Describe the feature or problem you'd like to solve
For Anthropic models (e.g. Claude Opus 4.8), thinking and reasoning effort are separate API parameters, but the CLI only exposes effort. There's no first-class way to turn extended thinking on/off independently of the effort level.
Proposed solution
Surface thinking as its own control, decoupled from reasoning effort:
- a
--thinking on|off flag (and /thinking off in interactive mode), and/or
- a 4th step in the
/model wizard. It's currently model → reasoning effort → context size; add a Thinking on/off step.
Default to current behavior so nothing changes unless a user opts in, on models that support it.
Why
- Anthropic exposes
effort (token spend, all output) and thinking (adaptive/disabled) as independent params; effort explicitly doesn't require thinking enabled. Docs: effort, extended thinking.
- Cursor's CLI already ships both axes (
claude-opus-4-8-xhigh vs claude-opus-4-8-thinking-xhigh), so it's implementable on a CLI surface.
- The plumbing already exists in the CLI:
COPILOT_DISABLE_ANTHROPIC_THINKING=1 sets thinking: {type: "disabled"} while keeping effort, and is honored end-to-end. But it's an undocumented, launch-only, process-wide env var that's invisible in /model — this ask is to promote it to a real control.
Example workflows
--model claude-opus-4.8 --effort xhigh --thinking off: long agentic run at high effort, no thinking tokens.--effort low --thinking on: cheap pass that still reasons on hard subproblems.- Headless
--print runs pinned to thinking off for lower-latency, deterministic output.
Describe the feature or problem you'd like to solve
For Anthropic models (e.g. Claude Opus 4.8), thinking and reasoning effort are separate API parameters, but the CLI only exposes effort. There's no first-class way to turn extended thinking on/off independently of the effort level.
Proposed solution
Surface thinking as its own control, decoupled from reasoning effort:
--thinking on|offflag (and/thinking offin interactive mode), and/or/modelwizard. It's currently model → reasoning effort → context size; add a Thinking on/off step.Default to current behavior so nothing changes unless a user opts in, on models that support it.
Why
effort(token spend, all output) andthinking(adaptive/disabled) as independent params;effortexplicitly doesn't require thinking enabled. Docs: effort, extended thinking.claude-opus-4-8-xhighvsclaude-opus-4-8-thinking-xhigh), so it's implementable on a CLI surface.COPILOT_DISABLE_ANTHROPIC_THINKING=1setsthinking: {type: "disabled"}while keeping effort, and is honored end-to-end. But it's an undocumented, launch-only, process-wide env var that's invisible in/model— this ask is to promote it to a real control.Example workflows
--model claude-opus-4.8 --effort xhigh --thinking off: long agentic run at high effort, no thinking tokens.--effort low --thinking on: cheap pass that still reasons on hard subproblems.--printruns pinned to thinking off for lower-latency, deterministic output.