Yaojia Wang
b8654aa31f
feat: upgrade LangGraph to 1.x and migrate deprecated APIs
...
- Bump langgraph from 0.4 to 1.0+, langgraph-supervisor from 0.0.12 to 0.0.30+
- Bump langchain-core, langchain-anthropic, langchain-openai to 1.x
- Add langchain>=1.0 dependency for new create_agent location
- Migrate create_react_agent -> create_agent (prompt -> system_prompt)
- Fix create_supervisor positional arg to named agents= parameter
- Replace AsyncMock checkpointer with InMemorySaver in tests (v1 type validation)
- Update version references in README, ARCHITECTURE, eng-review-plan
2026-04-06 14:51:51 +02:00
Yaojia Wang
1050df780d
feat: complete phase 2 -- multi-agent routing, interrupt TTL, escalation, templates
...
- Intent classification with LLM structured output (single/multi/ambiguous)
- Discount agent with apply_discount and generate_coupon tools
- Interrupt manager with 30-min TTL auto-expiration and retry prompts
- Webhook escalation module with exponential backoff retry (max 3)
- Three vertical industry templates (e-commerce, SaaS, fintech)
- Template loading in AgentRegistry
- Enhanced supervisor prompt with dynamic agent descriptions
- 153 tests passing, 90.18% coverage
2026-03-30 21:04:39 +02:00
Yaojia Wang
33488fd634
feat: complete phase 1 -- core framework with chat loop, agents, and React UI
...
Backend:
- FastAPI WebSocket /ws endpoint with streaming via LangGraph astream
- LangGraph Supervisor connecting 3 mock agents (order_lookup, order_actions, fallback)
- YAML Agent Registry with Pydantic validation and immutable configs
- PostgresSaver checkpoint persistence via langgraph-checkpoint-postgres
- Session TTL with 30-min sliding window and interrupt extension
- LLM provider abstraction (Anthropic/OpenAI/Google)
- Token usage + cost tracking callback handler
- Input validation: message size cap, thread_id format, content length
- Security: no hardcoded defaults, startup API key validation, no input reflection
Frontend:
- React 19 + TypeScript + Vite chat UI
- WebSocket hook with reconnect + exponential backoff
- Streaming token display with agent attribution
- Interrupt approval/reject UI for write operations
- Collapsible tool call viewer
Testing:
- 87 unit tests, 87% coverage (exceeds 80% requirement)
- Ruff lint + format clean
Infrastructure:
- Docker Compose (PostgreSQL 16 + backend)
- pyproject.toml with full dependency management
2026-03-30 00:54:21 +02:00
