feat(copilot): enhance prompt system and add Markdown rendering for ghost text

- Rewrite prompt builder with comprehensive rules for seamless text completion
- Implement Markdown parsing for ghost text with proper mark handling
- Update LLM parameters (temperature 0.7, repeat_penalty, think mode)
- Add CSS styles for formatted ghost text elements
- Add planning documentation for Copilot prompt system analysis

backend/llm.py

@@ -1,52 +1,38 @@
 import os
-import json
 import ollama
-from typing import AsyncGenerator
+from dotenv import load_dotenv
+
+load_dotenv()
 
 OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
 OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
 
-if OLLAMA_HOST.endswith('/v1/'):
-    OLLAMA_HOST = OLLAMA_HOST[:-4]
-elif OLLAMA_HOST.endswith('/v1'):
-    OLLAMA_HOST = OLLAMA_HOST[:-3]
-
-os.environ['OLLAMA_HOST'] = OLLAMA_HOST
-
-print(f"[LLM] Ollama host: {OLLAMA_HOST}")
-print(f"[LLM] Model: {OLLAMA_MODEL}")
-
 client = ollama.AsyncClient(host=OLLAMA_HOST)
 
-async def stream_openai(prompt: str) -> AsyncGenerator[str, None]:
-    print(f"[LLM] Calling Ollama API with prompt length: {len(prompt)}")
+async def call_ollama(prompt: str) -> dict:
+    """
+    调用 Ollama API 并返回 content 和 thinking。
+    """
+    response = await client.chat(
+        model=OLLAMA_MODEL,
+        messages=[{'role': 'user', 'content': prompt}],
+        stream=False,
+        options={
+            'temperature': 0.7,
+            'repeat_penalty': 1.1,
+        },
+        think='high'
+    )
     
-    try:
-        print(f"[LLM] Awaiting client.chat...")
-        stream = await client.chat(
-            model=OLLAMA_MODEL,
-            messages=[{'role': 'user', 'content': prompt}],
-            stream=True,
-            options={
-                'temperature': 0.7,
-                'repeat_penalty': 1.1,
-            },
-            think='high'
-        )
-        print(f"[LLM] Got stream object, starting iteration...")
-        
-        chunk_count = 0
-        async for chunk in stream:
-            if chunk['message'] and chunk['message']['content']:
-                content = chunk['message']['content']
-                chunk_count += 1
-                print(f"[LLM] Chunk {chunk_count}: {content}")
-                yield json.dumps({"content": content})
-        
-        print(f"[LLM] Stream complete, total chunks: {chunk_count}")
-    except Exception as e:
-        error_msg = f"Error: {str(e)}"
-        print(f"[LLM] Error: {error_msg}")
-        import traceback
-        traceback.print_exc()
-        yield json.dumps({"error": str(e)})
+    content = ""
+    thinking = ""
+    
+    if hasattr(response, 'message') and response.message:
+        content = response.message.content or ""
+        thinking = getattr(response.message, 'thinking', '') or ""
+    elif isinstance(response, dict):
+        msg = response.get('message', {})
+        content = msg.get('content', '') or ""
+        thinking = msg.get('thinking', '') or ""
+    
+    return {"content": content, "thinking": thinking}