Yijia-Xiao b43bc31479 fix(cli): resume a checkpoint without duplicating messages or leaking the saver ...

- on resume, the CLI and propagate re-passed the initial state to a thread with
  an existing checkpoint; nodes do not re-run, but the message reducer appended
  the initial messages again, duplicating them in the resumed state
- feed None on resume (checkpoint_input) so LangGraph continues the interrupted
  run, and wrap the CLI stream in try/finally so the checkpointer tears down even
  if the stream raises
- correct the _fetch_returns docstring to the 4-tuple return #1249

2026-08-31 01:29:14 +00:00

5.1 KiB

Raw Blame History

View Raw