fix: PR review nits — response shape, landing copy, form reset

- /llm/generate's "model is downloading" branch was raising HTTPException(202, detail={...}), which wraps the payload in {"detail": ...} and forces clients to parse a success status as if it were an error. Switched to JSONResponse so the payload sits at the top level.
- The landing page's "Language Models" card advertised "Qwen 3.5" with sizes 4B/2B/0.8B; we ship Qwen3 at 0.6B/1.7B/4B. Aligned to what's actually in the binary.
- ProfileForm's discard-draft button reset the form without touching `personality` or `avatarFile`, so stale persona text and an attached avatar would survive the discard. The other three resets in the file already include both fields — this brings the discard path in line.

backend/routes/llm.py

@@ -1,6 +1,7 @@
 """LLM inference endpoints."""
 
 from fastapi import APIRouter, HTTPException
+from fastapi.responses import JSONResponse
 
 from .. import models
 from ..backends import get_llm_model_configs
@@ -39,9 +40,9 @@ async def llm_generate(request: models.LLMGenerateRequest):
         task_manager.start_download(progress_model_name)
         create_background_task(download_llm_background())
 
-        raise HTTPException(
+        return JSONResponse(
             status_code=202,
-            detail={
+            content={
                 "message": f"Qwen3 {model_size} is being downloaded. Please wait and try again.",
                 "model_name": progress_model_name,
                 "downloading": True,