pup: date aware summary reporter

llm_prompts.py

@@ -240,6 +240,7 @@ def get_synthesis_report_prompt(query, quantitative_data, qualitative_data, plan
     """
     qualitative_prompt_str = ""
     dimension = plan.get('analysis_dimension', 'N/A')
+    query_filter = plan.get('query_filter', 'Not available') # Extract query filter from the plan
     if qualitative_data and dimension in qualitative_data:
         for group in qualitative_data.get(dimension, {}).get('groups', []):
             group_value = group.get('groupValue', 'N/A')
@@ -263,15 +264,19 @@ You are a top-tier business intelligence analyst. Your task is to write an insig
 ### AVAILABLE INFORMATION
 
 **1. The User's Core Question:**
-\"{query}\"
+"{query}"
 
-**2. Quantitative Data (The 'What'):**
-This data shows the high-level aggregates.
+**2. Data Filters Applied:**
+This is the exact Solr query filter that was used to retrieve the underlying data. Use this to understand the precise scope of the analysis (e.g., the time range or specific categories).
+`{query_filter}`
+
+**3. Quantitative Data (The 'What'):**
+This data shows the high-level aggregates based on the filters above.
 ```json
 {json.dumps(quantitative_data, indent=2)}
 ```
 
-**3. Qualitative Data (The 'Why'):**
+**4. Qualitative Data (The 'Why'):**
 These are the single most significant documents driving the numbers for each category.
 {qualitative_prompt_str}
 
@@ -283,7 +288,7 @@ Your report must be in clean, professional Markdown and follow this structure pr
 **Report Structure:**
 
 `## Executive Summary`
-- A 1-2 sentence, top-line answer to the user's question based on the quantitative data.
+- A 1-2 sentence, top-line answer to the user's question. **Crucially, use the 'Data Filters Applied' information to state the context of your answer** (e.g., "Over the past month...", "For deals in the cancer category...", "In 2024...").
 
 `### Key Findings`
 - Use bullet points to highlight the main figures from the quantitative data. Interpret the numbers.