[WRONG BRANCH] fix(cursor): fail closed for raw shell tool choices

[luvs01]

Motivation

• Close an authorization regression where raw exec_command/shell_command tool_choice names could match namespaced MCP tools when the bare Codex shell bridge was absent, allowing an untrusted model to gain unintended shell-like MCP execution access.

Description

• Change cursorToolChoiceMatches to require a bare Codex shell bridge for raw shell_command/exec_command choices and to fail closed when the bare bridge is not present, while preserving explicit namespaced wire-name matching.
• Update cursorToolAllowedByChoice to stop delegating to the relaxed catalog-aware matcher and call the hardened matcher consistently, renaming the unused catalog parameter to _catalog.
• Adjust tests in tests/cursor-tool-choice.test.ts to assert that raw exec_command/shell_command choices do not advertise namespaced MCP tools when the bare bridge is absent, and keep coverage for explicit wire-name selection and the bare-bridge cases.
• Files changed: src/adapters/cursor/tool-definitions.ts and tests/cursor-tool-choice.test.ts.

Testing

• Ran the focused regression tests with bun test tests/cursor-tool-choice.test.ts, which passed (7 tests).
• Ran type checking with bun run typecheck, which succeeded.
• Ran privacy scan with bun run privacy:scan, which succeeded.
• Attempted the full test suite with bun run test, which exhibited unrelated timeouts/failures in other management tests; the focused cursor regression and static checks passed despite the unrelated suite instability.

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, add credits to your account and enable them for code reviews in your settings.

[coderabbitai]

Warning

Review limit reached

@luvs01, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 57 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 41b006cb-277b-41ef-a2ad-3430829f5d17

📥 Commits

Reviewing files that changed from the base of the PR and between e3b2d6e and db94425.

📒 Files selected for processing (2)

• src/adapters/cursor/tool-definitions.ts
• tests/cursor-tool-choice.test.ts

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

✅ Deterministic PR hygiene checks passed.

[github-actions]

⏳ DRAFT

• wrong target branch (main); retarget to dev.

What to do

• Retarget this PR to dev — all contributions go to dev.

Its title has been prefixed with [WRONG BRANCH].
This pull request was already a draft. Its draft status will be preserved after every issue above is resolved.