Skip to content

feat(adaptor): add '-xhigh' suffix to reasoning effort options - #2429

Merged
Calcium-Ion merged 1 commit into
mainfrom
feat/xhigh
Dec 12, 2025
Merged

feat(adaptor): add '-xhigh' suffix to reasoning effort options#2429
Calcium-Ion merged 1 commit into
mainfrom
feat/xhigh

Conversation

@Calcium-Ion

@Calcium-Ion Calcium-Ion commented Dec 12, 2025

Copy link
Copy Markdown
Member

Summary by CodeRabbit

  • New Features
    • Added support for "-xhigh" model suffix recognition, enabling the system to handle new AI model variants with extended reasoning effort levels. The system now properly processes these model identifiers and extracts the appropriate configuration values.

✏️ Tip: You can customize this high-level summary in your review settings.

@coderabbitai

coderabbitai Bot commented Dec 12, 2025

Copy link
Copy Markdown
Contributor

Walkthrough

The change extends the parseReasoningEffortFromModelSuffix function in OpenAI adaptor to recognize the "-xhigh" model suffix. When a model name ends with "-xhigh", the function now extracts "xhigh" as the effort level and returns the stripped model name alongside it.

Changes

Cohort / File(s) Summary
Model suffix recognition
relay/channel/openai/adaptor.go
Added "-xhigh" to effortSuffixes slice in parseReasoningEffortFromModelSuffix function to support extended reasoning effort level recognition

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

Poem

🐰 A suffix arrives, so bold and so bright,
"-xhigh" joins the fold, effort at height!
Little tweaks make the models align,
One more level of reasoning—simply divine! ✨

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately describes the main change: adding '-xhigh' suffix support to the parseReasoningEffortFromModelSuffix function in the adaptor.
Docstring Coverage ✅ Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch feat/xhigh

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 147659f and 50854c1.

📒 Files selected for processing (1)
  • relay/channel/openai/adaptor.go (1 hunks)

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@Calcium-Ion
Calcium-Ion merged commit 30cb224 into main Dec 12, 2025
1 check passed
Ridter pushed a commit to Ridter/new-api that referenced this pull request Dec 13, 2025
feat(adaptor): add '-xhigh' suffix to reasoning effort options
@Calcium-Ion
Calcium-Ion deleted the feat/xhigh branch January 29, 2026 17:10
ennnnny pushed a commit to ennnnny/new-api that referenced this pull request Mar 17, 2026
feat(adaptor): add '-xhigh' suffix to reasoning effort options
@coderabbitai coderabbitai Bot mentioned this pull request Apr 16, 2026
11 tasks
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