feat: unify Coder Agents model pickers#27175
Conversation
|
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c30d9a5e8a
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".
|
|
@codex review |
|
Codex Review: Didn't find any major issues. You're on a roll. 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". |
Unifies Coder Agents model selection on the shared searchable
ModelSelector, including personal root and subagent overrides plus advisor settings. Advisor model overrides can now select a supported reasoning effort while preserving fallback, unavailable, malformed, and disabled states.Adds versioned advisor configuration storage so legacy unversioned reasoning settings remain ignored, validates effort against the selected model, and applies it only when the explicit advisor model resolves. Dogfood UAT passed across advisor, personal override, create-chat, and active-chat picker flows.