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

..

common

Allow upstream interruption when canceling Responses Lite turns (#57864)

2026-10-29 00:03:28 +00:00

remote_env_windows

Bind capability roots to environment selections (#51493)

2026-10-06 22:39:32 +00:00

suite

Use serving assessments for adaptive Guardian review (#58075)

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

all.rs

[codex] Use expect in integration tests (#28441)

2026-06-15 21:53:47 -07:00

code_mode_tracing.rs

Add code-mode output truncation protocol contracts (#57272)

2026-10-26 21:36:35 +00:00

mcp_trace_propagation.rs

Add negotiated network policy metadata support for MCP calls (#56278)

2026-10-22 22:33:07 +00:00

responses_headers.rs

Add a credential file override for GCP provider authentication (#57188)

2026-10-26 18:33:05 +00:00

windows_sandbox.rs

Move Windows sandbox tests into a dedicated integration binary (#51678)

2026-10-07 12:47:04 +00:00