🤖 feat: add Mux Extension Platform v1#3255
Conversation
|
/coder-agents-review |
|
@codex review |
![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: 78225309f0
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".
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
![coder-agents-review[bot]](https://avatars.githubusercontent.com/in/3454270?s=60&v=4){kind=small}
There was a problem hiding this comment.
First-pass review (Netero only). These are mechanical findings from the first-pass scan. The full review panel has not yet reviewed this PR. The panel will review after these findings are addressed.
Severity count: 2 P2, 1 P3, 1 Nit, 1 Note.
The extension platform is well-structured: broad test coverage (~51% test-to-code ratio), clean error handling patterns, no circular imports, and thoughtful domain modeling. The architecture separates concerns cleanly across common/node/browser layers.
"TypeScript structural typing makes the mismatch compile-safe, but the displayName and extensionId fields from the registry are silently dropped by every consumer." (Netero)
🤖 This review was automatically generated with Coder Agents.
|
/coder-agents-review |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 782fdaeb28
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".
|
/coder-agents-review |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 782fdaeb28
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".
|
/coder-agents-review |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: efc6c71a1f
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".
There was a problem hiding this comment.
Panel review (10 reviewers: Bisky, Hisoka, Kite, Knov, Mafuuu, Melody, Meruem, Nami, Pariston, Zoro). All 5 R1 Netero findings addressed; thank you for the quick fixes.
Severity count: 1 P1, 5 P2, 7 P3, 2 Nit.
The architecture is well-designed: clean domain model separation, strong test coverage (51% ratio), thoughtful conflict resolution, and principled ADRs. The permission model, telemetry gating, and path containment are solid foundations.
The P1 is surgical: PolicyFileSchema.passthrough() was the only schema loosened while all others remain strict. The P2s cluster around scope-blind stale detection, async UI coordination, and accessibility. Most P3s are correctness-in-future-scenarios (multi-root, identity conflicts) that are latent in v1 but worth fixing before the code fossilizes.
"A Governor administrator who fat-fingers
extensionPlatfrom: falsepreviously got a parse error. Now it passes, the intended kill switch never fires, and the extension platform runs unblocked on a managed fleet." (Hisoka)
🤖 This review was automatically generated with Coder Agents.
There was a problem hiding this comment.
Round 3 is blocked. Further review is paused until the author responds to or pushes fixes for the open findings from Round 2.
DEREM-6 (P3, initialize user root) and DEREM-8 (P2, scope-blind stale records) were addressed in efc6c71. Thank you.
The following findings remain open with no response:
- DEREM-7 (P1): PolicyFileSchema
.strict()to.passthrough()(policy.ts:81). The security kill switch typo gap. - DEREM-9 (P2): wrapBusy async race (ExtensionCard.tsx:512)
- DEREM-10 (P2): aria-modal without focus trap (ConsentShortcutModal.tsx, DestructiveConfirmDialog.tsx, ExtensionsCheatSheetModal.tsx)
- DEREM-11 (P2): projectExtensionStateService non-atomic read-then-write (projectExtensionStateService.ts:60)
- DEREM-12 (P2): resolveScopeByRootId maps bundled to global scope (extensionRegistryService.ts:251)
- DEREM-13 (P3): permissions map keyed by extensionId alone
- DEREM-14 (P3): extensionRootWatcher scheduleReload missing closed check
- DEREM-15 (P3): homepage link no protocol validation
- DEREM-16 (P3): no loading state for extensions section
- DEREM-17 (P3): cheat sheet modal no Escape handler
- DEREM-18 (P3): onChanged multicast test 10ms sleep fragility
- DEREM-19 (P3): runReloadRoot stale flags from spliced roots
- DEREM-20 (Nit): useCallback/useMemo vs React Compiler convention
- DEREM-21 (Nit): dead manifest-invalid UnavailableReason variant
🤖 This review was automatically generated with Coder Agents.
|
/coder-agents-review |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 15c9e0283c
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".
|
/coder-agents-review |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7e95e2ef3a
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".
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7e95e2ef3a
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".
|
/coder-agents-review |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 78bfd470c6
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".
There was a problem hiding this comment.
Re-review (4 reviewers: Mafuuu, Meruem, Nami, Kite). All 14 R2 fixes verified clean. DEREM-20 (useCallback/useMemo) closed by panel vote (2/2 accept author defense).
Severity count: 2 P2, 5 P3.
The R3/R4 fix commits addressed every P1 and P2 from Round 2 correctly. The new findings cluster around a common root: the multi-root improvements (efc6c71) added support for multiple project-local roots in rendering (getRootSections), but the keyboard navigation, trust shortcuts, and permission lookup paths still assume at most one project-local root. These are fix-chain artifacts from the DEREM-8/DEREM-19 fixes that broadened root enumeration.
The keyboard-behind-modal finding (DEREM-31) is the highest priority: the consent modal is a security-consent surface, and having the section shortcut handler execute r (reload), e (enable), t (trust) behind it undermines the consent flow.
"Pressing J to navigate: the focus ring moves through bundled, user-global, and the first project-local root's extensions, then stops. Extensions from the second project-local root are visible on screen but unreachable via keyboard." (Mafuuu)
🤖 This review was automatically generated with Coder Agents.
There was a problem hiding this comment.
Round 5 is blocked. Further review is paused until the author responds to or pushes fixes for the open findings from Round 4.
DEREM-33 (lookupLiveRequestedPermissions) and DEREM-34 (conflict descriptor) were addressed. Thank you.
The following findings remain open with no response:
- DEREM-30 (P2):
orderedExtensionsonly traverses first project-local root; J/K navigation skips the rest (ExtensionsSection.tsx:746) - DEREM-31 (P2): Keyboard handler fires behind open consent/destructive modals (ExtensionsSection.tsx:770)
- DEREM-28 (P3):
reloadRoot(rootId)name claims targeted but is full reload (extensionRegistryService.ts:292) - DEREM-32 (P3): Trust shortcut targets only first project-local root (ExtensionsSection.tsx:760)
- DEREM-35 (P3):
body-failedcondition changed with zero test coverage (extensionRegistryService.ts:639) - DEREM-36 (P3): Modals lack focus trapping; Tab escapes to background (ConsentShortcutModal.tsx:74)
🤖 This review was automatically generated with Coder Agents.
|
/coder-agents-review |
|
@codex review Addressed the registration capability approval feedback:
Validation:
|
|
@codex review Addressed the draft module watcher feedback by watching valid module-name child directories even before Validation:
|
|
Codex Review: Didn't find any major issues. 🚀 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 Follow-up: made the palette subscription-order test deterministic by extracting the subscribe-then-fetch sequence into a small helper and testing that helper directly, avoiding React effect scheduling delays seen in the full remote unit suite. Validation:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ab59970168
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 Addressed the Quick Setup rollback trust finding by no longer calling Validation:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 42edba78b8
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 Addressed the reserved first-party Extension Name feedback by rejecting non-bundled static manifests whose folder/name uses the reserved Validation:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e583fbb69f
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 Addressed the CLI scaffold reserved-name feedback by applying the same reserved Validation:
|
|
Codex Review: Didn't find any major issues. What shall we delve into next? 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 Pushed a follow-up that fixes full unit-suite isolation failures: restoring mocked modules after test files and avoiding an eager rejected mock promise in the workspace fork test. |
|
Codex Review: Didn't find any major issues. You're on a roll. 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 Pushed a follow-up for the CI-only unit timeout: ImmersiveReviewView tests now mock diff highlighting so the line-budget regression test does not wait on the Shiki worker under CI. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 505e6e37a8
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".
|
Addressed latest Codex finding:
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 15887f14db
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".
|
Addressed latest Codex finding:
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: bcf81e6585
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".
|
Addressed latest Codex finding:
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b496a26323
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".
|
Addressed latest Codex finding:
@codex review |
|
Codex Review: Didn't find any major issues. Nice work! 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 Pushed a follow-up for the unit failure on the latest head: the line-budget ImmersiveReviewView regression now uses a |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a897fc223f
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".
|
Addressed latest Codex finding:
@codex review |
|
Codex Review: Didn't find any major issues. Already looking forward to the next diff. 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 Pushed a follow-up for the latest unit failures: the long-running boundary tests now have explicit 10s Bun timeouts, and the ImmersiveReviewView line-budget test still uses a text fixture to avoid highlighter work while exercising the 1500-line boundary. |
|
Codex Review: Didn't find any major issues. Keep it up! 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". |
1 participant
Summary
Adds the Mux Extension Platform v1 behind the
EXTENSION_PLATFORMexperiment and documents the platform's architectural pivot to Extension Modules: extension folders with a singleextension.ts, statically extractable manifests, QuickJS-based discovery/activation, skill-style root precedence, source locks, and Mux-owned trust/capability state. The implementation is now partially refactored toward that model: trusted roots can discover direct child Extension Module folders via staticextension.tsmanifest extraction, local authoring roots use~/.mux/extensions/local, and source-lock schemas now model git/vendored extension sources without carrying trust state.Background
This PR grew out of the need to consolidate Mux's extension surfaces across skills, tools, agents, policies, themes, and future runtime contributions. During review, the design moved away from npm-package identity and repo-stored project approvals toward a Go-modules-like Extension Module model. The updated docs capture that decision, the code hardens the current scaffold so repositories cannot provide security authority, and the latest slices begin moving discovery/root layout/source metadata from package manifests to static Extension Module manifests and locks.
Implementation
extension.tsmanifest extraction forexport const manifest = defineManifest({ ... })or a literal object export, rejecting dynamic manifest values without executing extension code.extension.ts, including folder-name validation,manifest.namemismatch diagnostics, project-local pre-trust no-read behavior, and static capability validation.~/.mux/extensions/localand updatesinitializeUserRootto create that folder instead of a package-rootpackage.json.bun run debug extensions.agent_skill_*tool reads, including hardened skill-body reads that reject symlinks and TOCTOU path swaps.extension.ts) as the target architecture.~/.mux/extensions/project-state/<project-hash>/, not inside the target repository.Validation
make static-checkmake test -j1bun test src/node/extensions/extensionRoots.test.ts src/node/orpc/extensionsRouter.test.ts src/common/extensions/sourceLocks.test.ts src/node/extensions/staticManifestExtractor.test.ts src/node/extensions/extensionDiscoveryService.test.tsbun test src/common/extensions/conflictResolver.test.ts src/common/extensions/permissionCalculator.test.tsbun test src/node/extensions/bundledExtensionsAssemble.test.tsbun test src/node/extensions/projectExtensionStateService.test.tsbun test src/node/orpc/extensionsRouter.test.tsbun test src/cli/debug/extensions.test.tsbun test src/browser/features/Settings/Sections/ExtensionCard.test.tsx src/browser/features/Settings/Sections/ExtensionsSection.test.tsxRisks
This is a large additive subsystem touching startup wiring, settings UI, package assembly, telemetry, and skill discovery. The primary rollback lever is the default-on
EXTENSION_PLATFORMexperiment. The highest remaining architectural risk is that full QuickJS Registration Discovery/Full Activation and git install/store materialization are still follow-up work; the current module-discovery slice intentionally publishes no module-registered skills until that runtime path exists.Pains
This PR required several review and merge cycles: resolving older security findings, integrating concurrent
mainchanges around heartbeat/image-generation skill filtering, aligning extension skill IDs with agent skill schemas, moving project extension state out of repositories after review identified the trust-injection vulnerability, and beginning the package-to-Extension-Module refactor while preserving transitional compatibility.Generated with
mux• Model:openai:gpt-5.5• Thinking:off• Cost:$916.09