Add dashboard-triggered replay jobs and detector deltas

Closes the last ROADMAP §1 item. The replay/replay-graylog CLI backend
already existed and was already safe (a temporary, auto-cleaned SQLite
baseline, never touching live state) — the gap was purely that a human had
to SSH in and run it by hand. Extracts the core logic from cli.py into
run_local_replay()/run_graylog_replay() in replay.py, reused by both the
CLI (now thin wrappers) and a new dashboard panel (Diagnostics -> Replay &
Detector Deltas). Runs as a background job via an in-memory job store,
since the dashboard already runs ThreadingHTTPServer and this session
directly observed live MCP polling take anywhere from 9 minutes to over an
hour — a synchronous request/response was never viable. Deliberately
serialized to one job at a time given this box's GPU/CPU constraints.

Also removed a redundant "Detector Precision" panel that duplicated (with
a weaker, current-poll-cycle-only computation) what the new Detector
Health panel already does correctly with real historical data.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
larssand
2026-09-24 18:39:54 +02:00
parent bc4d2f465f
commit 3e01ac977d
8 changed files with 474 additions and 156 deletions

View File

@@ -1,7 +1,10 @@
import json
import tempfile
import unittest
from pathlib import Path
from fgai.logs import parse_log_line
from fgai.replay import replay_comparison, replay_events
from fgai.replay import _configured_streams, replay_comparison, replay_events, run_graylog_replay, run_local_replay
from fgai.stream_profiles import parse_profiles
@@ -29,3 +32,87 @@ class ReplayTests(unittest.TestCase):
self.assertEqual(result["source_anomalies_delta"], 1)
self.assertEqual(result["detector_count_delta"]["auth_failure_burst"], -1)
self.assertEqual(result["detector_count_delta"]["rare_value"], 3)
def test_configured_streams_uses_enabled_streams_by_default(self):
config = {
"graylog_streams": [
{"id": "fortigate", "title": "Fortigate", "enabled": True},
{"id": "adguard", "title": "Adguard", "enabled": False},
]
}
self.assertEqual(_configured_streams(config), [{"id": "fortigate", "title": "Fortigate"}])
def test_configured_streams_can_select_disabled_stream(self):
config = {
"graylog_streams": [
{"id": "fortigate", "title": "Fortigate", "enabled": True},
{"id": "adguard", "title": "Adguard", "enabled": False},
]
}
self.assertEqual(_configured_streams(config, ["adguard"]), [{"id": "adguard", "title": "Adguard"}])
def test_configured_streams_preserves_selected_order(self):
config = {
"graylog_streams": [
{"id": "fortigate", "title": "Fortigate", "enabled": True},
{"id": "adguard", "title": "Adguard", "enabled": False},
]
}
self.assertEqual(
_configured_streams(config, ["adguard", "fortigate"]),
[{"id": "adguard", "title": "Adguard"}, {"id": "fortigate", "title": "Fortigate"}],
)
def test_run_local_replay_matches_replay_events_output(self):
with tempfile.TemporaryDirectory() as directory:
config_path = Path(directory) / "config.json"
config_path.write_text(json.dumps({"graylog_stream_profiles": [{"stream_id": "windows", "entity_field": "username", "categorical_fields": ["action"]}]}), encoding="utf-8")
logs_path = Path(directory) / "events.log"
lines = [
f"timestamp={1_700_000_000 + index * 300} username=alice action=failed event={index}"
for index in range(12)
]
lines.extend(f"timestamp={1_700_003_600} username=alice action=failed burst={index}" for index in range(5))
logs_path.write_text("\n".join(lines), encoding="utf-8")
result = run_local_replay(str(config_path), str(logs_path), stream_id="windows")
self.assertEqual(result["events"], 17)
self.assertGreaterEqual(result["field_detector_counts"].get("auth_failure_burst", 0), 1)
def test_run_local_replay_with_compare_config_reports_comparison(self):
with tempfile.TemporaryDirectory() as directory:
config_path = Path(directory) / "config.json"
config_path.write_text(json.dumps({"graylog_stream_profiles": [{"stream_id": "windows", "entity_field": "username", "categorical_fields": ["action"]}]}), encoding="utf-8")
candidate_path = Path(directory) / "candidate.json"
candidate_path.write_text(json.dumps({"graylog_stream_profiles": [{"stream_id": "windows", "entity_field": "username", "categorical_fields": []}]}), encoding="utf-8")
logs_path = Path(directory) / "events.log"
lines = [
f"timestamp={1_700_000_000 + index * 300} username=alice action=failed event={index}"
for index in range(12)
]
lines.extend(f"timestamp={1_700_003_600} username=alice action=failed burst={index}" for index in range(5))
logs_path.write_text("\n".join(lines), encoding="utf-8")
result = run_local_replay(str(config_path), str(logs_path), stream_id="windows", compare_config_file=str(candidate_path))
self.assertIn("comparison", result)
self.assertIn("current", result)
self.assertIn("candidate", result)
self.assertEqual(result["candidate_config_file"], str(candidate_path))
def test_run_graylog_replay_requires_mcp_configuration(self):
with tempfile.TemporaryDirectory() as directory:
config_path = Path(directory) / "config.json"
config_path.write_text(json.dumps({}), encoding="utf-8")
with self.assertRaises(RuntimeError):
run_graylog_replay(str(config_path))
def test_run_graylog_replay_requires_selected_streams(self):
with tempfile.TemporaryDirectory() as directory:
config_path = Path(directory) / "config.json"
config_path.write_text(json.dumps({"graylog_mcp_url": "https://graylog.example", "graylog_mcp_token": "token"}), encoding="utf-8")
with self.assertRaises(RuntimeError):
run_graylog_replay(str(config_path))