feat: implement inline autocomplete suggestions with FastAPI backend and Milkdown editor integration

backend/.env

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=ollama
+OLLAMA_BASE_URL=http://192.168.0.120:11434/v1/
+OLLAMA_MODEL=gpt-oss:120b

backend/.env.example

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=ollama
+OLLAMA_BASE_URL=http://192.168.0.120:11434/v1/
+OLLAMA_MODEL=gpt-oss:120b

backend/llm.py

@@ -0,0 +1,44 @@
+import os
+from typing import AsyncGenerator
+from openai import AsyncOpenAI
+import json
+
+api_key = os.getenv('OPENAI_API_KEY', 'ollama')
+base_url = os.getenv('OLLAMA_BASE_URL', 'http://192.168.0.120:11434/v1/')
+model = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
+
+print(f"[LLM] API key configured: {'Yes' if api_key else 'No'}")
+print(f"[LLM] Base URL: {base_url}")
+print(f"[LLM] Model: {model}")
+
+client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+
+async def stream_openai(prompt: str) -> AsyncGenerator[str, None]:
+    """
+    调用 OpenAI/Ollama API 并流式返回补全内容。
+    参考 completions-sample-code 的 streaming 逻辑。
+    """
+    print(f"[LLM] Calling API with prompt length: {len(prompt)}")
+    
+    try:
+        stream = await client.chat.completions.create(
+            model=model,
+            messages=[{"role": "user", "content": prompt}],
+            stream=True,
+            max_tokens=128,
+            temperature=0.2,
+        )
+
+        chunk_count = 0
+        async for chunk in stream:
+            if chunk.choices[0].delta.content:
+                content = chunk.choices[0].delta.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}")
+        yield json.dumps({"error": str(e)})

backend/main.py

@@ -0,0 +1,47 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import StreamingResponse
+from pydantic import BaseModel
+import os
+import json
+
+app = FastAPI()
+
+class CompletionRequest(BaseModel):
+    prefix: str
+    suffix: str
+    languageId: str = 'markdown'
+
+def generate_stream(request: CompletionRequest):
+    from prompt import build_prompt
+    from llm import stream_openai
+    
+    print(f"[Backend] Received request - prefix length: {len(request.prefix)}, suffix length: {len(request.suffix)}")
+    
+    try:
+        prompt = build_prompt(request.prefix, request.suffix)
+        print(f"[Backend] Built prompt (first 100 chars): {prompt[:100]}...")
+        
+        async def gen():
+            chunk_count = 0
+            async for chunk in stream_openai(prompt):
+                chunk_count += 1
+                yield f"data: {chunk}\n\n"
+                if chunk_count % 5 == 0:
+                    print(f"[Backend] Sent chunk {chunk_count}")
+            yield "data: {\"done\": true}\n\n"
+            print(f"[Backend] Stream complete, total chunks: {chunk_count}")
+        return gen()
+    except Exception as e:
+        error_msg = f"{{\"error\": \"{str(e)}\"}}"
+        print(f"[Backend] Error: {e}")
+        yield f"data: {error_msg}\n\n"
+
+@app.post("/v1/completions")
+async def create_completion(request: CompletionRequest):
+    print(f"[Backend] POST /v1/completions called")
+    return StreamingResponse(generate_stream(request), media_type="text/event-stream")
+
+if __name__ == "__main__":
+    import uvicorn
+    print("[Backend] Starting server on http://0.0.0.0:8000")
+    uvicorn.run(app, host="0.0.0.0", port=8000)

backend/prompt.py

@@ -0,0 +1,28 @@
+import os
+from typing import Tuple
+
+def build_prompt(prefix: str, suffix: str) -> str:
+    """
+    构建用于代码补全的 Prompt。
+    参考 completions-sample-code 的 extractPrompt 逻辑简化实现。
+    """
+    MAX_CONTEXT_LINES = 30
+    
+    prefix_lines = prefix.split('\n')
+    suffix_lines = suffix.split('\n') if suffix else []
+    
+    recent_prefix = '\n'.join(prefix_lines[-MAX_CONTEXT_LINES:])
+    recent_suffix = '\n'.join(suffix_lines[:5])
+
+    prompt = f"""
+You are a helpful writing assistant. Continue the text naturally based on the context.
+
+Context (before cursor):
+{recent_prefix}
+
+Complete this:
+{suffix if suffix else '(cursor here)'}
+
+Continue:"""
+    
+    return prompt.strip()

backend/requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+openai
+pydantic
+python-dotenv