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.

docs/agent_skills.md

@@ -109,6 +109,13 @@ returns a `ModelCardContext`. Example images are matched to the model's
 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
+run and passes it down. Enriching the eight checkpoints of one ModelScope
+repository costs two HTTP requests instead of sixteen; only the per-file
+selection is redone for each file. Nothing is cached across runs, and download
+URLs never go through it.
+
 #### Deterministic data is applied whether or not an LLM is configured
 
 `AgentService._load_source_card()` runs for every source-backed enrichment, and