signal-bot/tests/test_liveness.py

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""The deafness gate: silence plus a failing probe is not health."""

from __future__ import annotations

import logging
from typing import TYPE_CHECKING

import httpx

from signal_bot.liveness import Liveness

if TYPE_CHECKING:
    from collections.abc import Callable

    import pytest

    from signal_bot.config import Config

DEAD_BODY = {"error": "Failed to get linked devices: Closed unexpectedly"}


class Clock:
    """A monotonic clock the test moves by hand."""

    def __init__(self) -> None:
        self.seconds = 0.0

    def __call__(self) -> float:
        return self.seconds


def gate(
    config: Config,
    handler: Callable[[httpx.Request], httpx.Response],
    clock: Clock,
    *,
    slept: list[float] | None = None,
) -> Liveness:
    """A Liveness wired to a mock API and a hand-cranked clock."""

    async def sleeper(seconds: float) -> None:
        if slept is not None:
            slept.append(seconds)

    return Liveness(
        config,
        httpx.AsyncClient(transport=httpx.MockTransport(handler)),
        ticker=clock,
        sleeper=sleeper,
    )


async def test_it_starts_healthy_without_asking_anybody(config: Config) -> None:
    """A cold start must not 503: the installer waits on /healthz."""
    calls: list[str] = []

    def handler(request: httpx.Request) -> httpx.Response:
        calls.append(str(request.url))
        return httpx.Response(200, json=[])

    assert gate(config, handler, Clock()).healthy is True
    assert calls == []


async def test_a_live_account_answers_the_probe(config: Config) -> None:
    def handler(request: httpx.Request) -> httpx.Response:
        assert request.url.path == "/v1/devices/+15550000000"
        return httpx.Response(200, json=[{"id": 1}])

    assert await gate(config, handler, Clock()).probe() is True


async def test_the_real_outage_shape_fails_the_probe(config: Config) -> None:
    live = gate(config, lambda r: httpx.Response(400, json=DEAD_BODY), Clock())
    assert await live.probe() is False
    assert "Closed unexpectedly" in live.reason


async def test_a_hanging_api_fails_the_probe_rather_than_the_loop(config: Config) -> None:
    """/v1/devices was seen to hang past 20s during the outage."""

    timed_out = "timed out"

    def handler(request: httpx.Request) -> httpx.Response:
        raise httpx.TimeoutException(timed_out, request=request)

    live = gate(config, handler, Clock())
    assert await live.probe() is False
    assert "TimeoutException" in live.reason


async def test_silence_alone_never_probes(config: Config) -> None:
    """A quiet group is normal; only long silence is worth a round trip."""
    calls: list[str] = []
    clock = Clock()
    slept: list[float] = []

    def handler(request: httpx.Request) -> httpx.Response:
        calls.append(str(request.url))
        return httpx.Response(200, json=[])

    live = gate(config, handler, clock, slept=slept)
    await live.run(iterations=2)
    assert slept == [30.0, 30.0]
    assert calls == []
    assert live.healthy is True


async def test_a_successful_probe_resets_the_silence_clock(config: Config) -> None:
    """One probe per silence window, not one per tick."""
    calls: list[str] = []
    clock = Clock()

    def handler(request: httpx.Request) -> httpx.Response:
        calls.append(str(request.url))
        clock.seconds += 30.0
        return httpx.Response(200, json=[])

    live = gate(config, handler, clock)

    async def tick() -> None:
        clock.seconds += 30.0
        await live.run(iterations=1)

    for _ in range(8):
        await tick()
    assert len(calls) == 2
    assert live.healthy is True


async def test_three_failures_make_the_bot_admit_it_is_deaf(
    config: Config, caplog: pytest.LogCaptureFixture
) -> None:
    clock = Clock()
    live = gate(config, lambda r: httpx.Response(400, json=DEAD_BODY), clock)
    with caplog.at_level(logging.WARNING):
        for _ in range(3):
            clock.seconds += 200.0
            await live.run(iterations=1)
            if live.healthy:
                assert "cannot reach Signal" in caplog.text
    assert live.healthy is False
    assert "nothing received for" in live.reason
    assert caplog.text.count("cannot reach Signal") == 3

    # A fourth failure must not say "failure 4 of 3": the verdict is in.
    with caplog.at_level(logging.WARNING):
        clock.seconds += 200.0
        await live.run(iterations=1)
    assert caplog.text.count("cannot reach Signal") == 3
    assert "still deaf: 4 failed probe(s)" in caplog.text


async def test_one_frame_clears_the_alarm(config: Config, caplog: pytest.LogCaptureFixture) -> None:
    clock = Clock()
    live = gate(config, lambda r: httpx.Response(400, json=DEAD_BODY), clock)
    for _ in range(3):
        clock.seconds += 200.0
        await live.run(iterations=1)
    assert live.healthy is False

    with caplog.at_level(logging.WARNING):
        live.note_envelope()
    assert live.healthy is True
    assert "recovered after 3 failed probe(s)" in caplog.text
    assert live.silent_for == 0.0


async def test_a_frame_while_healthy_says_nothing(
    config: Config, caplog: pytest.LogCaptureFixture
) -> None:
    """The recovery line must mean something, so it cannot fire per frame."""
    live = gate(config, lambda r: httpx.Response(200, json=[]), Clock())
    with caplog.at_level(logging.WARNING):
        live.note_envelope()
    assert caplog.text == ""