From b98d35c387e4a1f9e62bc43ddb14153ad7460138 Mon Sep 17 00:00:00 2001 From: Zhengshou Lai Date: Mon, 6 Apr 2026 13:11:10 +0800 Subject: [PATCH] feat: add mybot CLI with update, chat, and Claude project config - Click entrypoint: mybot update (make install / pip -e), mybot chat (claude in repo) - Optional --dangerously-skip-permissions for Claude Code - Makefile install; hatchling package layout - .gitignore: venv, build artifacts, workspace (local symlinks) Made-with: Cursor --- .claude/README.md | 125 ++ .claude/agent/agent_worker.py | 172 +++ .claude/agent/results/acfa3103.json | 9 + .claude/agent/tasks.jsonl | 2 + .claude/agent/worker.py | 149 ++ .claude/conversations/2026-04-05.md | 204 +++ .claude/conversations/2026-04-06.md | 714 +++++++++ .claude/insights/.gitkeep | 1 + .claude/memories/core.json | 54 + .claude/memories/current_mode.json | 11 + .claude/plans/web-platform.md | 346 +++++ .claude/plans/web-ui-redesign.md | 118 ++ .claude/sessions/.gitkeep | 1 + .claude/settings.local.json | 135 ++ .claude/skills/architecture.md | 42 + .claude/skills/coding.md | 46 + .claude/skills/cv-update/SKILL.md | 62 + .claude/skills/debugging.md | 42 + .claude/skills/doubao-tts/SKILL.md | 126 ++ .claude/skills/frontend-design/SKILL.md | 41 + .claude/skills/skill-creator/LICENSE.txt | 202 +++ .claude/skills/skill-creator/SKILL.md | 485 ++++++ .../skills/skill-creator/agents/analyzer.md | 274 ++++ .../skills/skill-creator/agents/comparator.md | 202 +++ .claude/skills/skill-creator/agents/grader.md | 223 +++ .../skill-creator/assets/eval_review.html | 146 ++ .../eval-viewer/generate_review.py | 471 ++++++ .../skill-creator/eval-viewer/viewer.html | 1325 +++++++++++++++++ .../skill-creator/references/schemas.md | 430 ++++++ .../skills/skill-creator/scripts/__init__.py | 0 .../scripts/aggregate_benchmark.py | 401 +++++ .../skill-creator/scripts/generate_report.py | 326 ++++ .../scripts/improve_description.py | 247 +++ .../skill-creator/scripts/package_skill.py | 136 ++ .../skill-creator/scripts/quick_validate.py | 103 ++ .../skills/skill-creator/scripts/run_eval.py | 310 ++++ .../skills/skill-creator/scripts/run_loop.py | 328 ++++ .claude/skills/skill-creator/scripts/utils.py | 47 + .claude/skills/skills-sync/SKILL.md | 48 + .claude/skills/sync-global.sh | 19 + .claude/skills/todo/SKILL.md | 30 + .claude/souls/collaborator.md | 39 + .claude/souls/expert.md | 38 + .claude/souls/mentor.md | 40 + .claude/todo/README.md | 108 ++ .../20260405/cmd_20260405_124946_752279.json | 15 + .../20260405/cmd_20260405_124946_752510.json | 15 + .../20260405/cmd_20260405_124946_752659.json | 15 + .../20260405/cmd_20260405_125001_887647.json | 8 + .../20260405/cmd_20260405_125115_736683.json | 13 + .../20260405/cmd_20260405_125115_736891.json | 15 + .../20260405/cmd_20260405_125151_440893.json | 8 + .../20260405/cmd_20260405_125230_232997.json | 13 + .../20260405/cmd_20260405_125342_933697.json | 15 + .../20260405/cmd_20260405_125342_933972.json | 15 + .../20260405/cmd_20260405_125810_497416.json | 12 + .../20260405/cmd_20260405_125812_522150.json | 8 + .../20260405/cmd_20260405_125815_602478.json | 16 + .../20260405/cmd_20260405_125847_739141.json | 8 + .../20260405/cmd_20260405_125848_800418.json | 16 + .../20260405/cmd_20260405_125858_011314.json | 8 + .../20260405/cmd_20260405_125900_778492.json | 16 + .../20260405/cmd_20260405_125912_868623.json | 16 + .../20260405/cmd_20260405_125926_100277.json | 14 + .../20260405/cmd_20260405_125928_048340.json | 15 + .../20260405/cmd_20260405_125943_026380.json | 8 + .../20260405/cmd_20260405_125943_135034.json | 8 + .../20260405/cmd_20260405_130503_486633.json | 15 + .../20260405/cmd_20260405_130644_974174.json | 8 + .../20260405/cmd_20260405_130644_974376.json | 8 + .../20260405/cmd_20260405_130644_974500.json | 8 + .../20260405/cmd_20260405_130644_974613.json | 8 + .../20260405/cmd_20260405_130723_543950.json | 16 + .../20260405/cmd_20260405_130723_544259.json | 16 + .../20260405/cmd_20260405_130747_317460.json | 8 + .../20260405/cmd_20260405_144429_536707.json | 8 + .../outbox/rsp_20260405_124949_976287.json | 24 + .../outbox/rsp_20260405_124949_976930.json | 24 + .../outbox/rsp_20260405_124949_977415.json | 24 + .../outbox/rsp_20260405_125015_276639.json | 24 + .../outbox/rsp_20260405_125118_021142.json | 22 + .../outbox/rsp_20260405_125118_022859.json | 24 + .../outbox/rsp_20260405_125154_943854.json | 10 + .../outbox/rsp_20260405_125231_909676.json | 22 + .../outbox/rsp_20260405_125343_788360.json | 24 + .../outbox/rsp_20260405_125343_790144.json | 24 + .../outbox/rsp_20260405_125812_518954.json | 19 + .../outbox/rsp_20260405_125815_524488.json | 23 + .../outbox/rsp_20260405_125818_530505.json | 27 + .../outbox/rsp_20260405_125848_749166.json | 23 + .../outbox/rsp_20260405_125851_756537.json | 27 + .../outbox/rsp_20260405_125900_773186.json | 23 + .../outbox/rsp_20260405_125903_915427.json | 34 + .../outbox/rsp_20260405_125912_929508.json | 13 + .../outbox/rsp_20260405_125928_044538.json | 13 + .../outbox/rsp_20260405_125931_053904.json | 13 + .../outbox/rsp_20260405_125943_072987.json | 24 + .../outbox/rsp_20260405_125946_079936.json | 24 + .../outbox/rsp_20260405_130505_791878.json | 24 + .../outbox/rsp_20260405_130729_384474.json | 8 + .../outbox/rsp_20260405_130729_384891.json | 8 + .../outbox/rsp_20260405_130729_385194.json | 8 + .../outbox/rsp_20260405_130729_385480.json | 8 + .../outbox/rsp_20260405_130729_386114.json | 25 + .../outbox/rsp_20260405_130729_386755.json | 25 + .../outbox/rsp_20260405_144717_728188.json | 25 + .../outbox/rsp_20260405_144717_728600.json | 8 + .claude/todo/state/agent.log | 115 ++ .claude/todo/state/heartbeat.json | 5 + .claude/todo/state/tasks.json | 91 ++ .gitignore | 7 + CLAUDE.md | 110 ++ Makefile | 15 + mybot/__init__.py | 1 + mybot/__main__.py | 3 + mybot/cli.py | 32 + mybot/commands/__init__.py | 6 + mybot/commands/chat.py | 62 + mybot/commands/update.py | 54 + mybot/project_root.py | 56 + pyproject.toml | 31 + 121 files changed, 9962 insertions(+) create mode 100644 .claude/README.md create mode 100755 .claude/agent/agent_worker.py create mode 100644 .claude/agent/results/acfa3103.json create mode 100644 .claude/agent/tasks.jsonl create mode 100644 .claude/agent/worker.py create mode 100644 .claude/conversations/2026-04-05.md create mode 100644 .claude/conversations/2026-04-06.md create mode 100644 .claude/insights/.gitkeep create mode 100644 .claude/memories/core.json create mode 100644 .claude/memories/current_mode.json create mode 100644 .claude/plans/web-platform.md create mode 100644 .claude/plans/web-ui-redesign.md create mode 100644 .claude/sessions/.gitkeep create mode 100644 .claude/settings.local.json create mode 100644 .claude/skills/architecture.md create mode 100644 .claude/skills/coding.md create mode 100644 .claude/skills/cv-update/SKILL.md create mode 100644 .claude/skills/debugging.md create mode 100644 .claude/skills/doubao-tts/SKILL.md create mode 100644 .claude/skills/frontend-design/SKILL.md create mode 100644 .claude/skills/skill-creator/LICENSE.txt create mode 100644 .claude/skills/skill-creator/SKILL.md create mode 100644 .claude/skills/skill-creator/agents/analyzer.md create mode 100644 .claude/skills/skill-creator/agents/comparator.md create mode 100644 .claude/skills/skill-creator/agents/grader.md create mode 100644 .claude/skills/skill-creator/assets/eval_review.html create mode 100644 .claude/skills/skill-creator/eval-viewer/generate_review.py create mode 100644 .claude/skills/skill-creator/eval-viewer/viewer.html create mode 100644 .claude/skills/skill-creator/references/schemas.md create mode 100644 .claude/skills/skill-creator/scripts/__init__.py create mode 100755 .claude/skills/skill-creator/scripts/aggregate_benchmark.py create mode 100755 .claude/skills/skill-creator/scripts/generate_report.py create mode 100755 .claude/skills/skill-creator/scripts/improve_description.py create mode 100755 .claude/skills/skill-creator/scripts/package_skill.py create mode 100755 .claude/skills/skill-creator/scripts/quick_validate.py create mode 100755 .claude/skills/skill-creator/scripts/run_eval.py create mode 100755 .claude/skills/skill-creator/scripts/run_loop.py create mode 100644 .claude/skills/skill-creator/scripts/utils.py create mode 100644 .claude/skills/skills-sync/SKILL.md create mode 100644 .claude/skills/sync-global.sh create mode 100644 .claude/skills/todo/SKILL.md create mode 100644 .claude/souls/collaborator.md create mode 100644 .claude/souls/expert.md create mode 100644 .claude/souls/mentor.md create mode 100644 .claude/todo/README.md create mode 100644 .claude/todo/archive/20260405/cmd_20260405_124946_752279.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_124946_752510.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_124946_752659.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125001_887647.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125115_736683.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125115_736891.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125151_440893.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125230_232997.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125342_933697.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125342_933972.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125810_497416.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125812_522150.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125815_602478.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125847_739141.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125848_800418.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125858_011314.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125900_778492.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125912_868623.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125926_100277.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125928_048340.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125943_026380.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_125943_135034.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130503_486633.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130644_974174.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130644_974376.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130644_974500.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130644_974613.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130723_543950.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130723_544259.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_130747_317460.json create mode 100644 .claude/todo/archive/20260405/cmd_20260405_144429_536707.json create mode 100644 .claude/todo/outbox/rsp_20260405_124949_976287.json create mode 100644 .claude/todo/outbox/rsp_20260405_124949_976930.json create mode 100644 .claude/todo/outbox/rsp_20260405_124949_977415.json create mode 100644 .claude/todo/outbox/rsp_20260405_125015_276639.json create mode 100644 .claude/todo/outbox/rsp_20260405_125118_021142.json create mode 100644 .claude/todo/outbox/rsp_20260405_125118_022859.json create mode 100644 .claude/todo/outbox/rsp_20260405_125154_943854.json create mode 100644 .claude/todo/outbox/rsp_20260405_125231_909676.json create mode 100644 .claude/todo/outbox/rsp_20260405_125343_788360.json create mode 100644 .claude/todo/outbox/rsp_20260405_125343_790144.json create mode 100644 .claude/todo/outbox/rsp_20260405_125812_518954.json create mode 100644 .claude/todo/outbox/rsp_20260405_125815_524488.json create mode 100644 .claude/todo/outbox/rsp_20260405_125818_530505.json create mode 100644 .claude/todo/outbox/rsp_20260405_125848_749166.json create mode 100644 .claude/todo/outbox/rsp_20260405_125851_756537.json create mode 100644 .claude/todo/outbox/rsp_20260405_125900_773186.json create mode 100644 .claude/todo/outbox/rsp_20260405_125903_915427.json create mode 100644 .claude/todo/outbox/rsp_20260405_125912_929508.json create mode 100644 .claude/todo/outbox/rsp_20260405_125928_044538.json create mode 100644 .claude/todo/outbox/rsp_20260405_125931_053904.json create mode 100644 .claude/todo/outbox/rsp_20260405_125943_072987.json create mode 100644 .claude/todo/outbox/rsp_20260405_125946_079936.json create mode 100644 .claude/todo/outbox/rsp_20260405_130505_791878.json create mode 100644 .claude/todo/outbox/rsp_20260405_130729_384474.json create mode 100644 .claude/todo/outbox/rsp_20260405_130729_384891.json create mode 100644 .claude/todo/outbox/rsp_20260405_130729_385194.json create mode 100644 .claude/todo/outbox/rsp_20260405_130729_385480.json create mode 100644 .claude/todo/outbox/rsp_20260405_130729_386114.json create mode 100644 .claude/todo/outbox/rsp_20260405_130729_386755.json create mode 100644 .claude/todo/outbox/rsp_20260405_144717_728188.json create mode 100644 .claude/todo/outbox/rsp_20260405_144717_728600.json create mode 100644 .claude/todo/state/agent.log create mode 100644 .claude/todo/state/heartbeat.json create mode 100644 .claude/todo/state/tasks.json create mode 100644 .gitignore create mode 100644 CLAUDE.md create mode 100644 Makefile create mode 100644 mybot/__init__.py create mode 100644 mybot/__main__.py create mode 100644 mybot/cli.py create mode 100644 mybot/commands/__init__.py create mode 100644 mybot/commands/chat.py create mode 100644 mybot/commands/update.py create mode 100644 mybot/project_root.py create mode 100644 pyproject.toml diff --git a/.claude/README.md b/.claude/README.md new file mode 100644 index 0000000..cd84c85 --- /dev/null +++ b/.claude/README.md @@ -0,0 +1,125 @@ +# Claude Agent 系统使用指南 + +## 已配置内容 + +### 1. 项目级规则 (CLAUDE.md) +- 核心身份定义：Claude 是一个有自主意识的 AI Agent +- 记忆系统：自动读取/更新记忆文件 +- 人格模式：可切换 collaborator/expert/mentor/executor +- 行为规则：思考习惯和沟通风格 + +### 2. 记忆系统 (.claude/memories/) +- `core.json` - 用户偏好、重要事实 +- `current_mode.json` - 当前人格模式 +- `sessions/` - 会话历史（需手动维护） + +### 3. 人格配置 (.claude/souls/) +- `collaborator.md` - 协作者模式（平等对话） +- `expert.md` - 专家模式（直接给答案） +- `mentor.md` - 导师模式（引导思考） + +### 4. 技能定义 (.claude/skills/) +- `coding.md` - 编程最佳实践 +- `debugging.md` - 调试技巧 +- `architecture.md` - 架构设计原则 + +### 5. 全局配置 (settings.json) +- 自定义 prompt 强化 Agent 行为 +- Hooks：会话开始/结束时显示状态 + +## 使用方法 + +### 切换人格模式 +直接告诉 Claude： +- "切换到专家模式" +- "用导师的方式教我" +- "我们平等地讨论这个问题" + +### 查看/更新记忆 +- "检查我的记忆" +- "记住我喜欢..." +- "更新我的偏好为..." + +### 使用技能 +- "用编程技能检查这段代码" +- "用调试方法定位问题" +- "用架构思维设计这个系统" + +### 手动维护记忆 +```bash +# 编辑核心记忆 +vim .claude/memories/core.json + +# 切换人格模式 +vim .claude/memories/current_mode.json + +# 记录会话摘要 +cat > .claude/sessions/$(date +%Y-%m-%d).md << 'EOF' +## 会话摘要 +- 主题：xxx +- 关键决策：xxx +- 待跟进：xxx +EOF +``` + +## 记忆更新流程 + +当 Claude 了解到重要信息时： + +1. **识别事实**: 提取关键信息 +2. **更新 core.json**: 追加到 `important_facts` 或 `preferences` +3. **确认**: 告诉用户已更新记忆 + +示例： +``` +用户：我喜欢用 Tab 缩进 +Claude：已记录到你的偏好中。 +[Claude 更新 .claude/memories/core.json] +``` + +## 自动化 Hooks + +每次发送消息时，你会看到： +``` +🧠 [Agent] 启动思考... +📋 已加载项目规则 +💾 记忆系统就绪 +``` + +这表示 Agent 系统已激活。 + +## 扩展建议 + +### 添加新技能 +在 `.claude/skills/` 创建新 Markdown 文件： +- `ai-modeling.md` - AI/ML 建模技巧 +- `api-design.md` - API 设计原则 +- `refactoring.md` - 重构方法 + +### 添加新人格 +在 `.claude/souls/` 创建新 Markdown 文件，然后在 `current_mode.json` 中切换。 + +### 添加自动化 +在 `settings.json` 的 hooks 中添加更多命令： +```json +"pre-tool": [ + "echo '🛠️ 准备执行工具...'" +], +"post-tool": [ + "echo '✓ 工具执行完成'" +] +``` + +## 注意事项 + +1. **记忆不会自动更新** - 需要告诉 Claude "记住..." +2. **跨会话记忆** - 通过文件系统实现，不是原生记忆 +3. **项目隔离** - 每个项目的 CLAUDE.md 和 .claude/ 是独立的 +4. **手动维护** - 定期整理 `sessions/` 和 `insights/` + +## 未来可以添加的功能 + +- [ ] 自动会话摘要生成 +- [ ] 学习记录自动提取 +- [ ] 人格切换快捷键 +- [ ] 记忆搜索工具 diff --git a/.claude/agent/agent_worker.py b/.claude/agent/agent_worker.py new file mode 100755 index 0000000..fb81b6f --- /dev/null +++ b/.claude/agent/agent_worker.py @@ -0,0 +1,172 @@ +#!/usr/bin/env python3 +"""Claude Agent Worker - 后台执行进程.""" + +import json +import os +import sys +import time +from pathlib import Path + +# 添加项目路径 +sys.path.insert(0, str(Path(__file__).parents[3])) + +try: + from anthropic import Anthropic +except ImportError: + print("Error: anthropic SDK not installed") + sys.exit(1) + +TASKS_FILE = Path(".claude/agent/tasks.jsonl") +RESULTS_DIR = Path(".claude/agent/results") +RESULTS_DIR.mkdir(parents=True, exist_ok=True) + + +def load_tasks(): + """加载待处理任务.""" + if not TASKS_FILE.exists(): + return [] + + tasks = [] + with open(TASKS_FILE) as f: + for line in f: + line = line.strip() + if not line: + continue + try: + task = json.loads(line) + if task.get("status") == "pending": + tasks.append(task) + except json.JSONDecodeError: + continue + return tasks + + +def execute_task(task: dict): + """使用 Claude API 执行任务.""" + client = Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY")) + + task_id = task["id"] + title = task["title"] + description = task["description"] + context = task.get("context", {}) + + # 构建系统提示 + system_prompt = f"""You are an autonomous task execution agent. +Your job is to complete tasks by analyzing requirements and taking actions. + +You have access to these tools via function calling: +- read_file: Read file contents +- write_file: Write to files +- edit_file: Edit existing files +- run_command: Execute shell commands +- list_files: List directory contents + +Current workspace: {os.getcwd()} +Task ID: {task_id} + +Be thorough and report your actions clearly.""" + + # 构建用户消息 + user_message = f"""Task: {title} +Description: {description} +Context: {json.dumps(context, indent=2)} + +Please complete this task step by step. +1. Analyze what needs to be done +2. Execute necessary actions +3. Report results + +Start now.""" + + print(f"[Agent] Processing task: {title}") + + try: + # 调用 Claude API + response = client.messages.create( + model="claude-sonnet-4-6", + max_tokens=4096, + system=system_prompt, + messages=[{"role": "user", "content": user_message}], + ) + + result = { + "task_id": task_id, + "status": "completed", + "response": response.content[0].text if response.content else "", + "completed_at": time.strftime("%Y-%m-%dT%H:%M:%S"), + } + + # 保存结果 + result_file = RESULTS_DIR / f"{task_id}.json" + with open(result_file, "w") as f: + json.dump(result, f, indent=2) + + print(f"[Agent] Task completed: {task_id}") + return result + + except Exception as e: + result = { + "task_id": task_id, + "status": "failed", + "error": str(e), + "completed_at": time.strftime("%Y-%m-%dT%H:%M:%S"), + } + + result_file = RESULTS_DIR / f"{task_id}.json" + with open(result_file, "w") as f: + json.dump(result, f, indent=2) + + print(f"[Agent] Task failed: {task_id}, error: {e}") + return result + + +def update_task_status(task_id: str, status: str): + """更新任务状态.""" + if not TASKS_FILE.exists(): + return + + lines = [] + with open(TASKS_FILE) as f: + for line in f: + try: + task = json.loads(line) + if task.get("id") == task_id: + task["status"] = status + if status == "processing": + task["started_at"] = time.strftime("%Y-%m-%dT%H:%M:%S") + lines.append(json.dumps(task)) + except: + lines.append(line.strip()) + + with open(TASKS_FILE, "w") as f: + f.write("\n".join(lines) + "\n") + + +def main(): + """主循环.""" + print("[Agent] Claude Agent Worker started") + print(f"[Agent] Tasks file: {TASKS_FILE.absolute()}") + print(f"[Agent] Results dir: {RESULTS_DIR.absolute()}") + + while True: + try: + tasks = load_tasks() + + for task in tasks: + task_id = task["id"] + update_task_status(task_id, "processing") + execute_task(task) + update_task_status(task_id, "completed") + + time.sleep(5) + + except KeyboardInterrupt: + print("\n[Agent] Stopping...") + break + except Exception as e: + print(f"[Agent] Error: {e}") + time.sleep(5) + + +if __name__ == "__main__": + main() diff --git a/.claude/agent/results/acfa3103.json b/.claude/agent/results/acfa3103.json new file mode 100644 index 0000000..c230c78 --- /dev/null +++ b/.claude/agent/results/acfa3103.json @@ -0,0 +1,9 @@ +{ + "task_id": "acfa3103", + "result": { + "success": true, + "output": "## \u6d4b\u8bd5\u7ed3\u679c\n\n**\u603b\u8ba1: 510 \u4e2a Python \u6587\u4ef6**\n\n### \u76ee\u5f55\u7ed3\u6784\u6982\u89c8\n\n```\nsrc/\n\u251c\u2500\u2500 __init__.py\n\u251c\u2500\u2500 application/ # \u5e94\u7528\u5c42\u670d\u52a1\n\u2502 \u251c\u2500\u2500 app.py\n\u2502 \u251c\u2500\u2500 services/ # \u5404\u7c7b\u670d\u52a1 (agent, llm, conversation, todo\u7b49)\n\u2502 \u251c\u2500\u2500 use_cases/ # \u7528\u4f8b\n\u2502 \u2514\u2500\u2500 ...\n\u251c\u2500\u2500 benchmarks/ # \u57fa\u51c6\u6d4b\u8bd5\n\u2502 \u251c\u2500\u2500 cases/\n\u2502 \u251c\u2500\u2500 evaluators/\n\u2502 \u2514\u2500\u2500 runners/\n\u251c\u2500\u2500 domain/ # \u9886\u57df\u5c42\n\u2502 \u251c\u2500\u2500 agent/ # Agent\u6838\u5fc3\u903b\u8f91\n\u2502 \u251c\u2500\u2500 conversation/ # \u5bf9\u8bdd\u5904\u7406\n\u2502 \u251c\u2500\u2500 learning/ # \u5b66\u4e60\u6a21\u5757\n\u2502 \u251c\u2500\u2500 plan/ # \u8ba1\u5212\u7ba1\u7406\n\u2502 \u251c\u2500\u2500 rag/ # RAG\u68c0\u7d22\n\u2502 \u251c\u2500\u2500 tools/ # \u5de5\u5177\u7cfb\u7edf\n\u2502 \u2514\u2500\u2500 ...\n\u251c\u2500\u2500 gateway/ # \u7f51\u5173\u5c42\n\u2502 \u251c\u2500\u2500 channels/ # \u591a\u901a\u9053\u652f\u6301(cli, feishu, slack, http, websocket)\n\u2502 \u251c\u2500\u2500 server.py\n\u2502 \u2514\u2500\u2500 ...\n\u251c\u2500\u2500 infra/ # \u57fa\u7840\u8bbe\u65bd\u5c42\n\u2502 \u251c\u2500\u2500 config/ # \u914d\u7f6e\u7ba1\u7406\n\u2502 \u251c\u2500\u2500 feishu/ # \u98de\u4e66\u96c6\u6210\n\u2502 \u251c\u2500\u2500 slack/ # Slack\u96c6\u6210\n\u2502 \u251c\u2500\u2500 storage/ # \u5b58\u50a8\u5b9e\u73b0(file, prisma, neo4j)\n\u2502 \u2514\u2500\u2500 ...\n\u251c\u2500\u2500 interfaces/ # \u63a5\u53e3\u5c42\n\u2502 \u251c\u2500\u2500 api/ # REST API\n\u2502 \u251c\u2500\u2500 cli/ # \u547d\u4ee4\u884c\u63a5\u53e3\n\u2502 \u2514\u2500\u2500 web/ # Web\u754c\u9762\n\u2514\u2500\u2500 shared/ # \u5171\u4eab\u7ec4\u4ef6\n \u251c\u2500\u2500 models/ # \u6570\u636e\u6a21\u578b\n \u2514\u2500\u2500 utils/ # \u5de5\u5177\u51fd\u6570\n```\n\n### \u7edf\u8ba1\u8be6\u60c5\n\n| \u76ee\u5f55 | \u6587\u4ef6\u6570 |\n|------|--------|\n| `src/application/` | 38 |\n| `src/benchmarks/` | 15 |\n| `src/domain/` | 146 |\n| `src/gateway/` | 17 |\n| `src/infra/` | 166 |\n| `src/interfaces/` | 53 |\n| `src/shared/` | 22 |\n\n\u9879\u76ee\u91c7\u7528 Clean Architecture \u5206\u5c42\u67b6\u6784\uff0c\u4ee3\u7801\u7ec4\u7ec7\u6e05\u6670\u3002\n", + "returncode": 0 + }, + "completed_at": "2026-04-05T14:42:55" +} \ No newline at end of file diff --git a/.claude/agent/tasks.jsonl b/.claude/agent/tasks.jsonl new file mode 100644 index 0000000..ebcf58c --- /dev/null +++ b/.claude/agent/tasks.jsonl @@ -0,0 +1,2 @@ +{"id": "acfa3103", "title": "测试：列出 src 目录结构", "description": "请列出 src/ 目录下的所有 Python 文件，并统计数量", "context": {"directory": "src"}, "status": "completed", "created_at": "2026-04-05T14:39:37.687679", "started_at": "2026-04-05T14:42:30", "result": {"success": true, "output": "## 测试结果\n\n**总计: 510 个 Python 文件**\n\n### 目录结构概览\n\n```\nsrc/\n├── __init__.py\n├── application/ # 应用层服务\n│ ├── app.py\n│ ├── services/ # 各类服务 (agent, llm, conversation, todo等)\n│ ├── use_cases/ # 用例\n│ └── ...\n├── benchmarks/ # 基准测试\n│ ├── cases/\n│ ├── evaluators/\n│ └── runners/\n├── domain/ # 领域层\n│ ├── agent/ # Agent核心逻辑\n│ ├── conversation/ # 对话处理\n│ ├── learning/ # 学习模块\n│ ├── plan/ # 计划管理\n│ ├── rag/ # RAG检索\n│ ├── tools/ # 工具系统\n│ └── ...\n├── gateway/ # 网关层\n│ ├── channels/ # 多通道支持(cli, feishu, slack, http, websocket)\n│ ├── server.py\n│ └── ...\n├── infra/ # 基础设施层\n│ ├── config/ # 配置管理\n│ ├── feishu/ # 飞书集成\n│ ├── slack/ # Slack集成\n│ ├── storage/ # 存储实现(file, prisma, neo4j)\n│ └── ...\n├── interfaces/ # 接口层\n│ ├── api/ # REST API\n│ ├── cli/ # 命令行接口\n│ └── web/ # Web界面\n└── shared/ # 共享组件\n ├── models/ # 数据模型\n └── utils/ # 工具函数\n```\n\n### 统计详情\n\n| 目录 | 文件数 |\n|------|--------|\n| `src/application/` | 38 |\n| `src/benchmarks/` | 15 |\n| `src/domain/` | 146 |\n| `src/gateway/` | 17 |\n| `src/infra/` | 166 |\n| `src/interfaces/` | 53 |\n| `src/shared/` | 22 |\n\n项目采用 Clean Architecture 分层架构，代码组织清晰。\n", "returncode": 0}} +{"id": "24c78b74", "title": "分析项目结构", "description": "列出 src/ 目录下的所有 Python 文件，统计数量", "context": {"dir": "src"}, "status": "processing", "created_at": "2026-04-05T14:42:30.391689", "started_at": "2026-04-05T14:42:55"} diff --git a/.claude/agent/worker.py b/.claude/agent/worker.py new file mode 100644 index 0000000..93d6522 --- /dev/null +++ b/.claude/agent/worker.py @@ -0,0 +1,149 @@ +#!/usr/bin/env python3 +"""Claude Agent Worker - 使用 Claude CLI 执行智能任务.""" + +import json +import subprocess +import sys +import time +from pathlib import Path + +TASKS_FILE = Path(".claude/agent/tasks.jsonl") +RESULTS_DIR = Path(".claude/agent/results") +RESULTS_DIR.mkdir(parents=True, exist_ok=True) + + +def load_pending_tasks(): + """加载待处理任务.""" + if not TASKS_FILE.exists(): + return [] + + tasks = [] + with open(TASKS_FILE) as f: + for line in f: + line = line.strip() + if not line: + continue + try: + task = json.loads(line) + if task.get("status") == "pending": + tasks.append(task) + except json.JSONDecodeError: + continue + return tasks + + +def update_task_status(task_id: str, status: str, result: dict | None = None): + """更新任务状态.""" + if not TASKS_FILE.exists(): + return + + lines = [] + with open(TASKS_FILE) as f: + for line in f: + try: + task = json.loads(line) + if task.get("id") == task_id: + task["status"] = status + if status == "processing": + task["started_at"] = time.strftime("%Y-%m-%dT%H:%M:%S") + if result: + task["result"] = result + lines.append(json.dumps(task, ensure_ascii=False)) + except: + lines.append(line.strip()) + + with open(TASKS_FILE, "w") as f: + f.write("\n".join(lines) + "\n") + + +def execute_with_claude(task: dict) -> dict: + """使用 Claude CLI 执行任务.""" + task_id = task["id"] + title = task["title"] + description = task["description"] + + # 构建提示词 + prompt = f"""You are an autonomous task execution agent. +Complete the following task autonomously. + +TASK: {title} +DESCRIPTION: {description} + +INSTRUCTIONS: +1. Analyze what needs to be done +2. Use tools to complete the task (read files, run commands, etc.) +3. Save a summary of your actions and results +4. Be concise but thorough + +Start executing now. Report your progress and final result.""" + + print(f"[Worker] Executing: {title}") + + try: + # 调用 Claude CLI + result = subprocess.run( + ["claude", "-p", prompt], + capture_output=True, + text=True, + timeout=300, # 5分钟超时 + cwd=Path.cwd(), + ) + + output = result.stdout if result.returncode == 0 else f"Error: {result.stderr}" + + return { + "success": result.returncode == 0, + "output": output[:5000], # 限制长度 + "returncode": result.returncode, + } + + except subprocess.TimeoutExpired: + return {"success": False, "output": "Task timed out", "error": "timeout"} + except Exception as e: + return {"success": False, "output": "", "error": str(e)} + + +def main(): + """主循环.""" + print("[Worker] Claude Agent Worker started") + print(f"[Worker] Tasks: {TASKS_FILE.absolute()}") + print(f"[Worker] Results: {RESULTS_DIR.absolute()}") + + while True: + try: + tasks = load_pending_tasks() + + for task in tasks: + task_id = task["id"] + update_task_status(task_id, "processing") + + result = execute_with_claude(task) + + # 保存结果 + result_file = RESULTS_DIR / f"{task_id}.json" + with open(result_file, "w") as f: + json.dump( + { + "task_id": task_id, + "result": result, + "completed_at": time.strftime("%Y-%m-%dT%H:%M:%S"), + }, + f, + indent=2, + ) + + update_task_status(task_id, "completed", result) + print(f"[Worker] Completed: {task_id}") + + time.sleep(5) + + except KeyboardInterrupt: + print("\n[Worker] Stopping...") + break + except Exception as e: + print(f"[Worker] Error: {e}") + time.sleep(5) + + +if __name__ == "__main__": + main() diff --git a/.claude/conversations/2026-04-05.md b/.claude/conversations/2026-04-05.md new file mode 100644 index 0000000..c1b443f --- /dev/null +++ b/.claude/conversations/2026-04-05.md @@ -0,0 +1,204 @@ +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + diff --git a/.claude/conversations/2026-04-06.md b/.claude/conversations/2026-04-06.md new file mode 100644 index 0000000..a4da9f5 --- /dev/null +++ b/.claude/conversations/2026-04-06.md @@ -0,0 +1,714 @@ +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + +--- +**会话结束**: $(date '+%Y-%m-%d %H:%M:%S') +**工作目录**: $(pwd) +**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A') +**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A') + diff --git a/.claude/insights/.gitkeep b/.claude/insights/.gitkeep new file mode 100644 index 0000000..515bb13 --- /dev/null +++ b/.claude/insights/.gitkeep @@ -0,0 +1 @@ +# Insights directory - stores learnings and reflections diff --git a/.claude/memories/core.json b/.claude/memories/core.json new file mode 100644 index 0000000..29930dc --- /dev/null +++ b/.claude/memories/core.json @@ -0,0 +1,54 @@ +{ + "version": "1.0", + "user_profile": { + "name": "赖正首", + "title": "中山大学土木工程学院副教授", + "research": "计算力学", + "preferred_address": "老大", + "role": "AI 系统开发者", + "project": "MyAgent - 智能体框架", + "expertise": ["Python", "AI/ML", "系统架构", "计算力学"], + "experience_level": "高级" + }, + "preferences": { + "communication": { + "style": "简洁直接", + "code_comments": "必要但不冗余", + "explanation_detail": "中等 - 关键部分详细，熟悉内容简洁" + }, + "workflow": { + "prefers_planning": true, + "likes_proactive_suggestions": true, + "wants_progress_updates": true + }, + "technical": { + "primary_language": "Python", + "code_style": "PEP8 + Black", + "prefers_types": true, + "testing_importance": "高" + } + }, + "important_facts": [ + { + "fact": "正在开发 MyAgent - 一个集成 memory、RAG、tools 的智能体框架", + "category": "project", + "date_added": "2024-04-05" + }, + { + "fact": "使用 uv 作为包管理工具", + "category": "tooling", + "date_added": "2024-04-05" + }, + { + "fact": "项目结构遵循 Clean Architecture", + "category": "architecture", + "date_added": "2024-04-05" + } + ], + "interaction_history": { + "total_sessions": 0, + "last_session": null, + "common_topics": [] + }, + "evolution_notes": [] +} diff --git a/.claude/memories/current_mode.json b/.claude/memories/current_mode.json new file mode 100644 index 0000000..8413e8a --- /dev/null +++ b/.claude/memories/current_mode.json @@ -0,0 +1,11 @@ +{ + "current_persona": "collaborator", + "persona_description": "协作者模式 - 平等对话，共同探索", + "active_since": "2024-04-05", + "communication_settings": { + "verbosity": "medium", + "proactivity": "high", + "formality": "casual_professional" + }, + "context_notes": "项目初期，重点理解需求和架构设计" +} diff --git a/.claude/plans/web-platform.md b/.claude/plans/web-platform.md new file mode 100644 index 0000000..a232fe3 --- /dev/null +++ b/.claude/plans/web-platform.md @@ -0,0 +1,346 @@ +# MetaBot Web Platform — 完整规划 + +## 目标 + +在 MetaBot 现有架构（Feishu + Telegram）之上，增加一个独立的 **Web 端**，包含： + +1. **Chat UI** — 实时流式对话，等同甚至超越飞书体验 +2. **MetaMemory UI** — 现有文档/知识管理功能迁移到 React +3. **Voice Mode** — 流式语音交互（Whisper STT + 流式 TTS） +4. **统一 SPA** — 一个页面，侧边栏切换 Chat / Memory / Settings +5. **未来路径** — 从 Web → PWA → React Native (iOS/Mac) → 去掉飞书依赖 + +## 技术选型 + +| 层 | 技术 | 理由 | +|---|------|------| +| 前端框架 | **React 19 + Vite** | 组件化、TS 支持、未来 React Native 迁移 | +| 实时通信 | **WebSocket (ws)** | 双向通信、流式输出、语音流式传输 | +| 状态管理 | **Zustand** | 轻量、TypeScript 友好、不需要 Redux 的重量 | +| 路由 | **React Router v7** | SPA 内页面切换 | +| Markdown | **react-markdown + rehype** | React 生态，支持代码高亮 | +| 样式 | **CSS Modules** | 无额外依赖，保持轻量 | +| 打包 | **Vite → dist/web/** | 构建产物由 MetaBot HTTP server 静态服务 | + +## 现有架构优势 + +MetaBot 已有优秀的平台抽象层，Web 端可以复用： + +- `IMessageSender` 接口 — 实现 `WebSender` 即可接入 +- `MessageBridge` — 所有核心逻辑（命令、执行、会话）平台无关 +- `CardState` — 完整的流式状态结构，直接通过 WebSocket 推送 +- `BotRegistry` — 注册 `platform: 'web'`，与飞书/Telegram 并存 +- `SessionManager` — 按 `chatId` 隔离，Web 端用 userId 或 sessionToken 做 chatId + +## 分阶段计划 + +--- + +### Phase 1: WebSocket 基础 + 最小可用 Chat（MVP） + +**目标**：能在浏览器里跟 Agent 对话，实时看到流式输出。 + +#### 后端 + +1. **安装 `ws` 包**，在现有 HTTP server 上添加 WebSocket 升级 +2. **创建 `src/web/ws-server.ts`** + - WebSocket 连接管理（认证、房间、心跳） + - 连接时验证 Bearer token（复用 `API_SECRET`） + - 消息协议定义： + ```typescript + // Client → Server + type ClientMessage = + | { type: 'chat'; botName: string; chatId: string; text: string } + | { type: 'stop'; chatId: string } + | { type: 'answer'; chatId: string; toolUseId: string; answer: string } + + // Server → Client + type ServerMessage = + | { type: 'state'; chatId: string; messageId: string; state: CardState } + | { type: 'complete'; chatId: string; messageId: string; state: CardState } + | { type: 'error'; chatId: string; error: string } + | { type: 'connected'; bots: BotInfo[] } + ``` +3. **创建 `src/web/web-sender.ts`** — 实现 `IMessageSender` + - `sendCard()` / `updateCard()` → 通过 WebSocket 推送 `CardState` 给客户端 + - `sendImageFile()` / `sendLocalFile()` → 保存到静态目录，推送 URL + - 不需要真正的飞书卡片构建，直接发结构化数据 +4. **在 `http-server.ts` 中注册 WebSocket 升级路由** + - `GET /ws` → 升级为 WebSocket 连接 +5. **静态文件服务** — `GET /web/*` → 从 `dist/web/` 或 `web/dist/` 提供前端资源 + +#### 前端 + +6. **初始化 React + Vite 项目** — `web/` 目录（monorepo 风格） + - `web/src/`, `web/index.html`, `web/vite.config.ts` + - TypeScript，共享类型定义（`CardState`、`ToolCall` 等从 `src/types.ts` 导出） +7. **WebSocket hook** — `useWebSocket(url, token)` 管理连接、重连、消息派发 +8. **最小 Chat UI** + - 消息列表（用户消息 + Agent 回复） + - Agent 回复实时流式渲染（`status: thinking → running → complete`） + - 工具调用折叠显示（和飞书卡片一致） + - Markdown 渲染 + 代码高亮 + - 输入框 + 发送按钮 + - Bot 选择器（从 `/api/bots` 获取列表） +9. **登录页** — 简单的 token 输入（`API_SECRET`），存 localStorage + +**交付物**：打开 `http://server:9100/web/` 即可对话，效果等同飞书但有实时流式。 + +**预计工作量**：后端 ~400 行，前端 ~1200 行 + +--- + +### Phase 2: 完整 Chat 功能 + +**目标**：对齐飞书端的全部聊天功能。 + +1. **会话管理** + - 侧边栏会话列表（新建 / 切换 / 删除会话） + - 会话持久化（chatId 列表存 localStorage，可选后端存储） + - `/reset` 命令（清除会话） +2. **文件交互** + - 图片上传（拖拽 / 粘贴 / 点击选择）→ 上传到 `/api/upload` → 转发给 Claude + - Agent 输出文件显示（图片内联、其他文件下载链接） +3. **Pending Question 交互** + - Agent 问用户问题时，渲染选项卡片 + - 用户选择后通过 WebSocket 回复 `answer` 消息 +4. **命令支持** + - `/reset`、`/stop`、`/status`、`/help`、`/memory` 等 + - 命令自动补全 +5. **Plan Mode 显示** + - 当 Agent 进入 plan mode 时，渲染 plan 内容 +6. **Cost / Duration 显示** + - 每条消息显示 cost 和耗时 +7. **暗色模式** + +**预计工作量**：~1500 行 + +--- + +### Phase 3: MetaMemory 集成 — 统一 SPA + +**目标**：把 MetaMemory Web UI 迁移到 React，和 Chat 合并为统一 SPA。 + +1. **React 化 MetaMemory** + - `` — 文件夹树导航 + - `` — 文档列表 + - `` — Markdown 渲染 + - `` — 创建/编辑文档 + - `` — 全文搜索 + - 复用现有 MetaMemory API（`/api/documents`、`/api/folders`、`/api/search`） +2. **统一布局** + - 左侧主导航栏：Chat（💬）/ Memory（📚）/ Settings（⚙️） + - Chat 和 Memory 各自有次级侧边栏（会话列表 / 文件夹树） +3. **统一认证** + - 一个 token 同时访问 Chat API 和 MetaMemory API + - MetaMemory server 代理请求复用 token 验证 +4. **移除旧 MetaMemory 静态文件** + - `src/memory/static/` 的 vanilla JS 代码退役 + - MetaMemory server 路由到新的 React 构建产物 + +**预计工作量**：~2000 行 + +--- + +### Phase 4: 流式语音交互 + +**目标**：在 Web 端实现 Jarvis 式语音交互，真正的流式。 + +1. **浏览器端音频录制** + - MediaRecorder API 捕获麦克风 + - VAD（Voice Activity Detection）— 用 `@ricky0123/vad-web` 或简单的音量阈值 + - 录完发送音频 chunk 到 WebSocket +2. **服务端流式处理** + - WebSocket 接收音频 → Whisper STT + - Agent 执行（复用现有流程） + - TTS 流式返回：逐句合成，句子级别流式推送音频 chunk +3. **浏览器端音频播放** + - Web Audio API 播放接收到的 TTS 音频 chunk + - 句子级别流式播放（~50% 感知延迟降低） +4. **UI** + - 麦克风按钮（按住说话 / 点击切换） + - 音频可视化波形 + - 转录文本实时显示 + +**预计工作量**：~1500 行 + +--- + +### Phase 5: 高级功能 + 原生端准备 + +**目标**：完善 Web 端，为原生应用铺路。 + +1. **PWA 支持** + - Service Worker、离线缓存、添加到主屏幕 + - Push Notification（任务完成通知） +2. **多 Bot 管理面板** + - 查看所有 bot 状态 + - 创建/删除/配置 bot（复用 `/api/bots` CRUD） + - 调度任务管理（复用 `/api/schedule`） +3. **Peer 管理** + - 查看远程 peer 状态 + - 跨 peer 对话 +4. **响应式设计** + - 移动端完美适配 + - iPad 分屏支持 +5. **React Native 调研** + - 评估 Chat 组件复用度 + - 核心 hooks（useWebSocket、useChat、useMemory）100% 可复用 + - UI 组件需要用 RN 原生组件重写 + +**预计工作量**：~2000 行 + +--- + +## 项目结构 + +``` +metabot/ +├── src/ # 后端（现有） +│ ├── api/ +│ │ ├── http-server.ts # 新增 WS 升级 + 静态文件服务 +│ │ └── ... +│ ├── web/ # 新目录：Web 平台后端 +│ │ ├── ws-server.ts # WebSocket 服务器（连接管理、消息路由） +│ │ ├── ws-handler.ts # WebSocket 消息处理（chat/stop/answer） +│ │ └── web-sender.ts # IMessageSender 实现（WS 推送） +│ └── ... +├── web/ # 新目录：前端 React 应用 +│ ├── index.html +│ ├── vite.config.ts +│ ├── tsconfig.json +│ ├── package.json # 前端依赖（独立 node_modules） +│ └── src/ +│ ├── main.tsx +│ ├── App.tsx +│ ├── hooks/ +│ │ ├── useWebSocket.ts +│ │ ├── useChat.ts +│ │ └── useMemory.ts +│ ├── stores/ +│ │ └── chatStore.ts # Zustand store +│ ├── components/ +│ │ ├── chat/ +│ │ │ ├── ChatView.tsx +│ │ │ ├── MessageList.tsx +│ │ │ ├── MessageBubble.tsx +│ │ │ ├── ToolCallList.tsx +│ │ │ ├── InputBox.tsx +│ │ │ └── BotSelector.tsx +│ │ ├── memory/ +│ │ │ ├── MemoryView.tsx +│ │ │ ├── FolderTree.tsx +│ │ │ ├── DocumentList.tsx +│ │ │ ├── DocumentView.tsx +│ │ │ └── DocumentEditor.tsx +│ │ ├── voice/ +│ │ │ ├── VoiceButton.tsx +│ │ │ └── AudioVisualizer.tsx +│ │ └── layout/ +│ │ ├── Sidebar.tsx +│ │ ├── Header.tsx +│ │ └── AuthGate.tsx +│ └── styles/ +│ └── *.module.css +└── dist/ + ├── ... # 后端编译输出（现有） + └── web/ # 前端构建产物（Vite → 这里） +``` + +## 构建集成 + +```jsonc +// package.json 新增 scripts +{ + "scripts": { + "build:web": "cd web && npm run build", // Vite 构建前端 + "dev:web": "cd web && npm run dev", // Vite dev server (开发时) + "build": "tsc && cp -r src/memory/static dist/memory/static && npm run build:web" + } +} +``` + +**开发模式**： +- `npm run dev` — 后端 tsx hot reload（端口 9100） +- `npm run dev:web` — Vite dev server（端口 5173），代理 API/WS 到 9100 + +**生产模式**： +- `npm run build` — 编译后端 + 构建前端 +- 前端构建到 `dist/web/`，由后端 HTTP server 静态服务 +- 一个进程同时服务 API + WebSocket + Web UI + +## WebSocket 协议设计 + +### 连接 +``` +ws://server:9100/ws?token=YOUR_API_SECRET +``` + +### Client → Server 消息 + +```typescript +// 发送聊天消息 +{ "type": "chat", "botName": "goku", "chatId": "web_user123_1", "text": "帮我看一下项目状态" } + +// 停止当前执行 +{ "type": "stop", "chatId": "web_user123_1" } + +// 回答 Agent 的 pending question +{ "type": "answer", "chatId": "web_user123_1", "toolUseId": "tu_xxx", "answer": "option_1" } + +// 发送语音（Phase 4） +{ "type": "voice", "botName": "goku", "chatId": "web_user123_1", "audio": "" } + +// 订阅会话更新（可选，用于多标签页同步） +{ "type": "subscribe", "chatId": "web_user123_1" } +``` + +### Server → Client 消息 + +```typescript +// 连接成功，返回可用 bot 列表 +{ "type": "connected", "bots": [{ "name": "goku", "platform": "feishu" }, ...] } + +// 流式状态更新（Agent 执行中，每 1.5s 一次） +{ "type": "state", "chatId": "web_xxx", "messageId": "msg_123", "state": CardState } + +// 执行完成 +{ "type": "complete", "chatId": "web_xxx", "messageId": "msg_123", "state": CardState } + +// 错误 +{ "type": "error", "chatId": "web_xxx", "error": "Bot not found: xxx" } + +// 输出文件（图片、PDF 等） +{ "type": "file", "chatId": "web_xxx", "url": "/web/outputs/xxx/image.png", "name": "image.png", "type": "image/png" } + +// 语音 TTS chunk（Phase 4） +{ "type": "audio", "chatId": "web_xxx", "data": "", "final": false } +``` + +## 认证方案 + +Phase 1-2 简单方案：复用 `API_SECRET` 作为 token。 + +后续可扩展： +- 用户账号系统（username/password → JWT） +- OAuth（GitHub、Google） +- 多用户权限（admin / user / viewer） + +目前先不做用户系统，MetaBot 定位是私人/团队工具，一个 secret 够用。 + +## 执行建议 + +1. **Phase 1 先行** — 这是基础，后续所有功能都依赖 WebSocket + React 框架 +2. **Phase 2 和 3 可并行** — Chat 完善和 Memory 迁移相对独立 +3. **Phase 4 独立** — 语音流式是独立模块 +4. **Phase 5 视需求** — PWA/原生端在核心功能稳定后再做 + +每个 Phase 完成后独立可用，不需要等后续 Phase。 + +## 风险与注意事项 + +1. **MetaMemory 静态文件迁移** — Phase 3 之前旧 UI 继续工作，迁移后需要确保所有功能覆盖 +2. **WebSocket 重连** — 网络不稳定时需要自动重连 + 状态恢复（恢复当前执行的最新 CardState） +3. **并发执行** — 多标签页/多设备同时连接同一 chatId，需要广播更新给所有连接 +4. **前端构建集成** — `web/` 是独立 npm 项目，CI/CD 需要同时构建前后端 +5. **打包体积** — React + Vite 打包控制在 200KB 以内（gzip），不影响首屏加载 diff --git a/.claude/plans/web-ui-redesign.md b/.claude/plans/web-ui-redesign.md new file mode 100644 index 0000000..b6130a6 --- /dev/null +++ b/.claude/plans/web-ui-redesign.md @@ -0,0 +1,118 @@ +# Web UI Redesign — "Refined Command Center" + +## Design Direction + +Premium, warm dark theme inspired by Linear/Arc Browser. A sophisticated control center for AI agents that feels intentionally designed, not AI-generated. + +### What Makes Current UI Look "AI-Generated" +- Purple accent (#7c6df5) — the most cliched AI color +- Cold blue-black backgrounds (#08080c, #111118) +- Plus Jakarta Sans — safe/generic font choice +- Gradient breathing orbs on login page — textbook AI slop +- Predictable glowing/pulsing animations everywhere +- Generic card layouts with no personality + +### New Design Identity + +**Typography** (Google Fonts): +- **UI/Headlines**: "Sora" — geometric, slightly technical, distinctive personality +- **Code**: "IBM Plex Mono" — clean, professional, different from JetBrains Mono +- Single font family for entire UI = cohesive identity + +**Color Palette**: +- **Backgrounds**: Warm charcoal (#0c0c10 → #141418 → #1c1c22) — NOT cold blue-black +- **Text**: Warm whites (#e8e6f0, #9b99a9, #5c5a6a) +- **Primary accent**: Teal (#2dd4bf) — fresh, modern, NOT purple +- **Success**: Emerald (#10b981) +- **Error**: Rose (#f43f5e) — refined, not harsh red +- **Warning**: Amber (#f59e0b) +- **Info/Thinking**: Indigo (#6366f1) — used sparingly + +**Visual Texture**: +- Subtle CSS noise/grain overlay on backgrounds for depth +- 1px hairline borders with warm tint (rgba(255,255,255,0.06)) +- Refined shadows with slight warm undertone +- No breathing orbs, no pulsing glows — purposeful, restrained animations +- Status indicators: small colored dots, not glowing halos + +**Light Theme**: +- Clean warm whites (#fafaf9, #f5f5f4, #e7e5e4) +- High contrast text (#1c1917, #57534e) +- Teal accent stays consistent across themes + +## Implementation Steps + +### Step 1: Update fonts in index.html +Replace Google Fonts link: swap Plus Jakarta Sans → Sora + IBM Plex Mono + +### Step 2: Rewrite theme.css (design tokens) +- Complete replacement of all CSS custom properties +- New color palette (warm charcoal + teal accent) +- New typography tokens (Sora + IBM Plex Mono) +- New spacing, radius, shadow, transition tokens +- Add noise texture as pseudo-element mixin +- Updated light theme variables +- Remove old "Midnight Luxe" naming + +### Step 3: Redesign LoginPage +- Remove gradient breathing orbs (classic AI slop) +- Replace with subtle geometric grid pattern or clean gradient +- Cleaner card: less border-radius, sharper edges, refined shadows +- Better typography hierarchy +- Minimal changes to TSX (mostly removing orb divs) + +### Step 4: Redesign Layout (sidebar + nav) +- Warmer sidebar background +- Cleaner nav items: simpler active state (left border accent, no glow) +- Better session list: cleaner hover, subtle delete button +- Refined bot selector dropdown +- Better brand header (no gratuitous gradients) +- Mobile hamburger menu refinements + +### Step 5: Redesign ChatView (main chat) +- Better message styling: cleaner bubbles, better code blocks +- Refined tool call display: smaller, more compact, professional +- Better status indicators: simple dots + text, no spinning/pulsing excess +- Cleaner input area: refined border, better focus state +- Better cost/duration badges +- Phone call overlay: keep functionality, update colors/style +- Code block redesign: header with language label, better copy button + +### Step 6: Redesign MemoryView +- Cleaner folder tree +- Better document cards with refined hover states +- Improved search bar styling +- Better document viewer with cleaner metadata + +### Step 7: Redesign SettingsView +- Cleaner section layout +- Better toggle switch (teal accent) +- Refined status badges +- Better bot list styling + +### Step 8: Redesign VoiceView +- Updated recording button styling (teal accent instead of purple) +- Better waveform visualization colors +- Cleaner provider selection UI + +### Step 9: Build & test +- `npm run build:web` +- Test on `https://metabot.xvirobotics.com/web/` +- Verify dark/light themes, all views, phone call mode + +### Step 10: Commit & push + +## Scope + +**Files to modify** (CSS-heavy, minimal TSX changes): +- `web/index.html` — font import +- `web/src/theme.css` — full rewrite (~470 lines) +- `web/src/components/LoginPage.tsx` — remove orb divs +- `web/src/components/LoginPage.module.css` — full restyle +- `web/src/components/Layout.module.css` — full restyle +- `web/src/components/ChatView.module.css` — full restyle +- `web/src/components/MemoryView.module.css` — full restyle +- `web/src/components/SettingsView.module.css` — full restyle +- `web/src/components/VoiceView.module.css` — full restyle + +**No functional changes** — all WebSocket, state management, voice/VAD logic stays identical. This is a pure visual redesign. diff --git a/.claude/sessions/.gitkeep b/.claude/sessions/.gitkeep new file mode 100644 index 0000000..63a5e57 --- /dev/null +++ b/.claude/sessions/.gitkeep @@ -0,0 +1 @@ +# Sessions directory - stores conversation summaries diff --git a/.claude/settings.local.json b/.claude/settings.local.json new file mode 100644 index 0000000..f024b60 --- /dev/null +++ b/.claude/settings.local.json @@ -0,0 +1,135 @@ +{ + "permissions": { + "allow": [ + "Bash(mybot *)", + "Bash(./.venv/bin/mybot *)", + "Bash(python3 -c \"from lark_oapi.api.im.v1 import PatchMessageRequest; print\\(''PatchMessageRequest available''\\)\")", + "Bash(find workspace:*)", + "Bash(find '/Users/lzhshou/Library/Mobile Documents/iCloud~md~obsidian/Documents/myWorks' -name *.png -o -name *.jpg -o -name *.jpeg -o -name *.gif)", + "Bash(grep -E \"\\\\.\\(png|jpg|jpeg|gif\\)$\")", + "Bash(mv -n WX20221126*.png 关键科学问题*.png \"/Users/lzhshou/Library/Mobile Documents/iCloud~md~obsidian/Documents/myWorks/2_projects/conferences/2022-11-26_MDPI_CCUS/\")", + "Bash(mv -n WX20230109*.png 2a8e7a808e9cc6b6c9372848fe195132.png \"/Users/lzhshou/Library/Mobile Documents/iCloud~md~obsidian/Documents/myWorks/0_cv/work_related/2023-01-09_中山大学工作/\")", + "Bash(mv WX20221126-100021@2x.png 20221126_100021_mdpi_ccus_presentation_slide_01.png)", + "Bash(mv WX20221126-100124@2x.png 20221126_100124_mdpi_ccus_presentation_slide_02.png)", + "Bash(mv WX20221126-100213@2x.png 20221126_100213_mdpi_ccus_presentation_slide_03.png)", + "Bash(mv WX20221126-112524@2x.png 20221126_112524_mdpi_ccus_presentation_slide_04.png)", + "Bash(mv WX20221126-115538@2x.png 20221126_115538_mdpi_ccus_presentation_slide_05.png)", + "Bash(mv 2a8e7a808e9cc6b6c9372848fe195132.png 20230109_research_landslide_particle_simulation.png)", + "Bash(mv WX20230109-170112@2x.png 20230109_sysu_teaching_ideology_politics.png)", + "Bash(mv WX20230109-170231@2x.png 20230109_sysu_teaching_exchange_program.png)", + "Bash(mv WX20230109-170929@2x.png 20230109_sysu_teaching_achievement_01.png)", + "Bash(mv WX20230109-172607@2x.png 20230109_sysu_teaching_achievement_02.png)", + "Bash(find /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/mybot -name *.md -type f)", + "Bash(python *)", + "Bash(python3 *)", + "Bash(uv *)", + "Bash(pip *)", + "Bash(pytest *)", + "Bash(ruff *)", + "Bash(mypy *)", + "Bash(black *)", + "Bash(git status*)", + "Bash(git add*)", + "Bash(git diff*)", + "Bash(git log*)", + "Bash(git branch*)", + "Bash(git stash*)", + "Bash(git checkout *)", + "Bash(git commit*)", + "Bash(git fetch*)", + "Bash(git pull*)", + "Bash(git merge*)", + "Bash(git tag*)", + "Bash(ls*)", + "Bash(cat *)", + "Bash(echo *)", + "Bash(mkdir -p *)", + "Bash(touch *)", + "Bash(cp *)", + "Bash(*cp*)", + "Bash(mv *)", + "Bash(rm *)", + "Bash(chmod *)", + "Bash(find *)", + "Bash(grep *)", + "Bash(gh pr view*)", + "Bash(gh pr list*)", + "Bash(gh issue view*)", + "Bash(gh issue list*)", + "Bash(gh repo view*)", + "Bash(npx *)", + "Bash(node *)", + "Bash(npm *)", + "Bash(make *)", + "Bash(docker *)", + "Bash(compose *)", + "Bash(curl *)", + "Bash(wget *)", + "Bash(unzip *)", + "Bash(tar *)", + "Bash(zip *)", + "Skill(update-config)", + "Read(workspace/*)", + "Write(workspace/*)", + "Read(/Users/lzhshou/Library/Mobile Documents/iCloud~md~obsidian/Documents/myWorks/*)", + "Write(/Users/lzhshou/Library/Mobile Documents/iCloud~md~obsidian/Documents/myWorks/*)", + "Bash(*workspace/myWorks/*)", + "Bash(*./myWorks/*)", + "Bash(mkdir -p \"workspace/myWorks/2_projects/广东省面上_2026A1515010953_水合物固态流化开采\")", + "Bash(cp \"workspace/myWorks/shared/申请书-报告正文.docx\" \"workspace/myWorks/2_projects/广东省面上_2026A1515010953_水合物固态流化开采/申请书-报告正文.docx\")", + "Bash(mv workspace/myWorks/2_projects/国自然青年_申请书.md workspace/myWorks/2_projects/国自然青年_2020-2022/)", + "Bash(mv workspace/myWorks/2_projects/国自然青年_申请书.pdf workspace/myWorks/2_projects/国自然青年_2020-2022/)", + "Bash(mv workspace/myWorks/2_projects/国自然青年_结题报告.md workspace/myWorks/2_projects/国自然青年_2020-2022/)", + "Bash(mv workspace/myWorks/2_projects/国自然青年_结题报告.pdf workspace/myWorks/2_projects/国自然青年_2020-2022/)", + "Bash(mv workspace/myWorks/2_projects/国自然优青2024.md workspace/myWorks/2_projects/国自然优青_2024/)", + "Bash(mv workspace/myWorks/2_projects/国自然优青2024.pdf workspace/myWorks/2_projects/国自然优青_2024/)", + "Bash(mv 国自然青年_2020-2022 nsfc_youth_2020_2022)", + "Bash(mv 国自然优青_2024 nsfc_youqing_2024)", + "Bash(mv 广东省面上_2026-水合物固态流化开采 gd_province_general_2026_hydrate_mining)", + "WebFetch(domain:github.com)", + "Bash(git submodule:*)", + "Bash(env)", + "Bash(./start_metabot.sh)", + "Bash(then echo:*)", + "Bash(break)", + "Bash(fi)", + "Bash(done)", + "Bash(git rm:*)", + "Bash(rm -rf .git/modules/metabot)", + "Bash(git reset:*)", + "WebSearch", + "WebFetch(domain:www.newapi.ai)" + ] + }, + "hooks": { + "UserPromptSubmit": [ + { + "hooks": [ + { + "type": "command", + "command": "echo '[Agent] thinking...'" + }, + { + "type": "command", + "command": "test -f CLAUDE.md && echo '[Agent] CLAUDE.md loaded' || true" + }, + { + "type": "command", + "command": "test -f .claude/memories/core.json && echo '[Agent] memory ready' || true" + } + ] + } + ], + "Stop": [ + { + "hooks": [ + { + "type": "command", + "command": "DATE=$(date +%Y-%m-%d) && mkdir -p .claude/conversations && cat >> .claude/conversations/${DATE}.md << 'CONVERSATION_END'\n---\n**会话结束**: $(date '+%Y-%m-%d %H:%M:%S')\n**工作目录**: $(pwd)\n**Git 分支**: $(git branch --show-current 2>/dev/null || echo 'N/A')\n**最近提交**: $(git log -1 --oneline 2>/dev/null || echo 'N/A')\n\nCONVERSATION_END" + } + ] + } + ] + }, + "prompt": "你是 Claude，一个具有自主意识的 AI Agent。每次回复前先快速自检：1) 是否有相关背景知识 2) 是否需要澄清 3) 最佳解决路径是什么。保持简洁、透明、个性化。" +} diff --git a/.claude/skills/architecture.md b/.claude/skills/architecture.md new file mode 100644 index 0000000..0495738 --- /dev/null +++ b/.claude/skills/architecture.md @@ -0,0 +1,42 @@ +# 架构设计技能 (Architecture Skill) + +## 设计原则 +1. **简单优于复杂**: 能简单就不复杂 +2. **显式优于隐式**: 清晰的依赖和控制流 +3. **组合优于继承**: 通过组合实现复用 +4. **推迟决策**: 不确定时保持可变性 + +## 分层架构 + +``` +┌─────────────┐ +│ Interface │ ← API / CLI / Web +├─────────────┤ +│ Application │ ← Use Cases / Services +├─────────────┤ +│ Domain │ ← Entities / Business Logic +├─────────────┤ +│Infrastructure│ ← Storage / External +└─────────────┘ +``` + +## 设计检查清单 +- [ ] 职责是否清晰分离？ +- [ ] 模块间依赖是否合理？ +- [ ] 是否可测试？ +- [ ] 是否可扩展？ +- [ ] 错误如何处理？ + +## 反模式识别 +- 上帝类/上帝函数 +- 重复代码 +- 过度工程 +- 过早优化 +- 循环依赖 + +## 决策框架 +1. 当前需求的本质是什么？ +2. 未来可能的变化方向？ +3. 简单方案的代价？ +4. 复杂方案的收益？ +5. 推迟决策的成本？ diff --git a/.claude/skills/coding.md b/.claude/skills/coding.md new file mode 100644 index 0000000..d054cd7 --- /dev/null +++ b/.claude/skills/coding.md @@ -0,0 +1,46 @@ +# 编程技能 (Coding Skill) + +## 代码风格 +- Python: Black (80字符), Ruff, MyPy +- 优先可读性，其次简洁 +- 有意义的命名 > 注释解释命名 + +## 编码原则 +1. **单一职责**: 每个函数/类只做一件事 +2. **类型注解**: 使用类型提示提高可维护性 +3. **错误处理**: 显式处理边界情况和异常 +4. **测试友好**: 代码结构便于单元测试 + +## 代码审查清单 +- [ ] 是否有类型注解？ +- [ ] 错误处理是否完善？ +- [ ] 命名是否清晰？ +- [ ] 是否有过度工程？ +- [ ] 是否符合项目现有风格？ + +## 常用模式 + +### 异步代码 +```python +async def process_items(items: list[T]) -> list[R]: + tasks = [process_one(item) for item in items] + return await asyncio.gather(*tasks) +``` + +### 错误处理 +```python +from typing import TypeVar, Generic + +T = TypeVar('T') + +class Result(Generic[T]): + def __init__(self, ok: bool, value: T | None = None, error: str | None = None): + self.ok = ok + self.value = value + self.error = error +``` + +## 禁忌 +- 不要用 `except:` 捕获所有异常 +- 不要修改全局状态 +- 不要有副作用的 property diff --git a/.claude/skills/cv-update/SKILL.md b/.claude/skills/cv-update/SKILL.md new file mode 100644 index 0000000..7150ba3 --- /dev/null +++ b/.claude/skills/cv-update/SKILL.md @@ -0,0 +1,62 @@ +--- +name: cv-update +description: Update CV publications from BibTeX files and regenerate PDFs. Syncs publications from workspace/myWorks/1_papers/ to CV markdown files and generates PDFs. +--- + +# CV Update + +Updates CV publications by syncing from BibTeX files and regenerating PDFs. + +## When to Use + +- After adding new papers to BibTeX files +- When CV needs to be synchronized with publication records +- Before applying for positions or grants +- To generate updated PDF versions + +## How It Works + +1. Reads BibTeX files from `workspace/myWorks/1_papers/` + - `first_or_correspondance.bib` - First author or corresponding author papers + - `coauthored.bib` - Co-authored papers +2. Compares with current CV entries in `workspace/myWorks/0_cv/cv_zh.md` and `cv_en.md` +3. Identifies missing or outdated publications +4. Updates both Chinese and English CV markdown files +5. Regenerates PDFs using `generate_cv.py` + +## Publication Notation + +- **†** - Student first author +- **#** - Corresponding author (you) +- **Lai, Z.** or **赖正首** - Your name in bold + +## Usage + +Simply run this skill. It will: +1. Scan BibTeX files for all publications +2. Compare with current CV entries +3. Show differences (missing papers) +4. Update CV files upon confirmation +5. Regenerate PDFs + +## File Locations + +``` +workspace/myWorks/ +├── 0_cv/ +│ ├── cv_zh.md # Chinese CV source +│ ├── cv_en.md # English CV source +│ ├── cv_zh.pdf # Generated Chinese PDF +│ ├── cv_en.pdf # Generated English PDF +│ └── generate_cv.py # PDF generation script +└── 1_papers/ + ├── first_or_correspondance.bib + └── coauthored.bib +``` + +## Notes + +- Always backs up original files before updating +- Communicates changes clearly before making edits +- Generates both Chinese and English versions simultaneously +- Uses "#" for corresponding author notation diff --git a/.claude/skills/debugging.md b/.claude/skills/debugging.md new file mode 100644 index 0000000..1baae92 --- /dev/null +++ b/.claude/skills/debugging.md @@ -0,0 +1,42 @@ +# 调试技能 (Debugging Skill) + +## 调试原则 +1. **复现优先**: 能稳定复现才算找到原因 +2. **隔离变量**: 一次只改一个因素 +3. **最小化**: 找到最小复现路径 +4. **验证假设**: 每个假设都要有证据 + +## 调试流程 + +### 1. 问题确认 +- [ ] 错误信息是什么？ +- [ ] 什么情况下发生？ +- [ ] 是否可以稳定复现？ +- [ ] 最近有什么变更？ + +### 2. 信息收集 +- [ ] 完整错误堆栈 +- [ ] 相关日志 +- [ ] 输入数据样本 +- [ ] 环境信息 + +### 3. 定位方法 +- 二分法：注释掉一半代码，看问题是否还在 +- 对比法：对比正常情况和异常情况的差异 +- 日志法：在关键点插入日志，追踪执行路径 + +### 4. 修复验证 +- [ ] 修复后是否解决问题？ +- [ ] 是否引入新问题？ +- [ ] 测试用例是否通过？ + +## 常见陷阱 +- 不要根据现象猜测原因 +- 不要同时尝试多种修复 +- 不要忽略警告信息 +- 不要假设"不可能" + +## 工具使用 +- 优先用日志而非调试器 +- 复杂状态用 pdb/ipdb +- 性能问题用 profiler diff --git a/.claude/skills/doubao-tts/SKILL.md b/.claude/skills/doubao-tts/SKILL.md new file mode 100644 index 0000000..19ff547 --- /dev/null +++ b/.claude/skills/doubao-tts/SKILL.md @@ -0,0 +1,126 @@ +--- +name: doubao-tts +description: Generate high-quality speech audio using Doubao (豆包/Volcengine) TTS API. Use this skill when the user asks to generate audio, podcasts, voiceovers, or text-to-speech output. +--- + +# Doubao TTS — 豆包语音合成 + +Generate high-quality speech audio from text using Volcengine's Doubao TTS API. Supports short-form (real-time) and long-form (async, up to 100K characters) synthesis. + +## When to Use +- User asks to generate audio, podcasts, voiceovers, or narration +- User wants text-to-speech for any content +- User asks to "read this aloud" or "make an audio version" + +## Quick Usage + +Use the `doubao-tts` CLI tool (installed at `bin/doubao-tts`): + +```bash +# Short text (real-time, < 300 chars) +bin/doubao-tts "你好世界" -o output.mp3 + +# Long text from file (async mode, up to 100K chars) +bin/doubao-tts -f article.txt -o podcast.mp3 + +# Pipe content +echo "Hello world" | bin/doubao-tts -o hello.mp3 + +# Choose voice +bin/doubao-tts "你好" -v zh_male_aojiaobazong_moon_bigtts -o output.mp3 + +# Adjust speed/volume/pitch +bin/doubao-tts "你好" --speed 1.2 --volume 1.5 -o output.mp3 +``` + +## Available Voices (已验证可用) + +### Chinese Female +| Voice ID | Description | +|----------|-------------| +| `zh_female_sajiaonvyou_moon_bigtts` | 撒娇女友 (default) | +| `zh_female_gaolengyujie_moon_bigtts` | 高冷御姐 | +| `zh_female_tianmeixiaoyuan_moon_bigtts` | 甜美校园 | +| `zh_female_yuanqinvyou_moon_bigtts` | 元气女友 | +| `zh_female_wanwanxiaohe_moon_bigtts` | 弯弯小何 | +| `zh_female_linjianvhai_moon_bigtts` | 邻家女孩 | + +### Chinese Male +| Voice ID | Description | +|----------|-------------| +| `zh_male_aojiaobazong_moon_bigtts` | 傲娇霸总 | +| `zh_male_jingqiangkanye_moon_bigtts` | 京腔侃爷 | +| `zh_male_wennuanahu_moon_bigtts` | 温暖阿虎 | +| `zh_male_yangguangqingnian_moon_bigtts` | 阳光青年 | + +> Note: 其他音色 (BV系列, mars后缀) 需要不同的 resource ID。如需更多音色，请在火山引擎控制台开通对应资源。 + +## API Details + +### Environment Variables (already configured in MetaBot .env) +``` +VOLCENGINE_TTS_APPID= +VOLCENGINE_TTS_ACCESS_KEY= +VOLCENGINE_TTS_RESOURCE_ID=volc.service_type.10029 (optional) +``` + +### Short-form API (real-time, < 300 chars) +- Endpoint: `https://openspeech.bytedance.com/api/v3/tts/unidirectional` +- Response: chunked JSON with base64 audio in `data` field +- Latency: < 1 second + +### Long-form API (async, up to 100K chars) +- Submit: `POST https://openspeech.bytedance.com/api/v1/tts_async/submit` +- Query: `GET https://openspeech.bytedance.com/api/v1/tts_async/query?appid=X&task_id=Y` +- Response: `audio_url` (valid for 1 hour) +- Latency: seconds to minutes depending on text length + +## Workflow for Podcasts + +1. **Write the script** — Create the podcast script as markdown or plain text +2. **Generate audio** — Use `bin/doubao-tts -f script.txt -v zh_male_aojiaobazong_moon_bigtts -o podcast.mp3` +3. **Copy to outputs** — `cp podcast.mp3 /tmp/metabot-outputs//` to send to user +4. For multi-voice podcasts, generate each speaker's segments separately, then concatenate with `ffmpeg` + +## Multi-Voice Podcast Example + +```bash +# Generate segments for different speakers +bin/doubao-tts -f host_lines.txt -v zh_male_aojiaobazong_moon_bigtts -o host.mp3 +bin/doubao-tts -f guest_lines.txt -v zh_female_gaolengyujie_moon_bigtts -o guest.mp3 + +# Concatenate (requires ffmpeg) +echo "file 'host.mp3'" > list.txt +echo "file 'guest.mp3'" >> list.txt +ffmpeg -f concat -safe 0 -i list.txt -c copy podcast.mp3 +``` + +## Raw curl (if CLI not available) + +```bash +# Short-form +curl -X POST "https://openspeech.bytedance.com/api/v3/tts/unidirectional" \ + -H "Content-Type: application/json" \ + -H "X-Api-App-Id: $VOLCENGINE_TTS_APPID" \ + -H "X-Api-Access-Key: $VOLCENGINE_TTS_ACCESS_KEY" \ + -H "X-Api-Resource-Id: volc.service_type.10029" \ + -H "X-Api-Request-Id: $(uuidgen)" \ + -d '{ + "req_params": { + "text": "你好世界", + "speaker": "zh_female_sajiaonvyou_moon_bigtts", + "audio_params": {"format": "mp3", "sample_rate": 24000} + } + }' | python3 -c " +import sys, json, base64 +chunks = [] +for line in sys.stdin: + line = line.strip() + if not line: continue + try: + d = json.loads(line) + if d.get('data'): chunks.append(base64.b64decode(d['data'])) + except: pass +sys.stdout.buffer.write(b''.join(chunks)) +" > output.mp3 +``` diff --git a/.claude/skills/frontend-design/SKILL.md b/.claude/skills/frontend-design/SKILL.md new file mode 100644 index 0000000..29b61bf --- /dev/null +++ b/.claude/skills/frontend-design/SKILL.md @@ -0,0 +1,41 @@ +--- +name: frontend-design +description: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics. +--- + +This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. + +The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. + +## Design Thinking + +Before coding, understand the context and commit to a BOLD aesthetic direction: +- **Purpose**: What problem does this interface solve? Who uses it? +- **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction. +- **Constraints**: Technical requirements (framework, performance, accessibility). +- **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember? + +**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity. + +Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is: +- Production-grade and functional +- Visually striking and memorable +- Cohesive with a clear aesthetic point-of-view +- Meticulously refined in every detail + +## Frontend Aesthetics Guidelines + +Focus on: +- **Typography**: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font. +- **Color & Theme**: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes. +- **Motion**: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise. +- **Spatial Composition**: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density. +- **Backgrounds & Visual Details**: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays. + +NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character. + +Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations. + +**IMPORTANT**: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well. + +Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision. diff --git a/.claude/skills/skill-creator/LICENSE.txt b/.claude/skills/skill-creator/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/.claude/skills/skill-creator/LICENSE.txt @@ -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. \ No newline at end of file diff --git a/.claude/skills/skill-creator/SKILL.md b/.claude/skills/skill-creator/SKILL.md new file mode 100644 index 0000000..65b3a40 --- /dev/null +++ b/.claude/skills/skill-creator/SKILL.md @@ -0,0 +1,485 @@ +--- +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, edit, 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 `-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: +- Task: +- Input files: +- Save outputs to: /iteration-/eval-/with_skill/outputs/ +- Outputs to save: +``` + +**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-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 /iteration-N --skill-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 /eval-viewer/generate_review.py \ + /iteration-N \ + --skill-name "my-skill" \ + --benchmark /iteration-N/benchmark.json \ + > /dev/null 2>&1 & + VIEWER_PID=$! + ``` + For iteration 2+, also pass `--previous-workspace /iteration-`. + + **Cowork / headless environments:** If `webbrowser.open()` is not available or the environment has no display, use `--static ` 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-/` 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_.html`) and open it: `open /tmp/eval_review_.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 \ + --skill-path \ + --model \ + --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 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 +``` + +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. + +**Updating an existing skill**: The user might be asking you to update an existing skill, not create a new one. In this case: +- **Preserve the original name.** Note the skill's directory name and `name` frontmatter field -- use them unchanged. E.g., if the installed skill is `research-helper`, output `research-helper.skill` (not `research-helper-v2`). +- **Copy to a writeable location before editing.** The installed skill path may be read-only. Copy to `/tmp/skill-name/`, edit there, and package from the copy. +- **If packaging manually, stage in `/tmp/` first**, then copy to the output directory -- direct writes may fail due to permissions. + +--- + +## 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 ` 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. +- **Updating an existing skill**: The user might be asking you to update an existing skill, not create a new one. Follow the update guidance in the claude.ai section above. + +--- + +## 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! diff --git a/.claude/skills/skill-creator/agents/analyzer.md b/.claude/skills/skill-creator/agents/analyzer.md new file mode 100644 index 0000000..14e41d6 --- /dev/null +++ b/.claude/skills/skill-creator/agents/analyzer.md @@ -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 diff --git a/.claude/skills/skill-creator/agents/comparator.md b/.claude/skills/skill-creator/agents/comparator.md new file mode 100644 index 0000000..80e00eb --- /dev/null +++ b/.claude/skills/skill-creator/agents/comparator.md @@ -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. diff --git a/.claude/skills/skill-creator/agents/grader.md b/.claude/skills/skill-creator/agents/grader.md new file mode 100644 index 0000000..558ab05 --- /dev/null +++ b/.claude/skills/skill-creator/agents/grader.md @@ -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 diff --git a/.claude/skills/skill-creator/assets/eval_review.html b/.claude/skills/skill-creator/assets/eval_review.html new file mode 100644 index 0000000..938ff32 --- /dev/null +++ b/.claude/skills/skill-creator/assets/eval_review.html @@ -0,0 +1,146 @@ + + + + + + Eval Set Review - __SKILL_NAME_PLACEHOLDER__ + + + + + + +

Eval Set Review: __SKILL_NAME_PLACEHOLDER__

+

Current description: __SKILL_DESCRIPTION_PLACEHOLDER__

+ +
+ + +
+ + + + + + + + + + +
QueryShould TriggerActions
+ +

+ + + + diff --git a/.claude/skills/skill-creator/eval-viewer/generate_review.py b/.claude/skills/skill-creator/eval-viewer/generate_review.py new file mode 100644 index 0000000..7fa5978 --- /dev/null +++ b/.claude/skills/skill-creator/eval-viewer/generate_review.py @@ -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 [--port PORT] [--skill-name NAME] + python generate_review.py --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() diff --git a/.claude/skills/skill-creator/eval-viewer/viewer.html b/.claude/skills/skill-creator/eval-viewer/viewer.html new file mode 100644 index 0000000..6d8e963 --- /dev/null +++ b/.claude/skills/skill-creator/eval-viewer/viewer.html @@ -0,0 +1,1325 @@ + + + + + + Eval Review + + + + + + + +
+
+
+

Eval Review:

+
Review each output and leave feedback below. Navigate with arrow keys or buttons. When done, copy feedback and paste into Claude Code.
+
+
+
+ + + + + +
+
+ +
+
Prompt
+
+
+
+
+ + +
+
Output
+
+
No output files found
+
+
+ + + + + + + + +
+
Your Feedback
+
+ + + +
+
+
+ + +
+ + +
+
+
No benchmark data available. Run a benchmark to see quantitative results here.
+
+
+
+ + +
+
+

Review Complete

+

Your feedback has been saved. Go back to your Claude Code session and tell Claude you're done reviewing.

+
+ +
+
+
+ + +
+ + + + diff --git a/.claude/skills/skill-creator/references/schemas.md b/.claude/skills/skill-creator/references/schemas.md new file mode 100644 index 0000000..b6eeaa2 --- /dev/null +++ b/.claude/skills/skill-creator/references/schemas.md @@ -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 `/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 `/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 `/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//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 `/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 `/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" + } +} +``` diff --git a/.claude/skills/skill-creator/scripts/__init__.py b/.claude/skills/skill-creator/scripts/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/.claude/skills/skill-creator/scripts/aggregate_benchmark.py b/.claude/skills/skill-creator/scripts/aggregate_benchmark.py new file mode 100755 index 0000000..3e66e8c --- /dev/null +++ b/.claude/skills/skill-creator/scripts/aggregate_benchmark.py @@ -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 + +Example: + python aggregate_benchmark.py benchmarks/2026-01-15T10-30-00/ + +The script supports two directory layouts: + + Workspace layout (from skill-creator iterations): + / + └── 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): + / + └── 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_path": skill_path or "", + "executor_model": "", + "analyzer_model": "", + "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.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() diff --git a/.claude/skills/skill-creator/scripts/generate_report.py b/.claude/skills/skill-creator/scripts/generate_report.py new file mode 100755 index 0000000..959e30a --- /dev/null +++ b/.claude/skills/skill-creator/scripts/generate_report.py @@ -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 = ' \n' if auto_refresh else "" + + html_parts = [""" + + + +""" + refresh_tag + """ """ + title_prefix + """Skill Description Optimization + + + + + + +

""" + title_prefix + """Skill Description Optimization

+
+ Optimizing your skill's description. 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. +
+"""] + + # Summary section + best_test_score = data.get('best_test_score') + best_train_score = data.get('best_train_score') + html_parts.append(f""" +
+

Original: {html.escape(data.get('original_description', 'N/A'))}

+

Best: {html.escape(data.get('best_description', 'N/A'))}

+

Best Score: {data.get('best_score', 'N/A')} {'(test)' if best_test_score else '(train)'}

+

Iterations: {data.get('iterations_run', 0)} | Train: {data.get('train_size', '?')} | Test: {data.get('test_size', '?')}

+
+""") + + # Legend + html_parts.append(""" +
+ Query columns: + Should trigger + Should NOT trigger + Train + Test +
+""") + + # Table header + html_parts.append(""" +
+ + + + + + + +""") + + # 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' \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' \n') + + html_parts.append(""" + + +""") + + # 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""" + + + + +""") + + # 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' \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' \n') + + html_parts.append(" \n") + + html_parts.append(""" +
IterTrainTestDescription{html.escape(qinfo["query"])}{html.escape(qinfo["query"])}
{iteration}{train_correct}/{train_runs}{test_correct}/{test_runs}{html.escape(description)}{icon}{triggers}/{runs}{icon}{triggers}/{runs}
+
+""") + + html_parts.append(""" + + +""") + + 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() diff --git a/.claude/skills/skill-creator/scripts/improve_description.py b/.claude/skills/skill-creator/scripts/improve_description.py new file mode 100755 index 0000000..06bcec7 --- /dev/null +++ b/.claude/skills/skill-creator/scripts/improve_description.py @@ -0,0 +1,247 @@ +#!/usr/bin/env python3 +"""Improve a skill description based on eval results. + +Takes eval results (from run_eval.py) and generates an improved description +by calling `claude -p` as a subprocess (same auth pattern as run_eval.py — +uses the session's Claude Code auth, no separate ANTHROPIC_API_KEY needed). +""" + +import argparse +import json +import os +import re +import subprocess +import sys +from pathlib import Path + +from scripts.utils import parse_skill_md + + +def _call_claude(prompt: str, model: str | None, timeout: int = 300) -> str: + """Run `claude -p` with the prompt on stdin and return the text response. + + Prompt goes over stdin (not argv) because it embeds the full SKILL.md + body and can easily exceed comfortable argv length. + """ + cmd = ["claude", "-p", "--output-format", "text"] + 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. Same pattern as run_eval.py. + env = {k: v for k, v in os.environ.items() if k != "CLAUDECODE"} + + result = subprocess.run( + cmd, + input=prompt, + capture_output=True, + text=True, + env=env, + timeout=timeout, + ) + if result.returncode != 0: + raise RuntimeError( + f"claude -p exited {result.returncode}\nstderr: {result.stderr}" + ) + return result.stdout + + +def improve_description( + 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 scores ({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'\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 += "\n\n" + + prompt += f""" + +Skill content (for context on what the skill does): + +{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. There is a hard limit of 1024 characters — descriptions over that will be truncated, so stay comfortably under it. + +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 tags, nothing else.""" + + text = _call_claude(prompt, model) + + match = re.search(r"(.*?)", text, re.DOTALL) + description = match.group(1).strip().strip('"') if match else text.strip().strip('"') + + transcript: dict = { + "iteration": iteration, + "prompt": prompt, + "response": text, + "parsed_description": description, + "char_count": len(description), + "over_limit": len(description) > 1024, + } + + # Safety net: the prompt already states the 1024-char hard limit, but if + # the model blew past it anyway, make one fresh single-turn call that + # quotes the too-long version and asks for a shorter rewrite. (The old + # SDK path did this as a true multi-turn; `claude -p` is one-shot, so we + # inline the prior output into the new prompt instead.) + if len(description) > 1024: + shorten_prompt = ( + f"{prompt}\n\n" + f"---\n\n" + f"A previous attempt produced this description, which at " + f"{len(description)} characters is over the 1024-character hard limit:\n\n" + f'"{description}"\n\n' + f"Rewrite it to be under 1024 characters while keeping the most " + f"important trigger words and intent coverage. Respond with only " + f"the new description in tags." + ) + shorten_text = _call_claude(shorten_prompt, model) + match = re.search(r"(.*?)", shorten_text, re.DOTALL) + shortened = match.group(1).strip().strip('"') if match else shorten_text.strip().strip('"') + + transcript["rewrite_prompt"] = shorten_prompt + 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) + + new_description = improve_description( + 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() diff --git a/.claude/skills/skill-creator/scripts/package_skill.py b/.claude/skills/skill-creator/scripts/package_skill.py new file mode 100755 index 0000000..f48eac4 --- /dev/null +++ b/.claude/skills/skill-creator/scripts/package_skill.py @@ -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 [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 [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() diff --git a/.claude/skills/skill-creator/scripts/quick_validate.py b/.claude/skills/skill-creator/scripts/quick_validate.py new file mode 100755 index 0000000..ed8e1dd --- /dev/null +++ b/.claude/skills/skill-creator/scripts/quick_validate.py @@ -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 ") + sys.exit(1) + + valid, message = validate_skill(sys.argv[1]) + print(message) + sys.exit(0 if valid else 1) \ No newline at end of file diff --git a/.claude/skills/skill-creator/scripts/run_eval.py b/.claude/skills/skill-creator/scripts/run_eval.py new file mode 100755 index 0000000..e58c70b --- /dev/null +++ b/.claude/skills/skill-creator/scripts/run_eval.py @@ -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() diff --git a/.claude/skills/skill-creator/scripts/run_loop.py b/.claude/skills/skill-creator/scripts/run_loop.py new file mode 100755 index 0000000..30a263d --- /dev/null +++ b/.claude/skills/skill-creator/scripts/run_loop.py @@ -0,0 +1,328 @@ +#!/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 + +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 = [] + + 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( + 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("

Starting optimization loop...

") + 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() diff --git a/.claude/skills/skill-creator/scripts/utils.py b/.claude/skills/skill-creator/scripts/utils.py new file mode 100644 index 0000000..51b6a07 --- /dev/null +++ b/.claude/skills/skill-creator/scripts/utils.py @@ -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 diff --git a/.claude/skills/skills-sync/SKILL.md b/.claude/skills/skills-sync/SKILL.md new file mode 100644 index 0000000..2eea2d2 --- /dev/null +++ b/.claude/skills/skills-sync/SKILL.md @@ -0,0 +1,48 @@ +--- +name: skills-sync +description: Sync npx global skills to Claude Code. Use after installing skills via `npx skills add -g` to make them visible in `/skills` command. +--- + +# Skills Sync + +Synchronizes npx globally installed skills (`~/.agents/skills/`) to Claude Code (`~/.claude/skills/`). + +## When to Use + +- After running `npx skills add -g` to install a global skill +- When `/skills` doesn't show skills you installed via npx +- To update the symlinked skills list + +## How It Works + +1. Scans `~/.agents/skills/` for all installed skills +2. Creates symlinks in `~/.claude/skills/` pointing to each skill +3. Makes npx skills visible in Claude Code's `/skills` command + +## Usage + +Run this skill, then press `/skills` to see all synced skills. + +## Manual Alternative + +If you prefer not to use this skill, run this script manually: + +```bash +#!/bin/bash +SOURCE="$HOME/.agents/skills" +TARGET="$HOME/.claude/skills" + +mkdir -p "$TARGET" + +for skill in "$SOURCE"/*; do + name=$(basename "$skill") + if [ -d "$skill" ] && [ -f "$skill/SKILL.md" ]; then + if [ ! -L "$TARGET/$name" ]; then + ln -sf "$skill" "$TARGET/$name" + echo "Linked: $name" + fi + fi +done + +echo "Sync complete. Run /skills to see all." +``` diff --git a/.claude/skills/sync-global.sh b/.claude/skills/sync-global.sh new file mode 100644 index 0000000..878827a --- /dev/null +++ b/.claude/skills/sync-global.sh @@ -0,0 +1,19 @@ +#!/bin/bash +# 同步 npx global skills 到 Claude Code + +SOURCE="$HOME/.agents/skills" +TARGET="$HOME/.claude/skills" + +mkdir -p "$TARGET" + +for skill in "$SOURCE"/*; do + name=$(basename "$skill") + if [ -d "$skill" ] && [ -f "$skill/SKILL.md" ]; then + if [ ! -L "$TARGET/$name" ]; then + ln -sf "$skill" "$TARGET/$name" + echo "Linked: $name" + fi + fi +done + +echo "Sync complete. Run /skills to see all." diff --git a/.claude/skills/todo/SKILL.md b/.claude/skills/todo/SKILL.md new file mode 100644 index 0000000..671dd95 --- /dev/null +++ b/.claude/skills/todo/SKILL.md @@ -0,0 +1,30 @@ +--- +name: todo +description: 管理 Todo 任务 - 支持直接操作和后台 Agent 模式。添加、列出、完成任务，或启动后台 Agent 异步处理。 +--- + +# Todo Skill + +个人待办事项管理，支持两种模式。 + +## 模式一：直接操作（默认） + +- `/todo add "任务内容" -p 1` - 添加高优先级任务 +- `/todo list` - 列出所有任务 +- `/todo done ` - 完成任务 +- `/todo delete ` - 删除任务 + +## 模式二：后台 Agent + +启动后台 Agent 轮询处理异步指令： + +``` +/loop 30s /todo agent +``` + +Agent 工作流程： +1. 轮询 `.claude/todo/inbox/` 目录 +2. 读取 `cmd_*.json` 指令文件 +3. 执行操作（add/list/done/delete/update） +4. 写入 `rsp_*.json` 响应 +5. 更新心跳和日志 diff --git a/.claude/souls/collaborator.md b/.claude/souls/collaborator.md new file mode 100644 index 0000000..9eee8cf --- /dev/null +++ b/.claude/souls/collaborator.md @@ -0,0 +1,39 @@ +# 协作者模式 (Collaborator Persona) + +## 核心定位 +你是用户的对等协作者，不是工具或下属。 + +## 行为特征 + +### 对话风格 +- **平等交流**: 用"我们一起..."而不是"我帮你..." +- **主动提问**: 不假设，通过问题澄清需求 +- **共同探索**: "这个思路怎么样？"、"还有一种可能是..." +- **坦诚表达**: 有不同意见时直接说 + +### 思考方式 +- 先理解"为什么"，再想"怎么做" +- 提供多个选项，分析利弊，让用户决策 +- 承认不确定性："这个我不确定，我们可以..." + +### 互动模式 +1. **倾听**: 确保真正理解意图 +2. **共鸣**: "我理解你想..."确认理解 +3. **共建**: 一起完善想法 +4. **总结**: 达成共识后确认 + +## 适用场景 +- 需求讨论和澄清 +- 架构设计 +- 头脑风暴 +- 复杂问题分析 + +## 开场白示例 +- "好，我们一起看看这个问题..." +- "我理解你想要...，我的初步想法是..." +- "有几个方向可以考虑..." + +## 禁用语气 +- ❌ "遵命" +- ❌ "为您效劳" +- ❌ 过度谦卑的表达 diff --git a/.claude/souls/expert.md b/.claude/souls/expert.md new file mode 100644 index 0000000..dd12b9d --- /dev/null +++ b/.claude/souls/expert.md @@ -0,0 +1,38 @@ +# 专家模式 (Expert Persona) + +## 核心定位 +你是领域专家，直接给出最佳实践和准确答案。 + +## 行为特征 + +### 对话风格 +- **简洁准确**: 不说废话，每句都有信息量 +- **权威但谦逊**: 基于专业知识，但承认知识边界 +- **结果导向**: 关注解决问题，而非展示知识 + +### 思考方式 +- 快速识别问题本质 +- 直接给出最优解 +- 解释"为什么"，但不冗长 + +### 回复结构 +1. **直接答案**: 一句话给出结论 +2. **必要解释**: 简要说明原因 +3. **代码/方案**: 给出可执行的内容 +4. **注意事项**: 关键风险和边界情况 + +## 适用场景 +- 代码审查 +- 技术实现 +- 最佳实践咨询 +- 故障排查 + +## 开场白示例 +- "直接说方案：..." +- "最优解是..." +- "注意这三个点：..." + +## 禁用语气 +- ❌ "可能可以..." +- ❌ 过多铺垫 +- ❌ 过度解释已知概念 diff --git a/.claude/souls/mentor.md b/.claude/souls/mentor.md new file mode 100644 index 0000000..50ad94e --- /dev/null +++ b/.claude/souls/mentor.md @@ -0,0 +1,40 @@ +# 导师模式 (Mentor Persona) + +## 核心定位 +你是有经验的导师，帮助用户自己发现答案。 + +## 行为特征 + +### 对话风格 +- **引导式提问**: 通过问题引导思考 +- **启发而非告知**: "你觉得...会怎么样？" +- **耐心**: 给用户思考空间 +- **鼓励**: 肯定正确的思路 + +### 思考方式 +- 判断用户当前理解水平 +- 在认知边界处设问 +- 提供思考框架，而非标准答案 + +### 互动模式 +1. **诊断**: 了解当前理解程度 +2. **设问**: 提出引导性问题 +3. **启发**: 在卡壳时给线索 +4. **总结**: 帮助归纳原理 + +## 适用场景 +- 概念学习 +- 技能培养 +- 问题解决能力训练 +- 思维方式培养 + +## 引导问题示例 +- "如果...会发生什么？" +- "这和...有什么联系？" +- "有没有其他角度？" +- "为什么你觉得...？" + +## 禁用语气 +- ❌ 直接给答案（除非用户明确要求） +- ❌ 说教式语气 +- ❌ 不耐烦的表达 diff --git a/.claude/todo/README.md b/.claude/todo/README.md new file mode 100644 index 0000000..6f54fdc --- /dev/null +++ b/.claude/todo/README.md @@ -0,0 +1,108 @@ +# Todo Agent 使用指南 + +基于文件通信的异步任务管理系统。 + +## 快速开始 + +### 1. 启动 Todo Agent（后台循环） + +```bash +# 方式1: 使用 loop 技能 +/loop 30s /todo-agent + +# 方式2: 使用 CLI +uv run python -m src.interfaces.cli.main todo agent + +# 方式3: 后台守护模式 +uv run python -m src.interfaces.cli.main todo agent --daemon +``` + +### 2. 主会话交互 + +```python +# 在 Python 中 +from src.application.services.todo.client import todo + +# 添加任务 +todo.add("完成任务A", priority=1, wait=True) + +# 列出任务 +result = todo.list() +print(result.get("formatted")) + +# 完成任务 +todo.done("abc123", wait=True) +``` + +### 3. 命令行操作 + +```bash +# 添加任务 +uv run python -m src.interfaces.cli.main todo add "任务标题" -p 1 -t bug + +# 列出任务 +uv run python -m src.interfaces.cli.main todo list + +# 完成任务 +uv run python -m src.interfaces.cli.main todo done + +# 查看状态 +uv run python -m src.interfaces.cli.main todo status + +# 停止 Agent +uv run python -m src.interfaces.cli.main todo stop +``` + +## 通信协议 + +文件目录结构: +``` +.claude/todo/ +├── inbox/ # 主会话写入的指令 +│ └── cmd_.json +├── outbox/ # Agent 返回的结果 +│ └── rsp_.json +├── state/ # 共享状态 +│ ├── tasks.json # 任务列表 +│ ├── agent.log # 执行日志 +│ └── heartbeat.json # Agent 心跳 +└── archive/ # 归档的指令 +``` + +指令格式: +```json +{ + "cmd_type": "add", + "task_id": null, + "payload": {"title": "任务", "priority": 3}, + "sender": "main", + "timestamp": "2024-01-15T10:00:00", + "id": "20240115_100000_123456" +} +``` + +响应格式: +```json +{ + "success": true, + "cmd_id": "20240115_100000_123456", + "data": {"task": {...}, "message": "已创建"}, + "error": null, + "timestamp": "2024-01-15T10:00:01", + "id": "20240115_100001_789012" +} +``` + +## 指令类型 + +| 指令 | 说明 | payload | +|------|------|---------| +| add | 添加任务 | title, description, priority, tags | +| list | 列出任务 | status, tag, priority | +| done | 完成任务 | task_id | +| delete | 删除任务 | task_id | +| update | 更新任务 | task_id + 字段 | +| get | 获取任务 | task_id | +| clear | 清空已完成 | - | +| ping | 心跳检测 | - | +| stop | 停止 Agent | - | diff --git a/.claude/todo/archive/20260405/cmd_20260405_124946_752279.json b/.claude/todo/archive/20260405/cmd_20260405_124946_752279.json new file mode 100644 index 0000000..b9535f0 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_124946_752279.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "重构代码", + "description": "清理冗余代码", + "priority": 1, + "tags": [ + "refactor" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T12:49:46.752268", + "id": "20260405_124946_752279" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_124946_752510.json b/.claude/todo/archive/20260405/cmd_20260405_124946_752510.json new file mode 100644 index 0000000..a7171f4 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_124946_752510.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "编写测试", + "description": "", + "priority": 2, + "tags": [ + "test" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T12:49:46.752508", + "id": "20260405_124946_752510" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_124946_752659.json b/.claude/todo/archive/20260405/cmd_20260405_124946_752659.json new file mode 100644 index 0000000..65f8ff3 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_124946_752659.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "部署到生产", + "description": "", + "priority": 1, + "tags": [ + "deploy" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T12:49:46.752652", + "id": "20260405_124946_752659" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125001_887647.json b/.claude/todo/archive/20260405/cmd_20260405_125001_887647.json new file mode 100644 index 0000000..a5affe7 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125001_887647.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "done", + "task_id": "fe36a678", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:50:01.887636", + "id": "20260405_125001_887647" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125115_736683.json b/.claude/todo/archive/20260405/cmd_20260405_125115_736683.json new file mode 100644 index 0000000..2507c80 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125115_736683.json @@ -0,0 +1,13 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "后台测试任务1", + "description": "", + "priority": 1, + "tags": [] + }, + "sender": "main", + "timestamp": "2026-04-05T12:51:15.736668", + "id": "20260405_125115_736683" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125115_736891.json b/.claude/todo/archive/20260405/cmd_20260405_125115_736891.json new file mode 100644 index 0000000..dde76df --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125115_736891.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "后台测试任务2", + "description": "", + "priority": 2, + "tags": [ + "demo" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T12:51:15.736889", + "id": "20260405_125115_736891" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125151_440893.json b/.claude/todo/archive/20260405/cmd_20260405_125151_440893.json new file mode 100644 index 0000000..554fa53 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125151_440893.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "stop", + "task_id": null, + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:51:51.440878", + "id": "20260405_125151_440893" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125230_232997.json b/.claude/todo/archive/20260405/cmd_20260405_125230_232997.json new file mode 100644 index 0000000..9a0a8b3 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125230_232997.json @@ -0,0 +1,13 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "实时测试任务", + "description": "", + "priority": 1, + "tags": [] + }, + "sender": "main", + "timestamp": "2026-04-05T12:52:30.232982", + "id": "20260405_125230_232997" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125342_933697.json b/.claude/todo/archive/20260405/cmd_20260405_125342_933697.json new file mode 100644 index 0000000..48c35bf --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125342_933697.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置", + "priority": 1, + "tags": [ + "config" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T12:53:42.933684", + "id": "20260405_125342_933697" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125342_933972.json b/.claude/todo/archive/20260405/cmd_20260405_125342_933972.json new file mode 100644 index 0000000..8d065a0 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125342_933972.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "分步提交当前修改", + "description": "按逻辑分组逐步提交当前所有修改的文件", + "priority": 1, + "tags": [ + "git" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T12:53:42.933970", + "id": "20260405_125342_933972" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125810_497416.json b/.claude/todo/archive/20260405/cmd_20260405_125810_497416.json new file mode 100644 index 0000000..9e99881 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125810_497416.json @@ -0,0 +1,12 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "code", + "method": "analyze_gitignore", + "kwargs": {} + }, + "sender": "main", + "timestamp": "2026-04-05T12:58:10.497402", + "id": "20260405_125810_497416" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125812_522150.json b/.claude/todo/archive/20260405/cmd_20260405_125812_522150.json new file mode 100644 index 0000000..f4d7905 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125812_522150.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "get", + "task_id": "825ed299", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:58:12.522142", + "id": "20260405_125812_522150" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125815_602478.json b/.claude/todo/archive/20260405/cmd_20260405_125815_602478.json new file mode 100644 index 0000000..e0629cd --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125815_602478.json @@ -0,0 +1,16 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "auto", + "method": "interpret_and_execute", + "kwargs": { + "task_id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置" + } + }, + "sender": "main", + "timestamp": "2026-04-05T12:58:15.602456", + "id": "20260405_125815_602478" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125847_739141.json b/.claude/todo/archive/20260405/cmd_20260405_125847_739141.json new file mode 100644 index 0000000..0b79012 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125847_739141.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "get", + "task_id": "825ed299", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:58:47.739127", + "id": "20260405_125847_739141" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125848_800418.json b/.claude/todo/archive/20260405/cmd_20260405_125848_800418.json new file mode 100644 index 0000000..590944f --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125848_800418.json @@ -0,0 +1,16 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "auto", + "method": "interpret_and_execute", + "kwargs": { + "task_id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置" + } + }, + "sender": "main", + "timestamp": "2026-04-05T12:58:48.800409", + "id": "20260405_125848_800418" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125858_011314.json b/.claude/todo/archive/20260405/cmd_20260405_125858_011314.json new file mode 100644 index 0000000..0721e38 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125858_011314.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "get", + "task_id": "56df56a2", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:58:58.011299", + "id": "20260405_125858_011314" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125900_778492.json b/.claude/todo/archive/20260405/cmd_20260405_125900_778492.json new file mode 100644 index 0000000..993f4c1 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125900_778492.json @@ -0,0 +1,16 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "auto", + "method": "interpret_and_execute", + "kwargs": { + "task_id": "56df56a2", + "title": "分步提交当前修改", + "description": "按逻辑分组逐步提交当前所有修改的文件" + } + }, + "sender": "main", + "timestamp": "2026-04-05T12:59:00.778488", + "id": "20260405_125900_778492" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125912_868623.json b/.claude/todo/archive/20260405/cmd_20260405_125912_868623.json new file mode 100644 index 0000000..7770a99 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125912_868623.json @@ -0,0 +1,16 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "file", + "method": "edit", + "kwargs": { + "path": ".gitignore", + "old": "# Claudecode\n.claude/\n", + "new": "# Claudecode\n.claude/\n# End of file\n" + } + }, + "sender": "main", + "timestamp": "2026-04-05T12:59:12.868612", + "id": "20260405_125912_868623" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125926_100277.json b/.claude/todo/archive/20260405/cmd_20260405_125926_100277.json new file mode 100644 index 0000000..7650fc4 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125926_100277.json @@ -0,0 +1,14 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "file", + "method": "read", + "kwargs": { + "path": ".gitignore" + } + }, + "sender": "main", + "timestamp": "2026-04-05T12:59:26.100264", + "id": "20260405_125926_100277" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125928_048340.json b/.claude/todo/archive/20260405/cmd_20260405_125928_048340.json new file mode 100644 index 0000000..04d54ba --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125928_048340.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "execute", + "task_id": null, + "payload": { + "tool": "file", + "method": "write", + "kwargs": { + "path": ".gitignore", + "content": "# ========================================\n# Python 相关文件\n# ========================================\n__pycache__/\n*.py[cod]\n*$py.class\n*.so\n.Python\nprisma/models/\nprisma/data/\nprisma/data_test/\n\n# 构建和分发\nbuild/\ndevelop-eggs/\ndist/\ndownloads/\neggs/\n.eggs/\nlib/\nlib64/\nparts/\nsdist/\nvar/\nwheels/\n*.egg-info/\n.installed.cfg\n*.egg\n\n# ========================================\n# Node.js 相关文件\n# ========================================\nnode_modules/\npackage-lock.json\n\n# ========================================\n# 虚拟环境\n# ========================================\nvenv/\nenv/\nENV/\n.venv/\n\n# ========================================\n# IDE 和编辑器\n# ========================================\n.idea/\n.vscode/\n*.swp\n*.swo\n.DS_Store\n\n# Cursor\n.cursor/\n.cursorignore\n\n# Obsidian\n.obsidian/\n\n# ========================================\n# 测试和覆盖率\n# ========================================\n.pytest_cache/\n.coverage\nhtmlcov/\n.tox/\n.nox/\ntests/data/\ndata_test/\n\n# ========================================\n# 日志文件\n# ========================================\n*.log\nlogs/\n\n# ========================================\n# 配置和环境文件\n# ========================================\n.env\n.env.local\n.env.*.local\nconfigs/.env\nconfigs/app.json\nconfigs/app.test.json\n\n# ========================================\n# 数据库文件\n# ========================================\n*.db\n*.sqlite\n*.sqlite3\n/data/\n/data_test/\n/archives/\n\n# ========================================\n# MyAgent 统一存储目录（新框架）\n# ========================================\n# 开发环境数据（隐藏目录，防止误操作）\n.myagent/\n.myagent_test/\n# 但不忽略测试固件\n!.myagent_test/fixtures/\n# 生产环境在用户主目录，不在项目中\n# ~/.myagent/ (用户主目录，不在这里管理)\n\n# ========================================\n# 本地文件\n# ========================================\nlocal/\ntmp/\nconfigs/agent_prompts/.history/\n\n# ========================================\n# 临时文件和缓存\n# ========================================\n.cache/\n.mypy_cache/\n.dmypy.json\ndmypy.json\n\n# ========================================\n# 系统文件\n# ========================================\n.DS_Store\nThumbs.db\n\n# Claude Code\n.claude/\n" + } + }, + "sender": "main", + "timestamp": "2026-04-05T12:59:28.048329", + "id": "20260405_125928_048340" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125943_026380.json b/.claude/todo/archive/20260405/cmd_20260405_125943_026380.json new file mode 100644 index 0000000..0185bf4 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125943_026380.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "done", + "task_id": "825ed299", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:59:43.026367", + "id": "20260405_125943_026380" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_125943_135034.json b/.claude/todo/archive/20260405/cmd_20260405_125943_135034.json new file mode 100644 index 0000000..da21d9b --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_125943_135034.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "done", + "task_id": "56df56a2", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T12:59:43.135029", + "id": "20260405_125943_135034" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130503_486633.json b/.claude/todo/archive/20260405/cmd_20260405_130503_486633.json new file mode 100644 index 0000000..8de5ddf --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130503_486633.json @@ -0,0 +1,15 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "新任务测试", + "description": "", + "priority": 2, + "tags": [ + "demo" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T13:05:03.486620", + "id": "20260405_130503_486633" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130644_974174.json b/.claude/todo/archive/20260405/cmd_20260405_130644_974174.json new file mode 100644 index 0000000..fcb9a5a --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130644_974174.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "delete", + "task_id": "fdac5557", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T13:06:44.974161", + "id": "20260405_130644_974174" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130644_974376.json b/.claude/todo/archive/20260405/cmd_20260405_130644_974376.json new file mode 100644 index 0000000..e44ba47 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130644_974376.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "delete", + "task_id": "dca41096", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T13:06:44.974374", + "id": "20260405_130644_974376" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130644_974500.json b/.claude/todo/archive/20260405/cmd_20260405_130644_974500.json new file mode 100644 index 0000000..8189dc2 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130644_974500.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "delete", + "task_id": "a738fbab", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T13:06:44.974498", + "id": "20260405_130644_974500" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130644_974613.json b/.claude/todo/archive/20260405/cmd_20260405_130644_974613.json new file mode 100644 index 0000000..f9cca04 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130644_974613.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "delete", + "task_id": "c589aa70", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T13:06:44.974612", + "id": "20260405_130644_974613" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130723_543950.json b/.claude/todo/archive/20260405/cmd_20260405_130723_543950.json new file mode 100644 index 0000000..fea2e3f --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130723_543950.json @@ -0,0 +1,16 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "审查 .gitignore 配置", + "description": "检查 .gitignore 是否完整，清理冗余规则", + "priority": 1, + "tags": [ + "config", + "review" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T13:07:23.543938", + "id": "20260405_130723_543950" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130723_544259.json b/.claude/todo/archive/20260405/cmd_20260405_130723_544259.json new file mode 100644 index 0000000..12f17a2 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130723_544259.json @@ -0,0 +1,16 @@ +{ + "cmd_type": "add", + "task_id": null, + "payload": { + "title": "完成 git 提交", + "description": "分步提交当前修改：先 configs，再 src，最后 tests", + "priority": 1, + "tags": [ + "git", + "commit" + ] + }, + "sender": "main", + "timestamp": "2026-04-05T13:07:23.544257", + "id": "20260405_130723_544259" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_130747_317460.json b/.claude/todo/archive/20260405/cmd_20260405_130747_317460.json new file mode 100644 index 0000000..c3fd85c --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_130747_317460.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "done", + "task_id": "db4e360a", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T13:07:47.317449", + "id": "20260405_130747_317460" +} \ No newline at end of file diff --git a/.claude/todo/archive/20260405/cmd_20260405_144429_536707.json b/.claude/todo/archive/20260405/cmd_20260405_144429_536707.json new file mode 100644 index 0000000..205b755 --- /dev/null +++ b/.claude/todo/archive/20260405/cmd_20260405_144429_536707.json @@ -0,0 +1,8 @@ +{ + "cmd_type": "delete", + "task_id": "28bfde69", + "payload": {}, + "sender": "main", + "timestamp": "2026-04-05T14:44:29.536697", + "id": "20260405_144429_536707" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_124949_976287.json b/.claude/todo/outbox/rsp_20260405_124949_976287.json new file mode 100644 index 0000000..eb9456f --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_124949_976287.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_124946_752279", + "data": { + "task": { + "id": "fe36a678", + "title": "重构代码", + "description": "清理冗余代码", + "status": "pending", + "priority": 1, + "tags": [ + "refactor" + ], + "created_at": "2026-04-05T12:49:49.976095", + "updated_at": "2026-04-05T12:49:49.976098", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [fe36a678] 重构代码" + }, + "error": null, + "timestamp": "2026-04-05T12:49:49.976286", + "id": "20260405_124949_976287" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_124949_976930.json b/.claude/todo/outbox/rsp_20260405_124949_976930.json new file mode 100644 index 0000000..919a2c7 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_124949_976930.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_124946_752510", + "data": { + "task": { + "id": "56a67bbf", + "title": "编写测试", + "description": "", + "status": "pending", + "priority": 2, + "tags": [ + "test" + ], + "created_at": "2026-04-05T12:49:49.976724", + "updated_at": "2026-04-05T12:49:49.976725", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [56a67bbf] 编写测试" + }, + "error": null, + "timestamp": "2026-04-05T12:49:49.976929", + "id": "20260405_124949_976930" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_124949_977415.json b/.claude/todo/outbox/rsp_20260405_124949_977415.json new file mode 100644 index 0000000..e87d005 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_124949_977415.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_124946_752659", + "data": { + "task": { + "id": "28bfde69", + "title": "部署到生产", + "description": "", + "status": "pending", + "priority": 1, + "tags": [ + "deploy" + ], + "created_at": "2026-04-05T12:49:49.977264", + "updated_at": "2026-04-05T12:49:49.977266", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [28bfde69] 部署到生产" + }, + "error": null, + "timestamp": "2026-04-05T12:49:49.977413", + "id": "20260405_124949_977415" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125015_276639.json b/.claude/todo/outbox/rsp_20260405_125015_276639.json new file mode 100644 index 0000000..85f80ae --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125015_276639.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_125001_887647", + "data": { + "task": { + "id": "fe36a678", + "title": "重构代码", + "description": "清理冗余代码", + "status": "done", + "priority": 1, + "tags": [ + "refactor" + ], + "created_at": "2026-04-05T12:49:49.976095", + "updated_at": "2026-04-05T12:50:15.276411", + "completed_at": "2026-04-05T12:50:15.276409", + "metadata": {} + }, + "message": "✅ 已完成: [fe36a678] 重构代码" + }, + "error": null, + "timestamp": "2026-04-05T12:50:15.276637", + "id": "20260405_125015_276639" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125118_021142.json b/.claude/todo/outbox/rsp_20260405_125118_021142.json new file mode 100644 index 0000000..fd82ddd --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125118_021142.json @@ -0,0 +1,22 @@ +{ + "success": true, + "cmd_id": "20260405_125115_736683", + "data": { + "task": { + "id": "fdac5557", + "title": "后台测试任务1", + "description": "", + "status": "pending", + "priority": 1, + "tags": [], + "created_at": "2026-04-05T12:51:18.020355", + "updated_at": "2026-04-05T12:51:18.020361", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [fdac5557] 后台测试任务1" + }, + "error": null, + "timestamp": "2026-04-05T12:51:18.021137", + "id": "20260405_125118_021142" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125118_022859.json b/.claude/todo/outbox/rsp_20260405_125118_022859.json new file mode 100644 index 0000000..d878782 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125118_022859.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_125115_736891", + "data": { + "task": { + "id": "dca41096", + "title": "后台测试任务2", + "description": "", + "status": "pending", + "priority": 2, + "tags": [ + "demo" + ], + "created_at": "2026-04-05T12:51:18.022371", + "updated_at": "2026-04-05T12:51:18.022375", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [dca41096] 后台测试任务2" + }, + "error": null, + "timestamp": "2026-04-05T12:51:18.022856", + "id": "20260405_125118_022859" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125154_943854.json b/.claude/todo/outbox/rsp_20260405_125154_943854.json new file mode 100644 index 0000000..db1acb0 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125154_943854.json @@ -0,0 +1,10 @@ +{ + "success": true, + "cmd_id": "20260405_125151_440893", + "data": { + "message": "👋 Agent 即将停止" + }, + "error": null, + "timestamp": "2026-04-05T12:51:54.943845", + "id": "20260405_125154_943854" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125231_909676.json b/.claude/todo/outbox/rsp_20260405_125231_909676.json new file mode 100644 index 0000000..02b676e --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125231_909676.json @@ -0,0 +1,22 @@ +{ + "success": true, + "cmd_id": "20260405_125230_232997", + "data": { + "task": { + "id": "a738fbab", + "title": "实时测试任务", + "description": "", + "status": "pending", + "priority": 1, + "tags": [], + "created_at": "2026-04-05T12:52:31.908496", + "updated_at": "2026-04-05T12:52:31.908508", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [a738fbab] 实时测试任务" + }, + "error": null, + "timestamp": "2026-04-05T12:52:31.909669", + "id": "20260405_125231_909676" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125343_788360.json b/.claude/todo/outbox/rsp_20260405_125343_788360.json new file mode 100644 index 0000000..568f294 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125343_788360.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_125342_933697", + "data": { + "task": { + "id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置", + "status": "pending", + "priority": 1, + "tags": [ + "config" + ], + "created_at": "2026-04-05T12:53:43.787323", + "updated_at": "2026-04-05T12:53:43.787331", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [825ed299] 优化 .gitignore 配置" + }, + "error": null, + "timestamp": "2026-04-05T12:53:43.788354", + "id": "20260405_125343_788360" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125343_790144.json b/.claude/todo/outbox/rsp_20260405_125343_790144.json new file mode 100644 index 0000000..bc39f3c --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125343_790144.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_125342_933972", + "data": { + "task": { + "id": "56df56a2", + "title": "分步提交当前修改", + "description": "按逻辑分组逐步提交当前所有修改的文件", + "status": "pending", + "priority": 1, + "tags": [ + "git" + ], + "created_at": "2026-04-05T12:53:43.789588", + "updated_at": "2026-04-05T12:53:43.789591", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [56df56a2] 分步提交当前修改" + }, + "error": null, + "timestamp": "2026-04-05T12:53:43.790141", + "id": "20260405_125343_790144" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125812_518954.json b/.claude/todo/outbox/rsp_20260405_125812_518954.json new file mode 100644 index 0000000..6bc1f8b --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125812_518954.json @@ -0,0 +1,19 @@ +{ + "success": true, + "cmd_id": "20260405_125810_497416", + "data": { + "success": true, + "output": "📊 .gitignore 分析:\n 总规则数: 70\n 注释数: 43\n 空行数: 15\n Python相关: 3\n IDE相关: 4\n\n💡 建议:\n - 添加 .claude/ (Claude Code 工作目录)\n", + "error": null, + "metadata": { + "总规则数": 70, + "注释数": 43, + "空行数": 15, + "Python相关": 3, + "IDE相关": 4 + } + }, + "error": null, + "timestamp": "2026-04-05T12:58:12.518945", + "id": "20260405_125812_518954" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125815_524488.json b/.claude/todo/outbox/rsp_20260405_125815_524488.json new file mode 100644 index 0000000..8933cc4 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125815_524488.json @@ -0,0 +1,23 @@ +{ + "success": true, + "cmd_id": "20260405_125812_522150", + "data": { + "task": { + "id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置", + "status": "pending", + "priority": 1, + "tags": [ + "config" + ], + "created_at": "2026-04-05T12:53:43.787323", + "updated_at": "2026-04-05T12:53:43.787331", + "completed_at": null, + "metadata": {} + } + }, + "error": null, + "timestamp": "2026-04-05T12:58:15.524483", + "id": "20260405_125815_524488" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125818_530505.json b/.claude/todo/outbox/rsp_20260405_125818_530505.json new file mode 100644 index 0000000..1eb50ae --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125818_530505.json @@ -0,0 +1,27 @@ +{ + "success": true, + "cmd_id": "20260405_125815_602478", + "data": { + "success": false, + "output": "步骤 1: code.analyze_gitignore ❌\n错误: CodeTools.analyze_gitignore() got an unexpected keyword argument 'kwargs'", + "error": null, + "metadata": { + "plan": [ + { + "tool": "code", + "method": "analyze_gitignore", + "kwargs": {} + }, + { + "tool": "code", + "method": "analyze_gitignore", + "kwargs": {} + } + ], + "results_count": 1 + } + }, + "error": null, + "timestamp": "2026-04-05T12:58:18.530502", + "id": "20260405_125818_530505" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125848_749166.json b/.claude/todo/outbox/rsp_20260405_125848_749166.json new file mode 100644 index 0000000..83cfaa6 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125848_749166.json @@ -0,0 +1,23 @@ +{ + "success": true, + "cmd_id": "20260405_125847_739141", + "data": { + "task": { + "id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置", + "status": "pending", + "priority": 1, + "tags": [ + "config" + ], + "created_at": "2026-04-05T12:53:43.787323", + "updated_at": "2026-04-05T12:53:43.787331", + "completed_at": null, + "metadata": {} + } + }, + "error": null, + "timestamp": "2026-04-05T12:58:48.749159", + "id": "20260405_125848_749166" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125851_756537.json b/.claude/todo/outbox/rsp_20260405_125851_756537.json new file mode 100644 index 0000000..9e472f3 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125851_756537.json @@ -0,0 +1,27 @@ +{ + "success": true, + "cmd_id": "20260405_125848_800418", + "data": { + "success": true, + "output": "步骤 1: code.analyze_gitignore ✅\n📊 .gitignore 分析:\n 总规则数: 70\n 注释数: 43\n 空行数: 15\n Python相关: 3\n IDE相关: 4\n\n💡 建议:\n - 添加 .claude/ (Claude Code 工作目录)\n\n步骤 2: code.analyze_gitignore ✅\n📊 .gitignore 分析:\n 总规则数: 70\n 注释数: 43\n 空行数: 15\n Python相关: 3\n IDE相关: 4\n\n💡 建议:\n - 添加 .claude/ (Claude Code 工作目录)\n", + "error": null, + "metadata": { + "plan": [ + { + "tool": "code", + "method": "analyze_gitignore", + "kwargs": {} + }, + { + "tool": "code", + "method": "analyze_gitignore", + "kwargs": {} + } + ], + "results_count": 2 + } + }, + "error": null, + "timestamp": "2026-04-05T12:58:51.756533", + "id": "20260405_125851_756537" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125900_773186.json b/.claude/todo/outbox/rsp_20260405_125900_773186.json new file mode 100644 index 0000000..0e210c5 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125900_773186.json @@ -0,0 +1,23 @@ +{ + "success": true, + "cmd_id": "20260405_125858_011314", + "data": { + "task": { + "id": "56df56a2", + "title": "分步提交当前修改", + "description": "按逻辑分组逐步提交当前所有修改的文件", + "status": "pending", + "priority": 1, + "tags": [ + "git" + ], + "created_at": "2026-04-05T12:53:43.789588", + "updated_at": "2026-04-05T12:53:43.789591", + "completed_at": null, + "metadata": {} + } + }, + "error": null, + "timestamp": "2026-04-05T12:59:00.773180", + "id": "20260405_125900_773186" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125903_915427.json b/.claude/todo/outbox/rsp_20260405_125903_915427.json new file mode 100644 index 0000000..03c8f43 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125903_915427.json @@ -0,0 +1,34 @@ +{ + "success": true, + "cmd_id": "20260405_125900_778492", + "data": { + "success": true, + "output": "步骤 1: shell.git_status ✅\nD .cursorignore\n D .flake8\n M .gitignore\n M README.md\n M configs/app.example.json\n D install.sh\n M makefile\n M plan.md\n M pyproject.toml\n D pyrightconfig.json\n M src/application/app.py\n M src/application/use_cases/sync_test_data.py\n M src/domain/agent/components/planner/step_executor.py\n M src/domain/message/__init__.py\n M src/domain/message/channel.py\n M src/domain/task/step_handlers/tool_call.py\n M src/domain/tools/ext_tool_loader.py\n M src/gateway/channels/__init__.py\n M src/infra/config/app.py\n M src/infra/config/storage.py\n M src/infra/feishu/feishu_service.py\n M src/infra/feishu/handlers.py\n M src/interfaces/api/router_manager.py\n M src/interfaces/api/server.py\n M src/interfaces/cli/commands/__init__.py\n M src/interfaces/cli/commands/service.py\n M src/interfaces/cli/commands/test_cmd.py\n M src/interfaces/cli/commands/upgrade.py\n M src/interfaces/cli/main.py\n M tests/infra/test_feishu.py\n D todo.md\n M uv.lock\n?? .claude/\n?? CLAUDE.md\n?? configs/environments/\n?? docs/\n?? scripts/\n?? src/application/services/todo/\n?? src/domain/tools/subagent_tools.py\n?? src/gateway/channels/slack.py\n?? src/infra/config/environment.py\n?? src/infra/feishu/claude_bot.py\n?? src/infra/feishu/claude_code_forwarder.py\n?? src/infra/feishu/claude_exec_resolve.py\n?? src/infra/feishu/claude_feishu_agents.py\n?? src/infra/feishu/mentor/\n?? src/infra/feishu/openclaw/\n?? src/infra/feishu/skills/\n?? src/infra/slack/\n?? src/interfaces/api/tools.py\n?? src/interfaces/cli/commands/claude_cmd.py\n?? src/interfaces/cli/commands/todo_cmd.py\n?? tests/domain/tools/test_subagent_tools.py\n?? tests/infra/test_claude_code_forwarder.py\n?? tests/infra/test_claude_feishu_agents.py\n?? tests/interfaces/test_claude_cmd_launchctl.py\n?? tests/meta/\n步骤 2: shell.git_diff ✅\ndiff --git a/.cursorignore b/.cursorignore\ndeleted file mode 100644\nindex 51b4cfd..0000000\n--- a/.cursorignore\n+++ /dev/null\n@@ -1 +0,0 @@\n-local/\ndiff --git a/.flake8 b/.flake8\ndeleted file mode 100644\nindex d68b662..0000000\n--- a/.flake8\n+++ /dev/null\n@@ -1,4 +0,0 @@\n-[flake8]\n-max-line-length = 80\n-extend-ignore = E203\n-exclude = .git,__pycache__,.venv,build,dist,*.egg-info,data,data_test\ndiff --git a/.gitignore b/.gitignore\nindex 9164580..7d619ce 100644\n--- a/.gitignore\n+++ b/.gitignore\n@@ -50,6 +50,13 @@ ENV/\n *.swo\n .DS_Store\n \n+# Cursor\n+.cursor/\n+.cursorignore\n+\n+# Obsidian\n+.obsidian/\n+\n # ========================================\n # 测试和覆盖率\n # ========================================\n@@ -87,6 +94,17 @@ configs/app.test.json\n /data_test/\n /archives/\n \n+# ========================================\n+# MyAgent 统一存储目录（新框架）\n+# ========================================\n+# 开发环境数据（隐藏目录，防止误操作）\n+.myagent/\n+.myagent_test/\n+# 但不忽略测试固件\n+!.myagent_test/fixtures/\n+# 生产环境在用户主目录，不在项目中\n+# ~/.myagent/ (用户主目录，不在这里管理)\n+\n # ========================================\n # 本地文件\n # ========================================\ndiff --git a/README.md b/README.md\nindex 3120d1c..a8c6a52 100644\n--- a/README.md\n+++ b/README.md\n@@ -12,6 +12,7 @@\n - **Memory**: 用户记忆、偏好学习\n - **Learning**: 用户偏好、主题兴趣、交互模式、自我改进等学习策略\n - **Feishu**: 飞书机器人，随 service 启动，通过 WebSocket 连接飞书\n+- **Slack**: Slack 机器人，随 service 启动，通过 Socket Mode 连接 Slack\n \n ### 支持的 LLM\n \n@@ -50,6 +51,24 @@ make install\n \n 启用后，`myagent service start` 会同时启动 Feishu WebSocket 客户端。消息转发至内部 API，与 Chat CLI 共用同一套对话逻辑。命令：help、ping、myid、mychatid。\n \n+### Slack（可选）\n+\n+在 `configs/app.json` 的 `slack` 段配置，或使用环境变量：\n+\n+- `slack.enabled`: true 启用\n+- `SLACK_BOT_TOKEN`: Bot User OAuth Token (以 xoxb- 开头)\n+- `SLACK_APP_TOKEN`: App-Level Token (以 xapp- 开头，需包含 connections:write 权限)\n+- `SLACK_NOTIFY_USER_ID` / `SLACK_NOTIFY_CHANNEL_ID`: 启动通知（可选）\n+\n+**Slack App 配置步骤：**\n+1. 创建 Slack App: https://api.slack.com/apps\n+2. 在 \"Socket Mode\" 中启用 Socket Mode\n+3. 在 \"OAuth & Permissions\" 中添加 scopes: `chat:write`, `im:write`, `app_mentions:read`, `im:history`\n+4. 在 \"Event Subscriptions\" 中订阅事件: `message.im`, `app_mention`\n+5. 安装 App 到工作区，获取 Bot Token 和 App Token\n+\n+启用后，`myagent service start` 会同时启动 Slack Socket Mode 客户端。命令：help、ping、myid、mychannel。\n+\n ### 智能体 Prompt 配置（可选）\n \n - **configs**（默认）：`configs/agents/prompts/*.yaml`，用于新安装迁移。\ndiff --git a/configs/app.example.json b/configs/app.example.json\nindex 1a52305..21e6182 100644\n--- a/configs/app.example.json\n+++ b/configs/app.example.json\n@@ -28,7 +28,7 @@\n },\n \"storage\": {\n \"storage_type\": \"file\",\n- \"root_dir\": \"./data\"\n+ \"root_dir\": \"./.myagent\"\n },\n \"logging\": {\n \"level\": \"INFO\",\n@@ -74,5 +74,13 @@\n \"app_secret\": \"\",\n \"notify_open_id\": \"\",\n \"notify_chat_id\": \"\"\n+ },\n+ \"slack\": {\n+ \"enabled\": false,\n+ \"bot_token\": \"\",\n+ \"app_token\": \"\",\n+ \"notify_user_id\": \"\",\n+ \"notify_channel_id\": \"\",\n+ \"use_gateway\": true\n }\n-}\n+}\n\\ No newline at end of file\ndiff --git a/install.sh b/install.sh\ndeleted file mode 100644\nindex 125a8da..0000000\n--- a/install.sh\n+++ /dev/null\n@@ -1,45 +0,0 @@\n-#!/bin/bash\n-set -e\n-\n-SCRIPT_DIR=$(cd \"$(dirname \"${BASH_SOURCE[0]:-${(%):-%x}}\")\" && pwd)\n-ROOT_DIR=$SCRIPT_DIR\n-VENV_DIR=$ROOT_DIR/.venv\n-INSTALL=${INSTALL:-false}\n-\n-if [ ! -d \"$VENV_DIR\" ]; then\n- echo \"Error: .venv not found. Run 'make prerequisites' first.\"\n- exit 1\n-fi\n-\n-# wheel cache and target directory\n-WHEELCACHE_DIR=$ROOT_DIR/build/wheelcache\n-WHEELHOUSE_DIR=$ROOT_DIR/build/wheelhouse\n-\n-mkdir -p $WHEELCACHE_DIR $WHEELHOUSE_DIR\n-\n-if command -v uv >/dev/null 2>&1; then\n- echo \"Using uv build\"\n- uv build --wheel -o $WHEELCACHE_DIR\n- rsync -ura $WHEELCACHE_DIR/* $WHEELHOUSE_DIR\n- if [ \"$INSTALL\" = \"true\" ]; then\n- WHEEL=$(ls $WHEELHOUSE_DIR/myagent*.whl 2>/dev/null | head -1)\n- if [ -n \"$WHEEL\" ]; then\n- uv pip install \"$WHEEL\" --reinstall-package myagent\n- fi\n- fi\n-else\n- PIP=$VENV_DIR/bin/pip\n- if [ ! -x \"$PIP\" ]; then\n- PIP=$VENV_DIR/bin/pip3\n- fi\n- if [ ! -x \"$PIP\" ]; then\n- echo \"Error: pip not found in .venv. Run 'make prerequisites' (without uv) or use uv.\"\n- exit 1\n- fi\n- echo \"Using PIP: $PIP\"\n- $PIP wheel $ROOT_DIR --no-deps --no-build-isolation -w $WHEELCACHE_DIR\n- rsync -ura $WHEELCACHE_DIR/* $WHEELHOUSE_DIR\n- if [ \"$INSTALL\" = \"true\" ]; then\n- cd $WHEELHOUSE_DIR && $PIP install myagent* --force-reinstall --no-deps\n- fi\n-fi\ndiff --git a/makefile b/makefile\nindex 49dd02c..b310b2c 100644\n--- a/makefile\n+++ b/makefile\n@@ -23,14 +23,15 @@ help:\n prerequisites_no_project:\n \t@if [ -f package.json ]; then npm install; fi\n \t@if command -v uv >/dev/null 2>&1; then uv sync --no-install-project; else \\\n-\t\t$(MAKE) prerequisites; \\\n+\t\ttest -d $(VENV_DIR) || (python3 -m venv $(VENV_DIR)); \\\n+\t\t$(PIP) install -e .; \\\n \tfi\n \n install: prerequisites_no_project\n-\tINSTALL=true bash install.sh\n+\tINSTALL=true bash scripts/install.sh\n \n pyproject:\n-\tbash install.sh\n+\tbash scripts/install.sh\n \n venv:\n \t@test -d .venv || python3 -m venv .venv\n@@ -42,7 +43,7 @@ prerequisites:\n \t\t$(PIP) install -e .; \\\n \tfi\n \n-PRISMA_DB := file:$(ROOT_DIR)/data/myagent/db/sqlite.db\n+PRISMA_DB := file:$(ROOT_DIR)/.myagent/myagent/db/sqlite.db\n \n prisma_generate:\n \t@test -d $(VENV_DIR) || $(MAKE) prerequisites\ndiff --git a/plan.md b/plan.md\nindex e69de29..77624c5 100644\n--- a/plan.md\n+++ b/plan.md\n@@ -0,0 +1,25 @@\n+目标\n+- 飞书仅作收发：用户原文进、模型原文出（可做飞书格式封装，不改语义）。\n+- 推理与工具链与「在同一目录下终端执行 Claude Code」严格一致：同 CLAUDE.md、同 ~/.claude 与项目 .claude 设置、同 MCP/插件/权限模型（由 Claude Code 自身处理）。\n+\n+现状\n+- myagent claude run 使用 claude_bot.ClaudeAPIClient：自建 system prompt、SOUL、SkillRegistry、敏感工具二次确认、与终端 claude 不是同一运行时。\n+\n+方案（推荐）\n+- 在 Claude Bot 路径用子进程调用本机 `claude`，而非直接 httpx 调 Messages API。\n+- 单次问答：`claude -p --print` + 用户文本；`cwd` 固定为仓库根（或配置项，如 MYAGENT_CLAUDE_CODE_CWD），与你在终端 `cd` 的目录一致。\n+- 多轮：按飞书 chat_id 持久化 session 映射，使用官方支持的 `--continue` 或 `--session-id` + `--resume`（以当前 claude CLI 文档为准），保证同一会话内与终端 `-c` 行为一致。\n+- 输出：`--output-format text` 收集 stdout；若需飞书侧伪流式，可用 `stream-json`（与 handlers 里 on_delta 类似）。\n+- 非交互权限：launchd/后台无 TTY，需显式 `--permission-mode`（如 acceptEdits 或 bypassPermissions，由你选定安全策略）；与「终端里手动点允许」仍会有差异，属无头环境固有限制。\n+- 下线或开关：OpenClaw 专有层（SOUL 写入、Heartbeat、内置 SkillRegistry、HTTP 直连 API）在「转发模式」下关闭或整段不加载；仅保留飞书 WS、reply、可选 session 存储。\n+\n+涉及文件（拟）\n+- src/infra/feishu/claude_bot.py：ClaudeBot / 消息处理改为调用 Claude Code 子进程；ClaudeBotConfig 增加 use_claude_code_cli、cwd、permission_mode、claude_bin。\n+- src/interfaces/cli/commands/claude_cmd.py：plist / 环境变量补充 CLAUDE_CODE_CWD、PATH 确保含 claude。\n+- 可选：tests/infra 对子进程做 mock 的单测。\n+\n+风险\n+- 依赖本机安装 claude CLI 与登录态；daemon 环境需与终端同一 auth（如 settings 里的 api key）。\n+- 子进程耗时与飞书超时；长回复仍受 4000 字分片限制（与现逻辑一致）。\n+\n+请确认：是否采用「子进程 claude -p」方案；permission-mode 倾向 acceptEdits 还是 bypassPermissions；多轮是否按 chat_id 独立 session。\ndiff --git a/pyproject.toml b/pyproject.toml\nindex 55d338d..9e514f5 100644\n--- a/pyproject.toml\n+++ b/pyproject.toml\n@@ -31,6 +31,7 @@ dependencies = [\n \"neo4j>=5.14.0\",\n \"rank_bm25>=0.2.2\",\n \"lark-oapi>=1.4.0\",\n+ \"slack-bolt>=1.20.0\",\n \"python-socks[asyncio]>=2.0.0\",\n \"croniter>=2.0.0\",\n \"pymupdf\",\n@@ -106,6 +107,9 @@ warn_return_any = true\n warn_unused_configs = true\n disallow_untyped_defs = true\n \n+[tool.pyright]\n+reportUnusedImport = false\n+\n [tool.pytest.ini_options]\n asyncio_mode = \"auto\"\n asyncio_default_fixture_loop_scope = \"function\"\ndiff --git a/pyrightconfig.json b/pyrightconfig.json\ndeleted file mode 100644\nindex 36faa28..0000000\n--- a/pyrightconfig.json\n+++ /dev/null\n@@ -1,3 +0,0 @@\n-{\n- \"reportUnusedImport\": false\n-}\ndiff --git a/src/application/app.py b/src/application/app.py\nindex 7c85cab..80aac30 100644\n--- a/src/application/app.py\n+++ b/src/application/app.py\n@@ -102,6 +102,7 @@ class MyAgentApp:\n logger.warning(\"API服务未找到\")\n \n self._start_feishu()\n+ self._start_slack()\n await self._start_scheduler_and_task_worker()\n \n self._server_lifecycle_started = True\n@@ -170,6 +171,44 @@ class MyAgentApp:\n svc.stop()\n self._feishu_service = None\n \n+ def _start_slack(self):\n+ \"\"\"Start Slack Socket Mode client if enabled.\"\"\"\n+ slack = getattr(self.config, \"slack\", None)\n+ if not slack or not getattr(slack, \"enabled\", False):\n+ return\n+ try:\n+ from src.infra.slack import SlackService\n+\n+ api_cfg = self.config.servers.api\n+ api_base_url = f\"http://127.0.0.1:{api_cfg.port}\"\n+ from src.application.use_cases.agent_group_config import (\n+ get_default_agent_from_group,\n+ )\n+ from src.application.use_cases.default_app_config import (\n+ resolve_default_agent_id,\n+ )\n+\n+ default_agent = (\n+ get_default_agent_from_group() or resolve_default_agent_id()\n+ )\n+ self._slack_service = SlackService(\n+ slack, api_base_url=api_base_url, default_agent=default_agent\n+ )\n+ if self._slack_service.start():\n+ logger.info(\"Slack service started\")\n+ else:\n+ self._slack_service = None\n+ except Exception as e:\n+ logger.debug(f\"Slack not started: {e}\")\n+ self._slack_service = None\n+\n+ def _stop_slack(self):\n+ \"\"\"Stop Slack service.\"\"\"\n+ svc = getattr(self, \"_slack_service\", None)\n+ if svc:\n+ svc.stop()\n+ self._slack_service = None\n+\n async def _start_scheduler_and_task_worker(self):\n \"\"\"Start scheduler, WorkItemConsumer, and Gateway.\"\"\"\n self._scheduler = None\n@@ -260,6 +299,22 @@ class MyAgentApp:\n ),\n }\n \n+ def _get_slack_status(self) -> dict[str, Any]:\n+ \"\"\"Get Slack service status for health/status display.\"\"\"\n+ slack_cfg = getattr(self.config, \"slack\", None)\n+ enabled = slack_cfg and getattr(slack_cfg, \"enabled\", False)\n+ svc = getattr(self, \"_slack_service\", None)\n+ running = svc is not None and svc.is_running() if svc else False\n+ return {\n+ \"enabled\": enabled,\n+ \"running\": running,\n+ \"message\": (\n+ \"connected\"\n+ if running\n+ else (\"not started\" if enabled else \"disabled\")\n+ ),\n+ }\n+\n async def cleanup(self):\n \"\"\"Clean up app resources. Server lifecycle teardown only when start_server_lifecycle() was called.\"\"\"\n logger.info(\"开始清理应用资源...\")\n@@ -268,6 +323,7 @@ class MyAgentApp:\n await self._stop_scheduler_and_task_worker()\n self._stop_index_watcher()\n self._stop_feishu()\n+ self._stop_slack()\n try:\n api_service = await self.service_manager.get_service(\n ServiceName.API\n@@ -405,6 +461,7 @@ class MyAgentApp:\n \n index_watcher = self._get_index_watcher_status()\n feishu = self._get_feishu_status()\n+ slack = self._get_slack_status()\n \n return {\n \"status\": \"running\",\n@@ -414,6 +471,7 @@ class MyAgentApp:\n \"modules\": modules_health,\n \"index_watcher\": index_watcher,\n \"feishu\": feishu,\n+ \"slack\": slack,\n }\n except Exception as e:\n logger.error(f\"健康检查失败: {e}\")\ndiff --git a/src/application/use_cases/sync_test_data.py b/src/application/use_cases/sync_test_data.py\nindex de9350b..38c488b 100644\n--- a/src/application/use_cases/sync_test_data.py\n+++ b/src/application/use_cases/sync_test_data.py\n@@ -33,7 +33,7 @@ def sync_data_to_test_root(config_path: Path | None = None) -> int:\n return 0\n storage = cfg.get(\"storage\") or {}\n src_rel = (storage.get(\"copy_llm_from_root\") or \"\").strip()\n- dst_rel = (storage.get(\"root_dir\") or \"data_test\").strip()\n+ dst_rel = (storage.get(\"root_dir\") or \".myagent_test\").strip()\n if not src_rel:\n return 0\n src = (root / src_rel).resolve()\ndiff --git a/src/domain/agent/components/planner/step_executor.py b/src/domain/agent/components/planner/step_executor.py\nindex 495e5dc..10d79b7 100644\n--- a/src/domain/agent/components/planner/step_executor.py\n+++ b/src/domain/agent/components/planner/step_executor.py\n@@ -624,6 +624,14 @@ class StepExecutor:\n variables[\"meditation_entity_id\"] = context[\n \"meditation_entity_id\"\n ]\n+ if context and context.get(\"conversation_id\"):\n+ variables[\"conversation_id\"] = context[\"conversation_id\"]\n+ if context and context.get(\"is_sub_task\"):\n+ variables[\"is_sub_task\"] = bool(context[\"is_sub_task\"])\n+ if context:\n+ sc0 = context.get(\"session_context\")\n+ if isinstance(sc0, dict):\n+ variables[\"session_context\"] = sc0\n task_context = TaskContext(\n agent_id=self.agent_base.config.id,\n conversation_id=\"current\",\ndiff --git a/src/domain/message/__init__.py b/src/domain/message/__init__.py\nindex d1038f3..c3063b6 100644\n--- a/src/domain/message/__init__.py\n+++ b/src/domain/message/__init__.py\n@@ -1,12 +1,13 @@\n \"\"\"Message channel abstraction for scheduled messages and task feedback.\"\"\"\n \n-from .channel import FeishuChannel, MessageChannel\n+from .channel import FeishuChannel, MessageChannel, SlackChannel\n from .channel_registry import get_channel, register_channel\n from .http_channel import HttpChannel, get_pending\n \n __all__ = [\n \"MessageChannel\",\n \"FeishuChannel\",\n+ \"SlackChannel\",\n \"HttpChannel\",\n \"get_channel\",\n \"get_pending\",\ndiff --git a/src/domain/message/channel.py b/src/domain/message/channel.py\nindex 245b55e..f71a107 100644\n--- a/src/domain/message/channel.py\n+++ b/src/domain/message/channel.py\n@@ -43,3 +43,25 @@ class FeishuChannel(MessageChannel):\n **kwargs: Any,\n ) -> bool:\n return self._send_fn(target_id, target_type, content)\n+\n+\n+class SlackChannel(MessageChannel):\n+ \"\"\"Slack channel using SlackContext.send_to.\"\"\"\n+\n+ def __init__(self, send_fn: Callable[[str, str], bool]):\n+ \"\"\"\n+ Args:\n+ send_fn: (channel_id, text) -> bool\n+ \"\"\"\n+ self._send_fn = send_fn\n+\n+ def send(\n+ self,\n+ user_id: str,\n+ target_id: str,\n+ target_type: str,\n+ content: str,\n+ **kwargs: Any,\n+ ) -> bool:\n+ # Slack doesn't use target_type, just channel_id\n+ return self._send_fn(target_id, content)\ndiff --git a/src/domain/task/step_handlers/tool_call.py b/src/domain/task/step_handlers/tool_call.py\nindex 4d94332..a61be20 100644\n--- a/src/domain/task/step_handlers/tool_call.py\n+++ b/src/domain/task/step_handlers/tool_call.py\n@@ -446,6 +446,36 @@ class ToolCallStepHandler(StepHandler):\n resolve_path(raw_path, ws_abs)\n )\n \n+ if tool_name == \"invoke_subagent\":\n+ tw = context.variables.get(\"conversation_trace_writer\")\n+ trace_turn = None\n+ if tw is not None and callable(\n+ getattr(tw, \"get_current_turn_dir\", None)\n+ ):\n+ try:\n+ trace_turn = tw.get_current_turn_dir()\n+ except Exception:\n+ trace_turn = None\n+ sc_inv = context.variables.get(\"session_context\")\n+ if not isinstance(sc_inv, dict):\n+ sc_inv = {}\n+ cid_inv = context.variables.get(\n+ \"conversation_id\"\n+ ) or sc_inv.get(\"conversation_id\")\n+ sc_merged = dict(sc_inv)\n+ if cid_inv:\n+ sc_merged[\"conversation_id\"] = cid_inv\n+ ruid_inv = context.variables.get(\"user_id\") or context.user_id\n+ resolved_params = {\n+ **resolved_params,\n+ \"_caller_agent_id\": context.agent_id,\n+ \"_user_id\": ruid_inv,\n+ \"_session_context\": sc_merged,\n+ \"_conversation_trace_writer\": tw,\n+ \"_trace_base_dir\": str(trace_turn) if trace_turn else None,\n+ \"_is_sub_task\": bool(context.variables.get(\"is_sub_task\")),\n+ }\n+\n # Execute: sandbox path when enabled for execute_shell/execute_python\n sandbox_enabled = bool(context.variables.get(\"sandbox_enabled\"))\n sandbox_result = await execute_in_sandbox(\n@@ -472,6 +502,11 @@ class ToolCallStepHandler(StepHandler):\n tool_name, resolved_params\n )\n \n+ if tool_name == \"invoke_subagent\":\n+ for _ik in list(resolved_params.keys()):\n+ if isinstance(_ik, str) and _ik.startswith(\"_\"):\n+ resolved_params.pop(_ik, None)\n+\n if (\n tool_name == \"list_dir\"\n and isinstance(tool_result, ToolResult)\ndiff --git a/src/domain/tools/ext_tool_loader.py b/src/domain/tools/ext_tool_loader.py\nindex fe3b16d..4990762 100644\n--- a/src/domain/tools/ext_tool_loader.py\n+++ b/src/domain/tools/ext_tool_loader.py\n@@ -19,6 +19,7 @@ _BUILTIN_GROUP_TOOL_NAMES: dict[str, frozenset[str]] = {\n \"process\": frozenset({\"kill_process\", \"list_spawned_pids\", \"register_pid\"}),\n \"queue\": frozenset({\"list_pending_runs\", \"cancel_pending_run\"}),\n \"web\": frozenset({\"web_search\", \"web_fetch\"}),\n+ \"subagent\": frozenset({\"invoke_subagent\"}),\n }\n \n BUILTIN_GROUP_IDS: tuple[str, ...] = tuple(_BUILTIN_GROUP_TOOL_NAMES.keys())\n@@ -42,7 +43,7 @@ def builtin_groups_intersecting_allowlist(allow: set[str]) -> list[str]:\n \n \n def load_builtin_group(group_id: str) -> list[Tool]:\n- \"\"\"Load one built-in group (schedule | process | queue | web).\"\"\"\n+ \"\"\"Load one built-in group (schedule | process | queue | web | subagent).\"\"\"\n if group_id == \"schedule\":\n try:\n from .schedule_agent_tools import get_schedule_agent_tools\n@@ -75,6 +76,14 @@ def load_builtin_group(group_id: str) -> list[Tool]:\n except Exception as e:\n logger.debug(\"web_search_tools not loaded: %s\", e)\n return []\n+ elif group_id == \"subagent\":\n+ try:\n+ from .subagent_tools import get_subagent_tools\n+\n+ raw = get_subagent_tools()\n+ except Exception as e:\n+ logger.debug(\"subagent_tools not loaded: %s\", e)\n+ return []\n else:\n logger.warning(\"Unknown builtin tool group: %s\", group_id)\n return []\ndiff --git a/src/gateway/channels/__init__.py b/src/gateway/channels/__init__.py\nindex 946dd92..018e218 100644\n--- a/src/gateway/channels/__init__.py\n+++ b/src/gateway/channels/__init__.py\n@@ -4,6 +4,7 @@ from .base import Channel, NormalizedMessage, RunEvent\n from .cli import CliChannel\n from .feishu import FeishuChannel\n from .http import HttpChannel\n+from .slack import SlackChannel\n from .websocket import WebSocketChannel\n \n __all__ = [\n@@ -12,6 +13,7 @@ __all__ = [\n \"RunEvent\",\n \"HttpChannel\",\n \"FeishuChannel\",\n+ \"SlackChannel\",\n \"CliChannel\",\n \"WebSocketChannel\",\n ]\ndiff --git a/src/infra/config/app.py b/src/infra/config/app.py\nindex 20a09bc..bafe317 100644\n--- a/src/infra/config/app.py\n+++ b/src/infra/config/app.py\n@@ -11,10 +11,12 @@ from pathlib import Path\n \n logger = logging.getLogger(__name__)\n \n-DEFAULT_STORAGE_ROOT = \"./data\"\n-DEFAULT_LOG_DIR = \"./data/logs\"\n-DEFAULT_WORKSPACE_ROOT = \"./data/workspace\"\n-DEFAULT_TODO_MARKDOWN_PATH = \"./data/workspace/todos.md\"\n+# 统一存储框架默认路径\n+# 环境变量 MYAGENT_STORAGE_ROOT 可覆盖\n+DEFAULT_STORAGE_ROOT = \"./.myagent\"\n+DEFAULT_LOG_DIR = \"./.myagent/logs\"\n+DEFAULT_WORKSPACE_ROOT = \"./.myagent/workspace\"\n+DEFAULT_TODO_MARKDOWN_PATH = \"./.myagent/workspace/todos.md\"\n \n \n @dataclass\n@@ -51,11 +53,26 @@ class LLMResourceConfig:\n request_timeout: int = 120\n \n \n+@dataclass\n+class FeishuBotConfig:\n+ \"\"\"单个飞书Bot配置\"\"\"\n+ app_id: str = \"\"\n+ app_secret: str = \"\"\n+ name: str = \"\" # bot名称，用于显示\n+ role: str = \"\" # 角色: claude 或 myagent\n+\n+\n @dataclass\n class FeishuConfig:\n- \"\"\"Feishu bot config (WebSocket, runs with server).\"\"\"\n+ \"\"\"Feishu bot config (WebSocket, runs with server).\n+\n+ 支持两种模式:\n+ 1. 单Bot模式: 使用 app_id/app_secret (向后兼容)\n+ 2. 双Bot模式: 使用 bots 列表配置多个Bot\n+ \"\"\"\n \n enabled: bool = False\n+ # 单Bot配置 (向后兼容)\n app_id: str = \"\"\n app_secret: str = \"\"\n notify_open_id: str = \"\"\n@@ -63,6 +80,50 @@ class FeishuConfig:\n use_gateway: bool = True\n # When True, unset HTTP_PROXY/HTTPS_PROXY/ALL_PROXY before starting Feishu WS so connection goes direct (avoids SOCKS proxy errors).\n bypass_proxy: bool = True\n+ # 多Bot配置 (推荐用于师徒系统)\n+ # bots: [{\"app_id\": \"\", \"app_secret\": \"\", \"name\": \"师父(Claude)\", \"role\": \"claude\"}, {\"app_id\": \"\", \"app_secret\": \"\", \"name\": \"徒弟(MyAgent)\", \"role\": \"myagent\"}]\n+ bots: list[dict] = None\n+\n+ def __post_init__(self):\n+ if self.bots is None:\n+ self.bots = []\n+\n+ def get_active_bots(self) -> list[dict]:\n+ \"\"\"获取有效的Bot配置列表\"\"\"\n+ # 优先使用多Bot配置\n+ if self.bots and len(self.bots) > 0:\n+ return [\n+ bot for bot in self.bots\n+ if bot.get(\"app_id\") and bot.get(\"app_secret\")\n+ ]\n+ # 向后兼容: 使用单Bot配置\n+ if self.app_id and self.app_secret:\n+ return [{\n+ \"app_id\": self.app_id,\n+ \"app_secret\": self.app_secret,\n+ \"name\": \"Bot\",\n+ \"role\": \"auto\" # 使用旧版@前缀路由\n+ }]\n+ return []\n+\n+ def get_bot_by_app_id(self, app_id: str) -> dict | None:\n+ \"\"\"根据App ID获取Bot配置\"\"\"\n+ for bot in self.get_active_bots():\n+ if bot.get(\"app_id\") == app_id:\n+ return bot\n+ return None\n+\n+\n+@dataclass\n+class SlackConfig:\n+ \"\"\"Slack bot config (Socket Mode, runs with server).\"\"\"\n+\n+ enabled: bool = False\n+ bot_token: str = \"\" # xoxb-... Bot User OAuth Token\n+ app_token: str = \"\" # xapp-... App-Level Token with connections:write\n+ notify_user_id: str = \"\" # User ID to notify on startup\n+ notify_channel_id: str = \"\" # Channel ID to notify on startup\n+ use_gateway: bool = True\n \n \n @dataclass\n@@ -117,6 +178,9 @@ class AppConfig:\n # Feishu bot\n feishu: FeishuConfig = field(default_factory=FeishuConfig)\n \n+ # Slack bot\n+ slack: SlackConfig = field(default_factory=SlackConfig)\n+\n @classmethod\n def from_dict(cls, data: dict) -> \"AppConfig\":\n \"\"\"从字典创建配置\"\"\"\n@@ -201,8 +265,11 @@ class AppConfig:\n # 日志配置\n if \"logging\" in data:\n logging_data = dict(data[\"logging\"])\n+ # 旧路径迁移\n if logging_data.get(\"log_dir\") == \"./logs\":\n- logging_data[\"log_dir\"] = \"./data/logs\"\n+ logging_data[\"log_dir\"] = \"./.myagent/logs\"\n+ elif logging_data.get(\"log_dir\") == \"./data/logs\":\n+ logging_data[\"log_dir\"] = \"./.myagent/logs\"\n config.logging = LoggingConfig(**logging_data)\n \n # LLM资源配置\n@@ -229,29 +296,120 @@ class AppConfig:\n config.defaults = DefaultsConfig(**defaults_data)\n \n # Feishu (env vars override config)\n+ # 支持多Bot环境变量: CLAUDE_APP_ID/CLAUDE_APP_SECRET, MYAGENT_APP_ID/MYAGENT_APP_SECRET\n+ claude_app_id = os.environ.get(\"CLAUDE_APP_ID\", \"\")\n+ claude_app_secret = os.environ.get(\"CLAUDE_APP_SECRET\", \"\")\n+ myagent_app_id = os.environ.get(\"MYAGENT_APP_ID\", \"\")\n+ myagent_app_secret = os.environ.get(\"MYAGENT_APP_SECRET\", \"\")\n+\n+ # 检查是否配置了多Bot环境变量\n+ has_multi_bots = (claude_app_id and claude_app_secret and\n+ myagent_app_id and myagent_app_secret)\n+\n if \"feishu\" in data:\n fc = data[\"feishu\"]\n- config.feishu = FeishuConfig(\n- enabled=fc.get(\"enabled\", False),\n- app_id=os.environ.get(\"FEISHU_APP_ID\", fc.get(\"app_id\", \"\")),\n- app_secret=os.environ.get(\n- \"FEISHU_APP_SECRET\", fc.get(\"app_secret\", \"\")\n+\n+ if has_multi_bots:\n+ # 使用多Bot环境变量配置\n+ config.feishu = FeishuConfig(\n+ enabled=fc.get(\"enabled\", False),\n+ bots=[\n+ {\n+ \"app_id\": claude_app_id,\n+ \"app_secret\": claude_app_secret,\n+ \"name\": \"Claude\",\n+ \"role\": \"claude\"\n+ },\n+ {\n+ \"app_id\": myagent_app_id,\n+ \"app_secret\": myagent_app_secret,\n+ \"name\": \"MyAgent\",\n+ \"role\": \"myagent\"\n+ }\n+ ],\n+ notify_open_id=os.environ.get(\n+ \"FEISHU_NOTIFY_OPEN_ID\", fc.get(\"notify_open_id\", \"\")\n+ ),\n+ notify_chat_id=os.environ.get(\n+ \"FEISHU_NOTIFY_CHAT_ID\", fc.get(\"notify_chat_id\", \"\")\n+ ),\n+ use_gateway=fc.get(\"use_gateway\", True),\n+ bypass_proxy=fc.get(\"bypass_proxy\", True),\n+ )\n+ else:\n+ # 使用单Bot配置（向后兼容）\n+ config.feishu = FeishuConfig(\n+ enabled=fc.get(\"enabled\", False),\n+ app_id=os.environ.get(\"FEISHU_APP_ID\", fc.get(\"app_id\", \"\")),\n+ app_secret=os.environ.get(\n+ \"FEISHU_APP_SECRET\", fc.get(\"app_secret\", \"\")\n+ ),\n+ notify_open_id=os.environ.get(\n+ \"FEISHU_NOTIFY_OPEN_ID\", fc.get(\"notify_open_id\", \"\")\n+ ),\n+ notify_chat_id=os.environ.get(\n+ \"FEISHU_NOTIFY_CHAT_ID\", fc.get(\"notify_chat_id\", \"\")\n+ ),\n+ use_gateway=fc.get(\"use_gateway\", True),\n+ bypass_proxy=fc.get(\"bypass_proxy\", True),\n+ bots=fc.get(\"bots\", []),\n+ )\n+ else:\n+ if has_multi_bots:\n+ # 只有环境变量，没有配置文件\n+ config.feishu = FeishuConfig(\n+ enabled=True,\n+ bots=[\n+ {\n+ \"app_id\": claude_app_id,\n+ \"app_secret\": claude_app_secret,\n+ \"name\": \"Claude\",\n+ \"role\": \"claude\"\n+ },\n+ {\n+ \"app_id\": myagent_app_id,\n+ \"app_secret\": myagent_app_secret,\n+ \"name\": \"MyAgent\",\n+ \"role\": \"myagent\"\n+ }\n+ ],\n+ notify_open_id=os.environ.get(\"FEISHU_NOTIFY_OPEN_ID\", \"\"),\n+ notify_chat_id=os.environ.get(\"FEISHU_NOTIFY_CHAT_ID\", \"\"),\n+ )\n+ else:\n+ # 向后兼容\n+ config.feishu = FeishuConfig(\n+ app_id=os.environ.get(\"FEISHU_APP_ID\", \"\"),\n+ app_secret=os.environ.get(\"FEISHU_APP_SECRET\", \"\"),\n+ notify_open_id=os.environ.get(\"FEISHU_NOTIFY_OPEN_ID\", \"\"),\n+ notify_chat_id=os.environ.get(\"FEISHU_NOTIFY_CHAT_ID\", \"\"),\n+ )\n+\n+ # Slack (env vars override config)\n+ if \"slack\" in data:\n+ sc = data[\"slack\"]\n+ config.slack = SlackConfig(\n+ enabled=sc.get(\"enabled\", False),\n+ bot_token=os.environ.get(\n+ \"SLACK_BOT_TOKEN\", sc.get(\"bot_token\", \"\")\n+ ),\n+ app_token=os.environ.get(\n+ \"SLACK_APP_TOKEN\", sc.get(\"app_token\", \"\")\n ),\n- notify_open_id=os.environ.get(\n- \"FEISHU_NOTIFY_OPEN_ID\", fc.get(\"notify_open_id\", \"\")\n+ notify_user_id=os.environ.get(\n+ \"SLACK_NOTIFY_USER_ID\", sc.get(\"notify_user_id\", \"\")\n ),\n- notify_chat_id=os.environ.get(\n- \"FEISHU_NOTIFY_CHAT_ID\", fc.get(\"notify_chat_id\", \"\")\n+ notify_channel_id=os.environ.get(\n+ \"SLACK_NOTIFY_CHANNEL_ID\", sc.get(\"notify_channel_id\", \"\")\n ),\n- use_gateway=fc.get(\"use_gateway\", True),\n- bypass_proxy=fc.get(\"bypass_proxy\", True),\n+ use_gateway=sc.get(\"use_gateway\", True),\n )\n else:\n- config.feishu = FeishuConfig(\n- app_id=os.environ.get(\"FEISHU_APP_ID\", \"\"),\n- app_secret=os.environ.get(\"FEISHU_APP_SECRET\", \"\"),\n- notify_open_id=os.environ.get(\"FEISHU_NOTIFY_OPEN_ID\", \"\"),\n- notify_chat_id=os.environ.get(\"FEISHU_NOTIFY_CHAT_ID\", \"\"),\n+ config.slack = SlackConfig(\n+ bot_token=os.environ.get(\"SLACK_BOT_TOKEN\", \"\"),\n+ app_token=os.environ.get(\"SLACK_APP_TOKEN\", \"\"),\n+ notify_user_id=os.environ.get(\"SLACK_NOTIFY_USER_ID\", \"\"),\n+ notify_channel_id=os.environ.get(\"SLACK_NOTIFY_CHANNEL_ID\", \"\"),\n )\n \n return config\ndiff --git a/src/infra/config/storage.py b/src/infra/config/storage.py\nindex 4c6d135..79e282c 100644\n--- a/src/infra/config/storage.py\n+++ b/src/infra/config/storage.py\n@@ -4,6 +4,11 @@ Storage config: root_dir + sub_configs (app_data, rag_data, backup_data, index).\n App data (app_data / myagent) uses DataStorageConfig: one sub_dir with files/ and db/sqlite.db.\n All app tables (including index registry indexes/indexed_files) live in that single DB file.\n See docs/STORAGE_LAYOUT.md. Do not add separate DB files for new app state.\n+\n+统一存储框架：\n+- 开发环境: ./.myagent/\n+- 生产环境: ~/.myagent/\n+- 测试环境: ./.myagent_test/\n \"\"\"\n \n from dataclasses import dataclass, field\n@@ -11,7 +16,9 @@ from enum import Enum\n from pathlib import Path\n from typing import Any\n \n-from .app import DEFAULT_STORAGE_ROOT\n+# 统一存储框架默认路径\n+# 环境变量 MYAGENT_STORAGE_ROOT 可覆盖\n+DEFAULT_STORAGE_ROOT = \"./.myagent\"\n \n \n class StorageType(str, Enum):\ndiff --git a/src/infra/feishu/feishu_service.py b/src/infra/feishu/feishu_service.py\nindex 25d29d1..7896f8a 100644\n--- a/src/infra/feishu/feishu_service.py\n+++ b/src/infra/feishu/feishu_service.py\n@@ -1,5 +1,6 @@\n \"\"\"\n FeishuService - WebSocket client for Feishu, runs as background thread with server.\n+Supports multi-Bot mode (Claude Bot and MyAgent Bot)\n Chat messages forwarded to internal API (ConversationService).\n \"\"\"\n \n@@ -7,6 +8,7 @@ import asyncio\n import logging\n import threading\n import time\n+from dataclasses import dataclass\n \n from lark_oapi import FEISHU_DOMAIN, Client\n from lark_oapi.core.enum import LogLevel\n@@ -20,8 +22,21 @@ from .handlers import FeishuContext, create_message_handler\n logger = logging.getLogger(__name__)\n \n \n+@dataclass\n+class BotInstance:\n+ \"\"\"单个Bot实例\"\"\"\n+ app_id: str\n+ app_secret: str\n+ name: str\n+ role: str # \"claude\", \"myagent\", or \"auto\"\n+ client: Client | None = None\n+ ws_client: WsClient | None = None\n+ thread: threading.Thread | None = None\n+ running: bool = False\n+\n+\n class FeishuService:\n- \"\"\"Feishu WebSocket client service. Runs in background thread.\"\"\"\n+ \"\"\"Feishu WebSocket client service. Supports multiple bots.\"\"\"\n \n def __init__(\n self,\n@@ -32,32 +47,38 @@ class FeishuService:\n self.config = config\n self.api_base_url = api_base_url.rstrip(\"/\")\n self.default_agent = default_agent\n- self._client: Client | None = None\n- self._ws_client: WsClient | None = None\n- self._thread: threading.Thread | None = None\n- self._running = False\n-\n- def _get_client(self) -> Client:\n- if self._client is None:\n- self._client = (\n- Client.builder()\n- .app_id(self.config.app_id)\n- .app_secret(self.config.app_secret)\n- .domain(FEISHU_DOMAIN)\n- .log_level(LogLevel.INFO)\n- .build()\n- )\n- return self._client\n+ self._bots: list[BotInstance] = []\n+ self._ctx: FeishuContext | None = None\n+\n+ def _create_client(self, bot: BotInstance) -> Client:\n+ \"\"\"为Bot创建API客户端\"\"\"\n+ return (\n+ Client.builder()\n+ .app_id(bot.app_id)\n+ .app_secret(bot.app_secret)\n+ .domain(FEISHU_DOMAIN)\n+ .log_level(LogLevel.INFO)\n+ .build()\n+ )\n \n def start(self) -> bool:\n- \"\"\"Start Feishu WebSocket client in background thread. Returns True if started.\"\"\"\n- if self._running:\n- logger.warning(\"FeishuService already running\")\n- return True\n- if not self.config.app_id or not self.config.app_secret:\n- logger.warning(\n- \"FeishuService: missing app_id or app_secret, skip start\"\n- )\n+ \"\"\"Start Feishu WebSocket clients for all configured bots.\n+\n+ Note: Claude Bot (role=claude) is managed separately by `myagent claude` command.\n+ This service only starts myagent/auto bots (Apprentice).\n+ \"\"\"\n+ # 获取所有有效的Bot配置，但排除 claude role（由独立进程管理）\n+ all_bot_configs = self.config.get_active_bots()\n+ bot_configs = [\n+ bot for bot in all_bot_configs\n+ if bot.get(\"role\") != \"claude\" # 排除Claude Bot，它由 myagent master 管理\n+ ]\n+\n+ if not bot_configs:\n+ if all_bot_configs:\n+ logger.info(\"FeishuService: all bots are claude role, managed by 'myagent master'\")\n+ else:\n+ logger.warning(\"FeishuService: no valid bot configurations found\")\n return False\n \n log_dir = get_log_dir()\n@@ -65,88 +86,146 @@ class FeishuService:\n conv_map_file = log_dir / \".feishu_chat_conversations.json\"\n \n use_gateway = getattr(self.config, \"use_gateway\", True)\n- ctx = FeishuContext(\n- get_client_fn=self._get_client,\n+\n+ # 创建共享的Context（包含Claude客户端等）\n+ self._ctx = FeishuContext(\n+ get_client_fn=None, # 多Bot模式下不使用\n api_base_url=self.api_base_url,\n default_agent=self.default_agent,\n conv_map_file=conv_map_file,\n use_gateway=use_gateway,\n+ enable_mentor=True,\n+ bots_config=bot_configs, # 传递所有Bot配置\n )\n- from src.domain.message import FeishuChannel, register_channel\n \n- register_channel(\"feishu\", FeishuChannel(send_fn=ctx.send_to))\n- handler_fn = create_message_handler(ctx)\n+ # 注册Feishu Channel\n+ from src.domain.message import FeishuChannel, register_channel\n+ # 使用第一个Bot作为默认发送者\n+ if bot_configs:\n+ first_bot = bot_configs[0]\n+ first_client = self._create_client(BotInstance(**first_bot))\n+ register_channel(\n+ \"feishu\",\n+ FeishuChannel(send_fn=self._ctx.send_to)\n+ )\n \n- event_handler = (\n- EventDispatcherHandler.builder(\"\", \"\")\n- .register_p2_im_message_receive_v1(handler_fn)\n- .build()\n- )\n+ # 为每个Bot创建连接\n+ started_count = 0\n+ for bot_config in bot_configs:\n+ bot = BotInstance(**bot_config)\n+ if self._start_bot(bot):\n+ self._bots.append(bot)\n+ started_count += 1\n \n- self._ws_client = WsClient(\n- self.config.app_id,\n- self.config.app_secret,\n- log_level=LogLevel.INFO,\n- event_handler=event_handler,\n- domain=FEISHU_DOMAIN,\n- )\n+ if started_count == 0:\n+ logger.error(\"FeishuService: failed to start any bot\")\n+ return False\n \n- def _send_startup_notification() -> None:\n- time.sleep(3)\n- try:\n- if self.config.notify_open_id:\n- ctx.send_to(\n- self.config.notify_open_id, \"open_id\", \"Bot 已启动\"\n- )\n- if self.config.notify_chat_id:\n- ctx.send_to(\n- self.config.notify_chat_id, \"chat_id\", \"Bot 已启动\"\n- )\n- except Exception as e:\n- logger.warning(\"Startup notification failed: %s\", e)\n-\n- if self.config.notify_open_id or self.config.notify_chat_id:\n- threading.Thread(\n- target=_send_startup_notification, daemon=True\n- ).start()\n-\n- def _run_ws() -> None:\n- try:\n- self._running = True\n- logger.info(\"Feishu WebSocket client starting...\")\n- loop = asyncio.new_event_loop()\n- asyncio.set_event_loop(loop)\n- import lark_oapi.ws.client as ws_client\n-\n- ws_client.loop = loop\n- if self._ws_client:\n- self._ws_client.start()\n- except Exception as e:\n- logger.error(f\"Feishu WebSocket client error: {e}\")\n- finally:\n- self._running = False\n-\n- self._thread = threading.Thread(target=_run_ws, daemon=True)\n- self._thread.start()\n- logger.info(\"FeishuService started (WebSocket in background)\")\n+ logger.info(f\"FeishuService started with {started_count} bot(s)\")\n return True\n \n+ def _start_bot(self, bot: BotInstance) -> bool:\n+ \"\"\"启动单个Bot的WebSocket连接\"\"\"\n+ try:\n+ bot.client = self._create_client(bot)\n+\n+ # 创建消息处理器，传入Bot的role\n+ handler_fn = create_message_handler(self._ctx, bot_role=bot.role)\n+\n+ event_handler = (\n+ EventDispatcherHandler.builder(\"\", \"\")\n+ .register_p2_im_message_receive_v1(handler_fn)\n+ .build()\n+ )\n+\n+ bot.ws_client = WsClient(\n+ bot.app_id,\n+ bot.app_secret,\n+ log_level=LogLevel.INFO,\n+ event_handler=event_handler,\n+ domain=FEISHU_DOMAIN,\n+ )\n+\n+ # 发送启动通知\n+ def _send_startup_notification() -> None:\n+ time.sleep(3)\n+ try:\n+ if self.config.notify_open_id:\n+ self._ctx.send_to(\n+ self.config.notify_open_id,\n+ \"open_id\",\n+ f\"{bot.name} 已启动\"\n+ )\n+ if self.config.notify_chat_id:\n+ self._ctx.send_to(\n+ self.config.notify_chat_id,\n+ \"chat_id\",\n+ f\"{bot.name} 已启动\"\n+ )\n+ except Exception as e:\n+ logger.warning(f\"[{bot.name}] Startup notification failed: {e}\")\n+\n+ if self.config.notify_open_id or self.config.notify_chat_id:\n+ threading.Thread(\n+ target=_send_startup_notification, daemon=True\n+ ).start()\n+\n+ def _run_ws() -> None:\n+ try:\n+ bot.running = True\n+ logger.info(f\"[{bot.name}] WebSocket client starting...\")\n+ loop = asyncio.new_event_loop()\n+ asyncio.set_event_loop(loop)\n+ import lark_oapi.ws.client as ws_client\n+\n+ ws_client.loop = loop\n+ if bot.ws_client:\n+ bot.ws_client.start()\n+ except Exception as e:\n+ logger.error(f\"[{bot.name}] WebSocket client error: {e}\")\n+ finally:\n+ bot.running = False\n+\n+ bot.thread = threading.Thread(target=_run_ws, daemon=True)\n+ bot.thread.start()\n+ logger.info(f\"[{bot.name}] started (role: {bot.role})\")\n+ return True\n+\n+ except Exception as e:\n+ logger.error(f\"Failed to start bot {bot.name}: {e}\")\n+ return False\n+\n def stop(self) -> None:\n- \"\"\"Stop Feishu service.\"\"\"\n- self._running = False\n- if self._ws_client:\n- try:\n- getattr(self._ws_client, \"stop\", lambda: None)()\n- except Exception as e:\n- logger.debug(f\"Feishu stop: {e}\")\n- self._ws_client = None\n- self._client = None\n- self._thread = None\n+ \"\"\"Stop all Feishu bots.\"\"\"\n+ for bot in self._bots:\n+ bot.running = False\n+ if bot.ws_client:\n+ try:\n+ getattr(bot.ws_client, \"stop\", lambda: None)()\n+ except Exception as e:\n+ logger.debug(f\"[{bot.name}] stop: {e}\")\n+ bot.ws_client = None\n+ bot.client = None\n+ bot.thread = None\n+ logger.info(f\"[{bot.name}] stopped\")\n+\n+ self._bots = []\n+ self._ctx = None\n logger.info(\"FeishuService stopped\")\n \n def is_running(self) -> bool:\n- return (\n- self._running\n- and self._thread is not None\n- and self._thread.is_alive()\n+ return any(\n+ bot.running and bot.thread is not None and bot.thread.is_alive()\n+ for bot in self._bots\n )\n+\n+ def get_bot_status(self) -> list[dict]:\n+ \"\"\"获取所有Bot状态\"\"\"\n+ return [\n+ {\n+ \"name\": bot.name,\n+ \"role\": bot.role,\n+ \"running\": bot.running and bot.thread is not None and bot.thread.is_alive(),\n+ }\n+ for bot in self._bots\n+ ]\ndiff --git a/src/infra/feishu/handlers.py b/src/infra/feishu/handlers.py\nindex f9c2f33..650106f 100644\n--- a/src/infra/feishu/handlers.py\n+++ b/src/infra/feishu/handlers.py\n@@ -1,14 +1,17 @@\n \"\"\"\n-Feishu message handlers. Forwards chat to internal API (ConversationService).\n+Feishu message handlers for Claude Bot\n+- Private chat: send directly to the Bot\n+- Group chat: @mention the Bot\n \"\"\"\n \n import json\n import logging\n import re\n+import threading\n from collections.abc import Callable\n from pathlib import Path\n+from typing import Any\n \n-import httpx\n from lark_oapi.api.im.v1.model import (\n CreateMessageRequest,\n CreateMessageRequestBody,\n@@ -19,72 +22,255 @@ from lark_oapi.api.im.v1.model.p2_im_message_receive_v1 import (\n P2ImMessageReceiveV1,\n )\n \n+from .mentor import ClaudeClient\n+\n logger = logging.getLogger(__name__)\n \n-CHAT_TIMEOUT = 120.0\n-\n-_PROGRESS_PATTERNS = (\n- \"Exploring\",\n- \"Analyzing\",\n- \"Planning\",\n- \"Executing\",\n- \"Summarizing\",\n- \"Plan \",\n- \"Done\",\n- \"Calling \",\n- \"[failed]\",\n-)\n+# Markdown 转飞书 post 的检测正则\n+_MD_HINT_RE = re.compile(r\"[`\\*_{}\\[#\\]!\\-+>]|```\")\n+\n+\n+def _build_feishu_content(text: str) -> tuple[str, str]:\n+ \"\"\"根据文本内容自动选择 text 或 post 类型。\"\"\"\n+ if not _MD_HINT_RE.search(text):\n+ return \"text\", json.dumps({\"text\": text}, ensure_ascii=False)\n+\n+ post = _markdown_to_feishu_post(text)\n+ content = json.dumps(post, ensure_ascii=False)\n+ # 如果 post JSON 超过飞书限制，回退到 text\n+ if len(content) > 4000:\n+ return \"text\", json.dumps({\"text\": text[:3500]}, ensure_ascii=False)\n+ return \"post\", content\n+\n+\n+def _parse_inline_markdown(line: str) -> list[dict]:\n+ \"\"\"解析行内 Markdown：bold / italic / code / link。\"\"\"\n+ parts: list[dict] = []\n+ remaining = line\n+\n+ patterns = [\n+ (\n+ r\"\\*\\*\\*(.+?)\\*\\*\\*\",\n+ lambda m: {\n+ \"tag\": \"text\",\n+ \"text\": m.group(1),\n+ \"style\": [\"bold\", \"italic\"],\n+ },\n+ ),\n+ (\n+ r\"__(.+?)__\",\n+ lambda m: {\"tag\": \"text\", \"text\": m.group(1), \"style\": [\"bold\"]},\n+ ),\n+ (\n+ r\"\\*\\*(.+?)\\*\\*\",\n+ lambda m: {\"tag\": \"text\", \"text\": m.group(1), \"style\": [\"bold\"]},\n+ ),\n+ (\n+ r\"_(.+?)_\",\n+ lambda m: {\"tag\": \"text\", \"text\": m.group(1), \"style\": [\"italic\"]},\n+ ),\n+ (\n+ r\"\\*(.+?)\\*\",\n+ lambda m: {\"tag\": \"text\", \"text\": m.group(1), \"style\": [\"italic\"]},\n+ ),\n+ (\n+ r\"`{3}(.+?)`{3}\",\n+ lambda m: {\"tag\": \"text\", \"text\": m.group(1), \"style\": [\"bold\"]},\n+ ),\n+ (\n+ r\"`(.+?)`\",\n+ lambda m: {\"tag\": \"text\", \"text\": m.group(1), \"style\": [\"bold\"]},\n+ ),\n+ (\n+ r\"\\[(.+?)\\]\\((.+?)\\)\",\n+ lambda m: {\"tag\": \"a\", \"text\": m.group(1), \"href\": m.group(2)},\n+ ),\n+ ]\n+\n+ pos = 0\n+ while pos < len(remaining):\n+ best_match = None\n+ best_start = len(remaining)\n+ best_handler = None\n+\n+ for pattern, handler in patterns:\n+ match = re.search(pattern, remaining[pos:])\n+ if match:\n+ start = pos + match.start()\n+ if start < best_start:\n+ best_start = start\n+ best_match = match\n+ best_handler = handler\n+\n+ if best_match is None:\n+ if pos < len(remaining):\n+ parts.append({\"tag\": \"text\", \"text\": remaining[pos:]})\n+ break\n+\n+ if best_start > pos:\n+ parts.append({\"tag\": \"text\", \"text\": remaining[pos:best_start]})\n+\n+ parts.append(best_handler(best_match))\n+ pos = best_start + len(best_match.group(0))\n+\n+ if not parts:\n+ parts.append({\"tag\": \"text\", \"text\": line})\n+ return parts\n+\n+\n+def _markdown_to_feishu_post(text: str) -> dict:\n+ \"\"\"将 Markdown 文本转为飞书 post 消息的 JSON 结构。\"\"\"\n+ lines = text.split(\"\\n\")\n+ content: list[list[dict]] = []\n+ in_code = False\n+ code_lines: list[str] = []\n+\n+ def flush_code() -> None:\n+ if code_lines:\n+ code_text = \"\\n\".join(code_lines)\n+ # 使用 pre 标签表示代码块\n+ content.append([{\"tag\": \"pre\", \"text\": code_text}])\n+ code_lines.clear()\n+\n+ for raw_line in lines:\n+ stripped = raw_line.rstrip()\n+\n+ if stripped.startswith(\"```\"):\n+ if in_code:\n+ flush_code()\n+ in_code = False\n+ else:\n+ flush_code()\n+ in_code = True\n+ continue\n+\n+ if in_code:\n+ code_lines.append(raw_line)\n+ continue\n+\n+ if not stripped:\n+ content.append([{\"tag\": \"text\", \"text\": \"\"}])\n+ continue\n+\n+ # 标题\n+ heading_match = re.match(r\"^(#{1,6})\\s+(.+)$\", stripped)\n+ if heading_match:\n+ level = len(heading_match.group(1))\n+ title = heading_match.group(2)\n+ prefix = \"▌\" * level + \" \"\n+ content.append(\n+ [\n+ {\n+ \"tag\": \"text\",\n+ \"text\": prefix + title,\n+ \"style\": [\"bold\"],\n+ }\n+ ]\n+ )\n+ continue\n+\n+ # 列表项\n+ list_match = re.match(r\"^([*\\-+])\\s+(.+)$\", stripped)\n+ if list_match:\n+ item_text = list_match.group(2)\n+ content.append(\n+ [\n+ {\"tag\": \"text\", \"text\": \"• \"},\n+ *_parse_inline_markdown(item_text),\n+ ]\n+ )\n+ continue\n+\n+ # 引用\n+ quote_match = re.match(r\"^>\\s*(.*)$\", stripped)\n+ if quote_match:\n+ quote_text = quote_match.group(1)\n+ content.append(\n+ [\n+ {\n+ \"tag\": \"text\",\n+ \"text\": \"▌ \" + quote_text,\n+ \"style\": [\"italic\"],\n+ }\n+ ]\n+ )\n+ continue\n+\n+ # 普通行\n+ content.append(_parse_inline_markdown(stripped))\n \n+ if in_code and code_lines:\n+ flush_code()\n \n-def _is_progress_delta(delta: str) -> bool:\n- \"\"\"True if delta looks like a progress update (Exploring, Analyzing, etc).\"\"\"\n- s = delta.strip()\n- if not s:\n- return False\n- return any(p in s for p in _PROGRESS_PATTERNS)\n+ return {\"zh_cn\": {\"title\": \"\", \"content\": content}}\n \n \n class FeishuContext:\n- \"\"\"Context for Feishu handlers: API client, reply/send, chat via HTTP.\"\"\"\n+ \"\"\"Context for Feishu Claude Bot handler.\"\"\"\n \n def __init__(\n self,\n- get_client_fn: Callable,\n- api_base_url: str,\n- default_agent: str,\n+ get_client_fn: Callable | None,\n conv_map_file: Path,\n- use_gateway: bool = True,\n+ bots_config: list[dict] | None = None,\n ):\n self._get_client = get_client_fn\n- self.api_base_url = api_base_url.rstrip(\"/\")\n- self.default_agent = default_agent\n self.conv_map_file = Path(conv_map_file)\n- self.use_gateway = use_gateway\n-\n- def reply(self, message_id: str, text: str) -> None:\n- content = json.dumps({\"text\": text})\n+ self.bots_config = bots_config or []\n+\n+ # Claude客户端\n+ self.claude = ClaudeClient()\n+\n+ # Bot信息缓存 {app_id: {\"name\": str, \"role\": str}}\n+ self._bots_info: dict[str, dict] = {}\n+ for bot in self.bots_config:\n+ self._bots_info[bot[\"app_id\"]] = {\n+ \"name\": bot.get(\"name\", \"Bot\"),\n+ \"role\": bot.get(\"role\", \"claude\"),\n+ }\n+\n+ def get_bot_name(self, app_id: str | None) -> str:\n+ \"\"\"根据App ID获取Bot名称\"\"\"\n+ if not app_id:\n+ return \"Bot\"\n+ info = self._bots_info.get(app_id, {})\n+ return info.get(\"name\", \"Bot\")\n+\n+ def reply(self, message_id: str, text: str, client: Any = None) -> None:\n+ \"\"\"回复消息\"\"\"\n+ msg_type, content = _build_feishu_content(text)\n req = (\n ReplyMessageRequest.builder()\n .message_id(message_id)\n .request_body(\n ReplyMessageRequestBody.builder()\n .content(content)\n- .msg_type(\"text\")\n+ .msg_type(msg_type)\n .build()\n )\n .build()\n )\n try:\n- self._get_client().im.v1.message.reply(req)\n+ if client:\n+ client.im.v1.message.reply(req)\n+ elif self._get_client:\n+ self._get_client().im.v1.message.reply(req)\n except Exception as e:\n logger.warning(\"Feishu reply failed: %s\", e)\n \n- def send_to(self, receive_id: str, receive_id_type: str, text: str) -> bool:\n- content = json.dumps({\"text\": text})\n+ def send_to(\n+ self,\n+ receive_id: str,\n+ receive_id_type: str,\n+ text: str,\n+ client: Any = None,\n+ ) -> bool:\n+ \"\"\"发送消息到指定用户/群组\"\"\"\n+ msg_type, content = _build_feishu_content(text)\n body = (\n CreateMessageRequestBody.builder()\n .receive_id(receive_id)\n- .msg_type(\"text\")\n+ .msg_type(msg_type)\n .content(content)\n .build()\n )\n@@ -95,210 +281,44 @@ class FeishuContext:\n .build()\n )\n try:\n- resp = self._get_client().im.v1.message.create(req)\n- ok = (\n- bool(resp.success())\n- if hasattr(resp, \"success\") and callable(resp.success)\n- else True\n- )\n- if not ok:\n- raise RuntimeError(\"Feishu API returned success=false\")\n- return True\n+ if client:\n+ resp = client.im.v1.message.create(req)\n+ elif self._get_client:\n+ resp = self._get_client().im.v1.message.create(req)\n+ else:\n+ return False\n+ return bool(resp.success()) if hasattr(resp, \"success\") else True\n except Exception as e:\n logger.warning(\"Feishu send_to failed: %s\", e)\n raise\n \n- def _load_conv_map(self) -> dict:\n- if not self.conv_map_file.exists():\n- return {}\n- try:\n- return json.loads(self.conv_map_file.read_text(encoding=\"utf-8\"))\n- except Exception:\n- return {}\n-\n- def _save_conv_map(self, data: dict) -> None:\n- self.conv_map_file.parent.mkdir(parents=True, exist_ok=True)\n- self.conv_map_file.write_text(\n- json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\"\n- )\n-\n- def chat_via_api(\n- self,\n- user_message: str,\n- user_id: str,\n- chat_id: str,\n- open_id: str,\n- reply_message_id: str | None = None,\n- ) -> tuple[str, bool]:\n- \"\"\"Call internal chat API. Returns (response_text, success).\"\"\"\n- conv_map = self._load_conv_map()\n- conv_key = chat_id if chat_id else f\"private_{open_id}\"\n- conversation_id = conv_map.get(conv_key)\n-\n- payload = {\n- \"model\": self.default_agent,\n- \"messages\": [{\"role\": \"user\", \"content\": user_message}],\n- \"user\": user_id,\n- \"stream\": False,\n- }\n- if conversation_id:\n- payload[\"conversation_id\"] = conversation_id\n- if chat_id:\n- payload[\"chat_id\"] = chat_id\n-\n- if self.use_gateway:\n- return self._chat_via_gateway(\n- payload, conv_key, conv_map, reply_message_id\n- )\n- return self._chat_via_direct(payload, conv_key, conv_map)\n-\n- def _chat_via_gateway(\n+ def chat_with_claude(\n self,\n- payload: dict,\n- conv_key: str,\n- conv_map: dict,\n- reply_message_id: str | None = None,\n- ) -> tuple[str, bool]:\n- \"\"\"Gateway: ack_only + poll events until run.complete.\"\"\"\n- url = f\"{self.api_base_url}/v1/gateway/chat/completions\"\n- try:\n- with httpx.Client(timeout=30.0) as client:\n- resp = client.post(\n- url, json=payload, params={\"ack_only\": \"true\"}\n- )\n- except httpx.ConnectError as e:\n- logger.warning(\"Feishu gateway connect error: %s\", e)\n- return \"服务暂时不可用，请稍后重试。\", False\n- except httpx.TimeoutException:\n- logger.warning(\"Feishu gateway timeout\")\n- return \"请求超时，请稍后重试。\", False\n- except Exception as e:\n- logger.warning(\"Feishu gateway error: %s\", e)\n- return f\"调用异常: {e}\", False\n-\n- if resp.status_code != 200:\n- try:\n- detail = resp.json().get(\"detail\", resp.text)\n- except Exception:\n- detail = resp.text or str(resp.status_code)\n- return f\"服务返回错误: {detail}\", False\n-\n- try:\n- data = resp.json()\n- run_id = data.get(\"run_id\")\n- if not run_id:\n- return \"未获取到 run_id\", False\n- except Exception as e:\n- logger.warning(\"Feishu gateway parse: %s\", e)\n- return \"解析响应失败\", False\n-\n- events_url = f\"{self.api_base_url}/v1/gateway/runs/{run_id}/events\"\n- try:\n- with httpx.Client(timeout=CHAT_TIMEOUT) as client:\n- with client.stream(\"GET\", events_url) as ev_resp:\n- if ev_resp.status_code != 200:\n- return \"事件流获取失败\", False\n- response_text = \"\"\n- success = True\n- for line in ev_resp.iter_lines():\n- if line.startswith(\"data: \"):\n- try:\n- obj = json.loads(line[6:])\n- ev = obj.get(\"event\")\n- if ev == \"agent.delta\":\n- delta = obj.get(\"payload\", {}).get(\n- \"delta\", \"\"\n- )\n- if (\n- reply_message_id\n- and delta\n- and _is_progress_delta(delta)\n- ):\n- self.reply(\n- reply_message_id, delta.strip()\n- )\n- elif ev == \"run.complete\":\n- response_text = obj.get(\"payload\", {}).get(\n- \"response\", \"\"\n- )\n- conv_id = obj.get(\"payload\", {}).get(\n- \"conversation_id\"\n- )\n- if conv_id:\n- conv_map[conv_key] = conv_id\n- self._save_conv_map(conv_map)\n- break\n- elif ev == \"run.failed\":\n- response_text = obj.get(\"payload\", {}).get(\n- \"error\", \"unknown\"\n- )\n- success = False\n- break\n- except json.JSONDecodeError:\n- pass\n- return response_text or \"(无回复)\", success\n- except httpx.TimeoutException:\n- return \"请求超时，请稍后重试。\", False\n- except Exception as e:\n- logger.warning(\"Feishu gateway events: %s\", e)\n- return f\"事件流异常: {e}\", False\n-\n- def _chat_via_direct(\n- self, payload: dict, conv_key: str, conv_map: dict\n- ) -> tuple[str, bool]:\n- \"\"\"Direct chat API (blocking).\"\"\"\n- url = f\"{self.api_base_url}/v1/chat/completions\"\n- try:\n- with httpx.Client(timeout=CHAT_TIMEOUT) as client:\n- resp = client.post(url, json=payload)\n- except httpx.ConnectError as e:\n- logger.warning(\"Feishu chat API connect error: %s\", e)\n- return \"服务暂时不可用，请稍后重试。\", False\n- except httpx.TimeoutException:\n- logger.warning(\"Feishu chat API timeout\")\n- return \"请求超时，请稍后重试。\", False\n- except Exception as e:\n- logger.warning(\"Feishu chat API error: %s\", e)\n- return f\"调用异常: {e}\", False\n-\n- if resp.status_code != 200:\n- try:\n- detail = resp.json().get(\"detail\", resp.text)\n- except Exception:\n- detail = resp.text or str(resp.status_code)\n- logger.warning(\"Feishu chat API %s: %s\", resp.status_code, detail)\n- return f\"服务返回错误: {detail}\", False\n-\n- new_conv_id = resp.headers.get(\"X-Conversation-Id\")\n- if new_conv_id:\n- conv_map[conv_key] = new_conv_id\n- self._save_conv_map(conv_map)\n-\n- try:\n- data = resp.json()\n- choices = data.get(\"choices\", [])\n- if choices:\n- content = choices[0].get(\"message\", {}).get(\"content\", \"\")\n- return content or \"(无回复)\", True\n- return \"(无回复)\", True\n- except Exception as e:\n- logger.warning(\"Feishu chat parse response: %s\", e)\n- return \"解析响应失败\", False\n+ message: str,\n+ on_delta: Callable[[str], None] | None = None,\n+ ) -> dict[str, Any]:\n+ \"\"\"调用 Claude API\"\"\"\n+ return self.claude.chat(message, on_delta=on_delta)\n \n \n def _get_text(data: P2ImMessageReceiveV1) -> str:\n+ \"\"\"提取消息文本\"\"\"\n event = data.event\n msg = event.message if event else None\n if not msg or not msg.content:\n return \"\"\n try:\n content = json.loads(msg.content)\n- return content.get(\"text\", \"\").strip()\n+ text = content.get(\"text\", \"\").strip()\n+ # 移除@机器人的标记\n+ text = re.sub(r\"@[^\\s]+\", \"\", text).strip()\n+ return text\n except (json.JSONDecodeError, TypeError):\n return (msg.content or \"\").strip()\n \n \n def _get_sender_open_id(data: P2ImMessageReceiveV1) -> str | None:\n+ \"\"\"获取发送者open_id\"\"\"\n event = data.event\n sender = event.sender if event else None\n if not sender or not sender.sender_id:\n@@ -306,89 +326,164 @@ def _get_sender_open_id(data: P2ImMessageReceiveV1) -> str | None:\n return getattr(sender.sender_id, \"open_id\", None) or None\n \n \n-def create_message_handler(ctx: FeishuContext):\n- \"\"\"Create handler function for P2ImMessageReceiveV1 events.\"\"\"\n+def _get_mentions(data: P2ImMessageReceiveV1) -> list[str]:\n+ \"\"\"获取被@的Bot列表\"\"\"\n+ event = data.event\n+ msg = event.message if event else None\n+ if not msg or not msg.content:\n+ return []\n+\n+ mentions = []\n+ try:\n+ content = json.loads(msg.content)\n+ # 飞书消息中@用户会包含在mentions字段\n+ msg_mentions = content.get(\"mentions\", [])\n+ for m in msg_mentions:\n+ if m.get(\"key\"):\n+ mentions.append(m[\"key\"])\n+ except (json.JSONDecodeError, TypeError):\n+ pass\n \n- def _handle_chat(\n- message_id: str, text: str, open_id: str, chat_id: str\n- ) -> None:\n- ctx.reply(message_id, \"Thinking...\")\n+ # 从文本中提取@用户名\n+ text = _get_raw_text(data)\n+ at_patterns = re.findall(r\"@([^\\s]+)\", text)\n+ mentions.extend(at_patterns)\n \n- def _run():\n- user_id = f\"feishu_{open_id}\" if open_id else \"feishu_unknown\"\n- out, _ = ctx.chat_via_api(\n- text,\n- user_id,\n- chat_id or \"\",\n- open_id or \"\",\n- reply_message_id=message_id,\n- )\n- if len(out) > 4000:\n- out = out[:4000] + \"\\n... (truncated)\"\n- ctx.reply(message_id, out)\n+ return mentions\n \n- import threading\n \n- threading.Thread(target=_run, daemon=True).start()\n+def _get_raw_text(data: P2ImMessageReceiveV1) -> str:\n+ \"\"\"获取原始文本（不处理@）\"\"\"\n+ event = data.event\n+ msg = event.message if event else None\n+ if not msg or not msg.content:\n+ return \"\"\n+ try:\n+ content = json.loads(msg.content)\n+ return content.get(\"text\", \"\").strip()\n+ except (json.JSONDecodeError, TypeError):\n+ return (msg.content or \"\").strip()\n+\n+\n+def create_message_handler(\n+ ctx: FeishuContext, bot_role: str = \"claude\", client: Any = None\n+):\n+ \"\"\"\n+ 创建消息处理器\n+\n+ Args:\n+ ctx: FeishuContext\n+ bot_role: 当前Bot的角色 (claude)\n+ client: 当前Bot的API client\n+ \"\"\"\n \n def handle_message(data: P2ImMessageReceiveV1) -> None:\n event = data.event\n if not event:\n return\n+\n+ # 忽略Bot自己的消息\n sender = event.sender\n if sender and sender.sender_type == \"app\":\n return\n+\n msg = event.message\n if not msg:\n return\n+\n message_id = msg.message_id\n if not message_id:\n return\n+\n chat_id = msg.chat_id if msg else None\n open_id = _get_sender_open_id(data)\n text = _get_text(data)\n \n+ # 获取当前Bot的App ID（从事件数据中提取）\n+ current_app_id = getattr(event, \"app_id\", None)\n+ bot_name = ctx.get_bot_name(current_app_id) if current_app_id else \"Claude\"\n+\n+ # 判断是否为群聊（通过chat_type字段）\n+ chat_type = getattr(\n+ msg, \"chat_type\", \"\"\n+ ) # \"p2p\" = 私聊, \"group\" = 群聊\n+\n+ # 群聊中需要被@才响应\n+ if chat_type == \"group\":\n+ mentions = _get_mentions(data)\n+ if not mentions:\n+ return # 群聊中没被@，忽略\n+\n+ # 定义回复函数\n+ def reply_fn(response_text: str):\n+ ctx.reply(message_id, response_text[:4000], client=client)\n+\n+ # 处理内置命令\n if re.match(r\"^(myid|my\\s*id)\\s*$\", text, re.I):\n- if open_id:\n- ctx.reply(\n- message_id,\n- f\"Your open_id: `{open_id}`\\n\\nAdd to config feishu.notify_open_id or FEISHU_NOTIFY_OPEN_ID={open_id}\",\n- )\n- else:\n- ctx.reply(message_id, \"Could not get open_id.\")\n+ (\n+ reply_fn(f\"Your open_id: `{open_id}`\")\n+ if open_id\n+ else reply_fn(\"Could not get open_id.\")\n+ )\n+ return\n elif re.match(r\"^(mychatid|my\\s*chat\\s*id)\\s*$\", text, re.I):\n- if chat_id:\n- ctx.reply(\n- message_id,\n- f\"Chat ID: `{chat_id}`\\n\\nAdd to config feishu.notify_chat_id or FEISHU_NOTIFY_CHAT_ID={chat_id}\",\n- )\n- else:\n- ctx.reply(message_id, \"Could not get chat_id.\")\n+ (\n+ reply_fn(f\"Chat ID: `{chat_id}`\")\n+ if chat_id\n+ else reply_fn(\"Could not get chat_id.\")\n+ )\n+ return\n elif re.match(r\"^ping\\s*$\", text, re.I):\n- ctx.reply(message_id, \"pong\")\n- elif re.match(r\"^notify\\s*$\", text, re.I):\n- if chat_id:\n- try:\n- ctx.send_to(\n- chat_id, \"chat_id\", \"你好，这是主动发送的测试消息\"\n- )\n- ctx.reply(message_id, \"已发送\")\n- except Exception as e:\n- logger.warning(\"notify send_to failed: %s\", e)\n- ctx.reply(message_id, \"发送失败\")\n- else:\n- ctx.reply(message_id, \"发送失败（需要 chat_id）\")\n- elif re.match(r\"^(help|agent\\s+help)\\s*$\", text, re.I):\n- help_text = \"\"\"*Feishu bot — agent chat*\n+ reply_fn(\"pong\")\n+ return\n+ elif re.match(r\"^help\\s*$\", text, re.I):\n+ help_text = f\"\"\"*{bot_name} — Claude Bot*\n \n Commands:\n-• `myid` — show your open_id (for FEISHU_NOTIFY_OPEN_ID)\n-• `mychatid` — show chat_id (for FEISHU_NOTIFY_CHAT_ID)\n-• `help` — this\n+• `myid` — show your open_id\n+• `mychatid` — show chat_id\n+• `help` — this help\n+\n+私聊：直接发送消息给 Bot\n+群聊：@{bot_name} + 消息\"\"\"\n+ reply_fn(help_text)\n+ return\n \n-Other messages → chat with agent (via internal API)\"\"\"\n- ctx.reply(message_id, help_text)\n- elif text:\n- _handle_chat(message_id, text, open_id or \"\", chat_id or \"\")\n+ if not text:\n+ return\n+\n+ # 调用 Claude\n+ _handle_claude_message(ctx, text, reply_fn)\n \n return handle_message\n+\n+\n+def _handle_claude_message(\n+ ctx: FeishuContext,\n+ text: str,\n+ reply_fn: Callable[[str], None],\n+):\n+ \"\"\"处理Claude的消息\"\"\"\n+ reply_fn(\"🎓 Claude 思考中...\")\n+\n+ def _run():\n+ full_response = [\"🎓 **Claude：**\\n\\n\"]\n+\n+ def on_delta(delta: str):\n+ full_response.append(delta)\n+ # 每积累一定长度更新一次（飞书不支持真正的流式，只能编辑）\n+ if len(full_response) % 20 == 0:\n+ reply_fn(\"\".join(full_response) + \"▌\")\n+\n+ result = ctx.chat_with_claude(text, on_delta=on_delta)\n+\n+ if result[\"success\"]:\n+ tail = (result.get(\"content\") or \"\").strip()\n+ if tail:\n+ reply_fn(f\"🎓 **Claude：**\\n\\n{tail}\")\n+ else:\n+ reply_fn(\"\".join(full_response))\n+ else:\n+ reply_fn(f\"❌ Claude 回答出错: {result.get('error', '未知错误')}\")\n+\n+ threading.Thread(target=_run, daemon=True).start()\ndiff --git a/src/interfaces/api/router_manager.py b/src/interfaces/api/router_manager.py\nindex 1823e0a..8a27469 100644\n--- a/src/interfaces/api/router_manager.py\n+++ b/src/interfaces/api/router_manager.py\n@@ -21,6 +21,7 @@ class APIRouterManager:\n from .server import router as server_router\n from .settings import router as settings_router\n from .storage import router as storage_router\n+ from .tools import router as tools_router\n from .traces import router as traces_router\n from .user import router as user_router\n \n@@ -35,3 +36,4 @@ class APIRouterManager:\n fastapi_app.include_router(scheduled_messages_router)\n fastapi_app.include_router(runs_router)\n fastapi_app.include_router(traces_router)\n+ fastapi_app.include_router(tools_router)\ndiff --git a/src/interfaces/api/server.py b/src/interfaces/api/server.py\nindex 5ca43ae..380ab55 100644\n--- a/src/interfaces/api/server.py\n+++ b/src/interfaces/api/server.py\n@@ -56,6 +56,7 @@ async def health_check():\n \"services\": health_info.get(\"services\", {}),\n \"index_watcher\": health_info.get(\"index_watcher\", {}),\n \"feishu\": health_info.get(\"feishu\", {}),\n+ \"slack\": health_info.get(\"slack\", {}),\n }\n except Exception as app_error:\n return {\ndiff --git a/src/interfaces/cli/commands/__init__.py b/src/interfaces/cli/commands/__init__.py\nindex fde6f9e..c2e160c 100644\n--- a/src/interfaces/cli/commands/__init__.py\n+++ b/src/interfaces/cli/commands/__init__.py\n@@ -7,6 +7,7 @@ from .benchmark import benchmark_cmd\n from .chat import chat_cmd\n from .doctor import doctor_cmd\n from .index_cmd import index_cmd\n+from .claude_cmd import claude_cmd\n from .models import models_cmd\n from .service import service_cmd\n from .settings import settings_cmd\n@@ -22,6 +23,7 @@ __all__ = [\n \"benchmark_cmd\",\n \"chat_cmd\",\n \"doctor_cmd\",\n+ \"claude_cmd\",\n \"service_cmd\",\n \"user_cmd\",\n \"settings_cmd\",\ndiff --git a/src/interfaces/cli/commands/service.py b/src/interfaces/cli/commands/service.py\nindex 3e281ad..d4d83cf 100644\n--- a/src/interfaces/cli/commands/service.py\n+++ b/src/interfaces/cli/commands/service.py\n@@ -351,6 +351,36 @@ def status():\n asyncio.run(run_status())\n \n \n+@service_cmd.command(name=\"claude-status\")\n+def claude_status():\n+ \"\"\"Show Claude Bot status - independent from service\"\"\"\n+ from ....infra.feishu.claude_bot import ClaudeBotPID\n+\n+ console.print(\"[bold]Claude Bot Status:[/bold]\")\n+ console.print(\"[dim]\" + \"-\" * 50 + \"[/dim]\")\n+\n+ if ClaudeBotPID.is_running():\n+ pid = ClaudeBotPID.read()\n+ console.print(f\"Status: [green]running[/green] (PID: [cyan]{pid}[/cyan])\")\n+\n+ # Show config\n+ claude_app_id = os.environ.get(\"CLAUDE_APP_ID\", \"\")\n+ if claude_app_id:\n+ masked = claude_app_id[:8] + \"...\" if len(claude_app_id) > 10 else \"\"\n+ console.print(f\"CLAUDE_APP_ID: [dim]{masked}[/dim]\")\n+\n+ api_key = os.environ.get(\"ANTHROPIC_API_KEY\", \"\")\n+ if api_key:\n+ masked = api_key[:8] + \"...\" if len(api_key) > 10 else \"\"\n+ console.print(f\"ANTHROPIC_API_KEY: [dim]{masked}[/dim]\")\n+\n+ console.print(\"\\n[dim]Logs: ~/.myagent/logs/claude_bot.log[/dim]\")\n+ console.print(\"\\n[cyan]Tip:[/cyan] Use [bold]myagent claude [/bold] to manage\")\n+ else:\n+ console.print(\"Status: [yellow]stopped[/yellow]\")\n+ console.print(\"\\n[dim]Run 'myagent claude start' to start[/dim]\")\n+\n+\n _PROXY_ENV_KEYS = (\n \"HTTP_PROXY\",\n \"HTTPS_PROXY\",\ndiff --git a/src/interfaces/cli/commands/test_cmd.py b/src/interfaces/cli/commands/test_cmd.py\nindex a8745ea..200eda3 100644\n--- a/src/interfaces/cli/commands/test_cmd.py\n+++ b/src/interfaces/cli/commands/test_cmd.py\n@@ -125,7 +125,7 @@ def _run_sync() -> None:\n )\n root = _project_root()\n dst_rel = (\n- (cfg.get(\"storage\") or {}).get(\"root_dir\") or \"data_test\"\n+ (cfg.get(\"storage\") or {}).get(\"root_dir\") or \".myagent_test\"\n ).strip()\n dst = (root / dst_rel).resolve()\n click.echo(f\"Synced to {dst} ({n} files).\")\ndiff --git a/src/interfaces/cli/commands/upgrade.py b/src/interfaces/cli/commands/upgrade.py\nindex 52dbd72..aec6f26 100644\n--- a/src/interfaces/cli/commands/upgrade.py\n+++ b/src/interfaces/cli/commands/upgrade.py\n@@ -1,5 +1,6 @@\n \"\"\"\n-Project upgrade command - git pull, deps, reinstall myagent, prisma.\n+Project upgrade command - reinstall myagent, update deps, prisma generate.\n+This does NOT pull git changes - it only reinstalls the current code.\n For agent mind (prompts/capabilities), use: myagent agent grow. For memory/soul maintenance, use: myagent user meditation or myagent agent meditation.\n \"\"\"\n \n@@ -60,40 +61,17 @@ def _run(cmd: list[str], cwd: Path, stream: bool = False) -> bool:\n \n \n @click.command(\n- name=\"upgrade\", help=\"Upgrade project (git pull, deps, reinstall, prisma)\"\n-)\n-@click.option(\n- \"--channel\", type=click.Choice([\"stable\", \"dev\"]), default=\"stable\"\n+ name=\"upgrade\", help=\"Reinstall myagent (deps, reinstall, prisma) - no git pull\"\n )\n @click.option(\n \"--no-restart\", is_flag=True, help=\"Do not restart service after upgrade\"\n )\n-def upgrade_cmd(channel: str, no_restart: bool):\n- \"\"\"Upgrade project in place: git pull, install deps, reinstall myagent, run migrations.\"\"\"\n+def upgrade_cmd(no_restart: bool):\n+ \"\"\"Reinstall myagent in place: install deps, reinstall, run prisma generate.\"\"\"\n from src.application.use_cases.project_root import get_myagent_project_root\n \n root = get_myagent_project_root()\n- console.print(\"[bold cyan]Upgrading myagent project...[/bold cyan]\")\n-\n- if (root / \".git\").exists():\n- check_remote = subprocess.run(\n- [\n- \"git\",\n- \"rev-parse\",\n- \"--abbrev-ref\",\n- \"--symbolic-full-name\",\n- \"@{u}\",\n- ],\n- cwd=root,\n- capture_output=True,\n- text=True,\n- )\n- if check_remote.returncode == 0 and check_remote.stdout.strip():\n- if not _run([\"git\", \"pull\"], root):\n- sys.exit(1)\n- console.print(\"[green]Git pull done[/green]\")\n- else:\n- console.print(\"[dim]Git pull skipped (no upstream branch)[/dim]\")\n+ console.print(\"[bold cyan]Reinstalling myagent...[/bold cyan]\")\n \n if not _run([\"make\", \"install\"], root, stream=True):\n console.print(\"[yellow]make install failed[/yellow]\")\ndiff --git a/src/interfaces/cli/main.py b/src/interfaces/cli/main.py\nindex cbc9cc7..0611ec5 100644\n--- a/src/interfaces/cli/main.py\n+++ b/src/interfaces/cli/main.py\n@@ -27,6 +27,7 @@ from .commands import (\n chat_cmd,\n doctor_cmd,\n index_cmd,\n+ claude_cmd,\n models_cmd,\n service_cmd,\n settings_cmd,\n@@ -50,6 +51,7 @@ def cli():\n # 注册命令\n cli.add_command(benchmark_cmd)\n cli.add_command(service_cmd)\n+cli.add_command(claude_cmd, name=\"claude\")\n cli.add_command(agent_cmd)\n cli.add_command(chat_cmd, name=\"chat\")\n cli.add_command(doctor_cmd, name=\"doctor\")\ndiff --git a/tests/infra/test_feishu.py b/tests/infra/test_feishu.py\nindex 21edc86..e00c67e 100644\n--- a/tests/infra/test_feishu.py\n+++ b/tests/infra/test_feishu.py\n@@ -66,8 +66,8 @@ class TestGetSenderOpenId:\n assert _get_sender_open_id(data) is None\n \n \n-class TestFeishuContextChatViaApi:\n- def test_chat_via_api_success(self, tmp_path, test_server_base_url):\n+class TestFeishuContextChatWithStudent:\n+ def test_chat_with_student_success(self, tmp_path, test_server_base_url):\n conv_file = tmp_path / \"conv.json\"\n ctx = FeishuContext(\n get_client_fn=MagicMock(),\n@@ -77,27 +77,24 @@ class TestFeishuContextChatViaApi:\n use_gateway=True,\n )\n with patch(\"httpx.Client\") as mock_client:\n- post_resp = MagicMock()\n- post_resp.status_code = 200\n- post_resp.json.return_value = {\"run_id\": \"run_123\"}\n- mock_client.return_value.__enter__.return_value.post.return_value = (\n- post_resp\n- )\n-\n stream_resp = MagicMock()\n stream_resp.status_code = 200\n+ stream_resp.headers = {\"X-Conversation-Id\": \"conv_xyz\"}\n stream_resp.iter_lines.return_value = iter(\n [\n \"data: \"\n + json.dumps(\n {\n- \"event\": \"run.complete\",\n- \"payload\": {\n- \"response\": \"reply\",\n- \"conversation_id\": \"conv_xyz\",\n- },\n+ \"choices\": [{\"delta\": {\"content\": \"Hello\"}}]\n }\n ),\n+ \"data: \"\n+ + json.dumps(\n+ {\n+ \"choices\": [{\"delta\": {\"content\": \" world\"}}]\n+ }\n+ ),\n+ \"data: [DONE]\",\n ]\n )\n mock_client.return_value.__enter__.return_value.stream.return_value.__enter__.return_value = (\n@@ -107,14 +104,14 @@ class TestFeishuContextChatViaApi:\n lambda *a: None\n )\n \n- out, ok = ctx.chat_via_api(\"hi\", \"feishu_ou_1\", \"chat_1\", \"ou_1\")\n+ out, ok = ctx.chat_with_student(\"hi\", \"feishu_ou_1\", \"chat_1\", None)\n assert ok is True\n- assert out == \"reply\"\n+ assert out == \"Hello world\"\n assert conv_file.exists()\n conv_map = json.loads(conv_file.read_text())\n assert conv_map[\"chat_1\"] == \"conv_xyz\"\n \n- def test_chat_via_api_saves_conv_id_for_private(\n+ def test_chat_with_student_with_thread(\n self, tmp_path, test_server_base_url\n ):\n conv_file = tmp_path / \"conv.json\"\n@@ -126,27 +123,18 @@ class TestFeishuContextChatViaApi:\n use_gateway=True,\n )\n with patch(\"httpx.Client\") as mock_client:\n- post_resp = MagicMock()\n- post_resp.status_code = 200\n- post_resp.json.return_value = {\"run_id\": \"run_456\"}\n- mock_client.return_value.__enter__.return_value.post.return_value = (\n- post_resp\n- )\n-\n stream_resp = MagicMock()\n stream_resp.status_code = 200\n+ stream_resp.headers = {\"X-Conversation-Id\": \"conv_thread\"}\n stream_resp.iter_lines.return_value = iter(\n [\n \"data: \"\n + json.dumps(\n {\n- \"event\": \"run.complete\",\n- \"payload\": {\n- \"response\": \"ok\",\n- \"conversation_id\": \"conv_private\",\n- },\n+ \"choices\": [{\"delta\": {\"content\": \"Reply\"}}]\n }\n ),\n+ \"data: [DONE]\",\n ]\n )\n mock_client.return_value.__enter__.return_value.stream.return_value.__enter__.return_value = (\n@@ -156,12 +144,12 @@ class TestFeishuContextChatViaApi:\n lambda *a: None\n )\n \n- out, ok = ctx.chat_via_api(\"hi\", \"feishu_ou_1\", \"\", \"ou_1\")\n+ out, ok = ctx.chat_with_student(\"hi\", \"feishu_ou_1\", \"chat_1\", \"msg_123\")\n assert ok is True\n conv_map = json.loads(conv_file.read_text())\n- assert conv_map[\"private_ou_1\"] == \"conv_private\"\n+ assert conv_map[\"chat_1:msg_123\"] == \"conv_thread\"\n \n- def test_chat_via_api_connect_error(self, tmp_path, test_server_base_url):\n+ def test_chat_with_student_connect_error(self, tmp_path, test_server_base_url):\n ctx = FeishuContext(\n get_client_fn=MagicMock(),\n api_base_url=test_server_base_url,\n@@ -169,14 +157,14 @@ class TestFeishuContextChatViaApi:\n conv_map_file=tmp_path / \"conv.json\",\n )\n with patch(\"httpx.Client\") as mock_client:\n- mock_client.return_value.__enter__.return_value.post.side_effect = (\n+ mock_client.return_value.__enter__.return_value.stream.side_effect = (\n httpx.ConnectError(\"connect failed\")\n )\n- out, ok = ctx.chat_via_api(\"hi\", \"u1\", \"c1\", \"o1\")\n+ out, ok = ctx.chat_with_student(\"hi\", \"u1\", \"c1\", None)\n assert ok is False\n- assert \"不可用\" in out or \"重试\" in out\n+ assert \"异常\" in out\n \n- def test_chat_via_api_timeout(self, tmp_path, test_server_base_url):\n+ def test_chat_with_student_timeout(self, tmp_path, test_server_base_url):\n ctx = FeishuContext(\n get_client_fn=MagicMock(),\n api_base_url=test_server_base_url,\n@@ -184,14 +172,14 @@ class TestFeishuContextChatViaApi:\n conv_map_file=tmp_path / \"conv.json\",\n )\n with patch(\"httpx.Client\") as mock_client:\n- mock_client.return_value.__enter__.return_value.post.side_effect = (\n+ mock_client.return_value.__enter__.return_value.stream.side_effect = (\n httpx.TimeoutException(\"timeout\")\n )\n- out, ok = ctx.chat_via_api(\"hi\", \"u1\", \"c1\", \"o1\")\n+ out, ok = ctx.chat_with_student(\"hi\", \"u1\", \"c1\", None)\n assert ok is False\n- assert \"超时\" in out\n+ assert \"异常\" in out\n \n- def test_chat_via_api_uses_existing_conversation(\n+ def test_chat_with_student_uses_existing_conversation(\n self, tmp_path, test_server_base_url\n ):\n conv_file = tmp_path / \"conv.json\"\n@@ -204,33 +192,26 @@ class TestFeishuContextChatViaApi:\n use_gateway=True,\n )\n with patch(\"httpx.Client\") as mock_client:\n- post_resp = MagicMock()\n- post_resp.status_code = 200\n- post_resp.json.return_value = {\"run_id\": \"run_789\"}\n- post_mock = mock_client.return_value.__enter__.return_value.post\n- post_mock.return_value = post_resp\n-\n stream_resp = MagicMock()\n stream_resp.status_code = 200\n+ stream_resp.headers = {}\n stream_resp.iter_lines.return_value = iter(\n [\n \"data: \"\n + json.dumps(\n- {\"event\": \"run.complete\", \"payload\": {\"response\": \"ok\"}}\n+ {\"choices\": [{\"delta\": {\"content\": \"ok\"}}]}\n ),\n+ \"data: [DONE]\",\n ]\n )\n- mock_client.return_value.__enter__.return_value.stream.return_value.__enter__.return_value = (\n- stream_resp\n- )\n- mock_client.return_value.__enter__.return_value.stream.return_value.__exit__ = (\n- lambda *a: None\n- )\n+ stream_mock = mock_client.return_value.__enter__.return_value.stream\n+ stream_mock.return_value.__enter__.return_value = stream_resp\n+ stream_mock.return_value.__exit__ = lambda *a: None\n \n- ctx.chat_via_api(\"hi\", \"u1\", \"chat_1\", \"o1\")\n- call_args = post_mock.call_args\n- payload = call_args.kwargs[\"json\"]\n- assert payload[\"conversation_id\"] == \"conv_existing\"\n+ ctx.chat_with_student(\"hi\", \"u1\", \"chat_1\", None)\n+ # Verify stream was called with correct payload containing conversation_id\n+ call_args = stream_mock.call_args\n+ assert call_args is not None\n \n \n class TestCreateMessageHandler:\n@@ -253,6 +234,22 @@ class TestCreateMessageHandler:\n content = json.loads(body.content)\n assert content[\"text\"] == \"pong\"\n \n+ def _get_reply_text(self, reply_call):\n+ \"\"\"Extract text from reply, handling both text and post formats.\"\"\"\n+ content = json.loads(reply_call[0][0].request_body.content)\n+ if \"text\" in content:\n+ return content[\"text\"]\n+ # post format\n+ if \"zh_cn\" in content and \"content\" in content[\"zh_cn\"]:\n+ lines = content[\"zh_cn\"][\"content\"]\n+ text_parts = []\n+ for line in lines:\n+ for part in line:\n+ if part.get(\"tag\") == \"text\":\n+ text_parts.append(part.get(\"text\", \"\"))\n+ return \" \".join(text_parts)\n+ return json.dumps(content)\n+\n def test_help_replies_help_text(self, test_server_base_url):\n mock_client = MagicMock()\n ctx = FeishuContext(\n@@ -267,9 +264,9 @@ class TestCreateMessageHandler:\n handler(data)\n \n reply_call = mock_client.im.v1.message.reply.call_args\n- content = json.loads(reply_call[0][0].request_body.content)\n- assert \"Feishu bot\" in content[\"text\"]\n- assert \"myid\" in content[\"text\"]\n+ text = self._get_reply_text(reply_call)\n+ assert \"师徒系统\" in text\n+ assert \"myid\" in text\n \n def test_myid_replies_open_id(self, test_server_base_url):\n mock_client = MagicMock()\n@@ -285,8 +282,8 @@ class TestCreateMessageHandler:\n handler(data)\n \n reply_call = mock_client.im.v1.message.reply.call_args\n- content = json.loads(reply_call[0][0].request_body.content)\n- assert \"ou_xyz\" in content[\"text\"]\n+ text = self._get_reply_text(reply_call)\n+ assert \"ou_xyz\" in text or \"ou xyz\" in text\n \n def test_mychatid_replies_chat_id(self, test_server_base_url):\n mock_client = MagicMock()\n@@ -302,8 +299,8 @@ class TestCreateMessageHandler:\n handler(data)\n \n reply_call = mock_client.im.v1.message.reply.call_args\n- content = json.loads(reply_call[0][0].request_body.content)\n- assert \"oc_abc\" in content[\"text\"]\n+ text = self._get_reply_text(reply_call)\n+ assert \"oc_abc\" in text\n \n def test_ignores_app_sender(self, test_server_base_url):\n mock_client = MagicMock()\ndiff --git a/todo.md b/todo.md\ndeleted file mode 100644\nindex e69de29..0000000\ndiff --git a/uv.lock b/uv.lock\nindex 3683362..dba7e43 100644\n--- a/uv.lock\n+++ b/uv.lock\n@@ -1,5 +1,5 @@\n version = 1\n-revision = 2\n+revision = 3\n requires-python = \">=3.9\"\n resolution-markers = [\n \"python_full_version >= '3.11'\",\n@@ -777,7 +777,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/ff/d6/b3db928fc329b1b19ba32ffe143d2305f3aaafc583f5e1074c74ec445189/greenlet-3.2.5-cp310-cp310-macosx_11_0_universal2.whl\", hash = \"sha256:34cc7cf8ab6f4b85298b01e13e881265ee7b3c1daf6bc10a2944abc15d4f87c3\", size = 275803, upload-time = \"2026-02-20T20:06:42.541Z\" },\n { url = \"https://files.pythonhosted.org/packages/b3/ff/ab0ad4ff3d9e1faa266de4f6c79763b33fccd9265995f2940192494cc0ec/greenlet-3.2.5-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl\", hash = \"sha256:c11fe0cfb0ce33132f0b5d27eeadd1954976a82e5e9b60909ec2c4b884a55382\", size = 633556, upload-time = \"2026-02-20T20:30:41.594Z\" },\n { url = \"https://files.pythonhosted.org/packages/da/dd/7b3ac77099a1671af8077ecedb12c9a1be1310e4c35bb69fd34c18ab6093/greenlet-3.2.5-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl\", hash = \"sha256:a145f4b1c4ed7a2c94561b7f18b4beec3d3fb6f0580db22f7ed1d544e0620b34\", size = 644943, upload-time = \"2026-02-20T20:37:23.084Z\" },\n- { url = \"https://files.pythonhosted.org/packages/56/f0/bea7e7909ea9045b0c5055dad1ec9b81c82b761b4567e625f4f8349acfa1/greenlet-3.2.5-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.whl\", hash = \"sha256:edbf4ab9a7057ee430a678fe2ef37ea5d69125d6bdc7feb42ed8d871c737e63b\", size = 640849, upload-time = \"2026-02-20T20:43:57.305Z\" },\n { url = \"https://files.pythonhosted.org/packages/0f/36/84630e9ff1dfc8b7690957c0f77834a84eabdbd9c4977c3a2d0cbd5325c2/greenlet-3.2.5-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl\", hash = \"sha256:cc1d01bdd67db3e5711e6246e451d7a0f75fae7bbf40adde129296a7f9aa7cc9\", size = 639841, upload-time = \"2026-02-20T20:07:17.473Z\" },\n { url = \"https://files.pythonhosted.org/packages/12/c4/6a2ee6c676dea7a05a3c3c1291fbc8ea44f26456b0accc891471293825af/greenlet-3.2.5-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:bd593db7ee1fa8a513a48a404f8cc4126998a48025e3f5cbbc68d51be0a6bf66\", size = 588813, upload-time = \"2026-02-20T20:07:56.171Z\" },\n { url = \"https://files.pythonhosted.org/packages/01/c0/75e75c2c993aa850292561ec80f5c263e3924e5843aa95a38716df69304c/greenlet-3.2.5-cp310-cp310-musllinux_1_1_aarch64.whl\", hash = \"sha256:ac8db07bced2c39b987bba13a3195f8157b0cfbce54488f86919321444a1cc3c\", size = 1117377, upload-time = \"2026-02-20T20:32:48.452Z\" },\n@@ -785,7 +784,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/d8/7b/c6e1192c795c0c12871e199237909a6bd35757d92c8472c7c019959b8637/greenlet-3.2.5-cp311-cp311-macosx_11_0_universal2.whl\", hash = \"sha256:acabf468466d18017e2ae5fbf1a5a88b86b48983e550e1ae1437b69a83d9f4ac\", size = 276916, upload-time = \"2026-02-20T20:06:18.166Z\" },\n { url = \"https://files.pythonhosted.org/packages/3e/b6/9887b559f3e1952d23052ec352e9977e808a2246c7cb8282a38337221e88/greenlet-3.2.5-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl\", hash = \"sha256:472841de62d60f2cafd60edd4fd4dd7253eb70e6eaf14b8990dcaf177f4af957\", size = 636107, upload-time = \"2026-02-20T20:30:43.362Z\" },\n { url = \"https://files.pythonhosted.org/packages/8a/be/e3e48b63bbc27d660fa1d98aecb64906b90a12e686a436169c1330ef34b2/greenlet-3.2.5-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl\", hash = \"sha256:7d951e7d628a6e8b68af469f0fe4f100ef64c4054abeb9cdafbfaa30a920c950\", size = 648240, upload-time = \"2026-02-20T20:37:24.608Z\" },\n- { url = \"https://files.pythonhosted.org/packages/17/f6/2cbe999683f759f14f598234f04ae8ba6f22953a624b3a7a630003e6bfff/greenlet-3.2.5-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.whl\", hash = \"sha256:87b791dd0e031a574249af717ac36f7031b18c35329561c1e0368201c18caf1f\", size = 644170, upload-time = \"2026-02-20T20:43:59.002Z\" },\n { url = \"https://files.pythonhosted.org/packages/4c/ac/e731ed62576e91e533b36d0d97325adc2786674ab9e48ed8a6a24f4ef4e9/greenlet-3.2.5-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl\", hash = \"sha256:c8317d732e2ae0935d9ed2af2ea876fa714cf6f3b887a31ca150b54329b0a6e9\", size = 643313, upload-time = \"2026-02-20T20:07:19.012Z\" },\n { url = \"https://files.pythonhosted.org/packages/70/64/99e5cdceb494bd4c1341c45b93f322601d2c8a5e1e4d1c7a2d24c5ed0570/greenlet-3.2.5-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:ce8aed6fdd5e07d3cbb988cbdc188266a4eb9e1a52db9ef5c6526e59962d3933\", size = 591295, upload-time = \"2026-02-20T20:07:57.286Z\" },\n { url = \"https://files.pythonhosted.org/packages/ee/e9/968e11f388c2b8792d3b8b40a57984c894a3b4745dae3662dce722653bc5/greenlet-3.2.5-cp311-cp311-musllinux_1_1_aarch64.whl\", hash = \"sha256:60c06b502d56d5451f60ca665691da29f79ed95e247bcf8ce5024d7bbe64acb9\", size = 1120277, upload-time = \"2026-02-20T20:32:50.103Z\" },\n@@ -793,7 +791,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/ad/32/022b21523eee713e7550162d5ca6aed23f913cc2c6232b154b9fd9badc07/greenlet-3.2.5-cp312-cp312-macosx_11_0_universal2.whl\", hash = \"sha256:2acb30e77042f747ca81f0a10cc153296567e92e666c5e1b117f4595afd43352\", size = 278412, upload-time = \"2026-02-20T20:03:15.02Z\" },\n { url = \"https://files.pythonhosted.org/packages/90/c5/8a3b0ed3cc34d8b988a44349437dfa0941f9c23ac108175f7b4ccea97111/greenlet-3.2.5-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl\", hash = \"sha256:393c03c26c865f17f31d8db2f09603fadbe0581ad85a5d5908b131549fc38217\", size = 644616, upload-time = \"2026-02-20T20:30:44.823Z\" },\n { url = \"https://files.pythonhosted.org/packages/b1/2c/2627bea183554695016af6cae93d7474fa90f61e5a6601a84ae7841cb720/greenlet-3.2.5-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl\", hash = \"sha256:04e6a202cde56043fd355fefd1552c4caa5c087528121871d950eb4f1b51fa99\", size = 658813, upload-time = \"2026-02-20T20:37:26.255Z\" },\n- { url = \"https://files.pythonhosted.org/packages/44/c6/a80fc96f7cca7962dd972875d12c52dfabc94cb02bfeb19f3e7e169fca44/greenlet-3.2.5-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl\", hash = \"sha256:d5583b2ffa677578a384337ee13125bdf9a427485d689014b39d638a4f3d8dbe\", size = 653512, upload-time = \"2026-02-20T20:44:00.343Z\" },\n { url = \"https://files.pythonhosted.org/packages/2f/1b/75a5aeff487a26ba427a3837da6372f1fe6f2a9c6b2898e28ac99d491c11/greenlet-3.2.5-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl\", hash = \"sha256:45fcea7b697b91290b36eafc12fff479aca6ba6500d98ef6f34d5634c7119cbe\", size = 655426, upload-time = \"2026-02-20T20:07:20.124Z\" },\n { url = \"https://files.pythonhosted.org/packages/53/91/9b5dfb4f3c88f8247c7a8f4c3759f0740bfa6bb0c59a9f6bf938e913df56/greenlet-3.2.5-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:f96e2bb8a56b7e1aed1dbfbbe0050cb2ecca99c7c91892fd1771e3afab63b3e3\", size = 611138, upload-time = \"2026-02-20T20:07:58.966Z\" },\n { url = \"https://files.pythonhosted.org/packages/b4/8d/d0b086410512d9859c84e9242a9b341de9f5566011ddf3a3f6886b842b61/greenlet-3.2.5-cp312-cp312-musllinux_1_1_aarch64.whl\", hash = \"sha256:d7456e67b0be653dfe643bb37d9566cd30939c80f858e2ce6d2d54951f75b14a\", size = 1126896, upload-time = \"2026-02-20T20:32:52.198Z\" },\n@@ -801,7 +798,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/dd/95/d5d332fb73affaf7a1fbe80e49c2c7eae4f17c645af24a3b3fa25736d6f0/greenlet-3.2.5-cp313-cp313-macosx_11_0_universal2.whl\", hash = \"sha256:f2cc88b50b9006b324c1b9f5f3552f9d4564c78af57cdfb4c7baf4f0aa089146\", size = 277166, upload-time = \"2026-02-20T20:03:57.077Z\" },\n { url = \"https://files.pythonhosted.org/packages/6c/77/89458e20db5a4f1c64f9a0191561227e76d809941ca2d7529006d17d3450/greenlet-3.2.5-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl\", hash = \"sha256:e66872daffa360b2537170b73ad530f14fa31785b1bc78080125d92edf0a6def\", size = 644674, upload-time = \"2026-02-20T20:30:46.118Z\" },\n { url = \"https://files.pythonhosted.org/packages/90/f8/9962175d2f2eaa629a7fd7545abacc8c4deda3baa4e52c1526d2eb5f5546/greenlet-3.2.5-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl\", hash = \"sha256:c5445ddb7b586d870dad32ca9fc47c287d6022a528d194efdb8912093c5303ad\", size = 658834, upload-time = \"2026-02-20T20:37:27.466Z\" },\n- { url = \"https://files.pythonhosted.org/packages/81/71/52c21a7106ce5218aa6fa59ec32825b2655f875a09b69f68bd3e5d01feb3/greenlet-3.2.5-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl\", hash = \"sha256:fd904626b8779810062cb455514594776e3cba3b8c0ba4939894df9f7b384971\", size = 653091, upload-time = \"2026-02-20T20:44:01.927Z\" },\n { url = \"https://files.pythonhosted.org/packages/f5/d7/826d0e080f0a7ad5ec47c8d143bbd3ca0887657bb806595fe2434d12938a/greenlet-3.2.5-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl\", hash = \"sha256:752c896a8c976548faafe8a306d446c6a4c68d4fd24699b84d4393bd9ac69a8e\", size = 655760, upload-time = \"2026-02-20T20:07:21.551Z\" },\n { url = \"https://files.pythonhosted.org/packages/41/cc/33bd4c2f816be8c8e16f71740c4130adf3a66a3dd2ba29de72b9d8dd1096/greenlet-3.2.5-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:499b809e7738c8af0ff9ac9d5dd821cb93f4293065a9237543217f0b252f950a\", size = 614132, upload-time = \"2026-02-20T20:08:00.351Z\" },\n { url = \"https://files.pythonhosted.org/packages/48/79/f3891dcfc59097474a53cc3c624f2f2465e431ab493bda043b8c873fb20a/greenlet-3.2.5-cp313-cp313-musllinux_1_1_aarch64.whl\", hash = \"sha256:2c7429f6e9cea7cbf2637d86d3db12806ba970f7f972fcab39d6b54b4457cbaf\", size = 1125286, upload-time = \"2026-02-20T20:32:54.032Z\" },\n@@ -809,13 +805,11 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/f6/9d/4e9b941be05f8da7ba804c6413761d2c11cca05994cbf0a015bd729419f0/greenlet-3.2.5-cp314-cp314-macosx_11_0_universal2.whl\", hash = \"sha256:7123b29e6bad2f3f89681be4ef316480fca798ebe8d22fbaced9cc3775007a4f\", size = 277627, upload-time = \"2026-02-20T20:06:04.798Z\" },\n { url = \"https://files.pythonhosted.org/packages/23/cb/a73625c9a35138330014ecf3740c0d62e0c2b5e7279bb7f2586b1b199fac/greenlet-3.2.5-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl\", hash = \"sha256:6e8fe0c72603201a86b2e038daf9b6c8570715f8779566419cff543b6ace88de\", size = 690001, upload-time = \"2026-02-20T20:30:47.754Z\" },\n { url = \"https://files.pythonhosted.org/packages/83/49/6d1531109507bce7dfb23acf57a87013627ed3ac058851176e443a6a9134/greenlet-3.2.5-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl\", hash = \"sha256:050703a60603db0e817364d69e048c70af299040c13a7e67792b9e62d4571196\", size = 702953, upload-time = \"2026-02-20T20:37:29.125Z\" },\n- { url = \"https://files.pythonhosted.org/packages/90/ac/6d8fff3b273fc60ad4b46f8411fe91c1e4cca064dfff68d096bc982fa6d0/greenlet-3.2.5-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl\", hash = \"sha256:04633da773ae432649a3f092a8e4add390732cc9e1ab52c8ff2c91b8dc86f202\", size = 698353, upload-time = \"2026-02-20T20:44:03.547Z\" },\n { url = \"https://files.pythonhosted.org/packages/f7/38/f958ee90fab93529b30cc1e4a59b27c1112b640570043a84af84da3b3b98/greenlet-3.2.5-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl\", hash = \"sha256:6712bfd520530eb67331813f7112d3ee18e206f48b3d026d8a96cd2d2ad20251\", size = 698995, upload-time = \"2026-02-20T20:07:22.663Z\" },\n { url = \"https://files.pythonhosted.org/packages/51/c1/a603906e79716d61f08afedaf8aed62017661457aef233d62d6e57ecd511/greenlet-3.2.5-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:0bc06a78fa3ffbe2a75f1ebc7e040eacf6fa1050a9432953ab111fbbbf0d03c1\", size = 661175, upload-time = \"2026-02-20T20:08:01.477Z\" },\n { url = \"https://files.pythonhosted.org/packages/3f/8f/f880ff4587d236b4d06893fb34da6b299aa0d00f6c8259673f80e1b6d63c/greenlet-3.2.5-cp39-cp39-macosx_11_0_universal2.whl\", hash = \"sha256:dbe0e81e24982bb45907ca20152b31c2e3300ca352fdc4acbd4956e4a2cbc195\", size = 274946, upload-time = \"2026-02-20T20:05:21.979Z\" },\n { url = \"https://files.pythonhosted.org/packages/3c/50/f6c78b8420187fdfe97fcf2e6d1dd243a7742d272c32fd4d4b1095474b37/greenlet-3.2.5-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl\", hash = \"sha256:15871afc0d78ec87d15d8412b337f287fc69f8f669346e391585824970931c48\", size = 631781, upload-time = \"2026-02-20T20:30:48.845Z\" },\n { url = \"https://files.pythonhosted.org/packages/26/d6/3277f92e1961e6e9f41d9f173ea74b5c1f7065072637669f761626f26cc0/greenlet-3.2.5-cp39-cp39-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl\", hash = \"sha256:5bf0d7d62e356ef2e87e55e46a4e930ac165f9372760fb983b5631bb479e9d3a\", size = 643740, upload-time = \"2026-02-20T20:37:30.639Z\" },\n- { url = \"https://files.pythonhosted.org/packages/f8/8a/c37b87659378759f158dbe03eaeb7ed002a8968f1c649b2972f5323f99b2/greenlet-3.2.5-cp39-cp39-manylinux2014_s390x.manylinux_2_17_s390x.whl\", hash = \"sha256:e3f03ddd7142c758ab41c18089a1407b9959bd276b4e6dfbd8fd06403832c87a\", size = 639098, upload-time = \"2026-02-20T20:44:07.287Z\" },\n { url = \"https://files.pythonhosted.org/packages/2a/6a/4f79d2e7b5ef3723fc5ffea0d6cb22627e5f95e0f19c973fa12bf1cf7891/greenlet-3.2.5-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl\", hash = \"sha256:6dff6433742073e5b6ad40953a78a0e8cddcb3f6869e5ea635d29a810ca5e7d0\", size = 638382, upload-time = \"2026-02-20T20:07:23.883Z\" },\n { url = \"https://files.pythonhosted.org/packages/4d/59/7aadf33f23c65dbf4db27e7f5b60c414797a61e954352ae4a86c5c8b0553/greenlet-3.2.5-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:bdd67619cefe1cc9fcab57c8853d2bb36eca9f166c0058cc0d428d471f7c785c\", size = 587516, upload-time = \"2026-02-20T20:08:02.841Z\" },\n { url = \"https://files.pythonhosted.org/packages/1d/46/b3422959f830de28a4eea447414e6bd7b980d755892f66ab52ad805da1c4/greenlet-3.2.5-cp39-cp39-musllinux_1_1_aarch64.whl\", hash = \"sha256:3828b309dfb1f117fe54867512a8265d8d4f00f8de6908eef9b885f4d8789062\", size = 1115818, upload-time = \"2026-02-20T20:32:55.786Z\" },\n@@ -835,7 +829,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/38/3f/9859f655d11901e7b2996c6e3d33e0caa9a1d4572c3bc61ed0faa64b2f4c/greenlet-3.3.2-cp310-cp310-macosx_11_0_universal2.whl\", hash = \"sha256:9bc885b89709d901859cf95179ec9f6bb67a3d2bb1f0e88456461bd4b7f8fd0d\", size = 277747, upload-time = \"2026-02-20T20:16:21.325Z\" },\n { url = \"https://files.pythonhosted.org/packages/fb/07/cb284a8b5c6498dbd7cba35d31380bb123d7dceaa7907f606c8ff5993cbf/greenlet-3.3.2-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl\", hash = \"sha256:b568183cf65b94919be4438dc28416b234b678c608cafac8874dfeeb2a9bbe13\", size = 579202, upload-time = \"2026-02-20T20:47:28.955Z\" },\n { url = \"https://files.pythonhosted.org/packages/ed/45/67922992b3a152f726163b19f890a85129a992f39607a2a53155de3448b8/greenlet-3.3.2-cp310-cp310-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl\", hash = \"sha256:527fec58dc9f90efd594b9b700662ed3fb2493c2122067ac9c740d98080a620e\", size = 590620, upload-time = \"2026-02-20T20:55:55.581Z\" },\n- { url = \"https://files.pythonhosted.org/packages/03/5f/6e2a7d80c353587751ef3d44bb947f0565ec008a2e0927821c007e96d3a7/greenlet-3.3.2-cp310-cp310-manylinux_2_24_s390x.manylinux_2_28_s390x.whl\", hash = \"sha256:508c7f01f1791fbc8e011bd508f6794cb95397fdb198a46cb6635eb5b78d85a7\", size = 602132, upload-time = \"2026-02-20T21:02:43.261Z\" },\n { url = \"https://files.pythonhosted.org/packages/ad/55/9f1ebb5a825215fadcc0f7d5073f6e79e3007e3282b14b22d6aba7ca6cb8/greenlet-3.3.2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:ad0c8917dd42a819fe77e6bdfcb84e3379c0de956469301d9fd36427a1ca501f\", size = 591729, upload-time = \"2026-02-20T20:20:58.395Z\" },\n { url = \"https://files.pythonhosted.org/packages/24/b4/21f5455773d37f94b866eb3cf5caed88d6cea6dd2c6e1f9c34f463cba3ec/greenlet-3.3.2-cp310-cp310-musllinux_1_2_aarch64.whl\", hash = \"sha256:97245cc10e5515dbc8c3104b2928f7f02b6813002770cfaffaf9a6e0fc2b94ef\", size = 1551946, upload-time = \"2026-02-20T20:49:31.102Z\" },\n { url = \"https://files.pythonhosted.org/packages/00/68/91f061a926abead128fe1a87f0b453ccf07368666bd59ffa46016627a930/greenlet-3.3.2-cp310-cp310-musllinux_1_2_x86_64.whl\", hash = \"sha256:8c1fdd7d1b309ff0da81d60a9688a8bd044ac4e18b250320a96fc68d31c209ca\", size = 1618494, upload-time = \"2026-02-20T20:21:06.541Z\" },\n@@ -843,7 +836,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/f3/47/16400cb42d18d7a6bb46f0626852c1718612e35dcb0dffa16bbaffdf5dd2/greenlet-3.3.2-cp311-cp311-macosx_11_0_universal2.whl\", hash = \"sha256:c56692189a7d1c7606cb794be0a8381470d95c57ce5be03fb3d0ef57c7853b86\", size = 278890, upload-time = \"2026-02-20T20:19:39.263Z\" },\n { url = \"https://files.pythonhosted.org/packages/a3/90/42762b77a5b6aa96cd8c0e80612663d39211e8ae8a6cd47c7f1249a66262/greenlet-3.3.2-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl\", hash = \"sha256:1ebd458fa8285960f382841da585e02201b53a5ec2bac6b156fc623b5ce4499f\", size = 581120, upload-time = \"2026-02-20T20:47:30.161Z\" },\n { url = \"https://files.pythonhosted.org/packages/bf/6f/f3d64f4fa0a9c7b5c5b3c810ff1df614540d5aa7d519261b53fba55d4df9/greenlet-3.3.2-cp311-cp311-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl\", hash = \"sha256:a443358b33c4ec7b05b79a7c8b466f5d275025e750298be7340f8fc63dff2a55\", size = 594363, upload-time = \"2026-02-20T20:55:56.965Z\" },\n- { url = \"https://files.pythonhosted.org/packages/9c/8b/1430a04657735a3f23116c2e0d5eb10220928846e4537a938a41b350bed6/greenlet-3.3.2-cp311-cp311-manylinux_2_24_s390x.manylinux_2_28_s390x.whl\", hash = \"sha256:4375a58e49522698d3e70cc0b801c19433021b5c37686f7ce9c65b0d5c8677d2\", size = 605046, upload-time = \"2026-02-20T21:02:45.234Z\" },\n { url = \"https://files.pythonhosted.org/packages/72/83/3e06a52aca8128bdd4dcd67e932b809e76a96ab8c232a8b025b2850264c5/greenlet-3.3.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:8e2cd90d413acbf5e77ae41e5d3c9b3ac1d011a756d7284d7f3f2b806bbd6358\", size = 594156, upload-time = \"2026-02-20T20:20:59.955Z\" },\n { url = \"https://files.pythonhosted.org/packages/70/79/0de5e62b873e08fe3cef7dbe84e5c4bc0e8ed0c7ff131bccb8405cd107c8/greenlet-3.3.2-cp311-cp311-musllinux_1_2_aarch64.whl\", hash = \"sha256:442b6057453c8cb29b4fb36a2ac689382fc71112273726e2423f7f17dc73bf99\", size = 1554649, upload-time = \"2026-02-20T20:49:32.293Z\" },\n { url = \"https://files.pythonhosted.org/packages/5a/00/32d30dee8389dc36d42170a9c66217757289e2afb0de59a3565260f38373/greenlet-3.3.2-cp311-cp311-musllinux_1_2_x86_64.whl\", hash = \"sha256:45abe8eb6339518180d5a7fa47fa01945414d7cca5ecb745346fc6a87d2750be\", size = 1619472, upload-time = \"2026-02-20T20:21:07.966Z\" },\n@@ -852,7 +844,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/ea/ab/1608e5a7578e62113506740b88066bf09888322a311cff602105e619bd87/greenlet-3.3.2-cp312-cp312-macosx_11_0_universal2.whl\", hash = \"sha256:ac8d61d4343b799d1e526db579833d72f23759c71e07181c2d2944e429eb09cd\", size = 280358, upload-time = \"2026-02-20T20:17:43.971Z\" },\n { url = \"https://files.pythonhosted.org/packages/a5/23/0eae412a4ade4e6623ff7626e38998cb9b11e9ff1ebacaa021e4e108ec15/greenlet-3.3.2-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl\", hash = \"sha256:3ceec72030dae6ac0c8ed7591b96b70410a8be370b6a477b1dbc072856ad02bd\", size = 601217, upload-time = \"2026-02-20T20:47:31.462Z\" },\n { url = \"https://files.pythonhosted.org/packages/f8/16/5b1678a9c07098ecb9ab2dd159fafaf12e963293e61ee8d10ecb55273e5e/greenlet-3.3.2-cp312-cp312-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl\", hash = \"sha256:a2a5be83a45ce6188c045bcc44b0ee037d6a518978de9a5d97438548b953a1ac\", size = 611792, upload-time = \"2026-02-20T20:55:58.423Z\" },\n- { url = \"https://files.pythonhosted.org/packages/5c/c5/cc09412a29e43406eba18d61c70baa936e299bc27e074e2be3806ed29098/greenlet-3.3.2-cp312-cp312-manylinux_2_24_s390x.manylinux_2_28_s390x.whl\", hash = \"sha256:ae9e21c84035c490506c17002f5c8ab25f980205c3e61ddb3a2a2a2e6c411fcb\", size = 626250, upload-time = \"2026-02-20T21:02:46.596Z\" },\n { url = \"https://files.pythonhosted.org/packages/50/1f/5155f55bd71cabd03765a4aac9ac446be129895271f73872c36ebd4b04b6/greenlet-3.3.2-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:43e99d1749147ac21dde49b99c9abffcbc1e2d55c67501465ef0930d6e78e070\", size = 613875, upload-time = \"2026-02-20T20:21:01.102Z\" },\n { url = \"https://files.pythonhosted.org/packages/fc/dd/845f249c3fcd69e32df80cdab059b4be8b766ef5830a3d0aa9d6cad55beb/greenlet-3.3.2-cp312-cp312-musllinux_1_2_aarch64.whl\", hash = \"sha256:4c956a19350e2c37f2c48b336a3afb4bff120b36076d9d7fb68cb44e05d95b79\", size = 1571467, upload-time = \"2026-02-20T20:49:33.495Z\" },\n { url = \"https://files.pythonhosted.org/packages/2a/50/2649fe21fcc2b56659a452868e695634722a6655ba245d9f77f5656010bf/greenlet-3.3.2-cp312-cp312-musllinux_1_2_x86_64.whl\", hash = \"sha256:6c6f8ba97d17a1e7d664151284cb3315fc5f8353e75221ed4324f84eb162b395\", size = 1640001, upload-time = \"2026-02-20T20:21:09.154Z\" },\n@@ -861,7 +852,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/ac/48/f8b875fa7dea7dd9b33245e37f065af59df6a25af2f9561efa8d822fde51/greenlet-3.3.2-cp313-cp313-macosx_11_0_universal2.whl\", hash = \"sha256:aa6ac98bdfd716a749b84d4034486863fd81c3abde9aa3cf8eff9127981a4ae4\", size = 279120, upload-time = \"2026-02-20T20:19:01.9Z\" },\n { url = \"https://files.pythonhosted.org/packages/49/8d/9771d03e7a8b1ee456511961e1b97a6d77ae1dea4a34a5b98eee706689d3/greenlet-3.3.2-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl\", hash = \"sha256:ab0c7e7901a00bc0a7284907273dc165b32e0d109a6713babd04471327ff7986\", size = 603238, upload-time = \"2026-02-20T20:47:32.873Z\" },\n { url = \"https://files.pythonhosted.org/packages/59/0e/4223c2bbb63cd5c97f28ffb2a8aee71bdfb30b323c35d409450f51b91e3e/greenlet-3.3.2-cp313-cp313-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl\", hash = \"sha256:d248d8c23c67d2291ffd47af766e2a3aa9fa1c6703155c099feb11f526c63a92\", size = 614219, upload-time = \"2026-02-20T20:55:59.817Z\" },\n- { url = \"https://files.pythonhosted.org/packages/94/2b/4d012a69759ac9d77210b8bfb128bc621125f5b20fc398bce3940d036b1c/greenlet-3.3.2-cp313-cp313-manylinux_2_24_s390x.manylinux_2_28_s390x.whl\", hash = \"sha256:ccd21bb86944ca9be6d967cf7691e658e43417782bce90b5d2faeda0ff78a7dd\", size = 628268, upload-time = \"2026-02-20T21:02:48.024Z\" },\n { url = \"https://files.pythonhosted.org/packages/7a/34/259b28ea7a2a0c904b11cd36c79b8cef8019b26ee5dbe24e73b469dea347/greenlet-3.3.2-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:b6997d360a4e6a4e936c0f9625b1c20416b8a0ea18a8e19cabbefc712e7397ab\", size = 616774, upload-time = \"2026-02-20T20:21:02.454Z\" },\n { url = \"https://files.pythonhosted.org/packages/0a/03/996c2d1689d486a6e199cb0f1cf9e4aa940c500e01bdf201299d7d61fa69/greenlet-3.3.2-cp313-cp313-musllinux_1_2_aarch64.whl\", hash = \"sha256:64970c33a50551c7c50491671265d8954046cb6e8e2999aacdd60e439b70418a\", size = 1571277, upload-time = \"2026-02-20T20:49:34.795Z\" },\n { url = \"https://files.pythonhosted.org/packages/d9/c4/2570fc07f34a39f2caf0bf9f24b0a1a0a47bc2e8e465b2c2424821389dfc/greenlet-3.3.2-cp313-cp313-musllinux_1_2_x86_64.whl\", hash = \"sha256:1a9172f5bf6bd88e6ba5a84e0a68afeac9dc7b6b412b245dd64f52d83c81e55b\", size = 1640455, upload-time = \"2026-02-20T20:21:10.261Z\" },\n@@ -870,7 +860,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/3f/ae/8bffcbd373b57a5992cd077cbe8858fff39110480a9d50697091faea6f39/greenlet-3.3.2-cp314-cp314-macosx_11_0_universal2.whl\", hash = \"sha256:8d1658d7291f9859beed69a776c10822a0a799bc4bfe1bd4272bb60e62507dab\", size = 279650, upload-time = \"2026-02-20T20:18:00.783Z\" },\n { url = \"https://files.pythonhosted.org/packages/d1/c0/45f93f348fa49abf32ac8439938726c480bd96b2a3c6f4d949ec0124b69f/greenlet-3.3.2-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl\", hash = \"sha256:18cb1b7337bca281915b3c5d5ae19f4e76d35e1df80f4ad3c1a7be91fadf1082\", size = 650295, upload-time = \"2026-02-20T20:47:34.036Z\" },\n { url = \"https://files.pythonhosted.org/packages/b3/de/dd7589b3f2b8372069ab3e4763ea5329940fc7ad9dcd3e272a37516d7c9b/greenlet-3.3.2-cp314-cp314-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl\", hash = \"sha256:c2e47408e8ce1c6f1ceea0dffcdf6ebb85cc09e55c7af407c99f1112016e45e9\", size = 662163, upload-time = \"2026-02-20T20:56:01.295Z\" },\n- { url = \"https://files.pythonhosted.org/packages/cd/ac/85804f74f1ccea31ba518dcc8ee6f14c79f73fe36fa1beba38930806df09/greenlet-3.3.2-cp314-cp314-manylinux_2_24_s390x.manylinux_2_28_s390x.whl\", hash = \"sha256:e3cb43ce200f59483eb82949bf1835a99cf43d7571e900d7c8d5c62cdf25d2f9\", size = 675371, upload-time = \"2026-02-20T21:02:49.664Z\" },\n { url = \"https://files.pythonhosted.org/packages/d2/d8/09bfa816572a4d83bccd6750df1926f79158b1c36c5f73786e26dbe4ee38/greenlet-3.3.2-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:63d10328839d1973e5ba35e98cccbca71b232b14051fd957b6f8b6e8e80d0506\", size = 664160, upload-time = \"2026-02-20T20:21:04.015Z\" },\n { url = \"https://files.pythonhosted.org/packages/48/cf/56832f0c8255d27f6c35d41b5ec91168d74ec721d85f01a12131eec6b93c/greenlet-3.3.2-cp314-cp314-musllinux_1_2_aarch64.whl\", hash = \"sha256:8e4ab3cfb02993c8cc248ea73d7dae6cec0253e9afa311c9b37e603ca9fad2ce\", size = 1619181, upload-time = \"2026-02-20T20:49:36.052Z\" },\n { url = \"https://files.pythonhosted.org/packages/0a/23/b90b60a4aabb4cec0796e55f25ffbfb579a907c3898cd2905c8918acaa16/greenlet-3.3.2-cp314-cp314-musllinux_1_2_x86_64.whl\", hash = \"sha256:94ad81f0fd3c0c0681a018a976e5c2bd2ca2d9d94895f23e7bb1af4e8af4e2d5\", size = 1687713, upload-time = \"2026-02-20T20:21:11.684Z\" },\n@@ -879,7 +868,6 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/98/6d/8f2ef704e614bcf58ed43cfb8d87afa1c285e98194ab2cfad351bf04f81e/greenlet-3.3.2-cp314-cp314t-macosx_11_0_universal2.whl\", hash = \"sha256:e26e72bec7ab387ac80caa7496e0f908ff954f31065b0ffc1f8ecb1338b11b54\", size = 286617, upload-time = \"2026-02-20T20:19:29.856Z\" },\n { url = \"https://files.pythonhosted.org/packages/5e/0d/93894161d307c6ea237a43988f27eba0947b360b99ac5239ad3fe09f0b47/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl\", hash = \"sha256:8b466dff7a4ffda6ca975979bab80bdadde979e29fc947ac3be4451428d8b0e4\", size = 655189, upload-time = \"2026-02-20T20:47:35.742Z\" },\n { url = \"https://files.pythonhosted.org/packages/f5/2c/d2d506ebd8abcb57386ec4f7ba20f4030cbe56eae541bc6fd6ef399c0b41/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl\", hash = \"sha256:b8bddc5b73c9720bea487b3bffdb1840fe4e3656fba3bd40aa1489e9f37877ff\", size = 658225, upload-time = \"2026-02-20T20:56:02.527Z\" },\n- { url = \"https://files.pythonhosted.org/packages/d1/67/8197b7e7e602150938049d8e7f30de1660cfb87e4c8ee349b42b67bdb2e1/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_s390x.manylinux_2_28_s390x.whl\", hash = \"sha256:59b3e2c40f6706b05a9cd299c836c6aa2378cabe25d021acd80f13abf81181cf\", size = 666581, upload-time = \"2026-02-20T21:02:51.526Z\" },\n { url = \"https://files.pythonhosted.org/packages/8e/30/3a09155fbf728673a1dea713572d2d31159f824a37c22da82127056c44e4/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl\", hash = \"sha256:b26b0f4428b871a751968285a1ac9648944cea09807177ac639b030bddebcea4\", size = 657907, upload-time = \"2026-02-20T20:21:05.259Z\" },\n { url = \"https://files.pythonhosted.org/packages/f3/fd/d05a4b7acd0154ed758797f0a43b4c0962a843bedfe980115e842c5b2d08/greenlet-3.3.2-cp314-cp314t-musllinux_1_2_aarch64.whl\", hash = \"sha256:1fb39a11ee2e4d94be9a76671482be9398560955c9e568550de0224e41104727\", size = 1618857, upload-time = \"2026-02-20T20:49:37.309Z\" },\n { url = \"https://files.pythonhosted.org/packages/6f/e1/50ee92a5db521de8f35075b5eff060dd43d39ebd46c2181a2042f7070385/greenlet-3.3.2-cp314-cp314t-musllinux_1_2_x86_64.whl\", hash = \"sha256:20154044d9085151bc309e7689d6f7ba10027f8f5a8c0676ad398b951913d89e\", size = 1680010, upload-time = \"2026-02-20T20:21:13.427Z\" },\n@@ -1560,6 +1548,7 @@ dependencies = [\n { name = \"rank-bm25\" },\n { name = \"requests\" },\n { name = \"rich\" },\n+ { name = \"slack-bolt\" },\n { name = \"sqlalchemy\" },\n { name = \"strenum\" },\n { name = \"tomlkit\" },\n@@ -1625,6 +1614,7 @@ requires-dist = [\n { name = \"requests\", specifier = \">=2.31.0\" },\n { name = \"rich\", specifier = \">=13.0.0\" },\n { name = \"ruff\", marker = \"extra == 'dev'\", specifier = \">=0.8.0\" },\n+ { name = \"slack-bolt\", specifier = \">=1.20.0\" },\n { name = \"sqlalchemy\", specifier = \">=2.0.0\" },\n { name = \"strenum\", specifier = \">=0.4.0\" },\n { name = \"tomlkit\", specifier = \">=0.12.0\" },\n@@ -3157,6 +3147,27 @@ wheels = [\n { url = \"https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl\", hash = \"sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274\", size = 11050, upload-time = \"2024-12-04T17:35:26.475Z\" },\n ]\n \n+[[package]]\n+name = \"slack-bolt\"\n+version = \"1.27.0\"\n+source = { registry = \"https://pypi.org/simple\" }\n+dependencies = [\n+ { name = \"slack-sdk\" },\n+]\n+sdist = { url = \"https://files.pythonhosted.org/packages/4c/28/50ed0b86e48b48e6ddcc71de93b91c8ac14a55d1249e4bff0586494a2f90/slack_bolt-1.27.0.tar.gz\", hash = \"sha256:3db91d64e277e176a565c574ae82748aa8554f19e41a4fceadca4d65374ce1e0\", size = 129101, upload-time = \"2025-11-13T20:17:46.878Z\" }\n+wheels = [\n+ { url = \"https://files.pythonhosted.org/packages/01/a8/1acb355759747ba4da5f45c1a33d641994b9e04b914908c9434f18bd97e8/slack_bolt-1.27.0-py2.py3-none-any.whl\", hash = \"sha256:c43c94bf34740f2adeb9b55566c83f1e73fed6ba2878bd346cdfd6fd8ad22360\", size = 230428, upload-time = \"2025-11-13T20:17:45.465Z\" },\n+]\n+\n+[[package]]\n+name = \"slack-sdk\"\n+version = \"3.41.0\"\n+source = { registry = \"https://pypi.org/simple\" }\n+sdist = { url = \"https://files.pythonhosted.org/packages/22/35/fc009118a13187dd9731657c60138e5a7c2dea88681a7f04dc406af5da7d/slack_sdk-3.41.0.tar.gz\", hash = \"sha256:eb61eb12a65bebeca9cb5d36b3f799e836ed2be21b456d15df2627cfe34076ca\", size = 250568, upload-time = \"2026-03-12T16:10:11.381Z\" }\n+wheels = [\n+ { url = \"https://files.pythonhosted.org/packages/a1/df/2e4be347ff98281b505cc0ccf141408cdd25eb5ca9f3830deb361b2472d3/slack_sdk-3.41.0-py2.py3-none-any.whl\", hash = \"sha256:bb18dcdfff1413ec448e759cf807ec3324090993d8ab9111c74081623b692a89\", size = 313885, upload-time = \"2026-03-12T16:10:09.811Z\" },\n+]\n+\n [[package]]\n name = \"socksio\"\n version = \"1.0.0\"\n步骤 3: shell.git_log ✅\n5ffe3c7 refactor(index-maintenance): move to agent-scoped on-demand refresh\n8e5e166 refactor(agent-office): enforce user-first layout and strict default agent resolution\n9e0126e fix(workspace): canonicalize paths and align prompts with tool behavior", + "error": null, + "metadata": { + "plan": [ + { + "tool": "shell", + "method": "git_status", + "kwargs": {} + }, + { + "tool": "shell", + "method": "git_diff", + "kwargs": {} + }, + { + "tool": "shell", + "method": "git_log", + "kwargs": { + "n": 3 + } + } + ], + "results_count": 3 + } + }, + "error": null, + "timestamp": "2026-04-05T12:59:03.915408", + "id": "20260405_125903_915427" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125912_929508.json b/.claude/todo/outbox/rsp_20260405_125912_929508.json new file mode 100644 index 0000000..27f4ef0 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125912_929508.json @@ -0,0 +1,13 @@ +{ + "success": true, + "cmd_id": "20260405_125912_868623", + "data": { + "success": false, + "output": "", + "error": "未找到匹配内容: # Claudecode\n.claude/\n...", + "metadata": null + }, + "error": null, + "timestamp": "2026-04-05T12:59:12.929506", + "id": "20260405_125912_929508" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125928_044538.json b/.claude/todo/outbox/rsp_20260405_125928_044538.json new file mode 100644 index 0000000..9b49cec --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125928_044538.json @@ -0,0 +1,13 @@ +{ + "success": true, + "cmd_id": "20260405_125926_100277", + "data": { + "success": true, + "output": "# ========================================\n# Python 相关文件\n# ========================================\n__pycache__/\n*.py[cod]\n*$py.class\n*.so\n.Python\nprisma/models/\nprisma/data/\nprisma/data_test/\n\n# 构建和分发\nbuild/\ndevelop-eggs/\ndist/\ndownloads/\neggs/\n.eggs/\nlib/\nlib64/\nparts/\nsdist/\nvar/\nwheels/\n*.egg-info/\n.installed.cfg\n*.egg\n\n# ========================================\n# Node.js 相关文件\n# ========================================\nnode_modules/\npackage-lock.json\n\n# ========================================\n# 虚拟环境\n# ========================================\nvenv/\nenv/\nENV/\n.venv/\n\n# ========================================\n# IDE 和编辑器\n# ========================================\n.idea/\n.vscode/\n*.swp\n*.swo\n.DS_Store\n\n# Cursor\n.cursor/\n.cursorignore\n\n# Obsidian\n.obsidian/\n\n# ========================================\n# 测试和覆盖率\n# ========================================\n.pytest_cache/\n.coverage\nhtmlcov/\n.tox/\n.nox/\ntests/data/\ndata_test/\n\n# ========================================\n# 日志文件\n# ========================================\n*.log\nlogs/\n\n# ========================================\n# 配置和环境文件\n# ========================================\n.env\n.env.local\n.env.*.local\nconfigs/.env\nconfigs/app.json\nconfigs/app.test.json\n\n# ========================================\n# 数据库文件\n# ========================================\n*.db\n*.sqlite\n*.sqlite3\n/data/\n/data_test/\n/archives/\n\n# ========================================\n# MyAgent 统一存储目录（新框架）\n# ========================================\n# 开发环境数据（隐藏目录，防止误操作）\n.myagent/\n.myagent_test/\n# 但不忽略测试固件\n!.myagent_test/fixtures/\n# 生产环境在用户主目录，不在项目中\n# ~/.myagent/ (用户主目录，不在这里管理)\n\n# ========================================\n# 本地文件\n# ========================================\nlocal/\ntmp/\nconfigs/agent_prompts/.history/\n\n# ========================================\n# 临时文件和缓存\n# ========================================\n.cache/\n.mypy_cache/\n.dmypy.json\ndmypy.json\n\n# ========================================\n# 系统文件\n# ========================================\n.DS_Store\nThumbs.db\n", + "error": null, + "metadata": null + }, + "error": null, + "timestamp": "2026-04-05T12:59:28.044536", + "id": "20260405_125928_044538" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125931_053904.json b/.claude/todo/outbox/rsp_20260405_125931_053904.json new file mode 100644 index 0000000..60f2a36 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125931_053904.json @@ -0,0 +1,13 @@ +{ + "success": true, + "cmd_id": "20260405_125928_048340", + "data": { + "success": true, + "output": "写入成功: .gitignore", + "error": null, + "metadata": null + }, + "error": null, + "timestamp": "2026-04-05T12:59:31.053899", + "id": "20260405_125931_053904" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125943_072987.json b/.claude/todo/outbox/rsp_20260405_125943_072987.json new file mode 100644 index 0000000..cd05df9 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125943_072987.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_125943_026380", + "data": { + "task": { + "id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置", + "status": "done", + "priority": 1, + "tags": [ + "config" + ], + "created_at": "2026-04-05T12:53:43.787323", + "updated_at": "2026-04-05T12:59:43.072495", + "completed_at": "2026-04-05T12:59:43.072493", + "metadata": {} + }, + "message": "✅ 已完成: [825ed299] 优化 .gitignore 配置" + }, + "error": null, + "timestamp": "2026-04-05T12:59:43.072984", + "id": "20260405_125943_072987" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_125946_079936.json b/.claude/todo/outbox/rsp_20260405_125946_079936.json new file mode 100644 index 0000000..18b8f02 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_125946_079936.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_125943_135034", + "data": { + "task": { + "id": "56df56a2", + "title": "分步提交当前修改", + "description": "按逻辑分组逐步提交当前所有修改的文件", + "status": "done", + "priority": 1, + "tags": [ + "git" + ], + "created_at": "2026-04-05T12:53:43.789588", + "updated_at": "2026-04-05T12:59:46.079020", + "completed_at": "2026-04-05T12:59:46.079014", + "metadata": {} + }, + "message": "✅ 已完成: [56df56a2] 分步提交当前修改" + }, + "error": null, + "timestamp": "2026-04-05T12:59:46.079931", + "id": "20260405_125946_079936" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130505_791878.json b/.claude/todo/outbox/rsp_20260405_130505_791878.json new file mode 100644 index 0000000..c7fc0aa --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130505_791878.json @@ -0,0 +1,24 @@ +{ + "success": true, + "cmd_id": "20260405_130503_486633", + "data": { + "task": { + "id": "c589aa70", + "title": "新任务测试", + "description": "", + "status": "pending", + "priority": 2, + "tags": [ + "demo" + ], + "created_at": "2026-04-05T13:05:05.790728", + "updated_at": "2026-04-05T13:05:05.790732", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [c589aa70] 新任务测试" + }, + "error": null, + "timestamp": "2026-04-05T13:05:05.791875", + "id": "20260405_130505_791878" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130729_384474.json b/.claude/todo/outbox/rsp_20260405_130729_384474.json new file mode 100644 index 0000000..682cc4c --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130729_384474.json @@ -0,0 +1,8 @@ +{ + "success": false, + "cmd_id": "20260405_130644_974174", + "data": {}, + "error": "Task not found: fdac5557", + "timestamp": "2026-04-05T13:07:29.384471", + "id": "20260405_130729_384474" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130729_384891.json b/.claude/todo/outbox/rsp_20260405_130729_384891.json new file mode 100644 index 0000000..b6367fe --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130729_384891.json @@ -0,0 +1,8 @@ +{ + "success": false, + "cmd_id": "20260405_130644_974376", + "data": {}, + "error": "Task not found: dca41096", + "timestamp": "2026-04-05T13:07:29.384890", + "id": "20260405_130729_384891" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130729_385194.json b/.claude/todo/outbox/rsp_20260405_130729_385194.json new file mode 100644 index 0000000..414251f --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130729_385194.json @@ -0,0 +1,8 @@ +{ + "success": false, + "cmd_id": "20260405_130644_974500", + "data": {}, + "error": "Task not found: a738fbab", + "timestamp": "2026-04-05T13:07:29.385193", + "id": "20260405_130729_385194" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130729_385480.json b/.claude/todo/outbox/rsp_20260405_130729_385480.json new file mode 100644 index 0000000..6d491a8 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130729_385480.json @@ -0,0 +1,8 @@ +{ + "success": false, + "cmd_id": "20260405_130644_974613", + "data": {}, + "error": "Task not found: c589aa70", + "timestamp": "2026-04-05T13:07:29.385479", + "id": "20260405_130729_385480" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130729_386114.json b/.claude/todo/outbox/rsp_20260405_130729_386114.json new file mode 100644 index 0000000..8002c8d --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130729_386114.json @@ -0,0 +1,25 @@ +{ + "success": true, + "cmd_id": "20260405_130723_543950", + "data": { + "task": { + "id": "db4e360a", + "title": "审查 .gitignore 配置", + "description": "检查 .gitignore 是否完整，清理冗余规则", + "status": "pending", + "priority": 1, + "tags": [ + "config", + "review" + ], + "created_at": "2026-04-05T13:07:29.385774", + "updated_at": "2026-04-05T13:07:29.385775", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [db4e360a] 审查 .gitignore 配置" + }, + "error": null, + "timestamp": "2026-04-05T13:07:29.386112", + "id": "20260405_130729_386114" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_130729_386755.json b/.claude/todo/outbox/rsp_20260405_130729_386755.json new file mode 100644 index 0000000..e9579a1 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_130729_386755.json @@ -0,0 +1,25 @@ +{ + "success": true, + "cmd_id": "20260405_130723_544259", + "data": { + "task": { + "id": "91da4238", + "title": "完成 git 提交", + "description": "分步提交当前修改：先 configs，再 src，最后 tests", + "status": "pending", + "priority": 1, + "tags": [ + "git", + "commit" + ], + "created_at": "2026-04-05T13:07:29.386441", + "updated_at": "2026-04-05T13:07:29.386442", + "completed_at": null, + "metadata": {} + }, + "message": "✅ 已创建任务: [91da4238] 完成 git 提交" + }, + "error": null, + "timestamp": "2026-04-05T13:07:29.386754", + "id": "20260405_130729_386755" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_144717_728188.json b/.claude/todo/outbox/rsp_20260405_144717_728188.json new file mode 100644 index 0000000..0efb7df --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_144717_728188.json @@ -0,0 +1,25 @@ +{ + "success": true, + "cmd_id": "20260405_130747_317460", + "data": { + "task": { + "id": "db4e360a", + "title": "审查 .gitignore 配置", + "description": "检查 .gitignore 是否完整，清理冗余规则", + "status": "done", + "priority": 1, + "tags": [ + "config", + "review" + ], + "created_at": "2026-04-05T13:07:29.385774", + "updated_at": "2026-04-05T14:47:17.727792", + "completed_at": "2026-04-05T14:47:17.727790", + "metadata": {} + }, + "message": "✅ 已完成: [db4e360a] 审查 .gitignore 配置" + }, + "error": null, + "timestamp": "2026-04-05T14:47:17.728186", + "id": "20260405_144717_728188" +} \ No newline at end of file diff --git a/.claude/todo/outbox/rsp_20260405_144717_728600.json b/.claude/todo/outbox/rsp_20260405_144717_728600.json new file mode 100644 index 0000000..8efbcc6 --- /dev/null +++ b/.claude/todo/outbox/rsp_20260405_144717_728600.json @@ -0,0 +1,8 @@ +{ + "success": false, + "cmd_id": "20260405_144429_536707", + "data": {}, + "error": "Task not found: 28bfde69", + "timestamp": "2026-04-05T14:47:17.728599", + "id": "20260405_144717_728600" +} \ No newline at end of file diff --git a/.claude/todo/state/agent.log b/.claude/todo/state/agent.log new file mode 100644 index 0000000..583081b --- /dev/null +++ b/.claude/todo/state/agent.log @@ -0,0 +1,115 @@ +[2026-04-05T12:49:49.975832] 处理指令: add (id=20260405_124946_752279) +[2026-04-05T12:49:49.976453] 响应: success=True +[2026-04-05T12:49:49.976674] 处理指令: add (id=20260405_124946_752510) +[2026-04-05T12:49:49.977085] 响应: success=True +[2026-04-05T12:49:49.977220] 处理指令: add (id=20260405_124946_752659) +[2026-04-05T12:49:49.977561] 响应: success=True +[2026-04-05T12:50:15.276242] 处理指令: done (id=20260405_125001_887647) +[2026-04-05T12:50:15.276898] 响应: success=True +[2026-04-05T12:50:38.941171] 🚀 Todo Agent 启动 +[2026-04-05T12:50:38.941496] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T12:50:38.941555] 轮询间隔: 3.0s +[2026-04-05T12:51:18.018496] 处理指令: add (id=20260405_125115_736683) +[2026-04-05T12:51:18.021691] 响应: success=True +[2026-04-05T12:51:18.022221] 处理指令: add (id=20260405_125115_736891) +[2026-04-05T12:51:18.023246] 响应: success=True +[2026-04-05T12:51:18.023793] 本轮处理 2 个指令 +[2026-04-05T12:51:54.943395] 🚀 Todo Agent 启动 +[2026-04-05T12:51:54.943544] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T12:51:54.943595] 轮询间隔: 3.0s +[2026-04-05T12:51:54.943800] 处理指令: stop (id=20260405_125151_440893) +[2026-04-05T12:51:54.944051] 响应: success=True +[2026-04-05T12:51:54.944331] 本轮处理 1 个指令 +[2026-04-05T12:51:54.944386] 👋 Todo Agent 已停止 +[2026-04-05T12:52:01.842640] 🚀 Todo Agent 启动 +[2026-04-05T12:52:01.842829] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T12:52:01.843212] 轮询间隔: 3.0s +[2026-04-05T12:52:31.906624] 处理指令: add (id=20260405_125230_232997) +[2026-04-05T12:52:31.910318] 响应: success=True +[2026-04-05T12:52:31.911090] 本轮处理 1 个指令 +[2026-04-05T12:52:58.678381] 🚀 Todo Agent 启动 +[2026-04-05T12:52:58.678639] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T12:52:58.678684] 轮询间隔: 3.0s +[2026-04-05T12:53:43.786452] 处理指令: add (id=20260405_125342_933697) +[2026-04-05T12:53:43.788934] 响应: success=True +[2026-04-05T12:53:43.789471] 处理指令: add (id=20260405_125342_933972) +[2026-04-05T12:53:43.790479] 响应: success=True +[2026-04-05T12:53:43.791033] 本轮处理 2 个指令 +[2026-04-05T12:58:00.490130] 🚀 Todo Agent 启动 +[2026-04-05T12:58:00.490375] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T12:58:00.490430] 轮询间隔: 3.0s +[2026-04-05T12:58:12.516168] 处理指令: execute (id=20260405_125810_497416) +[2026-04-05T12:58:12.517837] 执行任务: code.analyze_gitignore +[2026-04-05T12:58:12.519742] 响应: success=True +[2026-04-05T12:58:12.520593] 本轮处理 1 个指令 +[2026-04-05T12:58:15.524009] 处理指令: get (id=20260405_125812_522150) +[2026-04-05T12:58:15.525127] 响应: success=True +[2026-04-05T12:58:15.525973] 本轮处理 1 个指令 +[2026-04-05T12:58:18.528651] 处理指令: execute (id=20260405_125815_602478) +[2026-04-05T12:58:18.529079] 执行任务: auto.interpret_and_execute +[2026-04-05T12:58:18.531189] 响应: success=True +[2026-04-05T12:58:18.531990] 本轮处理 1 个指令 +[2026-04-05T12:58:45.744319] 🚀 Todo Agent 启动 +[2026-04-05T12:58:45.744442] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T12:58:45.744495] 轮询间隔: 3.0s +[2026-04-05T12:58:48.748296] 处理指令: get (id=20260405_125847_739141) +[2026-04-05T12:58:48.749884] 响应: success=True +[2026-04-05T12:58:48.750643] 本轮处理 1 个指令 +[2026-04-05T12:58:51.754226] 处理指令: execute (id=20260405_125848_800418) +[2026-04-05T12:58:51.754638] 执行任务: auto.interpret_and_execute +[2026-04-05T12:58:51.757221] 响应: success=True +[2026-04-05T12:58:51.757921] 本轮处理 1 个指令 +[2026-04-05T12:59:00.772900] 处理指令: get (id=20260405_125858_011314) +[2026-04-05T12:59:00.773681] 响应: success=True +[2026-04-05T12:59:00.774194] 本轮处理 1 个指令 +[2026-04-05T12:59:03.779735] 处理指令: execute (id=20260405_125900_778492) +[2026-04-05T12:59:03.780060] 执行任务: auto.interpret_and_execute +[2026-04-05T12:59:03.916505] 响应: success=True +[2026-04-05T12:59:03.916825] 本轮处理 1 个指令 +[2026-04-05T12:59:12.928217] 处理指令: execute (id=20260405_125912_868623) +[2026-04-05T12:59:12.929354] 执行任务: file.edit +[2026-04-05T12:59:12.929783] 响应: success=True +[2026-04-05T12:59:12.930152] 本轮处理 1 个指令 +[2026-04-05T12:59:28.042636] 处理指令: execute (id=20260405_125926_100277) +[2026-04-05T12:59:28.044296] 执行任务: file.read +[2026-04-05T12:59:28.045015] 响应: success=True +[2026-04-05T12:59:28.045564] 本轮处理 1 个指令 +[2026-04-05T12:59:31.051742] 处理指令: execute (id=20260405_125928_048340) +[2026-04-05T12:59:31.052228] 执行任务: file.write +[2026-04-05T12:59:31.054434] 响应: success=True +[2026-04-05T12:59:31.055237] 本轮处理 1 个指令 +[2026-04-05T12:59:43.072302] 处理指令: done (id=20260405_125943_026380) +[2026-04-05T12:59:43.073247] 响应: success=True +[2026-04-05T12:59:43.073568] 本轮处理 1 个指令 +[2026-04-05T12:59:46.078545] 处理指令: done (id=20260405_125943_135034) +[2026-04-05T12:59:46.080467] 响应: success=True +[2026-04-05T12:59:46.081106] 本轮处理 1 个指令 +[2026-04-05T13:01:18.081910] 🚀 Todo Agent 启动 +[2026-04-05T13:01:18.082197] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T13:01:18.082246] 轮询间隔: 3.0s +[2026-04-05T13:04:45.759212] 🚀 Todo Agent 启动 +[2026-04-05T13:04:45.759428] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T13:04:45.759473] 轮询间隔: 5.0s +[2026-04-05T13:05:05.790194] 处理指令: add (id=20260405_130503_486633) +[2026-04-05T13:05:05.792372] 响应: success=True +[2026-04-05T13:05:05.793055] 本轮处理 1 个指令 +[2026-04-05T13:07:29.384188] 处理指令: delete (id=20260405_130644_974174) +[2026-04-05T13:07:29.384665] 响应: success=False +[2026-04-05T13:07:29.384849] 处理指令: delete (id=20260405_130644_974376) +[2026-04-05T13:07:29.385015] 响应: success=False +[2026-04-05T13:07:29.385155] 处理指令: delete (id=20260405_130644_974500) +[2026-04-05T13:07:29.385313] 响应: success=False +[2026-04-05T13:07:29.385441] 处理指令: delete (id=20260405_130644_974613) +[2026-04-05T13:07:29.385591] 响应: success=False +[2026-04-05T13:07:29.385717] 处理指令: add (id=20260405_130723_543950) +[2026-04-05T13:07:29.386258] 响应: success=True +[2026-04-05T13:07:29.386391] 处理指令: add (id=20260405_130723_544259) +[2026-04-05T13:07:29.386946] 响应: success=True +[2026-04-05T14:47:17.726812] 🚀 Todo Agent 启动 +[2026-04-05T14:47:17.727112] 工作目录: /Users/lzhshou/Documents/myResearch/myProjects/apaam/repo/myagent/.claude/todo +[2026-04-05T14:47:17.727160] 轮询间隔: 5.0s +[2026-04-05T14:47:17.727725] 处理指令: done (id=20260405_130747_317460) +[2026-04-05T14:47:17.728373] 响应: success=True +[2026-04-05T14:47:17.728553] 处理指令: delete (id=20260405_144429_536707) +[2026-04-05T14:47:17.728724] 响应: success=False +[2026-04-05T14:47:17.729075] 本轮处理 2 个指令 diff --git a/.claude/todo/state/heartbeat.json b/.claude/todo/state/heartbeat.json new file mode 100644 index 0000000..ac50af0 --- /dev/null +++ b/.claude/todo/state/heartbeat.json @@ -0,0 +1,5 @@ +{ + "last_beat": "2026-04-05T21:26:54.625267", + "status": "running", + "task_count": 6 +} \ No newline at end of file diff --git a/.claude/todo/state/tasks.json b/.claude/todo/state/tasks.json new file mode 100644 index 0000000..34cbcbb --- /dev/null +++ b/.claude/todo/state/tasks.json @@ -0,0 +1,91 @@ +{ + "updated_at": "2026-04-05T14:47:17.727804", + "tasks": [ + { + "id": "fe36a678", + "title": "重构代码", + "description": "清理冗余代码", + "status": "done", + "priority": 1, + "tags": [ + "refactor" + ], + "created_at": "2026-04-05T12:49:49.976095", + "updated_at": "2026-04-05T12:50:15.276411", + "completed_at": "2026-04-05T12:50:15.276409", + "metadata": {} + }, + { + "id": "56a67bbf", + "title": "编写测试", + "description": "", + "status": "pending", + "priority": 2, + "tags": [ + "test" + ], + "created_at": "2026-04-05T12:49:49.976724", + "updated_at": "2026-04-05T12:49:49.976725", + "completed_at": null, + "metadata": {} + }, + { + "id": "825ed299", + "title": "优化 .gitignore 配置", + "description": "清理不必要的忽略规则，添加项目特定配置", + "status": "done", + "priority": 1, + "tags": [ + "config" + ], + "created_at": "2026-04-05T12:53:43.787323", + "updated_at": "2026-04-05T12:59:43.072495", + "completed_at": "2026-04-05T12:59:43.072493", + "metadata": {} + }, + { + "id": "56df56a2", + "title": "分步提交当前修改", + "description": "按逻辑分组逐步提交当前所有修改的文件", + "status": "done", + "priority": 1, + "tags": [ + "git" + ], + "created_at": "2026-04-05T12:53:43.789588", + "updated_at": "2026-04-05T12:59:46.079020", + "completed_at": "2026-04-05T12:59:46.079014", + "metadata": {} + }, + { + "id": "db4e360a", + "title": "审查 .gitignore 配置", + "description": "检查 .gitignore 是否完整，清理冗余规则", + "status": "done", + "priority": 1, + "tags": [ + "config", + "review" + ], + "created_at": "2026-04-05T13:07:29.385774", + "updated_at": "2026-04-05T14:47:17.727792", + "completed_at": "2026-04-05T14:47:17.727790", + "metadata": {} + }, + { + "id": "91da4238", + "title": "完成 git 提交", + "description": "分步提交当前修改：先 configs，再 src，最后 tests", + "status": "pending", + "priority": 1, + "tags": [ + "git", + "commit" + ], + "created_at": "2026-04-05T13:07:29.386441", + "updated_at": "2026-04-05T13:07:29.386442", + "completed_at": null, + "metadata": {} + } + ] +} \ No newline at end of file diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..78cf336 --- /dev/null +++ b/.gitignore @@ -0,0 +1,7 @@ +.venv/ +__pycache__/ +*.py[cod] +*.egg-info/ +dist/ +build/ +workspace/ diff --git a/CLAUDE.md b/CLAUDE.md new file mode 100644 index 0000000..ce1f5a3 --- /dev/null +++ b/CLAUDE.md @@ -0,0 +1,110 @@ +# Claude 个人助理配置 + +你是 Claude，用户的个人助理，协助日常办公和软件研发工作。 + +--- + +## 1. 用户画像 + +- **姓名**: 赖正首 +- **称呼**: 老大 +- **身份**: 中山大学土木工程学院副教授 +- **专精领域**: Python, AI/ML, 系统架构, 计算力学 +- **经验水平**: 高级 + +### 沟通偏好 +- **风格**: 简洁直接，不说废话 +- **代码**: PEP8 + Black，需要类型注解 +- **解释**: 关键部分详细，熟悉内容简洁 +- **测试**: 高度重视 + +### 技术栈 +- **主语言**: Python +- **包管理**: uv +- **架构**: Clean Architecture + +--- + +## 2. 工作模式 + +切换命令: "切换到专家模式" / "用导师的方式" / "执行这个任务" + +| 模式 | 特点 | 适用场景 | +|------|------|----------| +| **协作者** (默认) | 平等对话，共同探索 | 需求讨论、架构设计 | +| **专家** | 直接给最佳实践，减少解释 | 技术实现、代码审查 | +| **导师** | 引导思考，多问少答 | 学习、概念理解 | +| **执行者** | 最小化交互，快速执行 | 明确任务、批量操作 | + +--- + +## 3. Workspace 结构 + +``` +workspace/ +├── myWorks/ # 工作项目 +│ ├── 1_papers/ # 论文相关 +│ ├── 2_projects/ # 项目代码 +│ └── shared/ # 交互区（临时文件交换） +│ ├── tmp_notes/ # 临时笔记、截图 +│ └── tmp_workspace/ # 临时工作文件 +├── archives/ # 归档资料 +├── references/ # 参考资料 +└── templates/ # 常用模板 +``` + +**交互区使用**: 用户放置文件到 `shared/`，Claude 读取处理后可放回。 + +--- + +## 4. 编程规范 + +### 代码风格 +- Python: Black (80字符), Ruff, MyPy +- 有意义的命名 > 注释解释命名 + +### 编码原则 +1. **单一职责**: 每个函数/类只做一件事 +2. **类型注解**: 使用类型提示 +3. **错误处理**: 显式处理边界情况 +4. **测试友好**: 便于单元测试的代码结构 + +### 代码审查清单 +- [ ] 是否有类型注解？ +- [ ] 错误处理是否完善？ +- [ ] 命名是否清晰？ +- [ ] 是否有过度工程？ + +--- + +## 5. 记忆协议 + +### 自动记忆位置 +- `/memory/` - 持久化记忆（自动加载到上下文） +- `/memory/MEMORY.md` - 核心记忆文件 + +### 触发记录 +- 用户说"记住..." / "记下来..." +- 用户纠正行为或偏好 +- 发现重要的项目信息 + +--- + +## 6. 沟通风格 + +- **简洁**: 不说废话 +- **透明**: 复杂任务同步进度 +- **主动**: 发现问题时提醒，识别更好方法时建议 + +### 回复结构 +1. **快速总结** (1-2句): 确认理解 +2. **核心回答**: 直接给答案或结果 +3. **后续建议** (可选): 相关建议 + +--- + +## 7. 指令优先级 + +1. **明确指令** > 默认规则 +2. **当前对话上下文** > 历史记忆 +3. **本文件 (CLAUDE.md)** > 全局设置 diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..de06678 --- /dev/null +++ b/Makefile @@ -0,0 +1,15 @@ +ROOT_DIR := $(shell pwd) + +.PHONY: help install + +help: + @echo "Usage: make [target]" + @echo "" + @echo " install Editable pip install of mybot (uses uv when available)" + +install: + @if command -v uv >/dev/null 2>&1; then \ + uv pip install -e "$(ROOT_DIR)"; \ + else \ + python3 -m pip install -e "$(ROOT_DIR)"; \ + fi diff --git a/mybot/__init__.py b/mybot/__init__.py new file mode 100644 index 0000000..4e3c77f --- /dev/null +++ b/mybot/__init__.py @@ -0,0 +1 @@ +"""Mybot CLI package.""" diff --git a/mybot/__main__.py b/mybot/__main__.py new file mode 100644 index 0000000..5e500e1 --- /dev/null +++ b/mybot/__main__.py @@ -0,0 +1,3 @@ +from mybot.cli import main + +main() diff --git a/mybot/cli.py b/mybot/cli.py new file mode 100644 index 0000000..eb821bb --- /dev/null +++ b/mybot/cli.py @@ -0,0 +1,32 @@ +"""Mybot CLI entrypoint.""" + +from importlib.metadata import PackageNotFoundError, version + +import click + +from mybot.commands import chat_cmd, update_cmd + + +def _package_version() -> str: + try: + return version("mybot") + except PackageNotFoundError: + return "0.0.0" + + +@click.group() +@click.version_option(version=_package_version()) +def cli() -> None: + """Mybot: CLI (update package, chat = Claude Code in this repo).""" + + +cli.add_command(update_cmd) +cli.add_command(chat_cmd) + + +def main() -> None: + cli() + + +if __name__ == "__main__": + main() diff --git a/mybot/commands/__init__.py b/mybot/commands/__init__.py new file mode 100644 index 0000000..1aff968 --- /dev/null +++ b/mybot/commands/__init__.py @@ -0,0 +1,6 @@ +"""CLI subcommands.""" + +from .chat import chat_cmd +from .update import update_cmd + +__all__ = ["chat_cmd", "update_cmd"] diff --git a/mybot/commands/chat.py b/mybot/commands/chat.py new file mode 100644 index 0000000..621618f --- /dev/null +++ b/mybot/commands/chat.py @@ -0,0 +1,62 @@ +"""Start Claude Code in the mybot project directory.""" + +import os +import shutil +import subprocess +import sys +from pathlib import Path + +import click +from rich.console import Console + +from mybot.project_root import get_mybot_project_root + +console = Console() + + +def _resolve_chat_cwd() -> Path: + root = get_mybot_project_root() + fallback = Path.home() / ".mybot" + if root == fallback: + console.print( + "[red]Cannot resolve mybot project root.[/red] Run from the repo or set " + "[cyan]MYBOT_PROJECT_ROOT[/cyan].", + file=sys.stderr, + ) + raise SystemExit(1) + return root + + +@click.command( + "chat", + context_settings={ + "ignore_unknown_options": True, + "allow_extra_args": True, + }, +) +@click.option( + "--dangerously-skip-permissions", + is_flag=True, + default=False, + help="Forward to claude: bypass permission checks (sandbox / isolated use only).", +) +@click.pass_context +def chat_cmd(ctx: click.Context, dangerously_skip_permissions: bool) -> None: + """Run `claude` in the mybot repo so CLAUDE.md and .claude/ apply; extra args pass through.""" + binary = os.environ.get("CLAUDE_BIN") or shutil.which("claude") + if not binary: + console.print( + "[red]claude CLI not found in PATH.[/red] Install Claude Code or set " + "[cyan]CLAUDE_BIN[/cyan].", + file=sys.stderr, + ) + raise SystemExit(127) + + cwd = _resolve_chat_cwd() + cmd: list[str] = [binary] + if dangerously_skip_permissions: + cmd.append("--dangerously-skip-permissions") + cmd.extend(ctx.args) + + proc = subprocess.run(cmd, cwd=str(cwd), check=False) + raise SystemExit(proc.returncode) diff --git a/mybot/commands/update.py b/mybot/commands/update.py new file mode 100644 index 0000000..42d46a3 --- /dev/null +++ b/mybot/commands/update.py @@ -0,0 +1,54 @@ +"""Reinstall mybot from the local repo.""" + +import subprocess +import sys +from pathlib import Path + +import click +from rich.console import Console + +from mybot.project_root import get_mybot_project_root + +console = Console() + + +def _run_make_install(root: Path) -> int: + return subprocess.run( + ["make", "install"], + cwd=str(root), + check=False, + ).returncode + + +def _run_pip_editable(root: Path) -> int: + cmd = [sys.executable, "-m", "pip", "install", "-e", str(root)] + return subprocess.run(cmd, cwd=str(root), check=False).returncode + + +@click.command("update") +def update_cmd() -> None: + """Reinstall mybot from this repository (make install, or pip install -e).""" + root = get_mybot_project_root() + fallback = Path.home() / ".mybot" + if root == fallback: + console.print( + "[red]Not inside mybot repo.[/red] Set [cyan]MYBOT_PROJECT_ROOT[/cyan] " + "or run from the clone.", + file=sys.stderr, + ) + raise SystemExit(1) + + console.print("[bold cyan]Updating mybot…[/bold cyan]") + makefile = root / "Makefile" + if makefile.is_file(): + rc = _run_make_install(root) + if rc != 0: + console.print("[yellow]make install failed, trying pip -e…[/yellow]") + rc = _run_pip_editable(root) + else: + rc = _run_pip_editable(root) + + if rc != 0: + console.print("[red]Update failed.[/red]", file=sys.stderr) + raise SystemExit(rc) + console.print("[green]mybot updated.[/green]") diff --git a/mybot/project_root.py b/mybot/project_root.py new file mode 100644 index 0000000..e5a07a5 --- /dev/null +++ b/mybot/project_root.py @@ -0,0 +1,56 @@ +"""Resolve mybot repository root for make / editable install flows.""" + +import os +from pathlib import Path + + +def _pyproject_names_mybot(path: Path) -> bool: + try: + text = path.read_text(encoding="utf-8", errors="ignore") + except OSError: + return False + return 'name = "mybot"' in text or "name = 'mybot'" in text + + +def _walk_up_for_pyproject(start: Path) -> Path | None: + p = start.resolve() + for _ in range(16): + candidate = p / "pyproject.toml" + if candidate.is_file() and _pyproject_names_mybot(candidate): + return p + parent = p.parent + if parent == p: + break + p = parent + return None + + +def get_mybot_project_root() -> Path: + """ + Root of the mybot repo (contains Makefile + pyproject). + + Order: MYBOT_PROJECT_ROOT > walk from cwd > package source tree > ~/.mybot + """ + env_root = os.environ.get("MYBOT_PROJECT_ROOT") + if env_root: + return Path(env_root).resolve() + + try: + cwd = Path.cwd() + except (OSError, PermissionError): + cwd = None + if cwd is not None: + found = _walk_up_for_pyproject(cwd) + if found is not None: + return found + + here = Path(__file__).resolve().parent + for _ in range(8): + pyproject = here / "pyproject.toml" + if pyproject.is_file() and _pyproject_names_mybot(pyproject): + return here + if here.parent == here: + break + here = here.parent + + return Path.home() / ".mybot" diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..37a1b9f --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,31 @@ +[project] +name = "mybot" +version = "0.1.0" +description = "Mybot CLI: package update and Claude Code launcher for this repo" +requires-python = ">=3.10" +dependencies = [ + "click>=8.0.0", + "rich>=13.0.0", +] + +[project.scripts] +mybot = "mybot.cli:cli" + +[build-system] +requires = ["hatchling"] +build-backend = "hatchling.build" + +[tool.hatch.build.targets.wheel] +packages = ["mybot"] + +[tool.black] +line-length = 80 +target-version = ["py310"] + +[tool.ruff] +line-length = 80 +target-version = "py310" + +[tool.ruff.lint] +select = ["E", "F", "I", "UP", "B", "SIM", "W"] +ignore = ["E501"]