Add Cursor Cloud Agents AI provider support

[Modsofthenation]

Summary

Settings → AI can now use Cursor Cloud Agents with dashboard crsr_… keys. Digests and drafts launch a short-lived no-repo agent via https://api.cursor.com/v1 (not OpenAI chat completions).

Changes

• New cursorCloud.ts client: create agent → poll run → return result → archive
• Provider Cursor Cloud Agents (cursor) uses that path; models blank = account default
• OpenAI-compatible (custom URL) is a separate provider (openai_compatible)
• Legacy provider=cursor + gateway URL still maps to OpenAI-compatible until re-saved
• Saving Cursor Cloud Agents clears any leftover gateway URL so it is not mis-detected as OpenAI-compatible
• Test AI for Cloud Agents probes GET /v1/me (fast key check)
• Docs + changelog updated

Notes

Cloud Agents are slower than Anthropic/OpenAI chat (async agent runs). Prefer those for interactive writing-desk latency; Cursor is for users who already have Cursor API keys.

Verification

• pnpm --filter @prm/api exec node --import tsx --test src/ai.cursor.test.ts (7 pass)
• pnpm --filter @prm/api typecheck
• pnpm --filter @prm/ui typecheck

  

Summary by CodeRabbit

• New Features

  • Added support for Cursor Cloud Agents, including dashboard keys, no-repository agent runs, status tracking, and result retrieval.
  • Added support for OpenAI-compatible gateways with provider-specific settings, models, and connection testing.
  • Settings now show clearer provider descriptions, key guidance, optional test samples, and environment-key availability.

• Bug Fixes

  • Improved provider detection, gateway handling, Cursor authentication checks, and connection-test errors.
  • Added clearer Desktop AI network error and save-then-test status messaging.

• Documentation

  • Updated AI integration and feature documentation for Cursor Cloud Agents and OpenAI-compatible gateways.

[coderabbitai]

Warning

Review limit reached

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

Next review available in: 22 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: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 63a763d8-0a92-49ae-b609-1355c29710ee

📥 Commits

Reviewing files that changed from the base of the PR and between 22cf073 and 6dbf3bf.

📒 Files selected for processing (9)

• CHANGELOG.md
• apps/api/src/ai.cursor.test.ts
• apps/api/src/ai.ts
• apps/api/src/aiEstimate.ts
• apps/api/src/cursorCloud.ts
• apps/api/src/index.ts
• apps/ui/src/pages/SettingsPage.tsx
• docs/ai/AI_INTEGRATION.md
• docs/product/FEATURES.md

📝 Walkthrough

Walkthrough

This change adds Cursor Cloud Agents as a separate AI provider. It adds agent execution, provider normalization, connection probing, settings UI updates, tests, pricing defaults, and documentation for Cursor Cloud and OpenAI-compatible gateways.

Changes

Cursor Cloud Agents integration

Layer / File(s)	Summary
Cursor Cloud agent client apps/api/src/cursorCloud.ts, apps/api/src/ai.cursor.test.ts	Adds no-repository agent creation, run polling, result extraction, timeout handling, archival, and lifecycle tests.
Provider normalization and API routing apps/api/src/ai.ts, apps/api/src/index.ts, apps/api/src/aiEstimate.ts, apps/api/src/ai.cursor.test.ts	Separates Cursor Cloud from OpenAI-compatible providers, resolves legacy settings, probes Cursor keys, routes chat requests, and updates model and pricing defaults.
Provider settings and connection testing apps/ui/src/pages/SettingsPage.tsx	Adds provider-specific fields, labels, placeholders, defaults, save behavior, and connection-test samples.
Documentation and release notes docs/ai/AI_INTEGRATION.md, docs/product/FEATURES.md, CHANGELOG.md	Documents Cursor Cloud Agents, dashboard keys, no-repository agents, environment variables, account-default models, and gateway separation.

Estimated code review effort: 4 (Complex) | ~45 minutes

Sequence Diagram(s)

sequenceDiagram
  participant SettingsUI
  participant API
  participant CursorCloud
  SettingsUI->>API: Save Cursor provider and test connection
  API->>CursorCloud: Probe /v1/me with configured key
  CursorCloud-->>API: Return account and model information
  API-->>SettingsUI: Return provider, model, base URL, and sample

Loading

Possibly related PRs

• Modsofthenation/PerformanceReviewManager#40: Both changes modify AI connection handling in the API and settings UI.
• Modsofthenation/PerformanceReviewManager#60: This change extends the related provider and base-URL handling with Cursor Cloud Agents support.

Suggested reviewers: cursoragent

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch cursor/cursor-cloud-agents-ebae

---

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