fix(compaction): pass maxOutputSize to resolveCompletionBudget#482
Open
liuhaoyooc wants to merge 1 commit into
Open
fix(compaction): pass maxOutputSize to resolveCompletionBudget#482liuhaoyooc wants to merge 1 commit into
liuhaoyooc wants to merge 1 commit into
Conversation
🦋 Changeset detectedLatest commit: 17beca6 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
The compaction worker was not passing maxOutputSize to resolveCompletionBudget, causing it to fall back to max_context_size as the completion token cap. For models like glm-5.1 configured via openai_legacy provider, this resulted in max_tokens being set to the full context window (e.g. 202752), which the upstream API rejected with a 400 error. Normal chat requests already pass maxOutputSize correctly via Agent.llm.
liuhaoyooc
force-pushed
the
fix/compaction-max-output-size
branch
from
617184b to
17beca6
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The compaction worker was not passing \maxOutputSize\ to \resolveCompletionBudget, causing it to fall back to \max_context_size\ as the completion token cap.
For models configured via the openai_legacy provider (e.g. glm-5.1), this resulted in \max_tokens\ being set to the full context window size, which upstream APIs may reject with a 400 error.
Normal chat requests already pass \maxOutputSize\ correctly via \Agent.llm. This change aligns the compaction path with the normal request path.