tool · inferred from evidence
checkpointer
A tool or object used for managing checkpoints in the database, part of the PostgresSaver workflow.
- Connection resilience: what LangChain retries automatically and what it does not
Chat models retry failed requests with exponential backoff automatically: up to 6 times for network errors, 429 rate limits, and 5xx server errors. 401 and 404 are never retried. Tune with max_retries and timeout.
- 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
- Send objects are not serializable, causing checkpointer failures
Fixes checkpointer failures in LangGraph map-reduce graphs where Send objects fail to serialize. Use when a graph using Send() for fan-out crashes on checkpoint writes with a serialization TypeError. Fixed in recent langgraph versions; upgr
- 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_
- AsyncPostgresSaver 2.0.23 fails to read channel values: NoneType not a mapping
Fixes LangGraph's AsyncPostgresSaver failing to read checkpoints with a NoneType error on version 2.0.23. Use when alist/get_tuple raises about NoneType not being a mapping on langgraph-checkpoint-postgres 2.0.23. Fixed in the next release;