Ahmed Abushagur c6d0cb218e improve: make QA bot more effective with structured failures and verification (#1034) ... 5 improvements to the QA cycle: 1. Fix agents now get structured failure context — categorized failures (exit_code, missing_api_call, missing_env, no_fixture) instead of raw 500-line test output, plus a passing agent for comparison 2. Fix agent changes are verified before committing — re-runs mock tests after the agent finishes and only commits if results actually improved, discarding bad fixes that would create noise PRs 3. Test results now include failure categories — mock.sh records cloud/agent:fail:reason instead of just cloud/agent:fail, enabling smarter failure routing 4. Mock curl logs NO_FIXTURE warnings when no fixture matches a GET request, surfacing false-confidence gaps where tests pass with synthetic fallback data 5. Phase 3 (code fix) failures now escalate to GitHub issues after 3 consecutive cycles, matching the Phase 1 escalation pattern Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-13 20:07:54 -05:00
..
fixtures	refactor: extract mock test env config and API assertions into per-cloud fixture files (#803)	2026-02-13 02:16:11 -08:00
mock.sh	improve: make QA bot more effective with structured failures and verification (#1034)	2026-02-13 20:07:54 -05:00
qa-dry-run.sh	feat: qa bot and emails (#565)	2026-02-11 20:19:45 -08:00
record.sh	refactor: decompose multi-credential config handling in test/record.sh (#1004)	2026-02-13 13:34:37 -08:00
run.sh	refactor: extract helpers from run_script_test and run_shellcheck in test/run.sh (#776)	2026-02-12 17:19:32 -08:00
update-readme.py	QA-Bot setup (#335)	2026-02-10 19:51:07 -08:00