hai/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-22 04:38:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add debug escalation tests (validation + LLM judge + E2E)

Browse Source 
Skill validation: 11 new assertions covering Phase 8g trigger, structured
handoff fields, agent result handlers, debug escalation summary, Step 5.7
recommendation, ship reverted QA detection, and debug browse setup.

LLM judge: evaluates Phase 8g template quality — structured brief format,
result handling, working tree cleanup, sequential processing.

E2E: prompt-level deterministic test (verifies escalation prompt has all
required fields) + full flow stub (fixture TODO for planted regression).

Touchfile entries for diff-based test selection.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-18 11:13:12 -07:00
parent 21daf76723
commit 5044c664c6
5 changed files with 155 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
test/helpers/touchfiles.ts
View File

@@ -90,6 +90,10 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// gstack-upgrade
'gstack-upgrade-happy-path': ['gstack-upgrade/**'],
// Debug escalation
'qa-debug-prompt-logic': ['qa/**', 'debug/**'],
'qa-debug-escalation': ['qa/**', 'debug/**', 'browse/src/**'],
};
/**
@@ -123,6 +127,9 @@ export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
'retro/SKILL.md instructions': ['retro/SKILL.md', 'retro/SKILL.md.tmpl'],
'qa-only/SKILL.md workflow': ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl'],
// Debug escalation
'qa/SKILL.md debug escalation': ['qa/SKILL.md', 'qa/SKILL.md.tmpl', 'debug/SKILL.md', 'debug/SKILL.md.tmpl'],
};
/**