bvandeusenandClaude Opus 5.5
96c1ea9407
- Agent 1.12.0 stamps each post with sent_at; ingest compares it with the moment the post arrived: clock_offset_s / clock_checked_at on the registration (host_agent_003), and a clock_off_secs metric (either way) that alert rules can watch. Replaces the old skew log, which measured the newest sample and was off by up to an interval. - Settings -> Thresholds: Clock drift, 30 s warn / 5 min critical. - Host page: 'clock 0.3s ahead' in the vitals line, toned past the warning. - Hosts list: names hosts whose clock is off; when every reporting host is off by about the same amount, says Steward's own clock is the likely one. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
# plugins/host_agent/__init__.py
|
|
from __future__ import annotations
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from quart import Quart
|
|
|
|
_app: "Quart | None" = None
|
|
|
|
|
|
def setup(app: "Quart") -> None:
|
|
global _app
|
|
_app = app
|
|
|
|
|
|
def get_scheduled_tasks() -> list:
|
|
from .scheduler import make_task
|
|
return [make_task(_app)]
|
|
|
|
|
|
def get_blueprint():
|
|
from .routes import host_agent_bp
|
|
return host_agent_bp
|
|
|
|
|
|
def register_mcp_tools(register) -> None:
|
|
from .mcp_tools import register_tools
|
|
register_tools(register)
|
|
|
|
|
|
async def mcp_overview(db) -> list[dict]:
|
|
from .mcp_tools import mcp_overview as findings
|
|
return await findings(db)
|
|
|
|
|
|
def get_alert_metrics() -> dict[str, list[str]]:
|
|
"""Host metrics ingest records for alert rules (resource = the host name;
|
|
disk_used_pct per mount, resource "<host>:<mount>"). seconds_since_seen
|
|
comes from the scheduler, not the agent: "agent offline" is > 180.
|
|
clock_off_secs is how far the host's clock is from Steward's, either way
|
|
(agent ≥ 1.12.0): "clock drifting" is > 30."""
|
|
return {"host_agent": [
|
|
"cpu_pct", "mem_used_pct", "mem_available_bytes", "swap_used_bytes",
|
|
"disk_used_pct_worst", "disk_used_pct", "load_1m", "load_5m", "load_15m",
|
|
"uptime_secs", "seconds_since_seen", "clock_off_secs",
|
|
]}
|