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,97.92,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9924)&<26>й<EFBFBD><D0B9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025041422001422381449980431 ,43126600004802000039A250414610148650227661220 ,,
2025-04-14 11:43:30,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,173******20,<EFBFBD><EFBFBD>Ƭ,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025041422001122381453241654 ,T200P4300345117610367849 ,,
2025-04-14 11:37:32,<EFBFBD>˿<EFBFBD>,t***6,173******20,<EFBFBD>˿<EFBFBD>-<2D><>Ƭ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025041422001122381453245314_4300593192077367849 ,T200P4300593192077367849 ,,
2025-04-14 11:35:33,<EFBFBD>˿<EFBFBD>,t***6,173******20,<EFBFBD>˿<EFBFBD>-<2D><>Ƭ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025041422001122381453225807_4300591248323367849 ,T200P4300591248323367849 ,,
2025-04-14 11:01:53,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,173******20,<EFBFBD><EFBFBD>Ƭ,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025041422001122381453245314 ,T200P4300593192077367849 ,,
2025-04-14 11:01:20,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,173******20,<EFBFBD><EFBFBD>Ƭ,֧<EFBFBD><EFBFBD>,2.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025041422001122381453225807 ,T200P4300591248323367849 ,,
2025-04-14 10:34:51,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ϻ<EFBFBD>**<2A><>,asl***@service.taobao.com,<EFBFBD><EFBFBD>Ʊ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{7965555900978|1_2_2025000348147343343},֧<EFBFBD><EFBFBD>,485.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025041422001122381452093535 ,T1400P4300580667428367849 ,,
2025-04-14 03:32:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250414363497793381 , ,,
2025-04-13 04:28:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250413358594360381 , ,,
2025-04-12 05:30:37,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250412354363495381 , ,,
2025-04-11 03:50:48,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250411348035212381 , ,,
2025-04-10 04:24:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250410342227115381 , ,,
2025-04-09 03:49:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250409336257650381 , ,,
2025-04-08 04:47:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250408331031742381 , ,,
2025-04-07 03:49:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250407325804318381 , ,,
2025-04-06 04:33:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250406320846154381 , ,,
2025-04-05 03:51:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250405315725115381 , ,,
2025-04-05 02:52:51,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ͼ<EFBFBD>΢<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD>ƶ<EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,100.00,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025040522001422381412426585 ,23126600004802000039A250405103615315933742770 ,,
2025-04-05 02:18:41,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ͼ<EFBFBD>΢<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD>ƶ<EFBFBD>֧<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,95.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(9683)&<26><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025040522001422381412300183 ,60126600004802000039A250405103613258530340770 ,,
2025-04-04 04:22:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250404310648628381 , ,,
2025-04-03 03:55:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250403305339574381 , ,,
2025-04-02 03:19:26,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.04.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250402399272127381 , ,,
2025-04-01 03:35:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.31-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.05,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250401393645123381 , ,,
2025-03-31 09:05:04,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,96.75,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(1074)&<26>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025033100003001380039156119 ,5100398784953 ,,
2025-03-31 03:51:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250331388662815381 , ,,
2025-03-30 03:35:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250330383944464381 , ,,
2025-03-29 03:59:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250329379104764381 , ,,
2025-03-28 03:26:12,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250328373449578381 , ,,
2025-03-27 04:04:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250327368689259381 , ,,
2025-03-26 03:31:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250326362175344381 , ,,
2025-03-25 04:21:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250325357329279381 , ,,
2025-03-24 04:15:28,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250324351488769381 , ,,
2025-03-23 04:26:41,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250323346615175381 , ,,
2025-03-22 03:13:15,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250322340725049381 , ,,
2025-03-21 03:16:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250321334904832381 , ,,
2025-03-20 04:25:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250320329108584381 , ,,
2025-03-19 04:03:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250319323991428381 , ,,
2025-03-18 04:20:41,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250318319030253381 , ,,
2025-03-17 02:30:36,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250317312380117381 , ,,
2025-03-16 03:21:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250316304252520381 , ,,
2025-03-15 03:59:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250315301742125381 , ,,
2025-03-14 03:59:43,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250314392368918381 , ,,
2025-03-13 03:23:34,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250313391149705381 , ,,
2025-03-13 01:07:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,30.52,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250313019130101000380048089984 ,20250313009130501000380052503275 ,,
2025-03-12 16:13:22,<EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϣ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,xys***@service.aliyun.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>-<2D><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(4214286182805564629)<29>ۿ<EFBFBD>,֧<EFBFBD><EFBFBD>,0.18,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025031210032004750274056580 , ,,
2025-03-12 04:06:37,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250312385333443381 , ,,
2025-03-11 21:44:30,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,С***6,298***@qq.com,ȫ<EFBFBD><EFBFBD>DB˫<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧<EFBFBD><EFBFBD>ƻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>汾<EFBFBD>ֻ<EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD><EFBFBD>5G<EFBFBD><EFBFBD>ѹ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,68.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025031123001122381426705452 ,T200P4261626757893367849 ,,
2025-03-11 20:30:24,<EFBFBD>˿<EFBFBD>,<EFBFBD><EFBFBD>***0,186******03,<EFBFBD>˿<EFBFBD>-DB<44><42><EFBFBD>¿<EFBFBD><C2BF><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ģʽ <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD><CBAB>5G û<><C3BB><EFBFBD>鷳<EFBFBD>IJ<EFBFBD><C4B2><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,77.00,Mastercard(0476),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025030923001122381414815283_4258932949961367849 ,T200P4258932949961367849 ,,
2025-03-11 03:38:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250311380443675381 , ,,
2025-03-10 03:43:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250310375027489381 , ,,
2025-03-09 13:09:33,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD><EFBFBD>***0,186******03,DB<EFBFBD><EFBFBD><EFBFBD>¿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ģʽ <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˫<EFBFBD><CBAB>5G û<><C3BB><EFBFBD>鷳<EFBFBD>IJ<EFBFBD><C4B2><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,77.00,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025030923001122381414815283 ,T200P4258932949961367849 ,,
2025-03-09 02:45:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250309368887613381 , ,,
2025-03-08 05:14:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250308364433130381 , ,,
2025-03-07 03:43:34,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250307357963406381 , ,,
2025-03-06 14:53:18,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,508.05,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025030600003001380037010006 , ,,
2025-03-06 04:12:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250306350137363381 , ,,
2025-03-05 03:35:51,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250305344507326381 , ,,
2025-03-04 20:39:12,<EFBFBD>˶<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ź<EFBFBD><EFBFBD><EFBFBD><EFBFBD>е綯<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ӫ<EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ź<EFBFBD><EFBFBD><EFBFBD><EFBFBD>е綯<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ӫ<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,4699.83,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301)&<26><><EFBFBD><EFBFBD>ɨ<EFBFBD><C9A8><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025030422001422381454730764 ,561266000048180000T6665635659250304203912588001 ,,
2025-03-04 05:22:27,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250304339047126381 , ,,
2025-03-03 02:34:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250303329478603381 , ,,
2025-03-02 11:32:35,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,649.62,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025030200003001380036282124 , ,,
2025-03-02 03:51:39,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.03.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250302326972354381 , ,,
2025-03-01 21:34:46,ĸӤ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ȱ<EFBFBD>**<2A><>,nin***@163.com,bebetour<EFBFBD>ʼұ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>װֽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ<EFBFBD><EFBFBD><EFBFBD>㳬<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Яװ4Ƭ,֧<EFBFBD><EFBFBD>,0.90,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025030123001122381445140579 ,T200P4249463977002367849 ,,
2025-03-01 04:22:49,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250301322776406381 , ,,
2025-02-28 04:35:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250228317608363381 , ,,
2025-02-27 03:18:38,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.26-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250227308581205381 , ,,
2025-02-26 03:09:24,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.25-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250226305765743381 , ,,
2025-02-25 22:23:28,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,20.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022522001422381429426039 ,47404934080112300022388 ,,
2025-02-25 22:22:33,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,100.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022522001422381429426038 ,47404933532112300022388 ,,
2025-02-25 22:18:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022522001422381430805203 ,47404931299112300022388 ,,
2025-02-25 03:14:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.24-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250225300616953381 , ,,
2025-02-24 22:39:55,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>ɶ<EFBFBD><EFBFBD>츮<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>˾,/,ȼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>-<2D><><EFBFBD><EFBFBD>****<2A><>,֧<EFBFBD><EFBFBD>,200.00,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022400003001380035690150 ,650706779 ,,
2025-02-24 22:39:24,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>ɶ<EFBFBD><EFBFBD>츮<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>˾,/,ȼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>-<2D><><EFBFBD><EFBFBD>****<2A><>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,37.62,,<EFBFBD>ѹر<EFBFBD>,2025022400003001380035685302 ,650706779 ,,
2025-02-24 22:38:23,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,540.86,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025022400003001380035681128 , ,,
2025-02-24 22:32:30,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,199.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022422001422381427924669 ,47404075506112300022388 ,,
2025-02-24 22:29:46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,198.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022422001422381427914430 ,47404073861112300022388 ,,
2025-02-24 22:27:16,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022422001422381427912971 ,47404072358112300022388 ,,
2025-02-24 22:26:51,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022422001422381427656777 ,47404072112112300022388 ,,
2025-02-24 22:24:45,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022422001422381427197699 ,47404070853112300022388 ,,
2025-02-24 22:23:26,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,198.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022422001422381427918735 ,47404070062112300022388 ,,
2025-02-24 10:17:13,<EFBFBD><EFBFBD><EFBFBD>ý軹,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,108.62,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(1074)&<26>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025022400003001380035623528 , ,,
2025-02-24 04:10:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.23-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250224394922078381 , ,,
2025-02-24 00:51:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,219.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250224019130101000380031332923 ,20250224009130501000380030849135 ,,
2025-02-23 21:50:31,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,*<2A><>,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,199.00,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022322001433151449379546 ,47403186309332323333155 ,,
2025-02-23 21:44:56,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,*<2A><>,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,20.00,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022322001433151446566795 ,47403182961332323333155 ,,
2025-02-23 21:18:51,<EFBFBD>˿<EFBFBD>,t***6,187******16,<EFBFBD>˿<EFBFBD>-<2D><>˶TUF GAMING B460M PLUS<55><53><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,188.00,Mastercard(8736),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025022323001122381422509391_4242158571292367849 ,T200P4242158571292367849 ,,
2025-02-23 21:13:53,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,x***0,150******08,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>b460m mortar<61><72><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,177.32,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022323001122381423166868 ,T200P4242468240550367849 ,,
2025-02-23 18:30:38,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD>ؾ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,138******76,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,20.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022322001422381423979430 ,17403066384112300022388 ,,
2025-02-23 14:28:15,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***6,187******16,<EFBFBD><EFBFBD>˶TUF GAMING B460M PLUS<55><53><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,188.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025022323001122381422509391 ,T200P4242158571292367849 ,,
2025-02-23 10:17:10,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,t***3,199******56,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Tiny5 tiny4 M910x M720q,֧<EFBFBD><EFBFBD>,26.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022323001122381422511100 ,T200P4241706372341367849 ,,
2025-02-23 03:25:41,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.22-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250223389430034381 , ,,
2025-02-22 13:27:25,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022222001422381418250421 ,47402020448112300022388 ,,
2025-02-22 13:26:12,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022222001422381418272602 ,47402019722112300022388 ,,
2025-02-22 13:24:46,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022222001422381418661984 ,47402018864112300022388 ,,
2025-02-22 13:23:32,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022222001422381418238037 ,47402018125112300022388 ,,
2025-02-22 13:21:54,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022222001422381418362760 ,47402017139112300022388 ,,
2025-02-22 13:20:41,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025022222001422381418234695 ,47402016410112300022388 ,,
2025-02-22 03:21:31,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.21-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250222384252236381 , ,,
2025-02-21 04:07:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.20-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250221379512308381 , ,,
2025-02-20 03:12:52,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.19-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250220368684665381 , ,,
2025-02-19 02:57:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.18-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250219365289236381 , ,,
2025-02-18 04:11:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.17-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250218362386590381 , ,,
2025-02-17 02:30:22,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.16-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250217356196377381 , ,,
2025-02-16 13:14:47,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025021622001422381453970417 ,47396828876112300022388 ,,
2025-02-16 13:12:45,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025021622001422381453758589 ,47396827655112300022388 ,,
2025-02-16 13:11:57,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025021622001422381453883650 ,47396827172112300022388 ,,
2025-02-16 13:10:36,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025021622001422381452936521 ,47396826365112300022388 ,,
2025-02-16 04:20:16,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.15-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250216351182170381 , ,,
2025-02-15 03:03:21,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.14-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250215345841337381 , ,,
2025-02-14 04:02:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.13-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250214341466891381 , ,,
2025-02-13 02:54:23,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.12-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250213335163035381 , ,,
2025-02-12 04:11:46,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.11-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250212330794201381 , ,,
2025-02-11 03:41:41,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.10-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250211325700665381 , ,,
2025-02-10 03:46:19,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.09-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250210320078131381 , ,,
2025-02-09 04:02:33,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.08-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250209314711809381 , ,,
2025-02-08 19:30:50,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>ɶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,shh***@163.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>決 ȫ<><C8AB><EFBFBD><EFBFBD><C2B6><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> 110g,֧<EFBFBD><EFBFBD>,13.80,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020823001422381425818069 ,P18M6666031250208342467367849 ,,
2025-02-08 10:31:54,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,7.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381422226758 ,9712660000483100009975643144697912287232 ,,
2025-02-08 10:29:43,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381422466169 ,3112660000483100009971643144149770940416 ,,
2025-02-08 10:29:15,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381423881246 ,0912660000483100009918643144032997662720 ,,
2025-02-08 10:27:53,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381424721358 ,7012660000483100009945643143689823723520 ,,
2025-02-08 10:26:34,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,200.00,,<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025020822001422381423584279 ,6112660000483100009935643143358607925248 ,,
2025-02-08 10:26:03,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381422807006 ,5612660000483100009955643143226302640128 ,,
2025-02-08 10:24:06,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381422988871 ,2112660000483100009944643142735078678528 ,,
2025-02-08 10:18:43,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381424560169 ,9812660000483100009950643141380540604416 ,,
2025-02-08 10:18:12,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381424684713 ,0212660000483100009948643141250164699136 ,,
2025-02-08 10:17:12,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381424585899 ,2212660000483100009979643141002168426496 ,,
2025-02-08 10:16:37,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381424585898 ,3912660000483100009940643140853253857280 ,,
2025-02-08 10:15:51,ס<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ҵ,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD><EFBFBD><EFBFBD>ҵ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ϸ<EFBFBD>-<2D>ɶ<EFBFBD><C9B6><EFBFBD><EFBFBD>ø<EFBFBD><C3B8><EFBFBD>4<EFBFBD><34>1<EFBFBD><31>Ԫ1304<30><34>,֧<EFBFBD><EFBFBD>,200.00,Mastercard(1756),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020822001422381423804742 ,3212660000483100009956643140658575056896 ,,
2025-02-08 03:14:11,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.07-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.03,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250208309407088381 , ,,
2025-02-07 21:20:06,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ߵ´<EFBFBD><EFBFBD><EFBFBD>,aut***@autonavi.com,<EFBFBD>ߵ´򳵶<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,17.14,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020723001422381422756897 ,0001N202502070000000009612974583 ,,
2025-02-07 04:16:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.06-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250207305080956381 , ,,
2025-02-06 21:16:05,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,z97***@service.aliyun.com,Ϊ19267221762<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,100.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020622001422381419223587 ,2025020600003100003838604563 ,,
2025-02-06 21:14:22,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,z97***@service.aliyun.com,Ϊ19267221762<EFBFBD><EFBFBD><EFBFBD>ѳ<EFBFBD>ֵ,֧<EFBFBD><EFBFBD>,100.00,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020622001422381420529027 ,2025020600003100003838599588 ,,
2025-02-06 10:56:27,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,c***8,135******67,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>6<EFBFBD><EFBFBD>7<EFBFBD><EFBFBD><EFBFBD><EFBFBD> M910X <20><>ѹ<EFBFBD><D1B9> <20><><EFBFBD><EFBFBD>С<EFBFBD><D0A1><EFBFBD><EFBFBD>׼ϵͳ b,֧<EFBFBD><EFBFBD>,370.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020623001122381415545642 ,T200P4222333621116367849 ,,
2025-02-06 05:27:30,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.05-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250206300081951381 , ,,
2025-02-05 22:15:37,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD><EFBFBD>Ʊ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,161.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025020522001422381414961470_M20250205230778108 ,M20250205230598085 ,,
2025-02-05 22:15:17,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,153.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020522001422381415184556 ,M20250205230769494 ,,
2025-02-05 21:59:24,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,161.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׹ر<EFBFBD>,2025020522001422381414961470 ,M20250205230598085 ,,
2025-02-05 15:53:28,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,554.10,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025020500003001380033534385 , ,,
2025-02-05 03:14:35,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.04-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250205394490427381 , ,,
2025-02-04 02:33:49,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.03-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250204386164620381 , ,,
2025-02-03 04:15:44,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.02-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250203386278218381 , ,,
2025-02-02 03:34:42,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.02.01-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250202380819136381 , ,,
2025-02-01 11:38:52,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ߵ´<EFBFBD><EFBFBD><EFBFBD>,aut***@autonavi.com,<EFBFBD>ߵ´򳵶<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,41.14,Mastercard(8736),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025020123001422381400090382 ,0001N202502010000000009564290543 ,,
2025-02-01 03:40:47,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.01.31-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250201376652184381 , ,,
2025-01-31 12:32:38,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,197.71,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025013100003001380032860811 , ,,
2025-01-31 03:15:13,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.01.30-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250131371108861381 , ,,
2025-01-30 05:06:20,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.01.29-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250130368334806381 , ,,
2025-01-29 15:16:30,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>̴<EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD>POS<EFBFBD><EFBFBD>_<EFBFBD>츮<EFBFBD>㳡<EFBFBD><EFBFBD>_141259_1000288_<EFBFBD><EFBFBD>_<EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,18.75,Mastercard(0476)&<26><>һ<EFBFBD><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025012923001422381449942804 ,391266000048180000154649137522125012915163015437 ,,
2025-01-29 12:17:50,<EFBFBD><EFBFBD><EFBFBD>ý軹,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,202.27,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025012900003001380032766601 , ,,
2025-01-29 03:48:29,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.01.28-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250129363559449381 , ,,
2025-01-28 03:17:40,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>̩<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,/,<EFBFBD><EFBFBD><EFBFBD>-2025.01.27-<2D><><EFBFBD>淢<EFBFBD><E6B7A2>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,0.04,<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250128358805911381 , ,,
2025-01-27 18:13:59,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ѵ,С¹,173******20,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,5.00,Visa(2752),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025012722001422381444493525 ,17379728396112300022388 ,,
2025-01-27 14:59:31,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˳<EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>˳<EFBFBD>,֧<EFBFBD><EFBFBD>,4.10,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025012723001422381442704896 ,322017092208872157440205003488000022501270449896 ,,
2025-01-26 17:50:19,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,<EFBFBD><EFBFBD>***9,136******49,ȫ<EFBFBD><EFBFBD>ӰʯInsta360 Flow Pro AI<41>ֻ<EFBFBD><D6BB>ȶ<EFBFBD><C8B6><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,407.50,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(1074)&<26>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025012623001122381440895863 ,T200P4216523691560367849 ,,
2025-01-24 01:22:05,Ͷ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>,zfb***@gtfund.com,<EFBFBD><EFBFBD><EFBFBD>-<2D>Զ<EFBFBD>ת<EFBFBD><D7AA>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,1000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250124019130101000380098582185 ,20250124009130501000380090198448 ,,
2025-01-23 14:53:21,<EFBFBD><EFBFBD><EFBFBD>ý軹,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,109.74,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɹ<EFBFBD>,2025012300003001380032281914 , ,,
2025-01-23 13:11:15,ת<EFBFBD>˺<EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,173******20,<EFBFBD><EFBFBD>˵<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>dzԷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,1000.00,<EFBFBD>˻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,20250123200040011100150078423041 , ,,
2025-01-23 12:40:00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,****b,153******06,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20><><EFBFBD><EFBFBD> <20>ķ<EFBFBD><C4B7><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,30.70,,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025012322001148751408938508 ,T200P4214286182805564629 ,,
2025-01-20 16:55:30,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>**,223***@qq.com,<EFBFBD><EFBFBD>Idea<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>漤<EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֱ<EFBFBD>Ӽ<EFBFBD><EFBFBD><EFBFBD> idea<65><61><EFBFBD>Ѳ<EFBFBD><D1B2><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> ֧<>ֶ<EFBFBD><D6B6>豸,֧<EFBFBD><EFBFBD>,23.88,<EFBFBD>й<EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(9924)&<26>й<EFBFBD><D0B9><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025012023001122381420082252 ,T200P4211332921504367849 ,,
2025-01-19 02:36:08,<EFBFBD>Ƶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>㽭<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>缼<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,q-a***@service.taobao.com,<EFBFBD><EFBFBD>Ʊ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ż<EFBFBD>-δ<><CEB4><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ۻ<EFBFBD><DBBB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ż<EFBFBD>,֧<EFBFBD><EFBFBD>,30.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011922001122381410705303 ,T200P4209608304830367849 ,,
2025-01-17 21:31:48,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>**x,131******06,<EFBFBD><EFBFBD><EFBFBD>õ<EFBFBD><EFBFBD><EFBFBD>12ƻ<EFBFBD><EFBFBD>iPhoneX<EFBFBD><EFBFBD><EFBFBD><EFBFBD>11ԭװXR/13/6s<36><73>Ʒ8p/7plusԭ<73><D4AD>XsMax,֧<EFBFBD><EFBFBD>,45.16,ƽ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7571)&ƽ<><C6BD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD><C3BF><EFBFBD><EFBFBD>ֵֿ<D6B5>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011723001122381407989440 ,T200P4208137992734367849 ,,
2025-01-17 21:27:45,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ʒ<EFBFBD>**1,953***@qq.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ƻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ļ iPhone11ԭװ<D4AD><D7B0><EFBFBD><EFBFBD><EFBFBD><EFBFBD> XS<58><53><EFBFBD><EFBFBD><EFBFBD><EFBFBD>XR XSMԭ<4D><D4AD>11P12P,֧<EFBFBD><EFBFBD>,253.00,<EFBFBD>ַ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8676)&<26>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011723001122381408035222 ,T200P4208308850354367849 ,,
2025-01-16 19:40:21,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD>񶼻<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,/,<EFBFBD>츮<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɶ<EFBFBD>Ƭ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ<EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,42.53,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011623001422381406562609 ,8320171129002506942025011619402100069057874 ,,
2025-01-14 19:29:03,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,ɰ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,134******43,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,13.00,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011422001422381458124301 ,17368541428112300022388 ,,
2025-01-14 18:58:02,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʳ,<EFBFBD><EFBFBD><EFBFBD>ؾ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,138******76,<EFBFBD><EFBFBD>Ǯ<EFBFBD><EFBFBD><EFBFBD>տ<EFBFBD>,֧<EFBFBD><EFBFBD>,20.00,Mastercard(0476),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011422001422381459368453 ,17368522824112300022388 ,,
2025-01-14 08:05:15,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD>˿<EFBFBD>-<2D><><EFBFBD><EFBFBD>Ʊ,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֧,22.87,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8050)&<26>Ż<EFBFBD>,<EFBFBD>˿<EFBFBD><EFBFBD>ɹ<EFBFBD>,2025011322001422381455533744_M20250114273884243 ,M20250113269656475 ,,
2025-01-13 20:01:30,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>·12306,chi***@alipay.com,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ʊ,֧<EFBFBD><EFBFBD>,530.92,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(8050)&<26><>ͨ<EFBFBD><CDA8><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011322001422381455533744 ,M20250113269656475 ,,
2025-01-10 11:53:01,<EFBFBD><EFBFBD>ֵ<EFBFBD>ɷ<EFBFBD>,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ɶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>繫˾,/,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,100.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(7049),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025011000003001380031032736 ,5100398784953 ,,
2025-01-08 15:08:35,<EFBFBD><EFBFBD><EFBFBD>ðٻ<EFBFBD>,׷***<2A><>,185******73,USIMȫ<EFBFBD>Զ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> <20><><EFBFBD><EFBFBD>QPE<50>Զ<EFBFBD><D4B6><EFBFBD><EFBFBD><EFBFBD> <20>ȶ<EFBFBD><C8B6><EFBFBD><EFBFBD><EFBFBD>,֧<EFBFBD><EFBFBD>,18.66,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>д<EFBFBD><EFBFBD>(4301),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010823001122381437115016 ,T200P4195969957326367849 ,,
2025-01-07 16:31:00,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ɶ<EFBFBD><EFBFBD>츮ͨ<EFBFBD><EFBFBD><EFBFBD>ֿƼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,tft***@cdtft.cn,<EFBFBD>ɶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(˫<><CBAB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>2<EFBFBD><32>վ¥2025-01-07 15:47:09--<2D>ĺ<EFBFBD>2025-01-07 16:30:53),֧<EFBFBD><EFBFBD>,6.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010722001422381432268684 ,3121881243204608 ,,
2025-01-06 23:02:09,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ּ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,dom***@metrofastpass.com,<EFBFBD>Ͼ<EFBFBD><EFBFBD><EFBFBD>·-<2D><>ɳ,֧<EFBFBD><EFBFBD>,5.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010622001422381430264812 ,20250106230208337023083205321826 ,,
2025-01-06 21:24:46,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ּ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,dom***@metrofastpass.com,<EFBFBD><EFBFBD>ɽ<EFBFBD><EFBFBD>԰-<2D>Ͼ<EFBFBD><CFBE><EFBFBD>·,֧<EFBFBD><EFBFBD>,4.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010622001422381428268837 ,20250106212444461072033222215568 ,,
2025-01-06 17:31:02,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ּ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,dom***@metrofastpass.com,<EFBFBD>Ͼ<EFBFBD><EFBFBD><EFBFBD>·-<2D><>ɽ<EFBFBD><C9BD>԰,֧<EFBFBD><EFBFBD>,4.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010622001422381429053665 ,20250106173101339072033227022726 ,,
2025-01-06 16:17:03,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>Ϻ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ּ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,dom***@metrofastpass.com,<EFBFBD><EFBFBD><EFBFBD>Ż<EFBFBD><EFBFBD><EFBFBD>վ-<2D>Ͼ<EFBFBD><CFBE><EFBFBD>·,֧<EFBFBD><EFBFBD>,5.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010622001422381429745309 ,20250106161702581072033187617252 ,,
2025-01-06 12:12:25,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾<EFBFBD><EFBFBD>Ӫ<EFBFBD>ֹ<EFBFBD>˾,sun***@ntrailway.com,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><><EFBFBD>ʹ<EFBFBD><CDB4><EFBFBD>2025-01-06 11:33:06--<2D><><EFBFBD><EFBFBD>2025-01-06 12:12:24),֧<EFBFBD><EFBFBD>,3.80,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010622001422381428471580 ,T000013840107250106113306140735 ,,
2025-01-02 16:55:29,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾<EFBFBD><EFBFBD>Ӫ<EFBFBD>ֹ<EFBFBD>˾,sun***@ntrailway.com,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28><>ͨ<EFBFBD><CDA8>վ2025-01-02 16:04:07--ͼ<><CDBC><EFBFBD><EFBFBD>2025-01-02 16:55:20),֧<EFBFBD><EFBFBD>,5.70,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010222001422381416548439 ,T000012240122250102160407131695 ,,
2025-01-02 08:52:05,<EFBFBD><EFBFBD>ͨ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>,<EFBFBD>ɶ<EFBFBD><EFBFBD>츮ͨ<EFBFBD><EFBFBD><EFBFBD>ֿƼ<EFBFBD><EFBFBD><EFBFBD><EFBFBD>޹<EFBFBD>˾,tft***@cdtft.cn,<EFBFBD>ɶ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>(<28>ĺ<EFBFBD>2025-01-02 08:09:02--˫<><CBAB><EFBFBD><EFBFBD><EFBFBD><EFBFBD>2<EFBFBD><32>վ¥2025-01-02 08:51:57),֧<EFBFBD><EFBFBD>,6.00,<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ÿ<EFBFBD>(0634),<EFBFBD><EFBFBD><EFBFBD>׳ɹ<EFBFBD>,2025010222001422381413852396 ,3106823176990720 ,,
Can't render this file because it has a wrong number of fields in line 25.

BIN
17-ProjectMoneyX/2-概要详细设计/支付宝交易明细(20250101-20251231).xlsx Normal file
View File

Binary file not shown.

Some files were not shown because too many files have changed in this diff Show More