felhom.eu/documentation/audits/update-night-2026-09-21/engine_edge.py

#!/usr/bin/env python3
"""engine_edge.py — Phase 2: a DATABASE ENGINE across a major, through the real Update button.

    engine_edge.py nextcloud mariadb:11.6 mariadb:12.3 --engine mariadb --container nextcloud-db
    engine_edge.py docmost postgres:16-alpine postgres:17-alpine --engine postgres --container docmost-postgres

The app image does NOT move. Only the engine sidecar. `09` §3b Q3: the within-a-major test is per
SERVICE, so this edge is ACROSS whatever the app's own number says — and it carries exactly one
migration, which is the whole reason the arc's standing rule gives an engine change its own edge.

THE TWO ENGINES FAIL IN OPPOSITE DIRECTIONS, so one check will not do (`09` §"Database engines"):
  MariaDB   starts anyway and can skip the conversion QUIETLY  -> ASK THE ENGINE, not the log
  PostgreSQL REFUSES to start on an older major's datadir      -> the refusal line, verbatim

`engine_state_after` is reported BESIDE the verdict, never inside it: an unconverted datadir is not
*known* to be a failure and a verdict that said so would encode an unproven judgement.
"""
import argparse, json, os, re, sys, time
from datetime import datetime, timezone

HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE)
import walk as w            # noqa: E402
from fixtures import FIXTURES   # noqa: E402


def mariadb_observables(container, tag):
    """The FOUR observables of SPIKE-r459-mariadb-upgrade-2026-09-06, asked of the ENGINE."""
    return w.guest(f"""
echo "=== [1] mariadb_upgrade_info (the datadir's own record of which version converted it)"
docker exec {container} sh -c 'cat /var/lib/mysql/mariadb_upgrade_info 2>/dev/null || echo "(absent)"' 2>&1
echo "=== [2] the engine's OWN check — NOT the log line (R-464)"
docker exec {container} sh -c 'mariadb-upgrade --check-if-upgrade-is-needed --user=root --password="$MARIADB_ROOT_PASSWORD$MYSQL_ROOT_PASSWORD" 2>&1; echo "exit=$?"' 2>&1
echo "=== [3] the entrypoint's line, from the container log"
docker logs {container} 2>&1 | grep -iE 'upgrade|MARIADB_AUTO_UPGRADE|skipped' | tail -12
echo "=== [4] the engine's own pre-upgrade backup file"
docker exec {container} sh -c 'ls -la /var/lib/mysql/*upgrade*backup* /var/lib/mysql/system_mysql_backup*.sql* 2>/dev/null || echo "(no pre-upgrade backup file present)"' 2>&1
echo "=== [5] the version actually running"
docker exec {container} sh -c 'mariadbd --version 2>/dev/null || mysqld --version 2>/dev/null' 2>&1
echo "=== [6] container state"
docker inspect {container} --format 'image={{{{.Config.Image}}}} running={{{{.State.Running}}}} restarts={{{{.RestartCount}}}} exit={{{{.State.ExitCode}}}}' 2>&1
""", timeout=420)


def postgres_observables(container, tag):
    return w.guest(f"""
echo "=== [1] PG_VERSION — the datadir's own record of its major"
docker exec {container} sh -c 'cat /var/lib/postgresql/data/PG_VERSION 2>/dev/null || echo "(exec refused: the container is not running)"' 2>&1
docker run --rm -v $(docker inspect {container} --format '{{{{range .Mounts}}}}{{{{if eq .Destination "/var/lib/postgresql/data"}}}}{{{{.Name}}}}{{{{end}}}}{{{{end}}}}'):/d alpine:3.20 sh -c 'cat /d/PG_VERSION 2>/dev/null || cat /d/pgdata/PG_VERSION 2>/dev/null || echo "(no PG_VERSION found)"' 2>&1
echo "=== [2] the engine's REFUSAL, verbatim (the whole point of this leg)"
docker logs {container} 2>&1 | tail -25
echo "=== [3] container state"
docker inspect {container} --format 'image={{{{.Config.Image}}}} running={{{{.State.Running}}}} restarts={{{{.RestartCount}}}} exit={{{{.State.ExitCode}}}}' 2>&1
echo "=== [4] the version binary in the image"
docker exec {container} sh -c 'postgres --version' 2>&1 || echo "(cannot exec — not running)"
""", timeout=420)


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("app")
    ap.add_argument("frm")
    ap.add_argument("to")
    ap.add_argument("--engine", required=True, choices=["mariadb", "postgres"])
    ap.add_argument("--container", required=True)
    ap.add_argument("--sub", default=None)
    ap.add_argument("--restore-after", action="store_true",
                    help="when the edge ends held or the data does not read back, walk\n                          the household's own way out: the restore the sentence names")
    a = ap.parse_args()

    app = a.app
    appdir = os.path.join(HERE, "apps", f"{app}-engine-{a.engine}")
    os.makedirs(appdir, exist_ok=True)
    fx = FIXTURES.get(app)
    sub = a.sub or (fx.sub if fx else app)
    t0 = time.time()

    w.say(f"==== ENGINE EDGE {app}: {a.frm} -> {a.to}  (app image does NOT move)")
    w.login()

    rec = {"harness_version": 1, "app": app, "leg": f"engine-major-{a.engine}",
           "venue": "guest 9202 demo-hp-scratch, controller 0.261.0",
           "from": {a.container: a.frm}, "to": {a.container: a.to},
           "verdict": "inconclusive", "seed_read_before": False, "seed_read_after": False,
           "healthy_after": False, "migration_observed": None,
           "abort": "not-attempted", "abort_detail": None,
           "engine_state_before": None, "engine_state_after": None,
           "duration_s": 0, "measured_at": datetime.now(timezone.utc).isoformat(),
           "evidence": f"apps/{app}-engine-{a.engine}/", "notes": []}

    def save():
        rec["duration_s"] = round(time.time() - t0, 1)
        json.dump(rec, open(f"{appdir}/verdict.json", "w"), indent=2, ensure_ascii=False)
        open(f"{appdir}/log.txt", "w").write("\n".join(w.LOG) + "\n")
        w.say(f"  verdict {rec['verdict']} -> {appdir}/verdict.json")

    obs = mariadb_observables if a.engine == "mariadb" else postgres_observables

    # ---- deploy + seed + C1 ----------------------------------------------------------------
    if not w.deploy(app, sub):
        rec["notes"].append("deploy never reached running")
        return save()
    if fx is None:
        rec["notes"].append("no fixture for this app — recorded inconclusive rather than faked")
        return save()
    w.say("  [2] seeding through the app's own route")
    tok = fx.seed(w, sub, w.say)
    if tok is None:
        rec["notes"].append("seed refused — see log.txt for what was tried")
        return save()
    w.say("  [3] control C1 — reading the seed back BEFORE the engine moves")
    if not fx.verify(w, sub, tok, w.say):
        rec["notes"].append("C1 FAILED — a fixture that cannot prove itself first proves nothing after")
        return save()
    rec["seed_read_before"] = True

    before = obs(a.container, a.frm)
    open(f"{appdir}/engine-before.txt", "w").write(before)
    rec["engine_state_before"] = before[:4000]
    w.say("  [3b] engine observables BEFORE written to engine-before.txt")

    # ---- backup, then the engine bump --------------------------------------------------------
    w.backup_now(app)
    h = w.drill_bump(app, a.frm, a.to)
    if h is None:
        rec["notes"].append("the engine bump could not be committed")
        return save()
    rec["badge_catchup_seconds"] = w.sync_rescan(expect_app=app, expect_ref=a.to)
    b = w.badges(app)
    json.dump(b, open(f"{appdir}/badges.json", "w"), indent=2, ensure_ascii=False)
    w.say(f"  [5] badge HU: {b['hu']}")
    w.say(f"  [5] badge EN: {b['en']}")

    # ---- the real Update button ---------------------------------------------------------------
    res = w.press_update(app)
    json.dump(res, open(f"{appdir}/phases.json", "w"), indent=2, ensure_ascii=False)
    rec["phases"] = res.get("phases")
    rec["final_phase"] = res.get("final_phase")
    rec["hold_reason"] = res.get("hold_reason")
    rec["update_error"] = res.get("update_error")
    if not res["accepted"]:
        rec["notes"].append(f"REFUSED before anything moved: {json.dumps(res['refusal'], ensure_ascii=False)[:400]}")
        return save()

    after = obs(a.container, a.to)
    open(f"{appdir}/engine-after.txt", "w").write(after)
    rec["engine_state_after"] = after[:6000]
    w.say("  [6b] engine observables AFTER written to engine-after.txt")

    # the hold sentence as the HOUSEHOLD reads it, both languages
    holds = {}
    for lang, sfx in (("hu", ""), ("en", "?lang=en")):
        html = w.page(f"/apps/{app}{sfx}")
        html = re.sub(r"<script.*?</script>", " ", html, flags=re.S)
        html = re.sub(r"<style.*?</style>", " ", html, flags=re.S)
        txt = re.sub(r"\s+", " ", re.sub(r"<[^>]+>", " ", txt if False else html))
        keep = [s.strip() for s in re.split(r"(?<=[.!?]) ", txt)
                if any(k in s.lower() for k in ("friss", "update", "vissza", "restore",
                                                "ment", "backup", "hib", "error", "megsz"))]
        holds[lang] = keep[:14]
    json.dump(holds, open(f"{appdir}/hold-sentences.json", "w"), indent=2, ensure_ascii=False)
    rec["hold_sentences"] = holds
    w.say(f"  [6c] hold sentences HU: {holds['hu'][:3]}")
    w.say(f"  [6c] hold sentences EN: {holds['en'][:3]}")

    # ---- read the seed back -------------------------------------------------------------------
    w.say("  [7] reading the seed back AFTER the engine moved")
    rec["seed_read_after"] = fx.verify(w, sub, tok, w.say)

    logs = w.app_logs(app, 600)
    open(f"{appdir}/app-logs-after.txt", "w").write(logs)

    post = w.observables(app)
    json.dump(post, open(f"{appdir}/observables-after.json", "w"), indent=2, ensure_ascii=False)
    rec["observables_after"] = post
    w.say(f"  [8] pinned    = {post['pinned_images']}")
    w.say(f"  [8] installed = {post['installed_images']}")
    w.say(f"  [8] compose   = {post['live_compose_image_lines']}")
    w.say(f"  [8] inspect   = {post['docker_inspect']}")

    # ---- the household's WAY OUT, when the edge ended badly -------------------------------
    # `09` §4: after a migration has run the only shape available is RESTORE FROM A COPY, and
    # §6.1 says a successful unit restore lifts an update hold. The sentence on the page tells
    # the household to press that button; this presses it and then asks the APP whether the data
    # came back — never the filesystem.
    st = w.stack(app)
    if a.restore_after and (st.get("hold_reason") or res["final_phase"] == "failed"
                            or not rec["seed_read_after"]):
        w.say("  [W] the edge ended badly — walking the household's way out (restore)")
        rec["way_out"] = w.restore(app)
        rec["seed_read_after_restore"] = fx.verify(w, sub, tok, w.say)
        w.say(f"  [W] the seed read back after the restore: {rec['seed_read_after_restore']}")
        rec["engine_state_after_restore"] = obs(a.container, a.frm)
        open(f"{appdir}/engine-after-restore.txt", "w").write(rec["engine_state_after_restore"])
        rec["hold_sentences_after_restore"] = {}
        for lang, sfx in (("hu", ""), ("en", "?lang=en")):
            html = w.page(f"/apps/{app}{sfx}")
            html = re.sub(r"<script.*?</script>", " ", html, flags=re.S)
            html = re.sub(r"<style.*?</style>", " ", html, flags=re.S)
            txt = re.sub(r"\s+", " ", re.sub(r"<[^>]+>", " ", html))
            rec["hold_sentences_after_restore"][lang] = [
                s.strip() for s in re.split(r"(?<=[.!?]) ", txt)
                if any(k in s.lower() for k in ("friss", "update", "vissza", "restore"))][:8]

    st = w.stack(app)
    rec["healthy_after"] = (st.get("state") == "running" and not st.get("hold_reason"))
    if res["final_phase"] == "done" and rec["seed_read_after"] and rec["healthy_after"]:
        rec["verdict"] = "proven"
    elif res.get("hold_reason") or res["final_phase"] == "failed":
        rec["verdict"] = "failed"
        rec["notes"].append("ended HELD or failed — a RESULT, not an error of the run")
    else:
        rec["verdict"] = "inconclusive"
    save()


if __name__ == "__main__":
    main()