autosearch:channel-selection

What problem does it solve?

Group-first channel selection algorithm for v2 tool-supplier architecture. Given a research query + clarify rubrics + channel_priority hints, picks 1-3 relevant groups from the router index, then 3-8 leaf channels from within those groups. Replaces flat-rank selection across 41 channels with a two-stage pick so runtime AI never has to read all 41 SKILL.md bodies.

Core Features & Use Cases

• Two-stage selection reduces the need to read all 41 channel SKILL.md bodies by first selecting 1-3 groups and then 3-8 leaf channels.
• Integrates with autosearch router and 14 group index files to form a scalable routing strategy.
• Outputs a ranked set of groups and leaves to drive subsequent run_channel invocations with predictable latency and cost.
• Designed to be used after clarify and before run_channel to guide channel fan-out in complex queries.

Quick Start

Run the clarify step with a research query to prepare channel_priority hints, then execute the channel-selection step to pick groups and leaves before invoking run_channel.