hai/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-20 19:29:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: QA skill never refuses browser testing

Browse Source 
Add anti-refusal guardrails to /qa and /qa-only skills. When the user
invokes /qa, the skill must always use the browser — even if the diff
shows only backend/config changes with no obvious UI surface. Falls
back to Quick mode (homepage + top 5 nav targets) when no specific
pages are identified from the diff.

Adds LLM-as-judge eval to verify the anti-refusal behavior.
This commit is contained in:
Garry Tan
2026-03-18 22:27:29 -07:00
parent c4f679d829
commit b1159d951d
6 changed files with 67 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
test/helpers/touchfiles.ts
View File

@@ -116,6 +116,7 @@ export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
'regression vs baseline': ['SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json'],
'qa/SKILL.md workflow': ['qa/SKILL.md', 'qa/SKILL.md.tmpl'],
'qa/SKILL.md health rubric': ['qa/SKILL.md', 'qa/SKILL.md.tmpl'],
'qa/SKILL.md anti-refusal': ['qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'],
'baseline score pinning': ['SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json'],