Add safer TUI defaults for cyber models (#37055)

## What changed

- Propagate the optional `modelSpecialty` field through the model catalog and
  app-server `model/list` response.
- When a newly selected model has the `cyber` specialty, default an active TUI
  thread to workspace-write permissions with on-request approval. Use auto
  review when available, otherwise keep the user as reviewer, while respecting
  configured permission requirements.
- Show a notice when auto review is applied and strengthen the full-access
  warning for cyber models.
- Preserve explicitly selected permissions when only reasoning settings change.

## Testing

- Cover auto-review defaults, requirement-aware fallback behavior, permission
  preservation across reasoning changes, and the new warning notice.

GitOrigin-RevId: 8f25b0082d3051d9ff91f7355921236d0f82f758

codex-rs/tui/src/app_event.rs

@@ -805,6 +805,9 @@ pub(crate) enum AppEvent {
         effort: Option<ReasoningEffort>,
     },
 
+    /// Show the cyber auto-review notice after the model selection confirmation.
+    CyberModelAutoReviewNotice,
+
     /// Persist the selected personality to the appropriate config.
     PersistPersonalitySelection {
         personality: Personality,