UI and chatbot updates

server.py

@@ -8,11 +8,15 @@ from pathlib import Path
 from fastapi import FastAPI, HTTPException
 from fastapi.responses import HTMLResponse
 from fastapi.staticfiles import StaticFiles
+from dotenv import load_dotenv
 from pydantic import BaseModel
 
 from local_rag import LocalRAG
 from personas import DEFAULT_PERSONA, PERSONAS, PUBLIC_FIELDS
 
+# OPENAI_API_KEY may come from a local .env (git-ignored); an exported variable takes precedence.
+load_dotenv()
+
 OLLAMA_MODEL = "gemma4:12b"
 OPENAI_MODEL = "gpt-6-luna"
 # One RAG instance per (LLM provider, vector store), for on-the-fly provider switching.
@@ -101,6 +105,7 @@ def chat(request: ChatRequest):
             request.message.strip(),
             chat_history=chat_history,
             system_prompt=persona["system_prompt"],
+            tool_description=persona.get("tool_description"),
         )
         answer = result["answer"]
         retrieved = result.get("retrieved", [])