praxis/scripts/proxmox/test/e2e-deploy.bats

#!/usr/bin/env bats
# Bats END-TO-END integration suite for the praxis v0.2 Proxmox deploy
# stack (SLICE-09 capstone).
#
# Run (live): PRAXIS_E2E_LIVE=1 bats scripts/proxmox/test/e2e-deploy.bats
# Run (default, skipped): bats scripts/proxmox/test/e2e-deploy.bats
#
# Unlike the per-script orchestrator tests (lxc-deploy.bats) which stub
# every sibling, this suite runs the REAL lxc-deploy.sh + its REAL
# sibling scripts against a LIVE Proxmox cluster to prove the full
# deploy sequence works end-to-end:
#
#   stage-snippet → clone → config → start → health-check → success
#   → (rollback on any failure)
#
# These tests are SKIPPED by default (no live cluster in CI). Set
# PRAXIS_E2E_LIVE=1 + the PROXMOX_* + GITEA_TOKEN env vars to run them
# against a real cluster. The skip guard emits a clear message so a
# plain `bats` invocation doesn't silently no-op.
#
# Required env (when PRAXIS_E2E_LIVE=1):
#   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
#   PROXMOX_LXC_VMID       — target CT VMID (auto-allocated if unset)
#
# Optional env:
#   PRAXIS_E2E_LIVE        — set to 1 to run these tests (default: skip)
#   PRAXIS_VERSION         — git ref to deploy (default: main)
#   PRAXIS_PORT            — server HTTP port (default: 8789)
#   PRAXIS_HEALTH_URL      — override health-check URL
#   PRAXIS_HEALTH_TIMEOUT  — health-check timeout (default: 600)

# Skip guard: unless PRAXIS_E2E_LIVE=1, skip every test in this file
# with a clear message. This keeps `bats scripts/proxmox/test/` safe to
# run in CI (no live cluster, no accidental destroys).
setup() {
    if [ "${PRAXIS_E2E_LIVE:-0}" != "1" ]; then
        skip "PRAXIS_E2E_LIVE!=1 — set PRAXIS_E2E_LIVE=1 + PROXMOX_* env to run live e2e tests"
    fi
    SCRIPT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
    # Resolve the deploy script from the real source tree.
    DEPLOY="${SCRIPT_DIR}/lxc-deploy.sh"
    [ -x "$DEPLOY" ] || skip "lxc-deploy.sh not found at ${DEPLOY}"

    # Validate required live env vars are present.
    for var in PROXMOX_API_URL PROXMOX_API_TOKEN PROXMOX_NODE \
               PROXMOX_STORAGE PROXMOX_TEMPLATE_VOLID GITEA_TOKEN; do
        eval "val=\"\${${var}:-}\""
        [ -n "$val" ] || skip "${var} is required for live e2e (PRAXIS_E2E_LIVE=1)"
    done

    # Use a dedicated VMID for e2e to avoid clobbering a production CT.
    # If PROXMOX_LXC_VMID is unset, default to a high number + warn.
    if [ -z "${PROXMOX_LXC_VMID:-}" ]; then
        export PROXMOX_LXC_VMID="900"
        echo "e2e: PROXMOX_LXC_VMID unset — defaulting to 900 for live test" >&2
    fi
    echo "e2e: targeting VMID ${PROXMOX_LXC_VMID} on node ${PROXMOX_NODE}" >&2
}

teardown() {
    # Live teardown: if a test left a CT behind, clean it up so the
    # cluster isn't polluted. Only runs when PRAXIS_E2E_LIVE=1.
    if [ "${PRAXIS_E2E_LIVE:-0}" = "1" ] && [ -n "${PROXMOX_LXC_VMID:-}" ]; then
        SCRIPT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
        if [ -x "${SCRIPT_DIR}/rollback.sh" ]; then
            "${SCRIPT_DIR}/rollback.sh" "$PROXMOX_LXC_VMID" >/dev/null 2>&1 || true
        fi
    fi
}

# ── Live e2e tests (only run when PRAXIS_E2E_LIVE=1) ─────────────

@test "live e2e: full deploy — stage → clone → config → start → health → VMID=<n>" {
    run "${DEPLOY}"
    [ "$status" -eq 0 ]
    grep -q "^VMID=${PROXMOX_LXC_VMID}$" <<< "$output"
    grep -q 'deploy: praxis deployed successfully' <<< "$output"
    # No rollback on success.
    ! grep -q 'deploy: FAILED' <<< "$output"
}

@test "live e2e: idempotent re-deploy — same VMID healthy → skip clone" {
    # First deploy (the previous test should have left a healthy CT, OR
    # this test is run in isolation after a successful deploy).
    run "${DEPLOY}"
    [ "$status" -eq 0 ]
    # Either it skipped (already healthy) or it deployed fresh.
    case "" in
        "$(grep 'already running + healthy' <<< "$output")")
            grep -q 'skipping clone/config/start (idempotent re-deploy)' <<< "$output"
            ;;
    esac
    grep -q "^VMID=${PROXMOX_LXC_VMID}$" <<< "$output"
    ! grep -q 'deploy: FAILED' <<< "$output"
}

@test "live e2e: --recreate — rollback + redeploy succeeds" {
    run "${DEPLOY}" --recreate
    [ "$status" -eq 0 ]
    grep -q -- '--recreate' <<< "$output"
    grep -q "^VMID=${PROXMOX_LXC_VMID}$" <<< "$output"
    ! grep -q 'deploy: FAILED' <<< "$output"
}

@test "live e2e: unknown flag → exit 2 (usage)" {
    run "${DEPLOY}" --bogus-flag
    [ "$status" -eq 2 ]
    grep -q 'unknown argument: --bogus-flag' <<< "$output"
}

@test "live e2e: health-check against the deployed CT passes (praxis healthy)" {
    # Run health-check.sh directly against the deployed CT. If the CT
    # was destroyed by a prior teardown, this skips.
    SCRIPT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
    [ -x "${SCRIPT_DIR}/health-check.sh" ] || skip "health-check.sh not found"
    run "${SCRIPT_DIR}/health-check.sh" "${PROXMOX_LXC_VMID}"
    [ "$status" -eq 0 ]
    grep -q 'health-check: praxis healthy' <<< "$output"
}

@test "live e2e: rollback.sh cleans up the CT (idempotent, 404-tolerant)" {
    SCRIPT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
    [ -x "${SCRIPT_DIR}/rollback.sh" ] || skip "rollback.sh not found"
    run "${SCRIPT_DIR}/rollback.sh" "${PROXMOX_LXC_VMID}"
    [ "$status" -eq 0 ]
    grep -q 'rollback: VMID .* cleaned up' <<< "$output"
    # A second rollback must be 404-tolerant (idempotent).
    run "${SCRIPT_DIR}/rollback.sh" "${PROXMOX_LXC_VMID}"
    [ "$status" -eq 0 ]
    grep -q 'rollback: VMID .* cleaned up' <<< "$output"
}

@test "live e2e: rollback.sh on a never-existed VMID → exit 0 (404-tolerant)" {
    SCRIPT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
    [ -x "${SCRIPT_DIR}/rollback.sh" ] || skip "rollback.sh not found"
    # Pick a VMID that definitely doesn't exist (high random range).
    nonexistent="99999"
    run "${SCRIPT_DIR}/rollback.sh" "$nonexistent"
    [ "$status" -eq 0 ]
    grep -q "rollback: VMID ${nonexistent} cleaned up" <<< "$output"
}