mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 20:27:17 +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
145 lines
4.4 KiB
Python
145 lines
4.4 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""Shared fixtures and envelope builders."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import datetime as dt
|
|
import json
|
|
from typing import Any
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from signal_bot.config import Config
|
|
from signal_bot.discovery import GroupDirectory
|
|
from signal_bot.store import Store
|
|
from signal_bot.transport_fake import FakeTransport
|
|
from signal_bot.trust import InviteTrust
|
|
|
|
# Canonical ``group.<base64>`` ids, the spelling /v1/groups reports and the
|
|
# only one /v2/send accepts. The *_INTERNAL forms are what an envelope
|
|
# carries: exactly what the canonical form decodes to.
|
|
WATCHED_GROUP = "group.ZDJGMFkyaGxaQzFuY205MWNDMXBaQzB6TWkxaWVYUmxjeUVoSVNFaElRPT0="
|
|
WATCHED_INTERNAL = "d2F0Y2hlZC1ncm91cC1pZC0zMi1ieXRlcyEhISEhIQ=="
|
|
SECOND_GROUP = "group.YzJWamIyNWtMV2R5YjNWd0xXbGtMVE15TFdKNWRHVnpJU0VoSVNFaA=="
|
|
SECOND_INTERNAL = "c2Vjb25kLWdyb3VwLWlkLTMyLWJ5dGVzISEhISEh"
|
|
OTHER_GROUP = "group.YjNSb1pYSXRaM0p2ZFhBdGFXUXRNekl0WW5sMFpYTWhJU0VoSVNFPQ=="
|
|
|
|
# The operator, and somebody who is not.
|
|
TRUSTED_NUMBER = "+48123456789"
|
|
STRANGER_NUMBER = "+15555550123"
|
|
|
|
|
|
@pytest.fixture
|
|
def config() -> Config:
|
|
"""The production shape: no allowlist, groups discovered from the account."""
|
|
return Config(
|
|
phone_number="+15550000000",
|
|
api_base_url="http://localhost:9922",
|
|
database_path=":memory:",
|
|
cooldown_seconds=10,
|
|
)
|
|
|
|
|
|
def group_entry(group_id: str, *, member: bool = True, name: str = "e2e") -> dict[str, Any]:
|
|
"""One /v1/groups row, in both spellings the real API uses."""
|
|
return {"id": group_id, "internal_id": group_id, "name": name, "member": member}
|
|
|
|
|
|
def listing_client(entries: list[dict[str, Any]]) -> httpx.AsyncClient:
|
|
"""A client whose /v1/groups always answers with these rows."""
|
|
return httpx.AsyncClient(
|
|
transport=httpx.MockTransport(lambda request: httpx.Response(200, json=entries))
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
async def directory(config: Config, store: Store) -> GroupDirectory:
|
|
"""A directory that has already discovered both test groups."""
|
|
client = listing_client([group_entry(WATCHED_GROUP), group_entry(SECOND_GROUP)])
|
|
found = GroupDirectory(config, client, store, InviteTrust(()))
|
|
await found.refresh()
|
|
return found
|
|
|
|
|
|
@pytest.fixture
|
|
def store() -> Store:
|
|
with Store(":memory:") as opened:
|
|
yield opened
|
|
|
|
|
|
@pytest.fixture
|
|
def transport() -> FakeTransport:
|
|
return FakeTransport()
|
|
|
|
|
|
@pytest.fixture
|
|
def clock() -> dt.datetime:
|
|
return dt.datetime(2026, 8, 29, 12, 0, tzinfo=dt.UTC)
|
|
|
|
|
|
def envelope(
|
|
*,
|
|
text: str | None = "hello",
|
|
group_id: str | None = WATCHED_GROUP,
|
|
uuid: str = "uuid-alice",
|
|
name: str = "Alice",
|
|
sticker: bool = False,
|
|
reaction: bool = False,
|
|
sync: bool = False,
|
|
) -> str:
|
|
"""Build one raw websocket frame in either envelope shape."""
|
|
payload: dict[str, Any] = {"timestamp": 1719177917717}
|
|
if text is not None:
|
|
payload["message"] = text
|
|
if group_id is not None:
|
|
payload["groupInfo"] = {"groupId": group_id, "type": "DELIVER"}
|
|
if sticker:
|
|
payload["sticker"] = {"packId": "abc", "stickerId": 6}
|
|
if reaction:
|
|
payload["reaction"] = {"emoji": "👍", "targetAuthor": "x"}
|
|
|
|
body: dict[str, Any] = {
|
|
"source": name,
|
|
"sourceNumber": STRANGER_NUMBER,
|
|
"sourceUuid": uuid,
|
|
"sourceName": name,
|
|
"sourceDevice": 69,
|
|
"timestamp": 1719177917717,
|
|
}
|
|
if sync:
|
|
body["syncMessage"] = {"sentMessage": payload}
|
|
else:
|
|
body["dataMessage"] = payload
|
|
return json.dumps({"envelope": body, "account": "+15550000000"})
|
|
|
|
|
|
def update_envelope(
|
|
*,
|
|
group_id: str = WATCHED_GROUP,
|
|
number: str = TRUSTED_NUMBER,
|
|
uuid: str = "uuid-operator",
|
|
) -> str:
|
|
"""Build a group-membership-change frame: no text, groupInfo type UPDATE.
|
|
|
|
This is the shape signal-cli emits when somebody adds the bot to a
|
|
group, and the only frame that names who did it.
|
|
"""
|
|
return json.dumps(
|
|
{
|
|
"envelope": {
|
|
"source": number,
|
|
"sourceNumber": number,
|
|
"sourceUuid": uuid,
|
|
"sourceName": "kuhy",
|
|
"timestamp": 1719177917717,
|
|
"dataMessage": {
|
|
"timestamp": 1719177917717,
|
|
"message": None,
|
|
"groupInfo": {"groupId": group_id, "type": "UPDATE"},
|
|
},
|
|
},
|
|
"account": "+15550000000",
|
|
}
|
|
)
|