Stream Cursor Cloud Agent chat updates with richer empty-result errors

[Modsofthenation]

Summary

AI Chat with the Cursor Cloud Agents provider used to block until the run finished, then show a bare Cursor Cloud Agent finished with empty result when run.result was blank.

This change:

1. Streams Cloud Agent status + assistant text via the official /runs/{id}/stream SSE API into AI Chat
2. Recovers reply text from streamed assistant deltas when the terminal result field is empty
3. Improves empty-result errors with agent id, run id, duration, and a link to open the Cloud Agent transcript

JSON POST /api/ai/chat remains supported; the UI requests Accept: text/event-stream and falls back if needed. Polling is still used when the stream endpoint is unavailable (e.g. 410).

Test plan

• pnpm --filter @prm/api exec tsx --test src/ai.cursor.test.ts
• pnpm --filter @prm/api typecheck
• pnpm --filter @prm/ui typecheck
• Manual: Settings → AI → Cursor Cloud Agents → AI Chat over workspace; confirm live status/text while waiting
• Manual: confirm empty-result failures now include agent/run details + “Open Cloud Agent run” when a URL is known

  

[coderabbitai]

Warning

Review limit reached

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

Next review available in: 58 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: fa27f1e3-06dd-460d-aae0-0af58349545f

📥 Commits

Reviewing files that changed from the base of the PR and between 2e32ebe and 7a88f98.

📒 Files selected for processing (9)

• CHANGELOG.md
• apps/api/src/ai.cursor.test.ts
• apps/api/src/ai.ts
• apps/api/src/cursorCloud.ts
• apps/api/src/index.ts
• apps/ui/src/lib/api.ts
• apps/ui/src/pages/ChatPage.tsx
• apps/ui/src/styles.css
• docs/ai/AI_INTEGRATION.md

---

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