Untitled conversation
- User
[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
- Start a Cursor CLI agent session in Orca.
- Give the agent a task and wait for it to complete (agent finishes and produces final output).
- 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,
donereplaces spinner/working titles, the bareCursor Agenttitle, and stale permission titles withCursor ready;waitingorblockedusesCursor - 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.
- Assistant
Investigating how agent status and terminal titles are handled so we can implement the title resolver and fix the stuck loading state.
- Assistant
Implementing the title resolver and integrating it into the IPC status path.
- Assistant
Simplifying the implementation — the last block was redundant.
- Assistant
Fixed the stuck loading state by reconciling hook-reported agent state with synthetic terminal titles before storing the agent-status snapshot.
Root cause
Cursor CLI keeps emitting stale OSC titles (spinner frames like
⠋ Cursor Agent, the bare nativeCursor Agent, or permission titles) even after the hook reportsdone. Those titles were stored as-is inagentStatusByPaneKey.terminalTitle, so parts of the UI that read the title still treated the session as working.Fix
Added
resolveAgentStatusTerminalTitleinsrc/renderer/src/lib/agent-status-terminal-title.tsand wired it into the IPC status path inuseIpcEvents.tsbeforesetAgentStatusruns.For agents with synthetic title profiles (Cursor, OpenCode, Droid, Hermes):
Hook state Title reconciliation doneReplace stale spinner, working, bare native, or permission titles with the idle label ( Cursor ready, etc.); preserve descriptive completed titleswaiting/blockedMap to the permission label ( Cursor - action required, etc.)workingLeave the current title unchanged Agents without a synthetic profile (Codex, Claude, etc.) are unchanged.
Tests
- 12 unit tests in
agent-status-terminal-title.test.ts(all passing) - Integration test added in
useIpcEvents.test.tsfor the Cursordone+ spinner title case
After a Cursor CLI agent finishes, the stored title becomes
Cursor readyinstead of staying on a spinner, so loading indicators clear and the session shows idle/completed. - 12 unit tests in
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- fable-5Compare side by side →
- fable-5Compare side by side →