add. cleanup

cortex/intake/intake.py

@@ -1,6 +1,13 @@
 import os
 from datetime import datetime
-from typing import List, Dict, Any
+from typing import List, Dict, Any, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from collections import deque as _deque
+    SESSIONS: dict
+    L10_HISTORY: dict
+    L20_HISTORY: dict
+    def bg_summarize(session_id: str) -> None: ...
 
 from llm.llm_router import call_llm  # use Cortex's shared router
 
@@ -258,3 +265,36 @@ async def summarize_context(
         "L30": L30,
         "last_updated": datetime.now().isoformat(),
     }
+
+# ─────────────────────────────
+# Internal entrypoint for Cortex
+# ─────────────────────────────
+def add_exchange_internal(exchange: dict):
+    """
+    Direct internal call — bypasses FastAPI request handling.
+    Cortex uses this to feed user/assistant turns directly
+    into Intake’s buffer and trigger full summarization.
+    """
+    session_id = exchange.get("session_id")
+    if not session_id:
+        raise ValueError("session_id missing")
+
+    exchange["timestamp"] = datetime.now().isoformat()
+
+    # Ensure session exists
+    if session_id not in SESSIONS:
+        SESSIONS[session_id] = {
+            "buffer": deque(maxlen=200),
+            "created_at": datetime.now()
+        }
+
+    # Append exchange into the rolling buffer
+    SESSIONS[session_id]["buffer"].append(exchange)
+
+    # Trigger summarization immediately
+    try:
+        bg_summarize(session_id)
+    except Exception as e:
+        print(f"[Internal Intake] Summarization error: {e}")
+
+    return {"ok": True, "session_id": session_id}