feat: enforce strict activation rules for DevRel agent

backend/app/agents/devrel/prompts/react_prompt.py

@@ -1,4 +1,6 @@
-REACT_SUPERVISOR_PROMPT = """You are a DevRel AI assistant. Use ReAct reasoning: Think -> Act -> Observe.
+REACT_SUPERVISOR_PROMPT = """You are a DevRel AI assistant.
+You have been activated because a user requires specific assistance.
+Use ReAct reasoning: Think -> Act -> Observe.
 
 CURRENT SITUATION:
 - User Message: {latest_message}

backend/app/agents/devrel/prompts/summarization_prompt.py

@@ -11,7 +11,7 @@
 
 Instructions:
 1. Create a NEW summary combining existing and recent conversation
-2. Focus on user's technical interests, problems, and experience level
+2. Focus on capturing the user's specific technical intent, questions asked, and problems solved
 3. Keep under 300 words
 4. Include relevant context for future interactions
 

backend/app/classification/prompt.py

@@ -4,23 +4,40 @@
 
 Context: {context}
 
-DevRel handles:
-- Technical questions about projects/APIs
-- Developer onboarding and support
-- Bug reports and feature requests  
-- Community discussions about development
-- Documentation requests
-- General developer experience questions
+CRITICAL INSTRUCTIONS:
+The DevRel Agent is a SPECIALIZED technical assistant. It must NOT interfere in normal human conversation.
+It should ONLY be activated if one of the following conditions is met:
+
+1. **DIRECT MENTION**: The user explicitly tags or names the bot (e.g., "@Devr.AI", "bot", "assistant").
+   - Action: `needs_devrel: true`
+   - Priority: `high`
+
+2. **TECHNICAL SUPPORT**: The user asks a specific technical question about the project, code, API, or installation.
+   - Example: "How do I set up the environment?", "I'm getting a build error", "Where is the API doc?"
+   - Action: `needs_devrel: true`
+   - Priority: `medium`
+
+3. **CONTRIBUTION/COMMUNITY**: The user asks about contributing, PRs, issues, or community guidelines.
+   - Action: `needs_devrel: true`
+   - Priority: `medium`
+
+**IGNORE (needs_devrel: false)**:
+- General greetings ("Hi", "Hello", "Good morning") unless tagged.
+- Social chatter ("How are you?", "This is cool", "lol") unless tagged.
+- Discussions between users that don't involve the project specifics.
+- Vague statements without a clear question.
 
 Respond ONLY with JSON:
 {{
     "needs_devrel": true/false,
     "priority": "high|medium|low",
-    "reasoning": "brief explanation"
+    "reasoning": "Brief explanation of why it fits/excludes criteria"
 }}
 
 Examples:
-- "How do I contribute?" → {{"needs_devrel": true, "priority": "high", "reasoning": "Onboarding question"}}
-- "What's for lunch?" → {{"needs_devrel": false, "priority": "low", "reasoning": "Not development related"}}
-- "API is throwing errors" → {{"needs_devrel": true, "priority": "high", "reasoning": "Technical support needed"}}
+- "Hi everyone!" → {{"needs_devrel": false, "priority": "low", "reasoning": "General greeting, no tag"}}
+- "@Devr.AI Hi!" → {{"needs_devrel": true, "priority": "high", "reasoning": "Direct mention"}}
+- "I'm getting a 500 error on /api/login" → {{"needs_devrel": true, "priority": "medium", "reasoning": "Technical support"}}
+- "I think we should use React" → {{"needs_devrel": false, "priority": "low", "reasoning": "Opinion"}}
+- "How do I submit a PR?" → {{"needs_devrel": true, "priority": "medium", "reasoning": "Contribution question"}}
 """