broker: REASONING_EFFORT knob for reasoning-line Realtime models

README.md

@@ -68,6 +68,7 @@ The broker fetches HA's tools at startup and registers them on the Realtime sess
 |---|---|---|
 | `OPENAI_API_KEY` | — | required |
 | `MODEL` | `gpt-realtime` | Realtime model |
+| `REASONING_EFFORT` | unset | reasoning effort for reasoning-line models (`gpt-realtime-2.1`+): `minimal`/`low`/`medium`/`high`/`xhigh`; leave unset for non-reasoning models |
 | `VOICE` | `marin` | Realtime voice |
 | `INSTRUCTIONS` | generic | system prompt / persona |
 | `WS_HOST` / `WS_PORT` | `0.0.0.0` / `8765` | where the device connects |

broker/realtime_broker/agent.py

@@ -16,8 +16,10 @@
     AudioConfiguration,
     AudioInput,
     AudioOutput,
+    ClientEvent,
     InputAudioTranscription,
     SessionProperties,
+    SessionUpdateEvent,
     TurnDetection,
 )
 from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
@@ -42,11 +44,27 @@ class VoicePERealtimeService(OpenAIRealtimeLLMService):
     its own response.create).
     """
 
+    def __init__(self, *args, reasoning_effort: str | None = None, **kwargs):
+        super().__init__(*args, **kwargs)
+        self._reasoning_effort = reasoning_effort
+
     async def _handle_context(self, context: LLMContext) -> None:
         self._context = context
         self._llm_needs_conversation_setup = False
         await self._process_completed_function_calls(send_new_results=True)
 
+    async def send_client_event(self, event: ClientEvent) -> None:
+        # Pipecat 0.0.97's SessionProperties has no `reasoning` field and
+        # pydantic serializes by declared type, so a subclass field would be
+        # dropped — inject into the wire dict instead. Applies to every
+        # session.update (initial setup and mid-session).
+        if self._reasoning_effort and isinstance(event, SessionUpdateEvent):
+            dump = event.model_dump(exclude_none=True)
+            dump["session"]["reasoning"] = {"effort": self._reasoning_effort}
+            await self._ws_send(dump)
+            return
+        await super().send_client_event(event)
+
 # Custom broker tools, registered with handlers by the server.
 CUSTOM_TOOLS = [
     {
@@ -206,6 +224,7 @@ async def build_agent(config: Config, mcp: MCPClient | None) -> OpenAIRealtimeLL
         model=config.model,
         session_properties=session,
         start_audio_paused=False,
+        reasoning_effort=config.reasoning_effort,
     )
 
     if mcp is not None and tools_schema is not None:

broker/realtime_broker/config.py

@@ -14,6 +14,11 @@ class Config:
     model: str = "gpt-realtime"
     voice: str = "marin"
     instructions: str = "You are a helpful voice assistant."
+    # Reasoning effort for reasoning-line Realtime models (gpt-realtime-2.1+):
+    # minimal/low/medium/high/xhigh. The server default (low) makes the model
+    # deliberate and pad its spoken replies; "minimal" suits command-and-control.
+    # None = field not sent, required for non-reasoning models (gpt-realtime).
+    reasoning_effort: str | None = None
 
     ws_host: str = "0.0.0.0"
     ws_port: int = 8765
@@ -80,6 +85,7 @@ def from_env(cls) -> "Config":
             openai_api_key=api_key,
             model=os.environ.get("MODEL", "gpt-realtime"),
             voice=os.environ.get("VOICE", "marin"),
+            reasoning_effort=os.environ.get("REASONING_EFFORT") or None,
             instructions=os.environ.get("INSTRUCTIONS", cls.instructions),
             ws_host=os.environ.get("WS_HOST", "0.0.0.0"),
             ws_port=int(os.environ.get("WS_PORT", "8765")),