fix: auto-fix ruff linting errors and remove unsupported upload-artifact

handler_base/clients/llm.py

@@ -1,8 +1,9 @@
 """
 LLM service client (vLLM/OpenAI-compatible).
 """
+
 import logging
-from typing import Optional, AsyncIterator
+from typing import AsyncIterator, Optional
 
 import httpx
 
@@ -15,33 +16,33 @@ logger = logging.getLogger(__name__)
 class LLMClient:
     """
     Client for the LLM service (vLLM with OpenAI-compatible API).
-    
+
     Usage:
         client = LLMClient()
         response = await client.generate("Hello, how are you?")
-        
+
         # With context for RAG
         response = await client.generate(
             "What is the capital?",
             context="France is a country in Europe..."
         )
-        
+
         # Streaming
         async for chunk in client.stream("Tell me a story"):
             print(chunk, end="")
     """
-    
+
     def __init__(self, settings: Optional[LLMSettings] = None):
         self.settings = settings or LLMSettings()
         self._client = httpx.AsyncClient(
             base_url=self.settings.llm_url,
             timeout=self.settings.http_timeout,
         )
-    
+
     async def close(self) -> None:
         """Close the HTTP client."""
         await self._client.aclose()
-    
+
     async def generate(
         self,
         prompt: str,
@@ -54,7 +55,7 @@ class LLMClient:
     ) -> str:
         """
         Generate a response from the LLM.
-        
+
         Args:
             prompt: User prompt/query
             context: Optional context for RAG
@@ -63,19 +64,19 @@ class LLMClient:
             temperature: Sampling temperature
             top_p: Top-p sampling
             stop: Stop sequences
-            
+
         Returns:
             Generated text response
         """
         with create_span("llm.generate") as span:
             messages = self._build_messages(prompt, context, system_prompt)
-            
+
             if span:
                 span.set_attribute("llm.model", self.settings.llm_model)
                 span.set_attribute("llm.prompt_length", len(prompt))
                 if context:
                     span.set_attribute("llm.context_length", len(context))
-            
+
             payload = {
                 "model": self.settings.llm_model,
                 "messages": messages,
@@ -85,21 +86,21 @@ class LLMClient:
             }
             if stop:
                 payload["stop"] = stop
-            
+
             response = await self._client.post("/v1/chat/completions", json=payload)
             response.raise_for_status()
-            
+
             result = response.json()
             content = result["choices"][0]["message"]["content"]
-            
+
             if span:
                 span.set_attribute("llm.response_length", len(content))
                 usage = result.get("usage", {})
                 span.set_attribute("llm.prompt_tokens", usage.get("prompt_tokens", 0))
                 span.set_attribute("llm.completion_tokens", usage.get("completion_tokens", 0))
-            
+
             return content
-    
+
     async def stream(
         self,
         prompt: str,
@@ -110,19 +111,19 @@ class LLMClient:
     ) -> AsyncIterator[str]:
         """
         Stream a response from the LLM.
-        
+
         Args:
             prompt: User prompt/query
             context: Optional context for RAG
             system_prompt: Optional system prompt
             max_tokens: Maximum tokens to generate
             temperature: Sampling temperature
-            
+
         Yields:
             Text chunks as they're generated
         """
         messages = self._build_messages(prompt, context, system_prompt)
-        
+
         payload = {
             "model": self.settings.llm_model,
             "messages": messages,
@@ -130,25 +131,24 @@ class LLMClient:
             "temperature": temperature or self.settings.llm_temperature,
             "stream": True,
         }
-        
-        async with self._client.stream(
-            "POST", "/v1/chat/completions", json=payload
-        ) as response:
+
+        async with self._client.stream("POST", "/v1/chat/completions", json=payload) as response:
             response.raise_for_status()
-            
+
             async for line in response.aiter_lines():
                 if line.startswith("data: "):
                     data = line[6:]
                     if data == "[DONE]":
                         break
-                    
+
                     import json
+
                     chunk = json.loads(data)
                     delta = chunk["choices"][0].get("delta", {})
                     content = delta.get("content", "")
                     if content:
                         yield content
-    
+
     def _build_messages(
         self,
         prompt: str,
@@ -157,32 +157,36 @@ class LLMClient:
     ) -> list[dict]:
         """Build the messages list for the API call."""
         messages = []
-        
+
         # System prompt
         if system_prompt:
             messages.append({"role": "system", "content": system_prompt})
         elif context:
             # Default RAG system prompt
-            messages.append({
-                "role": "system",
-                "content": (
-                    "You are a helpful assistant. Use the provided context to answer "
-                    "the user's question. If the context doesn't contain relevant "
-                    "information, say so."
-                ),
-            })
-        
+            messages.append(
+                {
+                    "role": "system",
+                    "content": (
+                        "You are a helpful assistant. Use the provided context to answer "
+                        "the user's question. If the context doesn't contain relevant "
+                        "information, say so."
+                    ),
+                }
+            )
+
         # Add context as a separate message if provided
         if context:
-            messages.append({
-                "role": "user",
-                "content": f"Context:\n{context}\n\nQuestion: {prompt}",
-            })
+            messages.append(
+                {
+                    "role": "user",
+                    "content": f"Context:\n{context}\n\nQuestion: {prompt}",
+                }
+            )
         else:
             messages.append({"role": "user", "content": prompt})
-        
+
         return messages
-    
+
     async def health(self) -> bool:
         """Check if the LLM service is healthy."""
         try: