Skip to content

LLMKube

v0.9.4 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai apple-silicon autoscaling edge-computing gguf gpu
+12 more
self-hosted inference kubernetes llama-cpp llm local-llm metal mlx multi-gpu nvidia tgi vllm

Summary

AI summary

Updates 0.9.4, Bug Fixes, and 2026-07-11 across a mixed release.

Changes in this release

Feature Medium

Adds support for multiple agent fleets in chart component

Adds support for multiple agent fleets in chart component

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds --revise-from-branch flag to CLI for in-place PR refresh

Adds --revise-from-branch flag to CLI for in-place PR refresh

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds llmkube foreman slice to render a sliced Workload from a plan

Adds llmkube foreman slice to render a sliced Workload from a plan

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds ability to plan an issue into slices via llmkube foreman slice

Adds ability to plan an issue into slices via llmkube foreman slice

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds flag to unverify facts instead of inventing them in foreman slicer

Adds flag to unverify facts instead of inventing them in foreman slicer

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds integration and reconciliation of AgenticTask kinds with slice payload in foreman

Adds integration and reconciliation of AgenticTask kinds with slice payload in foreman

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds library for disjoint slice union to foreman

Adds library for disjoint slice union to foreman

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Makes EditFreeStreak guard grounding‑aware in foreman

Makes EditFreeStreak guard grounding‑aware in foreman

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds reconciliation library for sliced‑workload interface drift in foreman

Adds reconciliation library for sliced‑workload interface drift in foreman

Source: llm_adapter@2026-07-15

Confidence: high

Feature Medium

Adds run_integrate tool for sliced‑workload union in foreman

Adds run_integrate tool for sliced‑workload union in foreman

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Ships default integrate/reconcile Agents for sliced workloads in foreman

Ships default integrate/reconcile Agents for sliced workloads in foreman

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Feature Low

Adds SGLang runtime backend to runtime component

Adds SGLang runtime backend to runtime component

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Feature Low

Publishes a cross‑platform Homebrew formula instead of macOS‑only cask for release

Publishes a cross‑platform Homebrew formula instead of macOS‑only cask for release

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Medium

Keeps slicer planner output as YAML only, fixing regression

Keeps slicer planner output as YAML only, fixing regression

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Medium

Adds payload.branchStrategy to foreman to prevent stale revisions reverting merged work

Adds payload.branchStrategy to foreman to prevent stale revisions reverting merged work

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Medium

Anchors recovery soft‑reset at merge-base branch point in foreman

Anchors recovery soft‑reset at merge-base branch point in foreman

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Medium

Defaults to rebase when reviseFromBranch is set without branchStrategy in foreman

Defaults to rebase when reviseFromBranch is set without branchStrategy in foreman

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Low

Sets fsGroup on gate pod so non‑root gates can write XDG_DATA_HOME in foreman

Sets fsGroup on gate pod so non‑root gates can write XDG_DATA_HOME in foreman

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Low

Stops coder from running envtest it cannot run in foreman

Stops coder from running envtest it cannot run in foreman

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Bugfix Low

Gives the union commit an explicit git identity in slicer

Gives the union commit an explicit git identity in slicer

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Full changelog

0.9.4 (2026-07-11)

Features

  • chart: support multiple agent fleets in one release (#1028) (a9a6c6b)
  • cli: --revise-from-branch on foreman dispatch for in-place PR refresh (#1043) (26f807b)
  • cli: llmkube foreman slice renders a sliced Workload from a plan (#1049) (ce586ed)
  • cli: plan an issue into slices in llmkube foreman slice (#1050) (c4a967c)
  • foreman: flag unverifiable facts instead of inventing them (slicer anti-confabulation) (#1062) (81bbfe9)
  • foreman: integrate + reconcile AgenticTask kinds + slice payload (#1037) (0899e9f)
  • foreman: integrate library for disjoint slice union (#1036) (39131f6)
  • foreman: make the EditFreeStreak guard grounding-aware (#1067) (63a71ae)
  • foreman: reconcile library for sliced-workload interface drift (#1034) (b14f687)
  • foreman: run_integrate tool for sliced-workload union (#1045) (5098b4e)
  • foreman: run_reconcile tool for sliced-workload drift check (#1046) (6bde143)
  • foreman: ship default integrate/reconcile Agents for sliced workloads (#1052) (00dd7c0)
  • runtime: add SGLang runtime backend (#974) (#1059) (9daa186)

Bug Fixes

  • cli: keep the slicer planner output to YAML only (fixes #1062 regression) (#1064) (5d0eb9c)
  • foreman: add payload.branchStrategy to stop stale revisions reverting merged work (#1042) (9f806d4)
  • foreman: anchor recovery soft-reset at merge-base branch point (#1044) (2492d15)
  • foreman: default to rebase when reviseFromBranch is set without branchStrategy (#1065) (2792634)
  • foreman: set fsGroup on the gate pod so non-root gates can write XDG_DATA_HOME (#1068) (7465e2b)
  • foreman: stop the coder from running envtest it cannot run (#1070) (bf203fe)
  • release: publish a cross-platform Homebrew formula, not a macOS-only cask (#1041) (32dcfea)
  • slicer: give the union commit an explicit git identity (#1057) (15d906f)

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track LLMKube

Get notified when new releases ship.

Sign up free

About LLMKube

Kubernetes operator for llama.cpp-native LLM inference with GPU scheduling, Apple Silicon Metal support, and OpenAI-compatible API.

All releases →

Related context

Earlier breaking changes

  • v0.8.1 foreman: requestTimeoutSeconds now sets loop-wide budget, default changes from 600 to 3600.

Beta — feedback welcome: [email protected]