Skip to content

feat(vanity-gateway): pass the LLM Gateway endpoint through the stack - #1026

Draft
Max-NV wants to merge 1 commit into
mxing/vanity-gateway-llm-endpoint-chartfrom
mxing/vanity-gateway-llm-stack-wiring
Draft

feat(vanity-gateway): pass the LLM Gateway endpoint through the stack#1026
Max-NV wants to merge 1 commit into
mxing/vanity-gateway-llm-endpoint-chartfrom
mxing/vanity-gateway-llm-stack-wiring

Conversation

@Max-NV

@Max-NV Max-NV commented Aug 20, 2026

Copy link
Copy Markdown
Contributor

TL;DR

The self-managed stack enumerates the Vanity Gateway config keys individually when rendering chart values, so llmGatewayEndpoint was dropped. Any deployment declaring a host under mappingConfig.v2config.llmGateway failed to start with "LLM_GATEWAY_ENDPOINT is required".

Additional Details

The mappingConfig half already passed through untouched via dig "addons" "vanityGateway" "mappingConfig" ..., so an operator could configure the section but it could never work. This adds the missing key to the rendered config: block and documents it in base.yaml, defaulting to the in-cluster LLM Gateway service.

Chart and image pins are deliberately not bumped. Both need a published artifact carrying the service-side change, which does not exist yet. That bump is follow-up work once the service PR lands and releases.

Stacked on #1025, which adds the chart key. Merging this first would break installs: the chart config block is additionalProperties: false, so it would reject the value the stack now sends. Base is set to that branch and will retarget to main when it merges.

For the Reviewer

Two lines of substance. The global.yaml.gotmpl line mirrors the adjacent nvcfApiEndpoint line exactly.

For QA

Rendered the full chain rather than eyeballing the template. Using a scratch environment enabling addons.vanityGateway and addons.llm with one llmGateway host, helmfile write-values produced llmGatewayEndpoint: http://llm-api-gateway.nvcf.svc.cluster.local:8080 alongside the mapping section, and feeding those exact values into the chart with helm template emitted both LLM_GATEWAY_ENDPOINT in the env ConfigMap and the host in the mapping ConfigMap. Scratch files were removed. No QA needed.

Issues

Relates to #1021

Checklist

  • I am familiar with the Contributing Guidelines.
  • I have signed off my commits for Developer Certificate of Origin (DCO) compliance.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.

The self-managed stack enumerates the Vanity Gateway config keys one by one
when rendering chart values, so llmGatewayEndpoint was dropped and the
gateway failed to start with "LLM_GATEWAY_ENDPOINT is required" whenever a
host was declared under mappingConfig.v2config.llmGateway. The mappingConfig
half already passed through untouched, so the section could be configured
but never worked.

Adds the key to the rendered config block and documents it in base.yaml with
the in-cluster LLM Gateway as the default.

Chart and image pins are not bumped here. Both need a published artifact
carrying the service-side change, which does not exist yet.

Signed-off-by: Max Xing <mxing@nvidia.com>
@Max-NV
Max-NV requested a review from a team as a code owner August 20, 2026 00:55
@Max-NV
Max-NV requested a review from arpitad-nv August 20, 2026 00:55
@coderabbitai

coderabbitai Bot commented Aug 20, 2026

Copy link
Copy Markdown

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

🗂️ Base branches to auto review (1)
  • main

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: af76a9ec-fda5-45b0-b982-d6ffdfa12286

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review

Comment @coderabbitai help to get the list of available commands.

@Max-NV
Max-NV marked this pull request as draft August 20, 2026 00:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant