cortex rework continued.

cortex/router.py

@@ -197,26 +197,110 @@ class IngestPayload(BaseModel):
     user_msg: str
     assistant_msg: str
 
+
 @cortex_router.post("/ingest")
-async def ingest_stub():
-    # Intake is internal now — this endpoint is only for compatibility.
-    return {"status": "ok", "note": "intake is internal now"}
+async def ingest(payload: IngestPayload):
+    """
+    Receives (session_id, user_msg, assistant_msg) from Relay
+    and pushes directly into Intake's in-memory buffer.
 
-
-    # 1. Update Cortex session state
-    update_last_assistant_message(payload.session_id, payload.assistant_msg)
-
-    # 2. Feed Intake internally (no HTTP)
+    Uses lenient error handling - always returns success to avoid
+    breaking the chat pipeline.
+    """
     try:
+        # 1. Update Cortex session state
+        update_last_assistant_message(payload.session_id, payload.assistant_msg)
+    except Exception as e:
+        logger.warning(f"[INGEST] Failed to update session state: {e}")
+        # Continue anyway (lenient mode)
+
+    try:
+        # 2. Feed Intake internally (no HTTP)
         add_exchange_internal({
             "session_id": payload.session_id,
             "user_msg": payload.user_msg,
             "assistant_msg": payload.assistant_msg,
         })
-
         logger.debug(f"[INGEST] Added exchange to Intake for {payload.session_id}")
     except Exception as e:
-        logger.warning(f"[INGEST] Failed to add exchange to Intake: {e}")
+        logger.warning(f"[INGEST] Failed to add to Intake: {e}")
+        # Continue anyway (lenient mode)
 
-    return {"ok": True, "session_id": payload.session_id}
+    # Always return success (user requirement: never fail chat pipeline)
+    return {
+        "status": "ok",
+        "session_id": payload.session_id
+    }
+
+# -----------------------------
+# Debug endpoint: summarized context
+# -----------------------------
+@cortex_router.get("/debug/summary")
+async def debug_summary(session_id: str):
+    """
+    Diagnostic endpoint that runs Intake's summarize_context() for a session.
+
+    Shows exactly what L1/L5/L10/L20/L30 summaries would look like
+    inside the actual Uvicorn worker, using the real SESSIONS buffer.
+    """
+    from intake.intake import SESSIONS, summarize_context
+
+    # Validate session
+    session = SESSIONS.get(session_id)
+    if not session:
+        return {"error": "session not found", "session_id": session_id}
+
+    # Convert deque into the structure summarize_context expects
+    buffer = session["buffer"]
+    exchanges = [
+        {
+            "user_msg": ex.get("user_msg", ""),
+            "assistant_msg": ex.get("assistant_msg", ""),
+        }
+        for ex in buffer
+    ]
+
+    # 🔥 CRITICAL FIX — summarize_context is async
+    summary = await summarize_context(session_id, exchanges)
+
+    return {
+        "session_id": session_id,
+        "buffer_size": len(buffer),
+        "exchanges_preview": exchanges[-5:],   # last 5 items
+        "summary": summary
+    }
+
+# -----------------------------
+# Debug endpoint for SESSIONS
+# -----------------------------
+@cortex_router.get("/debug/sessions")
+async def debug_sessions():
+    """
+    Diagnostic endpoint to inspect SESSIONS from within the running Uvicorn worker.
+    This shows the actual state of the in-memory SESSIONS dict.
+    """
+    from intake.intake import SESSIONS
+
+    sessions_data = {}
+    for session_id, session_info in SESSIONS.items():
+        buffer = session_info["buffer"]
+        sessions_data[session_id] = {
+            "created_at": session_info["created_at"].isoformat(),
+            "buffer_size": len(buffer),
+            "buffer_maxlen": buffer.maxlen,
+            "recent_exchanges": [
+                {
+                    "user_msg": ex.get("user_msg", "")[:100],
+                    "assistant_msg": ex.get("assistant_msg", "")[:100],
+                    "timestamp": ex.get("timestamp", "")
+                }
+                for ex in list(buffer)[-5:]  # Last 5 exchanges
+            ]
+        }
+
+    return {
+        "sessions_object_id": id(SESSIONS),
+        "total_sessions": len(SESSIONS),
+        "sessions": sessions_data
+    }