Add realtime transcription mode for websocket sessions (#14556)

- add experimental_realtime_ws_mode (conversational/transcription) and
plumb it into realtime conversation session config
- switch realtime websocket intent and session.update payload shape
based on mode
- update config schema and realtime/config tests

---------

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

codex-rs/core/config.schema.json

@@ -1342,6 +1342,13 @@
       },
       "type": "object"
     },
+    "RealtimeWsMode": {
+      "enum": [
+        "conversational",
+        "transcription"
+      ],
+      "type": "string"
+    },
     "ReasoningEffort": {
       "description": "See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning",
       "enum": [
@@ -1816,6 +1823,14 @@
       "description": "Experimental / do not use. Overrides only the realtime conversation websocket transport base URL (the `Op::RealtimeConversation` `/v1/realtime` connection) without changing normal provider HTTP requests.",
       "type": "string"
     },
+    "experimental_realtime_ws_mode": {
+      "allOf": [
+        {
+          "$ref": "#/definitions/RealtimeWsMode"
+        }
+      ],
+      "description": "Experimental / do not use. Selects the realtime websocket intent mode. `conversational` is speech-to-speech while `transcription` is transcript-only."
+    },
     "experimental_realtime_ws_model": {
       "description": "Experimental / do not use. Selects the realtime websocket model/snapshot used for the `Op::RealtimeConversation` connection.",
       "type": "string"