perf(modelscope): fetch a repository's model card once per run

A collection repository publishes many model files under a single source id,
but enrichment re-read the README and the model-detail payload for every one
of them: eight checkpoints meant sixteen HTTP requests, each detail payload
being 10-22 KB of JSON.

Add `ModelSourceCache`, created by `execute_skill()` for the duration of a
run and passed to the provider through a new optional `cache` argument on
`fetch_model_card_context()`. The agent caches the README (repository-wide
and provider-agnostic), and ModelScope caches its detail payload under a
provider-namespaced key.

Only successful reads are memoised, so a transient failure is still retried
for the next file, and the per-file selection is redone from the cached
payload so a checkpoint never inherits a sibling's example images. Nothing
is retained across runs — a model card can change at any time — and download
URLs are not routed through the cache.

Measured over the eight checkpoints of one ModelScope repository: 16
requests before, 2 after.

To keep the two concerns separable, `_build_card_context()` now turns a
detail payload into a `ModelCardContext` as a pure function.

tests/services/test_agent_enrichment_source.py

@@ -104,8 +104,10 @@ class TestBuildPromptContext:
 
         mock_fetch.assert_awaited_once_with("jj3550945163/Krea-2-LORA")
         # The per-file lookup must receive the basename, not the full path.
-        mock_context.assert_awaited_once_with(
-            "jj3550945163/Krea-2-LORA", "krea.safetensors"
+        mock_context.assert_awaited_once()
+        assert mock_context.call_args.args == (
+            "jj3550945163/Krea-2-LORA",
+            "krea.safetensors",
         )
         assert context["source_platform"] == "modelscope"
         assert context["source_id"] == "jj3550945163/Krea-2-LORA"
@@ -444,7 +446,8 @@ class TestLoadSourceCard:
                 },
             )
 
-        mock_ctx.assert_awaited_once_with("u/r", "krea.safetensors")
+        mock_ctx.assert_awaited_once()
+        assert mock_ctx.call_args.args == ("u/r", "krea.safetensors")
         assert context is card
         assert variables["readme_content_full"] == "# card"
         assert variables["source_description"] == "作者说明"

tests/services/test_model_sources.py

@@ -10,6 +10,7 @@ from __future__ import annotations
 import pytest
 
 from py.services.model_sources import (
+    ModelSourceCache,
     HuggingFaceSource,
     ModelScopeSource,
     TensorArtSource,
@@ -688,3 +689,113 @@ class TestDownloadSourceRegistry:
         assert get_download_source("nope") is None
         assert get_download_source("modelscope").platform == "modelscope"
         assert get_download_source("huggingface").platform == "huggingface"
+
+
+# ---------------------------------------------------------------------------
+# Per-run model-card cache
+# ---------------------------------------------------------------------------
+
+
+class TestModelSourceCache:
+    def test_starts_empty(self):
+        cache = ModelSourceCache()
+        assert cache.readmes == {}
+        assert cache.provider == {}
+
+
+class TestCachedModelCardFetch:
+    @pytest.mark.asyncio
+    async def test_detail_payload_is_fetched_once_per_source_id(self, monkeypatch):
+        """A collection repo's files share one detail request, not one each."""
+        calls: list[str] = []
+
+        async def fake_fetch_json(url, **_kwargs):
+            calls.append(url)
+            return 200, _modelscope_detail_payload()
+
+        monkeypatch.setattr(
+            "py.services.model_sources.modelscope.fetch_json", fake_fetch_json
+        )
+
+        source = ModelScopeSource()
+        cache = ModelSourceCache()
+        filenames = [
+            "Krea-2-LORA_c1-st1000.safetensors",
+            "Krea-2-LORA_c1-st8000.safetensors",
+            "Krea-2-LORA_c1-st1000.safetensors",
+        ]
+        for name in filenames:
+            await source.fetch_model_card_context("u/r", name, cache=cache)
+
+        assert calls == ["https://modelscope.cn/api/v1/models/u/r"]
+        assert ("modelscope", "detail", "u/r") in cache.provider
+
+    @pytest.mark.asyncio
+    async def test_per_file_selection_still_runs_for_each_file(self, monkeypatch):
+        """The cached payload must not leak one file's images to another."""
+
+        async def fake_fetch_json(url, **_kwargs):
+            return 200, _modelscope_detail_payload()
+
+        monkeypatch.setattr(
+            "py.services.model_sources.modelscope.fetch_json", fake_fetch_json
+        )
+
+        source = ModelScopeSource()
+        cache = ModelSourceCache()
+
+        st1000 = await source.fetch_model_card_context(
+            "u/r", "Krea-2-LORA_c1-st1000.safetensors", cache=cache
+        )
+        st8000 = await source.fetch_model_card_context(
+            "u/r", "Krea-2-LORA_c1-st8000.safetensors", cache=cache
+        )
+
+        assert st1000.example_images == [
+            "https://resources.modelscope.cn/cover-images/b.png",
+            "https://resources.modelscope.cn/cover-images/c.png",
+        ]
+        assert st8000.example_images == [
+            "https://resources.modelscope.cn/cover-images/a.png"
+        ]
+        assert st8000.trigger_words == []
+
+    @pytest.mark.asyncio
+    async def test_failures_are_not_cached(self, monkeypatch):
+        """A transient error must be retried for the next file."""
+        calls: list[str] = []
+
+        async def fake_fetch_json(url, **_kwargs):
+            calls.append(url)
+            return 500, None
+
+        monkeypatch.setattr(
+            "py.services.model_sources.modelscope.fetch_json", fake_fetch_json
+        )
+
+        source = ModelScopeSource()
+        cache = ModelSourceCache()
+        for _ in range(2):
+            context = await source.fetch_model_card_context("u/r", "a.safetensors", cache=cache)
+            assert context.is_empty()
+
+        assert len(calls) == 2
+        assert cache.provider == {}
+
+    @pytest.mark.asyncio
+    async def test_no_cache_keeps_the_uncached_behaviour(self, monkeypatch):
+        calls: list[str] = []
+
+        async def fake_fetch_json(url, **_kwargs):
+            calls.append(url)
+            return 200, _modelscope_detail_payload()
+
+        monkeypatch.setattr(
+            "py.services.model_sources.modelscope.fetch_json", fake_fetch_json
+        )
+
+        source = ModelScopeSource()
+        for _ in range(2):
+            await source.fetch_model_card_context("u/r", "a.safetensors")
+
+        assert len(calls) == 2