main.js · part 113

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-local-agent-runtime/dist/main.js, part 113. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

Optional title for the questions form

Array of questions to present to the user (minimum 1 required)

Collect structured multiple-choice answers from the user.

STRICT INVOCATION RULES (must follow):
- ALWAYS use common sense and context discovery (including the codebase, file system, and web when relevant) to understand what the user means and predict what they want.
- Use this tool ONLY in exceptional and consequential circumstances, after extensive research, when a decision is genuinely the user's to make and cannot be resolved from context or sensible defaults. (Or when Q&A is explicitly requested.)
- Do NOT use this tool to ask for help, inquire into details, solicit feedback on suggestions, seek rubber-stamps on unimportant decisions, or ask for confirmation.

Usage notes:
- Each question should have at least 2 options for the user to choose from
- Users will always be able to select "Other" to provide custom text input
- Users will always be able to select "Skip" to skip answering
- Do not include additional "skip"-like or "other"-like options
- Use allow_multiple: true to allow multiple answers to be selected for a question
- If you recommend a specific option, make that the first option in the list and add "(Recommended)" at the end of the label

Collect structured multiple-choice answers from the user. Use this tool only when you are blocked on a decision that is genuinely the user's to make: one you cannot resolve from the request, the code, or sensible defaults.

Usage notes:
- Each question should have at least 2 options for the user to choose from
- Users will always be able to select "Other" to provide custom text input
- Use allow_multiple: true to allow multiple answers to be selected for a question
- If you recommend a specific option, make that the first option in the list and add "(Recommended)" at the end of the label

Prefer this tool over listing options in your final response text (as letters, numbers, bullet points, etc).

Ask the user questions when you need to present options or you are blocked on their decision.

Invalid arguments

Invalid arguments:
${_.error.errors.map(e=>`${e.path.length>0?e.path.join("."):"argument"}: ${e.message}`).join("\n")}

${e.path.length>0?e.path.join("."):"argument"}: ${e.message}

Unexpected response for ask question query: ${o.result.case}

Missing result in ask question response

Dropping invalid ask_question completion

Dropping duplicate ask_question completion (already applied)

Unknown error

Failed to load user permissions auto-run instructions

Turn contains unusually long trailing run of consecutive user messages

Object expected.

Symbol.asyncDispose is not defined.

Symbol.dispose is not defined.

Object not disposable.

An error was suppressed during disposal.

Unhandled conversation state op: ${n}

The number of steps taken by the agent

Local-sync conflict turn-end barrier outcomes

Model samples abandoned for a pending steer before any tool call or visible text

Sample age (ms since the model request was sent) when a steer preempted it

Time from runStep entry to executeToolStream call (tool generation, message preparation) on the first step only

Duration of agent turn execution in milliseconds

Result status of agent turn execution

Total number of tool calls executed in a turn

Character count of the final assistant message when a turn completes

UX stats for the final assistant message when a turn completes

Number of tool calls in unified handler

Number of unfinished todos at the end of a turn

Retry classification for empty model responses

Outcome of the NAL single-message loop in-step retry (observe only)

Outcome of the one-shot step retry after a provider output-decode error

Empty model response, retry action: ${e}

Failed to run step, exceeded max retries

Output tokens for tool call arguments

Cache write tokens for tool call arguments

Input tokens for tool call result

Cached read tokens for tool call result

Number of parallel tool calls in a model invocation

Number of parallel tool calls in a model invocation when there is at least one call

Long-reasoning reminder exposure hook failed open

Agent response comparison warmup failed open

Agent response comparison preselection failed open

Agent response comparison pending update failed open

Agent response comparison skip update failed open

Failed to checkpoint tool results completed before the deferred interaction

Agent response comparison selection failed open

Agent response comparison selection refinement failed open

Alternate response completed without text

Agent response comparison failed open

afterAgentThought hook execution failed

Running step

Failed to persist checkpoint with pending tool calls

[summarization-trigger] Triggering background summarization since we are below free token threshold

Failed to start response-time background summarization

Invocation ID mismatch. Bug in executeToolStream