fix(modelscope): identify a model file by hash before filename

A file was matched to its published version by comparing basenames against
each version's `stats.fileList`.  Renaming the weights — routine once a
model is filed away, and the reason the scanner records a sha256 at all —
made the match fail silently, so the file lost its example images and its
preview with no indication why.

The detail payload's `ModelInfos.safetensor.files[]` carries a real sha256
per published file, and the local hash is already on disk, so match on that
first: it is the one identifier a rename cannot invalidate.  Exact basename
and `showName` matching remain as fallbacks, and an unknown hash falls
through to them rather than giving up, so a re-encoded file still resolves.

Verified against the live repository: a renamed `c1-st1000` file with its
hash yields the c1-st1000 image, the same rename without a hash yields
nothing, and supplying c1-st2000's hash resolves to the c1-st2000 image even
when the filename claims otherwise.

docs/agent_skills.md

@@ -104,10 +104,12 @@ boilerplate README and put everything useful in `Description`, so reading only
 the README yields almost nothing.
 
 Providers opt in by overriding `ModelSource.fetch_model_card_context()`, which
-returns a `ModelCardContext`. Example images are matched to the model's
-**basename**, so each checkpoint in a collection repo gets its own images.
-Sites with no such extras inherit an empty context, and the pipeline behaves
-exactly as before.
+returns a `ModelCardContext`. The wanted file is identified by its sha256 when
+the caller knows it (the scanner already records one) and by **basename**
+otherwise, so each checkpoint in a collection repo gets its own images — and
+keeps getting them after the user renames the weights, which is the only
+identifier a rename cannot invalidate. Sites with no such extras inherit an
+empty context, and the pipeline behaves exactly as before.
 
 The README and the repository metadata describe the whole repository, not one
 file, so `execute_skill()` creates a `ModelSourceCache` for the duration of a

py/services/agent/agent_service.py

@@ -474,9 +474,13 @@ class AgentService:
                 cache.readmes[cache_key] = readme
 
         # Sites such as ModelScope keep part of the model card outside the
-        # README (author summary, curated tags, per-file example images).
+        # README (author summary, curated tags, per-file example images).  The
+        # recorded hash identifies the file even after the user renames it.
         card_context = await source.fetch_model_card_context(
-            ref.source_id, os.path.basename(model_path), cache=cache,
+            ref.source_id,
+            os.path.basename(model_path),
+            sha256=(metadata.get("sha256") or "").strip(),
+            cache=cache,
         )
         variables["source_description"] = card_context.description
         variables["source_base_model"] = card_context.base_model

py/services/model_sources/base.py

@@ -307,19 +307,24 @@ class ModelSource:
         source_id: str,
         filename: str = "",
         *,
+        sha256: str = "",
         cache: Optional["ModelSourceCache"] = None,
     ) -> ModelCardContext:
         """Return the card extras the site keeps outside the README.
 
-        *filename* is the model file's basename (no directory) and selects
-        the right entry when a repository holds several models.  Sites whose
-        model card is fully described by :meth:`fetch_model_card` need no
-        override and inherit this empty context.
+        *filename* is the model file's basename (no directory) and *sha256*
+        its content hash; between them they select the right entry when a
+        repository holds several models.  A site that records per-file hashes
+        should prefer *sha256*, because it is the only identifier that
+        survives the user renaming the weights.
 
         *cache* is an optional per-run memo (see :class:`ModelSourceCache`)
         that lets a provider avoid re-fetching repository-wide data for every
         file in a collection repository.
 
+        Sites whose model card is fully described by :meth:`fetch_model_card`
+        need no override and inherit this empty context.
+
         Implementations must never raise: enrichment treats a missing
         context as "the site had nothing extra to say".
         """

py/services/model_sources/modelscope.py

@@ -117,6 +117,7 @@ class ModelScopeSource(ModelSource):
         source_id: str,
         filename: str = "",
         *,
+        sha256: str = "",
         cache: Optional["ModelSourceCache"] = None,
     ) -> ModelCardContext:
         """Read the model-detail API that backs the ModelScope model page.
@@ -128,10 +129,11 @@ class ModelScopeSource(ModelSource):
         no further description") and put everything useful in ``Description``,
         so enrichment that reads only the README comes back nearly empty.
 
-        Example images are matched to *filename* through each version's
-        ``stats.fileList``, which means the images returned belong to the
-        exact ``.safetensors`` being enriched — essential for collection
-        repositories, where every checkpoint has its own sample image.
+        The wanted file is identified by its sha256 when the caller knows it
+        and by *filename* otherwise; see :func:`_matching_versions`.  The
+        images and trigger words returned belong to that exact
+        ``.safetensors`` — essential for collection repositories, where every
+        checkpoint has its own sample image.
 
         The detail payload describes the whole repository and is therefore
         shared across every file in it, so it is read through *cache* when the
@@ -141,7 +143,7 @@ class ModelScopeSource(ModelSource):
         data = await self._fetch_detail(source_id, cache=cache)
         if data is None:
             return ModelCardContext()
-        return _build_card_context(data, filename)
+        return _build_card_context(data, filename, sha256)
 
     async def _fetch_detail(
         self,
@@ -245,7 +247,9 @@ def _first_string(value: Any) -> str:
     return ""
 
 
-def _build_card_context(data: dict[str, Any], filename: str) -> ModelCardContext:
+def _build_card_context(
+    data: dict[str, Any], filename: str, sha256: str = ""
+) -> ModelCardContext:
     """Turn a model-detail payload into a :class:`ModelCardContext`.
 
     Separated from the HTTP fetch so the repository-wide payload can be cached
@@ -260,7 +264,12 @@ def _build_card_context(data: dict[str, Any], filename: str) -> ModelCardContext
         official_tags=_official_tags(data.get("OfficialTags")),
     )
 
-    versions = _matching_versions(data.get("MuseInfo"), filename)
+    versions = _matching_versions(
+        data.get("MuseInfo"),
+        filename,
+        digests=_file_digests(data),
+        sha256=sha256,
+    )
     if versions:
         context.example_images = _cover_image_urls(versions)
         context.trigger_words = _version_trigger_words(versions)
@@ -350,16 +359,56 @@ def _version_show_name(version: dict[str, Any]) -> str:
     return _clean_text(model_version.get("showName")).lower()
 
 
-def _matching_versions(muse_info: Any, filename: str) -> list[dict[str, Any]]:
-    """Return the ``versions`` entries that publish *filename*.
+def _file_digests(data: dict[str, Any]) -> dict[str, str]:
+    """Return ``basename -> sha256`` for every published weight file.
 
-    Matching is by exact basename first, then by the version's ``showName``
-    appearing in the file stem (which absorbs the naming drift ModelScope
-    sometimes applies to uploaded weights).  All matches are returned so a
-    file re-published across several versions contributes all of its
-    example images.  With no *filename* only an unambiguous single-version
-    repository is used, because a per-file image must never be attributed
-    to the wrong file.
+    ``ModelInfos`` groups the repository's files by kind (``safetensor``,
+    …) and records a real sha256 for each, which is what makes it possible to
+    recognise a file the user has renamed.
+    """
+
+    digests: dict[str, str] = {}
+    model_infos = data.get("ModelInfos")
+    if not isinstance(model_infos, dict):
+        return digests
+    for info in model_infos.values():
+        files = info.get("files") if isinstance(info, dict) else None
+        if not isinstance(files, list):
+            continue
+        for entry in files:
+            if not isinstance(entry, dict):
+                continue
+            name = _clean_text(entry.get("name"))
+            digest = _clean_text(entry.get("sha256"))
+            if name and digest:
+                digests.setdefault(os.path.basename(name).lower(), digest.lower())
+    return digests
+
+
+def _matching_versions(
+    muse_info: Any,
+    filename: str,
+    *,
+    digests: dict[str, str] | None = None,
+    sha256: str = "",
+) -> list[dict[str, Any]]:
+    """Return the ``versions`` entries that publish the wanted model file.
+
+    Strategies, in order:
+
+    1. **sha256** — the file's content hash, looked up through
+       :func:`_file_digests`.  This is the only strategy that survives the
+       user renaming the weights, which is common once a model is filed away.
+    2. **Exact basename** against each version's ``stats.fileList``.
+    3. **``showName`` inside the file stem**, which absorbs the naming drift
+       ModelScope sometimes applies to uploaded weights.
+
+    A known-but-unmatched hash falls through to the filename strategies
+    rather than giving up, in case the local file was re-encoded.  All matches
+    are returned so a file re-published across several versions contributes
+    all of its example images.  With no *filename* and no *sha256*, only an
+    unambiguous single-version repository is used, because a per-file image
+    must never be attributed to the wrong file.
     """
 
     if not isinstance(muse_info, dict):
@@ -371,6 +420,18 @@ def _matching_versions(muse_info: Any, filename: str) -> list[dict[str, Any]]:
     if not entries:
         return []
 
+    target_hash = (sha256 or "").strip().lower()
+    if target_hash:
+        known = digests or {}
+        by_hash: list[dict[str, Any]] = []
+        for version in entries:
+            for path in _version_files(version):
+                if known.get(os.path.basename(path).lower()) == target_hash:
+                    by_hash.append(version)
+                    break
+        if by_hash:
+            return by_hash
+
     if not filename:
         return entries if len(entries) == 1 else []
 

tests/services/test_model_sources.py

@@ -7,9 +7,12 @@ each provider's model-card fetching and capability flags.
 
 from __future__ import annotations
 
+from unittest import mock
 import pytest
 
+from py.services.agent.agent_service import AgentService
 from py.services.model_sources import (
+    ModelCardContext,
     ModelSourceCache,
     HuggingFaceSource,
     ModelScopeSource,
@@ -381,6 +384,22 @@ def _modelscope_detail_payload() -> dict:
                     },
                 ]
             },
+            "ModelInfos": {
+                "safetensor": {
+                    "files": [
+                        {
+                            "name": "Krea-2-LORA_c1-st8000.safetensors",
+                            "sha256": "a" * 64,
+                            "size": 234680568,
+                        },
+                        {
+                            "name": "Krea-2-LORA_c1-st1000.safetensors",
+                            "sha256": "b" * 64,
+                            "size": 234680568,
+                        },
+                    ]
+                }
+            },
         },
     }
 
@@ -799,3 +818,141 @@ class TestCachedModelCardFetch:
             await source.fetch_model_card_context("u/r", "a.safetensors")
 
         assert len(calls) == 2
+
+
+class TestHashBasedVersionMatching:
+    """A renamed file must still find its own example images."""
+
+    ST1000_HASH = "b" * 64
+    ST8000_HASH = "a" * 64
+
+    @staticmethod
+    def _patch(monkeypatch):
+        async def fake_fetch_json(url, **_kwargs):
+            return 200, _modelscope_detail_payload()
+
+        monkeypatch.setattr(
+            "py.services.model_sources.modelscope.fetch_json", fake_fetch_json
+        )
+
+    @pytest.mark.asyncio
+    async def test_renamed_file_is_matched_by_sha256(self, monkeypatch):
+        self._patch(monkeypatch)
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "krea脸模-st1000-我改的名字.safetensors", sha256=self.ST1000_HASH
+        )
+
+        assert context.example_images == [
+            "https://resources.modelscope.cn/cover-images/b.png",
+            "https://resources.modelscope.cn/cover-images/c.png",
+        ]
+        assert context.trigger_words == ["kreaface", "kreamodel"]
+
+    @pytest.mark.asyncio
+    async def test_renamed_file_without_a_hash_finds_nothing(self, monkeypatch):
+        """Pins the behaviour the hash match exists to fix."""
+        self._patch(monkeypatch)
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "krea脸模-st1000-我改的名字.safetensors"
+        )
+
+        assert context.example_images == []
+        # Repo-wide fields are unaffected by the miss.
+        assert context.base_model == "krea/Krea-2-Turbo"
+
+    @pytest.mark.asyncio
+    async def test_hash_wins_over_a_filename_that_matches_another_version(
+        self, monkeypatch
+    ):
+        """An inconsistent name/hash pair trusts the content hash."""
+        self._patch(monkeypatch)
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "Krea-2-LORA_c1-st8000.safetensors", sha256=self.ST1000_HASH
+        )
+
+        assert context.example_images == [
+            "https://resources.modelscope.cn/cover-images/b.png",
+            "https://resources.modelscope.cn/cover-images/c.png",
+        ]
+
+    @pytest.mark.asyncio
+    async def test_unknown_hash_falls_back_to_the_filename(self, monkeypatch):
+        """A re-encoded file still matches by name rather than losing its images."""
+        self._patch(monkeypatch)
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "Krea-2-LORA_c1-st1000.safetensors", sha256="f" * 64
+        )
+
+        assert context.example_images == [
+            "https://resources.modelscope.cn/cover-images/b.png",
+            "https://resources.modelscope.cn/cover-images/c.png",
+        ]
+
+    @pytest.mark.asyncio
+    async def test_hash_is_case_insensitive(self, monkeypatch):
+        self._patch(monkeypatch)
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "renamed.safetensors", sha256=self.ST1000_HASH.upper()
+        )
+
+        assert len(context.example_images) == 2
+
+    @pytest.mark.asyncio
+    async def test_blank_hash_is_ignored(self, monkeypatch):
+        self._patch(monkeypatch)
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "Krea-2-LORA_c1-st8000.safetensors", sha256="   "
+        )
+
+        assert context.example_images == [
+            "https://resources.modelscope.cn/cover-images/a.png"
+        ]
+
+    @pytest.mark.asyncio
+    async def test_missing_model_infos_degrades_to_filename_matching(self, monkeypatch):
+        payload = _modelscope_detail_payload()
+        del payload["Data"]["ModelInfos"]
+
+        async def fake_fetch_json(url, **_kwargs):
+            return 200, payload
+
+        monkeypatch.setattr(
+            "py.services.model_sources.modelscope.fetch_json", fake_fetch_json
+        )
+
+        context = await ModelScopeSource().fetch_model_card_context(
+            "u/r", "Krea-2-LORA_c1-st1000.safetensors", sha256=self.ST1000_HASH
+        )
+
+        assert len(context.example_images) == 2
+
+    @pytest.mark.asyncio
+    async def test_real_published_hashes_are_used_by_the_agent(self):
+        """The agent must pass the recorded hash, not just the filename."""
+        service = AgentService()
+        with (
+            mock.patch(
+                "py.services.model_sources.modelscope.ModelScopeSource.fetch_model_card",
+                new=mock.AsyncMock(return_value="# card"),
+            ),
+            mock.patch(
+                "py.services.model_sources.modelscope.ModelScopeSource.fetch_model_card_context",
+                new=mock.AsyncMock(return_value=ModelCardContext()),
+            ) as mock_ctx,
+        ):
+            await service._load_source_card(
+                "/models/loras/renamed.safetensors",
+                {
+                    "source_platform": "modelscope",
+                    "source_url": "https://modelscope.cn/models/u/r",
+                    "sha256": "c" * 64,
+                },
+            )
+
+        assert mock_ctx.call_args.kwargs["sha256"] == "c" * 64