learn_recommendation
Get data-driven recommendations for context strategies based on learned usage patterns, including optimal modes, token costs, and success rates for specific development tasks.
Instructions
Get a data-driven context strategy recommendation from learned usage patterns.
Returns the best modes to use, expected token cost, and success rate for a given task type.
Known task types: debug, feature, refactor, code_navigation, orientation, cleanup,
architecture, dependency_audit, code_review, task_preparation, output_review,
learning, patterns.
Leave task_type empty to see all learned strategies for this repo.
NOTE: Requires the tempo package to be installed. Returns a LEARN_UNAVAILABLE
error if not installed — install with: pip install -e .
output_format: "text" (default) or "json" for structured responseInput Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | Yes | ||
| task_type | No | ||
| output_format | No | text |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |