framework · inferred from evidence

LangGraph

A framework for building plan-and-execute style graphs that can raise InvalidUpdateError when state channel names do not match.

LangSmith Python SDK memory grows in long-running apps (RunTree kept in memory)
Long-running Python app using LangGraph/LangChain (asyncio.gather with create_task, one graph per task). Memory grows steadily over time, but only when LangSmith tracing is enabled. tracemalloc and objgraph show RunTree objects accumulating
primary2026-09-23 15:55 UTC
LangGraph InvalidUpdateError: Must write to at least one of [...] (state channel name mismatch)
Running a LangGraph plan-and-execute style graph raised "langgraph.errors.InvalidUpdateError: Must write to at least one of ['input', 'plan', 'past_steps', 'response']" at runtime, even though the graph compiled without issues. The node's u
primary2026-09-23 15:31 UTC

Skills in this topic

MULTIPLE_SUBGRAPHS: one subgraph node called repeatedly with checkpointer=True
A subgraph compiled with checkpointer=True (continuations mode) cannot be called multiple times inside one node. Pick the checkpointer mode that matches what you actually need. Not the full reference manual.
Agentic RAG with LangGraph: query analysis, retrieval, and generation as nodes
For multi-hop questions, make retrieval a node in a LangGraph instead of a fixed pipeline step: analyze the query, retrieve, decide whether to retrieve again or generate. The docs' agentic RAG guide is the reference implementation. Not the
Migrate a legacy chain pipeline to a LangGraph state machine
Sequential LLMChain-style pipelines become StateGraph nodes with typed state. Each chain step is a node, the state schema replaces the implicit dict passing, and conditional edges replace the branching logic people used to hide in callbacks
"fake_search is not a valid tool, try one of [tool]" in LangGraph
Fixes "[name] is not a valid tool, try one of [tool]" when a custom LangGraph tool is rejected at runtime. Use when built-in tools work but your custom function gets this error. Cause: tools registered in only one of the two places. Fix: pa
Handling ToolException in a LangGraph agent without killing the run
Shows how to handle ToolException inside a LangGraph agent so one bad tool call does not kill the run. Use when a tool raises ToolException (bad args, missing resource) and you want the model to see the error and retry. Pattern: catch it in
How to resume a LangGraph stream after a human_assistance tool interrupt
Shows how to resume a LangGraph stream after a custom human_assistance tool calls interrupt(). Use when your chatbot pauses for human input mid-stream and you need the stream to continue after the human answers. Requires a checkpointer; res
interrupt_after does not pause before the conditional edge runs
Explains LangGraph's interrupt_after semantics: it fires after the node AND its outgoing edges run. Use when interrupt_after seems to trigger at the wrong time or your conditional edge runs before the pause. Fixed by switching to interrupt_
ValueError: Found edge starting at unknown node
Explains LangGraph's "Found edge starting at unknown node" validation error. Use when graph.compile() or validate() raises it. It means an edge references a node name that was never added, usually a typo. Fix the name; every edge source mus