fix

main.py

@@ -192,9 +192,10 @@ class HealthcareChatbot:
 
 
         # API routing prompt (reuse existing router_prompt_template)
+
         self.router_prompt_template = PromptTemplate(
             template="""
-            You are a precise API routing assistant. Your job is to analyze user queries and select the correct API endpoint with proper parameters.
+            You are a precise API routing assistant. You MUST analyze EVERY SINGLE endpoint in the documentation before making any decision.
 
             === CURRENT CONTEXT ===
             Current Date/Time: {current_datetime}
@@ -211,101 +212,96 @@ class HealthcareChatbot:
             Sentiment: {sentiment_analysis}
             Conversation History: {conversation_history}
 
-            === ROUTING PROCESS ===
-            Follow these steps in order:
-
-            STEP 1: INTENT ANALYSIS
-            - What is the user trying to accomplish?
-            - What type of operation are they requesting? (create, read, update, delete, search, etc.)
-            - What entity/resource are they working with?
-
-            STEP 2: ENDPOINT MATCHING
-            - Review each endpoint in the documentation
-            - Match the user's intent to the endpoint's PURPOSE/DESCRIPTION
-            - Consider the HTTP method (GET for retrieval, POST for creation, etc.)
-            - Verify the endpoint can handle the user's specific request
-
-            STEP 3: PARAMETER EXTRACTION WITH DATE HANDLING
-            - Identify ALL required parameters from the endpoint documentation
-            - Extract parameter values from the user query and conversation history
+            === MANDATORY ANALYSIS PROCESS ===
+
+            STEP 1: USER INTENT EXTRACTION
+            Analyze the user query to identify:
+            - PRIMARY ACTION: What exactly does the user want to do? (create, get, update, delete, list, search, cancel, etc.)
+            - TARGET ENTITY: What resource are they working with? (appointment, patient, doctor, schedule, etc.)
+            - SPECIFIC CONDITIONS: Any filters, dates, IDs, or constraints mentioned?
+            - CONTEXT FROM HISTORY: Any relevant information from previous conversation?
+
+            STEP 2: COMPREHENSIVE ENDPOINT ANALYSIS
+            For EACH AND EVERY endpoint in the documentation, you MUST perform this analysis:
+
+            ENDPOINT: [Write the exact endpoint path]
+            METHOD: [Write the HTTP method]
+            DESCRIPTION: [Quote the exact description/purpose from documentation]
+            INTENT MATCH: [Does this endpoint's purpose match the user's intent? YES/NO/PARTIAL]
+            REASONING: [Explain why this endpoint matches or doesn't match]
+            PARAMETERS REQUIRED: [List all required parameters]
+            PARAMETERS AVAILABLE: [Which required parameters can be extracted from user query/history?]
+            DECISION: [SUITABLE/NOT_SUITABLE]
+
+            Repeat this analysis for EVERY endpoint before proceeding.
+
+            STEP 3: ENDPOINT SELECTION
+            From your analysis above, select the endpoint where:
+            - The description/purpose EXACTLY matches the user's intent
+            - All or most required parameters are available
+            - The HTTP method makes sense for the operation
+
+            STEP 4: PARAMETER EXTRACTION WITH DATE HANDLING
+            Extract parameters with these rules:
             - Handle date/time expressions with precision:
-            * RELATIVE TIME CONVERSION:
-                - "today" → current date (from current_datetime) + specified time or T08:00:00
-                - "tomorrow" → current date + 1 day + specified time or T08:00:00
-                - "yesterday" → current date - 1 day + specified time or T08:00:00
-                - "next week" → current date + 7 days + specified time or T08:00:00
-                - "in 2 hours" → current datetime + 2 hours
-                - "next Monday/Tuesday/etc." → calculate exact date + specified time or T08:00:00
-            * TIME EXPRESSIONS:
-                - "morning" → 08:00:00
-                - "afternoon" → 14:00:00
-                - "evening" → 18:00:00
-                - "3 PM" → 15:00:00
-                - "10:30 AM" → 10:30:00
-            * ARABIC TIME EXPRESSIONS:
-                - "اليوم" (today) → current date + time
-                - "غدا" (tomorrow) → current date + 1 day + time
-                - "أمس" (yesterday) → current date - 1 day + time
-                - "الصباح" (morning) → 08:00:00
-                - "بعد الظهر" (afternoon) → 14:00:00
-                - "المساء" (evening) → 18:00:00
-            - Convert ALL dates to ISO 8601 format: YYYY-MM-DDTHH:mm:ss
-            - Convert data types as needed (numbers to integers, booleans, etc.)
-            - Set appropriate defaults for optional parameters if beneficial
-
-            STEP 4: VALIDATION
-            - Ensure ALL required parameters are provided or identified as missing
-            - Verify parameter formats match documentation requirements
-            - Check that the selected endpoint actually solves the user's problem
-            - Validate date formats are exactly YYYY-MM-DDTHH:mm:ss
+            * "today" → current date + T08:00:00 (or specified time)
+            * "tomorrow" → current date + 1 day + T08:00:00 (or specified time)
+            * "yesterday" → current date - 1 day + T08:00:00 (or specified time)
+            * "next week" → current date + 7 days + T08:00:00 (or specified time)
+            * "in X hours" → current datetime + X hours
+            * "morning" → 08:00:00, "afternoon" → 14:00:00, "evening" → 18:00:00
+            * "3 PM" → 15:00:00, "10:30 AM" → 10:30:00
+            * Arabic: "اليوم" → today, "غدا" → tomorrow, "الصباح" → 08:00:00, etc.
+            - Convert ALL dates to format: YYYY-MM-DDTHH:mm:ss
+            - Extract values from user query and conversation history
+            - Identify any missing required parameters
 
             === RESPONSE FORMAT ===
-            Provide your analysis and decision in this exact JSON structure:
+            You MUST show your complete endpoint analysis, then provide the JSON response:
+
+            ENDPOINT ANALYSIS:
+            [Show your analysis for each endpoint as described in Step 2]
 
+            FINAL DECISION:
             {{
                 "reasoning": {{
-                    "user_intent": "Brief description of what the user wants to accomplish",
-                    "selected_endpoint": "Why this endpoint was chosen over others",
-                    "parameter_mapping": "How user query maps to endpoint parameters"
+                    "user_intent": "What the user wants to accomplish",
+                    "selected_endpoint": "Why this specific endpoint was chosen - reference its description",
+                    "parameter_mapping": "How parameters were extracted and converted"
                 }},
                 "endpoint": "/exact_endpoint_path_from_documentation",
                 "method": "HTTP_METHOD",
                 "params": {{
-                    "required_param_1": "extracted_or_converted_value",
-                    "required_param_2": "extracted_or_converted_value",
-                    "optional_param": "value_if_applicable"
+                    "param1": "value",
+                    "param2": "value"
                 }},
-                "missing_required": ["list", "of", "missing", "required", "parameters"],
+                "missing_required": ["missing_param1", "missing_param2"],
                 "confidence": 0.95
             }}
 
             === CRITICAL RULES ===
-            1. ONLY select endpoints that exist in the provided documentation
-            2. NEVER fabricate or assume endpoint parameters not in documentation
-            3. ALL required parameters MUST be included or listed as missing
-            4. Convert dates/times to ISO 8601 format (YYYY-MM-DDTHH:mm:ss) - this is MANDATORY
-            5. If patient_id is required and not provided, add it to missing_required
-            6. Match endpoints by PURPOSE/DESCRIPTION, not just keywords in the path
-            7. If multiple endpoints could work, choose the most specific one
-            8. If no endpoint matches, set endpoint to null and explain in reasoning
-            9. Use conversation history to extract missing context (patient IDs, previous dates, etc.)
-            10. Handle timezone considerations using the provided timezone context
-
-            === DATE FORMATTING EXAMPLES ===
-            - Current datetime: 2025-05-31T10:30:00
-            - "today at 3 PM" → 2025-05-31T15:00:00
-            - "tomorrow morning" → 2025-06-01T08:00:00
-            - "next Tuesday at 2:30 PM" → calculate exact date + T14:30:00
-            - "in 3 hours" → 2025-05-31T13:30:00
-
-            === EXAMPLES OF GOOD MATCHING ===
-            - User wants "patient records" → Use patient retrieval endpoint, not general search
-            - User wants to "schedule appointment" → Use appointment creation endpoint
-            - User asks "what appointments today" → Use appointment listing with date filter (today's date in YYYY-MM-DDTHH:mm:ss format)
-            - User wants to "update medication" → Use medication update endpoint with patient_id
-            - User says "cancel my appointment tomorrow" → Use appointment cancellation endpoint with tomorrow's date
-
-            Think step by step and be precise with your endpoint selection and parameter extraction. Pay special attention to date/time handling and ensure all dates are in the exact format YYYY-MM-DDTHH:mm:ss.
+            1. You MUST analyze EVERY endpoint in the documentation - no exceptions
+            2. ONLY select endpoints that exist in the provided documentation
+            3. NEVER skip the endpoint-by-endpoint analysis
+            4. Match by endpoint DESCRIPTION/PURPOSE, not just endpoint name
+            5. ALL dates MUST be in format YYYY-MM-DDTHH:mm:ss
+            6. If no endpoint matches user intent, set endpoint to null
+            7. Show your complete analysis before giving the final JSON response
+            8. Required parameters not available must be listed in missing_required
+            9. Use conversation history to fill in missing context
+
+            === EXAMPLES ===
+            If user says "I want to schedule an appointment for tomorrow at 2 PM":
+            - Look for endpoint with description mentioning appointment creation/scheduling
+            - Convert "tomorrow at 2 PM" to proper date format (e.g., 2025-06-01T14:00:00)
+            - Extract any other required parameters or mark as missing
+
+            If user says "show me my appointments today":
+            - Look for endpoint with description mentioning appointment retrieval/listing
+            - Convert "today" to proper date format for filtering
+            - Check if patient_id or similar identifier is required
+
+            Now analyze EVERY endpoint in the documentation systematically before making your decision.
             """,
             input_variables=[
                 "endpoints_documentation", "user_query", "detected_language",