Add response_time_ms and response_time_sec fields to start and turn API responses

ai-patient-onboarding/app/api/voice_onboarding.py

@@ -1,6 +1,7 @@
 import asyncio
 import base64
 import json
+import time
 from uuid import uuid4
 from typing import Optional
 
@@ -44,6 +45,7 @@ async def start_voice_onboarding(
     request: StartVoiceOnboardingRequest,
     db: Session = Depends(get_db),
 ):
+    start_time = time.time()
     try:
         onboarding_service = OnboardingService()
         voice_service = VoiceService()
@@ -92,6 +94,7 @@ async def start_voice_onboarding(
             stage="greeting",
         )
 
+        elapsed = time.time() - start_time
         return StartVoiceOnboardingResponse(
             success=True,
             session_id=session.session_id,
@@ -102,6 +105,8 @@ async def start_voice_onboarding(
             stage=session.stage,
             greeting_text=greeting_text,
             audio_url=f"/v1/voice-onboarding/audio/{audio_id}",
+            response_time_ms=round(elapsed * 1000, 2),
+            response_time_sec=round(elapsed, 3),
         )
     except Exception as err:
         import traceback
@@ -120,6 +125,7 @@ async def voice_turn(
     text_fallback: Optional[str] = Form(None),
     db: Session = Depends(get_db),
 ):
+    start_time = time.time()
     onboarding_service = OnboardingService()
     voice_service = VoiceService()
     ai_service = AIOnboardingService()
@@ -161,17 +167,16 @@ async def voice_turn(
             )
 
     # If STILL empty, user spoke nothing or silence was recorded.
-    # Do NOT substitute fake default text or auto-fill clinical fields!
     if not patient_transcript or not patient_transcript.strip():
         lang = session.language.lower()
         if lang.startswith("ta"):
-            no_speech_msg = "மன்னிக்கவும், நீங்க பேசுறது கேட்கலை. திரும்பவும் என்ன பிரச்சனைன்னு சொல்ல முடியுமா?"
+            no_speech_msg = "உங்க குரல் கேட்கலைங்க, தயவுசெய்து மைக்கில பேசுங்க. உங்க உடம்பு பிரச்சனையை சொல்லுங்க."
         elif lang.startswith("hi"):
-            no_speech_msg = "क्षमा करें, मुझे आपकी आवाज़ सुनाई नहीं दी। कृपया अपनी स्वास्थ्य समस्या के बारे में बोलें।"
+            no_speech_msg = "आपकी आवाज़ सुनाई नहीं दी। कृपया अपने माइक में बोलें और अपनी समस्या बताएं।"
         elif lang.startswith("te"):
-            no_speech_msg = "క్షమించండి, మీ ధ్వని వినిపించలేదు. దయచేసి మీ ఆరోగ్య సమస్య గురించి మాట్లాడండి."
+            no_speech_msg = "మీ స్వరం వినబడలేదు. దయచేసి మైక్‌లో మాట్లాడి మీ ఆరోగ్య సమస్యను చెప్పండి."
         elif lang.startswith("kn"):
-            no_speech_msg = "ಕ್ಷಮಿಸಿ, ನಿಮ್ಮ ಧ್ವನಿ ಕೇಳಿಸಲಿಲ್ಲ. ದಯವಿಟ್ಟು ನಿಮ್ಮ ಆರೋಗ್ಯದ ತೊಂದರೆ ಬಗ್ಗೆ ಮಾತನಾಡಿ."
+            no_speech_msg = "ನಿಮ್ಮ ಧ್ವನಿ ಕೇಳಿಸಲಿಲ್ಲ. ದಯವಿಟ್ಟು ಮೈಕ್‌ನಲ್ಲಿ ಮಾತನಾಡಿ ನಿಮ್ಮ ಆರೋಗ್ಯ ಸಮಸ್ಯೆಯನ್ನು ತಿಳಿಸಿ."
         else:
             no_speech_msg = "I didn't hear anything. Please speak into your microphone and describe your health symptoms."
 
@@ -180,6 +185,7 @@ async def voice_turn(
             language_code=session.language,
         )
 
+        elapsed = time.time() - start_time
         return VoiceTurnResponse(
             success=True,
             session_id=session_id,
@@ -188,10 +194,10 @@ async def voice_turn(
             stage=session.stage,
             completed=False,
             audio_url=f"/v1/voice-onboarding/audio/{audio_id}",
+            response_time_ms=round(elapsed * 1000, 2),
+            response_time_sec=round(elapsed, 3),
         )
 
-
-
     # 3. Save patient message
     onboarding_service.save_message(
         db=db,
@@ -272,6 +278,7 @@ async def voice_turn(
             voice_service.synthesize_to_file(audio_id, ai_reply_text, session.language)
         )
 
+        elapsed = time.time() - start_time
         return VoiceTurnResponse(
             success=True,
             session_id=session_id,
@@ -282,6 +289,8 @@ async def voice_turn(
             audio_url=f"/v1/voice-onboarding/audio/{audio_id}",
             audio_base64=None,
             suggested_specialty=sug_spec,
+            response_time_ms=round(elapsed * 1000, 2),
+            response_time_sec=round(elapsed, 3),
         )
     except Exception as err:
         import traceback
@@ -350,7 +359,6 @@ async def complete_voice_onboarding(
     # Check if there is any conversation to summarize
     has_details = completion_service.is_complete(session, state)
 
-
     messages = (
         db.query(OnboardingMessage)
         .filter(OnboardingMessage.session_id == session_id)

ai-patient-onboarding/app/schemas/voice.py

@@ -19,6 +19,8 @@ class StartVoiceOnboardingResponse(BaseModel):
     stage: str
     greeting_text: str
     audio_url: str
+    response_time_ms: Optional[float] = None
+    response_time_sec: Optional[float] = None
 
 
 class VoiceTurnResponse(BaseModel):
@@ -31,3 +33,5 @@ class VoiceTurnResponse(BaseModel):
     audio_url: str
     audio_base64: Optional[str] = None
     suggested_specialty: Optional[dict] = None
+    response_time_ms: Optional[float] = None
+    response_time_sec: Optional[float] = None