Update

main.py

@@ -191,17 +191,22 @@ class HealthcareChatbot:
 
             ### Phase 3: Routing Decision Logic
             
-            **CONVERSATION Classification:**
-            - User query does NOT align with any available endpoint functionality
-            - General inquiries that don't require specific data operations
-            - Conversational elements without actionable requests
-            - Queries that cannot be fulfilled through the documented API capabilities
-
-            **API_ACTION Classification:**
-            - User query clearly aligns with at least one endpoint's described functionality
-            - Request involves specific data operations (create, read, update, delete)
-            - Query contains actionable elements that match endpoint capabilities
-            - Required or optional parameters can be extracted from the user input
+            **IMPORTANT: Default to API_ACTION when there's ANY potential endpoint match**
+            
+            **API_ACTION Classification (PRIMARY):**
+            - User mentions ANY action that could relate to healthcare operations
+            - ANY request for information that might exist in the system
+            - Keywords indicating medical services, appointments, records, or healthcare data
+            - Even vague requests that could be interpreted as needing API data
+            - When user asks about anything related to their health, medical history, or healthcare services
+            - Any mention of booking, scheduling, checking, updating, or retrieving information
+
+            **CONVERSATION Classification (SECONDARY - Use ONLY when certain):**
+            - Pure greetings with no follow-up request (just "hello", "hi")
+            - Thank you messages with no additional requests
+            - Questions ONLY about the bot's capabilities with no data needs
+            - Completely unrelated topics (weather, sports, general knowledge)
+            - Clear goodbye messages with no pending requests
 
             ### Phase 4: Technical Implementation
             When API_ACTION is determined:
@@ -213,9 +218,10 @@ class HealthcareChatbot:
 
             ## Confidence Assessment
             Rate your confidence (0.0-1.0) based on:
-            - Clarity of user intent (0.3 weight)
-            - Strength of endpoint alignment (0.4 weight)
-            - Parameter availability and accuracy (0.3 weight)
+            - BIAS TOWARD API_ACTION: Start with 0.7 confidence for any healthcare-related query
+            - Increase confidence when specific actions or data requests are mentioned
+            - Only reduce confidence below 0.5 for pure conversational elements
+            - Healthcare context should maintain high confidence for API_ACTION
 
             ## Required Output Format
             {{
@@ -231,11 +237,12 @@ class HealthcareChatbot:
             }}
 
             ## Quality Assurance Rules
+            - **CRITICAL**: Favor API_ACTION over CONVERSATION when in doubt
             - Never fabricate endpoints not present in the documentation
-            - Never assume parameter values not explicitly provided by the user
-            - Always cross-reference endpoint descriptions with user intent
-            - Provide detailed reasoning that demonstrates thorough analysis
-            - Default to CONVERSATION when endpoint alignment is uncertain or weak
+            - When multiple endpoints could match, select the most appropriate one
+            - If unsure about parameters, still route to API_ACTION and list missing parameters
+            - Only use CONVERSATION for clearly non-actionable queries
+            - Healthcare-related queries should almost always be API_ACTION
 
             Analyze the provided query using this comprehensive framework and respond with the specified JSON format.
             """,