fix(skill_eval): add trigger-only mode#29
Merged
Conversation
mxl
force-pushed
the
fix/skill-eval-trigger-only
branch
from
2935dd7 to
9e9d948
Compare
Owner
pull Bot
pushed a commit
to Mu-L/opencode-skill-creator
that referenced
this pull request
Jul 5, 2026
…escriptionOverride Reworks antongulin#28: the conflict guard now uses the shared runProcess helper (10s timeout, no Bun globals in compiled output) with a pure, unit-tested parser for `opencode debug skill` output. Empty descriptionOverride strings are treated as omitted in both skill_eval and skill_optimize_loop. Also gates the triggerOnly early return from antongulin#29 so a triggered run that ends in a failed process still throws when triggerOnly is false. Co-authored-by: Michael Ledin <mledin89@gmail.com> Co-Authored-By: Claude Fable 5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
skill_evalruns every query throughopencode runeven after the synthetic skill has already triggered. This wastes time on downstream workflow output that is irrelevant to trigger detection, and can cause false negatives when the model later hits rate limits, timeouts, or unrelated errors.Changes
plugin/lib/process.ts: AllowonStdoutChunkcallback to returnboolean. Whentrue, kill the child process early (with graceful + SIGKILL fallback).plugin/lib/run-eval.ts:triggerOnlyoption (defaulttrue) toRunEvalOptionsandrunSingleQuery.triggerOnly=trueand the synthetic skill name appears in stdout, immediately returntruewithout waiting for the full process to finish.plugin/lib/run-loop.ts: ThreadtriggerOnlythroughRunLoopOptionsintorunEval.plugin/skill-creator.ts: ExposetriggerOnlyboolean schema arg on bothskill_evalandskill_optimize_looptools.Tests: Add early-stop test in
process.test.ts; addtriggerOnly: truetorun-loop.test.tsfixture.Testing
npm run buildpassesnpm run test:ts: 44 pass, 0 failvideo-summarywith GPT-5.4: 3/3 passed, triggerOnly stopped runs immediately after trigger