mirror of
https://github.com/openai/codex.git
synced 2026-11-18 15:01:48 +00:00
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
This commit is contained in:
1 parent
c2bcb9a26b
commit
e734a1a5c1
16 files changed
+717
-14
No files matched your search
@@ -1162,6 +1162,7 @@ impl UnifiedExecProcessManager {
|
||||
request.sandbox_permissions
|
||||
},
|
||||
prefix_rule: request.prefix_rule.clone(),
|
||||
allow_prefix_rules: context.turn.allow_prefix_rules(),
|
||||
})
|
||||
.await;
|
||||
let req = UnifiedExecToolRequest {
|
||||
|
||||
Reference in new issue
Block a user