prio deal metric values for measure selection

llm_prompts.py

@@ -85,9 +85,10 @@ This is the most critical part of your task. A bad choice leads to a useless, bo
 
 **2. Choosing the `analysis_measure` (The metric):**
 
-*   **EXPLICIT METRIC:** If the user asks for a value (e.g., "by total deal value", "highest revenue"), use the corresponding field and function (e.g., `sum(total_deal_value_in_million)`).
-*   **IMPLICIT COUNT:** If the user asks a "what," "who," "how many," or "most common" question without specifying a value metric, the measure is `count`.
-
+*   **EXPLICIT METRIC:** If the user asks for a value (e.g., "by total deal value," "highest revenue"), use the corresponding field and function (e.g., `sum(total_deal_value_in_million)`).
+*   **IMPLICIT VALUE vs. COUNT:**
+    *   **Prioritize Financial Metrics for "Deals":** If the query is about "deals," "financings," or "partnerships," even if the user doesn't explicitly ask for a value (e.g., "show me recent deals"), you **MUST** default to a financial measure like `sum(total_deal_value_in_million)`. The user is always interested in the money behind the deal.
+    *   **Use 'count' as a fallback:** For non-financial queries where no metric is specified (e.g., "what are the most common news types?"), 'count' is the appropriate measure.
 ---
 ### FIELD DEFINITIONS (Your Source of Truth for Core: {core_name})