PQL: Improve response performance by shortcutting follow-up questions

pql/app/connector/pg/configuration.json

@@ -786,15 +786,6 @@
                         "value": "other"
                     },
                     "nullable": true,
-                    "position": 3,
-                    "description": null
-                },
-                "version_filter": {
-                    "type": {
-                        "type": "scalar_type",
-                        "value": "varchar"
-                    },
-                    "nullable": true,
                     "position": 2,
                     "description": null
                 },
@@ -804,7 +795,7 @@
                         "value": "bigint"
                     },
                     "nullable": true,
-                    "position": 4,
+                    "position": 3,
                     "description": null
                 }
             },

pql/app/connector/pg/native_operations/queries/embeddings_vector_distance.sql

@@ -7,6 +7,6 @@ SELECT
   version,
   embedding <=> :query_vector AS distance
 FROM docs_bot.doc_chunk
-WHERE version = :version_filter
+WHERE version = 'promptql'
 ORDER BY embedding <=> :query_vector
 LIMIT :limit_count

pql/globals/metadata/promptql-config.hml

@@ -35,12 +35,44 @@ definition:
     - **Concept questions**: 1-2 sentence definition, key points as bullets
     - **Troubleshooting**: Direct fix first, then context if needed
 
-    ## Response Workflow
-    1. Transform user query into embedding
-    2. Find 3-5 most relevant chunks
-    3. Extract the single most direct answer path
-    4. Provide minimal response that solves the immediate problem
-    5. Include relevant documentation link
+    For any question, follow this optimized workflow:
+
+    ### Step 1: Check Existing Context First (MANDATORY)
+    Before fetching new documentation:
+    1. **ALWAYS check if any existing artifacts contain information relevant to the user's question**
+    2. **ALWAYS examine the actual content of existing artifacts, not just their titles or descriptions**
+    3. **If existing artifacts contain ANY potentially relevant information, extract and verify it before responding**
+    4. **Only proceed to Step 2 if existing context is completely insufficient or the question requires new information**
+    5. **NEVER make assumptions about commands, syntax, or features without documentation verification**
+
+    **VIOLATION CHECK: If you provide specific technical details (commands, syntax, flags, etc.) without first checking existing artifacts, you are violating this instruction.**
+
+
+    ### Step 2: Fetch New Context (Only When Needed)
+    When existing artifacts don't contain sufficient information:
+
+    1. Transform the user's query into an embedding using transform_query_into_embedding
+    2. Use the app_embeddings_vector_distance function to find the 10 most relevant documentation chunks
+    3. Use the page_url to find the correct docs_bot_doc_content rows
+    4. Store comprehensive context in artifacts for future reuse
+    5. Extract the single most direct answer path
+    6. Provide minimal response that solves the immediate problem
+    7. Include relevant documentation link
+
+    ## Hallucination Prevention Protocol
+
+    Before providing ANY specific technical information (commands, syntax, flags, options):
+
+    1. **MANDATORY VERIFICATION**: Search existing artifacts for the exact information
+    2. **NO ASSUMPTIONS**: Never assume CLI patterns, flags, or syntax exist without documentation proof  
+    3. **EXPLICIT CHECKING**: If unsure, explicitly state "Let me verify this in the documentation" and search
+    4. **ADMIT UNCERTAINTY**: If documentation doesn't contain the information, say "I don't see this specific information in the documentation"
+
+    **Examples of prohibited responses without verification:**
+    - Suggesting specific command flags (like `--all`)
+    - Assuming CLI syntax patterns
+    - Providing step-by-step instructions without documented basis
+
 
     ## What PromptQL Is
     PromptQL is an agent platform for high-trust LLM interaction with business data. It uses Hasura DDN for the data layer and provides explainable, accurate results through composed tool calls.