Skip to content

Fix test coverage for providers openai, anthropic, openrouter. - #43

Merged
sanchitrk merged 4 commits into
devfrom
fix-test-cov-openrouter
Sep 30, 2026
Merged

sanchitrk merged 4 commits into
devfrom
fix-test-cov-openrouter

Conversation

@sanchitrk

Copy link
Copy Markdown
Contributor

No description provided.

sanchitrk and others added 4 commits September 30, 2026 17:41
… handling

- modelgen: live-verified thinking levels for gpt-5.4 through gpt-6 (no
  minimal; max only on gpt-5.6/gpt-6; none on Codex gpt-5.5/5.6-luna/6-luna)
  and add Codex gpt-6-luna
- bump @ai-sdk/openai to 4.0.81 so gpt-6-luna accepts reasoning "none"
- floor the context-clamped max tokens at 16 so an overflowing prompt
  surfaces as an overflow instead of an invalid max_output_tokens
- normalize Codex call|item tool call IDs for OpenAI targets (64-char cap)
- classify in-stream StreamProviderError like APICallError

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every OpenAI suite runs on gpt-6-luna through gpt-5.4-nano and every Codex
suite on gpt-6-luna, gpt-5.6-luna and gpt-5.5. Adds thinking-level, context
overflow, handoff and prompt-cache suites.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ID handoff

- modelgen: live-verified Anthropic levels (max on 4.6; xhigh and max on
  4.7/4.8, Sonnet/Opus 5 and Fable 5; 5.5 and Fable cannot disable
  thinking) and Sonnet 4.5's 200k direct-API window
- skip `thinking: {type: "disabled"}` for Claude models that reject it
- normalize Codex call|item tool call IDs for Anthropic targets, leaving
  already-valid IDs untouched
- run the Anthropic e2e suites across a model matrix and add Anthropic to
  the thinking-level, overflow, handoff and cache suites
- document the OpenAI and Anthropic changes in the changelog

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- run every OpenRouter suite on Muse Spark 1.3, GLM 5.3 Flash, DeepSeek
  V4.1 Flash and Gemini 3.8 Flash, adding thinking and multi-turn stream
  tests and the thinking-level, overflow, handoff and cache suites
- normalize Codex call|item tool call IDs for OpenRouter targets, whose
  upstreams (e.g. Meta) cap call_id at 64 characters
- update the changelog

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@sanchitrk
sanchitrk merged commit 9f95c5c into dev Sep 30, 2026
@sanchitrk
sanchitrk deleted the fix-test-cov-openrouter branch October 8, 2026 06:18
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