main.js · part 147

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-local-agent-runtime/dist/main.js, part 147. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

Invalid regex pattern: ${t}

${o?"Namespace":"MCP server"} "${d.server}" is ${f.serverStatus}.

MCP server

${t} Available tools: ${m.descriptor.tools.map(e=>e.toolName).join(", ")}

Tool "${d.toolName}" is already available directly and is not part of dynamic namespace "${d.server}". Invoke "${d.toolName}" directly instead of using dynamic tool discovery or invocation.

Tool "${d.toolName}" not found in namespace "${d.server}".

MCP tool "${d.toolName}" not found on server "${d.server}".

${t} Available tools: ${m.descriptor.tools.map(e=>e.toolName).join(", ")}

Invalid arguments

Object expected.

Symbol.asyncDispose is not defined.

Symbol.dispose is not defined.

Object not disposable.

An error was suppressed during disposal.

List available resources from configured MCP servers. Each returned resource will include all standard MCP resource fields plus a 'server' field indicating which server the resource belongs to. MCP resources are _not_ the same as tools, so don't call this function to discover MCP tools.

Optional server identifier to filter resources by. If not provided, resources from all servers will be returned.

Unknown error

Error listing MCP resources: ${t.result.value.error}

List MCP resources rejected: ${t.result.value.reason}

Unknown error

No MCP resources found.

• ${e.name||e.uri}

 - ${e.description}

 (${e.server})

 [${e.mimeType}]

  URI: ${e.uri}

Found ${n.length} MCP resource(s):
${o}

List MCP resources rejected

List MCP resources executor returned result without case

The MCP resources executor returned an empty result. This usually means the client is outdated or incompatible; update the client and retry.

Unexpected result case: ${s}

Optional array of file paths to image/video files to attach to your prompt to the ${e}. Use for forwarding relevant user-provided attachments to subagents. DO NOT use for non-user-provided files.

${"create"===r?"Failed to create agent":"Failed to send prompt to agent"}: ${n.value.error}

Failed to create agent

Failed to send prompt to agent

Failed to send prompt to agent: ${Dq.y7k}

 ${n.value.resultSuffix}

Created agent with agent_id: ${e}. It is running in the background.${t}

Sent the prompt to agent_id: ${e}. It is running in the background.${t}

Agent response was empty.

Unknown agent response.

agent_id: 

[Reference error: deprecated syntax, use $PROMPT_<user_message_id>]

[Reference error: no prompt found for user message id ${n}]

[Reference error: no response found for subagent ${o}]

[Reference error: invalid reference syntax]

Meta parent agents require client-side subagent execution.

Unknown meta-parent task result

title is required

A short, user-friendly title for the agent to create. This appears in the UI as the agent's name. Make it concrete and distinct, consider recent titles to avoid reuse, and vary the first word across agent titles.

description is required

A brief description of this agent's scope of work. 10 words or less.

prompt is required

The prompt for the new asynchronous agent. DO NOT tell the agent that you are a meta-agent. Your prompt should be presented as just a normal user prompt.

responding_to_message_ids must contain at least one message id

Array of user message IDs this tool call is responding to. Usually this is the latest user message ID, but include older IDs for delayed actions or when a later message clarifies an earlier one. List multiple IDs when replying to multiple user messages.

fork must be a non-empty agent_id

Optional agent_id of a direct child agent to fork from. Use when you wish to start a new agent with the history of an existing agent. Common cases: parallel work that does not depend on the child's in-flight output, status check or question for a running child without interrupting its work, or multiple independent follow-ups from a completed child (e.g. splitting independent TODOs). Explicitly instruct new agent to fully shift its focus to the new task rather than continuing work on the prior task. Do not stop the work of the agent you are forking from (if you are doing this, resume that agent with `interrupt=true` instead). New agent must be given its own unique title.

new agent

Create an asynchronous agent with the provided prompt. Use `title` to provide a short user-facing name for the new agent. Returns agent_id of the created agent. Agent results will be reported asynchronously as user messages surrounded by