af42bf5abd
Tracked Services and Tracked Processes were sharing a tab with system health cards, so what is running on the box and how the box itself is doing read as one list. They now sit in a Service/Process Monitors tab and the old tab is System Monitors. The group vocabulary is duplicated across the renderer, the tab map and the panel declarations with nothing checking they agree, and a group named in one but not the others is dropped in silence - that has eaten cards twice. Tests now pin the vocabulary on both sides. Boot type and NIC link state were collected in Phase 2 but shown nowhere. Boot type only renders when fast startup applies, because uptime measured from a resume understates how long the kernel has been up and that is the case worth naming. Link state leaves a disconnected NIC unknown rather than half duplex: live hardware returns empty speed and duplex when unplugged, and half duplex is the cable fault signature this column exists to catch.
1211 lines
57 KiB
Python
1211 lines
57 KiB
Python
"""Endpoints plugin main class.
|
|
|
|
Endpoint RMM telemetry reported by the ShopDB agent. Accepts collector input
|
|
over HTTPS per ADR-006: the agent posts a per-host payload to
|
|
POST /api/collector/endpoints, the plugin resolves the reported hostname to an
|
|
existing computer asset, overwrites that asset's cached EndpointState, and
|
|
appends any curated Windows events the report carried - all in one commit, so
|
|
the cached snapshot and the events it summarizes never disagree.
|
|
|
|
Identity is the hostname, resolved against the computers plugin. An unresolved
|
|
hostname is reported as a ValueError (surfaced to the caller as a validation
|
|
error), never silently dropped: an unknown host is a real gap between the fleet
|
|
and ShopDB, the same discipline the backups collector uses for machine numbers.
|
|
"""
|
|
|
|
import json
|
|
import logging
|
|
from datetime import datetime, timezone
|
|
from pathlib import Path
|
|
from typing import Dict, List, Optional, Type
|
|
|
|
from flask import Flask, Blueprint
|
|
|
|
from shopdb.plugins.base import BasePlugin, PluginMeta
|
|
from shopdb.api import db
|
|
|
|
from .api import endpoints_bp
|
|
from .eventcatalog import EVENT_CATALOG
|
|
from .models import (
|
|
EndpointState, EndpointEvent, EndpointCommand, EndpointApplication,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# The fixed catalog of Windows Event IDs the agent forwards. Derived from
|
|
# EVENT_CATALOG (eventcatalog.py) so the ingest filter and the display titles
|
|
# can never drift. IDs outside this set are ignored on ingest rather than
|
|
# stored, keeping endpointevents a readable security/stability history instead
|
|
# of a raw event firehose.
|
|
CURATED_EVENT_IDS = frozenset(EVENT_CATALOG)
|
|
|
|
# Top-level payload keys the ingest path knows about today - either persisted on
|
|
# EndpointState, appended as events, or relayed to the computers collector.
|
|
# Anything the agent sends outside this set is not stored yet; it is logged (see
|
|
# apply_collector_payload) so new agent telemetry - disks, bios, memory, etc. -
|
|
# is observable in the logs before the server grows columns for it. Keep this in
|
|
# lockstep with the keys consumed in apply_collector_payload and the computers
|
|
# handoff subset.
|
|
KNOWN_PAYLOAD_KEYS = frozenset({
|
|
'hostname', 'adopt', 'loggedinuser', 'serialnumber', 'pctype',
|
|
'machinenumber', 'vendorname', 'modelnumber', 'osname', 'ipaddress',
|
|
'agentversion', 'trayversion', 'lastboottime', 'uptimeseconds', 'idleseconds',
|
|
'cpupercent', 'memorypercent', 'services', 'ports', 'interfaces',
|
|
'scheduledtasks', 'applications', 'events',
|
|
'disks', 'bios', 'memory', 'processor', 'osinfo', 'domain',
|
|
'pendingreboot', 'usercontext', 'diskhealth',
|
|
'rebootreasons', 'bootinfo', 'defender',
|
|
})
|
|
|
|
|
|
def _parse_dt(value):
|
|
"""Best-effort parse of an ISO-8601 string to naive UTC, or None.
|
|
|
|
astimezone(tz=None) converts to the SERVER's local zone, not to UTC, so an
|
|
agent reporting 17:26:16Z was stored as 13:26:16 on an EDT server and then
|
|
re-served labelled 'Z'. The same row's server-written lastreportedat stayed
|
|
true UTC, so one row carried two time bases four hours apart, and the
|
|
dashboard's 48-hour stability window - which compares a real UTC cutoff
|
|
against these values - dropped events four hours early.
|
|
|
|
Invisible on a UTC server, which is why it survived: nothing in the
|
|
Dockerfile, the compose files or the Windows deploy pins TZ, so whether the
|
|
data is right depends on the host's clock settings.
|
|
|
|
AGENT-CONTRACT.md mandates UTC on the wire. A NAIVE value is therefore
|
|
taken as UTC already, rather than guessed at.
|
|
"""
|
|
if not value:
|
|
return None
|
|
if isinstance(value, datetime):
|
|
if value.tzinfo is not None:
|
|
return value.astimezone(timezone.utc).replace(tzinfo=None)
|
|
return value
|
|
text = str(value).strip().replace('Z', '+00:00')
|
|
try:
|
|
parsed = datetime.fromisoformat(text)
|
|
except ValueError:
|
|
return None
|
|
if parsed.tzinfo is not None:
|
|
parsed = parsed.astimezone(timezone.utc).replace(tzinfo=None)
|
|
return parsed
|
|
|
|
|
|
def _as_json(value):
|
|
"""Serialize a list/dict to JSON text, or None when nothing was sent."""
|
|
if value is None:
|
|
return None
|
|
return json.dumps(value, separators=(',', ':'), sort_keys=True)
|
|
|
|
|
|
def _clamp(value, length):
|
|
"""A string bounded to its column width, or None.
|
|
|
|
Ingest writes whatever an endpoint reports. A registry value longer than its
|
|
column is not a data-quality nuisance on MySQL: in strict mode it raises
|
|
Data too long and fails the whole check-in transaction, so one machine with
|
|
a malformed Uninstall entry stops reporting telemetry and events entirely.
|
|
"""
|
|
if value is None:
|
|
return None
|
|
text = str(value).strip()
|
|
return text[:length] or None
|
|
|
|
|
|
class EndpointsPlugin(BasePlugin):
|
|
"""Endpoint RMM telemetry ingest plus read/dashboard surface."""
|
|
|
|
def __init__(self):
|
|
self._manifest = self._load_manifest()
|
|
|
|
def _load_manifest(self) -> Dict:
|
|
manifest_path = Path(__file__).parent / 'manifest.json'
|
|
if manifest_path.exists():
|
|
with open(manifest_path, 'r') as f:
|
|
return json.load(f)
|
|
return {}
|
|
|
|
@property
|
|
def meta(self) -> PluginMeta:
|
|
return PluginMeta(
|
|
name=self._manifest.get('name', 'endpoints'),
|
|
version=self._manifest.get('version', '0.1.0'),
|
|
description=self._manifest.get(
|
|
'description', 'Endpoint RMM telemetry'),
|
|
author=self._manifest.get('author', 'ShopDB Team'),
|
|
dependencies=self._manifest.get('dependencies', ['computers']),
|
|
core_version=self._manifest.get('core_version', '>=0.20.0,<1.0.0'),
|
|
api_prefix=self._manifest.get('api_prefix', '/api/endpoints'),
|
|
)
|
|
|
|
def get_blueprint(self) -> Optional[Blueprint]:
|
|
return endpoints_bp
|
|
|
|
def get_models(self) -> List[Type]:
|
|
return [EndpointState, EndpointEvent, EndpointCommand,
|
|
EndpointApplication]
|
|
|
|
def get_permissions(self) -> List:
|
|
"""RBAC for the human-facing read routes.
|
|
|
|
View only. Ingest is not covered here: the collector path authorizes on
|
|
a collector.ingest-scoped service token, not a user JWT. There is no
|
|
write/delete permission because operators do not edit telemetry - the
|
|
agent is the sole author, and history is pruned by policy, not by hand.
|
|
"""
|
|
return [
|
|
('endpoints.view', 'View endpoint telemetry', 'endpoints'),
|
|
# The FLEET-WIDE list and dashboards, separate from endpoints.view,
|
|
# which covers reading ONE endpoint that the caller already reached
|
|
# through its PC page.
|
|
#
|
|
# They were one permission, and that made a reasonable policy
|
|
# impossible to express: a site that wants signed-out visitors to
|
|
# see live status on a PC page had to hand them the whole fleet,
|
|
# including every logged-in username on the floor, because the
|
|
# panels and the list were gated on the same string.
|
|
#
|
|
# The name avoids '.view' for readability, but the NAME no longer
|
|
# decides anything: guest_grantable_permissions is a declared list
|
|
# now, and this plugin blesses endpoints.view alone below. Adding
|
|
# endpoints.fleet there would be what opens the roster, and the
|
|
# docstring on that hook says why not to.
|
|
('endpoints.fleet',
|
|
'View the fleet-wide endpoint list and dashboards', 'endpoints'),
|
|
# Issue an allowlisted command to an endpoint agent (for example the
|
|
# MTConnect toggle). Separate from endpoints.view because acting on a
|
|
# shop-floor PC is a heavier grant than reading its telemetry.
|
|
('endpoints.command',
|
|
'Send allowlisted commands to endpoint agents', 'endpoints'),
|
|
# Elevated grant for destructive endpoint actions (system_restart).
|
|
# Required IN ADDITION to endpoints.command by the enqueue route, so a
|
|
# remote reboot is a strictly heavier grant than a routine toggle.
|
|
('endpoints.restart',
|
|
'Restart endpoint computers (destructive)', 'endpoints'),
|
|
# Elevated grant for software delivery (run_script, update_app).
|
|
# Required IN ADDITION to endpoints.command by the enqueue route, so
|
|
# running a staged script or pushing an installer is a strictly
|
|
# heavier grant than a routine service/process toggle.
|
|
('endpoints.deploy',
|
|
'Run staged scripts and push application installers to endpoints', 'endpoints'),
|
|
# Packaging the agent is a heavier grant than deploying to one, and
|
|
# it is not the same job either: the generated ZIP carries a live
|
|
# collector key stamped into its install script, so whoever holds
|
|
# this can mint a distributable artefact containing the fleet-wide
|
|
# command-channel credential. It was require_role('admin'), which
|
|
# this codebase otherwise reserves for the few genuinely
|
|
# role-shaped checks - and a role cannot be granted to one person
|
|
# for one job the way a permission can.
|
|
# It now also governs SUPPLYING the binary, not just wrapping it.
|
|
# Before the agent store, the exe could only be staged by someone
|
|
# with filesystem access to instance/siteagent/; the upload routes
|
|
# put that behind this same grant, so a holder chooses the file
|
|
# every future package installs and runs as SYSTEM. Whoever grants
|
|
# this has to be able to see that from the description.
|
|
('endpoints.agentpackage',
|
|
'Upload the agent binary the fleet installs, and generate or '
|
|
'download an agent or adoption-tool package (supplies an '
|
|
'executable that runs as SYSTEM; the package contains a live '
|
|
'collector key)', 'endpoints'),
|
|
# Pushing an agent REPLACEMENT to running endpoints is a distinct,
|
|
# heavier job than either packaging (endpoints.agentpackage) or
|
|
# pushing an ordinary application installer (endpoints.deploy).
|
|
# Kept separate on purpose: the agent runs as SYSTEM and is the
|
|
# command channel itself, so replacing it is self-modifying the
|
|
# control plane. Folding it into endpoints.deploy would let anyone
|
|
# who can push an app silently swap the agent; folding it into
|
|
# endpoints.agentpackage would let a packager who only mints ZIPs
|
|
# also force a live fleet-wide swap. A future Operator role can
|
|
# hold upload without this, or this without upload.
|
|
('endpoints.agentupdate',
|
|
'Push agent/tray binary updates to running endpoints '
|
|
'(replaces the SYSTEM agent)', 'endpoints'),
|
|
# Collector service scope for the endpoint agent. A managed token
|
|
# scoped to ONLY this authorizes the endpoints collector and nothing
|
|
# else, so rotating/revoking it stops endpoint-agent traffic without
|
|
# touching computers/geenforce collectors. Minted from the settings
|
|
# UI (see get_settings_cards). Admins hold it via the catalog.
|
|
('collector.ingest.endpoints',
|
|
'Submit endpoint agent telemetry (fleet reporting)', 'collector'),
|
|
]
|
|
|
|
def get_guest_grantable_permissions(self) -> List[str]:
|
|
"""Declared because a site chose it: live status on a PC page.
|
|
|
|
endpoints.view only. NOT endpoints.fleet - that is the roster, and the
|
|
whole reason the two were split.
|
|
|
|
KNOWN GAP, tracked separately: the per-asset panels this opens are
|
|
keyed on a small integer asset id and the status panel emits the
|
|
logged-in username, so walking ids reconstructs most of the roster the
|
|
split exists to protect. Bounding or rate-limiting the per-asset panels
|
|
is the fix. Until then a site enabling guest access should know the
|
|
split is a speed bump here, not a wall.
|
|
"""
|
|
return ['endpoints.view']
|
|
|
|
def get_settings_defaults(self) -> List[Dict]:
|
|
"""Settings owned by the endpoints agent-key kill switch.
|
|
|
|
`envkeyfallback` gates the bootstrap .env collector key: while true the
|
|
old COLLECTOR_API_KEY[_ENDPOINTS] still authorizes (back-compat, and the
|
|
only path before a UI key exists). The regenerate flow flips it false so
|
|
the .env key stops working and the managed token is the sole credential,
|
|
making revocation an instant kill switch. `agentkeyprovisioned` records
|
|
that a UI-managed key has been minted so the settings page can render
|
|
the rotate/revoke state instead of the first-run generate state.
|
|
"""
|
|
return [
|
|
{
|
|
'key': 'plugin.endpoints.envkeyfallback',
|
|
'value': 'true',
|
|
'valuetype': 'boolean',
|
|
'category': 'plugin.endpoints',
|
|
'description': 'Accept the bootstrap .env collector key for '
|
|
'endpoints. Turned off once a UI-managed agent '
|
|
'key is provisioned so revocation is a real kill '
|
|
'switch.',
|
|
},
|
|
{
|
|
'key': 'plugin.endpoints.agentkeyprovisioned',
|
|
'value': 'false',
|
|
'valuetype': 'boolean',
|
|
'category': 'plugin.endpoints',
|
|
'description': 'True once an operator has minted a UI-managed '
|
|
'endpoint agent key from the settings page.',
|
|
},
|
|
]
|
|
|
|
def get_settings_cards(self) -> List[Dict]:
|
|
"""The endpoints management card on the global settings page.
|
|
|
|
A settings card rather than a docs page because it is the operator's
|
|
control surface: manage the agent key (the kill switch), build the site
|
|
agent, and configure what it reports. Admin only - key management mints
|
|
a collector service credential.
|
|
"""
|
|
return [
|
|
{
|
|
'group': 'Endpoints',
|
|
'to': '/settings/endpoints/agentkey',
|
|
'icon': 'key',
|
|
'title': 'Endpoints',
|
|
'description': 'Manage the endpoint agent key, build the site '
|
|
'agent, and configure what it reports.',
|
|
'position': 27,
|
|
},
|
|
]
|
|
|
|
def get_navigation_items(self) -> List[Dict]:
|
|
"""Sidebar entry for the fleet list view.
|
|
|
|
Filed under Assets, immediately after PCs (position 15), because the
|
|
fleet view is a telemetry lens over the same computers rather than a
|
|
different kind of thing. It shipped declaring a section of its own,
|
|
which rendered a one-item 'Fleet' group at the bottom of the sidebar,
|
|
far from the PCs it describes.
|
|
"""
|
|
return [
|
|
{
|
|
'name': 'Fleet',
|
|
'icon': 'activity',
|
|
'route': '/endpoints',
|
|
'position': 16,
|
|
'permission': 'endpoints.fleet',
|
|
'section': 'assets',
|
|
},
|
|
# TEMPORARY / DEV ONLY. A manual bench to exercise the update_app and
|
|
# run_script delivery path while Cameron builds the production UI.
|
|
# Gated on endpoints.deploy so only delivery operators see it. Remove
|
|
# this entry (and the DeliveryTestBench view/route) once the real
|
|
# delivery UI ships.
|
|
{
|
|
'name': 'Delivery test bench',
|
|
'icon': 'send',
|
|
'route': '/endpoints/delivery-test',
|
|
'position': 17,
|
|
'permission': 'endpoints.deploy',
|
|
'section': 'assets',
|
|
},
|
|
]
|
|
|
|
def init_app(self, app: Flask, db_instance) -> None:
|
|
logger.info('Endpoints plugin initialized (v%s)', self.meta.version)
|
|
|
|
# ---- ADR-010 UI hooks -----------------------------------------------
|
|
|
|
def get_asset_panels(self) -> List[Dict]:
|
|
"""Per-PC detail panels, computer assets only.
|
|
|
|
Panels feeding the generic renderer: the current status snapshot
|
|
(keyvalue), monitored services and processes split into two list cards
|
|
that share one services snapshot (filtered by kind), the most recent
|
|
curated events (list), and the network interfaces (table). Each is a
|
|
single-asset indexed read, so the cost is the same profile as the
|
|
warranty/backups panels. Panels hide themselves when their endpoint
|
|
returns nothing.
|
|
"""
|
|
return [
|
|
{
|
|
'id': 'endpoints-status',
|
|
'title': 'Endpoint status',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/status',
|
|
'render': 'keyvalue',
|
|
'empty': 'No agent report yet.',
|
|
'position': 10,
|
|
},
|
|
{
|
|
'id': 'endpoints-tracked-services',
|
|
'title': 'Tracked Services',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/services',
|
|
'render': 'list',
|
|
'collapsible': True,
|
|
'filter': {'key': 'kind', 'equals': 'service'},
|
|
# Facet on the STATE, not the status colour. statecolor is only
|
|
# ever green, red or grey here, so chips derived from it would
|
|
# read "OK" and "Critical" - not how anybody talks about a
|
|
# service. statelabel carries the real vocabulary: Running,
|
|
# Stopped, Paused, and the Windows transitional states. Any
|
|
# value not listed still gets a chip, appended after these.
|
|
'facets': {
|
|
'key': 'statelabel',
|
|
'order': ['Running', 'Stopped', 'Paused', 'Start Pending',
|
|
'Stop Pending', 'Continue Pending', 'Pause Pending',
|
|
'Unknown'],
|
|
},
|
|
'status': {
|
|
'key': 'statecolor',
|
|
'levels': {
|
|
'green': 'ok',
|
|
'yellow': 'warning',
|
|
'red': 'critical',
|
|
},
|
|
},
|
|
'map': {
|
|
'title': 'name',
|
|
'badge': {'label': 'statelabel', 'color': 'statecolor'},
|
|
'action': 'action',
|
|
},
|
|
'commandendpoint': '/api/endpoints/{assetid}/commands',
|
|
'permission': 'endpoints.command',
|
|
'empty': 'No monitored services reported.',
|
|
'position': 12,
|
|
# Service state is what is being watched; the Start/Stop
|
|
# controls belong beside it, not in a tab of their own.
|
|
# Lives in serviceprocess rather than monitors: that tab is the
|
|
# box's own health, this is what runs on it.
|
|
'group': 'serviceprocess',
|
|
},
|
|
{
|
|
'id': 'endpoints-tracked-processes',
|
|
'title': 'Tracked Processes',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/services',
|
|
'render': 'list',
|
|
'collapsible': True,
|
|
'filter': {'key': 'kind', 'equals': 'process'},
|
|
# Facet on the STATE, not the status colour. statecolor is only
|
|
# ever green, red or grey here, so chips derived from it would
|
|
# read "OK" and "Critical" - not how anybody talks about a
|
|
# service. statelabel carries the real vocabulary: Running,
|
|
# Stopped, Paused, and the Windows transitional states. Any
|
|
# value not listed still gets a chip, appended after these.
|
|
'facets': {
|
|
'key': 'statelabel',
|
|
'order': ['Running', 'Stopped', 'Paused', 'Start Pending',
|
|
'Stop Pending', 'Continue Pending', 'Pause Pending',
|
|
'Unknown'],
|
|
},
|
|
'status': {
|
|
'key': 'statecolor',
|
|
'levels': {
|
|
'green': 'ok',
|
|
'yellow': 'warning',
|
|
'red': 'critical',
|
|
},
|
|
},
|
|
'map': {
|
|
'title': 'name',
|
|
'badge': {'label': 'statelabel', 'color': 'statecolor'},
|
|
'action': 'action',
|
|
},
|
|
'commandendpoint': '/api/endpoints/{assetid}/commands',
|
|
'permission': 'endpoints.command',
|
|
'empty': 'No monitored processes reported.',
|
|
'position': 13,
|
|
# observed process state, not something you act on here
|
|
'group': 'serviceprocess',
|
|
},
|
|
{
|
|
# One feed instead of two cards. Events and commands answer the
|
|
# same question - what happened to this box - and reading them
|
|
# separately meant interleaving two lists by eye. Sits high on
|
|
# the page because it is the first thing looked at when
|
|
# something has gone wrong, and NOT collapsed by default for
|
|
# the same reason.
|
|
'id': 'endpoints-activity',
|
|
'title': 'Activity',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/activity',
|
|
'render': 'list',
|
|
'collapsible': True,
|
|
'status': {
|
|
'key': 'severity',
|
|
'levels': {
|
|
'info': 'ok',
|
|
'warning': 'warning',
|
|
'critical': 'critical',
|
|
},
|
|
},
|
|
'map': {
|
|
'title': 'title',
|
|
'badge': {
|
|
'label': 'severity',
|
|
# The renderer reads the colour from a row field; with
|
|
# no colour declared every badge renders grey, which is
|
|
# what the feed spent its first version doing.
|
|
'color': 'severitycolor',
|
|
'labelmap': {
|
|
'critical': 'Critical',
|
|
'warning': 'Warning',
|
|
'info': 'Info',
|
|
},
|
|
},
|
|
'meta': [
|
|
{'key': 'detail'},
|
|
{'key': 'eventtime', 'label': 'At', 'format': 'date'},
|
|
],
|
|
# Expands in place on click. The message body is several
|
|
# hundred words of Windows boilerplate around the one or
|
|
# two lines that matter, so it stays collapsed until asked
|
|
# for rather than pushing every other row off the card.
|
|
'body': 'body',
|
|
},
|
|
'empty': 'Nothing recorded for this endpoint yet.',
|
|
'position': 20,
|
|
# the event and command feed IS the activity tab
|
|
'group': 'activity',
|
|
},
|
|
{
|
|
'id': 'endpoints-interfaces',
|
|
'title': 'Network interfaces',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/interfaces',
|
|
'render': 'table',
|
|
'collapsible': True,
|
|
'columns': [
|
|
{'key': 'alias', 'label': 'Adapter'},
|
|
{'key': 'ipv4', 'label': 'IPv4'},
|
|
{'key': 'mac', 'label': 'MAC'},
|
|
{'key': 'gateway', 'label': 'Gateway'},
|
|
{'key': 'subnet', 'label': 'Subnet'},
|
|
{'key': 'dhcp', 'label': 'Assignment'},
|
|
{'key': 'role', 'label': 'Role'},
|
|
{'key': 'link', 'label': 'Link'},
|
|
],
|
|
'empty': 'No network interfaces reported.',
|
|
'position': 16,
|
|
# adapter state is watched, not something you act on
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
# Installed-software (SBOM) inventory. Raw discovered list for
|
|
# now: no managed-application linkage is surfaced yet.
|
|
#
|
|
# NOT collapsible. It used to be, and started collapsed, because
|
|
# it was low-priority reference data sitting near the bottom of
|
|
# one long page. It is now the Software tab's whole reason to
|
|
# exist, and somebody who clicked that tab has already said what
|
|
# they came for - making them click again to see it is a step
|
|
# that asks a question already answered.
|
|
'id': 'endpoints-applications',
|
|
'title': 'Installed software',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/applications',
|
|
'render': 'table',
|
|
'columns': [
|
|
{'key': 'displayname', 'label': 'Name'},
|
|
{'key': 'displayversion', 'label': 'Version'},
|
|
{'key': 'publisher', 'label': 'Publisher'},
|
|
],
|
|
'empty': 'No installed software reported.',
|
|
'position': 30,
|
|
# the installed-software inventory
|
|
'group': 'software',
|
|
},
|
|
{
|
|
'id': 'endpoints-hardware',
|
|
'title': 'Hardware',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/hardware',
|
|
'render': 'keyvalue',
|
|
'collapsible': True,
|
|
'empty': 'No hardware inventory reported.',
|
|
'position': 14,
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
'id': 'endpoints-osinfo',
|
|
'title': 'Operating system',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/osinfo',
|
|
'render': 'keyvalue',
|
|
'collapsible': True,
|
|
'empty': 'No OS inventory reported.',
|
|
'position': 15,
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
'id': 'endpoints-storage',
|
|
'title': 'Storage',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/storage',
|
|
'render': 'table',
|
|
'collapsible': True,
|
|
'columns': [
|
|
{'key': 'drive', 'label': 'Drive'},
|
|
{'key': 'label', 'label': 'Label'},
|
|
{'key': 'filesystem', 'label': 'Filesystem'},
|
|
{'key': 'size', 'label': 'Size'},
|
|
{'key': 'free', 'label': 'Free'},
|
|
{'key': 'freepercent', 'label': 'Free %'},
|
|
],
|
|
'empty': 'No disks reported.',
|
|
'position': 17,
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
# Sits directly under Storage because an operator looking at a
|
|
# full disk and an operator looking at a dying disk are usually
|
|
# the same person in the same minute. Kept a separate panel
|
|
# because storage is per volume and this is per physical
|
|
# device; the two do not share a key.
|
|
'id': 'endpoints-diskhealth',
|
|
'title': 'Disk health',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/diskhealth',
|
|
'render': 'table',
|
|
'collapsible': True,
|
|
'columns': [
|
|
{'key': 'model', 'label': 'Drive'},
|
|
{'key': 'mediatype', 'label': 'Media'},
|
|
{'key': 'bustype', 'label': 'Bus'},
|
|
{'key': 'healthstatus', 'label': 'Health'},
|
|
{'key': 'verdict', 'label': 'Verdict'},
|
|
{'key': 'source', 'label': 'Source'},
|
|
],
|
|
'empty': 'No disk health reported.',
|
|
'position': 18,
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
# The listening set is the box's exposed network surface. The
|
|
# full connection table is deliberately not here: it is an
|
|
# on-demand command, because a per-cycle capture of every
|
|
# connection is a lot of rows nobody reads.
|
|
'id': 'endpoints-listeners',
|
|
'title': 'Listening ports',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/listeners',
|
|
'render': 'table',
|
|
'collapsible': True,
|
|
'columns': [
|
|
{'key': 'localport', 'label': 'Port'},
|
|
{'key': 'protocol', 'label': 'Protocol'},
|
|
{'key': 'localaddress', 'label': 'Address'},
|
|
{'key': 'processname', 'label': 'Process'},
|
|
{'key': 'processid', 'label': 'PID'},
|
|
],
|
|
'empty': 'No listening ports reported.',
|
|
'position': 19,
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
# Session-scoped data collected by a probe in the interactive
|
|
# user's session, so it is absent whenever nobody is signed in.
|
|
# Last on the page: it is the least reliably present card, and
|
|
# an empty one at the bottom reads as "not reported" rather
|
|
# than pushing the populated cards down.
|
|
'id': 'endpoints-usercontext',
|
|
'title': 'User context',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/asset/{assetid}/usercontext',
|
|
'render': 'keyvalue',
|
|
'collapsible': True,
|
|
'empty': 'No user session data reported.',
|
|
'position': 40,
|
|
'group': 'monitors',
|
|
},
|
|
{
|
|
# Operator-submitted issue reports: a free-text note and an
|
|
# optional screenshot the operator captured from the tray. Sits
|
|
# in the Monitors tab beside the other watch-and-observe panels.
|
|
# A custom render carries the thumbnail grid and the expanding
|
|
# lightbox with left/right cycling the generic modes cannot.
|
|
'id': 'endpoints-operator-reports',
|
|
'title': 'Operator Reports',
|
|
'assettypes': ['computer'],
|
|
'endpoint': '/api/endpoints/panel/{assetid}/operatorreports',
|
|
'render': 'operatorreports',
|
|
'imagebase': '/api/endpoints/operatorreports',
|
|
'collapsible': True,
|
|
'empty': 'No operator reports for this endpoint.',
|
|
'position': 18,
|
|
'group': 'monitors',
|
|
},
|
|
]
|
|
|
|
def get_dashboard_widgets(self) -> List[Dict]:
|
|
"""Fleet-wide exception cards. Run once on dashboard load, not per PC.
|
|
|
|
Both cards hide when empty and cap their rows, so a healthy fleet adds
|
|
nothing to the dashboard and an unhealthy one adds a bounded list.
|
|
"""
|
|
return [
|
|
{
|
|
'id': 'endpoints-quiet',
|
|
'viewall': '/pcs',
|
|
'title': 'Endpoints gone quiet',
|
|
'shortname': 'Agent quiet',
|
|
'endpoint': '/api/endpoints/dashboard/quiet',
|
|
'render': 'exceptions',
|
|
'severity': 'warning',
|
|
'permission': 'endpoints.fleet',
|
|
'empty': 'hide',
|
|
'position': 22,
|
|
'map': {
|
|
'title': 'hostname',
|
|
'detail': '',
|
|
'meta': [{'key': 'quietdays', 'label': 'silent',
|
|
'suffix': ' days'}],
|
|
'link': '/pcs/{computerid}',
|
|
},
|
|
},
|
|
{
|
|
'id': 'endpoints-stability',
|
|
'viewall': '/pcs',
|
|
'title': 'Endpoints with crashes or shutdowns',
|
|
'shortname': 'Crashes',
|
|
'endpoint': '/api/endpoints/dashboard/stability',
|
|
'render': 'exceptions',
|
|
'severity': 'critical',
|
|
'permission': 'endpoints.fleet',
|
|
'empty': 'hide',
|
|
'position': 16,
|
|
'map': {
|
|
'title': 'hostname',
|
|
'detail': '',
|
|
'meta': [{'key': 'eventcount', 'suffix': ' events (48h)'}],
|
|
'link': '/pcs/{computerid}',
|
|
},
|
|
},
|
|
]
|
|
|
|
# ---- ADR-006 collector contract -------------------------------------
|
|
|
|
def get_collector_schema(self) -> Optional[Dict]:
|
|
return {
|
|
'identityfield': 'hostname',
|
|
'fields': {
|
|
'type': 'object',
|
|
'required': ['hostname'],
|
|
'properties': {
|
|
'hostname': {
|
|
'type': 'string',
|
|
'description': 'Endpoint hostname. Resolved against '
|
|
'the computers plugin (computers.hostname).',
|
|
},
|
|
'adopt': {
|
|
'type': 'boolean',
|
|
'description': 'First-contact only. When true and the '
|
|
'hostname does not resolve, adoption is '
|
|
'delegated to the computers collector '
|
|
'(see DESIGN-DECISIONS-agent.md 1a). This '
|
|
'plugin never creates assets itself.',
|
|
},
|
|
'loggedinuser': {'type': 'string'},
|
|
'agentversion': {'type': 'string'},
|
|
'trayversion': {'type': 'string'},
|
|
'lastboottime': {'type': 'string', 'format': 'date-time'},
|
|
'uptimeseconds': {'type': 'integer'},
|
|
'idleseconds': {'type': 'integer'},
|
|
'cpupercent': {'type': 'number'},
|
|
'memorypercent': {'type': 'number'},
|
|
'services': {
|
|
'type': 'array',
|
|
'description': 'Monitored services/processes and their '
|
|
'run state (UDC, eDnc, Intune, ...).',
|
|
},
|
|
'ports': {
|
|
'type': 'array',
|
|
'description': 'Open listening ports.',
|
|
},
|
|
'interfaces': {
|
|
'type': 'array',
|
|
'description': 'Network interface information.',
|
|
},
|
|
'scheduledtasks': {
|
|
'type': 'array',
|
|
'description': 'Scheduled task inventory + last run.',
|
|
},
|
|
'disks': {
|
|
'type': 'array',
|
|
'description': 'Fixed local disks: {drive, label, '
|
|
'filesystem, sizebytes, freebytes, '
|
|
'usedbytes, freepercent}. Newest '
|
|
'snapshot, replaced on every report.',
|
|
},
|
|
'bios': {
|
|
'type': 'object',
|
|
'description': 'Firmware identity: vendor, version, '
|
|
'release date.',
|
|
},
|
|
'memory': {
|
|
'type': 'object',
|
|
'description': 'Physical memory totals in bytes.',
|
|
},
|
|
'processor': {
|
|
'type': 'object',
|
|
'description': 'CPU identity, core and logical '
|
|
'processor counts, max clock.',
|
|
},
|
|
'osinfo': {
|
|
'type': 'object',
|
|
'description': 'OS build, version, and install date.',
|
|
},
|
|
'domain': {
|
|
'type': 'string',
|
|
'description': 'Windows domain or workgroup membership.',
|
|
},
|
|
'pendingreboot': {
|
|
'type': 'boolean',
|
|
'description': 'True when the endpoint is holding a '
|
|
'reboot. Absent means never reported, '
|
|
'which is not the same as false.',
|
|
},
|
|
'diskhealth': {
|
|
'type': 'array',
|
|
'description': 'Per-drive health from two sources: '
|
|
'physicaldisk (the only one reporting '
|
|
'NVMe) and diskdrive (ATA/SATA and '
|
|
'fallback). Each entry carries a '
|
|
'precomputed predictfailure; null there '
|
|
'means the drive did not answer.',
|
|
},
|
|
'rebootreasons': {
|
|
'type': 'array',
|
|
'description': 'Which signal(s) drove pendingreboot: '
|
|
'componentbasedservicing, windowsupdate, '
|
|
'pendingfilerename. Empty array means '
|
|
'checked and nothing pending; omit when '
|
|
'the check failed.',
|
|
},
|
|
'bootinfo': {
|
|
'type': 'object',
|
|
'description': 'hiberbootenabled (fast startup is '
|
|
'configured) and lastboottype (what the '
|
|
'last boot actually did). Uptime is not '
|
|
'trustworthy when fast startup is in '
|
|
'play.',
|
|
},
|
|
'defender': {
|
|
'type': 'object',
|
|
'description': 'Defender service/realtime state and '
|
|
'signature and scan ages in days. '
|
|
'Persisted but not surfaced.',
|
|
},
|
|
'usercontext': {
|
|
'type': 'object',
|
|
'description': 'Session-scoped data collected by a probe '
|
|
'running as the signed-in user: mapped '
|
|
'drives (netuse), user-owned listeners, '
|
|
'and idle seconds. Absent when nobody is '
|
|
'signed in.',
|
|
},
|
|
'applications': {
|
|
'type': 'array',
|
|
'description': 'Installed-software SBOM from both '
|
|
'Windows Uninstall registry hives. Each '
|
|
'item is {displayname, displayversion, '
|
|
'publisher}, de-duped on name+version. '
|
|
'Stored as a per-asset snapshot, '
|
|
'replaced on every report.',
|
|
'items': {
|
|
'type': 'object',
|
|
'required': ['displayname'],
|
|
'properties': {
|
|
'displayname': {'type': 'string'},
|
|
'displayversion': {'type': 'string'},
|
|
'publisher': {'type': 'string'},
|
|
},
|
|
},
|
|
},
|
|
'events': {
|
|
'type': 'array',
|
|
'description': 'Curated Windows Event Log records. Only '
|
|
'IDs in the server catalog are stored.',
|
|
'items': {
|
|
'type': 'object',
|
|
'required': ['eventid'],
|
|
'properties': {
|
|
'eventid': {'type': 'integer'},
|
|
'eventrecordid': {
|
|
'type': 'integer',
|
|
'description': 'Windows event record id; '
|
|
'unique per channel per '
|
|
'machine, used to dedup.',
|
|
},
|
|
'eventchannel': {'type': 'string'},
|
|
'eventsource': {'type': 'string'},
|
|
'eventtime': {'type': 'string',
|
|
'format': 'date-time'},
|
|
'eventmessage': {'type': 'string'},
|
|
'fields': {'type': 'object'},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
# PC-identifying and hardware fields forwarded to the computers collector,
|
|
# which owns the Asset/Computer row and renders the Hardware and Network
|
|
# cards. The endpoints plugin only caches telemetry, so these must be
|
|
# relayed or vendor/model/OS/IP never land on the PC (see
|
|
# DESIGN-DECISIONS-agent.md 1a).
|
|
_COMPUTER_HANDOFF_FIELDS = (
|
|
'loggedinuser', 'serialnumber', 'pctype', 'machinenumber',
|
|
'vendorname', 'modelnumber', 'osname', 'ipaddress', 'lastboottime',
|
|
)
|
|
|
|
def _forward_to_computers(self, hostname: str, payload: Dict):
|
|
"""Return the computers plugin and the PC subset to hand off, or None.
|
|
|
|
Both adoption and steady-state reports relay the same hardware subset,
|
|
so the Hardware and Network cards fill in on every report, not just at
|
|
first contact.
|
|
"""
|
|
from flask import current_app
|
|
|
|
manager = current_app.extensions.get('plugin_manager')
|
|
computers = manager.get_plugin('computers') if manager else None
|
|
if computers is None:
|
|
return None, None
|
|
|
|
subset = {'hostname': hostname}
|
|
for field in self._COMPUTER_HANDOFF_FIELDS:
|
|
if payload.get(field):
|
|
subset[field] = payload.get(field)
|
|
return computers, subset
|
|
|
|
def _adopt_computer(self, hostname: str, payload: Dict,
|
|
warnings: List[str]) -> None:
|
|
"""Delegate first-contact adoption to the computers collector.
|
|
|
|
This plugin never creates Asset or Computer rows itself (see
|
|
DESIGN-DECISIONS-agent.md 1a). The computers plugin is the sole
|
|
authority for that, so on an unknown hostname we forward the
|
|
PC-identifying subset of the payload to its collector. It runs inside
|
|
the same transaction, so a later failure rolls the adoption back.
|
|
"""
|
|
computers, adoptpayload = self._forward_to_computers(hostname, payload)
|
|
if computers is None:
|
|
raise ValueError(
|
|
'cannot adopt {!r}: computers plugin is not available'
|
|
.format(hostname))
|
|
|
|
computers.apply_collector_payload(adoptpayload)
|
|
db.session.flush()
|
|
warnings.append('adopted new computer for hostname: {!r}'.format(hostname))
|
|
|
|
def _replace_applications(self, assetid: int, applications,
|
|
warnings: List[str]) -> int:
|
|
"""Replace an asset's SBOM snapshot with the reported set.
|
|
|
|
The agent reports the full installed-software list each cycle, so the
|
|
current inventory is the newest report, not an accumulation. Delete the
|
|
asset's existing rows and insert the reported ones in the same
|
|
transaction the caller flushes. appid is left null: no
|
|
discovery-to-catalog ("Managed Applications") matcher is wired yet.
|
|
Malformed items (no displayname) are skipped, not fatal.
|
|
"""
|
|
EndpointApplication.query.filter_by(assetid=assetid).delete(
|
|
synchronize_session=False)
|
|
|
|
if not applications:
|
|
return 0
|
|
|
|
stored = 0
|
|
for item in applications:
|
|
if not isinstance(item, dict):
|
|
warnings.append('skipped non-object application entry')
|
|
continue
|
|
displayname = (item.get('displayname') or '').strip()
|
|
if not displayname:
|
|
warnings.append('skipped application with no displayname')
|
|
continue
|
|
# TRUNCATE EVERY STRING, not just the name. On MySQL in strict
|
|
# mode an over-long value raises Data too long and takes down the
|
|
# WHOLE check-in transaction, so one machine with a malformed
|
|
# Uninstall registry entry stops reporting entirely - telemetry,
|
|
# events and all - until somebody uninstalls the offender. SQLite
|
|
# does not enforce declared lengths, so no test here would ever see
|
|
# it. displayname was already clamped; these two were not.
|
|
db.session.add(EndpointApplication(
|
|
assetid=assetid,
|
|
displayname=displayname[:255],
|
|
displayversion=_clamp(item.get('displayversion'), 128),
|
|
publisher=_clamp(item.get('publisher'), 255),
|
|
))
|
|
stored += 1
|
|
return stored
|
|
|
|
def apply_collector_payload(self, payload: Dict) -> Dict:
|
|
"""Idempotently upsert one endpoint's state and append its events.
|
|
|
|
The cached EndpointState and any EndpointEvent rows are written in the
|
|
same transaction (the dispatcher owns the commit), so a reader never
|
|
sees a snapshot without the events that produced it.
|
|
"""
|
|
from plugins.computers.models import Computer
|
|
|
|
warnings: List[str] = []
|
|
|
|
hostname = (payload.get('hostname') or '').strip()
|
|
if not hostname:
|
|
raise ValueError('hostname is required')
|
|
|
|
computer = (Computer.query
|
|
.filter(db.func.lower(Computer.hostname) == hostname.lower())
|
|
.first())
|
|
if computer is None:
|
|
# First-contact adoption is delegated to the computers collector,
|
|
# which is the only authority allowed to create Asset + Computer
|
|
# rows (DESIGN-DECISIONS-agent.md 1a). This plugin never invents
|
|
# assets itself. Adoption runs in the dispatcher's transaction, so a
|
|
# later ValueError rolls the whole report back.
|
|
if payload.get('adopt'):
|
|
self._adopt_computer(hostname, payload, warnings)
|
|
computer = (Computer.query
|
|
.filter(db.func.lower(Computer.hostname)
|
|
== hostname.lower())
|
|
.first())
|
|
if computer is None:
|
|
raise ValueError(
|
|
'could not resolve hostname to a computer: {!r}'.format(hostname))
|
|
else:
|
|
# Already adopted: relay the hardware/identity subset on every
|
|
# report so the computers plugin keeps vendor/model/OS/IP current.
|
|
# Without this, Hardware and Network stay blank after adoption
|
|
# because this plugin only caches telemetry.
|
|
computers, subset = self._forward_to_computers(hostname, payload)
|
|
if computers is not None and len(subset) > 1:
|
|
computers.apply_collector_payload(subset)
|
|
db.session.flush()
|
|
|
|
assetid = computer.assetid
|
|
|
|
state = EndpointState.query.filter_by(assetid=assetid).first()
|
|
action = 'updated'
|
|
if state is None:
|
|
state = EndpointState(assetid=assetid)
|
|
db.session.add(state)
|
|
action = 'created'
|
|
|
|
state.hostname = hostname
|
|
if 'loggedinuser' in payload:
|
|
state.loggedinuser = payload.get('loggedinuser')
|
|
if 'agentversion' in payload:
|
|
state.agentversion = payload.get('agentversion')
|
|
if 'trayversion' in payload:
|
|
state.trayversion = payload.get('trayversion')
|
|
if 'lastboottime' in payload:
|
|
state.lastboottime = _parse_dt(payload.get('lastboottime'))
|
|
if 'uptimeseconds' in payload:
|
|
state.uptimeseconds = payload.get('uptimeseconds')
|
|
if 'idleseconds' in payload:
|
|
state.idleseconds = payload.get('idleseconds')
|
|
if 'cpupercent' in payload:
|
|
state.cpupercent = payload.get('cpupercent')
|
|
if 'memorypercent' in payload:
|
|
state.memorypercent = payload.get('memorypercent')
|
|
if 'services' in payload:
|
|
state.servicesjson = _as_json(payload.get('services'))
|
|
if 'ports' in payload:
|
|
state.portsjson = _as_json(payload.get('ports'))
|
|
if 'interfaces' in payload:
|
|
state.interfacesjson = _as_json(payload.get('interfaces'))
|
|
if 'scheduledtasks' in payload:
|
|
state.scheduledtasksjson = _as_json(payload.get('scheduledtasks'))
|
|
|
|
# Hardware/OS inventory. Same presence guard as above: a report that
|
|
# omits a key must not wipe the last-known value. These change rarely
|
|
# (a RAM upgrade, a BIOS flash), so a transient collection failure on
|
|
# one cycle should leave the previous snapshot standing rather than
|
|
# blank the asset record.
|
|
if 'disks' in payload:
|
|
state.disksjson = _as_json(payload.get('disks'))
|
|
if 'bios' in payload:
|
|
state.biosjson = _as_json(payload.get('bios'))
|
|
if 'memory' in payload:
|
|
state.memoryjson = _as_json(payload.get('memory'))
|
|
if 'processor' in payload:
|
|
state.processorjson = _as_json(payload.get('processor'))
|
|
if 'osinfo' in payload:
|
|
state.osinfojson = _as_json(payload.get('osinfo'))
|
|
if 'domain' in payload:
|
|
state.domain = payload.get('domain')
|
|
if 'pendingreboot' in payload:
|
|
state.pendingreboot = payload.get('pendingreboot')
|
|
if 'diskhealth' in payload:
|
|
state.diskhealthjson = _as_json(payload.get('diskhealth'))
|
|
if 'rebootreasons' in payload:
|
|
state.rebootreasonsjson = _as_json(payload.get('rebootreasons'))
|
|
if 'bootinfo' in payload:
|
|
state.bootinfojson = _as_json(payload.get('bootinfo'))
|
|
if 'defender' in payload:
|
|
state.defenderjson = _as_json(payload.get('defender'))
|
|
|
|
# Session-scoped probe output. The agent repeats its last result between
|
|
# probe runs and omits the key entirely when nobody is signed in, so the
|
|
# presence guard preserves the last known mapped drives across an
|
|
# unattended period instead of flapping the field to null.
|
|
if 'usercontext' in payload:
|
|
state.usercontextjson = _as_json(payload.get('usercontext'))
|
|
|
|
# Installed-software SBOM: stored as a per-asset SNAPSHOT in its own
|
|
# table (endpointapplications), not a JSON blob on the state, so it can
|
|
# later join the applications catalog ("Managed Applications"). Only
|
|
# replace when the key is present: a report that omits applications must
|
|
# not wipe the last-known inventory. The delete + re-insert happens in
|
|
# this same transaction (the dispatcher owns the commit), so a reader
|
|
# never sees a half-written list. displayname is required; malformed
|
|
# rows are skipped rather than failing the whole report.
|
|
if 'applications' in payload:
|
|
self._replace_applications(assetid, payload.get('applications'),
|
|
warnings)
|
|
|
|
state.lastreportedat = datetime.utcnow()
|
|
|
|
# Warn-only reconciler: on this check-in, compare the monitors site
|
|
# policy expects to be running against what the snapshot reports, and
|
|
# cache the drift on the state in THIS transaction (same ledger commit as
|
|
# servicesjson). No start/stop is issued - drift is surfaced for an
|
|
# operator to act on. Reads the freshly reported services when present,
|
|
# else the last-known snapshot, so a report that omits services still
|
|
# reconciles against what we last saw. Fail-open: a reconciler error must
|
|
# never fail an otherwise-good check-in, so drift is left unchanged.
|
|
try:
|
|
if 'services' in payload:
|
|
reported_services = payload.get('services') or []
|
|
else:
|
|
reported_services = json.loads(state.servicesjson or '[]')
|
|
from .services.reconciler import compute_drift
|
|
state.driftjson = _as_json(compute_drift(assetid, reported_services))
|
|
except Exception:
|
|
logger.exception(
|
|
'reconciler failed for asset %s; leaving drift unchanged',
|
|
assetid)
|
|
|
|
# Log any keys the agent sent that the ingest path does not consume yet.
|
|
# New agent telemetry (disks, bios, memory, ...) lands here first: it is
|
|
# not persisted until the server grows columns for it, but logging the
|
|
# keys and a compact preview makes incoming telemetry visible in the
|
|
# logs so we can confirm the agent is sending it before wiring the UI.
|
|
unknown_keys = [key for key in payload if key not in KNOWN_PAYLOAD_KEYS]
|
|
if unknown_keys:
|
|
preview = {key: payload.get(key) for key in sorted(unknown_keys)}
|
|
try:
|
|
preview_text = json.dumps(preview, default=str)[:2000]
|
|
except (TypeError, ValueError):
|
|
preview_text = repr(preview)[:2000]
|
|
logger.info(
|
|
'endpoint %s sent %d unpersisted telemetry key(s): %s | preview=%s',
|
|
hostname, len(unknown_keys), sorted(unknown_keys), preview_text)
|
|
|
|
stored_events = 0
|
|
skipped_events = 0
|
|
|
|
# Records the agent already sent must not be appended a second time.
|
|
# The agent carries a per-channel watermark so the steady state is
|
|
# "only what is new", but a reinstalled agent, a restored image, or two
|
|
# overlapping reports can all replay records. Resolve that here rather
|
|
# than relying on the unique index to raise, because an IntegrityError
|
|
# would abort the whole collector transaction and lose the state upsert
|
|
# along with it.
|
|
#
|
|
# One query for the whole batch, not one per record: a seeding agent
|
|
# sends up to the per-channel cap at once.
|
|
candidates = []
|
|
for record in (payload.get('events') or []):
|
|
try:
|
|
eventid = int(record.get('eventid'))
|
|
except (TypeError, ValueError):
|
|
warnings.append('skipped event with non-integer eventid')
|
|
continue
|
|
if eventid not in CURATED_EVENT_IDS:
|
|
# Outside the catalog: ignored on purpose, not an error.
|
|
continue
|
|
|
|
try:
|
|
eventrecordid = record.get('eventrecordid')
|
|
eventrecordid = (int(eventrecordid)
|
|
if eventrecordid is not None else None)
|
|
except (TypeError, ValueError):
|
|
eventrecordid = None
|
|
|
|
candidates.append((eventid, eventrecordid, record))
|
|
|
|
keyed = [(record.get('eventchannel'), eventrecordid)
|
|
for _e, eventrecordid, record in candidates
|
|
if eventrecordid is not None]
|
|
already_stored = set()
|
|
if keyed:
|
|
rows = (db.session.query(EndpointEvent.eventchannel,
|
|
EndpointEvent.eventrecordid)
|
|
.filter(EndpointEvent.assetid == assetid,
|
|
EndpointEvent.eventrecordid.in_(
|
|
[recordid for _c, recordid in keyed]))
|
|
.all())
|
|
already_stored = {(channel, recordid) for channel, recordid in rows}
|
|
|
|
for eventid, eventrecordid, record in candidates:
|
|
eventchannel = record.get('eventchannel')
|
|
if eventrecordid is not None:
|
|
key = (eventchannel, eventrecordid)
|
|
if key in already_stored:
|
|
skipped_events += 1
|
|
continue
|
|
# Guard against the same record appearing twice inside one
|
|
# payload as well as against rows already in the table.
|
|
already_stored.add(key)
|
|
|
|
db.session.add(EndpointEvent(
|
|
assetid=assetid,
|
|
eventid=eventid,
|
|
eventrecordid=eventrecordid,
|
|
eventchannel=eventchannel,
|
|
eventsource=record.get('eventsource'),
|
|
eventtime=_parse_dt(record.get('eventtime')),
|
|
eventmessage=record.get('eventmessage'),
|
|
payloadjson=_as_json(record.get('fields')),
|
|
))
|
|
stored_events += 1
|
|
|
|
if skipped_events:
|
|
logger.debug(
|
|
'endpoint %s replayed %d already-stored event record(s)',
|
|
hostname, skipped_events)
|
|
|
|
# flush, not commit: the collector dispatcher owns the transaction.
|
|
db.session.flush()
|
|
|
|
return {
|
|
'action': action,
|
|
'assetid': assetid,
|
|
'identityvalue': hostname,
|
|
'storedevents': stored_events,
|
|
'warnings': warnings,
|
|
} |