fix(streaming): use finish_reason=length for partial stream stub#30988
Closed
ilonagaja509-glitch wants to merge 1 commit into
Closed
fix(streaming): use finish_reason=length for partial stream stub#30988ilonagaja509-glitch wants to merge 1 commit into
ilonagaja509-glitch wants to merge 1 commit into
Conversation
Partial stream stub responses were returning finish_reason=stop which caused the agent loop to exit prematurely even when budget remained. The model had not legitimately finished — the connection dropped mid-stream. Changing to finish_reason=length triggers the continuation path in conversation_loop.py, allowing the agent to retry or continue working on the goal. Fixes NousResearch#30963
7 tasks
Contributor
Author
|
Closing in favor of #30998 which also adds the truthful continuation prompt for network-error cases. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Partial stream stub responses returned finish_reason=stop which caused the agent loop to exit prematurely even when budget remained.
The model had not legitimately finished — the connection dropped mid-stream. Changing to finish_reason=length triggers the continuation path in conversation_loop.py, allowing the agent to retry or continue working on the goal.
Fixes #30963