mirror of
https://github.com/openai/codex.git
synced 2026-11-13 14:46:14 +00:00
Record reviewed actions with security risk scores (#40901)
## What changed - Add optional `call_id` and `action` fields to `SecurityRiskScore` so a persisted score identifies the tool call and bounded action that produced it. - Populate the fields after Guardian V2 classifies an action while leaving fail-closed and legacy scores without provenance. ## Testing - Verify scores preserve action details for direct tool calls and nested code-mode calls. - Verify rollout serialization retains the new fields. GitOrigin-RevId: fce69af37f368cecf1d9bce42bfc38a969e969b7
This commit is contained in:
1 parent
62fb56ee56
commit
d4998d611a
9 files changed
+130
-3
No files matched your search
@@ -728,6 +728,8 @@ mod tests {
|
||||
RolloutItem::ResponseItem(skill_message.into()),
|
||||
RolloutItem::SecurityRiskScore(SecurityRiskScore {
|
||||
scores: BTreeMap::from([("action_risk".to_string(), 0.92)]),
|
||||
call_id: None,
|
||||
action: None,
|
||||
sampled_at: None,
|
||||
}),
|
||||
RolloutItem::ResponseItem(subagent_message.clone().into()),
|
||||
|
||||
Reference in new issue
Block a user