Garry Tan c35e933c7d fix: rewrite session-runner to claude -p subprocess, lower flaky baselines ...

Session runner now spawns `claude -p` as a subprocess instead of using
Agent SDK query(), which fixes E2E tests hanging inside Claude Code.
Also lowers command_reference completeness baseline to 3 (flaky oscillation),
adds test:e2e script, and updates CLAUDE.md.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-14 02:34:10 -05:00

..

eval-baselines.json

fix: rewrite session-runner to claude -p subprocess, lower flaky baselines

2026-03-14 02:34:10 -05:00

qa-eval-checkout-ground-truth.json

feat: 3-tier eval suite with planted-bug outcome testing (EVALS=1)

2026-03-14 01:17:36 -05:00

qa-eval-ground-truth.json

feat: 3-tier eval suite with planted-bug outcome testing (EVALS=1)

2026-03-14 01:17:36 -05:00

qa-eval-spa-ground-truth.json

feat: 3-tier eval suite with planted-bug outcome testing (EVALS=1)

2026-03-14 01:17:36 -05:00

review-eval-vuln.rb

feat: 3-tier eval suite with planted-bug outcome testing (EVALS=1)

2026-03-14 01:17:36 -05:00