Files
frigate/frigate/test/test_analytics_schema.py
T
Josh HawkinsandGitHub 4eb60af5a7 Implement opt-in analytics (#24440)
* Add analytics opt-in setting, prompt notice kind, and notice watermarks

* Add the analytics report schema

* Add the analytics state file

* Add the install and hardware analytics collectors

* Add the detection analytics collector

* Add the cameras analytics collector

* Add the features analytics collector

* Add the health analytics collector

* Build analytics reports from the section collectors

* Add the analytics report transport

* Send the daily analytics report from the main process

* Add the analytics preview API

* Generate the analytics schema and check it in CI

* Record the image variant in each Dockerfile

* Show the analytics preview in telemetry settings

* Document anonymous analytics

* change wording

* fixes

* update network requirements docs

* adapt analytics to free-form model scenes, split notice counts, and peewee 4

* fixes

* change log levels

* docstrings

* docstrings

* honor file-only analytics opt-outs and skip pre-consent notices

An opt-out saved through the YAML editor's "Save only" or a hand edit never reached the live config, so reports kept going out under the old install ID until a restart. The reporter now reads telemetry.analytics from the config file when a report is due, validated with TelemetryConfig so yes, on, and 1 still count as consent, and an opt-out there deletes the state file and skips the send. The first report under a new install ID also carried every notice since the counters started, including ones from before the opt-in, so a fresh state file now resets the notice watermarks before the report's snapshot.

* take the notice baseline at opt-in instead of the first send

The watermark reset ran at the first send attempt, so notices raised between the opt-in and that send, up to 45 minutes after a startup, were absorbed into the reset and never reported. The reporter now writes the new install ID and resets the watermarks as soon as it sees consent without a state file.

* report notice counts cumulatively from a database baseline

Moving watermarks after each accepted send kept the install ID and the notice baseline out of step: pre-consent notices went out, notices raised before the first send were dropped, and a send that finished after an off/on toggle overwrote the new identity's baseline. health.notices now carries cumulative counts since the install ID was created. Creating an ID copies the lifetime counts into the existing reported_* columns before the state file names it, and nothing is written after a send, so the backend diffs consecutive reports per install ID.

* write held notice repeats before the analytics baseline reset

Repeats of batched kinds like failed_login wait in memory until the stats emitter flushes them, so a baseline reset taken while some were held left them out, and the next flush counted those pre-opt-in repeats as post-consent. The reset now writes held repeats to the notice history under the same lock before copying the counts.

* seed detector inference speed from the first inference

The average started at 0 so idle detectors read 0, but that made every detector's speed climb from 0 for its first couple dozen inferences after a start. Detectors now use the same InferenceSpeed helper as enrichments, so the first inference seeds the average and idle detectors still read 0.
2026-11-06 07:43:38 -07:00

138 lines
4.7 KiB
Python

"""Tests for the analytics report schema."""
import inspect
import re
import unittest
from enum import Enum
from typing import Any, get_args, get_origin
from pydantic import BaseModel
import frigate.detectors.hardware as detection_hardware
import frigate.util.hwaccel as hwaccel
from frigate.analytics.schema import (
AnalyticsReport,
DecodeFamily,
HardwareKey,
HwaccelKey,
InputPresetKey,
NoticeKindKey,
)
from frigate.ffmpeg_presets import PRESETS_HW_ACCEL_DECODE, PRESETS_INPUT
from frigate.notices.types import NOTICE_KINDS
from frigate.util.hwaccel import HwaccelFamily
# the only str fields: generated ids and strings the hardware reports
ALLOWED_STRINGS = {
("AnalyticsReport", "install_id"),
("AnalyticsReport", "report_id"),
("InstallSection", "version"),
("InstallSection", "kernel"),
("HardwareSection", "cpu_model"),
("GpuInfo", "name"),
("StorageInfo", "record_fs"),
("DetectionModel", "input"),
}
def nested_models(annotation: Any) -> list[type[BaseModel]]:
if isinstance(annotation, type) and issubclass(annotation, BaseModel):
return [annotation]
return [model for arg in get_args(annotation) for model in nested_models(arg)]
def all_models(
model: type[BaseModel], seen: set[type[BaseModel]] | None = None
) -> list[type[BaseModel]]:
seen = set() if seen is None else seen
if model in seen:
return []
seen.add(model)
found = [model]
for field in model.model_fields.values():
for nested in nested_models(field.annotation):
found += all_models(nested, seen)
return found
def dict_key_types(annotation: Any) -> list[Any]:
keys = [get_args(annotation)[0]] if get_origin(annotation) is dict else []
return keys + [key for arg in get_args(annotation) for key in dict_key_types(arg)]
class TestSchemaDiscipline(unittest.TestCase):
def test_every_field_has_a_description_and_public_flag(self):
for model in all_models(AnalyticsReport):
for name, field in model.model_fields.items():
with self.subTest(field=f"{model.__name__}.{name}"):
self.assertTrue(field.description)
self.assertIsInstance(field.json_schema_extra, dict)
self.assertIsInstance(field.json_schema_extra.get("x-public"), bool)
def test_strings_are_limited_to_ids_and_hardware_names(self):
for model in all_models(AnalyticsReport):
properties = model.model_json_schema()["properties"]
for name, field in model.model_fields.items():
if field.annotation is not str:
continue
with self.subTest(field=f"{model.__name__}.{name}"):
self.assertIn((model.__name__, name), ALLOWED_STRINGS)
self.assertTrue(
"maxLength" in properties[name] or "pattern" in properties[name]
)
def test_map_keys_are_enums(self):
for model in all_models(AnalyticsReport):
for name, field in model.model_fields.items():
for key_type in dict_key_types(field.annotation):
with self.subTest(field=f"{model.__name__}.{name}"):
self.assertTrue(issubclass(key_type, Enum))
class TestEnumsTrackTheirSources(unittest.TestCase):
def test_hardware_keys_cover_every_probe(self):
probed = set(
re.findall(
r'_hardware\(\s*"([^"]+)"', inspect.getsource(detection_hardware)
)
)
self.assertTrue(probed)
self.assertLessEqual(probed, {key.value for key in HardwareKey})
def test_decode_families_cover_every_hwaccel_family(self):
families = {
value.key
for value in vars(hwaccel).values()
if isinstance(value, HwaccelFamily)
}
self.assertTrue(families)
self.assertLessEqual(families, {family.value for family in DecodeFamily})
def test_preset_keys_mirror_the_presets(self):
for enum, presets in (
(HwaccelKey, PRESETS_HW_ACCEL_DECODE),
(InputPresetKey, PRESETS_INPUT),
):
with self.subTest(enum=enum.__name__):
self.assertEqual(
{key.value for key in enum},
{name.removeprefix("preset-") for name in presets}
| {"custom", "none"},
)
def test_notice_keys_are_the_reportable_kinds(self):
self.assertEqual(
{key.value for key in NoticeKindKey},
{key for key, kind in NOTICE_KINDS.items() if kind.reportable},
)
self.assertNotIn("analytics_prompt", {key.value for key in NoticeKindKey})