feat: track Cursor local storage

[steipete]

Summary

• add Cursor application data, CLI/config, and cache roots to optional provider storage tracking
• include current ToDesktop bundle and updater cache locations while retaining the legacy Cursor cache path
• document the read-only storage footprint behavior and add focused path-catalog coverage

Closes #1403.

Proof

• swift test --filter ProviderStorageFootprintTests — 16/16 passed
• make check — SwiftFormat/SwiftLint clean
• branch autoreview — clean after adding the installed Cursor bundle-ID cache paths (gpt-5.5, confidence 0.86)
• local installation confirms com.todesktop.230313mzl4w4u92 and .ShipIt cache roots

Risk

Low. Storage tracking is opt-in, scans on the existing detached utility-priority path, and remains read-only.

[clawsweeper]

Codex review: needs maintainer review before merge. Reviewed June 11, 2026, 11:39 PM ET / 03:39 UTC.

Summary
Review failed before ClawSweeper could summarize the requested change.

Reproducibility: unclear. The review failed before ClawSweeper could establish a reproduction path.

Review metrics: none identified.

Merge readiness
Overall: 🌊 off-meta tidepool
Proof: 🌊 off-meta tidepool
Patch quality: 🌊 off-meta tidepool
Result: rating does not apply to this item.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Risk before merge

• [P1] No close action taken because the review did not complete.

Maintainer options:

1. Decide the mitigation before merge
   Retry the Codex review after fixing the execution failure.
2. Pause or close
   Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

• Review did not complete, so no work-lane recommendation was made.

Review details

Best possible solution:

Retry the Codex review after fixing the execution failure.

Do we have a high-confidence way to reproduce the issue?

Unclear. The review failed before ClawSweeper could establish a reproduction path.

Is this the best way to solve the issue?

Unclear. Retry the review first so ClawSweeper can evaluate the actual issue and fix direction.

AGENTS.md: unclear because the file could not be read completely.

Codex review notes: model internal, reasoning high; reviewed against 9b22e65bbc91.

Label changes

Label changes:

• remove P3: Current review triage priority is none.

Label justifications:

• rating: 🌊 off-meta tidepool: Overall readiness is 🌊 off-meta tidepool; proof is 🌊 off-meta tidepool and patch quality is 🌊 off-meta tidepool.

Evidence reviewed

What I checked:

• failure reason: retryable codex transport failure (capacity)
• codex failure detail: Codex review failed for this PR with exit 1.
• codex stderr: _typename":"CheckRun","completedAt":"0001-01-01T00:00:00Z","conclusion":"","detailsUrl":"https://github.com/steipete/CodexBar/actions/runs/27392809835/job/80953833263","name":"build-linux-cli (linux-x64, ubuntu-24.04)","startedAt":"2026-06-12T03:36:18Z","status":"IN_PROGRESS","workflowName":"CI"},{"__typename":"CheckRun","completedAt":"0001-01-01T00:00:00Z","conclusion":"","detailsUrl":"https://github.com/steipete/CodexBar/actions/runs/27392810991/job/80953836528","name":"build-linux-cli (linux-arm64, ubuntu-24.04-arm)","startedAt":"2026-06-12T03:36:20Z","status":"IN_PROGRESS","workflowName":"CI"},{"__typename":"CheckRun","completedAt":"0001-01-01T00:00:00Z","conclusion":"","detailsUrl":"https://github.com/steipete/CodexBar/actions/runs/27392809835/job/80953833248","name":"build-linux-cli (linux-arm64, ubuntu-24.04-arm)","startedAt":"2026-06-12T03:36:17Z","status":"IN_PROGRESS","workflowName":"CI"},{"__typename":"CheckRun","completedAt":"2026-06-12T03:36:19Z","conclusion":"SUCCESS","detailsUrl":"https://dashboard.gitguardian.com","name":"GitGuardian Security Checks","startedAt":"2026-06-12T03:36:16Z","status":"COMPLETED","workflowName":""}]}.
• codex stdout: No stdout captured.

Likely related people:

• unknown: Codex failed before it could trace repository history. (role: review did not complete; confidence: low)

What the crustacean ranks mean

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f4649eef22

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".

[chatgpt-codex-connector]

Include Cursor's updater cache root

This cache list still misses Cursor's updater payload directory at ~/Library/Application Support/Caches/cursor-updater (I checked the current macOS Cursor uninstall/cleanup recipe, which removes it separately from ~/Library/Application Support/Cursor and the ~/Library/Caches/com.todesktop.* roots). When a failed or pending updater download is what is consuming space, the optional storage footprint will underreport Cursor's local usage even though this change says it tracks the updater caches.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 02294e3411

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".

[chatgpt-codex-connector]

Include Cursor HTTP storage caches

On macOS installs where Cursor's ToDesktop shell accumulates response cache data under ~/Library/HTTPStorages/com.todesktop.230313mzl4w4u92 (the current Cursor macOS cleanup recipe removes ~/Library/HTTPStorages/com.todesktop.* alongside these ToDesktop cache roots), this new catalog still reports little or no Cursor storage after the listed paths are scanned. Since the feature is meant to account for Cursor's local caches, add the matching HTTPStorages root so the optional footprint does not underreport users' local Cursor data.

Useful? React with 👍 / 👎.