feat: operational status endpoint + reconciler/peer state tracking 📊

- ReconciliationWorker._last_run stores per-pass stats (da_servers_polled,
  zones_in_da/db, orphans_found/queued, hostnames_backfilled/migrated,
  zones_healed, duration_seconds, dry_run flag)
- ReconciliationWorker.get_status() exposes state for API/UI consumption
- _heal_backends() now returns healed count
- PeerSyncWorker.get_peer_status() serialises _peer_health to JSON-safe dict
  (url, healthy, consecutive_failures, last_seen) with summary totals
- WorkerManager tracks dead-letter count; queue_status() now returns nested
  reconciler/peer_sync dicts replacing flat reconciler_alive/peer_syncer_alive
- New GET /status endpoint (StatusAPI) aggregates queue depths, worker liveness,
  reconciler last-run, peer health, and live zone count; computes ok/degraded/error
- .gitignore: exclude .claude/, .vscode/, .env (always local)
- app.yml: add documented datastore section (SQLite default + MySQL commented)
- 164 tests passing (23 new tests added)
This commit is contained in:
2026-02-25 18:51:56 +13:00
parent 0f417da204
commit db60d808de
11 changed files with 491 additions and 19 deletions

View File

@@ -394,3 +394,53 @@ def test_sync_empty_peer_list(patch_connect, monkeypatch):
monkeypatch.setattr("directdnsonly.app.peer_sync.requests.get", mock_get)
worker._sync_from_peer(_make_peer())
# ---------------------------------------------------------------------------
# get_peer_status
# ---------------------------------------------------------------------------
def test_get_peer_status_no_contact_yet():
worker = PeerSyncWorker(BASE_CONFIG)
status = worker.get_peer_status()
assert status["enabled"] is True
assert status["total"] == 1
assert status["healthy"] == 1
assert status["degraded"] == 0
assert status["peers"][0]["url"] == "http://ddo-2:2222"
assert status["peers"][0]["healthy"] is True
assert status["peers"][0]["last_seen"] is None
def test_get_peer_status_after_success():
worker = PeerSyncWorker(BASE_CONFIG)
worker._record_success("http://ddo-2:2222")
status = worker.get_peer_status()
assert status["healthy"] == 1
assert status["degraded"] == 0
assert status["peers"][0]["last_seen"] is not None
def test_get_peer_status_after_degraded():
from directdnsonly.app.peer_sync import FAILURE_THRESHOLD
worker = PeerSyncWorker(BASE_CONFIG)
for _ in range(FAILURE_THRESHOLD):
worker._record_failure("http://ddo-2:2222", Exception("timeout"))
status = worker.get_peer_status()
assert status["healthy"] == 0
assert status["degraded"] == 1
assert status["peers"][0]["healthy"] is False
def test_get_peer_status_disabled():
worker = PeerSyncWorker({})
status = worker.get_peer_status()
assert status["enabled"] is False
assert status["total"] == 0
assert status["peers"] == []