Repository navigation
Description
User Story
I use OpenShell for running coding agents in sandboxes through osh (a terminal dashboard over the OpenShell CLI), on macOS and Linux, with the Docker and Podman drivers.
I directly encountered this when moving our Linux test machine from Ubuntu 24.04 to Debian 13 (trixie): every sandbox on the Docker driver fails to provision.
This affects anyone running the Docker driver on Debian 13 with Debian's own Docker package.
Problem Statement
On a Debian 13 host with Debian's docker.io 26.1.5, openshell sandbox create on a Docker-driver gateway never reaches Ready. Provisioning fails with BoundaryConfigWriteFailed ... getent unable to find entry "1000:1000" in passwd database (status 500 from Docker). It happens for every sandbox, every time, with any image we tried.
Impact / Why This Matters
When this happens, users cannot use the Docker driver at all on Debian 13 with the distribution's Docker package: no sandbox ever starts, and the error does not say that the Docker version is involved.
The workaround is to replace docker.io with Docker's official docker-ce (29.9.3 works), or to use the Podman driver.
This matters because docker.io is what apt install docker.io gives on Debian's current stable release, and what many setup guides use.
Observed on the same host and setup:
- Debian 13 +
docker.io26.1.5: fails - Debian 13 +
docker-ce29.9.3: works - Debian 13 + Podman driver: works
- Ubuntu 24.04 + its
docker.io+ Docker driver: works
Acceptance Criteria
- On Debian 13 with
docker.io26.1.5,openshell sandbox create --from <image> --detachon a Docker-driver gateway reaches Ready. - Or, if that Docker version is not supported: the gateway or
sandbox createfails up front with a clear message naming the Docker server version and the minimum supported one, instead ofBoundaryConfigWriteFailed. - The supported Docker version range for the Docker driver is documented.
Reproduction Steps
- Debian 13 (trixie) host:
sudo apt-get install -y docker.io(gives 26.1.5+dfsg1-9+deb13u1), and add the user to thedockergroup. - Install OpenShell 0.1.7 and start a gateway with the Docker driver.
openshell sandbox create --name repro --from node:24-trixie-slim --detach- Observe that the sandbox enters the error phase while provisioning (log below).
- Replace Docker with
docker-ce29.9.3 from download.docker.com and repeat step 3: the sandbox reaches Ready.
Suggested UX (if applicable)
No response
Environment
- OpenShell: 0.1.7
- OS: Debian 13 (trixie), arm64, systemd (a privileged test container with systemd as PID 1, also expected on a plain Debian 13 host)
- Deployment: local gateway (systemd user service), Docker driver
- Docker:
docker.io26.1.5+dfsg1-9+deb13u1 (fails);docker-ce5:29.9.3-1debian.13trixie (works)
Logs
$ openshell sandbox create --name repro --from claude-code --policy sandbox-policy.yaml --detach
[0.0s] Sandbox allocated
[0.0s] Pulling image claude-code
[0.0s] Image already present
[2.8s] Starting sandbox Container created
Error: × sandbox entered error phase while provisioning: BoundaryConfigWriteFailed:
│ stage Docker sandbox bundle: Docker responded with status code 500: getent
│ unable to find entry "1000:1000" in passwd database
# The same Docker error without OpenShell, on that host (Docker 26.1.5),
# for a container whose user is uid:gid and a copy that keeps ownership:
$ id=$(docker create --user 1000:1000 claude-code true)
$ docker cp -a /tmp/f "$id":/tmp/f
Error response from daemon: getent unable to find entry "1000:1000" in passwd database
# --user 1000 and --user node work on 26.1.5; --user 1000:1000 works on docker-ce 29.9.3.
Activity
elezar commentedon Nov 6, 2026
Thanks for the detailed report. The User Story, impact, environment, and standalone
docker create --user 1000:1000+docker cp -arepro are all present.Assessment: valid, but the failing environment is outside the documented support range.
upload_to_containerusingcopy_uidgid=true(crates/openshell-driver-docker/src/lib.rs,stage_docker_sandbox_bundle). Your non-OpenShell repro shows that 26.1.x resolves a numericuid:gidthroughgetentin the image and rejects it when the group has no passwd entry. Newer Docker releases do not.docs/about/installation.mdx,docs/about/support-matrix.mdx). So the second acceptance criterion's documentation item is already met, and the first (make 26.1.5 work) is out of scope for a supported configuration.docker.version()in the driver startup path (lib.rs~L920) only verifies the call succeeds. Users on an unsupported Docker get an opaqueBoundaryConfigWriteFailedinstead of a clear message.Not reproduced locally: I did not set up Debian 13 +
docker.io26.1.5. The analysis is from the report and a code read, so the exact Docker-side cause is inferred from your repro.Suggested scope for a maintainer to decide: a startup check that compares the Docker server version (from the existing
version()response) against 28.0 and fails (or warns) with a message naming the detected and minimum versions, plus a pointer to the support matrix. Open questions: hard error vs. warning, since distro packages may backport fixes, and whether to check API version instead of engine version.Next human decision: whether to accept the "version preflight check with a clear error" as the work for this issue and retitle accordingly. Making 26.1.x work is not recommended given EOL.
TaylorMutch commentedon Nov 10, 2026
Accepting the issue with the narrower scope of warning when using a version older than the documented supported version.