Merge remote-tracking branch 'origin/main' into prep/pr-659

# Conflicts:
#	backend/database/models.py

backend/routes/models.py

@@ -244,6 +244,7 @@ async def get_model_status():
         use_scan_cache = False
 
     from ..backends import get_all_model_configs, check_model_loaded
+    from ..backends.base import has_in_progress_download
 
     registry_configs = get_all_model_configs()
     model_configs = [
@@ -293,8 +294,7 @@ async def get_model_status():
                         try:
                             cache_dir = hf_constants.HF_HUB_CACHE
                             blobs_dir = Path(cache_dir) / ("models--" + repo_id.replace("/", "--")) / "blobs"
-                            if blobs_dir.exists():
-                                has_incomplete = any(blobs_dir.glob("*.incomplete"))
+                            has_incomplete = has_in_progress_download(blobs_dir)
                         except Exception:
                             pass
 
@@ -314,7 +314,7 @@ async def get_model_status():
 
                     if repo_cache.exists():
                         blobs_dir = repo_cache / "blobs"
-                        has_incomplete = blobs_dir.exists() and any(blobs_dir.glob("*.incomplete"))
+                        has_incomplete = has_in_progress_download(blobs_dir)
 
                         if not has_incomplete:
                             snapshots_dir = repo_cache / "snapshots"

backend/routes/speak.py

@@ -1,4 +1,4 @@
-"""POST /speak — REST wrapper around voicebox.speak for non-MCP callers.
+"""POST /speak — REST wrapper around voicebox_speak for non-MCP callers.
 
 Shell scripts, ACP, A2A, or any agent that doesn't speak MCP can hit this
 endpoint to play text through a cloned voice. Uses the same profile
@@ -30,7 +30,7 @@ async def speak(
     request: Request,
     db: Session = Depends(get_db),
 ):
-    """Speak text in a voice profile. Mirrors voicebox.speak (MCP).
+    """Speak text in a voice profile. Mirrors voicebox_speak (MCP).
 
     Response shape matches POST /generate — a ``GenerationResponse`` with
     ``status="generating"`` and an ``id`` the caller polls at
@@ -75,7 +75,7 @@ async def speak(
         models.GenerationRequest(
             profile_id=profile.id,
             text=data.text,
-            language=data.language or "en",
+            language=data.language or profile.language or "en",
             engine=engine,
             personality=bool(personality_flag),
         ),