Hongming Wang b8b3d5ce1f fix(e2e): MODEL_PROVIDER is provider:model slug, not just provider ... workspace/config.py:258 reads MODEL_PROVIDER as the full model string (format 'provider:model', e.g. 'anthropic:claude-opus-4-7'). My prior 'openai' alone got parsed as the model name → 404 model_not_found. Use 'openai:gpt-4o' and also set OPENAI_BASE_URL to api.openai.com (default was openrouter.ai which takes different key format). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>		2026-04-21 10:33:27 -07:00
..
_extract_token.py	chore: apply round-7 review nits	2026-04-13 17:08:45 -07:00
_lib.sh	feat(platform): GET /admin/workspaces/:id/test-token for E2E (#6)	2026-04-14 09:35:26 -07:00
STAGING_SAAS_E2E.md	feat(e2e): pivot to admin-bearer-only auth + add sanity self-check workflow	2026-04-21 04:34:11 -07:00
test_a2a_e2e.sh	initial commit — Molecule AI platform	2026-04-13 11:55:37 -07:00
test_activity_e2e.sh	chore: apply code-review round-6 suggestions	2026-04-13 17:08:45 -07:00
test_api.sh	fix(e2e): stop asserting current_task on public workspace GET (#966)	2026-04-19 02:19:15 -07:00
test_claude_code_e2e.sh	chore: final open-source cleanup — binary, stale paths, private refs	2026-04-18 00:38:55 -07:00
test_comprehensive_e2e.sh	fix(e2e): make provisioning-status assertions robust to CI environment	2026-04-13 17:31:07 -07:00
test_saas_tenant.sh	chore: final open-source cleanup — binary, stale paths, private refs	2026-04-18 00:38:55 -07:00
test_staging_full_saas.sh	fix(e2e): MODEL_PROVIDER is provider:model slug, not just provider	2026-04-21 10:33:27 -07:00