addon-langchain-llm（addon LangChain LLM 命令行）

Add-on: LangChain LLM

Use this skill when an existing project needs LangChain primitives for chat, retrieval, or summarization.

Compatibility

• Works with architect-python-uv-fastapi-sqlalchemy, architect-python-uv-batch, and architect-nextjs-bun-app.
• Can be combined with addon-rag-ingestion-pipeline.
• Can be combined with addon-langgraph-agent when graph orchestration is required.
• Can be combined with addon-llm-judge-evals; when used together, declare langchain in config/skill_manifest.json so the judge runner can resolve the backend without guessing.

Inputs

Collect:

• LLM_PROVIDER: openai | anthropic | ollama.
• DEFAULT_MODEL: provider model id.
• ENABLE_STREAMING: yes | no (default yes).
• USE_RAG: yes | no.
• MAX_INPUT_TOKENS: default 8000.

Integration Workflow

1. Add dependencies:

• Python:

uv add langchain langchain-core langchain-community pydantic-settings tiktoken

• Next.js:

# Use the project's package manager (examples):
bun add langchain zod
pnpm add langchain zod

• Provider packages (as needed):

uv add langchain-openai langchain-anthropic langchain-ollama
# Use the project's package manager (examples):
bun add @langchain/openai @langchain/anthropic @langchain/ollama
pnpm add @langchain/openai @langchain/anthropic @langchain/ollama

1. Add files by architecture:

• Python API:

src/{{MODULE_NAME}}/llm/provider.py
src/{{MODULE_NAME}}/llm/chains.py
src/{{MODULE_NAME}}/api/routes/llm.py

• Next.js:

src/lib/llm/langchain.ts
src/lib/llm/chains.ts
src/app/api/llm/chat/route.ts

1. Enforce typed request/response contracts:

• Validate input lengths before chain invocation.
• Return stable schema for streaming and non-streaming modes.

1. If USE_RAG=yes, compose retriever + prompt + model chain:

• Keep retrieval source metadata in outputs.
• Bound document count and token budget.

1. If addon-llm-judge-evals is also selected:

• emit config/skill_manifest.json with addon-langchain-llm in addons
• declare "judge_backends": ["langchain"] in capabilities
• allow the judge runner to reuse DEFAULT_MODEL when JUDGE_MODEL is unset

Required Template

Chat response shape

{
  "outputText": "string",
  "model": "string",
  "provider": "string"
}

Guardrails

• Documentation contract for generated code:

- Python: write module docstrings and docstrings for public classes, methods, and functions. - Next.js/TypeScript: write JSDoc for exported components, hooks, utilities, and route handlers. - Add concise rationale comments only for non-obvious logic, invariants, or safety constraints. - Apply this contract even when using template snippets below; expand templates as needed.

• Enforce provider/model allow-lists.
• Add timeout and retry limits around provider calls.
• Never log secrets or raw auth headers.
• On streaming disconnect, stop upstream generation promptly.
• If judge evals are enabled, keep the judge path on the same provider abstraction instead of bypassing it with ad hoc SDK calls.

Validation Checklist

• Confirm generated code includes required docstrings/JSDoc and rationale comments for non-obvious logic.

uv run ruff check . || true
uv run mypy src || true
# Use the project's package manager (examples):
bun run lint || true
pnpm run lint || true
rg -n "langchain|outputText|provider" src

• Manual checks:
• Typed chat route returns valid response.
• Invalid payloads fail with controlled validation errors.

Decision Justification Rule

• Every non-trivial decision must include a concrete justification.
• Capture the alternatives considered and why they were rejected.
• State tradeoffs and residual risks for the chosen option.
• If justification is missing, treat the task as incomplete and surface it as a blocker.