feat: auto-summarize trigger for agent memory

- Memory Service: POST /agents/{agent_id}/summarize endpoint
  - Fetches recent events by agent_id (new db.list_facts_by_agent)
  - Generates structured summary via DeepSeek LLM
  - Saves summary to PostgreSQL facts + Qdrant vector store
  - Returns structured JSON (summary, goals, decisions, key_facts)

- Gateway memory_client: auto-trigger after 30 turns
  - Turn counter per chat (agent_id:channel_id)
  - 5-minute debounce between summarize calls
  - Fire-and-forget via asyncio.ensure_future (non-blocking)
  - Configurable via SUMMARIZE_TURN_THRESHOLD / SUMMARIZE_DEBOUNCE_SECONDS

- Database: list_facts_by_agent() for agent-level queries without user_id

Tested on NODE1: Helion summarize returns valid Ukrainian summary with 20 events.

Co-authored-by: Cursor <cursoragent@cursor.com>

services/memory-service/app/database.py

@@ -517,6 +517,25 @@ class Database:
                 
         return [dict(row) for row in rows]
         
+    async def list_facts_by_agent(
+        self,
+        agent_id: str,
+        channel_id: str = None,
+        limit: int = 60
+    ) -> list:
+        """List facts for an agent (any user), ordered by most recent."""
+        async with self.pool.acquire() as conn:
+            query = "SELECT * FROM user_facts WHERE agent_id = $1"
+            params = [agent_id]
+            if channel_id:
+                query += " AND fact_key LIKE '%' || $2 || '%'"
+                params.append(channel_id)
+            query += " ORDER BY updated_at DESC"
+            query += f" LIMIT ${len(params) + 1}"
+            params.append(limit)
+            rows = await conn.fetch(query, *params)
+        return [dict(row) for row in rows]
+
     async def delete_fact(
         self,
         user_id: str,