Update realtime websocket API (#13265)

- migrate the realtime websocket transport to the new session and
handoff flow
- make the realtime model configurable in config.toml and use API-key
auth for the websocket

---------

Co-authored-by: Codex <noreply@openai.com>

codex-rs/protocol/src/protocol.rs

@@ -116,12 +116,32 @@ pub struct RealtimeAudioFrame {
     pub samples_per_channel: Option<u32>,
 }
 
+#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, Eq, JsonSchema, TS)]
+pub struct RealtimeHandoffMessage {
+    pub role: String,
+    pub text: String,
+}
+
+#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, Eq, JsonSchema, TS)]
+pub struct RealtimeHandoffRequested {
+    pub handoff_id: String,
+    pub item_id: String,
+    pub input_transcript: String,
+    pub messages: Vec<RealtimeHandoffMessage>,
+}
+
 #[derive(Debug, Clone, Deserialize, Serialize, PartialEq, Eq, JsonSchema, TS)]
 pub enum RealtimeEvent {
-    SessionCreated { session_id: String },
-    SessionUpdated { backend_prompt: Option<String> },
+    SessionUpdated {
+        session_id: String,
+        instructions: Option<String>,
+    },
     AudioOut(RealtimeAudioFrame),
     ConversationItemAdded(Value),
+    ConversationItemDone {
+        item_id: String,
+    },
+    HandoffRequested(RealtimeHandoffRequested),
     Error(String),
 }