mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 20:37:03 +01:00
Today the bot was up, healthy and answering nothing for three hours. A host
firewall change (fixed in testsAndMisc 334c0cd9) cut every Docker container
off the internet; signal-cli lost Signal and reconnected in a loop from
15:32:50 onward. Nothing noticed:
- the container's own healthcheck answered 204
- /v1/groups answered 200 out of local state, so discovery saw no change
- the bot's WebSocket to the container stayed OPEN, so the transport's
reconnect logic never fired
- /healthz answered {"status": "ok"} the entire time
The only symptom was silence, which is also what a quiet evening looks like.
signal_bot/liveness.py asks the one question that cannot be answered from a
cache -- GET /v1/devices, which needs a live round trip -- but only after
SILENCE_SECONDS (120) with no frame of any kind, so a busy group costs
nothing and an idle one costs one request per window. Three consecutive
failures and /healthz answers 503 with the reason. Verified end to end in
scripts/e2e.sh against the real process: 503 after 84s with the fake's
connection cut, back to 200 on its own 30s after restoring it.
scripts/signal_api_watchdog.sh + a two-minute user timer do the recovery the
bot cannot do for itself, since a wedged bot cannot restart the container it
depends on. Two tiers, so the steady state costs no Signal round trip at
all: the bot's own /healthz first, the authenticated probe only when that is
not 200. It stops after 3 restarts in 6 hours and escalates instead -- a
deregistered account or a blocked network is not fixable by restarting, and
a restart loop would hide it. Its own bash suite stubs curl and docker and
drives every branch including the give-up cap.
signal_bot/trust.py answers the other half: TRUSTED_INVITERS decides who may
put this bot in a group. The gate sits in GroupDirectory._permitted, which
both _join_pending and _adopt already route through -- gating only invites
would gate the door nobody uses, since prime_profile.sh exists precisely so
that an add becomes a direct join. Evidence is either the group-update
envelope, which is the only frame naming an inviter, or a trusted identity
being a full member in the listing. A refusal is logged once, with that
group's members, so the operator can see which string to add.
verify_allowlist moved to membership.py to keep discovery.py under the
250-line gate; it was already the module that owns MembershipError.
Verified live, by stopping the container by hand and touching nothing else:
18:54:35 docker stop signal-api
18:56:36 liveness: failure 1 of 3 after 123s of silence
18:57:36 failure 3 of 3 -> /healthz answers 503 from 18:57:45
18:58:18 watchdog: probe failed (1/2)
19:00:28 watchdog: probe failed (2/2) -> docker restart signal-api
19:00:36 liveness: receive path recovered after 8 failed probe(s)
19:01:13 watchdog: signal-api is back
Six minutes, unattended, against three hours of silence this afternoon. All
four real groups are still adopted with TRUSTED_INVITERS=+48123456789 set,
and no group was refused.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KbjfWdAyHbCubac7wJKJZW
125 lines
4.2 KiB
Python
125 lines
4.2 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""GROUP_IDS as a restriction: pinning the bot, and refusing to start unpinned."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import replace
|
|
from typing import TYPE_CHECKING
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from signal_bot.discovery import GroupDirectory
|
|
from signal_bot.membership import MembershipError
|
|
from signal_bot.trust import InviteTrust
|
|
from tests.conftest import SECOND_GROUP, WATCHED_GROUP, group_entry
|
|
|
|
if TYPE_CHECKING:
|
|
from signal_bot.config import Config
|
|
from signal_bot.store import Store
|
|
|
|
|
|
def _directory(config: Config, store: Store, handler: object) -> GroupDirectory:
|
|
return GroupDirectory(
|
|
config,
|
|
httpx.AsyncClient(transport=httpx.MockTransport(handler)),
|
|
store,
|
|
InviteTrust(()),
|
|
)
|
|
|
|
|
|
async def test_the_allowlist_restricts_what_is_adopted(config: Config, store: Store) -> None:
|
|
"""GROUP_IDS still pins the bot when somebody wants it pinned."""
|
|
pinned = replace(config, group_ids=(WATCHED_GROUP,))
|
|
found = _directory(
|
|
pinned,
|
|
store,
|
|
lambda r: httpx.Response(200, json=[group_entry(WATCHED_GROUP), group_entry(SECOND_GROUP)]),
|
|
)
|
|
await found.refresh()
|
|
assert found.groups == (WATCHED_GROUP,)
|
|
await found.verify_allowlist()
|
|
|
|
|
|
async def test_verify_allowlist_names_a_pinned_group_that_is_missing(
|
|
config: Config, store: Store
|
|
) -> None:
|
|
pinned = replace(config, group_ids=(WATCHED_GROUP, SECOND_GROUP))
|
|
found = _directory(
|
|
pinned, store, lambda r: httpx.Response(200, json=[group_entry(WATCHED_GROUP)])
|
|
)
|
|
await found.refresh()
|
|
with pytest.raises(MembershipError, match="not a joined member") as raised:
|
|
await found.verify_allowlist()
|
|
assert SECOND_GROUP in str(raised.value)
|
|
|
|
|
|
async def test_verify_allowlist_reports_why_the_join_failed(config: Config, store: Store) -> None:
|
|
"""The refusal carries the API's own answer, not a generic complaint."""
|
|
pinned = replace(config, group_ids=(WATCHED_GROUP,))
|
|
|
|
def handler(request: httpx.Request) -> httpx.Response:
|
|
if request.method == "POST":
|
|
return httpx.Response(400, text="Cannot find service ID for self")
|
|
return httpx.Response(200, json=[group_entry(WATCHED_GROUP, member=False)])
|
|
|
|
found = _directory(pinned, store, handler)
|
|
await found.refresh()
|
|
with pytest.raises(MembershipError, match="Cannot find service ID"):
|
|
await found.verify_allowlist()
|
|
|
|
|
|
async def test_an_unpinned_bot_in_no_groups_is_allowed_to_start(
|
|
config: Config, store: Store
|
|
) -> None:
|
|
found = _directory(config, store, lambda r: httpx.Response(200, json=[]))
|
|
await found.refresh()
|
|
await found.verify_allowlist()
|
|
|
|
|
|
async def test_run_refreshes_on_a_schedule(config: Config, store: Store) -> None:
|
|
"""A group added while nobody is talking is still picked up."""
|
|
slept: list[float] = []
|
|
listings = iter([[], [group_entry(WATCHED_GROUP)]])
|
|
|
|
async def sleeper(seconds: float) -> None:
|
|
slept.append(seconds)
|
|
|
|
found = GroupDirectory(
|
|
config,
|
|
httpx.AsyncClient(
|
|
transport=httpx.MockTransport(lambda r: httpx.Response(200, json=next(listings)))
|
|
),
|
|
store,
|
|
InviteTrust(()),
|
|
sleeper=sleeper,
|
|
)
|
|
await found.run(iterations=2)
|
|
assert slept == [30.0, 30.0]
|
|
assert found.groups == (WATCHED_GROUP,)
|
|
|
|
|
|
async def test_a_failed_re_read_after_joining_keeps_the_old_set(
|
|
config: Config, store: Store
|
|
) -> None:
|
|
"""Fail closed: an unverified join must not be treated as membership."""
|
|
responses = iter(
|
|
[
|
|
httpx.Response(200, json=[group_entry(WATCHED_GROUP)]),
|
|
httpx.Response(
|
|
200, json=[group_entry(WATCHED_GROUP), group_entry(SECOND_GROUP, member=False)]
|
|
),
|
|
httpx.Response(201, text=""),
|
|
httpx.Response(503, text="gone"),
|
|
]
|
|
)
|
|
|
|
def handler(request: httpx.Request) -> httpx.Response:
|
|
return httpx.Response(201, text="") if request.method == "POST" else next(responses)
|
|
|
|
found = _directory(config, store, handler)
|
|
await found.refresh()
|
|
assert found.groups == (WATCHED_GROUP,)
|
|
await found.refresh()
|
|
assert found.groups == (WATCHED_GROUP,)
|