# fix\(server\): expose and resume held MCP thread queues · pingdotgg/t3code

[View on GitCafe](https://git.cafe/pingdotgg/t3code/commit/4068bcd4386d030b3661b11953f7fd0bb1a6b994)

Repository: [pingdotgg/t3code](https://git.cafe/pingdotgg/t3code)

Visibility: public

Requested revision: 4068bcd4386d030b3661b11953f7fd0bb1a6b994

Requested commit: 4068bcd4386d030b3661b11953f7fd0bb1a6b994

Commit: 4068bcd4386d030b3661b11953f7fd0bb1a6b994

Tree: 93e14fbc7de91d4d1e1e438d4a3e4cef8128fbf6

Author: Julius Marminge

Committer: Julius Marminge

## Message

```
fix(server): expose and resume held MCP thread queues

When a run fails and a queued run targets the same provider, the
orchestrator holds the thread's queue until a user message or the UI's
queue.resume releases it. An MCP orchestrator could neither see that hold
(t3_queue_list only returned ids and text) nor clear it, so a dispatcher
thread driven by scheduled tasks and webhooks sat with its queue stuck.

t3_queue_list now reports a thread-level `held` flag and `held` per item,
and the new t3_queue_resume tool dispatches the existing queue.resume
command, surfacing the usage-limit rejection as a clear error.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

```

## Parents

- [c7e3993fe9fb8e75ccfb1ac64fb360c130d91689](https://git.cafe/pingdotgg/t3code/commit/c7e3993fe9fb8e75ccfb1ac64fb360c130d91689?format=markdown)

[Source at this commit](https://git.cafe/pingdotgg/t3code/tree/4068bcd4386d030b3661b11953f7fd0bb1a6b994?format=markdown)