Make sure last successful node is not executed twice when restoring from Persistence checkpoints #1308
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Make sure last successful node is not executed twice when restoring from Persistence checkpoints
Motivation and Context
Previously, if latest node was a successful tool call or any other operation with a side-effect, it was re-executed again although we could've reused the latest successful result. The reason behind that was becaused internally input was required to restore the full subgraph structure.
In this PR,
lastInputfield of the checkpoints was changed tolastOutput, andresolveEdge()method was used in order to restore the NEXT node with the correct input instead of the current node.Breaking Changes
In checkpoints structure,
lastInputfield was changed tolastOutputType of the changes
Checklist
developas the base branchAdditional steps for pull requests adding a new feature