Previously, we validated that nodes explicitly route to END.
This feels a bit unnecessary, since graphs are expected to keep processing until no work is left to be done
Plus fix a small bug in validation.
- This introduces a new optional method BaseChannel.consume, which gets called when a channel triggers a node
- This is an alternative place to clean up channel state, in addition to the existing pattern of clearing state in the update() call for the next step
- Channels should implement consume() when they want to clean up state exactly if and only if the channel triggered a node
- Channels should clean up state in update() when they instead need to guarantee their value is available for a single step, irrespective of whether it was actually read
- any invalid utf-8 chars now removed on dumps
- fix serialization of Send
- remove serialization of NamedTuple, which doesn't work
- add test for custom serde passed to memory saver
- add test using Send and JsonPlus serde
- currently output of all nodes is streamed only when all nodes in that step finish
- checkpoint/values stream chunks still yielded only at the end of the step, as they require applying all updates
- reorganize checkpointing code to share code between input and step checkpoints
- do not emit debug/checkpoint events when there is no checkpointer attached
- emit debug/checkpoint event for input checkpoint as well
* Merge configurable fields with previous checkpoint config.
* Update update_state() and aupdate_state() to merge configurable fields with previous checkpoint config.
* Update tests to verify that all checkpoint metadata contain the expected configurable field keys. This assertion is needed because a run can have an arbitrary number of steps based on the construction of the graph.
- this avoids conflicts if multiple processes creating checkpoints in same thread at same time
- uuid6 with a monotically increasing clock_seq is sortable by creation time at ms precision (plus clock_seq for ties, plus 48 bits of randomness for further ties)
* Add managed values and IsLastStep
- managed values are read-only state keys whose values are managed by langgraph
- this PR implements one: IsLastValue, a boolean which is True in the last iteration, eg to allow you to return a nice "ran out of iterations" message to user
* Fix
* Fix some issues
* py39
* Break ref
* Fix types
* Fix
* Fix
* Update state.py
* Don't mutate dictionary while using it in for loop.
---------
Co-authored-by: Andrew Nguonly <andrewnguonly@gmail.com>
