Files
OpenShell/tasks/scripts/gateway.sh
Jesse JaggarsandDrew Newberry 02b664bb0d refactor(config): normalize and enforce gateway schema v2 (#2814)
* refactor(config): normalize compute driver field names

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* refactor(config): introduce canonical gateway fields

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* refactor(config): enforce gateway schema version 2

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): preserve compute driver runtime guarantees

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): address schema v2 review regressions

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): complete schema v2 migration safeguards

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(config): expand schema v2 regression coverage

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(config): add schema v2 parity manifest

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): correct parity manifest inventory

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* docs(config): record schema v2 intentional changes

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* docs(config): disposition schema v2 parity gaps

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): add dual schema parity harness

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): establish compute lifecycle parity baseline

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): preserve gateway option compatibility

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): record gateway option parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* docs(config): close gateway-wide parity gaps

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(podman): apply configured pids limit

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): validate Podman option parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): add Kubernetes option parity harness

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): record Kubernetes option parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): disposition VM parity lanes

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): add external driver parity lane

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): preserve external driver pull policy

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): attest parity artifacts and launches

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): require clean parity build sources

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): bind parity runtime artifacts

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): use isolated supervisor tags

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): qualify parity image tags

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): serve parity supervisor locally

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): isolate parity podman services

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): harden parity evidence provenance

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): pin parity sandbox artifacts

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): attest parity runtime inputs

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): bind parity runtime evidence

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): record compute boundary parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): disposition cross-cutting parity lanes

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(packaging): preflight gateway config upgrades

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): preserve rebase integration guarantees

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(ci): isolate temporary git signing config

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): update remaining schema v2 consumers

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(ci): provide e2fs tools to VM tests

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): align preflight with gateway startup

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(vm): preserve rootfs tar configuration

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* chore(config): adopt duration unit constructors

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(packaging): preflight RPM gateway config

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): address driver review findings

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): require fresh semantic parity evidence

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(docker): update tests for renamed sandbox label

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(gateway): preserve selective driver coverage after rebase

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>
Signed-off-by: Drew Newberry <anewberry@nvidia.com>
Co-authored-by: Drew Newberry <anewberry@nvidia.com>
2026-09-11 05:00:24 +00:00

311 lines
8.6 KiB
Bash

#!/usr/bin/env bash
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
# Start a standalone openshell-gateway using the detected compute driver.
#
# Auto-detection follows the gateway's runtime order:
# Kubernetes -> Podman -> Docker
#
# VM/MicroVM is intentionally explicit-only because it requires runtime setup.
# Use either:
# OPENSHELL_COMPUTE_DRIVER=vm mise run gateway
# mise run gateway:vm
set -euo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
# shellcheck source=tasks/scripts/gateway-pull-policy.sh
source "${ROOT}/tasks/scripts/gateway-pull-policy.sh"
GATEWAY_BIN="${OPENSHELL_GATEWAY_BIN:-${ROOT}/target/debug/openshell-gateway}"
usage() {
cat <<'EOF'
Usage: mise run gateway [-- --driver DRIVER]
Start a local OpenShell gateway with the detected compute driver.
Driver detection order:
kubernetes -> podman -> docker
Options:
--driver DRIVER Override detection. Accepted values:
kubernetes, podman, docker, vm, microvm
-h, --help Show this help.
Environment:
OPENSHELL_COMPUTE_DRIVER Driver override used by openshell-gateway.
OPENSHELL_GATEWAY_NAME Gateway name for delegated or Kubernetes runs.
OPENSHELL_BIND_ADDRESS Gateway listener address. Defaults to 127.0.0.1,
or ::1 for Podman Machine on macOS.
OPENSHELL_SERVER_PORT Gateway port. Defaults to 8080 for Kubernetes,
18080 for Podman/Docker, and 18081 for VM.
Docker, Podman, and VM runs delegate to their gateway:<driver> setup scripts.
EOF
}
normalize_driver() {
local driver
driver="$(printf '%s' "$1" | tr '[:upper:]' '[:lower:]')"
case "${driver}" in
kubernetes|k8s) echo "kubernetes" ;;
podman) echo "podman" ;;
docker) echo "docker" ;;
vm|microvm) echo "vm" ;;
"")
echo "ERROR: empty driver value" >&2
exit 2
;;
*)
echo "ERROR: unsupported driver '$1' (expected kubernetes, podman, docker, vm, or microvm)" >&2
exit 2
;;
esac
}
command_available() {
command -v "$1" >/dev/null 2>&1
}
require_mise() {
if ! command_available mise; then
echo "ERROR: mise is required to build local gateway artifacts" >&2
exit 1
fi
}
run_mise_task() {
require_mise
mise run "$@"
}
podman_available() {
command_available podman && podman info >/dev/null 2>&1
}
docker_available() {
command_available docker && docker info >/dev/null 2>&1
}
detect_driver() {
if [[ -n "${KUBERNETES_SERVICE_HOST:-}" ]]; then
echo "kubernetes"
return
fi
if podman_available; then
echo "podman"
return
fi
if docker_available; then
echo "docker"
return
fi
echo "ERROR: no compute driver detected." >&2
echo " Start Podman or Docker, run inside Kubernetes, or set OPENSHELL_COMPUTE_DRIVER." >&2
exit 2
}
port_is_in_use() {
local port=$1
if command_available lsof; then
lsof -nP -iTCP:"${port}" -sTCP:LISTEN >/dev/null 2>&1
return $?
fi
if command_available nc; then
nc -z 127.0.0.1 "${port}" >/dev/null 2>&1
return $?
fi
(echo >/dev/tcp/127.0.0.1/"${port}") >/dev/null 2>&1
}
register_gateway_metadata() {
local name=$1
local endpoint=$2
local port=$3
local config_home gateway_dir
config_home="${XDG_CONFIG_HOME:-${HOME}/.config}"
gateway_dir="${config_home}/openshell/gateways/${name}"
mkdir -p "${gateway_dir}"
cat >"${gateway_dir}/metadata.json" <<EOF
{
"name": "${name}",
"gateway_endpoint": "${endpoint}",
"is_remote": false,
"gateway_port": ${port},
"auth_mode": "plaintext"
}
EOF
printf '%s' "${name}" >"${config_home}/openshell/active_gateway"
}
explicit_driver=""
while [[ "$#" -gt 0 ]]; do
case "$1" in
--driver)
if [[ "$#" -lt 2 ]]; then
echo "ERROR: --driver requires a value" >&2
exit 2
fi
explicit_driver="$(normalize_driver "$2")"
shift 2
;;
--driver=*)
explicit_driver="$(normalize_driver "${1#--driver=}")"
shift
;;
-h|--help)
usage
exit 0
;;
*)
echo "ERROR: unknown gateway option '$1'" >&2
echo >&2
usage >&2
exit 2
;;
esac
done
if [[ -n "${explicit_driver}" && -n "${OPENSHELL_COMPUTE_DRIVER:-}" ]]; then
echo "ERROR: use either --driver or OPENSHELL_COMPUTE_DRIVER, not both" >&2
exit 2
fi
if [[ -z "${explicit_driver}" && -n "${OPENSHELL_COMPUTE_DRIVER:-}" ]]; then
if [[ "${OPENSHELL_COMPUTE_DRIVER}" == *,* ]]; then
echo "ERROR: mise run gateway supports one driver; got OPENSHELL_COMPUTE_DRIVER=${OPENSHELL_COMPUTE_DRIVER}" >&2
exit 2
fi
explicit_driver="$(normalize_driver "${OPENSHELL_COMPUTE_DRIVER}")"
fi
DRIVER="${explicit_driver:-$(detect_driver)}"
case "${DRIVER}" in
docker)
export OPENSHELL_DOCKER_GATEWAY_NAME="${OPENSHELL_DOCKER_GATEWAY_NAME:-${OPENSHELL_GATEWAY_NAME:-docker-dev}}"
exec bash "${ROOT}/tasks/scripts/gateway-docker.sh"
;;
podman)
export OPENSHELL_PODMAN_GATEWAY_NAME="${OPENSHELL_PODMAN_GATEWAY_NAME:-${OPENSHELL_GATEWAY_NAME:-podman-dev}}"
exec bash "${ROOT}/tasks/scripts/gateway-podman.sh"
;;
vm)
export OPENSHELL_VM_GATEWAY_NAME="${OPENSHELL_VM_GATEWAY_NAME:-${OPENSHELL_GATEWAY_NAME:-vm-dev}}"
exec bash "${ROOT}/tasks/scripts/gateway-vm.sh"
;;
esac
PORT="${OPENSHELL_SERVER_PORT:-8080}"
GATEWAY_NAME="${OPENSHELL_GATEWAY_NAME:-${DRIVER}-dev}"
STATE_DIR="${OPENSHELL_GATEWAY_STATE_DIR:-${ROOT}/.cache/gateway-${DRIVER}}"
SANDBOX_NAMESPACE="${OPENSHELL_SANDBOX_NAMESPACE:-${DRIVER}-dev}"
SANDBOX_IMAGE="${OPENSHELL_SANDBOX_IMAGE:-ghcr.io/nvidia/openshell-community/sandboxes/base:latest}"
SANDBOX_IMAGE_PULL_POLICY="$(normalize_image_pull_policy "${OPENSHELL_SANDBOX_IMAGE_PULL_POLICY:-if_not_present}")"
GRPC_ENDPOINT="${OPENSHELL_GRPC_ENDPOINT:-}"
LOG_LEVEL="${OPENSHELL_LOG_LEVEL:-info}"
PRIMARY_BIND_IP="${OPENSHELL_BIND_ADDRESS:-127.0.0.1}"
if [[ ! "${GATEWAY_NAME}" =~ ^[A-Za-z0-9._-]+$ ]]; then
echo "ERROR: OPENSHELL_GATEWAY_NAME must contain only letters, numbers, dots, underscores, or dashes" >&2
exit 2
fi
if port_is_in_use "${PORT}"; then
echo "ERROR: port ${PORT} is already in use; free it or set OPENSHELL_SERVER_PORT" >&2
exit 2
fi
echo "Building openshell-gateway..."
run_mise_task build:gateway
if [[ ! -x "${GATEWAY_BIN}" ]]; then
echo "ERROR: expected gateway binary at ${GATEWAY_BIN}" >&2
exit 1
fi
TLS_DIR="${STATE_DIR}/tls"
echo "Generating local gateway credentials..."
"${GATEWAY_BIN}" generate-certs \
--output-dir "${TLS_DIR}" \
--server-san "127.0.0.1" \
--server-san "localhost" \
--server-san "host.openshell.internal"
mkdir -p "${STATE_DIR}"
CONFIG_PATH="${STATE_DIR}/gateway.toml"
# The config may reference credential-bearing material (e.g. proxy_auth_file);
# keep it owner-only regardless of the ambient umask.
install -m 600 /dev/null "${CONFIG_PATH}"
# Kubernetes is a shared deployment, so its sandbox JWTs must expire. Local
# drivers omit ttl_secs and inherit the gateway's non-expiring default, so a
# sandbox restarted while the gateway is down can still reconnect.
GATEWAY_JWT_TTL_CONFIG=""
if [[ "${DRIVER}" == "kubernetes" ]]; then
GATEWAY_JWT_TTL_CONFIG="ttl_secs = 3600"
fi
cat >"${CONFIG_PATH}" <<EOF
[openshell]
version = 2
[openshell.gateway]
name = "${GATEWAY_NAME}"
compute_driver = "${DRIVER}"
disable_tls = true
[openshell.gateway.otlp]
endpoint = "http://127.0.0.1:4317"
[openshell.gateway.auth]
allow_unauthenticated_users = true
[openshell.gateway.gateway_jwt]
signing_key_path = "${TLS_DIR}/jwt/signing.pem"
public_key_path = "${TLS_DIR}/jwt/public.pem"
kid_path = "${TLS_DIR}/jwt/kid"
gateway_id = "${GATEWAY_NAME}"
${GATEWAY_JWT_TTL_CONFIG}
EOF
cat >>"${CONFIG_PATH}" <<EOF
[openshell.drivers.kubernetes]
namespace = "${SANDBOX_NAMESPACE}"
default_image = "${SANDBOX_IMAGE}"
image_pull_policy = "${SANDBOX_IMAGE_PULL_POLICY}"
EOF
if [[ -n "${GRPC_ENDPOINT}" ]]; then
printf 'grpc_endpoint = "%s"\n' "${GRPC_ENDPOINT}" >>"${CONFIG_PATH}"
fi
GATEWAY_ENDPOINT="http://127.0.0.1:${PORT}"
register_gateway_metadata "${GATEWAY_NAME}" "${GATEWAY_ENDPOINT}" "${PORT}"
echo "Starting standalone ${DRIVER} gateway..."
echo " gateway: ${GATEWAY_NAME}"
echo " endpoint: ${GATEWAY_ENDPOINT}"
echo " bind: ${PRIMARY_BIND_IP}:${PORT}"
echo " namespace: ${SANDBOX_NAMESPACE}"
echo " state dir: ${STATE_DIR}"
echo
echo "Active gateway set to '${GATEWAY_NAME}'. The CLI now targets this gateway by default."
echo
exec "${GATEWAY_BIN}" \
--config "${CONFIG_PATH}" \
--bind-address "${PRIMARY_BIND_IP}" \
--port "${PORT}" \
--log-level "${LOG_LEVEL}" \
--compute-driver "${DRIVER}" \
--disable-tls \
--db-url "sqlite:${STATE_DIR}/gateway.db?mode=rwc"