完整的工具包，从AI编码助手中提取所有聊天、代理和代码上下文数据，用于机器学习训练。

🎯 这会带来什么

自动发现并提取完整的对话历史，包括：

• ✅ 用户消息与AI响应
• ✅ 代码上下文（文件路径、行号、片段）
• ✅ 代码差异及建议编辑
• ✅ 多文件上下文
• ✅ 工具使用与执行结果
• ✅ 时间戳和元数据

Pi和OMP会话导出使用一个共享解析器。默认解析器紧随激活解析器 分支;python3 extract_pi.py --all-branches 和 python3 extract_omp.py --all-branches 导出带有祖先和分支ID的单独叶对话。字符串 答案、自定义上下文、推理、工具调用ID、模型变更、顾问/子代理 会话和分支摘要被保留。OMP 还支持 --prompt-history 用于单独的只读 SQLite 快照，包括已提交的 WAL 行。

extract_droid.py 读取 ~/.factory/sessions 下的工厂/机器人会话和设置。 聚合脚本包含这三种。解析器合并包含 PR #26的Pi/OMP工作，#17的Joshua Warren的OMP报道，以及Umang Bhalla的

AI Coding Assistant Training Data Extraction Toolkit

Complete toolkit to extract ALL chat, agent, and code context data from AI coding assistants for machine learning training.

🎯 What This Does

Automatically discovers and extracts complete conversation history including:

• ✅ User messages & AI responses
• ✅ Code context (file paths, line numbers, snippets)
• ✅ Code diffs and suggested edits
• ✅ Multi-file contexts
• ✅ Tool use and execution results
• ✅ Timestamps and metadata

Pi and OMP session exports use one shared parser. The default follows the active branch; python3 extract_pi.py --all-branches and python3 extract_omp.py --all-branches export separate leaf conversations with their ancestry and branch IDs. String answers, custom context, reasoning, tool-call IDs, model changes, advisor/subagent sessions and branch summaries are preserved. OMP also supports --prompt-history for a separate read-only SQLite snapshot, including committed WAL rows.

extract_droid.py reads Factory/Droid sessions and settings under ~/.factory/sessions. The aggregate script includes all three. The parser consolidation carries the Pi/OMP work from PR #26, Joshua Warren’s OMP coverage from #17 and Umang Bhalla’s Droid contribution from #7, with regression fixes and attribution.

📦 Included Scripts

1. extract_claude_code.py

Extracts from Claude Code / Claude Desktop

• Searches: ~/.claude, ~/.claude-code, ~/.claude-local, ~/.claude-m2, ~/.claude-zai
• Formats: JSONL session files
• Includes: Messages, tool use, file contexts, diffs

2. extract_codex.py

Extracts from Codex (if installed)

• Searches: ~/.codex, ~/.codex-local
• Formats: Rollout JSONL files
• Includes: User/agent messages, tool results, diffs

3. extract_cursor.py

Extracts from Cursor (Chat + Composer + Agent) - ALL VERSIONS

• Searches: ~/Library/Application Support/Cursor (macOS) or equivalent
• Formats: SQLite databases (state.vscdb, cursorDiskKV)
• Handles:
  • Old Chat mode (workspace storage)
  • Composer inline storage (v1.x - messages in composerData array)
  • Composer separate storage (v1.x-v2.0 transition - messages in bubbleId keys)
  • Latest Composer/Agent (v2.0+)
• Includes:
  • Code context, selections, diffs
  • Suggested edits and code blocks
  • Tool results and execution outputs

4. extract_trae.py

Extracts from Trae

• Searches: ~/.trae, ~/Library/Application Support/Trae
• Formats: JSONL and SQLite databases
• Includes: Chat, agent data, tool use, diffs

5. extract_windsurf.py

Extracts from Windsurf

• Searches: ~/Library/Application Support/Windsurf or equivalent
• Formats: SQLite databases (VSCode-like format)
• Includes: Chat, agent/flow conversations, code context

6. extract_continue.py

Extracts from Continue AI Assistant

• Searches: ~/.continue/sessions/
• Formats: JSON session files
• Includes: