kai/smart-support
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
b8654aa31f66e74ba8093bd9d918548a8fa2cf1e
smart-support/TODOS.md
Yaojia Wang f93e8baef1 feat: initial project setup with planning docs 
Smart Support - AI customer service action layer framework.
Includes design doc, CEO plan, eng review, test plan, and README.
2026-03-29 21:11:36 +02:00

2.4 KiB
Raw Blame History

TODOS

Before Phase 3

  • Tool interface decision: The tool layer should support multiple backends, not just MCP:
    1. MCP tools — for complex, stateful interactions via MCP protocol (stdio/SSE)
    2. CLI tools — wrap existing CLIs (Shopify CLI, AWS CLI, Stripe CLI, etc.). Parse stdout/stderr.
    3. Direct API tools — simple REST/GraphQL HTTP calls, no MCP overhead. LangChain tools are just Python functions with descriptions — the backend is an implementation detail. Research MCP Python SDK (mcp on PyPI) for the MCP path. Design the tool base class to abstract over all three backends. ~2-3 hours research. Flagged by eng review outside voice + user feedback.

Before Production Deployment (P1)

  • Auth system: API key auth for chat WebSocket, session-based auth for dashboard/replay/import. Rate limiting on all endpoints. Blocks any real client deployment. Effort: M (CC: ~2 days). Depends on: Phase 4 completion.

Before Phase 4 (Client Engagement)

  • Checkpointer migration plan: InMemorySaver → PostgresSaver (or SQLiteSaver as intermediate). InMemorySaver loses all state on restart/crash. PostgresSaver requires schema, connection pooling, serialization compatibility. Not a simple config swap. Plan the migration before any real client deployment.

Design Changes from Eng Review

  • Use LangGraph built-ins: Checkpointers for session state, interrupt() for human-in-the-loop, supervisor pattern for multi-agent routing. Don't rebuild what LangGraph provides.
  • WebSocket for streaming: Bidirectional connection for streaming tokens + interrupt flow.
  • Supervisor pattern: Despite latency concern (8-15s per response), founder chose multi-agent supervisor over single-agent. Stream all tokens to mitigate perceived wait.
  • YAML agent registry: Declarative agent definitions for client configurability.
  • Prompt caching: Enabled from day one to reduce LLM costs.
  • Multi-LLM provider support: Use LangChain's provider abstractions (ChatAnthropic, ChatOpenAI, ChatGoogleGenerativeAI). Provider configurable per deployment.
  • Multi-backend tool support: Tool layer supports MCP servers, CLI wrappers, and direct API calls. LangChain tools abstract over all three backends.
  • Interrupt resume flow: Design WebSocket reconnection + re-send interrupt prompt on reconnect.
  • Tests per phase: 28 unit/integration + 4 E2E, written alongside each phase.