fix: add user's message to frontend chat store when sending

Previously, only the assistant's response was added to the frontend store.
Now both user and assistant messages are stored, so the conversation
displays correctly in the chat interface.

src/backend/app/api/auth.py

@@ -58,7 +58,7 @@ def get_current_user(
 
 
 @router.post(
-    "/register", response_model=UserResponse, status_code=status.HTTP_201_CREATED
+    "/register", response_model=Token, status_code=status.HTTP_201_CREATED
 )
 def register(user: UserCreate, db: Session = Depends(get_db)):
     existing_user = db.query(User).filter(User.email == user.email).first()
@@ -75,7 +75,10 @@ def register(user: UserCreate, db: Session = Depends(get_db)):
     db.add(db_user)
     db.commit()
     db.refresh(db_user)
-    return db_user
+    
+    # Generate and return access token so frontend can proceed immediately
+    access_token = create_access_token(data={"sub": db_user.id})
+    return Token(access_token=access_token, token_type="bearer")
 
 
 @router.post("/login", response_model=Token)

src/backend/app/services/ai_agent/crew.py

@@ -1,6 +1,6 @@
 from typing import List, Optional, Dict, Any
-from crewai import Agent, Task, Crew
-from .llm_connector import MiniMaxConnector, MiniMaxLLM
+from crewai import Agent, Task, Crew, LLM
+from .llm_connector import MiniMaxConnector
 from ...core.config import get_settings
 
 
@@ -141,7 +141,7 @@ def create_trading_designer_agent(
         role="Trading Strategy Designer",
         goal="Convert natural language trading requests into precise strategy configurations",
         backstory=system_prompt,
-        llm=MiniMaxLLM(api_key=api_key, model=model),
+        llm=LLM(model=model, api_key=api_key, api_base="https://api.minimax.io/v1"),
         verbose=True,
     )
 
@@ -155,7 +155,7 @@ def create_strategy_validator_agent(
         backstory="""You are a meticulous strategy validator with expertise in trading systems.
         You check that all required parameters are present, values are reasonable, and the 
         strategy makes logical sense. You never approve strategies with missing or invalid data.""",
-        llm=MiniMaxLLM(api_key=api_key, model=model),
+        llm=LLM(model=model, api_key=api_key, api_base="https://api.minimax.io/v1"),
         verbose=True,
     )
 
@@ -169,7 +169,7 @@ def create_strategy_explainer_agent(
         backstory="""You are a patient trading strategy explainer. You translate complex 
         strategy configurations into easy-to-understand language. You help users understand 
         exactly what their strategies will do when triggered.""",
-        llm=MiniMaxLLM(api_key=api_key, model=model),
+        llm=LLM(model=model, api_key=api_key, api_base="https://api.minimax.io/v1"),
         verbose=True,
     )
 

src/backend/app/services/ai_agent/llm_connector.py

@@ -1,11 +1,9 @@
 from typing import Optional, List, Dict, Any
 import httpx
-from crewai import LLM
 
 
-class MiniMaxLLM(LLM):
+class MiniMaxLLM:
     def __init__(self, api_key: str, model: str = "MiniMax-M2.7", **kwargs):
-        super().__init__(**kwargs)
         self.api_key = api_key
         self.model = model
         self.base_url = "https://api.minimax.io/v1"
@@ -23,7 +21,7 @@ class MiniMaxLLM(LLM):
         }
         with httpx.Client(timeout=60.0) as client:
             response = client.post(
-                f"{self.base_url}/chat/completions",
+                f"{self.base_url}/text/chatcompletion_v2",
                 headers=headers,
                 json=payload,
             )
@@ -35,7 +33,7 @@ class MiniMaxLLM(LLM):
 
 
 class MiniMaxConnector:
-    def __init__(self, api_key: str, model: str = "MiniMax-Text-01"):
+    def __init__(self, api_key: str, model: str = "MiniMax-M2.7"):
         self.api_key = api_key
         self.model = model
 

src/frontend/src/routes/bot/[id]/+page.svelte

@@ -44,6 +44,9 @@
 		
 		isSending = true;
 
+		// Add user's message immediately
+		addMessage({ role: 'user', content: message });
+
 		try {
 			const response = await api.bots.chat(botId, message);
 			addMessage({ role: 'assistant', content: response.response });