felixxia-oai c517cc6d84 Bypass risk scoring for models that require automatic review (#39981) ...

## Why

Models listed in `auto_review.required_on_models` must always use the full
automatic review path, regardless of any cached Guardian v2 risk score.

## What changed

- Skip Guardian v2 risk classification for models that require automatic
  review and clear any cached `SecurityRiskScore` before review routing.
- Count thread lookup failures as failed scoring attempts so stale scores
  cannot continue approving later tool calls.

## Testing

- Verify required-review models do not start a classifier and always run full
  reviews.
- Verify failed thread lookups advance score lag and fall back to strict review.

GitOrigin-RevId: 048d9a80ac2a282e05437a3abb0c46ec21391be8

2026-08-21 17:33:45 +00:00

..

v2

Bypass risk scoring for models that require automatic review (#39981)

2026-08-21 17:33:45 +00:00

auth.rs

Support Enterprise automation account plans (#36228)

2026-07-30 21:49:53 +00:00

conversation_summary.rs

Prefer persisted cwd when reading local threads (#37198)

2026-08-06 02:26:24 +00:00

fuzzy_file_search.rs

Simplify app-server integration test setup (#34786)

2026-07-22 16:30:12 +00:00

logging.rs

Exit the stdio app-server when its connection closes (#36035)

2026-07-29 22:00:20 +00:00

mod.rs

app-server: structure and test JSON shutdown logs (#30314)

2026-06-26 18:19:56 -07:00

strict_config.rs

Enforce managed authentication requirements locally (#37132)

2026-08-05 18:09:26 +00:00

zsh

fix: keep zsh-fork release assets after removing shell-tool-mcp (#15644)

2026-03-24 12:56:26 -07:00