bvandeusenandClaude Opus 5.5
c7ff5bc556
#5756 "The agent says when its host rebooted and when it lost contact, so downtime is recorded as what it was". Agent 1.14.0 posts events with the next post that gets through: started (with the host's boot time), stopping (on SIGTERM, with whether systemd says the host is going down) and lost_contact (from its first unanswered post to the one carrying it). Steward keeps them as the host's downtime (host_downtime): reboot, agent_stop, unclean (a boot after the agent was last heard that nobody announced) or lost_contact. Retried posts apply once. An announced stop explains the silence for reboot_grace_seconds (Settings -> Plugins -> host_agent, 10 minutes): seconds_since_seen reads 0 until then, and the host's other rules go quiet with it (agents_away beside #5721's registry). Past the grace, agent offline fires. The host's Agent card lists the last 7 days of downtime. Rows are pruned at data.retention_days. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
59 lines
2.6 KiB
Python
59 lines
2.6 KiB
Python
# plugins/host_agent/models.py
|
|
from __future__ import annotations
|
|
import uuid
|
|
from datetime import datetime, timezone
|
|
from sqlalchemy import Column, String, DateTime, Float, ForeignKey
|
|
from steward.models.base import Base
|
|
|
|
|
|
def _uuid() -> str:
|
|
return str(uuid.uuid4())
|
|
|
|
|
|
def _utcnow() -> datetime:
|
|
return datetime.now(timezone.utc)
|
|
|
|
|
|
class HostAgentRegistration(Base):
|
|
__tablename__ = "host_agent_registrations"
|
|
|
|
id = Column(String(36), primary_key=True, default=_uuid)
|
|
host_id = Column(String(36), ForeignKey("hosts.id", ondelete="CASCADE"),
|
|
unique=True, nullable=False)
|
|
token_hash = Column(String(64), nullable=False, unique=True, index=True)
|
|
token_created_at = Column(DateTime(timezone=True), nullable=False, default=_utcnow)
|
|
agent_version = Column(String(32), nullable=True)
|
|
kernel = Column(String(128), nullable=True)
|
|
distro = Column(String(128), nullable=True)
|
|
arch = Column(String(32), nullable=True)
|
|
# Agent-reported primary IP. 45 chars = max textual IPv6 (no zone suffix).
|
|
host_ip = Column(String(45), nullable=True)
|
|
last_seen_at = Column(DateTime(timezone=True), nullable=True)
|
|
# How far this host's clock is from Steward's, in seconds, positive when
|
|
# the host is ahead, measured from the agent's sent_at on the newest post;
|
|
# and when that was. None until an agent that stamps its posts reports.
|
|
clock_offset_s = Column(Float, nullable=True)
|
|
clock_checked_at = Column(DateTime(timezone=True), nullable=True)
|
|
created_at = Column(DateTime(timezone=True), nullable=False, default=_utcnow)
|
|
updated_at = Column(DateTime(timezone=True), nullable=False,
|
|
default=_utcnow, onupdate=_utcnow)
|
|
|
|
|
|
class HostDowntime(Base):
|
|
"""A span a host's agent was away, and what the agent said it was (#5756).
|
|
|
|
kind is "reboot" (the host went down and came back), "agent_stop" (the
|
|
agent stopped; the host stayed up), "unclean" (the host came back from a
|
|
boot nobody announced: power loss or a crash) or "lost_contact" (the agent
|
|
ran but couldn't reach Steward). ended_at is None while it is going on.
|
|
"""
|
|
__tablename__ = "host_downtime"
|
|
|
|
id = Column(String(36), primary_key=True, default=_uuid)
|
|
host_id = Column(String(36), ForeignKey("hosts.id", ondelete="CASCADE"),
|
|
nullable=False, index=True)
|
|
kind = Column(String(16), nullable=False)
|
|
started_at = Column(DateTime(timezone=True), nullable=False)
|
|
ended_at = Column(DateTime(timezone=True), nullable=True)
|
|
created_at = Column(DateTime(timezone=True), nullable=False, default=_utcnow)
|