QA Runner 0cc635bd5e docs(e2e): mark the model-selection gap fixed — specs pick a Claude model when the key is set ... The "Known gap" paragraph predicted the 4 LLM specs would fail with the secret set because they selected the fork-only "Demo (no key needed)" model. That is now fixed on the e2e suite branch (#220): the helper selects "Claude Sonnet 4.6" and the critical-path assertion checks for a nonempty streamed assistant answer. Update the paragraph accordingly: setting ANTHROPIC_API_KEY now yields 27 passed / 0 skipped (verified locally; keyless stays 23 passed / 4 skipped). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-07-22 11:38:12 -07:00
..
e2e-ci.md	docs(e2e): mark the model-selection gap fixed — specs pick a Claude model when the key is set	2026-07-22 11:38:12 -07:00
safe-local-testing.md	docs: add safe local testing guide	2026-05-04 20:09:05 -04:00
testing-coverage.md	test: cover critical backend libs, raise coverage ratchet, add roadmap	2026-07-20 11:21:35 -07:00