feat(openai): default new setups to GPT-5.6#103581
Merged
Merged
Conversation
openclaw-barnacle
Bot
added
docs
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 254242df69
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".
| const GPT_51_REASONING_EFFORTS = ["none", "low", "medium", "high"] as const; | ||
| const GPT_52_REASONING_EFFORTS = ["none", "low", "medium", "high", "xhigh"] as const; | ||
| const GPT_56_REASONING_EFFORTS = ["low", "medium", "high", "xhigh", "max"] as const; | ||
| const GPT_56_REASONING_EFFORTS = ["none", "low", "medium", "high", "xhigh", "max"] as const; |
Contributor
There was a problem hiding this comment.
none off Codex GPT-5.6 slugs
When the selected model is a ChatGPT/Codex GPT-5.6 slug (gpt-5.6-sol, gpt-5.6-terra, or gpt-5.6-luna) and the dynamic resolver synthesizes it without catalog compat, this id-family default makes resolveOpenAIReasoningEffortForModel(..., "none") return none. The Codex catalog path in this change still treats those slugs as low/medium/high/xhigh/max only (thinkingLevelMap.off = null), so default OpenAI Responses calls for fresh OAuth/Codex setups send reasoning.effort: "none" to the Codex backend instead of omitting reasoning. Please gate none on direct-API metadata/compat rather than the shared GPT-5.6 id family.
Useful? React with 👍 / 👎.
Contributor
Author
|
Land-ready proof:
Known proof gaps: no approved fresh OAuth completion and no valid credential denied only GPT-5.6 were available, so those two credential-dependent live clauses are not claimed. |
Contributor
Author
|
Merged via squash.
|
This was referenced Jul 10, 2026
github-actions Bot
pushed a commit
to Desicool/openclaw
that referenced
this pull request
Jul 11, 2026
* feat(openai): default fresh setup to GPT-5.6 * test(crestodian): expect GPT-5.6 Codex defaults * test(crestodian): expect GPT-5.6 bootstrap default
This was referenced Jul 11, 2026
steipete
added a commit
that referenced
this pull request
Jul 11, 2026
…faults for the stable cut (#104656) * feat(openai): default new setups to GPT-5.6 (#103581) * feat(openai): default fresh setup to GPT-5.6 * test(crestodian): expect GPT-5.6 Codex defaults * test(crestodian): expect GPT-5.6 bootstrap default (cherry picked from commit ab5d143) * fix(infra): converge legacy state migrations on archive collisions (cherry picked from commit 474d660) * fix(codex): prevent startup hangs after binding migration (#103281) * fix(codex): archive imported orphan binding sidecars * fix(codex): harden binding sidecar migration Co-authored-by: Benjamin Badejo <[email protected]> * chore: keep release notes out of contributor PRs --------- Co-authored-by: Benjamin Badejo <[email protected]> Co-authored-by: Peter Steinberger <[email protected]> (cherry picked from commit 1f3ea6f) * fix(migrations): converge recoverable legacy state (#104529) Signed-off-by: sallyom <[email protected]> (cherry picked from commit cdb58ca) * test(openai): align auth contract with provider default (#103760) (cherry picked from commit 9b4c7c0) * fix: clear remaining release validation blockers (#104555) * test: align provider tool call lifecycles * test: isolate plugin install repair migrations * fix: accept catalog temperature compatibility * fix: disable GPT-5.6 tool reasoning on completions * style: avoid shadowed stream model (cherry picked from commit 57af2bb) * test(release): keep GPT-5.6 backport scoped * test(release): restore doctor config type import --------- Signed-off-by: sallyom <[email protected]> Co-authored-by: Ayaan Zaidi <[email protected]> Co-authored-by: Ben Badejo <[email protected]> Co-authored-by: Benjamin Badejo <[email protected]> Co-authored-by: Sally O'Malley <[email protected]>
steipete
added a commit
that referenced
this pull request
Jul 11, 2026
* feat(openai): default fresh setup to GPT-5.6 * test(crestodian): expect GPT-5.6 Codex defaults * test(crestodian): expect GPT-5.6 bootstrap default (cherry picked from commit ab5d143)
steipete
added a commit
that referenced
this pull request
Jul 11, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #103234
What Problem This Solves
Fresh OpenAI setup still selected GPT-5.5, while GPT-5.6 Sol, Terra, and Luna were only partially represented across direct API, Codex OAuth, migration, model-list, and QA paths. Existing users also risked losing a usable allowlist entry when adding OpenAI auth to an already configured model setup.
Why This Change Was Made
Direct OpenAI API setup now defaults to the stable
openai/gpt-5.6Sol alias, while Codex OAuth and imported Codex credentials use the exactopenai/gpt-5.6-solreference required by the Codex catalog. The change keeps explicit primary/fallback/alias choices intact, separates direct API metadata from native Codex metadata, and maps GPT-5.6 reasoning Off to the API'snonevalue instead of omitting effort and accidentally requesting Medium.User Impact
New OpenAI API setups start on GPT-5.6 by default. Sol, Terra, and Luna remain selectable; direct API users get the documented 1.05M-token context metadata, native Codex keeps its authoritative 372K catalog metadata, and existing model configuration remains unchanged when OpenAI auth is added.
Evidence
tbx_01kx5ga0jy20zzq4b8rgbrab3h: 209 focused tests passed across OpenAI provider/defaults, reasoning effort, onboarding, model compatibility, QA selection, and provider-auth preservation.tsgo:coreandtsconfig.extensions.jsonpassed on the same Testbox.