Changelog

What changed in each release

Berth is a restricted beta for trusted cluster administrators on a single cluster. Earlier releases are listed on GitHub Releases.

Berth 0.5.1, 26 October 2026

In short: images and the Helm chart move to ghcr.io/cloudguys-io, log streams reconnect, and refused changes say why. Still a restricted beta on a single cluster.

Changed

  • The GitHub organisation was renamed from unishsys to cloudguys-io, and the container registry does not redirect the old name. The chart is now oci://ghcr.io/cloudguys-io/charts/berth and the image ghcr.io/cloudguys-io/berth. The 0.5.0 chart points at the old image path, which no longer resolves, so upgrade to this release.
  • Images from this release on are signed by workflows in github.com/cloudguys-io. Update the identity you pass to cosign verify.

Fixed

  • Log streams reconnect after the connection drops and do not repeat lines. The view says when a stream is interrupted, and offers Reconnect when retries run out. Before, a dropped stream silently stopped updating.
  • A change Kubernetes refuses now says why (permission denied, conflict, missing object, invalid change) instead of a generic server error.
  • Pressing Enter in the replica editor showed the new count without applying it. It now scales the deployment, and a refused change puts the row back.

Security

Dependency updates for newly published advisories, including a critical one in dompurify, and Go 1.27.3 with golang.org/x/net v0.60.0 on the server.

Upgrade

helm upgrade --install berth oci://ghcr.io/cloudguys-io/charts/berth \
  --version 0.5.1 --namespace berth --create-namespace --reuse-values

Berth 0.5.0, 7 October 2026

In short: a smaller AI SRE toolset, agent loops that end properly, corrected cost estimates, and published evaluation data. Still a restricted beta on a single cluster; no new SSO, per-user authorisation, audit viewer or multi-cluster support.

Changed

  • The assistant has 15 tools instead of 18. Three were merged into others: reading any single object is one tool (describe_resource, with an optional apiVersion for custom resources); discovering and listing resources is one tool (list_resources); and cluster_health now includes each node. The security behaviour is unchanged.
  • The default model for the Anthropic API is claude-sonnet-5-5. A model you saved in Settings, or pinned in your Helm values, is kept.
  • With Ollama, when the assistant runs out of tool calls it is now told to answer from what it has found, and a server error from Ollama is retried once.

Fixed

  • With Claude (Anthropic API and Bedrock), a run that hit the tool-call limit could return an empty or half-finished answer as if it had succeeded. It now produces an answer, marks one that was cut off, and reports an error when there is none.
  • The usage-cost estimate for Claude Opus 5.5 was 25% too high.

Compatibility

The tool names in the streamed tool events changed: get_resource, list_api_resources and list_nodes no longer exist. Anything that matches on those names needs updating.

Evidence

The scenarios, results and scoring changes behind these changes are at /evals/, with their limits.