turnstone/patterns/sources.yaml
pyr0ball 63c742a708 feat: periodic ingest scheduler + Orchard submission pipeline
Adds asyncio-native background scheduler (TURNSTONE_INGEST_INTERVAL,
default 900s) that runs batch ingest then pushes pattern-matched entries
to a remote CF harvest endpoint (TURNSTONE_SUBMIT_ENDPOINT).

- app/tasks/ingest_scheduler.py: IngestState, scheduler_loop, run_once,
  submit_matched, _query_matched_since — asyncio.Lock prevents concurrent runs
- app/rest.py: POST /api/ingest/batch (pre-parsed entry receiver),
  GET /api/tasks/ingest/status, POST /api/tasks/ingest (manual trigger),
  TURNSTONE_INGEST_INTERVAL + TURNSTONE_SUBMIT_ENDPOINT env wiring in lifespan
- docker-compose.submissions.yml: segregated contrib1 (8536) + contrib2 (8537)
  receiving instances on Heimdall, isolated DBs under
  /devl/docker/turnstone-submissions/<node>/
- podman-standalone.sh: pass-through for TURNSTONE_SUBMIT_ENDPOINT +
  TURNSTONE_SOURCE_HOST
- app/ingest/mqtt_subscriber.py: MQTT log source adapter
- app/ingest/wazuh.py: Wazuh alert JSON adapter
- tests/test_ingest_wazuh.py: Wazuh adapter test suite
2026-05-20 08:57:25 -07:00

96 lines
3.7 KiB
YAML

# Turnstone log sources — edit this file to add or remove services.
# NOTE: the system-journal entry requires export_journal.sh to run on the HOST
# before the container ingest step. See crontab setup instructions in the README.
# Run ingest manually:
# sudo podman exec turnstone python scripts/ingest_corpus.py \
# --sources /patterns/sources.yaml --db /data/turnstone.db
#
# Paths here are container-side paths under the /opt bind mount.
# Missing paths are skipped with a warning — safe to leave entries for
# services that are temporarily down.
sources:
# ── System (exported by export_journal.sh on the host) ───────────────────
# journal-export.jsonl and dmesg-export.txt are written to /opt/turnstone/data/
# by the export script before each ingest run.
- id: system-journal
path: /data/journal-export.jsonl
- id: dmesg
path: /data/dmesg-export.txt
# ── Syslog / rsyslog (direct file reads via /var/log bind mount) ──────────
# Uncomment the file(s) present on your system.
# Debian/Ubuntu:
# - id: syslog
# path: /var/log/syslog
# - id: auth-log
# path: /var/log/auth.log
# - id: kern-log
# path: /var/log/kern.log
# RHEL/Fedora/Rocky:
# - id: messages
# path: /var/log/messages
# - id: secure
# path: /var/log/secure
# ── Download ─────────────────────────────────────────────────────────────
- id: qbittorrent
path: /opt/qbittorrent/config/data/logs/qbittorrent.log
# ── Servarr stack ─────────────────────────────────────────────────────────
- id: sonarr
path: /opt/sonarr/config/logs/sonarr.0.txt
- id: radarr
path: /opt/radarr/config/logs/radarr.0.txt
- id: lidarr
path: /opt/lidarr/config/logs/Lidarr.0.txt
- id: readarr
path: /opt/readarr/config/logs/readarr.0.txt
- id: whisparr
path: /opt/whisparr/config/logs/whisparr.0.txt
- id: prowlarr
path: /opt/prowlarr/config/logs/prowlarr.0.txt
- id: bazarr
path: /opt/bazarr/config/log/bazarr.log
# ── Usenet ────────────────────────────────────────────────────────────────
- id: nzbget
path: /opt/nzbget/config/nzbget.log
# ── Media / Requests ─────────────────────────────────────────────────────
- id: tautulli
path: /opt/tautulli/config/logs/tautulli.log
- id: jellyseerr
path: /opt/jellyseerr/config/logs/jellyseerr.log
# ── MQTT / IoT (live — subscribe mode, no path needed) ───────────────────
# Requires: pip install circuitforge-core[mqtt]
# These sources are handled by the live MQTT subscriber task (not batch ingest).
# Uncomment and configure to enable.
#
# Meshtastic MQTT bridge (node must have MQTT uplink enabled):
# - id: meshtastic-home
# type: mqtt
# broker_host: 10.1.10.5 # IP of your local MQTT broker (e.g. Mosquitto on Huginn)
# broker_port: 1883
# topics:
# - msh/# # all Meshtastic regions; use msh/us-east/# to narrow
#
# Generic IoT sensors:
# - id: iot-home
# type: mqtt
# broker_host: localhost
# broker_port: 1883
# topics:
# - home/+/temperature
# - home/+/humidity
# - home/+/motion
# severity: INFO