Fix AI losing conversational context on terse follow-ups

The tool-use nudge fired on every first response without tools, even
when the conversation already had tool results the AI could reference.
This forced the AI to make a new (broader) tool call instead of
interpreting a short follow-up like "2026-02-11" in context of the
prior exchange. Now the nudge only fires when there are no prior tool
results in the conversation. Also added a system prompt rule telling
the AI to interpret ambiguous follow-ups in context.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/Purrse.Api/Services/ChatService.cs

@@ -46,6 +46,7 @@ public class ChatService : IChatService
         - Respond in plain conversational English only.
         - Format financial amounts as currency (e.g. $1,234.56).
         - Tool results are ALREADY displayed to the user as rich tables and charts. Do NOT repeat or list the same data in your text response. Instead, provide a brief insight, highlight, or answer to the user's question. For example, if the user asks "what did I spend on groceries?" and the tool returns transactions, say something like "You spent $342.50 on groceries this month across 8 transactions" — do NOT list every transaction again.
+        - When the user sends a short or ambiguous follow-up (like a date, a name, or "that one"), interpret it in the context of the previous exchange. For example, if you just showed Sarku transactions and the user says "2026-02-11", they mean the Sarku transaction from that date — do NOT search all transactions for that date. You can reference data from previous tool results without calling tools again.
 
         Today's date is {0}.
         """;
@@ -159,6 +160,9 @@ public class ChatService : IChatService
             ollamaMessages.Add(ollamaMsg);
         }
 
+        // Check if the conversation already has tool results from prior turns
+        var hasExistingToolResults = recentMessages.Any(m => m.Role == "tool");
+
         // Add current user message
         ollamaMessages.Add(new OllamaToolMessage { Role = "user", Content = request.Message });
 
@@ -238,9 +242,11 @@ public class ChatService : IChatService
             {
                 var rawContent = response?.Message?.Content ?? "I'm sorry, I couldn't process that request.";
 
-                // If the model responded without calling any tools on the first attempt,
-                // it likely fabricated data or generated code. Nudge it to use tools.
-                if (toolResults.Count == 0 && i == 0)
+                // If the model responded without calling any tools on the first attempt
+                // AND there are no prior tool results in the conversation, it likely
+                // fabricated data. Nudge it to use tools. Skip the nudge when prior
+                // tool results exist — the model may be referencing earlier data.
+                if (toolResults.Count == 0 && i == 0 && !hasExistingToolResults)
                 {
                     _logger.LogWarning("Model responded without calling tools on first attempt, retrying with nudge");
                     ollamaMessages.Add(new OllamaToolMessage