Do not bind a port; let the Space runner serve the ASGI app

The runner already serves the module-level app, so our own uvicorn.run was a
second server competing for 7860 — the container died on 'address already in
use' right after startup completed. Mount the Blocks UI onto the same app at
import time instead, keeping /asr and /translate at the root.

app.py

@@ -225,34 +225,40 @@ def translate(body: TranslateIn, x_service_token: str = Header(default=None)):
 
 
 # ------------------------------------------------------------------- LAUNCH ---
-# A Gradio-SDK Space runs `python app.py` and expects something listening on
-# 7860. Mounting the Blocks onto our own FastAPI (rather than calling
-# demo.launch()) keeps /asr and /translate at the root, where the backend
-# already expects them, and puts the UI at /ui.
-def _ui_check(_):
+# The Space runner serves the module-level `app` itself. Binding a port here as
+# well is what produced "address already in use" and killed the container: two
+# servers competing for 7860. So this module defines the ASGI app and never
+# listens.
+#
+# The Blocks UI is grafted onto that same app at import time, which keeps /asr
+# and /translate at the root where the backend expects them, with a status page
+# at /ui.
+def _ui_check():
     import json as _json
     return _json.dumps(health(), indent=2)
 
 
+_UI_TEXT = (
+    "## ScriptFlow inference service\n\n"
+    "Hausa ASR + Hausa->English MT. The REST API is the real interface:\n\n"
+    "- `POST /asr` — raw audio bytes as the body\n"
+    "- `POST /translate` — `{\"texts\": [...]}`\n\n"
+    "Both take an `X-Service-Token` header. The first call after a cold start "
+    "downloads ~1GB of weights and takes several minutes."
+)
+
+
 def _build_ui():
     import gradio as gr
     with gr.Blocks(title="ScriptFlow Hausa inference") as demo:
-        gr.Markdown(
-            "## ScriptFlow inference service\n"
-            "Hausa ASR + Hausa→English MT. The REST API is the real interface:\n"
-            "`POST /asr` (raw audio body) and `POST /translate` "
-            "(`{\"texts\": [...]}`), both with an `X-Service-Token` header.\n\n"
-            "Press the button to see whether the models have loaded — the first "
-            "call after a cold start downloads ~1GB and takes several minutes."
-        )
+        gr.Markdown(_UI_TEXT)
         out = gr.Code(label="GET /", language="json")
-        gr.Button("Check status").click(_ui_check, inputs=[gr.State(None)], outputs=out)
+        gr.Button("Check status").click(_ui_check, inputs=None, outputs=out)
     return demo
 
 
-if __name__ == "__main__":
-    import uvicorn
+try:
     import gradio as gr
-
-    application = gr.mount_gradio_app(app, _build_ui(), path="/ui")
-    uvicorn.run(application, host="0.0.0.0", port=int(os.environ.get("PORT", 7860)))
+    app = gr.mount_gradio_app(app, _build_ui(), path="/ui")
+except Exception as _e:                       # never let the UI break the API
+    print(f"gradio UI unavailable ({type(_e).__name__}: {_e}) — REST only", flush=True)