feat: add the OCI image source to ModelArtifact

.agents/skills/gpustack-operator-docs/SKILL.md

@@ -41,6 +41,7 @@ one, not to widen the overview.
 | Standing a cache up end to end, or which object comes first: the pasteable four-object sequence | `docs/kv-cache/walkthrough.md` |
 | How a **Pod** consumes a pool: the inject label and annotations, the injected keys per engine, a refusal, the isolation record | `docs/reference/kv-cache-injection.md` |
 | A `ModelArtifact`: its sources, resolution and revalidation, the manifest digest, how a `ModelDeployment` or an `Instance` mounts or downloads it, claim placement, the weight identity in KV keys | `docs/reference/model-artifact.md` |
+| The `image` source of a `ModelArtifact`: the digest contract, building weights into an image, image-volume delivery, the version floors, double storage, kubelet image GC, registry mirrors | `docs/reference/model-image-source.md` |
 | A `ModelStore`, `ModelStoreBinding` or `ModelPrefetch`: the grant, the budget, pinning, TTL expiry, the warm-up pod and why it is label-free | `docs/reference/model-prefetch.md` |
 | The `v1` views of `ModelArtifact` and `NodeModelStore`, the `progress` subresource and who may read it, the GPUStack server capability map | `docs/reference/model-artifact-views.md` |
 | A `NodeModelStore` or the `model-manager` plugin: a field and its writer, the status guard, mount authorization, materialization, a failure reason, collection, a metric | `docs/reference/node-model-store.md` |

.agents/skills/gpustack-operator-docs/references/page-map.md

@@ -270,7 +270,9 @@ picks and how to switch its policy (`model-deployment-routing.md`), what a `Mode
 and its engine's exit (`model-deployment-shutdown.md`), and the `ModelArtifact` contract — sources,
 resolution and revalidation, the manifest digest and its patterns, how a deployment or an Instance
 consumes it under each delivery, claim placement and the weight identity in KV keys
-(`model-artifact.md`), and the `NodeModelStore` resource with the node plugin behind it — its
+(`model-artifact.md`), the `image` source's own page — the digest contract, building weights into
+an image, image-volume delivery, the version floors, double storage, kubelet image GC and registry
+mirrors (`model-image-source.md`), and the `NodeModelStore` resource with the node plugin behind it — its
 writers and status guard, mount authorization, materialization, failure reasons, collection and
 metrics (`node-model-store.md`).
 

.agents/skills/gpustack-operator-e2e/SKILL.md

@@ -156,6 +156,7 @@ Each case is self-contained; its header (see **Case header contract**) states go
 | 109 | The NodeModelStore's lifecycle: a plugin restart and a deletion of the object each end with the node's entries rewritten from disk, and deleting a Node collects its object while the node registered again gets a new one | `pkg/modelmanager/{report,store}/**`, `pkg/worker/controllers/worker/node_model_store{,_kubelet}.go` | yes (confirm; deletes a worker's Node object and restarts its kubelet) | kind with two workers and docker reaching the node containers (else the Node row SKIPs), the chart with `modelManager.enabled`, the stock python image |
 | 110 | ModelPrefetch: the store layer names itself in the node's spec; a warm-up pod pinned to the target node mounts label-free and the digest goes Ready; a projection past the grant is refused at admission; pinning is refused without `allowPinned` and lands under it; deleting the prefetch removes its pod and its pin while the tree stays for the grace | `pkg/worker/controllers/worker/{model_prefetch,model_store,model_store_binding}.go`, `pkg/worker/webhooks/worker/{model_store_binding,model_prefetch}.go`, `pkg/worker/settings/value.go`, `cases/_model-hub{-lib.sh,.py}` | yes (confirm) | one worker labeled `e2e.gpustack.ai/warm-pool=true` by the case (case-110 labels and unlabels it), the chart with `modelManager.enabled`, the stock python image; docker reaching the node container for the tree row |
 | 111 | Node-to-node sync: a cold node materializes a digest from a peer's published tree with source=Peer and its hub byte counter at zero; the seed's plugin pod dying mid-pull still ends Ready (checkpoint resume); a tenant pod cannot reach the peer port | `pkg/modelmanager/peer/**`, `pkg/modelmanager/materialize/materialize.go`, `pkg/modelmanager/config.go`, `deploy/gpustack-operator/chart/templates/model-manager/**`, `docs/reference/node-peer-sync.md` | yes (confirm) | two schedulable workers (a seed and a puller), the chart installed with `modelManager.port` non-zero and the peer NetworkPolicy enabled, `model-store-peer-sync` at its `true` default |
+| 112 | Image source: a tag-only reference is refused naming the digest contract; an image artifact resolves claim-shaped (no manifest digest, no revision, no `status.nodes`); an Instance pinned to the node mounts the pinned image read-only through an image volume and reads the fixture byte for byte; a `ModelPrefetch` naming the artifact is refused | `pkg/worker/webhooks/worker/{model_artifact,model_prefetch}.go`, `pkg/worker/controllers/worker/{model_artifact_placement,model_deployment_artifact,instance,model_placement_preference}.go`, `pkg/kubediscovery/feature.go`, `cases/case-112.sh` | yes (confirm) | one worker whose kubelet/containerd serve image volumes (kubelet 1.35+, containerd 2.1+), docker on the runner, the stock `registry:2`, `python:3.12-slim` and `busybox:1.36` images pullable |
 
 Each note below is something the **lead** must act on before or around a run. What a case *does* — its goal, environment, inputs, assertions and cleanup — lives in its own header, which the **Case header contract** below requires to be readable on its own; the index never restates it.