LLMKube

v0.8.3 Feature

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

Published 1mo Containers & Orchestration

✓ No known CVEs patched

✓ 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 0.8.3, Bug Fixes, and 2026-06-11 across a mixed release.

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds support for hybrid‑thinking models via reasoning_content in foreman/loop. Adds support for hybrid‑thinking models via reasoning_content in foreman/loop. Source: llm_adapter@2026-06-11 Confidence: high	—
Feature	Medium	Adds computable scope‑overlap check that demotes drifted GO verdicts in foreman/reviewer. Adds computable scope‑overlap check that demotes drifted GO verdicts in foreman/reviewer. Source: llm_adapter@2026-06-11 Confidence: high	—
Feature	Medium	Adds demotion of unverifiable review verdicts to NO‑GO in foreman/reviewer. Adds demotion of unverifiable review verdicts to NO‑GO in foreman/reviewer. Source: llm_adapter@2026-06-11 Confidence: high	—
Bugfix	Medium	Maps reasoning‑only exhaustion to INCOMPLETE in foreman/executor. Maps reasoning‑only exhaustion to INCOMPLETE in foreman/executor. Source: llm_adapter@2026-06-11 Confidence: high	—
Bugfix	Medium	Keeps wire‑stripped reasoning‑only turns template‑valid in foreman/loop. Keeps wire‑stripped reasoning‑only turns template‑valid in foreman/loop. Source: llm_adapter@2026-06-11 Confidence: high	—

Full changelog

foreman/loop: support hybrid-thinking models via reasoning_content (#651) (b178de2)
foreman/reviewer: computable scope-overlap check demotes drifted GO verdicts (#648) (8afe0c1)
foreman/reviewer: demote unverifiable review verdicts to NO-GO (#645) (188dacd)

foreman/executor: map reasoning-only exhaustion to INCOMPLETE (#652) (d2f453e)
foreman/loop: keep wire-stripped reasoning-only turns template-valid (#653) (5ec14f6)

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.

About LLMKube

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

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