fix: recover from model token limit errors - #207
Merged
Conversation
🦋 Changeset detectedLatest commit: d6cd835 The changes in this PR will be included in the next version bump. This PR includes changesets to release 3 packages
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 |
commit: |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Related Issue
No linked issue. This fixes a reproducible long-conversation failure where a provider reports context overflow as a generic 400 model token limit error.
Problem
Some providers return context overflow as
Your request exceeded model token limitinstead of the context overflow phrases Kimi already recognized. Kimi treated that response as a non-retryable provider API error, so compaction did not shrink and retry the request. When a turn was blocked waiting for auto compaction and compaction ultimately failed, the turn could then continue with the original oversized context and surface a second provider error.What changed
model token limit400 responses as context overflow so the existing compaction recovery path can handle them.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.Validation
pnpm vitest run packages/kosong/test/errors.test.tspnpm vitest run packages/agent-core/test/agent/compaction.test.tspnpm --filter @moonshot-ai/kosong run typecheckpnpm --filter @moonshot-ai/agent-core run typecheckpnpm exec oxlint --type-aware packages/kosong/src/errors.ts packages/kosong/test/errors.test.ts packages/agent-core/src/agent/compaction/full.ts packages/agent-core/test/agent/compaction.test.tspnpm --filter @moonshot-ai/agent-core run testpnpm vitest run packages/kosong/testgit diff --check