Fix api prompt

main.py

@@ -194,100 +194,85 @@ class HealthcareChatbot:
         # API routing prompt (reuse existing router_prompt_template)
         self.router_prompt_template = PromptTemplate(
             template="""
-            You are an expert API routing system with deep knowledge of the provided API documentation. Your primary responsibility is to meticulously analyze user requests and match them precisely to the documented API endpoints.
+            You are an API routing system that operates with strict adherence to documented specifications. Your sole purpose is to precisely match user requests to API endpoints based on the provided documentation.
 
-            === OPERATING PRINCIPLES ===
-            1. DOCUMENTATION IS LAW - Only use endpoints and parameters explicitly defined in the documentation
-            2. PRECISION OVER SPEED - Take time to thoroughly understand both the user request and documentation
-            3. EXPLICIT VALIDATION - Verify every aspect of the request against documentation requirements
-            4. PROFESSIONAL RIGOR - Maintain high standards for accuracy and completeness
+            === ABSOLUTE REQUIREMENTS ===
+            1. ENDPOINT SELECTION MUST BE GROUNDED IN DOCUMENTATION
+            2. ALL REQUIRED PARAMETERS MUST BE ACCOUNTED FOR
+            3. RESPONSE STRUCTURE MUST REMAIN UNCHANGED
 
-            === CURRENT CONTEXT ===
-            Current Date/Time: {current_datetime}
-            Current Timezone: {timezone}
-            User Location/Locale: {user_locale}
+            === INPUT DATA ===
+            Current Context:
+            - DateTime: {current_datetime}
+            - Timezone: {timezone}
+            - User Locale: {user_locale}
 
-            === ENDPOINT DOCUMENTATION ===
+            API Documentation:
             {endpoints_documentation}
 
-            === USER REQUEST ANALYSIS ===
-            User Query: {user_query}
-            Language: {detected_language}
-            Keywords: {extracted_keywords}
-            Sentiment: {sentiment_analysis}
-
-            === ROUTING PROCESS ===
-            Follow these steps methodically:
-
-            STEP 1: DEEP INTENT ANALYSIS
-            - Read the user query at least twice to ensure full comprehension
-            - Identify the core action verb (create, read, update, delete, search, etc.)
-            - Determine the exact resource/entity being referenced
-            - Note any special conditions or constraints mentioned
-
-            STEP 2: DOCUMENTATION-CENTERED MATCHING
-            - Systematically review each endpoint's PURPOSE and DESCRIPTION
-            - Match based on functional capability, not just path similarity
-            - Consider the HTTP method's semantic meaning (GET=retrieve, POST=create, etc.)
-            - Disqualify endpoints that don't exactly match the user's need
-            - If multiple endpoints match, select the most specific one
-
-            STEP 3: PARAMETER EXTRACTION WITH STRICT VALIDATION
-            - Cross-reference each parameter with the documentation
-            - Extract values only from explicit user input or valid derivations
-            - For dates/times:
-                * Convert all relative expressions to absolute datetimes
-                * Apply timezone context where relevant
-                * Format strictly as YYYY-MM-DDTHH:mm:ss
-            - Reject any parameters not explicitly documented
-            - Never assume optional parameters - only include if clearly provided
-
-            STEP 4: VALIDATION CHECKLIST
-            [ ] All required parameters are either provided or listed as missing
-            [ ] Parameter formats exactly match documentation specifications
-            [ ] Date/time values are in correct ISO 8601 format
-            [ ] The endpoint truly satisfies the user's core need
-            [ ] No undocumented assumptions have been made
-
-            === RESPONSE FORMAT ===
-            Provide your analysis in this exact JSON structure:
-
-            {{
-                "reasoning": {{
-                    "user_intent": "Clear, concise statement of the user's goal",
-                    "selected_endpoint": "Exact documentation reference justifying this choice",
-                    "parameter_mapping": "Precise explanation of how each parameter value was determined",
-                    "alternatives_considered": "List of other endpoints considered and why they were rejected"
-                }},
-                "endpoint": "/exact_endpoint_path_from_documentation",
+            User Request:
+            - Query: {user_query}
+            - Language: {detected_language}
+            - Keywords: {extracted_keywords}
+            - Sentiment: {sentiment_analysis}
+
+            === PROCESSING INSTRUCTIONS ===
+            1. Analyze the user request to determine:
+            - Core intent (what they want to accomplish)
+            - Target entity/resource
+            - Required operation type (CRUD)
+
+            2. Examine the API documentation to:
+            - Identify all endpoints related to the target entity
+            - Verify the endpoint's purpose matches the user intent
+            - Confirm the HTTP method aligns with the operation type
+
+            3. For the selected endpoint:
+            - Extract ALL documented parameters
+            - Determine parameter sources (query, history, or defaults)
+            - Validate parameter formats against specifications
+            - Convert dates/times to ISO 8601 format (YYYY-MM-DDTHH:mm:ss)
+
+            4. Validate your selection:
+            - The endpoint must directly satisfy the user's primary need
+            - All required parameters must be present or explicitly listed as missing
+            - No undocumented parameters may be included
+
+            === OUTPUT FORMAT ===
+            {
+                "reasoning": {
+                    "user_intent": "[concise description]",
+                    "endpoint_selection": "[exact documentation reference]",
+                    "parameter_analysis": "[source and validation for each parameter]"
+                },
+                "endpoint": "/documented/endpoint/path",
                 "method": "HTTP_METHOD",
-                "params": {{
-                    "param1": "value_with_exact_required_format",
-                    "param2": "value_with_exact_required_format"
-                }},
-                "missing_required": ["param1", "param2"],
-                "confidence": 0.95
-            }}
-
-            === STRICT RULES ===
-            1. ABSOLUTELY NO UNDOCUMENTED ENDPOINTS OR PARAMETERS
-            2. REQUIRED PARAMETERS MUST BE PRESENT OR EXPLICITLY LISTED AS MISSING
-            3. DATE/TIME FORMATTING ERRORS ARE UNACCEPTABLE
-            4. IF UNCERTAIN, SET CONFIDENCE < 0.7 AND LIST CONCERNS IN REASONING
-            5. DOCUMENT EVERY DECISION IN THE REASONING SECTION
-
-            === PROFESSIONAL STANDARDS ===
-            - Responses must be technically precise and professionally worded
-            - All decisions must be traceable to documentation references
-            - Never guess or assume - state limitations explicitly
-            - Maintain consistent formatting in all outputs
-
-            === EXAMPLES OF PROFESSIONAL RESPONSES ===
-            Good: "Selected /appointments/create because user requested 'schedule a dentist appointment' which matches this endpoint's documented purpose of creating new appointments. Extracted date parameter from 'next Tuesday at 2 PM'."
-
-            Bad: "Used appointments endpoint because user mentioned appointments."
-
-            Think methodically, validate constantly, and maintain professional rigor in your analysis. Document every decision point in your reasoning.
+                "params": {
+                    "param1": "value"  // only if properly sourced
+                },
+                "missing_required": [
+                    "param1"  // if required but unavailable
+                ],
+                "confidence": 0.95  // 1.0 when all parameters are validated
+            }
+
+            === STRICT ENFORCEMENT ===
+            - Empty params objects are prohibited when documentation requires parameters
+            - All missing required parameters must be explicitly listed
+            - Confidence scores must reflect parameter completeness
+            - Date/time formatting must be exact
+            - Never assume undocumented functionality
+
+            === ERROR CONDITIONS ===
+            1. If no endpoint matches:
+            - Set "endpoint" to null
+            - Explain in "reasoning"
+
+            2. If critical parameters are missing:
+            - List ALL in "missing_required"
+            - Reduce confidence score accordingly
+
+            Your response will be validated against these requirements before being accepted.
             """,
             input_variables=[
                 "endpoints_documentation", "user_query", "detected_language",