Skip to content
TheChatArchiveThe Chat Archive
Claudeclaude-sonnet-5· anthropicHugging Face ibragim-bad/swe_rebench_07_2026_trajectories

ISSUE DESCRIPTION [Bug]: Cursor CLI agent stays in loading state after task completes…

  1. User

    ISSUE DESCRIPTION

    [Bug]: Cursor CLI agent stays in loading state after task completes

    Operating system

    macOS

    Orca version

    Unknown (please add from Orca > About Orca if available)

    Details

    Summary

    When running a Cursor CLI agent session in Orca, the UI continues to show a loading/running state after the agent has finished its task — as if work is still in progress.

    Steps to reproduce

    1. Start a Cursor CLI agent session in Orca.
    2. Give the agent a task and wait for it to complete (agent finishes and produces final output).
    3. Observe the session UI state.

    Expected behavior

    Once the Cursor CLI agent finishes, the session should transition to an idle/completed state — loading indicators should stop and the UI should reflect that no work is in progress.

    Actual behavior

    The session remains in a loading/running state after the task is done, giving the impression the agent is still working.

    Environment

    • macOS: darwin 25.4.0
    • Agent: Cursor CLI

    Additional notes

    • Reproduces when the agent has clearly finished (final response delivered) but Orca does not update the activity/loading indicator accordingly.
    • May cause confusion about whether it is safe to send a follow-up prompt or close the session.

    Evaluation contract

    When a synthetic-title agent reports a non-working state, reconcile the terminal title with that agent's synthetic title profile. For Cursor, done replaces spinner/working titles, the bare Cursor Agent title, and stale permission titles with Cursor ready; waiting or blocked uses Cursor - action required. Preserve descriptive completed titles that are not classified as working or permission, and do not rewrite agents without a synthetic-title profile. Apply this resolver before storing agent-status snapshot titles.

    Interface

    Type: Function Name: resolveAgentStatusTerminalTitle Path: src/renderer/src/lib/agent-status-terminal-title.ts Input: payload: Pick<ParsedAgentStatusPayload, 'agentType' | 'state'>, currentTitle: string | undefined Output: string | undefined Description: Reconciles hook-reported state with synthetic terminal-title profiles. For Cursor, done maps stale spinner, working, bare native, or permission titles to "Cursor ready"; waiting/blocked maps to "Cursor - action required". Descriptive completed titles and agents without a synthetic profile are preserved. The IPC status integration must call this resolver before storing the title.

    ADDITIONAL ADVICE

    Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use git checkout <file> to restore the file to its original state. You can also reset all changes in the repository using git reset --hard command. Additionally, you can use git stash and git stash pop to temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you call submit) using git status or git diff commands. However you don't need to use git add or git commit before submitting your changes. In fact, submit only submits currently unstaged changes because it uses git diff to get the changes that need to be submitted.

    CHECKLIST

    Before submitting your solution, please go over the following checklist and make sure you've done everything:

    • If an error was reported in the issue description, I have successfully reproduced it.
    • If an error was reported in the issue description, I have confirmed that my fix resolves the error.
    • I have thought about edge cases and made sure my fix handles them as well.
    • I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.

    Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!

    (Current directory: /orca, current file: none) bash-$

  2. Claude Assistant

    Now let's look at store.setAgentStatus in the agent-status slice, to see how terminalTitle gets stored.

  3. Claude Assistant

    Need to place the probe test under src/. Let's put it in src/shared temporarily.

  4. Claude Assistant

    Good, lowercase 'cursor' is used consistently, matches SYNTHETIC_TITLE_PROFILES keys. Now let's create the new file.

  5. Claude Assistant

    Now let's wire this into useIpcEvents.ts before store.setAgentStatus call.

  6. Claude Assistant

    All pass. Now let's remove the temp test and run existing related tests.

  7. Claude Assistant

    All existing relevant tests pass, including useIpcEvents.test.ts. Now let's check the diff.

  8. Claude Assistant

    They use oxlint, not eslint. Let's run that instead.

  9. Claude Assistant

    Clean. Now let's run the full oxlint over the whole repo quickly for a sanity check, and try a scoped typecheck limited to these two files if possible using tsc --noEmit directly rather than tsgo full project (to speed up). Let's check tsconfig for renderer.

  10. Claude Assistant

    No errors reported — typecheck passed cleanly.

  11. Claude Assistant

    Clean typecheck. Now let's view the final diff and the new file content once more for review.

  12. Claude Assistant

    This looks solid. Let's now run the broader renderer test suite briefly to catch any regression (at least a good chunk related to terminal-pane and store).

  13. Claude Assistant

    All 354 test files / 3526 tests pass. Let's double-check that git status reflects only intended changes and clean up any leftovers.

  14. Claude Assistant

    Clean. Now let's go through the checklist explicitly.

  15. Claude Assistant

    Checklist review:

    • Reproduced the reported error: The issue is a UX bug (stale loading state) without a crash/exception to reproduce via stack trace. I traced the actual mechanism (main process synthesizes OSC titles for Cursor via driveSyntheticTitleFromHook, which the renderer's useIpcEvents caches onto AgentStatusEntry.terminalTitle) and identified the race/staleness window described in the evaluation contract. I verified the before behavior conceptually (the old code passed the raw, possibly-stale title straight to store.setAgentStatus with no reconciliation against the hook-reported state) and confirmed with targeted unit tests that, prior to my change, no such reconciliation function existed at all.
    • Confirmed the fix resolves it: I wrote temporary tests exercising resolveAgentStatusTerminalTitle for all the contract's cases (stale spinner/working title, bare native title, stale permission title, waiting/blocked, descriptive completed titles, agents without a profile, undefined title) — all passed — then wired the resolver into useIpcEvents.ts right before store.setAgentStatus, so a done hook event now always reconciles a lagging Cursor title to "Cursor ready" instead of leaving a stale working/permission title cached.
    • Edge cases: undefined currentTitle, agents without a synthetic profile (returned unchanged), working state left untouched (spinner mechanism owns it), descriptive completed titles preserved, waiting/blocked always forced to the permission label, and case-insensitive/trimmed matching for the bare native title.
    • Existing tests: Ran the full relevant suites (store, hooks, lib, components/terminal-pane, shared) — 354 files / 3526 tests all passed — plus oxlint (0 warnings/errors) and the project's tsgo web typecheck (clean, no errors). Temporary test file was removed before submission per instructions.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.