Skip to content

chore: update known-models and E2E tests to latest cheapest models#529

Merged
FL4TLiN3 merged 3 commits intomainfrom
chore/update-e2e-models
Feb 15, 2026
Merged

chore: update known-models and E2E tests to latest cheapest models#529
FL4TLiN3 merged 3 commits intomainfrom
chore/update-e2e-models

Conversation

@FL4TLiN3
Copy link
Contributor

Summary

  • Add missing latest models to known-models: claude-opus-4-6, gpt-5.1, gpt-5.2, gpt-5.2-pro, gemini-3-flash-preview
  • Switch all E2E tests to cheapest models per provider to minimize CI cost:
    • Anthropic: claude-sonnet-4-5claude-haiku-4-5 ($1/$5 MTok)
    • OpenAI: o3-mini/gpt-4.1gpt-5-nano ($0.05/$0.40 MTok) — fixes CI failures from deprecated o3-mini
    • Google: gemini-2.5-flash unchanged (already cheapest stable)

Test plan

  • pnpm typecheck passes
  • pnpm test — 100 files, 1093 tests all passing
  • E2E tests on CI (requires API keys)

🤖 Generated with Claude Code

FL4TLiN3 and others added 3 commits February 15, 2026 14:17
Add missing models to known-models:
- claude-opus-4-6 (Anthropic latest flagship)
- gpt-5.1, gpt-5.2, gpt-5.2-pro (OpenAI latest)
- gemini-3-flash-preview (Google latest)

Update E2E test models:
- o3-mini → gpt-5-nano (o3-mini deprecated)
- gpt-4.1 → gpt-5-nano (providers test)
- claude-sonnet-4-20250514 → claude-sonnet-4-5 (streaming test)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Anthropic: claude-sonnet-4-5 → claude-haiku-4-5 (18 TOMLs + 3 test files)
- OpenAI: already gpt-5-nano from previous commit
- Google: gemini-2.5-flash unchanged (already cheapest stable)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@FL4TLiN3 FL4TLiN3 merged commit 211e47f into main Feb 15, 2026
11 checks passed
@FL4TLiN3 FL4TLiN3 mentioned this pull request Feb 15, 2026
@FL4TLiN3 FL4TLiN3 deleted the chore/update-e2e-models branch February 25, 2026 13:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant