#!/bin/bash

# Stalwart upgrade verifier.
# ---------------------------------------------------------------------------
# Stalwart publishes Kubernetes-style probes on its admin port (8080):
#   GET /healthz/live   — the process is alive and not deadlocked
#   GET /healthz/ready  — dependencies initialised, config loaded, accepting traffic
# https://stalw.art/docs/http/overview/
#
# Readiness is the one that matters after a version move: it only answers 200
# once the storage backend is open and the config has loaded, which is exactly
# the window where a schema change would otherwise go unnoticed. Liveness alone
# would pass on a process that is up but unable to serve.
#
# Deliberately weaker than the Nextcloud verifier: Stalwart's probes confirm the
# server is serving, but do not report a version, so this asserts readiness
# rather than "running exactly $expected". Stated plainly instead of implied —
# the ladder is only ever as strong as the check underneath it, and pretending
# otherwise is how a half-migrated app advances a rung.

# stalwart_upgrade_verify <app> <expected-tag> <deadline-epoch>
# 0 only when /healthz/ready answers 200 and keeps answering it.
stalwart_upgrade_verify() {
    local app="$1" expected="$2" deadline="$3"
    local stable=0 stable_needed=3 last=""

    while [ "$(date +%s)" -lt "$deadline" ]; do
        local code
        code="$(runFileOp docker exec stalwart-service curl -fsS -o /dev/null -w '%{http_code}' \
            --max-time 5 http://localhost:8080/healthz/ready 2>/dev/null | tr -d '\r')"
        last="healthz/ready=${code:-none}"

        if [ "$code" = "200" ]; then
            stable=$((stable + 1))
            # Ready must HOLD: a server that flaps ready/not-ready is mid-restart,
            # and one lucky 200 is not evidence the upgrade settled.
            if (( stable >= stable_needed )); then
                isSuccessful "Stalwart is ready (readiness probe stable) after moving to $expected."
                return 0
            fi
        else
            stable=0
        fi
        sleep 5
    done

    isError "Stalwart did not report ready for $expected before the deadline.${last:+ Last probe: $last}"
    return 1
}