This is what each option does in claude code effortLevel: "high" - this is pretty obvious, it decides the effort level of your model, and you can set either [low|medium|high|max|auto] DISABLE_1M_CONTEXT - removes the 1M token window. back to 200K. DISABLE_ADAPTIVE_THINKING - fixed thinking budget instead of one that scales with task difficulty. DISABLE_AUTO_MEMORY - No auto capture mid-session for important decisions or preferences. SUBAGENT_MODEL: "sonnet" - every sub-agent runs on sonnet.

@mdlahfir SUBAGENT_MODEL global is the blunt version. what works better for me: score each delegation by complexity and route per task - haiku for exploration, sonnet for planning/debugging, opus only when complexity hits 7+. same token savings without the quality cliff on harder tasks.

Wait this is interesting but is it functional on your side? When asked to change model mid session it says: "You have to change it with /model" And also @trq212 mentioned that changing model mid session loses the prompt cache for the session and it has to rebuild from scratch which will make it consume tokens?

different thing - not switching the main session model. you're right, /model mid-run kills the prompt cache and with it the whole incentive. you rebuild from scratch and pay the savings back in tokens. that's why i route per Task spawn instead. each subagent has its own context, so the main cache stays intact. SUBAGENT_MODEL sets the default, i override per call by complexity.