Adopt Hyper3-CLIP v1 model name

Author: mnm-matin

.agents/skills/hyperview-cli/SKILL.md

@@ -105,7 +105,7 @@ Read [references/extensions.md](references/extensions.md) when the task involves
 - Treat dataset creation and workspace binding as separate steps when needed: `dataset create ...` creates persisted data, `workspace create --dataset ...` or `workspace set-dataset ...` binds it to a workspace.
 - Prefer `workspace create --dataset ...` over separate create and dataset-attach calls when setting up a new workspace.
 - In Python dataset setup code, use public ingestion helpers such as `dataset.add_samples([...])` or `dataset.add_images_dir(...)`.
-- Prefer built-in providers before registering custom providers. For Hyper3-CLIP, use `dataset.compute_embeddings(model="hyper3-clip-v0.5", provider="hyper-models")`.
+- Prefer built-in providers before registering custom providers. For Hyper3-CLIP, use `dataset.compute_embeddings(model="hyper3-clip-v1", provider="hyper-models")`.
 - In comparison demos, fail fast when a required model/provider cannot compute embeddings; do not silently substitute the baseline model as a "candidate" fallback.
 - When a project truly needs a custom Python provider, use `hyperview provider register ...` from the CLI or `hv.register_provider(...)` in Python.
 - For custom panel code, create an extension under `.hyperview/extensions/<extension-name>/`; do not register arbitrary panel module files directly.

.agents/skills/hyperview-cli/references/commands.md

@@ -110,7 +110,7 @@ Use built-in providers directly when possible. Hyper3-CLIP is available through
 the `hyper-models` provider:
 
 ```python
-dataset.compute_embeddings(model="hyper3-clip-v0.5", provider="hyper-models")
+dataset.compute_embeddings(model="hyper3-clip-v1", provider="hyper-models")
 ```
 
 Register a custom provider only when the model is not available through a

pyproject.toml

@@ -28,10 +28,11 @@ dependencies = [
     "uvicorn[standard]>=0.40.0",
     "embed-anything>=0.7.0",
     "huggingface-hub>=1.11.0,<2.0",
-    # 0.3.1 is the floor, not a preference: 0.3.0 loads the Hyper3-CLIP v0.5 text
+    # 0.3.2 is the floor, not a preference: it publishes the Hyper3-CLIP v1
+    # catalog name. 0.3.0 also loads the Hyper3-CLIP text
     # tower with randomly initialised weights and still returns embeddings, so a
     # resolver allowed to keep 0.3.0 gives silently meaningless text search.
-    "hyper-models>=0.3.1",  # PyPI package: https://pypi.org/project/hyper-models/
+    "hyper-models>=0.3.2",  # PyPI package: https://pypi.org/project/hyper-models/
     "numpy>=1.26.4,<2.4",
     "umap-learn>=0.5.11",
     "pillow>=12.1.0",
@@ -61,7 +62,7 @@ publish = [
     "huggingface-hub>=1.11.0,<2.0",
 ]
 ml = [
-    "hyper-models[ml]>=0.3.1",
+    "hyper-models[ml]>=0.3.2",
     "torch>=2.9.1",
     "torchvision>=0.24.1",
     "timm>=1.0.0",

tests/test_public_panel_api.py

@@ -324,28 +324,28 @@ def test_find_layout_separates_two_spaces_of_one_model_by_modality() -> None:
     dataset = _make_dataset(f"find_layout_modality_{uuid4().hex}")
     image_only = _add_layout(
         dataset,
-        model_id="hyper3-clip-v0.5",
+        model_id="hyper3-clip-v1",
         provider="hyper-models",
         geometry="poincare",
         modality="image",
         space_key="hyper3-clip-v0_5__image",
     )
     multimodal = _add_layout(
         dataset,
-        model_id="hyper3-clip-v0.5",
+        model_id="hyper3-clip-v1",
         provider="hyper-models",
         geometry="poincare",
         modality="multimodal",
         space_key="hyper3-clip-v0_5__multimodal",
     )
     assert image_only != multimodal
 
-    assert dataset.find_layout(model="hyper3-clip-v0.5", modality="image") == image_only
-    assert dataset.find_layout(model="hyper3-clip-v0.5", modality="multimodal") == multimodal
+    assert dataset.find_layout(model="hyper3-clip-v1", modality="image") == image_only
+    assert dataset.find_layout(model="hyper3-clip-v1", modality="multimodal") == multimodal
 
     # Without the modality the two are indistinguishable, and the error says so.
     with pytest.raises(ValueError) as error:
-        dataset.find_layout(model="hyper3-clip-v0.5", geometry="poincare")
+        dataset.find_layout(model="hyper3-clip-v1", geometry="poincare")
     assert "modality=image" in str(error.value)
     assert "modality=multimodal" in str(error.value)
 

tests/test_text_retrieval.py

@@ -205,25 +205,25 @@ def test_embed_anything_text_query_passes_list_to_model() -> None:
 
 
 def test_hyper_models_image_only_model_does_not_claim_text_support() -> None:
-    provider = HyperModelsEmbeddings(name="hyper3-clip-v0.5")
+    provider = HyperModelsEmbeddings(name="hyper3-clip-v1")
     provider._model_info = SimpleNamespace(input_name="image", geometry="hyperboloid", dim=513)
 
     assert provider.supports == frozenset({"image"})
 
     with pytest.raises(
         ValueError,
-        match=r"hyper-models model 'hyper3-clip-v0.5' does not support text queries",
+        match=r"hyper-models model 'hyper3-clip-v1' does not support text queries",
     ):
         provider.compute_query_embeddings("dog in park")
 
 
 def test_hyper_models_image_only_text_search_fails_before_encoding() -> None:
-    provider = HyperModelsEmbeddings(name="hyper3-clip-v0.5")
+    provider = HyperModelsEmbeddings(name="hyper3-clip-v1")
     provider._model_info = SimpleNamespace(input_name="image", geometry="hyperboloid", dim=513)
     engine = EmbeddingEngine()
     spec = EmbeddingSpec(
         provider="hyper-models",
-        model_id="hyper3-clip-v0.5",
+        model_id="hyper3-clip-v1",
         modality="multimodal",
     )
     engine._cache[spec.content_hash()] = provider