Interrupt cyber model turns after one Guardian denial (#37190)

## What changed

- Add a Guardian circuit-breaker policy for models whose catalog specialty is
  `cyber`.
- Interrupt those models after the first Guardian denial while retaining the
  existing denial thresholds for other models.
- Centralize the `cyber` model-specialty identifier for use across core,
  protocol, app-server, and TUI code.

## Testing

- Cover the cyber-specific threshold in the circuit-breaker unit tests.
- Verify end to end that a denied command is not executed and the turn is
  interrupted after one denial.

GitOrigin-RevId: fad24c9e7aa280432580db1f0e39d13535779710

codex-rs/protocol/src/openai_models.rs

@@ -32,6 +32,8 @@ use crate::config_types::Verbosity;
 use crate::protocol::MultiAgentVersion;
 
 const PERSONALITY_PLACEHOLDER: &str = "{{ personality }}";
+/// Backend model-catalog specialty identifying cybersecurity-focused models.
+pub const MODEL_SPECIALTY_CYBER: &str = "cyber";
 pub const SPEED_TIER_FAST: &str = "fast";
 
 /// See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning