Skip to content

feat(copilot): add context and reasoning_effort config fields#437

Open
abezzub-dr wants to merge 1 commit into
majorcontext:mainfrom
abezzub-dr:copilot-context-effort
Open

feat(copilot): add context and reasoning_effort config fields#437
abezzub-dr wants to merge 1 commit into
majorcontext:mainfrom
abezzub-dr:copilot-context-effort

Conversation

@abezzub-dr

Copy link
Copy Markdown
Contributor

Add copilot.context and copilot.reasoning_effort to moat.yaml, with corresponding --context and --reasoning-effort CLI flags. CLI flags override config values, matching the existing --model precedence.

This lets users pin context window tier (default/long_context) and reasoning effort level (none/minimal/low/medium/high/xhigh/max) declaratively so settings persist across moat runs.

moat.yaml example

copilot:
  model: claude-opus-4.6
  context: long_context
  reasoning_effort: high

CLI usage

moat copilot --context long_context --reasoning-effort high

@abezzub-dr abezzub-dr force-pushed the copilot-context-effort branch from 22510f2 to 08c9911 Compare July 9, 2026 09:17

@abezzub-dr abezzub-dr left a comment

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(Review posted in error — ignore this comment.)

Add copilot.context and copilot.reasoning_effort to moat.yaml, with
corresponding --context and --reasoning-effort CLI flags. CLI flags
override config values, matching the existing --model precedence.

This lets users pin context window tier (default/long_context) and
reasoning effort level (none/minimal/low/medium/high/xhigh/max)
declaratively so settings persist across moat runs.
@abezzub-dr abezzub-dr force-pushed the copilot-context-effort branch from 08c9911 to 3e7eff7 Compare July 9, 2026 11:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants