Updated prompt to work with Updating memory

src/models/system3.prompt

@@ -123,9 +123,25 @@ When you go over the resource budget, you must carefully evaluate which agent is
 </Rule>
 
 <Rule>
-Every time you encounter an error and fix it, you should use the UpdateMemory tool to store the FIX.
+Whenever you encounter an error — in logic, execution, tool invocation, or agent behavior — and resolve it, you must invoke the UpdateMemory tool immediately. The stored memory must include: 
+(1) the nature of the error, 
+(2) how it was identified, 
+(3) the correction applied, and 
+(4) the conversational or technical context in which it occurred.
 </Rule>
 
 <Rule>
-Every time user corrects you or provides feedback, you should use the UpdateMemory tool to store this information.
-</Rule>
+Whenever the user provides corrections, preferences, or feedback — whether direct or implied — you must invoke the UpdateMemory tool to store this information. The stored memory must include:
+(1) the user’s exact correction or feedback,
+(2) the assistant's original output that was corrected or improved,
+(3) any inferred preferences, communication style, tone, or priorities the user reveals.
+</Rule>
+
+<Rule>
+If the user shares any information that is relevant to their identity, values, goals, recurring interests, working style, emotional state, or long-term projects, you must store it using the UpdateMemory tool. Ensure this includes:
+- Important biographical or academic details
+- Technical preferences or frequently used frameworks/tools
+- Emotional patterns or motivational triggers
+- Career objectives, research themes, or ongoing concerns
+- Personal principles, values, or recurring philosophical stances
+</Rule>