I have a custom A3B proxy that caps its thinking off. It is a known issue with the model that Qwen themselves documented but is almost never addressed in any harnesses. I also patched up a few other known bugs in the proxy. I highly recommend you shim A3B and when it hits 2K thinking tokens inject (paraphrasing) 'Time to wrap it up bud! Get to work' into its thinking stream. It almost always gets to work. If it needs more time to think there is always next turn.

In my experience it is almost never productively thinking past that point, just spinning in circles. I also reinject all of the thinking. And there are a few tells that it is getting stuck. I have an optional mode that takes the last few turns and tool calls and shoots it off to DSV4 with a prompt to basically understand where it is at and inject better thinking and or planning. It almost always gets it over relatively difficult humps, but some of the time I don't want things going remote. It might end up with 10-30 cents of DSV4 calls over a hours and the quality improvement is remarkable.

The other thing is I trick it into thinking a web_search tool is a web search but it really just asks DSV4 the prompt. DSV4 is a cheap filter to help prevent prompt injection lol. You can give it other models but DSV4 is my cheap-mode default.

edit: oh! My final 35B A3B tip -- use an extremely simple harness. Pi is good. Pi's default tools almost exactly match what Qwen says they tested the model with (likely meaning that tool set is also what they trained it with or something similar). So, in my experience bigger harnesses don't have a noticeable improve ment on tasks.

the “Actually… But wait!” style responses are so annoying, even Claude opus struggles with this so I’d be interested if meta has done something to cut down on that while still giving good responses