Nuno CamposandGitHub 4fb2aeacc7 Add checkpoint_during arg (#4169) ...

- This provides a new mode of execution where only the last checkpoint
is saved
- We save the last checkpoint no matter how the agent run is terminated
(success, error, interrupt, etc)
- This cuts down on cpu time spent on checkpointing, while not losing
any resilience benefits, given individual task writes are still saved
- If an error occurs and the run is retried, any tasks that completed
successfully before will be skipped (as currently)
- checkpoint_during=True is useful when you want to time-travel to inner
steps of a run
- The default value will remain the current behavior, ie.
checkpoint_during=True

2025-04-08 15:03:06 -07:00

..

__init__.py

Add benchmark/profile commands

2024-09-11 11:44:18 -07:00

__main__.py

Add checkpoint_during arg (#4169)

2025-04-08 15:03:06 -07:00

fanout_to_subgraph.py

Import TypedDict from typing_extensions, add ruff rule

2024-12-31 22:14:16 +09:00

pydantic_state.py

Add pydantic benchmark

2025-03-18 16:12:34 -07:00

react_agent.py

Fix some typing issues in langgraph lib

2024-09-19 11:38:41 -07:00

sequential.py

Avoid raise-catch strategy in BaseChannel.checkpoint()

2025-03-31 17:48:19 -07:00

wide_dict.py

Add benchmark script for typed dict version of existing wide state benchmark (#4174)

2025-04-04 18:37:57 +00:00

wide_state.py

Add benchmark script for typed dict version of existing wide state benchmark (#4174)

2025-04-04 18:37:57 +00:00