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

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)