add operator issue reports for endpoint agent

Operators had no way to flag a problem PC from the tray. This adds a report path: the tray captures a reason, free-text note, and optional screenshot and the agent uploads it on the collector token to a new operatorreports table linked to the asset. Ships the endpoints 0009 migration so the table exists before the code queries it; the running DB had drifted behind the code and returned HTTP 500 on upload.
This commit is contained in:
benjamin.baker
2026-09-01 19:39:32 -04:00
parent 8cc8b0c9b2
commit ab4b9d7ec9
24 changed files with 1596 additions and 51 deletions

View File

@@ -25,7 +25,10 @@ from shopdb.api import (
Application, AppVersion, Script,
)
from ..models import EndpointState, EndpointEvent, EndpointCommand, EndpointApplication
from ..models import (
EndpointState, EndpointEvent, EndpointCommand, EndpointApplication,
OperatorReport,
)
from ..commands import COMMAND_ALLOWLIST, is_allowed_action, ALLOWED_ACTIONS_FOR, row_actions_for, requires_target, action_targetkind, elevated_permission_for
from ..eventcatalog import CRITICAL_EVENT_IDS, event_severity, event_title
@@ -1766,3 +1769,174 @@ def download_script_body(script_id: int):
return send_upload(script_dir, script.filename, as_attachment=True)
# Operator issue reports (tray screenshot + free-text notes)
# ---------------------------------------------------------------------------
# Retention groundwork: how many days an operator report (and its screenshot
# file) is kept before the purge sweep removes it. Read from the Setting store
# so Agent Configuration can expose a toggle later without a code change; the
# default is 7 days. A value of 0 or less means "keep forever" (purge disabled).
OPERATOR_REPORT_RETENTION_SETTING = 'endpoints.operatorreport.retentiondays'
OPERATOR_REPORT_RETENTION_DEFAULT_DAYS = 7
# Screenshots are small PNGs from a virtual-screen grab. Cap the upload so a
# malformed or hostile agent cannot fill the disk with one request.
OPERATOR_REPORT_MAX_IMAGE_BYTES = 10 * 1024 * 1024
def _operator_report_dir():
return os.path.join(current_app.instance_path, 'operatorreports')
def _operator_report_retention_days():
"""Configured retention window in whole days (default 7, <=0 disables)."""
raw = Setting.get(OPERATOR_REPORT_RETENTION_SETTING)
if raw is None:
return OPERATOR_REPORT_RETENTION_DEFAULT_DAYS
try:
return int(raw)
except (TypeError, ValueError):
return OPERATOR_REPORT_RETENTION_DEFAULT_DAYS
def _purge_expired_operator_reports():
"""Delete operator reports older than the retention window, files and all.
Best-effort and idempotent: called opportunistically on upload so the feed
stays bounded without a scheduler. A retention of <=0 disables the sweep.
"""
days = _operator_report_retention_days()
if days <= 0:
return
cutoff = _naive_utcnow() - timedelta(days=days)
stale = OperatorReport.query.filter(OperatorReport.createdat < cutoff).all()
if not stale:
return
report_dir = _operator_report_dir()
for report in stale:
if report.imagefilename:
path = os.path.join(report_dir, report.imagefilename)
try:
os.remove(path)
except OSError:
pass
db.session.delete(report)
db.session.commit()
@endpoints_bp.route('/operatorreports', methods=['POST'])
def upload_operator_report():
"""Agent uploads one operator issue report (collector-token auth).
The tray captures the operator's free-text note and an optional screenshot,
then hands them to the service, which posts here as multipart/form-data on
the same endpoints collector token used for telemetry. The reported hostname
resolves to an asset; an unresolved hostname is a validation error. The
screenshot bytes are written to the operator-reports uploads dir and the row
holds only metadata plus the stored filename. One retention sweep runs
opportunistically so the feed stays bounded.
"""
from werkzeug.utils import secure_filename
import uuid
error = _collector_auth_or_error()
if error is not None:
return error
hostname = (request.form.get('hostname') or '').strip()
if not hostname:
return error_response(ErrorCodes.VALIDATION_ERROR,
'hostname is required')
asset_id = _resolve_asset_for_hostname(hostname)
if asset_id is None:
return error_response(
ErrorCodes.VALIDATION_ERROR,
'could not resolve hostname to a computer: {!r}'.format(hostname))
reason = (request.form.get('reason') or 'Other (free text)').strip()[:128]
details = (request.form.get('details') or '').strip() or None
imagefilename = None
imagemimetype = None
imagebytesize = None
upload = request.files.get('screenshot')
if upload is not None and upload.filename:
data = upload.read()
if len(data) > OPERATOR_REPORT_MAX_IMAGE_BYTES:
return error_response(
ErrorCodes.VALIDATION_ERROR,
'screenshot exceeds the {} byte limit'.format(
OPERATOR_REPORT_MAX_IMAGE_BYTES))
if data:
ext = os.path.splitext(secure_filename(upload.filename))[1].lower()
if ext != '.png':
ext = '.png'
imagefilename = 'report-{}{}'.format(uuid.uuid4().hex, ext)
imagemimetype = 'image/png'
imagebytesize = len(data)
report_dir = _operator_report_dir()
os.makedirs(report_dir, exist_ok=True)
with open(os.path.join(report_dir, imagefilename), 'wb') as handle:
handle.write(data)
report = OperatorReport(
assetid=asset_id,
reason=reason,
details=details,
imagefilename=imagefilename,
imagemimetype=imagemimetype,
imagebytesize=imagebytesize,
reportedhostname=hostname,
)
db.session.add(report)
db.session.commit()
# Keep the feed bounded without a scheduler. Best-effort: a purge failure
# must not fail the upload the operator already completed.
try:
_purge_expired_operator_reports()
except Exception:
db.session.rollback()
return success_response(report.to_dict(),
message='Operator report received', http_code=201)
@endpoints_bp.route('/panel/<int:asset_id>/operatorreports', methods=['GET'])
@require_permission('endpoints.view')
def panel_operator_reports(asset_id: int):
"""Operator Reports panel: this PC's recent operator issue reports.
Newest first. Each row carries a hasimage flag so the viewer knows whether
to request the screenshot from the serve route below. Runs a retention
sweep opportunistically so a viewed PC does not accumulate stale rows.
"""
try:
_purge_expired_operator_reports()
except Exception:
db.session.rollback()
reports = (OperatorReport.query
.filter_by(assetid=asset_id)
.order_by(OperatorReport.createdat.desc())
.all())
return success_response({'reports': [r.to_dict() for r in reports]})
@endpoints_bp.route('/operatorreports/<int:operatorreportid>/image',
methods=['GET'])
@require_permission('endpoints.view')
def serve_operator_report_image(operatorreportid: int):
"""Serve one operator report's screenshot (user JWT + endpoints.view)."""
from shopdb.api import send_upload
report = db.session.get(OperatorReport, operatorreportid)
if report is None or not report.imagefilename:
return error_response(ErrorCodes.NOT_FOUND,
'No screenshot for this report', http_code=404)
return send_upload(_operator_report_dir(), report.imagefilename)