v0.7.0 - Standard non cortex mode enabled

cortex/router.py

@@ -331,6 +331,108 @@ async def run_reason(req: ReasonRequest):
     }
 
 
+# -------------------------------------------------------------------
+# /simple endpoint - Standard chatbot mode (no reasoning pipeline)
+# -------------------------------------------------------------------
+@cortex_router.post("/simple")
+async def run_simple(req: ReasonRequest):
+    """
+    Standard chatbot mode - bypasses all cortex reasoning pipeline.
+    Just a simple conversation loop like a typical chatbot.
+    """
+    from datetime import datetime
+    from llm.llm_router import call_llm
+
+    start_time = datetime.now()
+
+    logger.info(f"\n{'='*100}")
+    logger.info(f"💬 SIMPLE MODE | Session: {req.session_id} | {datetime.now().strftime('%H:%M:%S.%f')[:-3]}")
+    logger.info(f"{'='*100}")
+    logger.info(f"📝 User: {req.user_prompt[:150]}...")
+    logger.info(f"{'-'*100}\n")
+
+    # Get conversation history from context
+    context_state = await collect_context(req.session_id, req.user_prompt)
+
+    # Build simple conversation history
+    messages = []
+    if context_state.get("recent_messages"):
+        for msg in context_state["recent_messages"]:
+            messages.append({
+                "role": msg.get("role", "user"),
+                "content": msg.get("content", "")
+            })
+
+    # Add current user message
+    messages.append({
+        "role": "user",
+        "content": req.user_prompt
+    })
+
+    # Format messages into a simple prompt for the LLM
+    conversation = ""
+    for msg in messages:
+        role = msg["role"]
+        content = msg["content"]
+        if role == "user":
+            conversation += f"User: {content}\n\n"
+        elif role == "assistant":
+            conversation += f"Assistant: {content}\n\n"
+
+    conversation += "Assistant: "
+
+    # Get backend from env (default to OPENAI for standard mode)
+    backend = os.getenv("STANDARD_MODE_LLM", "OPENAI")
+    temperature = req.temperature if req.temperature is not None else 0.7
+
+    # Direct LLM call
+    try:
+        response = await call_llm(
+            prompt=conversation,
+            backend=backend,
+            temperature=temperature,
+            max_tokens=2048
+        )
+    except Exception as e:
+        logger.error(f"❌ LLM call failed: {e}")
+        response = f"Error: {str(e)}"
+
+    # Update session with the exchange
+    try:
+        update_last_assistant_message(req.session_id, response)
+        add_exchange_internal({
+            "session_id": req.session_id,
+            "role": "user",
+            "content": req.user_prompt
+        })
+        add_exchange_internal({
+            "session_id": req.session_id,
+            "role": "assistant",
+            "content": response
+        })
+    except Exception as e:
+        logger.warning(f"⚠️  Session update failed: {e}")
+
+    duration = (datetime.now() - start_time).total_seconds() * 1000
+
+    logger.info(f"\n{'='*100}")
+    logger.info(f"✨ SIMPLE MODE COMPLETE | Session: {req.session_id} | Total: {duration:.0f}ms")
+    logger.info(f"📤 Output: {len(response)} chars")
+    logger.info(f"{'='*100}\n")
+
+    return {
+        "draft": response,
+        "neutral": response,
+        "persona": response,
+        "reflection": "",
+        "session_id": req.session_id,
+        "context_summary": {
+            "message_count": len(messages),
+            "mode": "standard"
+        }
+    }
+
+
 # -------------------------------------------------------------------
 # /ingest endpoint (internal)
 # -------------------------------------------------------------------