fix: classify 429 overloaded messages as overloaded instead of rate_limit#1
Open
boticlaw wants to merge 1 commit into
Open
fix: classify 429 overloaded messages as overloaded instead of rate_limit#1boticlaw wants to merge 1 commit into
boticlaw wants to merge 1 commit into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
In `classifyFailoverReasonFromHttpStatus()` (`src/agents/pi-embedded-helpers/errors.ts`), HTTP 429 responses are classified unconditionally as `rate_limit` without checking the error message body.
Current behavior
```typescript
if (status === 429) {
return "rate_limit"; // No message check
}
```
Fix
HTTP 429 now checks for overloaded messages via `isOverloadedErrorMessage()` before classifying, mirroring the pattern already used for 503 (line ~418) and 499 (line ~424):
```typescript
if (status === 429) {
if (message && isOverloadedErrorMessage(message)) {
return "overloaded";
}
return "rate_limit";
}
```
Why
Some providers (e.g., z.ai / ZhipuAI) return HTTP 429 with messages like:
This is a server capacity issue, not a consumer rate limit. Misclassifying it:
Diff
```diff
if (status === 429) {
return "rate_limit";
}
```