Fix false positive billing error detection in agent messages#76
Open
moscowchill wants to merge 1 commit intoKeygraphHQ:mainfrom
Open
Fix false positive billing error detection in agent messages#76moscowchill wants to merge 1 commit intoKeygraphHQ:mainfrom
moscowchill wants to merge 1 commit intoKeygraphHQ:mainfrom
Conversation
detectApiError() was checking the full assistant message content including serialized tool_use JSON. When agents wrote security reports containing terms like "usage limit" or "rate limit", the billing error patterns matched on report content inside Write tool calls, killing the agent. Add extractTextOnlyContent() that filters out tool_use blocks so only the agent's actual text responses are checked for billing patterns. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
detectApiError()was checking full assistant message content including serialized tool_use JSONBillingErrorextractTextOnlyContent()that filters out tool_use blocks so only the agent's actual text responses are checked for billing patternsTest plan
extractTextOnlyContentfiltering tool_use blocks🤖 Generated with Claude Code