Gated API access: accept explicit hf_token as 6th /generate input (gr.OAuthToken is None over gradio_client)

app.py

@@ -15,12 +15,14 @@ Hugging Face and being on the allowlist (the ``ALLOWLIST`` Space variable, a
 comma-separated list of usernames). Access is requested from ``@thbndi``.
 
 Programmatic access (gradio_client / the MovetsaDataset loading script):
-  - named API endpoint ``/generate`` with the 5 inputs below, in this order:
-        window_size, overlap, normalize, include_baselines, include_familiarization
-  - identity is injected by Gradio: in the browser via ``gr.OAuthProfile``;
-    over the API via ``gr.OAuthToken`` (resolved with ``whoami``). Callers just
-    pass ``hf_token=...`` to ``gradio_client.Client(...)``.
-  - requires ``hf_oauth: true`` in the Space README front-matter.
+  - named API endpoint ``/generate`` with 6 inputs, in this order:
+        window_size, overlap, normalize, include_baselines,
+        include_familiarization, hf_token
+  - identity: in the browser via ``gr.OAuthProfile`` (the LoginButton); over
+    the API via the explicit ``hf_token`` argument, resolved with ``whoami``.
+    ``gr.OAuthToken`` is NOT populated over the gradio_client API — it only
+    works through the browser OAuth login — so headless callers must pass their
+    token as the 6th argument.
 """
 
 import os
@@ -62,29 +64,42 @@ RAW_DIR = snapshot_download(RAW_REPO, repo_type="dataset", token=TOKEN,
 from MoveTSA.export_hf_dataset import build_windows  # noqa: E402  (needs sys.path)
 
 
-def _resolve_username(profile, oauth_token):
-    """Identity from the browser OAuth profile, or from an API token."""
+def _resolve_username(profile, oauth_token, hf_token):
+    """Identity from the browser OAuth profile, or from an explicit HF token.
+
+    In the browser, Gradio injects ``profile`` after the OAuth login. Headless
+    callers (gradio_client / the MovetsaDataset loading script) cannot go
+    through the OAuth flow, so they pass their token explicitly and we resolve
+    the username with ``whoami``. ``oauth_token`` is kept as a fallback but is
+    ``None`` over the API.
+    """
     if profile is not None:
         return profile.username
-    if oauth_token is not None and getattr(oauth_token, "token", None):
+    token = None
+    if hf_token:
+        token = hf_token
+    elif oauth_token is not None and getattr(oauth_token, "token", None):
+        token = oauth_token.token
+    if token:
         try:
-            return whoami(token=oauth_token.token).get("name")
+            return whoami(token=token).get("name")
         except Exception:  # noqa: BLE001
             return None
     return None
 
 
 def generate(window_size, overlap, normalize, include_baselines,
-             include_familiarization,
+             include_familiarization, hf_token="",
              profile: gr.OAuthProfile | None = None,
              oauth_token: gr.OAuthToken | None = None):
     """Run the pipeline with the chosen parameters and return a parquet file.
 
-    ``profile`` (browser) and ``oauth_token`` (API) are injected by Gradio and
-    are NOT part of the API signature — the named endpoint only exposes the 5
-    parameters above.
+    ``hf_token`` is the 6th API input: headless callers pass their HF token so
+    the Space can identify them (the browser leaves it empty and authenticates
+    via the LoginButton). ``profile``/``oauth_token`` are injected by Gradio and
+    are NOT part of the API signature.
     """
-    username = _resolve_username(profile, oauth_token)
+    username = _resolve_username(profile, oauth_token, hf_token)
     if username is None:
         return None, "Sign in with your Hugging Face account to generate."
     if username.lower() not in ALLOWLIST:
@@ -151,6 +166,9 @@ with gr.Blocks(title="MoveTSA dataset builder") as demo:
                 value=True, label="include baselines (B1–B4)")
             include_familiarization = gr.Checkbox(
                 value=True, label="include familiarization (F)")
+            # 6th API input: headless callers pass their HF token here; the
+            # browser leaves it empty and authenticates via the LoginButton.
+            hf_token = gr.Textbox(value="", visible=False, label="hf_token")
             btn = gr.Button("Generate parquet", variant="primary")
         with gr.Column():
             status = gr.Markdown()
@@ -159,7 +177,7 @@ with gr.Blocks(title="MoveTSA dataset builder") as demo:
     btn.click(
         generate,
         inputs=[window_size, overlap, normalize, include_baselines,
-                include_familiarization],
+                include_familiarization, hf_token],
         outputs=[out_file, status],
         api_name="generate",   # => client.predict(..., api_name="/generate")
     )