Add OpenAI GPT-6 Sol and Luna support - #1090
PeterDaveHello wants to merge 1 commit into
Conversation
Register GPT-6 Sol and Luna as built-in OpenAI models and replace their GPT-5.6 counterparts in the default preset list. Use GPT-6-compatible completion and temperature parameters while keeping the GPT-5.6 presets available for existing configurations. References: - https://developers.openai.com/api/docs/models/gpt-6-sol - https://developers.openai.com/api/docs/models/gpt-6-luna - https://openai.com/index/introducing-gpt-6-sol-and-luna/
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
|
Navigate logical layers of code changes, visualize relationships, and explore their blast radius. No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (9)
Included review availability: Your plan provides up to 10 included reviews per hour; 8 remain after this review. 📝 WalkthroughWalkthroughChangesGPT-6 Sol and Luna model support
Priority: ➖ Normal Estimated code review effort: 2 (Simple) | ~12 minutes Change: Feature Sequence Diagram(s)sequenceDiagram
participant ModelConfig
participant generateAnswersWithOpenAiApi
participant openai-token-params
participant temperature-params
participant OpenAIAPI
ModelConfig->>generateAnswersWithOpenAiApi: Select chatgptApi6Sol or chatgptApi6Luna
generateAnswersWithOpenAiApi->>openai-token-params: Resolve token parameter
generateAnswersWithOpenAiApi->>temperature-params: Resolve temperature parameter
openai-token-params->>OpenAIAPI: Send max_completion_tokens
temperature-params->>OpenAIAPI: Omit temperature
Merge Risk: ⚪ Minimal · up to GPT-6 Sol and Luna support is internally consistent and ready to merge after normal checks. 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
Full details: Docstring CoverageExplanation Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 2 functions across 8 files. (1 skipped: 1 unsupported.)
✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
PR Summary by QodoAdd OpenAI GPT-6 Sol and Luna support
AI Description
Diagram
High-Level Assessment
Files changed (9)
|
Code Review by Qodo
1. Other locales fall back to English
|
![qodo-code-review[bot]](https://avatars.githubusercontent.com/in/484649?s=60&v=4){kind=small}
There was a problem hiding this comment.
Copilot review overview
🟡 Changes recommended
Existing materialized profiles need a migration to replace GPT-5.6 defaults with GPT-6 while retaining the older models as selectable.
Get a fresh assessment by requesting another Copilot review.
Review effort: Lite
Findings: 1
Open (1)
What changed in this PR
Adds GPT-6 Sol and Luna as built-in OpenAI models with updated request parameters and picker labels.
Changes:
- Registers GPT-6 models and updates default presets.
- Uses GPT-6-compatible token and temperature parameters.
- Adds localization and test coverage.
| File | Summary |
|---|---|
tests/unit/utils/model-name-convert.test.mjs |
Tests model descriptions. |
tests/unit/services/apis/temperature-params.test.mjs |
Tests temperature handling. |
tests/unit/services/apis/openai-token-params.test.mjs |
Tests token parameter selection. |
tests/unit/services/apis/openai-api-compat.test.mjs |
Tests GPT-6 request payloads. |
tests/unit/config/config-predicates.test.mjs |
Tests model and default registration. |
src/services/apis/temperature-params.mjs |
Omits unsupported temperature overrides. |
src/services/apis/openai-token-params.mjs |
Uses completion-token parameters. |
src/config/index.mjs |
Adds models and defaults; existing profiles need migration to deactivate old defaults. |
src/_locales/en/main.json |
Adds English model labels. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
![pullfrog[bot]](https://avatars.githubusercontent.com/in/1768019?s=60&v=4){kind=small}
There was a problem hiding this comment.
✅ No new issues found.
Reviewed changes
- New OpenAI presets —
chatgptApi6Sol(gpt-6-sol) andchatgptApi6Luna(gpt-6-luna) added toModelsandchatgptApiModelKeys, with matching en locale strings. - Default preset swap —
defaultApiModeIdsdropschatgptApi5_6Sol/chatgptApi5_6Lunaand adds the GPT-6 pair; GPT-5.6 Sol/Luna remain selectable, and theknownApiModeDefaultIdsmigration appends the new defaults without removing existing ones. - Wire-param handling —
openai-token-params.mjsnow routesgpt-6-(astra|sol|luna)tomax_completion_tokens, and both ids are added toMODELS_WITHOUT_CUSTOM_TEMPERATUREso custom temperature is omitted. - Test updates — coverage extended across
config-predicates,openai-api-compat,openai-token-params,temperature-params, andmodel-name-convert.
The change follows the established GPT-6 Astra precedent end to end, keeps the older presets available, and the affected unit tests pass locally (node --import ./tests/setup/browser-shim.mjs --test).
DeepSeek Flash (free via Pullfrog for OSS) ｜ 𝕏
Summary
max_completion_tokensand omit customtemperaturefor GPT-6 requests.References