Changelog

Machine Runner:

• Run machine runners on spot or preemptible instances to cut compute costs, without failing jobs when an instance is reclaimed. With the new runner.enable_unsafe_retries option, a job that is still running when the runner receives SIGINT, SIGTERM or SIGHUP is retried on another runner instead of failing. The job restarts from the beginning, so only enable it for jobs that are safe to run more than once. Any other error still fails the job.
• SIGHUP now triggers a graceful shutdown rather than killing the runner.

Container Runner:

• SSH reruns are now generally available on container runner.
• The Helm chart (v101.2.1) now creates SSH TCPRoute resources with the gateway.networking.k8s.io/v1 API version, so standard channel Gateway API CRDs work and experimental CRDs are no longer needed. Gateway API v1.6 or later is now required for SSH reruns.

New

Machine Runner Orchestrator (previously Runner Provisioner), which automatically scales self-hosted machine runner VMs to match CI demand, is now generally available (GA).

Machine Runner Orchestrator adds:

• Multi-resource-class support: CPU, GPU, and ARM workloads can all autoscale from a single deployment, removing the single-resource-class limit from the preview release.
• Support for GKE, AKS, and EKS, in addition to any KubeVirt-based Kubernetes cluster.

Machine Runner Orchestrator is included with self-hosted runners on every CircleCI plan, at no additional cost.

Breaking

The product was fully renamed from runner-provisioner to machine-runner-orchestrator: Helm chart name, container image repository, and Packagecloud package repository all changed to reflect that. Existing deployments must be uninstalled and reinstalled under the new name.

helm list -n <k8s_namespace>
helm uninstall runner-provisioner -n <k8s_namespace>
helm repo add circleci_machine-runner-orchestrator https://packagecloud.io/circleci/machine-runner-orchestrator/helm
helm repo update
helm install machine-runner-orchestrator circleci_machine-runner-orchestrator/machine-runner-orchestrator \
  --namespace <k8s_namespace> \
  --version 1.0.0 \
  --values my-values.yaml

Keep in mind that Runners for the configured resource classes will be offline between uninstalling the old chart and installing the new one.

Security

This version patches two high-severity gRPC-Go denial-of-service vulnerabilities: heap memory exhaustion via HTTP/2 frame fragmentation (CVE-2026-84304) and a crash on requests missing :authority/Host headers (CVE-2026-84445).

New:

• Added support for SSH reruns on KubeVirt VM runners: you can now SSH directly into the exact VM that ran a job, over the public internet, for debugging. Off by default.

Improvements:

• runner-provisioner can now poll task counts using each resource class’s own token instead of a separate global CircleCI API token, so that token no longer needs to be provisioned as a secret. Existing configurations using the old token keep working.
• Added HTTP/HTTPS proxy support, so runner-provisioner and the VMs it provisions can operate in environments with restricted outbound internet access.
• Renamed the chart’s tokenProxy sidecar setting to sidecar for clarity; the old tokenProxy.enabled value is still honored.

Security:

• Patched a high-severity vulnerability in a bundled compression library (CVE-2026-63209).

This release lets a single provisioner deployment run many resource classes and ships a ready-to-use VM image so you can stand up a pool without building your own.

New:

• Multiple resource classes per deployment. One deployment now scales many resource classes at once, instead of needing a separate deployment per class.
• Default containerDisk image out of the box. Pool VMs boot from a maintained Ubuntu 24.04 image with Docker and common CI tooling pre-baked, so you get a working pool without building your own image first. An AlmaLinux image is also available for RHEL-family jobs.
• More flexible scaling. Time-based schedules to raise or lower capacity at set times of day, plus finer controls (headroom, scaleDownDelay, and maxSurge) grouped under a new scaling block.
• Hot-reload of resource-class config and secrets. Changes are picked up without restarting the pod.
• More per-class machine-runner options. workingDirectory, taskAgentDirectory, commandPrefix, useHomeSSHDirForCheckoutKeys, and maxRunTime are now configurable per resource class. See the machine runner 3 configuration reference.
• emptyDiskMounts to automatically format and mount extra disks on pool VMs.

Improvements:

• Runner token kept off pool VMs. A token-proxy sidecar, on by default and optional, holds the resource-class token and attaches it only on the task-claim call, so the token never reaches the VM and a job can’t read it from the machine it runs on. Jobs run as the unprivileged circleci user by default. A resource class can opt into elevated privileges with grantSudo, which relies on the proxy so even a root task still can’t reach the token.
• New operability, hardening, and log-level chart options.
• Config split into a ConfigMap and a Secret so non-sensitive settings and secrets are managed separately.
• Tuned default resource class and resized the Docker-baked containerDisk images.

See the runner provisioner guide for full setup and configuration details.

New:

• The provisioner now supports high-availability deployments: with multiple replicas, one is elected leader and standbys take over automatically on failover.
• Uninstalling the Helm release now scales the VM pool down to zero before deletion, so runner VMs are cleaned up automatically.
• Runner logs are now forwarded to each VM’s serial console, making runner output visible through the virtualization layer for troubleshooting.
• AWS EKS now supports nested virtualization, and runner-provisioner has been validated against it. Bare metal nodes are no longer required to run runner VMs.

Improvements:

• Pool VMs now install the circleci-runner packages from a bundled containerDisk image at boot instead of fetching from packagecloud each time. This speeds up boots once the image is cached and enables air-gapped clusters, since the bundle can be rehosted on an internal registry. Configurable via runnerBundle.image; enabled by default.
• Provisioned VMs now default to masquerade networking.
• The container image pull policy now defaults to Always.
• imagePullSecrets is no longer set by default on the provisioner deployment.

Dependency updates: routine dependency and security bumps, including a moderate-severity HTTP/3 fix in quic-go (CVE-2026-40898).

Runner Provisioner, a new Kubernetes controller that automatically scales CircleCI runner VMs using KubeVirt, is now available in preview. The controller polls the CircleCI API for pending and running tasks and adjusts a VirtualMachinePool replica count to match demand — giving teams elastic, on-demand self-hosted runner capacity inside their own Kubernetes clusters.

Preview version 0.1.0 includes:

• A Helm chart for installation into any Kubernetes cluster with KubeVirt v1.8+
• Automatic scaling of runner VMs based on real-time CircleCI task demand
• Support for CircleCI Cloud and Server v4+
• Setup guidance for GKE, AKS, and EKS, including nested-virtualization and tainted-node-pool configurations
• Externally managed secrets via provisioner.existingSecret (e.g., Vault, Sealed Secrets)
• Customizable VirtualMachineInstanceSpec per resource class

Configuration schema and APIs may change before GA.

Read the docs →

Container Runner SSH Rerun (Preview)

Container runner now supports SSH Rerun. Visit our documentation on setup and usage.

For more information on SSH rerun please see the following documentation.