Show datasets under the title; vision calls use the caller's token

The public Space stores no token. Back-translation and recognition run
on the signed-in user's account (HF OAuth, inference-api scope) or an
MCP caller's Bearer token, so the owner's credits are never spent.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -8,6 +8,9 @@ sdk_version: 6.27.0
 python_version: '3.12'
 app_file: app.py
 pinned: false
+hf_oauth: true
+hf_oauth_scopes:
+  - inference-api
 short_description: Visualisation and speed of input attempt
 ---
 

SPEC.md

@@ -101,7 +101,10 @@ Ladder rungs: original → 20k / 5k / 1k / 250 / 60 faces → convex hull → or
 box. With `check_recognition`, a vision model names each rung, and
 `simplest_recognized` is the lowest rung that still reads as the word.
 
-Secrets: `HF_TOKEN` (vision model calls). Optional env: `VLM_MODEL`, `VLI_CACHE`.
+**No secrets.** The Space is public, so it stores no token. Datasets are public
+and download without one. Vision-model calls (back-translation, recognition) use
+the **caller's** token: HF sign-in in the UI (`hf_oauth`, `inference-api` scope),
+or a Bearer `Authorization` header from MCP clients. Optional env: `VLM_MODEL`, `VLI_CACHE`.
 
 ## Known gaps / open questions
 

app.py

@@ -35,6 +35,14 @@ def _json(text, name, default=None):
         raise ValueError(f"{name} is not valid JSON")
 
 
+def _user_token(oauth_token, request):
+    """The caller's own token: from HF sign-in (UI) or a Bearer header (MCP). Never the Space's."""
+    if oauth_token is not None and oauth_token.token:
+        return oauth_token.token
+    auth = (request.headers.get("authorization", "") if request is not None else "")
+    return auth[7:].strip() if auth.lower().startswith("bearer ") else None
+
+
 def _seed(value):
     """Seeds arrive as strings (some MCP clients can't send numbers)."""
     try:
@@ -129,7 +137,8 @@ def refine_scene(ledger_json: str, changes_json: str = "[]", seed: str = "0") ->
         _fail(e)
 
 
-def simplify_item(ledger_json: str, item_id: str, check_recognition: bool = False) -> tuple[str, list, list]:
+def simplify_item(ledger_json: str, item_id: str, check_recognition: bool = False,
+                  oauth_token: gr.OAuthToken | None = None, request: gr.Request = None) -> tuple[str, list, list]:
     """Build the simplification ladder for one object: full asset -> fewer faces -> convex hull -> box.
 
     With check_recognition, a vision model names each rung's picture; the lowest rung
@@ -138,12 +147,16 @@ def simplify_item(ledger_json: str, item_id: str, check_recognition: bool = Fals
     Args:
         ledger_json: Ledger JSON from translate_to_scene or refine_scene.
         item_id: The object item to simplify, e.g. "n1".
-        check_recognition: Ask a vision model to name each rung (needs HF_TOKEN; slower).
+        check_recognition: Ask a vision model to name each rung (slower; runs on the caller's
+            own HF account, so it needs sign-in or a Bearer token).
 
     Returns:
         (report JSON string, gallery of rung pictures, GLB file per rung).
     """
     try:
+        token = _user_token(oauth_token, request) if check_recognition else None
+        if check_recognition and not token:
+            raise ValueError(vlm.SIGN_IN)  # before any heavy work
         ledger = _json(ledger_json, "ledger_json")
         item = next((i for i in ledger["items"] if i["id"] == item_id), None)
         if item is None or item["kind"] != "object":
@@ -158,7 +171,7 @@ def simplify_item(ledger_json: str, item_id: str, check_recognition: bool = Fals
             rung.export(glb)
             entry = {"rung": label, **simplify.stats(rung)}
             if check_recognition:
-                answer = vlm.name_object(png)
+                answer = vlm.name_object(png, token)
                 entry["named_as"] = answer
                 entry["recognized"] = item["word"].lower() in answer.lower()
             report["rungs"].append(entry)
@@ -172,10 +185,12 @@ def simplify_item(ledger_json: str, item_id: str, check_recognition: bool = Fals
         _fail(e)
 
 
-def describe_scene(ledger_json: str, seed: str = "0") -> str:
+def describe_scene(ledger_json: str, seed: str = "0",
+                   oauth_token: gr.OAuthToken | None = None, request: gr.Request = None) -> str:
     """Back-translate: render the ledger's scene and have a vision model describe it in English.
 
     Comparing the description with the original sentence checks the translation.
+    The vision model runs on the caller's own HF account (sign-in or Bearer token).
 
     Args:
         ledger_json: Ledger JSON from translate_to_scene or refine_scene.
@@ -185,11 +200,14 @@ def describe_scene(ledger_json: str, seed: str = "0") -> str:
         JSON string: {"original", "back_translation", "nouns_recovered": {word: bool}}.
     """
     try:
+        token = _user_token(oauth_token, request)
+        if not token:
+            raise ValueError(vlm.SIGN_IN)  # before any heavy work
         ledger = _json(ledger_json, "ledger_json")
         meshes = pipeline.settle_all(ledger)
         config = scene.configure(ledger, meshes, _seed(seed))
         png = scene.render_scene(ledger, meshes, config, os.path.join(tempfile.mkdtemp(), "scene.png"))
-        text = vlm.describe(png)
+        text = vlm.describe(png, token)
         nouns = [i["word"] for i in ledger["items"] if i["kind"] == "object"]
         return json.dumps({"original": ledger["sentence"], "back_translation": text,
                            "nouns_recovered": {n: n in text.lower() for n in nouns}}, indent=1)
@@ -234,9 +252,26 @@ def _use_primitive(primitives_json, word, shape):
 
 EXAMPLE_CHANGES = '[\n  {"id": "n1", "freeze": true},\n  {"reroll": true}\n]'
 
+DATASETS_MD = """
+**Dictionary (public datasets, read-only):**
+1. [NVIDIA SimReady](https://github.com/NVIDIA-Omniverse/simready-central): metric OpenUSD assets,
+   e.g. [nvidia/simready-assets](https://huggingface.co/datasets/nvidia/simready-assets). License per package
+   (e.g. CC-BY-4.0). Only geometry and the thumbnail are downloaded, not the ~1 GB of textures.
+2. [allenai/objaverse](https://huggingface.co/datasets/allenai/objaverse): the LVIS-labelled subset.
+   License per object; non-commercial (NC) and no-derivatives (ND) objects are skipped.
+3. Missing words: a primitive you choose (box, sphere, cylinder, cone, plane). Generation comes later.
+
+**Why sign in?** Building scenes needs no account: the datasets are public. Only *Back-translation* and
+*Check recognition* call a vision model ([Qwen2.5-VL](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
+via HF Inference), and those calls run on **your own** Hugging Face account. This Space stores no token,
+so nobody's credits are spent but the caller's.
+"""
+
 with gr.Blocks(title="VisualLearningIdea") as demo:
     gr.Markdown("# English → 3D\nType with the words the 3D dictionary has. **Bold** = an object asset; "
                 "verbs and prepositions are relations between meshes.")
+    gr.Markdown(DATASETS_MD)
+    gr.LoginButton()
     with gr.Row():
         sentence = gr.Textbox(label="Sentence", placeholder="the cat sat and the sun shone", scale=4)
         seed = gr.Textbox(label="Configuration seed", value="0", scale=1)

vli/vlm.py

@@ -1,16 +1,24 @@
-"""Back-translation: a vision model reads the picture back into English."""
+"""Back-translation: a vision model reads the picture back into English.
+
+Calls always use the *caller's* token, never one stored on the Space, so a
+public Space can't spend its owner's inference credits.
+"""
 import base64
 import os
 
 from huggingface_hub import InferenceClient
 
 VLM_MODEL = os.environ.get("VLM_MODEL", "Qwen/Qwen2.5-VL-7B-Instruct")
+SIGN_IN = ("The vision model runs on your own Hugging Face account: sign in first "
+           "(MCP callers: send your HF token as a Bearer Authorization header).")
 
 
-def ask(image_path, prompt, max_tokens=80):
+def ask(image_path, prompt, token, max_tokens=80):
+    if not token:
+        raise ValueError(SIGN_IN)
     with open(image_path, "rb") as f:
         data = base64.b64encode(f.read()).decode()
-    client = InferenceClient(token=os.environ.get("HF_TOKEN"))
+    client = InferenceClient(token=token)
     resp = client.chat_completion(
         model=VLM_MODEL, max_tokens=max_tokens,
         messages=[{"role": "user", "content": [
@@ -19,9 +27,9 @@ def ask(image_path, prompt, max_tokens=80):
     return resp.choices[0].message.content.strip()
 
 
-def describe(image_path):
-    return ask(image_path, "Describe this 3D scene in one short plain sentence.")
+def describe(image_path, token):
+    return ask(image_path, "Describe this 3D scene in one short plain sentence.", token)
 
 
-def name_object(image_path):
-    return ask(image_path, "What single object is this? Answer with one or two words.", max_tokens=10)
+def name_object(image_path, token):
+    return ask(image_path, "What single object is this? Answer with one or two words.", token, max_tokens=10)