| name | langchain-agents-langgraph-code |
| description | Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need explicit StateGraph control (multi-graph workflows, custom routing, non-standard state schemas, parallel branches). For the common case, use `create_agent` first (see middleware skill). |
LangGraph: editorial guidance
For API reference (signatures, imports, exhaustive method lists), use the mcpdoc MCP tools: fetch_docs("https://docs.langchain.com/oss/python/langgraph/..."). This skill is the opinions layer; the docs are the facts layer.
When to drop down to raw StateGraph
Most agents do NOT need this. Use create_agent(...) + middleware first (see the langchain-agents-middleware skill). Drop down to StateGraph only when:
- Multiple LLM calls in a single graph with custom routing between them.
- Branches that run in parallel and merge.
- Non-message state (custom dataclasses, dicts, dataframes flowing through nodes).
- Multi-graph workflows where one graph calls another as a subgraph.
If your problem fits "one model, some tools, in a loop" — even if the loop is complex — create_agent is the right tool. Don't reach for StateGraph out of habit.
Things the docs won't warn you about
- A node returning
{} is a no-op; return None to signal "no state change" cleanly.
add_conditional_edges mappings must include END if any branch terminates — leaving it out is a silent bug, not an error.compile() is not idempotent across bind_tools — rebind tools, then re-compile.
