Commit Graph
4 Commits
Author SHA1 Message Date
jif 0f2321f244 Refresh host skill catalogs through world state (#33425)
## Why

Host skills can change after a thread starts. Subsequent turns need the updated
catalog without reinjecting an unchanged catalog on every turn.

## What changed

- Register the host skill provider in app-server and project its catalog through
  a dedicated World State section.
- Render host skills with the existing metadata budget and usage instructions,
  including skill-root aliases when available.
- Suppress the legacy host catalog and contextual fragment when World State owns
  the catalog, while preserving host skills for explicit and shadow selection.

## Testing

Added an app-server test that installs a host skill at runtime and verifies the
catalog updates once and remains stable on the following turn.

GitOrigin-RevId: 4cacc6b2258fc3cab8499fbdf9aa6ab0324ec10d
2026-07-15 20:59:21 +00:00
Won Park 6e113acf5f Allow responses after image generation (#32866)
## What changed

Remove the image generation instruction that prohibited any response after an
image was generated.

GitOrigin-RevId: c779055da3142ba84cdbb9312e5f66b132f24b29
2026-07-13 20:12:42 +00:00
jif 2b0b37abb7 Align shadow skill selection with observable sources (#32768)
## Why

Shadow selection can observe invocations from host and orchestrator skills, but
including executor skills in its candidates can skew the resulting metrics.

## What changed

Limit eligible shadow-selection candidates to enabled, prompt-visible skills
from host or orchestrator sources.

## Testing

Extend the implicit-invocation test to add matching executor candidates and
verify that the host skill remains the selected invocation hit.

GitOrigin-RevId: fd444fe27254b5a880ef5c03c29b5e195127cd97
2026-07-13 11:05:31 +00:00
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