Repository navigation
feat!: choose the computer use model per organization - #31300
Conversation
Docs previewCheck off each page once it's been reviewed. If a page changes in a later push, its checkbox clears automatically so it gets a fresh look. Pages not yet wired into the docs navigation aren't listed here. |
|
@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. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a02e48e8da
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. Nice work! 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". |
|
@codex review |
1 similar comment
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 53907308a4
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 |
1 similar comment
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7925be9d53
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 |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 2a01eafecf
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 |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 47f5bd11ba
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 |
1 similar comment
|
@codex review |
|
Codex Review: Didn't find any major issues. Keep them coming! 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". |
|
@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". |
Store agents_computer_use_ai_provider_id next to the computer-use provider type. The PUT endpoint validates that the selected AI provider exists, is enabled, and matches the type, and writes both settings in one audited transaction. chatd routes computer-use turns and the computer_use subagent key check to the selected provider, and reports computer_use unavailable when the selection is unusable. Without a selection, behavior is unchanged.
DanielleMaywood
left a comment
There was a problem hiding this comment.
This review was performed by ai-review, an automated review bot.
8 inline findings.
Coverage
Coverage: 47 of 63 files reviewed, 11 unsupported, 4 generated, 1 deleted; 22 rules.
Candidates: 2572 found, 2517 outside changed lines, 3 already discussed, 52 evaluated.
Findings: 8 (20 sites, 3 pre-existing sites), 0 over budget, 0 failed.
Model: deepseek/deepseek-v4.1-flash; 34 questions, 34 answered, 0 abstained, 34 cached; 0 uncalibrated findings held back; 0 input and 0 output tokens.
Experiments: 1 run, 0 passed, 1 vetoed, 0 unverified, 0 skipped for time.
vetoed: TYPE-1 site/src/pages/AISettingsPage/CoderAgentsPage/OrganizationAgentSettingsView.tsx:129: 1 new type error, first src/pages/AISettingsPage/CoderAgentsPage/OrganizationAgentSettingsView.tsx: TS2345 Argument of type 'string
@codex review |
|
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". |
DanielleMaywood
left a comment
There was a problem hiding this comment.
This review was performed by ai-review, an automated review bot.
1 inline finding.
Coverage
Coverage: 47 of 63 files reviewed, 11 unsupported, 4 generated, 1 deleted; 22 rules.
Candidates: 2557 found, 2517 outside changed lines, 4 already discussed, 36 evaluated.
Findings: 3 (4 sites, 0 pre-existing sites), 0 over budget, 0 failed.
Model: deepseek/deepseek-v4.1-flash; 32 questions, 32 answered, 0 abstained, 32 cached; 0 uncalibrated findings held back; 0 input and 0 output tokens.
Experiments: 1 run, 0 passed, 1 vetoed, 0 unverified, 0 skipped for time.
vetoed: TYPE-1 site/src/pages/AISettingsPage/CoderAgentsPage/OrganizationAgentSettingsView.tsx:129: 1 new type error, first src/pages/AISettingsPage/CoderAgentsPage/OrganizationAgentSettingsView.tsx: TS2345 Argument of type 'string
…d mutation declarations
Renumber 000634_chat_model_override_computer_use to 000635 because main added 000634_aibridge_interception_organization. The migration test now steps to 634 before applying the renumbered migration.
@codex review |
|
Codex Review: Didn't find any major issues. Keep it up! 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". |
…on settings without an IIFE
@codex review |
|
Codex Review: Didn't find any major issues. Delightful! 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". |
…TestMigrationChain step
@codex review |
|
Codex Review: Didn't find any major issues. Already looking forward to the next diff. 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". |
@codex review |
|
Codex Review: Didn't find any major issues. More of your lovely PRs please. 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". |
@codex review |
|
Codex Review: Didn't find any major issues. Can't wait for the next one! 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". |
Note
Xum opened this PR for Mike (Coder agent). Mike reviews it before merge.
Fixes CODAGT-1472.
Computer use now runs on a chat model that each organization picks. Before, it ran a fixed model on the first enabled AI provider of a deployment-wide provider type, sorted by name. On dogfood that provider's key is rejected, so every computer use subagent failed.
What changed
computer_useorganization model override, set in the Computer use row of Organization settings on the Coder Agents admin page. Without an override, computer use runs on the organization's default model. If the chosen model is disabled, deleted, or unusable for the chat owner, computer use falls back to the default model, as other overrides do. It also falls back when the chosen model moves to an AI provider that is not Anthropic or OpenAI, and the row then says that the saved model is ignored.PUT /api/v2/organizations/{organization}/chats/model-overrides/computer_usereturns 404 while thechat-virtual-desktopexperiment is off, and 400 unless the model's AI provider type is Anthropic or OpenAI.computer_usesubagent runs on that model, and the computer tool flavor follows the model's provider type. OpenAI computer use always uses the Responses API, so a model that setsuse_responses_api: falsegets a configuration error. When no usable model exists,computer_useis unavailable, and the reason says whether a saved computer use model was skipped and why the default model cannot be used. The default model is read under the chat owner's model ACLs, as chat turns do.knownComputerUseModelsinknownModels/catalog.ts, exact match only). It also appears when the model's AI provider type is OpenAI and its Use Responses API override is Off, because OpenAI computer use needs the Responses API. The warning does not block saving. I built the list from a live probe on 2026-10-26 that sent each Anthropic and OpenAI model one request with the computer tool.virtual-desktop.md,models.md,organizations.md, andarchitecture.mddescribe the new setting, and chatd'sARCHITECTURE.mddescribes the computer use model routing.Breaking change
This removes the deployment-wide computer use provider setting (
agents_computer_use_provider), its experimentalGET/PUT /api/experimental/chats/config/computer-use-providerendpoints (shipped since v2.35), the Virtual desktop settings card, and its audit field. Migration 000635 deletes the stored value. After the upgrade, computer use runs on each organization's default model until an admin picks a computer use model. Computer use subagents created before the upgrade keep the model they inherited from their parent chat, so a follow-up message to one of them can fail; a new computer use subagent uses the organization's computer use model. Telemetry now reports the per-organization overrides instead of the provider, andnullwhen it cannot read them.Testing
make pre-commitpasses.go testpasses for./coderd/x/chatd/...,./coderd/database/migrations/, and the targeted coderd, telemetry, dbauthz, enterprise audit, and codersdk tests. Vitest and the touched Storybook stories pass.