guardian initial feedback / tweaks (#13897)

## Summary
- remove the remaining model-visible guardian-specific `on-request`
prompt additions so enabling the feature does not change the main
approval-policy instructions
- neutralize user-facing guardian wording to talk about automatic
approval review / approval requests rather than a second reviewer or
only sandbox escalations
- tighten guardian retry-context handling so agent-authored
`justification` stays in the structured action JSON and is not also
injected as raw retry context
- simplify guardian review plumbing in core by deleting dead
prompt-append paths and trimming some request/transcript setup code

## Notable Changes
- delete the dead `permissions/approval_policy/guardian.md` append path
and stop threading `guardian_approval_enabled` through model-facing
developer-instruction builders
- rename the experimental feature copy to `Automatic approval review`
and update the `/experimental` snapshot text accordingly
- make approval-review status strings generic across shell, patch,
network, and MCP review types
- forward real sandbox/network retry reasons for shell and unified-exec
guardian review, but do not pass agent-authored justification as raw
retry context
- simplify `guardian.rs` by removing the one-field request wrapper,
deduping reasoning-effort selection, and cleaning up transcript entry
collection

## Testing
- `just fmt`
- full validation left to CI

---------

Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
Charley Cunningham
2026-03-09 09:25:24 -07:00
committed by GitHub
parent 2bc3e52a91
commit f23fcd6ced
16 changed files with 421 additions and 352 deletions

View File

@@ -11,8 +11,9 @@ expression: popup
[ ] Multi-agents Ask Codex to spawn multiple agents to parallelize the work and win in efficiency.
[ ] Apps Use a connected ChatGPT App using "$". Install Apps via /apps command. Restart
Codex after enabling.
[ ] Guardian approvals Let a guardian subagent review `on-request` approval prompts instead of showing
them to you, including sandbox escapes and blocked network access.
[ ] Automatic approval review Dispatch `on-request` approval prompts (for e.g. sandbox escapes or blocked network
access) to a carefully-prompted security reviewer subagent rather than blocking the
agent on your input.
[ ] Prevent sleep while running Keep your computer awake while Codex is running a thread.
Press space to select or enter to save for next conversation

View File

@@ -12,8 +12,9 @@ expression: popup
[ ] Multi-agents Ask Codex to spawn multiple agents to parallelize the work and win in efficiency.
[ ] Apps Use a connected ChatGPT App using "$". Install Apps via /apps command. Restart
Codex after enabling.
[ ] Guardian approvals Let a guardian subagent review `on-request` approval prompts instead of showing
them to you, including sandbox escapes and blocked network access.
[ ] Automatic approval review Dispatch `on-request` approval prompts (for e.g. sandbox escapes or blocked network
access) to a carefully-prompted security reviewer subagent rather than blocking the
agent on your input.
[ ] Prevent sleep while running Keep your computer awake while Codex is running a thread.
Press space to select or enter to save for next conversation