🤖 feat: add GPT-6 Sol and Luna model support - #4348
Conversation
Complete September 22 model coverage alongside the Opus 5.5 support already on main. --- _Generated with `xum` • Model: `openai:gpt-6-astra` • Thinking: `high` • Cost: `$12.61`_ <!-- mux-attribution: model=openai:gpt-6-astra thinking=high costs=12.61 -->
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
|
@codex review |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 23bdfc2909
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Disable Sol/Luna reasoning on Chat Completions while retaining the selected effort on Responses. --- _Generated with `xum` • Model: `openai:gpt-6-astra` • Thinking: `high` • Cost: `$12.61`_ <!-- mux-attribution: model=openai:gpt-6-astra thinking=high costs=12.61 -->
|
@codex review |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
|
Codex Review: Didn't find any major issues. 🚀 Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
GPT alias now tracks GPT-6 Sol, which is not yet OAuth-allowlisted.
|
@codex review |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
|
Codex Review: Didn't find any major issues. Swish! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
Assume Codex serves the new tiers like Astra (372K cap); restore GPT-6 Luna as the naming fallback. --- _Generated with `xum` • Model: `openai:gpt-6-astra` • Thinking: `high` • Cost: `$24.87`_ <!-- mux-attribution: model=openai:gpt-6-astra thinking=high costs=24.87 -->
|
@codex review |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 2e46d26ef2
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| "gpt-6-sol", | ||
| "gpt-6-luna", |
There was a problem hiding this comment.
When either new model is selected and Codex OAuth is connected—including API-key users whose default auth remains oauth—these entries make providerModelFactory.ts route the request to the ChatGPT Codex endpoint. The current Codex catalog does not advertise these IDs, and the adjacent comment explicitly labels their availability as assumed, so the promoted gpt/sol and luna choices can return unsupported-model errors instead of using a configured API key; OAuth-only users also see unusable entries. Keep them API-key-only until Codex endpoint support is verified.
Useful? React with 👍 / 👎.
…their Codex context cap #4348 added GPT-6 Sol/Luna and clamps their Chat Completions reasoning effort to "none" in buildProviderOptions, but @ai-sdk/openai@4.0.71 strips "none" for every gpt-6 model, so the clamp never reached the request body and tool-bearing turns were rejected upstream. This adds a Bun patch that accepts "none" for exact Sol/Luna ids only, enforces the same clamp at the model boundary for headless tool loops (including Coder openai-compat aliases resolved through their scoped mapping), and replaces the assumed 372K Codex OAuth cap with the 272K published in the pinned Codex catalog. Wire-level regressions cover both. _Generated with `xum` • Model: `coder:anthropic/claude-fable-5-1` • Thinking: `xhigh` • Cost: `$174.60`_ <!-- mux-attribution: model=coder:anthropic/claude-fable-5-1 thinking=xhigh costs=174.60 -->
2 participants
Summary
Add GPT-6 Sol and GPT-6 Luna, released September 22, to the curated model catalog. Promote
gpt/solandlunato the new tiers while preserving older model strings. Today's Anthropic release, Claude Opus 5.5, is already supported on main by #3993; this PR completes the missing OpenAI additions rather than duplicating that work.Implementation
nonethrough nativemaxreasoning and Pro mode on supported Responses API routes, without broadening Astra's always-on reasoning rule or matching unannounced variants.nonereasoning for Sol/Luna on opt-in Chat Completions routes so agent function calls remain supported; preserve selected reasoning on Responses. Cover canonical IDs, dated IDs, and mapped aliases.Sources: OpenAI release notes, Sol, Luna, reasoning modes, Opus 5.5.
Validation
bun test srcrun.make static-checkandmake static-check-fullpassed, including documentation links.Risks
The short OpenAI aliases now select the newer tiers. Existing fully-qualified model IDs remain usable. Codex OAuth availability and the 372K cap for Sol/Luna are assumptions, not yet confirmed by a published Codex catalog. If either is wrong, OAuth-only users of
gpt/sol/lunaget request errors or early compaction until the allowlist is adjusted.Generated with
xum• Model:openai:gpt-6-astra• Thinking:high• Cost:$24.87