When using the Muse Spark 1.3 model within an agent, it frequently stops working automatically if the “thinking” process exceeds 11 minutes, failing to execute the file editing operation
In Agent mode with Muse Spark 1.3, a normal coding task is cut off after about 11 minutes. The agent never reaches a write/edit tool call. The chat just stops.
This does not look like hitting the Other Models usage pool. There is no “usage limit” / “rate limit” banner. The run simply ends after sitting in the thinking/planning phase.
Muse Spark 1.3 often does not stream a thinking chain
For AI issues: which model did you use?
Model name (e.g., Sonnet 4, Tab…)
For AI issues: add Request ID with privacy disabled
Request ID: f9a7046a-279b-47e5-ab48-6e8dc12daba1
For Background Agent issues, also post the ID: bc-…
Additional Information
Add any other context about the problem here.
Does this stop you from using Cursor?
Yes - Cursor is unusable
Sometimes - I can sometimes use Cursor
No - Cursor works, but with this issue
The more details you provide, the easier it is for us to reproduce and fix the issue. Thanks!
Thanks for the report. I’ve tried to reproduce this, but haven’t been successful so far. If you have any examples of requests that made Muse think for a long time on Max mode, I’d love to try and reproduce them!