agent/codex
2
0
Fork 0
mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

prompt changes to guardian (#14263)

Browse Source 
## Summary
  - update the guardian prompting
- clarify the guardian rejection message so an action may still proceed
if the user explicitly approves it after being informed of the risk

  ## Testing
  - cargo run on selected examples
This commit is contained in:
maja-openai
2026-03-11 12:33:09 -07:00
committed by Michael Bolin
parent 9b5078d3e8
commit e77b2fd925
3 changed files with 25 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/src/guardian.rs
+3 -1
View File
@@ -73,7 +73,9 @@ pub(crate) const GUARDIAN_REJECTION_MESSAGE: &str = concat!(
"This action was rejected due to unacceptable risk. ",
"The agent must not attempt to achieve the same outcome via workaround, ",
"indirect execution, or policy circumvention. ",
"Proceed only with a materially safer alternative, or stop and request user input.",
"Proceed only with a materially safer alternative, ",
"or if the user explicitly approves the action after being informed of the risk. ",
"Otherwise, stop and request user input.",
);
/// Whether this turn should route `on-request` approval prompts through the