fix(error_classifier): avoid large-context false overflow heuristics - #19723
Merged
Conversation
Generic 400 and server-disconnect heuristics used absolute token/message-count fallbacks that are too aggressive for 1M context sessions. Gate those absolute fallbacks to smaller context windows while preserving relative pressure checks. Fixes #16351
alt-glitch
added
type/bug
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Salvage of #16352 onto current main.
Summary
Generic HTTP 400 responses and server disconnects were being classified as
context_overflowon 1M-context sessions just because they had hundreds of messages. Absolute thresholds (approx_tokens > 120_000,num_messages > 200) are only valid proxies for smaller context windows. Gate the absolute thresholds oncontext_length <= 256000so large-context sessions rely on the percentage-based check instead.Validation
Manual review of diff.
Original PR: #16352