jif 9def09afa7 Use serving assessments for adaptive Guardian review (#58075) ...

## What changed

- Match final serving assessments to their response and output item, then retain them with tool invocations and code cells across waits.
- Use matching assessments instead of asynchronous scoring for adaptive review: low-risk actions can skip synchronous review, while elevated-risk actions require it.
- Revalidate captured authorization and policy before approval. Require fresh review for stale or incomplete authorization, preserve explicit review requirements, and discard assessments when hooks rewrite tool input.
- Keep asynchronous scoring as the fallback when an assessment is missing or does not match.

## Testing

Add integration coverage for direct and nested tool calls, hook rewrites, explicit escalation, interrupted responses, catalog-driven policy, incomplete authorization, and assessment retention across code-cell yields and waits.

GitOrigin-RevId: 4346a227204137f018c03c34b302d6f1e9592c96

2026-10-29 12:54:39 +00:00

..

examples

Require content kinds for extension prompt fragments (#40177)

2026-08-23 03:12:58 +00:00

src

Use serving assessments for adaptive Guardian review (#58075)

2026-10-29 12:54:39 +00:00

tests

Use serving assessments for adaptive Guardian review (#58075)

2026-10-29 12:54:39 +00:00

BUILD.bazel

extension: add initial typed extension API (#21736)

2026-05-11 11:06:24 +02:00

Cargo.toml

Back off failed cloud skill and plugin catalog refreshes (#55968)

2026-10-21 19:22:57 +00:00

notes.md

Normalize formatting in docs, web assets, and sample scripts (#52256)

2026-10-08 20:11:43 +00:00