docs: surface PassthroughModel and make examples runnable and drift-proof#138
Merged
Conversation
|
📄 Docs preview for |
…ingle source) Replaces the inline near-duplicate PassthroughModel YAML on the architecture page with a Vite ?raw import of examples/passthrough-openrouter.yaml, rendered via Starlight's <Code> component, so the docs page and the runnable manifest cannot drift. - architecture.md renamed to architecture.mdx to allow the import/JSX syntax. - astro.config.mjs: added vite.server.fs.allow (searchForWorkspaceRoot) so the cross-root ?raw import resolves during `astro dev`. - docs/test/docs-examples.test.mjs: new harness asserting the embed import and Code usage are present and that no inline duplicate of the manifest remains. Used the primary embed path (no prebuild-copy fallback needed): `npm run build` succeeded with the cross-directory ?raw import resolving, and the built docs/dist/architecture/index.html contains the embedded manifest content.
Convert quickstart.md to .mdx, embed the PassthroughModel example via the Task 1 pattern, and add a Route to an external provider section so the anchor referenced from architecture.mdx resolves. Also add an explicit kubectl command for creating the hf-token secret inline where authSecretName is introduced.
…prose The header comment showed 'kubectl -n <ns> create secret generic <name>' while the quickstart page renders 'kubectl create secret generic <name> -n <ns>' a few lines above the embedded manifest. Same command, consistent ordering now.
…LMModel namespace
Reconciles examples/*.yaml and installation.md pack version references against verified nebari-infrastructure-core source and the confirmed v0.1.1 pack tag: pack targetRevision v0.1.1, gpu-operator v25.10.1, AI Gateway repoURL without the oci:// prefix, clusterIssuer letsencrypt-issuer, and default storageClassName longhorn. Adds a link from installation.md's pack-app manifest to the standalone examples/argocd-application.yaml template.
The passthrough example's header comment is embedded verbatim into three rendered docs pages; a repo-relative filesystem path reads oddly there.
The configuration reference table and the shared-storage init-image reference pointed at the old ghcr path; the images now publish under llm-serving-pack. ghcr paths only; Go module path unaffected.
The pack chart is now published to quay.io/nebari/charts (release 0.1.2). Switch the ArgoCD Application examples in installation.md, examples/argocd-application.yaml, and README.md from a git-sourced chart (repoURL + path: charts/nebari-llm-serving) to the OCI Helm source form (repoURL + chart + targetRevision, no oci:// prefix). Cluster-config (LLMModel) sources are untouched. Update the two docs tests that hard-asserted the old git-tag values.
dcmcand
force-pushed
the
docs/runnable-examples
branch
from
July 16, 2026 06:37
b8d2867 to
934472a
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Readers couldn't find the PassthroughModel feature (external-provider routing, #96) anywhere in the docs, and several runnable manifests were orphaned, drifted, or shown only as fragments. This makes every documented feature copy-paste runnable and keeps the manifests in sync with the repo automatically.
Single source of truth for examples. Pages that show a manifest now import the real
examples/*.yamlfile via a Vite?rawimport and render it with Starlight's<Code>component, so what a reader copies is byte-identical to the repo file and can't drift. Applied toarchitecture,quickstart,configuration, andshared-storage(converted.md->.mdx).PassthroughModel is now documented.
PassthroughModel-> call the endpoint), mirroring the served-model flow.credentialSecretName-> upstream 401, missing AI-Gateway CRDs ->ApplyFailed, catch-all precedence), with commands verified against the operator source.Other fixes.
kubectl create secret generic hf-token ...command inline whereauthSecretNameis introduced.examples/models/minimal.yamlandexamples/models/advanced-scheduling.yaml.Version reconciliation (grounded in NIC / release tags, not guesses). Pack
v0.1.1(newest tag, contains the PassthroughModel CRD); gpu-operatorv25.10.1(the documented, justified version); AI Gatewaydocker.io/envoyproxywith nooci://prefix andv0.5.0(matches what nebari-infrastructure-core actually deploys);clusterIssuer: letsencrypt-issuerandstorageClassName: longhorn(NIC's actual values).installation.mdstays.md: its Application manifests are NIC-tuned and deliberately different from the standalone examples, so only its pack version was updated.Testing.
docs/test/docs-examples.test.mjs(25/25) asserts every embed, section, field, and reconciled value;npm run buildis clean (11 pages) with all embeds resolving.Follow-ups. Deferred docs items and the config/version cleanup are tracked in #137. End-to-end verification against a live cluster (applying the quickstart passthrough steps for a real 200) is deferred to post-merge, since no cluster was reachable.