mirror of
https://github.com/openai/codex.git
synced 2026-11-19 23:05:23 +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
@@ -728,6 +728,7 @@ mod tests {
|
||||
let mapped = map_requirements_toml_to_api(ConfigRequirementsToml {
|
||||
auto_review: Some(AutoReviewRequirementsToml {
|
||||
required_on_models: Some(vec!["gpt-protected".to_string()]),
|
||||
ignore_rules: None,
|
||||
}),
|
||||
models: Some(ModelsRequirementsToml {
|
||||
new_thread: Some(NewThreadModelDefaultsToml {
|
||||
|
||||
Reference in new issue
Block a user