🤖 feat: enable Astra Pro and advisor reasoning mode - #4106
Merged
Conversation
Enable GPT-6-Astra Pro on supported Responses routes and reuse the shared reasoning picker for advisor experiment settings. Persist advisor mode independently of effort and parent-chat mode, and pin provider route/wire options for safe request delivery. Validated with 522 targeted unit tests, 3 config IPC tests, 2 full-app story interactions, make static-check, and desktop/phone keyboard and persistence dogfooding. --- _Generated with [`mux`](https://github.com/coder/mux) • Model: `coder:openai/gpt-6-astra` • Thinking: `high`_ <!-- mux-attribution: model=coder:openai/gpt-6-astra thinking=high costs=11.03 -->
This comment has been minimized.
This comment has been minimized.
Member
Author
Member
Author
|
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". |
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f15e63a5f1
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".
Preserve capability-only advisor effort without applying chat minimums, reserve the full reasoning menu width, and document Astra Pro availability. Add effort-fidelity and menu-bound regressions plus tablet coverage. Validated with 388 targeted unit tests, 3 full-app stories, make static-check-full, and desktop/phone/tablet dogfood. --- _Generated with [`mux`](https://github.com/coder/mux) • Model: `coder:openai/gpt-6-astra` • Thinking: `high`_ <!-- mux-attribution: model=coder:openai/gpt-6-astra thinking=high costs=22.25 -->
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
Member
Author
Member
Author
This comment has been minimized.
This comment has been minimized.
Member
Author
|
Codex Review: Didn't find any major issues. Hooray! 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". |
This comment has been minimized.
This comment has been minimized.
Merged
yermakoffivan
pushed a commit
to yermakoffivan/mux
that referenced
this pull request
Sep 9, 2026
## Summary Version bump for the v0.28.5 patch release. Headline changes since v0.28.4: remote server connections in the desktop app (coder#4101), self-updating `xum server` under a restart supervisor (coder#4083, coder#4127), first-class GPT-6 Astra and Astra Pro support including Codex OAuth routing (coder#4064, coder#4094, coder#4106, coder#4124), token-budget context window rollovers (coder#4097), the workspace remembering model and mode on send (coder#3968), in-place plugin updates (coder#4164), the optional flat sidebar chat list (coder#3994), and copying selected chat text as Markdown (coder#4170). It also carries a long run of streaming, compaction, and task-lifecycle fixes (reconnect streaming coder#4123, message edits during active streams coder#4153, Codex OAuth prompt-cache routing coder#4159, compaction/history fencing coder#4133 through coder#4148, task lock ordering coder#4161) plus the Effect Wave 4 runtime refactors and deslop passes 1 through 3. ## Implementation Bumped with `node ./scripts/set-package-version.js 0.28.5` so the root `package.json` and the legacy `packages/mux-compat` forwarding package stay version-locked. `src/common/compat/productIdentity.test.ts` passes locally (8/8). After this PR merges, the `v0.28.5` tag will be applied to the squash commit and the GitHub Release published to trigger the desktop/npm/docker pipelines. --- _Generated with `xum` • Model: `anthropic:claude-fable-5-1` • Thinking: `xhigh` • Cost: `$1.64`_ <!-- mux-attribution: model=anthropic:claude-fable-5-1 thinking=xhigh costs=1.64 -->
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.
Summary
Enable GPT-6-Astra Pro mode and make Pro selectable independently of reasoning effort in Settings → Experiments → Advisor Tool.
Astra was explicitly excluded from the Pro capability check while launch documentation disagreed. Advisor configuration also lacked a saved reasoning mode. This adds Astra to the existing capability gate and reuses the shared route-aware reasoning picker rather than creating another settings control.
Validation
main;make static-check-fullpassed with the repository-pinned Bun 1.3.5 after review fixes.Provider payload serialization is covered with the real OpenAI SDK; no live provider calls were made. Pixel checks are excluded from merge-readiness evaluation at the requester's direction; responsive evidence is included below.
Dogfood evidence
Desktop
Phone
Keyboard and persistence walkthrough
advisor-low-pro-remount.webm
Generated with
mux• Model:coder:openai/gpt-6-astra• Thinking:high