feat: Add input validation and type hints

- Add validation for empty messages, temperature range, max_tokens
- Improve type hints with return type annotations
- Better error messages for validation failures

Testing CodeRabbit integration

.coderabbit.yaml

@@ -0,0 +1,30 @@
+# CodeRabbit configuration
+# See: https://docs.coderabbit.ai/configuration
+
+language: python
+
+review:
+  # Enable/disable review
+  enabled: true
+  
+  # Paths to include/exclude
+  paths:
+    - "app/**"
+    - "tests/**"
+    - "*.py"
+  
+  # Review settings
+  simple: false  # Set to true for faster, simpler reviews
+  high_level_summary: true
+  estimate_time: true
+  project_language: python
+
+chat:
+  enabled: true
+  # Allow asking questions about code in PR
+
+complaints:
+  # What CodeRabbit should focus on
+  enabled: true
+  # Include security, performance, and code quality checks
+

app/main.py

@@ -1,3 +1,4 @@
+from typing import Dict
 from fastapi import FastAPI
 from app.middleware import api_key_guard
 from app.routers import openai_api
@@ -38,7 +39,8 @@ async def startup_event():
     logger.info("Model initialization started in background")
 
 @app.get("/")
-async def root():
+async def root() -> Dict[str, str]:
+    """Root endpoint returning API status and information."""
     return {
         "status": "ok", 
         "service": "Qwen Open Finance R 8B Inference", 
@@ -48,7 +50,8 @@ async def root():
     }
 
 @app.get("/health")
-async def health():
+async def health() -> Dict[str, str]:
+    """Health check endpoint."""
     return {"status": "healthy", "service": "LLM Pro Finance API"}
 
 

app/routers/openai_api.py

@@ -54,6 +54,13 @@ async def reload_model(force: bool = Query(False, description="Force reload from
 async def chat_completions(body: ChatCompletionRequest):
     """Chat completions endpoint (OpenAI-compatible)"""
     try:
+        # Validate messages list is not empty
+        if not body.messages:
+            return JSONResponse(
+                status_code=400,
+                content={"error": {"message": "messages list cannot be empty", "type": "invalid_request_error"}}
+            )
+        
         # Build payload with all supported parameters
         payload: Dict[str, Any] = {
             "model": body.model or settings.model,
@@ -63,8 +70,20 @@ async def chat_completions(body: ChatCompletionRequest):
             "stream": body.stream or False,
         }
         
+        # Validate temperature range
+        if payload["temperature"] < 0 or payload["temperature"] > 2:
+            return JSONResponse(
+                status_code=400,
+                content={"error": {"message": "temperature must be between 0 and 2", "type": "invalid_request_error"}}
+            )
+        
         # Add optional max_tokens if provided
         if body.max_tokens is not None:
+            if body.max_tokens < 1:
+                return JSONResponse(
+                    status_code=400,
+                    content={"error": {"message": "max_tokens must be at least 1", "type": "invalid_request_error"}}
+                )
             payload["max_tokens"] = body.max_tokens
         
         logger.info(f"Chat completion request: model={payload['model']}, messages={len(payload['messages'])}, stream={payload['stream']}")