Will Miao e9e9ee20c6 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.

2026-09-14 21:24:57 +08:00

..

__init__.py

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

2026-09-14 21:24:57 +08:00

base.py

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

2026-09-14 21:24:57 +08:00

huggingface.py

feat(download): support ModelScope repositories in the URL downloader

2026-09-14 07:42:51 +08:00

modelscope.py

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

2026-09-14 21:24:57 +08:00

registry.py

feat(download): support ModelScope repositories in the URL downloader

2026-09-14 07:42:51 +08:00

tensorart.py

feat(links): support ModelScope and TensorArt as model sources

2026-09-14 07:24:08 +08:00