Relay provider rejection reasons to the model on retry - #157
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Requests the provider rejects as invalid (400) — tool names with channel markers invented tool names, malformed arguments — were retried blind: same context, new dice, no feedback. That cost 24 → 49 → 76 wasted generations across the last three overnight runs. The retry now appends the provider's own rejection message verbatim to the next attempt (detected purely by error type and status code, no text matching), so the model sees exactly what it broke and self-corrects in one step. The feedback is retry-scoped: never persisted to the conversation or any stored state. Also isolates provider unit tests from the machine's ~/.explorbot (a stray unhandled loadConfig was failing random tests locally).