feat(api): production security, cors hardening, latency optimizations, postman artifacts & frontend documentation

ai-patient-onboarding/app/ai/gemini_client.py

@@ -1,3 +1,4 @@
+import asyncio
 import json
 import base64
 from app.config import GEMINI_API_KEY, GEMINI_MODEL
@@ -15,7 +16,7 @@ class GeminiClient:
         mime_type: str,
         patient_context: dict,
     ) -> dict:
-        if not self.api_key or self.api_key == "your_gemini_key":
+        if not self.api_key or self.api_key in ["your_gemini_key", "your_gemini_api_key", ""]:
             return {
                 "document_type": "medical_report",
                 "extracted_text": "Sample HbA1c 7.2%, Blood Pressure 130/85 mmHg",
@@ -31,7 +32,7 @@ class GeminiClient:
         try:
             import google.generativeai as genai
             genai.configure(api_key=self.api_key)
-            model = genai.GenerativeModel(self.model)
+            model = genai.GenerativeModel(self.model or "gemini-1.5-flash")
 
             prompt = f"""
 You are a medical document extraction AI.
@@ -59,11 +60,14 @@ Return ONLY JSON:
                 "mime_type": mime_type,
                 "data": file_bytes,
             }
-            response = await model.generate_content_async([part, prompt])
+            response = await asyncio.wait_for(
+                model.generate_content_async([part, prompt]),
+                timeout=4.0
+            )
             cleaned_text = response.text.replace("```json", "").replace("```", "").strip()
             return json.loads(cleaned_text)
         except Exception as e:
-            print(f"[Gemini Extraction Error]: {e}")
+            print(f"[Gemini Extraction Warning]: {e}")
             return {
                 "document_type": "unknown",
                 "findings": [],
@@ -87,5 +91,8 @@ Return ONLY JSON:
             generation_config={"response_mime_type": "application/json"},
         )
         full_prompt = f"{system_prompt}\n\nPATIENT SAID: {user_message}"
-        response = await model.generate_content_async(full_prompt)
+        response = await asyncio.wait_for(
+            model.generate_content_async(full_prompt),
+            timeout=3.5
+        )
         return response.text