Sync

2 - Projects/Smart Support.md

@@ -44,7 +44,7 @@ AI 客服行动层框架。粘贴你的 API，获得一个能执行真实操作
 
 | 阶段 | 周期 | 内容 | 状态 | 详情 |
 |------|------|------|------|------|
-| Phase 1 | 第 1-3 周 | 核心框架 | 未开始 | [[Smart Support/Phase 1 - 核心框架]] |
+| Phase 1 | 第 1-3 周 | 核心框架 | COMPLETED (2026-03-30) | [[Smart Support/Phase 1 - 核心框架]] |
 | Phase 2 | 第 3-4 周 | 多 Agent + 安全 | 未开始 | [[Smart Support/Phase 2 - 多 Agent + 安全]] |
 | Phase 3 | 第 4-6 周 | OpenAPI 自动发现 | 未开始 | [[Smart Support/Phase 3 - OpenAPI 自动发现]] |
 | Phase 4 | 第 6-7 周 | 分析 + 回放 | 未开始 | [[Smart Support/Phase 4 - 分析 + 回放]] |
@@ -60,6 +60,12 @@ AI 客服行动层框架。粘贴你的 API，获得一个能执行真实操作
 - 分支：`main`
 - 本地路径：`/Users/yiukai/Documents/git/smart-support`
 
+## 完整文档（已同步）
+
+- [[Smart Support/Architecture]] - 系统架构文档（12 章，含 ADR、数据库设计、API 协议）
+- [[Smart Support/Development Plan]] - 详细开发计划（6 Phase，任务清单 + 检查点 + 风险）
+- [[Smart Support/Phase 1 Dev Log]] - Phase 1 开发日志（88% 覆盖率，82 个单元测试）
+
 ## 计划文档
 
 项目根目录下：

2 - Projects/Smart Support/Phase 1 Dev Log.md

@@ -0,0 +1,95 @@
+---
+created: "2026-03-30"
+type: log
+project: "[[Smart Support]]"
+source: "docs/phases/phase-1-dev-log.md"
+---
+
+# Phase 1: Core Framework -- Development Log
+
+> Status: COMPLETED
+> Phase branch: `phase-1/core-framework`
+> Date started: 2026-03-30
+> Date completed: 2026-03-30
+> Related plan section: [Phase 1 in DEVELOPMENT-PLAN](../DEVELOPMENT-PLAN.md#phase-1-核心框架-第-1-3-周)
+
+## What Was Built
+
+- FastAPI WebSocket backend with `/ws` endpoint for real-time chat
+- LangGraph Supervisor (via `langgraph-supervisor`) connecting 3 agents
+- YAML-based Agent Registry with Pydantic validation
+- 3 Mock Agents: order_lookup (read), order_actions (write + interrupt), fallback
+- PostgresSaver checkpoint persistence via `langgraph-checkpoint-postgres`
+- Session TTL management with 30-minute sliding window and interrupt extension
+- LLM provider abstraction (Anthropic/OpenAI/Google) with prompt caching support
+- Token usage tracking callback handler
+- React Chat UI with streaming display, interrupt confirmation, and agent action viewer
+- Docker Compose configuration (PostgreSQL 16 + backend)
+
+## Code Structure
+
+### New files
+
+Backend (`backend/app/`):
+- `config.py` -- pydantic-settings centralized configuration
+- `db.py` -- Async PostgreSQL pool + AsyncPostgresSaver setup
+- `llm.py` -- LLM provider factory (ChatAnthropic/ChatOpenAI/ChatGoogleGenerativeAI)
+- `callbacks.py` -- Token usage + cost tracking callback handler
+- `registry.py` -- YAML agent registry with validation + immutable config models
+- `session_manager.py` -- Session TTL with sliding window + interrupt extension
+- `graph.py` -- LangGraph Supervisor construction from registry
+- `ws_handler.py` -- WebSocket message dispatch + streaming logic
+- `main.py` -- FastAPI app entry with lifespan + WebSocket endpoint
+- `agents/__init__.py` -- Tool name-to-function bridge
+- `agents/order_lookup.py` -- Mock order status/tracking tools
+- `agents/order_actions.py` -- Mock cancel_order with interrupt()
+- `agents/fallback.py` -- Fallback response tool
+
+Frontend (`frontend/src/`):
+- `types.ts` -- WebSocket message protocol TypeScript types
+- `hooks/useWebSocket.ts` -- WebSocket connection + reconnect + message dispatch
+- `components/ChatMessages.tsx` -- Streaming message display
+- `components/ChatInput.tsx` -- Message input
+- `components/InterruptPrompt.tsx` -- Approve/reject interrupt UI
+- `components/AgentAction.tsx` -- Tool call inline display
+- `pages/ChatPage.tsx` -- Main chat page composing all components
+
+Infrastructure:
+- `backend/pyproject.toml` -- Dependencies + pytest + ruff config
+- `backend/agents.yaml` -- Agent registry YAML config
+- `backend/Dockerfile` -- Backend container
+- `docker-compose.yml` -- PostgreSQL 16 + backend services
+- `.gitignore` -- Updated for Python + Node artifacts
+
+Tests (`backend/tests/unit/`):
+- `test_config.py` -- Settings validation tests
+- `test_registry.py` -- 17 tests for registry loading/validation
+- `test_agents.py` -- 10 tests for tool functions + tool bridge
+- `test_llm.py` -- 3 tests for LLM provider factory
+- `test_callbacks.py` -- 9 tests for token usage tracking
+- `test_session_manager.py` -- 9 tests for session TTL logic
+- `test_graph.py` -- 4 tests for supervisor construction
+- `test_db.py` -- 5 tests for database setup
+- `test_ws_handler.py` -- 12 tests for WebSocket message handling
+- `test_main.py` -- 5 tests for app configuration
+
+## Test Coverage
+
+- Unit test count: 82
+- Integration test count: 0 (requires running PostgreSQL)
+- E2E test count: 0 (manual verification in plan)
+- Overall coverage: 88%
+
+## Deviations from Plan
+
+- Used `astream(stream_mode="messages")` instead of `astream_events()` per langgraph best practices
+- Separated WebSocket handler logic into `ws_handler.py` for testability (not in original plan)
+- Session manager uses in-memory storage instead of DB-backed (sufficient for Phase 1 single-instance)
+
+## Known Issues / Tech Debt
+
+- Session manager not DB-backed (loses state on restart) -- acceptable for Phase 1 single-instance
+- WebSocket reconnect does not re-send pending interrupt state from server
+- No rate limiting on WebSocket endpoint (Phase 2)
+- No authentication (Phase 2)
+- `main.py` coverage at 47% -- lifespan function not unit-testable without full DB

4 - Resources/Claude-Code/Everything Claude Code 方法论与最佳实践.md

@@ -65,12 +65,12 @@ npm search jwt verify
 
 **四种预设工作流**:
 
-| 工作流 | Agent 链 |
+| 工作流      | Agent 链                                                 |
-|--------|---------|
+| -------- | ------------------------------------------------------- |
-| feature | planner → tdd-guide → code-reviewer → security-reviewer |
+| feature  | planner → tdd-guide → code-reviewer → security-reviewer |
-| bugfix | planner → tdd-guide → code-reviewer |
+| bugfix   | planner → tdd-guide → code-reviewer                     |
-| refactor | architect → code-reviewer → tdd-guide |
+| refactor | architect → code-reviewer → tdd-guide                   |
-| security | security-reviewer → code-reviewer → architect |
+| security | security-reviewer → code-reviewer → architect           |
 
 **自定义链**: `/orchestrate custom "architect,tdd-guide,code-reviewer" "Redesign caching layer"`
 
@@ -122,13 +122,13 @@ npm search jwt verify
 
 **核心洞察**: Hook 触发率 100%（确定性），Skill/提示词触发率仅 50-80%（概率性）。因此关键质量控制应通过 Hook 实现，而非依赖提示词。
 
-| Hook 类型 | 触发时机 | 用途举例 |
+| Hook 类型      | 触发时机   | 用途举例              |
-|-----------|---------|---------|
+| ------------ | ------ | ----------------- |
-| PreToolUse | 工具执行前 | 开发服务器自启、安全监控 |
+| PreToolUse   | 工具执行前  | 开发服务器自启、安全监控      |
-| PostToolUse | 工具执行后 | 自动格式化、类型检查 |
+| PostToolUse  | 工具执行后  | 自动格式化、类型检查        |
-| PreCompact | 上下文压缩前 | 保存会话状态到 MEMORY.md |
+| PreCompact   | 上下文压缩前 | 保存会话状态到 MEMORY.md |
-| SessionStart | 新会话开始 | 加载上次上下文、检测包管理器 |
+| SessionStart | 新会话开始  | 加载上次上下文、检测包管理器    |
-| Stop | 每次响应后 | 检查 debug 语句、持久化指标 |
+| Stop         | 每次响应后  | 检查 debug 语句、持久化指标 |
 
 **例子 — hooks.json 配置**:
 

4 - Resources/Networking/OpenClash-Configuration.md

@@ -13,8 +13,8 @@ tags:
 # OpenClash 配置备份
 
 > 路由器：`192.168.68.63` (iStoreOS, EasePi Pro)
-> 最后更新：2026-03-19
+> 最后更新：2026-03-29
-> 用途：仅国内视频/音乐走代理回国，其余全部直连
+> 用途：仅国内视频/音乐走代理回国，其余全部直连（小红书已改为直连）
 
 ---