Add ASR interim results support in Assistant model and API

- Introduced `asr_interim_enabled` field in the Assistant model to control interim ASR results.
- Updated AssistantBase and AssistantUpdate schemas to include the new field.
- Modified the database schema to add the `asr_interim_enabled` column.
- Enhanced runtime metadata to reflect interim ASR settings.
- Updated API endpoints and tests to validate the new functionality.
- Adjusted documentation to include details about interim ASR results configuration.

api/app/routers/assistants.py

@@ -126,6 +126,9 @@ def _ensure_assistant_schema(db: Session) -> None:
     if "manual_opener_tool_calls" not in columns:
         db.execute(text("ALTER TABLE assistants ADD COLUMN manual_opener_tool_calls JSON"))
         altered = True
+    if "asr_interim_enabled" not in columns:
+        db.execute(text("ALTER TABLE assistants ADD COLUMN asr_interim_enabled BOOLEAN DEFAULT 0"))
+        altered = True
 
     if altered:
         db.commit()
@@ -317,6 +320,9 @@ def _resolve_runtime_metadata(db: Session, assistant: Assistant) -> tuple[Dict[s
         else:
             warnings.append(f"LLM model not found: {assistant.llm_model_id}")
 
+    asr_runtime: Dict[str, Any] = {
+        "enableInterim": bool(assistant.asr_interim_enabled),
+    }
     if assistant.asr_model_id:
         asr = db.query(ASRModel).filter(ASRModel.id == assistant.asr_model_id).first()
         if asr:
@@ -326,14 +332,15 @@ def _resolve_runtime_metadata(db: Session, assistant: Assistant) -> tuple[Dict[s
                 asr_provider = "openai_compatible"
             else:
                 asr_provider = "buffered"
-            metadata["services"]["asr"] = {
+            asr_runtime.update({
                 "provider": asr_provider,
                 "model": asr.model_name or asr.name,
                 "apiKey": asr.api_key if asr_provider in {"openai_compatible", "dashscope"} else None,
                 "baseUrl": asr.base_url if asr_provider in {"openai_compatible", "dashscope"} else None,
-            }
+            })
         else:
             warnings.append(f"ASR model not found: {assistant.asr_model_id}")
+    metadata["services"]["asr"] = asr_runtime
 
     if not assistant.voice_output_enabled:
         metadata["services"]["tts"] = {"enabled": False}
@@ -437,6 +444,7 @@ def assistant_to_dict(assistant: Assistant) -> dict:
         "speed": assistant.speed,
         "hotwords": assistant.hotwords or [],
         "tools": _normalize_assistant_tool_ids(assistant.tools),
+        "asrInterimEnabled": bool(assistant.asr_interim_enabled),
         "botCannotBeInterrupted": bool(assistant.bot_cannot_be_interrupted),
         "interruptionSensitivity": assistant.interruption_sensitivity,
         "configMode": assistant.config_mode,
@@ -457,6 +465,7 @@ def _apply_assistant_update(assistant: Assistant, update_data: dict) -> None:
         "firstTurnMode": "first_turn_mode",
         "manualOpenerToolCalls": "manual_opener_tool_calls",
         "interruptionSensitivity": "interruption_sensitivity",
+        "asrInterimEnabled": "asr_interim_enabled",
         "botCannotBeInterrupted": "bot_cannot_be_interrupted",
         "configMode": "config_mode",
         "voiceOutputEnabled": "voice_output_enabled",
@@ -651,6 +660,7 @@ def create_assistant(data: AssistantCreate, db: Session = Depends(get_db)):
         speed=data.speed,
         hotwords=data.hotwords,
         tools=_normalize_assistant_tool_ids(data.tools),
+        asr_interim_enabled=data.asrInterimEnabled,
         bot_cannot_be_interrupted=data.botCannotBeInterrupted,
         interruption_sensitivity=data.interruptionSensitivity,
         config_mode=data.configMode,