praxis/scripts/proxmox/lxc-deploy.sh

#!/bin/sh
# Praxis — Orchestrator: deploy praxis to a Proxmox LXC container.
#
# Adapted from coreci/scripts/proxmox/lxc-deploy.sh.
# Sequence: stage snippet → clone template → configure CT → start →
#           health-check → rollback on failure.
#
# Required env (see .env.example + ~/coreci/.ciagent/.env.secrets):
#   PROXMOX_API_URL        — https://proxmox:8006/api2/json
#   PROXMOX_API_TOKEN      — USER@REALM!TOKENID=SECRET
#   PROXMOX_NODE           — target node name
#   PROXMOX_STORAGE        — storage holding the template
#   PROXMOX_TEMPLATE_VOLID — local:vztmpl/debian-12-template.tar.zst
#   GITEA_TOKEN            — bearer token for the private Gitea repo
#                            (baked into the firstboot snippet by stage-snippet.sh)
#
# Optional env:
#   PROXMOX_LXC_VMID       — target CT VMID (default: auto-allocate via pve_nextid)
#   PRAXIS_VERSION         — git ref to deploy (default: main)
#   PRAXIS_PORT            — server HTTP port (default: 8789)
#   PRAXIS_HEALTH_URL      — override health-check URL
#   PROXMOX_MEMORY_MB      — CT memory limit (default: 4096)
#   PROXMOX_TLS_SKIP_VERIFY— accept self-signed certs (default: false)
#   DEEPGRAM_API_KEY       — voice-service key (optional, may be empty)
#   CARTESIA_API_KEY       — voice-service key (optional, may be empty)
#   OLLAMA_API_KEY         — voice-service key (optional, may be empty)
#
# Flags:
#   --recreate    — rollback.sh (stop + destroy) then full redeploy
#   --reconfigure — re-PUT lxc-config.sh + restart (no clone)
#
# Exit: 0 on successful deploy, 1 on failure (with rollback attempted)

set -eu

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# shellcheck source=api.sh disable=SC1091
. "${SCRIPT_DIR}/api.sh"
# shellcheck source=ct-exists.sh disable=SC1091
. "${SCRIPT_DIR}/ct-exists.sh"
# shellcheck source=timing.sh disable=SC1091
. "${SCRIPT_DIR}/timing.sh"

pve_env PROXMOX_API_URL PROXMOX_API_TOKEN PROXMOX_NODE \
    PROXMOX_STORAGE PROXMOX_TEMPLATE_VOLID GITEA_TOKEN

# ── Flag parsing ───────────────────────────────────────────────────
recreate=0
reconfigure=0
for arg in "$@"; do
    case "$arg" in
        --recreate)    recreate=1 ;;
        --reconfigure) reconfigure=1 ;;
        *) echo "deploy: unknown argument: $arg" >&2; exit 2 ;;
    esac
done

# Step 0: stage the first-boot hookscript to Proxmox snippet storage.
# G-101 FIX: stage-snippet.sh bakes GITEA_TOKEN into the snippet.
hookscript_volid="${PROXMOX_STORAGE:-local}:snippets/praxis-firstboot.sh"
existing=$(pve_get "/nodes/${PROXMOX_NODE}/storage/${PROXMOX_STORAGE:-local}/content" 2>/dev/null | jq -r --arg v "$hookscript_volid" '.[]? | select(.volid==$v) | .volid' 2>/dev/null || true)
if [ -n "$existing" ]; then
    echo "deploy: hookscript snippet ${hookscript_volid} already staged — skipping upload" >&2
else
    "${SCRIPT_DIR}/stage-snippet.sh"
fi

# Resolve target VMID (D-027: auto-allocate by default).
vmid="${PROXMOX_LXC_VMID:-auto}"
if [ "$vmid" = "auto" ]; then
    vmid=$(pve_nextid)
    echo "deploy: auto-allocated VMID ${vmid}" >&2
else
    echo "deploy: using configured VMID ${vmid}" >&2
fi

# Trap: rollback on any failure (mirrors coreci pattern).
deploy_failed=0
skip_rollback=0
trap 'deploy_failed=1' INT TERM
cleanup() {
    rc=$?
    if [ "$skip_rollback" -ne 1 ] && { [ "$deploy_failed" -ne 0 ] || [ "$rc" -ne 0 ]; }; then
        echo "deploy: FAILED (rc=${rc}) — rolling back VMID ${vmid}" >&2
        "${SCRIPT_DIR}/rollback.sh" "$vmid" 2>&1 || true
    fi
}
trap cleanup EXIT

# ── Idempotency: detect existing CT before clone ──────────────────
if ct_exists "$vmid"; then
    echo "deploy: VMID ${vmid} already exists — checking health" >&2
    ct_healthy=0
    if ct_running "$vmid"; then
        if PRAXIS_HEALTH_TIMEOUT="${IDEMPOTENCY_HEALTH_TIMEOUT:-30}" \
                "${SCRIPT_DIR}/health-check.sh" "$vmid" 2>/dev/null; then
            ct_healthy=1
        fi
    fi

    if [ "$ct_healthy" -eq 1 ]; then
        echo "deploy: VMID ${vmid} already running + healthy — skipping clone/config/start (idempotent re-deploy)" >&2
        skip_provision=1
    elif [ "$reconfigure" -eq 1 ]; then
        echo "deploy: VMID ${vmid} exists but unhealthy — --reconfigure: re-PUT config + restart" >&2
        skip_rollback=1
        timing_start reconfigure
        "${SCRIPT_DIR}/lxc-config.sh" "$vmid"
        "${SCRIPT_DIR}/lxc-start.sh" "$vmid"
        timing_end reconfigure
        timing_start health
        "${SCRIPT_DIR}/health-check.sh" "$vmid"
        timing_end health
        skip_provision=1
    elif [ "$recreate" -eq 1 ]; then
        echo "deploy: VMID ${vmid} exists but unhealthy — --recreate: rollback + redeploy" >&2
        "${SCRIPT_DIR}/rollback.sh" "$vmid"
        skip_provision=0
    else
        echo "deploy: ERROR — VMID ${vmid} exists but is unhealthy." >&2
        echo "deploy: Use --recreate to rollback + redeploy, or --reconfigure to update config + restart." >&2
        echo "deploy: No action taken (the existing CT was left intact for inspection)." >&2
        skip_rollback=1
        exit 1
    fi
else
    skip_provision=0
fi

if [ "${skip_provision:-0}" -eq 0 ]; then
    # Step 1: Clone the template
    timing_start clone
    "${SCRIPT_DIR}/lxc-clone.sh" "$vmid"
    timing_end clone

    # Step 2: Configure the CT
    timing_start config
    "${SCRIPT_DIR}/lxc-config.sh" "$vmid"
    timing_end config

    # Step 3: Start the CT
    timing_start start
    "${SCRIPT_DIR}/lxc-start.sh" "$vmid"
    timing_end start

    # Step 4: Health-check (G-104: 600s timeout for Docker build)
    timing_start health
    "${SCRIPT_DIR}/health-check.sh" "$vmid"
    timing_end health
fi

deploy_failed=0
echo "deploy: praxis deployed successfully to VMID ${vmid}" >&2
printf 'VMID=%s\n' "$vmid"