feat(container)!: Update image ghcr.io/home-operations/charts-mirror/llmkube (0.9.30 ➔ 0.10.0)

renovate-bot commented

2026-09-29 19:01:21 +02:00

Collaborator

This PR contains the following updates:

Package	Update	Change
ghcr.io/home-operations/charts-mirror/llmkube	minor	`0.9.30` → `0.10.0`

⚠️ Warning

Some dependencies could not be looked up. Check the Dependency Dashboard for more information.

Release Notes

defilantech/LLMKube (ghcr.io/home-operations/charts-mirror/llmkube)

`v0.10.0`

Compare Source

⚠ BREAKING CHANGES

metal-agent: serve engines on loopback behind an authenticated ingress (#1945)

Features

controller: front Metal InferenceServices with an authenticated relay (#1944) (37be11b)
metal-agent: serve engines on loopback behind an authenticated ingress (#1945) (cf55427)
metal-agent: tensorfold runtime for MLX speculative decoding (#1923) (8c9820c)

Bug Fixes

api: let InferenceService select Metal runtimes and fall back to the agent flag (#1912) (19191b4)
metal-agent: enforce a typed allowlist on extraArgs (#1941) (c09a4be)
metal-agent: enforce allowed roots on local model paths (#1939) (bcdd27f)
metal-agent: fail fast when llama-server exits during startup (#1917) (23f1fc6)
metal-agent: fail fast when mlx-server exits during startup (#1929) (c55f535)
metal-agent: fail fast when vllm-swift exits during startup (#1928) (46e4e96)
metal-agent: load local-path GGUF sources in place instead of downloading (#1920) (6c045b4)
metal-agent: never overwrite or delete a Service or EndpointSlice it does not own (#1932) (799194a)
metal-agent: size file:// model sources in the memory estimate (#1930) (39b1ef6)
metal-agent: spell mlock as --load-mode on llama.cpp 0.5.0+ (#1916) (f760639)
metal: stop routing to a Metal endpoint nothing is serving (#1921) (75c792f)

Configuration

📅 Schedule: (in timezone Europe/Rome)

Branch creation
- At any time (no schedule defined)
Automerge
- At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

If you want to rebase/retry this PR, check this box

This PR has been generated by Mend Renovate CLI.

This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/home-operations/charts-mirror/llmkube](https://github.com/defilantech/LLMKube) | minor | `0.9.30` → `0.10.0` | --- > ⚠️ **Warning** > > Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/6) for more information. --- ### Release Notes <details> <summary>defilantech/LLMKube (ghcr.io/home-operations/charts-mirror/llmkube)</summary> ### [`v0.10.0`](https://github.com/defilantech/LLMKube/blob/HEAD/CHANGELOG.md#0100-2026-09-29) [Compare Source](https://github.com/defilantech/LLMKube/compare/v0.9.30...v0.10.0) ##### ⚠ BREAKING CHANGES - **metal-agent:** serve engines on loopback behind an authenticated ingress ([#1945](https://github.com/defilantech/LLMKube/issues/1945)) ##### Features - **controller:** front Metal InferenceServices with an authenticated relay ([#1944](https://github.com/defilantech/LLMKube/issues/1944)) ([37be11b](https://github.com/defilantech/LLMKube/commit/37be11bbbbab6caecd1abdfadc042d90bb5fdeb4)) - **metal-agent:** serve engines on loopback behind an authenticated ingress ([#1945](https://github.com/defilantech/LLMKube/issues/1945)) ([cf55427](https://github.com/defilantech/LLMKube/commit/cf55427aec8478c680516d493a6c96b1225afce5)) - **metal-agent:** tensorfold runtime for MLX speculative decoding ([#1923](https://github.com/defilantech/LLMKube/issues/1923)) ([8c9820c](https://github.com/defilantech/LLMKube/commit/8c9820c45de1681cb0fa6868a91db1032668539d)) ##### Bug Fixes - **api:** let InferenceService select Metal runtimes and fall back to the agent flag ([#1912](https://github.com/defilantech/LLMKube/issues/1912)) ([19191b4](https://github.com/defilantech/LLMKube/commit/19191b4dfc06f9878f88f4b44092b04331bcc826)) - **metal-agent:** enforce a typed allowlist on extraArgs ([#1941](https://github.com/defilantech/LLMKube/issues/1941)) ([c09a4be](https://github.com/defilantech/LLMKube/commit/c09a4bebdc0ce894606479d667d797696c606950)) - **metal-agent:** enforce allowed roots on local model paths ([#1939](https://github.com/defilantech/LLMKube/issues/1939)) ([bcdd27f](https://github.com/defilantech/LLMKube/commit/bcdd27f875b5d70948dc69482ef8c824142b9516)) - **metal-agent:** fail fast when llama-server exits during startup ([#1917](https://github.com/defilantech/LLMKube/issues/1917)) ([23f1fc6](https://github.com/defilantech/LLMKube/commit/23f1fc689570e883099d735b3d47d5d03d3e8ea9)) - **metal-agent:** fail fast when mlx-server exits during startup ([#1929](https://github.com/defilantech/LLMKube/issues/1929)) ([c55f535](https://github.com/defilantech/LLMKube/commit/c55f5359e59e1e566fe008c3cfdaec7e1dc576ee)) - **metal-agent:** fail fast when vllm-swift exits during startup ([#1928](https://github.com/defilantech/LLMKube/issues/1928)) ([46e4e96](https://github.com/defilantech/LLMKube/commit/46e4e96f35c4b64e4bde877e417b325b3981d87f)) - **metal-agent:** load local-path GGUF sources in place instead of downloading ([#1920](https://github.com/defilantech/LLMKube/issues/1920)) ([6c045b4](https://github.com/defilantech/LLMKube/commit/6c045b4c2be99fa01b11e52bb40bc81208249824)) - **metal-agent:** never overwrite or delete a Service or EndpointSlice it does not own ([#1932](https://github.com/defilantech/LLMKube/issues/1932)) ([799194a](https://github.com/defilantech/LLMKube/commit/799194ae454b4c097b2ba719e3b4565afa5dc043)) - **metal-agent:** size file:// model sources in the memory estimate ([#1930](https://github.com/defilantech/LLMKube/issues/1930)) ([39b1ef6](https://github.com/defilantech/LLMKube/commit/39b1ef669124c70efefbb00835146e3259619759)) - **metal-agent:** spell mlock as --load-mode on llama.cpp 0.5.0+ ([#1916](https://github.com/defilantech/LLMKube/issues/1916)) ([f760639](https://github.com/defilantech/LLMKube/commit/f760639b92295b1688008a4f21595d9495ffac17)) - **metal:** stop routing to a Metal endpoint nothing is serving ([#1921](https://github.com/defilantech/LLMKube/issues/1921)) ([75c792f](https://github.com/defilantech/LLMKube/commit/75c792fc05224bf0e80e88e153ec5f65486582e8)) </details> --- ### Configuration 📅 **Schedule**: (in timezone Europe/Rome) - Branch creation - At any time (no schedule defined) - Automerge - At any time (no schedule defined) 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Mend Renovate CLI](https://github.com/renovatebot/renovate).

renovate-bot added the

renovate/container

type/minor

labels

2026-09-29 19:01:21 +02:00

renovate-bot added 1 commit

2026-09-29 19:01:21 +02:00

feat(container)!: Update image ghcr.io/home-operations/charts-mirror/llmkube (0.9.30 ➔ 0.10.0)

Labeler / Labeler (pull_request) Successful in 4s

Details

Lint / actionlint (pull_request) Successful in 6s

Details

Lint / yamllint (pull_request) Successful in 12s

Details

AI PR Review / AI PR Review (pull_request) Successful in 41s

Details

Konflate 4 resources changed

Details

47d20b6138

forgejo-actions added the

area/kubernetes

label

2026-09-29 19:01:25 +02:00

lab-assistant-bot commented

2026-09-29 19:02:01 +02:00

Collaborator

✅ Automated recommendation: APPROVE

Analysis engine: minimax/MiniMax-M2-7-anthropic@http://litellm.ai.svc.cluster.local:4000/v1 (anthropic)

Review: llmkube Chart 0.9.30 → 0.10.0

Recommendation: Approve

This is a straightforward OCI Helm chart version bump for the llmkube application. The single-line diff updates the ref.tag from 0.9.30 to 0.10.0 in the OCIRepository resource.

Change Summary

File changed: kubernetes/apps/ai/llmkube/app/ocirepository.yaml
Change: tag: 0.9.30 → tag: 0.10.0

Standards Compliance

OCI artifact pinning: This change follows the repository convention of pinning OCI artifacts by tag/version (not SHA digest). No flag raised.
Namespace absence: metadata.namespace is intentionally omitted from OCIRepository, consistent with documented conventions.

Breaking Change Caveat

The upstream release notes flag a breaking change ("metal-agent: serve engines on loopback behind an authenticated ingress"). This is an upstream chart concern — the change is limited to the chart version reference, and no HelmRelease values files were modified. If the authenticated ingress requires additional configuration or credentials in the HelmRelease, that would need to be addressed separately.

Evidence Summary

Konflate rendered-diff: No findings, clean render (info severity, exit 0)
Image digests: No digest changes detected
Tests: None present for this component

Non-blocking Note

The PR title includes the ! convention indicating a breaking change. Reviewers should be aware that if the llmkube HelmRelease requires value overrides to accommodate the upstream authentication change, those would need to be applied post-merge.

✅ **Automated recommendation: APPROVE** _Analysis engine: minimax/MiniMax-M2-7-anthropic@http://litellm.ai.svc.cluster.local:4000/v1 (anthropic)_ ## Review: llmkube Chart 0.9.30 → 0.10.0 ### Recommendation: Approve This is a straightforward OCI Helm chart version bump for the llmkube application. The single-line diff updates the `ref.tag` from `0.9.30` to `0.10.0` in the OCIRepository resource. ### Change Summary - **File changed**: `kubernetes/apps/ai/llmkube/app/ocirepository.yaml` - **Change**: `tag: 0.9.30` → `tag: 0.10.0` ### Standards Compliance - **OCI artifact pinning**: This change follows the repository convention of pinning OCI artifacts by tag/version (not SHA digest). No flag raised. - **Namespace absence**: `metadata.namespace` is intentionally omitted from OCIRepository, consistent with documented conventions. ### Breaking Change Caveat The upstream release notes flag a breaking change ("metal-agent: serve engines on loopback behind an authenticated ingress"). This is an upstream chart concern — the change is limited to the chart version reference, and no HelmRelease values files were modified. If the authenticated ingress requires additional configuration or credentials in the HelmRelease, that would need to be addressed separately. ### Evidence Summary - **Konflate rendered-diff**: No findings, clean render (info severity, exit 0) - **Image digests**: No digest changes detected - **Tests**: None present for this component ### Non-blocking Note The PR title includes the `!` convention indicating a breaking change. Reviewers should be aware that if the llmkube HelmRelease requires value overrides to accommodate the upstream authentication change, those would need to be applied post-merge.

lab-assistant-bot commented

2026-09-29 19:26:34 +02:00

Collaborator

4 resources changed across 2 apps · 1 CRD

Blast radius

Kustomization ai/llmkube: 1 dependent (ai/llmkube-models)

image	from	to	upstream
`ghcr.io/defilantech/llmkube-controller`	`0.9.30`	`0.10.0`	❔

_{konflate 0.6.4 · rendered 47d20b6 · full diff →}

**4 resources changed** across 2 apps · 1 CRD **Blast radius** - `Kustomization ai/llmkube`: 1 dependent (ai/llmkube-models) | image | from | to | upstream | |---|---|---|---| | `ghcr.io/defilantech/llmkube-controller` | `0.9.30` | `0.10.0` | ❔ | <sub>konflate 0.6.4 · rendered `47d20b6` · [full diff →](https://konflate.aresu.eu/#/pr/2244)</sub>