fix(llm): classify zai token limit overflow#35671
Merged
Merged
Conversation
github-actions
Bot
added
needs:compliance
Contributor
|
Thanks for updating your PR! It now meets our contributing guidelines. 👍 |
Collaborator
|
good pr ty |
shaheislam
pushed a commit
to shaheislam/opencode-vim
that referenced
this pull request
Jul 7, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
Fixes #27519
Also covers the Z.AI/GLM repro in #27629.
Type of change
What does this PR do?
Adds the Z.AI/GLM error text
tokens in request more than max tokens allowedto the shared context-overflow matcher. That makes APICallError conversion produceContextOverflowError, so the existing compaction path can run instead of treating the provider response as a generic API error.I added coverage at the shared LLM matcher and at the opencode session error conversion layer.
How did you verify your code works?
Before the implementation,
bun test --timeout 30000 test/session/message-v2.test.tsfrompackages/opencodefailed on the added provider message case.Passing checks after the fix:
bun test --timeout 30000 test/provider-error.test.tsfrompackages/llmbun test --timeout 30000 test/session/message-v2.test.tsfrompackages/opencodebun typecheckfrompackages/llmbun typecheckfrompackages/opencodebun turbo typecheckfrom repo root, 30 successful / 30 totalScreenshots / recordings
Not a UI change.
Checklist