fix: use MiniMax text/chatcompletion_v2 endpoint instead of chat/completions

The /v1/chat/completions endpoint returns 529 (overloaded) while
/v1/text/chatcompletion_v2 works reliably.

src/backend/.env.example

@@ -32,7 +32,7 @@ MINIMAX_API_KEY=your-minimax-api-key
 
 # MiniMax model to use
 # Common options: MiniMax-Text-01, MiniMax-M2.1
-MINIMAX_MODEL=MiniMax-Text-01
+MINIMAX_MODEL=MiniMax-M2.7
 
 # =============================================================================
 # AVE CLOUD API

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/__init__.py

@@ -1,4 +1,4 @@
-from .crew import CrewAgent
+from .crew import TradingCrew, get_trading_crew
-from .llm_connector import LLMConnector
+from .llm_connector import MiniMaxLLM, MiniMaxConnector
 
-__all__ = ["CrewAgent", "LLMConnector"]
+__all__ = ["TradingCrew", "get_trading_crew", "MiniMaxLLM", "MiniMaxConnector"]

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

@@ -1,7 +1,7 @@
 from typing import List, Optional, Dict, Any
-from crewai import Agent, Task, Crew
+from crewai import Agent, Task, Crew, LLM
-from .llm_connector import MiniMaxConnector, MiniMaxLLM
+from .llm_connector import MiniMaxConnector
-from ..core.config import get_settings
+from ...core.config import get_settings
 
 
 class StrategyValidator:
@@ -120,7 +120,7 @@ class StrategyExplainer:
 
 
 def create_trading_designer_agent(
-    api_key: str, model: str = "MiniMax-Text-01"
+    api_key: str, model: str = "MiniMax-M2.7"
 ) -> Agent:
     connector = MiniMaxConnector(api_key=api_key, model=model)
 
@@ -141,13 +141,13 @@ 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,
     )
 
 
 def create_strategy_validator_agent(
-    api_key: str, model: str = "MiniMax-Text-01"
+    api_key: str, model: str = "MiniMax-M2.7"
 ) -> Agent:
     return Agent(
         role="Strategy Validator",
@@ -155,13 +155,13 @@ 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,
     )
 
 
 def create_strategy_explainer_agent(
-    api_key: str, model: str = "MiniMax-Text-01"
+    api_key: str, model: str = "MiniMax-M2.7"
 ) -> Agent:
     return Agent(
         role="Strategy Explainer",
@@ -169,13 +169,13 @@ 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,
     )
 
 
 class TradingCrew:
-    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
         self.validator = StrategyValidator()

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

@@ -1,14 +1,12 @@
 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-Text-01", **kwargs):
+    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.chat/v1"
+        self.base_url = "https://api.minimax.io/v1"
 
     def _call(self, messages: List[Dict[str, str]], **kwargs) -> str:
         headers = {
@@ -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,
             )

src/backend/app/services/ave/client.py

@@ -90,6 +90,22 @@ class AveCloudClient:
                 return data.get("data", [])
             raise Exception(f"Failed to fetch klines: {data}")
 
+    async def get_token_price(self, token_id: str) -> Optional[Dict[str, Any]]:
+        url = f"{self.DATA_API_URL}/v2/tokens/price"
+        async with httpx.AsyncClient() as client:
+            response = await client.post(
+                url,
+                headers=self._data_headers(),
+                json={"token_ids": [token_id]},
+                timeout=30.0,
+            )
+            response.raise_for_status()
+            data = response.json()
+            if data.get("status") == 200:
+                prices = data.get("data", {})
+                return prices.get(token_id)
+            return None
+
     async def get_trending_tokens(
         self, chain: Optional[str] = None, limit: int = 20
     ) -> List[Dict[str, Any]]:

src/backend/app/services/backtest/ave_client.py

@@ -1,70 +0,0 @@
-import httpx
-from typing import List, Dict, Any, Optional
-from datetime import datetime
-
-
-class AveCloudClient:
-    BASE_URL = "https://prod.ave-api.com"
-
-    def __init__(self, api_key: str, plan: str = "free"):
-        self.api_key = api_key
-        self.plan = plan
-
-    def _headers(self) -> Dict[str, str]:
-        return {"X-API-KEY": self.api_key}
-
-    async def get_klines(
-        self,
-        token_id: str,
-        interval: str = "1h",
-        limit: int = 100,
-        start_time: Optional[int] = None,
-        end_time: Optional[int] = None,
-    ) -> List[Dict[str, Any]]:
-        url = f"{self.BASE_URL}/v2/klines/token/{token_id}"
-        params = {"interval": interval, "limit": limit}
-        if start_time:
-            params["start_time"] = start_time
-        if end_time:
-            params["end_time"] = end_time
-
-        async with httpx.AsyncClient() as client:
-            response = await client.get(
-                url, headers=self._headers(), params=params, timeout=30.0
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("status") == 200:
-                return data.get("data", [])
-            raise Exception(f"Failed to fetch klines: {data}")
-
-    async def get_token_price(self, token_id: str) -> Optional[Dict[str, Any]]:
-        url = f"{self.BASE_URL}/v2/tokens/price"
-        async with httpx.AsyncClient() as client:
-            response = await client.post(
-                url,
-                headers=self._headers(),
-                json={"token_ids": [token_id]},
-                timeout=30.0,
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("status") == 200:
-                prices = data.get("data", {})
-                return prices.get(token_id)
-            return None
-
-    async def get_batch_prices(self, token_ids: List[str]) -> Dict[str, Dict[str, Any]]:
-        url = f"{self.BASE_URL}/v2/tokens/price"
-        async with httpx.AsyncClient() as client:
-            response = await client.post(
-                url,
-                headers=self._headers(),
-                json={"token_ids": token_ids},
-                timeout=30.0,
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("status") == 200:
-                return data.get("data", {})
-            return {}

src/backend/app/services/backtest/engine.py

@@ -2,7 +2,7 @@ import uuid
 import asyncio
 from datetime import datetime
 from typing import Dict, Any, List, Optional
-from .ave_client import AveCloudClient
+from ..ave.client import AveCloudClient
 
 
 class BacktestEngine:

src/backend/app/services/simulate/engine.py

@@ -1,8 +1,11 @@
 import uuid
 import asyncio
+import logging
 from datetime import datetime
 from typing import Dict, Any, List, Optional
-from ..backtest.ave_client import AveCloudClient
+from ..ave.client import AveCloudClient
+
+logger = logging.getLogger(__name__)
 
 
 class SimulateEngine:
@@ -38,6 +41,7 @@ class SimulateEngine:
         self.entry_time: Optional[int] = None
         self.current_balance: float = config.get("initial_balance", 10000.0)
         self.trades: List[Dict[str, Any]] = []
+        self.errors: List[str] = []
 
     async def run(self) -> Dict[str, Any]:
         self.running = True
@@ -74,7 +78,9 @@ class SimulateEngine:
                         self.last_volume = current_volume
 
                 except Exception as e:
-                    pass
+                    logger.warning(f"Failed to get price for {token_id}: {e}")
+                    self.errors.append(f"Price fetch failed for {token_id}: {str(e)}")
+                    continue
 
                 for _ in range(self.check_interval):
                     if not self.running:
@@ -92,6 +98,8 @@ class SimulateEngine:
 
         self.results = self.results or {}
         self.results["total_signals"] = len(self.signals)
+        self.results["total_errors"] = len(self.errors)
+        self.results["errors"] = self.errors
         self.results["signals"] = self.signals
         self.results["started_at"] = self.started_at
         self.results["ended_at"] = datetime.utcnow()

src/backend/requirements.txt

@@ -6,6 +6,7 @@ pydantic-settings>=2.1.0
 email-validator>=2.0.0
 python-jose[cryptography]>=3.3.0
 passlib[bcrypt]>=1.7.4
+bcrypt>=4.0,<5.0  # Required for passlib compatibility
 crewai>=0.1.0
 anthropic>=0.18.0
 httpx>=0.26.0