From 0aa3a8d6b4e24dccca0bacdcd17af38db47a0221 Mon Sep 17 00:00:00 2001
From: Jamie Pine <ijamespine@me.com>
Date: Sat, 25 Apr 2026 01:21:21 -0700
Subject: [PATCH] =?UTF-8?q?fix:=20PR=20review=20nits=20=E2=80=94=20respons?=
 =?UTF-8?q?e=20shape,=20landing=20copy,=20form=20reset?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- /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.
---
 app/src/components/VoiceProfiles/ProfileForm.tsx | 2 ++
 backend/routes/llm.py                            | 5 +++--
 landing/src/components/SupportedModels.tsx       | 4 ++--
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/app/src/components/VoiceProfiles/ProfileForm.tsx b/app/src/components/VoiceProfiles/ProfileForm.tsx
index 6eb03e7f..7ef4651c 100644
--- a/app/src/components/VoiceProfiles/ProfileForm.tsx
+++ b/app/src/components/VoiceProfiles/ProfileForm.tsx
@@ -828,8 +828,10 @@ export function ProfileForm() {
                       name: '',
                       description: '',
                       language: 'en',
+                      personality: '',
                       sampleFile: undefined,
                       referenceText: '',
+                      avatarFile: undefined,
                     });
                     setSampleMode('record');
                   }}
diff --git a/backend/routes/llm.py b/backend/routes/llm.py
index 53d84d0a..36f4c174 100644
--- a/backend/routes/llm.py
+++ b/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,
diff --git a/landing/src/components/SupportedModels.tsx b/landing/src/components/SupportedModels.tsx
index 6774956b..aff25cea 100644
--- a/landing/src/components/SupportedModels.tsx
+++ b/landing/src/components/SupportedModels.tsx
@@ -138,9 +138,9 @@ const MODEL_GROUPS: ModelGroup[] = [
     subtitle: 'Transcript refinement, persona replies, and on-device reasoning.',
     models: [
       {
-        name: 'Qwen 3.5',
+        name: 'Qwen3',
         author: 'Alibaba',
-        sizes: ['4B', '2B', '0.8B'],
+        sizes: ['4B', '1.7B', '0.6B'],
         description:
           'Powers transcript cleanup, persona voice replies, and the voice I/O loop. Shares its runtime with the TTS/STT stack — one model cache, one GPU story.',
         tags: [