Repository navigation
fix(triggers): abios-feedback and /expert fire when they should (#764) - #791
Merged
Merged
Conversation
…engine first (#764) Measured with claude plugin eval (Haiku, traces kept): - tool-feedback 0/3 -> 2/3. In every failing run the model understood the report was for the tool's own repo but asked which verb was missing instead of loading abios-feedback. The description now says to load it before asking for details (it says what to collect), and the eval prompt names the verb, as a real report would. - expert-command-engine 0/2 -> 2/3. /expert applied gh-account (scripts) before opening its engine and ran out of turns; it now reads the engine first, like /scan, and resolves the account before the first GitHub call. Full suite (2 runs, with/without): every other case unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Sin hallazgos: cambios de prompts/docs coherentes (orden Read del engine antes de gh-account, descripción de abios-feedback y prompt del eval más concreto). Nada que objetar. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Refs #764. Trigger-eval failures, diagnosed from traces (--keep-temp).
The full eval suite shows no other changes. \�alidate --strict\ and the Update-Docs check pass. CommandSurface, Expert-Auto.Passthrough and InternalVocabularyLeak tests: 281/0.
Once merged, the webhook sends this version to the directory; with auto-publish on, it goes live after approval.
🤖 Generated with Claude Code