Enhance LLM functionality with PRO mode support and improved prompt handling

- Added support for PRO mode in LLM with specific instruction handling and context awareness.
- Updated prompt building functions to include prefill options for better context management.
- Introduced new inline examples for PRO mode in JSON format.
- Enhanced system prompts to reflect PRO mode capabilities and rules.
- Modified API endpoints to accommodate new parameters and ensure backward compatibility.
- Improved test cases to validate new functionality and ensure comprehensive coverage.

backend/main.py

@@ -179,7 +179,7 @@ async def create_completion(request: Request, req: CompletionRequest, api_key: s
         logger.info("[%s] llm_input_prefix=%r", request_tag, llm_prefix)
         logger.info("[%s] llm_input_suffix=%r", request_tag, llm_suffix)
 
-        system_prompt, user_prompt = build_completion_prompts(
+        system_prompt, user_prompt, prefill = build_completion_prompts(
             req.prefix,
             req.suffix,
             req.languageId,
@@ -196,6 +196,7 @@ async def create_completion(request: Request, req: CompletionRequest, api_key: s
                 temperature=_clamp_temperature(req.temperature, 0.7),
                 thinking=req.model_thinking if req.model_thinking != "none" else None,
                 model=req.model,
+                prefill=prefill or None,
             )
         )
 
@@ -262,7 +263,7 @@ async def create_pro_completion_stream(request: Request, req: CompletionRequest,
     logger.info("[%s] pro_llm_input_prefix=%r", request_tag, llm_prefix)
     logger.info("[%s] pro_llm_input_suffix=%r", request_tag, llm_suffix)
 
-    system_prompt, user_prompt = build_completion_prompts(
+    system_prompt, user_prompt, prefill = build_completion_prompts(
         req.prefix,
         req.suffix,
         req.languageId,
@@ -282,6 +283,7 @@ async def create_pro_completion_stream(request: Request, req: CompletionRequest,
                 thinking=req.model_thinking if req.model_thinking != "none" else None,
                 model=req.model,
                 use_pro_model=True,
+                prefill=prefill or None,
             ):
                 chunks.append(delta)
                 await queue.put(("chunk", json.dumps({"delta": delta}, ensure_ascii=False)))