Files
Sybil-2/scripts/devbox-update.sh
T

358 lines
13 KiB
Bash
Executable File

#!/usr/bin/env bash
set -euo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
REPO="${REPO:-Sybil-2}"
WORKLOAD="${WORKLOAD:-sybil-dev}"
CLUSTER="${CLUSTER:-viper}"
NAMESPACE="${NAMESPACE:-buzzert}"
QUOTA="${QUOTA:-research-api}"
SECRET="${SECRET:-sybil-dev-env}"
REMOTE_ROOT="${REMOTE_ROOT:-/root/code/$REPO}"
INGRESS_PORT="${INGRESS_PORT:-5173}"
CODEX_IMAGE="${CODEX_IMAGE:-openai.azurecr.io/rcall:crow-1b540b5e15f9-2026-01-22-2404-312}"
CODEX_SERVICE="${CODEX_SERVICE:-sybil-codex-devbox}"
CODEX_CONTAINER="${CODEX_CONTAINER:-codex-devbox}"
CODEX_SSH_SECRET="${CODEX_SSH_SECRET:-sybil-codex-ssh}"
CODEX_SSH_PORT="${CODEX_SSH_PORT:-2222}"
CODEX_WORKDIR="${CODEX_WORKDIR:-/workspace/sybil-codex}"
CODEX_SSH_KEY_PATH="${CODEX_SSH_KEY_PATH:-/run/secrets/sybil-codex-ssh/id_ed25519}"
echo "Syncing $REPO to $WORKLOAD on $CLUSTER/$NAMESPACE..."
brix create \
--project-root "$(dirname "$ROOT")" \
--path "$REPO=$ROOT" \
--repositories "$REPO" \
--include-untracked \
--reconcile-policy continuous \
-- \
"cluster=$CLUSTER" \
"namespace=$NAMESPACE" \
"name=$WORKLOAD" \
"pool.spec.quota=$QUOTA" \
"pool.spec.size.resource=cpu" \
"pool.spec.size.quantity=1" \
"pool.spec.priority=low"
if [[ "$REPO" != "openai" ]]; then
if kubectl --context "$CLUSTER" -n "$NAMESPACE" get git "$WORKLOAD" -o json 2>/dev/null | jq -e '.spec.repositories.openai?' >/dev/null; then
kubectl --context "$CLUSTER" -n "$NAMESPACE" patch git "$WORKLOAD" --type=json -p='[{"op":"remove","path":"/spec/repositories/openai"}]'
fi
fi
if [[ -n "${OPENAI_API_KEY:-}" && -n "${EXA_API_KEY:-}" ]]; then
kubectl --context "$CLUSTER" -n "$NAMESPACE" create secret generic "$SECRET" \
--from-literal=OPENAI_API_KEY="$OPENAI_API_KEY" \
--from-literal=EXA_API_KEY="$EXA_API_KEY" \
--dry-run=client -o yaml | kubectl --context "$CLUSTER" -n "$NAMESPACE" apply -f -
elif [[ -n "${OPENAI_API_KEY:-}" || -n "${EXA_API_KEY:-}" ]]; then
echo "Only one API key env var is set; keeping existing Kubernetes secret $SECRET." >&2
fi
if [[ "$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get secret "$SECRET" -o name 2>/dev/null || true)" == "" ]]; then
echo "Secret $SECRET does not exist. Re-run with OPENAI_API_KEY and EXA_API_KEY set." >&2
exit 1
fi
if [[ "$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get secret "$CODEX_SSH_SECRET" -o name 2>/dev/null || true)" == "" ]]; then
tmpdir="$(mktemp -d)"
trap 'rm -rf "$tmpdir"' EXIT
ssh-keygen -t ed25519 -N "" -C "sybil-codex@$WORKLOAD" -f "$tmpdir/id_ed25519" >/dev/null
kubectl --context "$CLUSTER" -n "$NAMESPACE" create secret generic "$CODEX_SSH_SECRET" \
--from-file=id_ed25519="$tmpdir/id_ed25519" \
--from-file=id_ed25519.pub="$tmpdir/id_ed25519.pub" \
--dry-run=client -o yaml | kubectl --context "$CLUSTER" -n "$NAMESPACE" apply -f -
fi
kubectl --context "$CLUSTER" -n "$NAMESPACE" patch secret "$SECRET" --type=merge -p "$(jq -n \
--arg host "$CODEX_SERVICE" \
--arg port "$CODEX_SSH_PORT" \
--arg workdir "$CODEX_WORKDIR" \
--arg keyPath "$CODEX_SSH_KEY_PATH" \
'{
stringData: {
CHAT_CODEX_TOOL_ENABLED: "true",
CHAT_CODEX_REMOTE_HOST: $host,
CHAT_CODEX_REMOTE_USER: "root",
CHAT_CODEX_REMOTE_PORT: $port,
CHAT_CODEX_REMOTE_WORKDIR: $workdir,
CHAT_CODEX_SSH_KEY_PATH: $keyPath,
CHAT_CODEX_EXEC_TIMEOUT_MS: "600000",
CHAT_SHELL_TOOL_ENABLED: "true"
}
}')"
ensure_codex_deployment() {
kubectl --context "$CLUSTER" -n "$NAMESPACE" apply -f - <<KUBE_MANIFEST
apiVersion: apps/v1
kind: Deployment
metadata:
name: $CODEX_SERVICE
labels:
app.kubernetes.io/name: $CODEX_SERVICE
app.kubernetes.io/part-of: sybil-dev
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: $CODEX_SERVICE
template:
metadata:
labels:
app.kubernetes.io/name: $CODEX_SERVICE
app.kubernetes.io/part-of: sybil-dev
spec:
tolerations:
- key: openai.com/team
operator: Exists
effect: NoSchedule
containers:
- name: $CODEX_CONTAINER
image: $CODEX_IMAGE
imagePullPolicy: IfNotPresent
command: ["/bin/bash", "-lc"]
args:
- |
set -euo pipefail
export DEBIAN_FRONTEND=noninteractive
if ! command -v sshd >/dev/null 2>&1; then
apt-get update
apt-get install -y --no-install-recommends openssh-server ca-certificates git curl
rm -rf /var/lib/apt/lists/*
fi
if ! command -v codex >/dev/null 2>&1; then
npm install -g @openai/codex
fi
mkdir -p /run/sshd /root/.ssh "$CODEX_WORKDIR"
cp /run/secrets/sybil-codex-ssh/id_ed25519.pub /root/.ssh/authorized_keys
chmod 700 /root/.ssh
chmod 600 /root/.ssh/authorized_keys
{
if [[ -n "\${OPENAI_API_KEY:-}" ]]; then
printf 'export OPENAI_API_KEY=%q\n' "\$OPENAI_API_KEY"
fi
if [[ -n "\${EXA_API_KEY:-}" ]]; then
printf 'export EXA_API_KEY=%q\n' "\$EXA_API_KEY"
fi
} >/root/.sybil-codex-env
chmod 600 /root/.sybil-codex-env
cat >/usr/local/bin/sybil-codex-ssh-command <<'SSH_COMMAND'
#!/usr/bin/env bash
set -euo pipefail
if [[ -f /root/.sybil-codex-env ]]; then
source /root/.sybil-codex-env
fi
if [[ -n "\${SSH_ORIGINAL_COMMAND:-}" ]]; then
exec /bin/bash -lc "\$SSH_ORIGINAL_COMMAND"
fi
exec /bin/bash -l
SSH_COMMAND
chmod 700 /usr/local/bin/sybil-codex-ssh-command
ssh-keygen -A
cat >/tmp/sybil-codex-sshd_config <<SSHD_CONFIG
Port $CODEX_SSH_PORT
ListenAddress 0.0.0.0
PermitRootLogin prohibit-password
PasswordAuthentication no
PubkeyAuthentication yes
AcceptEnv OPENAI_API_KEY EXA_API_KEY
AuthorizedKeysFile .ssh/authorized_keys
PermitUserEnvironment no
ForceCommand /usr/local/bin/sybil-codex-ssh-command
AllowTcpForwarding no
X11Forwarding no
Subsystem sftp internal-sftp
PidFile /run/sshd/sybil-codex.pid
SSHD_CONFIG
exec \$(command -v sshd) -D -e -f /tmp/sybil-codex-sshd_config
ports:
- name: ssh
containerPort: $CODEX_SSH_PORT
envFrom:
- secretRef:
name: $SECRET
resources:
requests:
cpu: "1"
memory: 4Gi
limits:
cpu: "1"
memory: 4Gi
volumeMounts:
- name: sybil-codex-ssh
mountPath: /run/secrets/sybil-codex-ssh
readOnly: true
- name: sybil-codex-workspace
mountPath: /workspace
volumes:
- name: sybil-codex-ssh
secret:
secretName: $CODEX_SSH_SECRET
defaultMode: 384
- name: sybil-codex-workspace
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: $CODEX_SERVICE
labels:
app.kubernetes.io/name: $CODEX_SERVICE
app.kubernetes.io/part-of: sybil-dev
spec:
type: ClusterIP
selector:
app.kubernetes.io/name: $CODEX_SERVICE
ports:
- name: ssh
port: $CODEX_SSH_PORT
targetPort: ssh
KUBE_MANIFEST
kubectl --context "$CLUSTER" -n "$NAMESPACE" rollout status "deployment/$CODEX_SERVICE" --timeout=300s
}
ensure_codex_deployment
ensure_env_from() {
local resource="$1"
local name="$2"
local jsonpath="$3"
local patch_path="$4"
local existing_env_from
existing_env_from="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get "$resource" "$name" \
-o "jsonpath=$jsonpath" 2>/dev/null || true)"
if [[ "$existing_env_from" == *"$SECRET"* ]]; then
return
fi
local patch
if [[ -z "$existing_env_from" ]]; then
patch="[{\"op\":\"add\",\"path\":\"$patch_path\",\"value\":[{\"secretRef\":{\"name\":\"$SECRET\"}}]}]"
else
patch="[{\"op\":\"add\",\"path\":\"$patch_path/-\",\"value\":{\"secretRef\":{\"name\":\"$SECRET\"}}}]"
fi
kubectl --context "$CLUSTER" -n "$NAMESPACE" patch "$resource" "$name" --type=json -p "$patch"
}
ensure_env_from \
workload \
"$WORKLOAD" \
"{.spec.pools[0].template.template.spec.workers.template.spec.containers[0].envFrom}" \
"/spec/pools/0/template/template/spec/workers/template/spec/containers/0/envFrom"
ensure_env_from \
pool \
"$WORKLOAD" \
"{.spec.workers.template.spec.containers[0].envFrom}" \
"/spec/workers/template/spec/containers/0/envFrom"
codex_ssh_volume_json="$(jq -n --arg secret "$CODEX_SSH_SECRET" '{
name: "sybil-codex-ssh",
secret: {
secretName: $secret,
defaultMode: 384
}
}')"
codex_main_mount_json="$(jq -n '{name: "sybil-codex-ssh", mountPath: "/run/secrets/sybil-codex-ssh", readOnly: true}')"
patch_pool_codex_mount() {
local pool_json containers volumes patch
pool_json="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get pool "$WORKLOAD" -o json)"
containers="$(jq \
--arg sidecarName "$CODEX_CONTAINER" \
--argjson mainMount "$codex_main_mount_json" \
'
def ensure_mount($mount):
.volumeMounts = (((.volumeMounts // []) | map(select(.name != $mount.name))) + [$mount]);
(.spec.workers.template.spec.containers // [])
| map(if .name == "main" then ensure_mount($mainMount) else . end)
| map(select(.name != $sidecarName))
' <<<"$pool_json")"
volumes="$(jq \
--argjson sshVolume "$codex_ssh_volume_json" \
'
(.spec.workers.template.spec.volumes // [])
| map(select(.name != $sshVolume.name and .name != "sybil-codex-workspace"))
+ [$sshVolume]
' <<<"$pool_json")"
patch="$(jq -n --argjson containers "$containers" --argjson volumes "$volumes" '{
spec: {
workers: {
template: {
spec: {
containers: $containers,
volumes: $volumes
}
}
}
}
}')"
kubectl --context "$CLUSTER" -n "$NAMESPACE" patch pool "$WORKLOAD" --type=merge -p "$patch"
}
patch_workload_codex_mount() {
local workload_json pools patch
workload_json="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get workload "$WORKLOAD" -o json)"
pools="$(jq \
--arg groupName "$WORKLOAD" \
--arg sidecarName "$CODEX_CONTAINER" \
--argjson mainMount "$codex_main_mount_json" \
--argjson sshVolume "$codex_ssh_volume_json" \
'
def ensure_mount($mount):
.volumeMounts = (((.volumeMounts // []) | map(select(.name != $mount.name))) + [$mount]);
.spec.pools
| map(
if .groupName == $groupName then
.template.template.spec.workers.template.spec.containers =
((.template.template.spec.workers.template.spec.containers // [])
| map(if .name == "main" then ensure_mount($mainMount) else . end)
| map(select(.name != $sidecarName)))
| .template.template.spec.workers.template.spec.volumes =
((.template.template.spec.workers.template.spec.volumes // [])
| map(select(.name != $sshVolume.name and .name != "sybil-codex-workspace"))
+ [$sshVolume])
else
.
end
)
' <<<"$workload_json")"
patch="$(jq -n --argjson pools "$pools" '{spec: {pools: $pools}}')"
kubectl --context "$CLUSTER" -n "$NAMESPACE" patch workload "$WORKLOAD" --type=merge -p "$patch"
}
patch_workload_codex_mount
patch_pool_codex_mount
echo "Waiting for $WORKLOAD-0 to run the current pool revision..."
deadline=$((SECONDS + 300))
while true; do
pool_revision="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get pool "$WORKLOAD" -o jsonpath='{.status.revision}' 2>/dev/null || true)"
pod_revision="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get pod "$WORKLOAD-0" -o jsonpath='{.metadata.labels.brix\.openai\.com/revision}' 2>/dev/null || true)"
pod_ready="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get pod "$WORKLOAD-0" -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}' 2>/dev/null || true)"
pod_deletion_timestamp="$(kubectl --context "$CLUSTER" -n "$NAMESPACE" get pod "$WORKLOAD-0" -o jsonpath='{.metadata.deletionTimestamp}' 2>/dev/null || true)"
if [[ -n "$pool_revision" && "$pod_revision" == "$pool_revision" && "$pod_ready" == "True" && -z "$pod_deletion_timestamp" ]]; then
break
fi
if (( SECONDS >= deadline )); then
echo "Timed out waiting for current ready pod. pool_revision=$pool_revision pod_revision=$pod_revision pod_ready=$pod_ready deleting=$pod_deletion_timestamp" >&2
exit 1
fi
sleep 5
done
brix run --clusters "$CLUSTER" --namespace "$NAMESPACE" --pools "$WORKLOAD" --dir "$REMOTE_ROOT" -- ./scripts/devbox-start.sh
ssh_check="ssh -n -i '$CODEX_SSH_KEY_PATH' -o BatchMode=yes -o StrictHostKeyChecking=accept-new -o UserKnownHostsFile=/tmp/sybil-codex-known-hosts -p '$CODEX_SSH_PORT' root@'$CODEX_SERVICE' true"
brix run --clusters "$CLUSTER" --namespace "$NAMESPACE" --pools "$WORKLOAD" --dir "$REMOTE_ROOT" -- /bin/bash -lc "$ssh_check"
url="$(brix ingress create --cluster "$CLUSTER" --namespace "$NAMESPACE" --pod "$WORKLOAD-0" --ports "web:$INGRESS_PORT" --root web --timeout 300 "$WORKLOAD" | tail -1)"
echo "Devbox update complete: $url"