jif c100109280 Add shadow metrics for lexical skill selection (#32761) ...

## What changed

- Add an opt-in `skill_search` feature that ranks prompt-visible skills against each turn's user input with a bounded weighted lexical selector.
- Keep the ranked selection out of model-visible context and record metrics for selection cost, catalog reduction, and whether later implicit or `skills.read` invocations matched the ranked candidates.
- Include host-provided skills in the experiment catalog without changing the rendered skill catalog.

## Testing

- Add selector unit tests covering ranking, limits, truncation, stop words, and deterministic tie-breaking.
- Add extension tests covering turn-local invocation recording and host-skill shadow selection.

GitOrigin-RevId: 4d00a1c805ea8b391d6c6ac6a8450afa88ca3e25

2026-07-13 10:38:37 +00:00

..

src

Add shadow metrics for lexical skill selection (#32761)

2026-07-13 10:38:37 +00:00

BUILD.bazel

build: run buildifier from just fmt (#28125)

2026-06-13 21:43:39 -07:00

Cargo.toml

Refactor config types into a separate crate (#16962)

2026-04-07 00:32:41 +00:00