andrewgu-oai e734a1a5c1 Ignore reusable command approvals for cyber models (#37516) ...

## What changed

- Filter saved `allow` prefix rules from the execution policy for cyber-specialized models and models listed in `auto_review.ignore_rules`, while preserving prompt, forbidden, network, and host-executable policy entries.
- Apply the filtered policy consistently to permission instructions, shell commands, unified exec, and the zsh-fork backend.
- Limit cyber-model command approvals to one-time decisions without proposing reusable policy amendments. General models continue to honor saved prefixes, including after switching models within a thread.

## Testing

- Add policy-level coverage for filtering allow-prefix rules while retaining restrictive and network rules.
- Add end-to-end coverage across shell and unified exec paths, zsh-fork execution, user and automatic review, and model switching.

GitOrigin-RevId: f3bd3872424291b12354ec415f33986ec369a368

2026-08-08 00:59:39 +00:00

..

common

Allow injecting model catalog caches (#36992)

2026-08-04 23:04:11 +00:00

remote_env_windows

Scope runtime workspace roots to execution environments (#32952)

2026-07-14 04:41:08 +00:00

suite

Ignore reusable command approvals for cyber models (#37516)

2026-08-08 00:59:39 +00:00

all.rs

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

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

responses_headers.rs

Include sandbox mode in response metadata (#37507)

2026-08-07 22:41:20 +00:00