fix: correct misleading send_message tool description for scheduled tasks (#729)
The send_message tool description incorrectly stated that a scheduled task's final output is not delivered to the user, instructing agents to use the MCP tool for any communication. In reality, task-scheduler.ts unconditionally forwards the agent's result to the user via a streaming output callback (deps.sendMessage), which is a direct call to the channel layer — entirely separate from the MCP tool path. This caused agents following the description to call send_message explicitly, resulting in duplicate messages: once via MCP and once via the native streaming callback. - Remove the incorrect note from the send_message tool description - Fix the misleading comment at task-scheduler.ts which attributed result delivery to the MCP tool rather than the streaming callback
This commit is contained in:
@@ -203,7 +203,7 @@ async function runTask(
|
||||
if (output.status === 'error') {
|
||||
error = output.error || 'Unknown error';
|
||||
} else if (output.result) {
|
||||
// Messages are sent via MCP tool (IPC), result text is just logged
|
||||
// Result was already forwarded to the user via the streaming callback above
|
||||
result = output.result;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user