Add Grok Bot Support to Cursor Card - #3127
Conversation
Grok Bot is billed on the Cursor session, so surface it as a fourth Cursor card bar instead of a separate provider. Co-authored-by: Cursor <cursoragent@cursor.com>
|
🦞👀 Pull request received. I will update this pull request when review starts. |
![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: a88820af65
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Cap the best-effort Sand request at 5s and do not fail Cursor login after usage-summary has already succeeded. Co-authored-by: Cursor <cursoragent@cursor.com>
clawsweeper
Bot
added
merge-risk: 🚨 auth-provider
|
Codex review: needs maintainer review before merge. Reviewed August 21, 2026, 7:07 PM ET / 23:07 UTC. ClawSweeper reviewWhat this changesThis PR adds a best-effort Cursor dashboard request that renders eligible Grok Bot weekly usage as an extra Cursor card and widget bar. Merge readinessKeep open for maintainer review. Current main does not contain this feature, and the current head addresses the earlier optional-fetch failure concern; the remaining question is whether default polling of Cursor’s dashboard endpoint with an existing session is an acceptable product and provider-contract tradeoff. Priority: P2 Review scores
Verification
Live VerificationCommand: Result: FAIL (failed) — execution before step 1 Assertions:
How this fits togetherCodexBar converts authenticated Cursor usage responses into common usage windows for the menu card, menu-bar metric, and widget. This change adds an optional Cursor-owned weekly allowance while retaining the existing monthly usage lanes. flowchart LR
A[Cursor session cookie] --> B[Cursor usage requests]
B --> C[Monthly usage summary]
B --> D[Grok Bot weekly status]
C --> E[Cursor usage snapshot]
D --> E
E --> F[Menu card]
E --> G[Widget rows]
Decision needed
Why: Only maintainers can accept the ongoing authenticated upstream-contract and availability tradeoff for all Cursor users. Before merge
Agent review detailsSecurityNone. Review metrics
Merge-risk optionsMaintainer options:
Technical reviewBest possible solution: Keep Grok Bot as a Cursor-owned optional usage window, with the same-session request bounded and fail-soft, if maintainers accept the upstream endpoint contract. Do we have a high-confidence way to reproduce the issue? Not applicable: this is an additive provider-usage feature, and the PR supplies direct post-change menu-card evidence rather than a bug report. Is this the best way to solve the issue? Yes, conditional on maintainer approval of the endpoint contract: representing the allowance as a Cursor extra window avoids a duplicate provider and preserves the monthly lanes on failure. AGENTS.md: found and applied where relevant. Codex review notes: model internal, reasoning high; reviewed against 95afa63a5e8c. LabelsLabel justifications:
EvidenceWhat I checked:
Likely related people:
Rank-up movesOptional improvements that raise the rating; they are not merge blockers.
Rating scale
Overall follows the weaker of proof and patch quality. Workflow
HistoryReview history (1 earlier review cycle)
|
2 participants
Summary
POST /api/dashboard/get-sand-usage-statuswith the same Cursor session cookie. This is not a new provider and not the existing Grok CLI provider.hasNonZeroIncludedLimit: false) omit the bar. Sand fetch failures leave the monthly Cursor bars intact.Test plan
make checkmake test(77/77 groups)Commands run
make checkmake test./Scripts/compile_and_run.sh