feat: add host_agent plugin — push-model host resource monitoring

Lightweight stdlib-only Python agent runs on each monitored host,
collects CPU / memory / disk / load / uptime from /proc every 30s,
and POSTs signed payloads to the Roundtable ingest endpoint. One-line
curl-pipe installer creates a hardened systemd unit; admin UI manages
host registrations with rotate / revoke.

- agent.py: 370 LoC single-file daemon, ring buffer + exponential backoff
- ingest route: bearer-token auth, metric expansion into plugin_metrics
- install.sh.j2: systemd unit with NoNewPrivileges / ProtectSystem / ProtectHome
- settings UI: add host / rotate token / delete registration (admin-only)
- dashboard widgets: fleet-glance table + per-host history chart
- stale-agent scheduler: 60s log warning for agents past 180s silence

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-15 01:04:51 -04:00
parent be4654fc72
commit 7468806bad
14 changed files with 1210 additions and 0 deletions
View File
+70
View File
@@ -0,0 +1,70 @@
# plugins/host_agent/migrations/env.py
"""Alembic env.py for the host_agent plugin."""
import asyncio
import os
import sys
from pathlib import Path
from logging.config import fileConfig
from sqlalchemy import pool
from sqlalchemy.engine import Connection
from sqlalchemy.ext.asyncio import async_engine_from_config
from alembic import context
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent))
from roundtable.models.base import Base
import roundtable.models # noqa: F401
from plugins.host_agent.models import HostAgentRegistration # noqa: F401
config = context.config
if config.config_file_name is not None:
fileConfig(config.config_file_name)
target_metadata = Base.metadata
def _get_url() -> str:
import yaml
cfg_path = os.environ.get("ROUNDTABLE_CONFIG", "config.yaml")
try:
with open(cfg_path) as f:
cfg = yaml.safe_load(f) or {}
url = cfg.get("database", {}).get("url", "")
except FileNotFoundError:
url = ""
return os.environ.get("ROUNDTABLE_DATABASE__URL", url)
def run_migrations_offline() -> None:
context.configure(
url=_get_url(), target_metadata=target_metadata,
literal_binds=True, dialect_opts={"paramstyle": "named"},
)
with context.begin_transaction():
context.run_migrations()
def do_run_migrations(connection: Connection) -> None:
context.configure(connection=connection, target_metadata=target_metadata)
with context.begin_transaction():
context.run_migrations()
async def run_async_migrations() -> None:
cfg = config.get_section(config.config_ini_section, {})
cfg["sqlalchemy.url"] = _get_url()
connectable = async_engine_from_config(cfg, prefix="sqlalchemy.", poolclass=pool.NullPool)
async with connectable.connect() as connection:
await connection.run_sync(do_run_migrations)
await connectable.dispose()
def run_migrations_online() -> None:
asyncio.run(run_async_migrations())
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()
@@ -0,0 +1,36 @@
# plugins/host_agent/migrations/versions/host_agent_001_initial.py
"""host_agent plugin initial tables
Revision ID: host_agent_001_initial
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
revision: str = "host_agent_001_initial"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = "host_agent"
depends_on: Union[str, Sequence[str], None] = ("0004_app_settings",)
def upgrade() -> None:
op.create_table(
"host_agent_registrations",
sa.Column("id", sa.String(36), primary_key=True),
sa.Column("host_id", sa.String(36),
sa.ForeignKey("hosts.id", ondelete="CASCADE"),
nullable=False, unique=True),
sa.Column("token_hash", sa.String(64), nullable=False, unique=True, index=True),
sa.Column("token_created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("agent_version", sa.String(32), nullable=True),
sa.Column("kernel", sa.String(128), nullable=True),
sa.Column("distro", sa.String(128), nullable=True),
sa.Column("arch", sa.String(32), nullable=True),
sa.Column("last_seen_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
)
def downgrade() -> None:
op.drop_table("host_agent_registrations")