mirror of
https://github.com/openai/codex.git
synced 2026-11-22 23:00:42 +00:00
Offer safer rewrites after safety blocks in the TUI (#57365)
## What changed - Show selectable safer follow-ups alongside safety-block explanations, with an option to enable Daybreak when disabled. - Submit the selected rewrite in a verified fork before the blocked turn, preserving the original chat's draft and current model settings. Mark the new turn with `safety_recourse_follow_up`. - Filter suggestions that could invoke commands, skills, apps, or plugins, and suppress recourse for unsupported servers and non-primary threads. ## Testing Extend coverage for fork history, draft preservation, model selection, turn metadata, suggestion filtering, and the Daybreak picker. GitOrigin-RevId: 49052df6301b6bfbba07262d40b007dcf97bb7c9
This commit is contained in:
@@ -135,6 +135,7 @@ stream_max_retries = 0
|
||||
let turn = app_server
|
||||
.turn_start(
|
||||
started.session.thread_id,
|
||||
"user",
|
||||
"tui-user-message".to_string(),
|
||||
vec![UserInput::Text {
|
||||
text: "hello".to_string(),
|
||||
|
||||
@@ -92,6 +92,7 @@ stream_max_retries = 0
|
||||
app_server
|
||||
.turn_start(
|
||||
thread_id,
|
||||
"user",
|
||||
"user-message".to_string(),
|
||||
vec![UserInput::Text {
|
||||
text: "hello".to_string(),
|
||||
|
||||
Reference in New Issue
Block a user