[edg5000]

I initially thought that getting agents to work for longer and in large groups was the future, but I'm increasingly thinking that, at least for engineering, just one thread makes more sense. The agent pulls things into context as needed. One thing that I've been experimenting with is also letting the agent remove things from context, such as files. But just adding to the context and compacting when it's full seems like it might beat a lot of more advanced options. Because the model is good, it knows what to put in the summary; just enough for the model to be able to rebuild the context from that seed (e.g. pulling in relevant files/data into the context).

[Schlagbohrer]

Have you used this method yourself for long workflows and with contexts approaching 1 million tokens? It doesn't work very well. LLM context is nearly half unusable.

[edg5000]

I always let GPT 5.5/5.6 sol reach compatction. I'm only offered a 258K window, but I think once they release 1M to normal plan users, it will be usable across the whole 1M. At least with Opus I could use the whole 1M. I'd argue that the more context I use, the better performance gets. It has more info already available. I don't notice degradation.

[noosphr]

I've found that model performance starts substantially degrading after 10%.

[Schlagbohrer]

I see with qwen3.6-35B running in Pi that it gets stuck in loops when the 262k context gets more than 30% full.