Three intertwined bodies of work developed and tested together this session. Full test suite green: python (edge) + phpunit (cloud). ## Edge/Pi install path - setup_online.sh: apt-lock retry (apt-daily contention), Type=exec unit + StartLimitIntervalSec in [Unit], journalctl-on-failure, crash-loop detection. - onnxruntime is now best-effort (no sdist / no 32-bit-ARM wheel); [6/8] probes the real backend and hard-fails if none works. - Hailo HEF auto-fetch: edge/tools/fetch_hailo_hef.py (pinned sha256, refuses to guess 8 vs 8L, HAILO_ARCH override for serial-less boards); hailo_pose.py run() timeout fix. - install_offline.sh: mirrors the backend gate; onnxruntime optional. ## Cafe24 cloud package (cloud/deploy/) - build_cafe24_package.sh emits move_detect_app/ (private, one folder) + www/move_detect/ (docroot subdir); no-dev classmap autoloader; preflight.php; hardened .htaccess. - Subdirectory mount support: Request::baseFrom/pathFor strip the mount prefix; index.php walks up to find the app root; views/JS prefix every URL with APP_BASE; session cookie scoped to the mount. ## Delivery audit — silent-failure & correctness (docs/delivery-audit.md) All 4 blockers + all Phase-1 silent-failure + Phase-2 HIGH correctness: - Edge cloud clients send a custom User-Agent (cafe24 WAF blocks python-requests) and allow_redirects=False. - Daemon fails loud on blank CAFE24_URL/DEVICE_SECRET; run_loop logs swallowed exceptions; heartbeat carries real fps + per-camera health; UvcSource reopens a dead camera; offline queue is size-capped and drops poison rows; TARGET_FPS/QUEUE_DB validated. - Zone coordinates normalized 0..1 on both sides (were canvas-px vs camera-px — every zone misplaced); pinch zones emit PINCH/HIGH (were downgraded to WARNING). - Fall detection uses bbox cues when keypoints are low-confidence (occluded fallen person); ghost incident not cancelled by a bystander; displacement normalized per-second (FPS-invariant). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019Xmn8KZWqiQUguEMRtn6rW
111 lines
4.4 KiB
Python
111 lines
4.4 KiB
Python
import pytest
|
|
|
|
from edge.daemon import run_loop
|
|
|
|
|
|
class _Runtime:
|
|
def __init__(self): self.steps = 0; self.applied = None
|
|
def step(self, now): self.steps += 1; return []
|
|
def apply_zones(self, zones): self.applied = zones
|
|
|
|
|
|
class _Client:
|
|
def __init__(self): self.configs = 0; self.beats = 0; self.metrics = []
|
|
def fetch_config(self): self.configs += 1; return {"zones": [], "thresholds": {}}
|
|
def send_heartbeat(self, m): self.beats += 1; self.metrics.append(m); return True
|
|
|
|
|
|
class _Queue:
|
|
def __init__(self): self.flushes = 0
|
|
def flush(self): self.flushes += 1; return 0
|
|
|
|
|
|
def test_loop_steps_and_periodics():
|
|
rt, cl, q = _Runtime(), _Client(), _Queue()
|
|
ticks = iter(range(1000))
|
|
counters = run_loop(rt, cl, q, clock=lambda: float(next(ticks)),
|
|
sleep=lambda s: None, iterations=10,
|
|
sync_every=5, heartbeat_every=5, flush_every=5)
|
|
assert rt.steps == 10
|
|
assert cl.configs == 2 and cl.beats == 2 and q.flushes == 2 # at frames 5 and 10
|
|
assert rt.applied == [] # zones applied from fetched config
|
|
|
|
|
|
def test_loop_survives_step_exception():
|
|
class Boom(_Runtime):
|
|
def step(self, now):
|
|
self.steps += 1
|
|
if self.steps == 2: raise RuntimeError("frame glitch")
|
|
return []
|
|
rt = Boom()
|
|
counters = run_loop(rt, _Client(), _Queue(), clock=lambda: 0.0,
|
|
sleep=lambda s: None, iterations=3,
|
|
sync_every=99, heartbeat_every=99, flush_every=99)
|
|
assert rt.steps == 3 # kept going past the exception
|
|
assert counters["errors"] == 1
|
|
|
|
|
|
def test_loop_logs_swallowed_step_exception_rate_limited():
|
|
# A permanently-broken pipeline must not present as a silent green unit: the swallowed
|
|
# exception has to be logged. But it must be rate-limited — a camera failing every frame
|
|
# cannot spam the journal thousands of times a second.
|
|
logs = []
|
|
|
|
class AlwaysBoom(_Runtime):
|
|
camera_id = "cam-x"
|
|
def step(self, now):
|
|
self.steps += 1
|
|
raise RuntimeError("perma-broken")
|
|
|
|
rt = AlwaysBoom()
|
|
counters = run_loop(rt, _Client(), _Queue(), clock=lambda: 0.0,
|
|
sleep=lambda s: None, iterations=5,
|
|
sync_every=99, heartbeat_every=99, flush_every=99,
|
|
log=lambda msg, exc=None: logs.append(msg))
|
|
assert counters["errors"] == 5 # every step raised
|
|
assert len(logs) == 1 # logged once, not five times (rate-limited)
|
|
assert "cam-x" in logs[0] # names the failing camera
|
|
|
|
|
|
def test_heartbeat_reports_real_fps_and_camera_health():
|
|
# A hardcoded fps=0.0 makes the cloud's device-health columns fiction; it can't tell a
|
|
# live device from a dead one. The heartbeat must carry the measured fps and per-camera
|
|
# health so a degraded device is visible remotely.
|
|
rt, cl, q = _Runtime(), _Client(), _Queue()
|
|
ticks = iter(float(t) for t in range(1000))
|
|
run_loop(rt, cl, q, clock=lambda: next(ticks), sleep=lambda s: None,
|
|
iterations=10, sync_every=99, heartbeat_every=10, flush_every=99)
|
|
assert len(cl.metrics) == 1
|
|
m = cl.metrics[0]
|
|
# 10 frames over the elapsed wall time between the first tick (t=0) and the beat (t=9).
|
|
assert m["fps"] == pytest.approx(10 / 9, rel=0.05)
|
|
assert m["cameras_total"] == 1
|
|
assert m["cameras_erroring"] == 0
|
|
|
|
|
|
def test_heartbeat_flags_a_failing_camera():
|
|
class AlwaysBoom(_Runtime):
|
|
camera_id = "cam-x"
|
|
def step(self, now):
|
|
self.steps += 1
|
|
raise RuntimeError("dead")
|
|
cl = _Client()
|
|
ticks = iter(float(t) for t in range(1000))
|
|
run_loop(AlwaysBoom(), cl, _Queue(), clock=lambda: next(ticks), sleep=lambda s: None,
|
|
iterations=10, sync_every=99, heartbeat_every=10, flush_every=99,
|
|
log=lambda *a, **k: None)
|
|
m = cl.metrics[0]
|
|
assert m["cameras_erroring"] == 1 # the cloud can now see the camera is down
|
|
|
|
|
|
def test_loop_survives_flush_exception():
|
|
class BoomQueue(_Queue):
|
|
def flush(self):
|
|
self.flushes += 1
|
|
raise RuntimeError("db locked")
|
|
rt = _Runtime()
|
|
counters = run_loop(rt, _Client(), BoomQueue(), clock=lambda: 0.0,
|
|
sleep=lambda s: None, iterations=5,
|
|
sync_every=99, heartbeat_every=99, flush_every=2)
|
|
assert rt.steps == 5 # loop kept running past the flush exceptions
|
|
assert counters["errors"] >= 1
|