signal-bot/tests/test_trust.py
Krzysztof kuhy Rudnicki d5c63b423b feat: refuse to look healthy while deaf, and heal the container by itself
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
2026-08-29 19:01:55 +02:00

178 lines
6.8 KiB
Python

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""Who may add this bot to a group, and what happens to everybody else."""
from __future__ import annotations
import logging
from dataclasses import replace
from typing import TYPE_CHECKING, Any
import pytest
from signal_bot.discovery import GroupDirectory
from signal_bot.groups import ConfigError
from signal_bot.models import parse_envelope
from signal_bot.trust import InviteTrust, parse_trusted_inviters
from tests.conftest import (
SECOND_GROUP,
STRANGER_NUMBER,
TRUSTED_NUMBER,
WATCHED_GROUP,
WATCHED_INTERNAL,
envelope,
group_entry,
listing_client,
update_envelope,
)
if TYPE_CHECKING:
from signal_bot.config import Config
from signal_bot.store import Store
OPERATOR_UUID = "b1c2d3e4-0000-4a00-8a00-000000000001"
def row(group_id: str, *, members: list[str], pending: list[str] | None = None) -> dict[str, Any]:
"""A /v1/groups row with the membership fields the gate reads."""
entry = group_entry(group_id)
entry["members"] = members
entry["pending_invites"] = pending if pending is not None else []
return entry
def test_parsing_accepts_numbers_uuids_and_nothing() -> None:
assert parse_trusted_inviters({}) == ()
assert parse_trusted_inviters({"TRUSTED_INVITERS": " "}) == ()
assert parse_trusted_inviters({"TRUSTED_INVITERS": f" {TRUSTED_NUMBER} , ,"}) == (
TRUSTED_NUMBER,
)
assert parse_trusted_inviters({"TRUSTED_INVITERS": f"{TRUSTED_NUMBER},{OPERATOR_UUID}"}) == (
TRUSTED_NUMBER,
OPERATOR_UUID,
)
def test_parsing_de_duplicates_and_rejects_junk() -> None:
same = f"{TRUSTED_NUMBER},{TRUSTED_NUMBER}"
assert parse_trusted_inviters({"TRUSTED_INVITERS": same}) == (TRUSTED_NUMBER,)
with pytest.raises(ConfigError, match="must be"):
parse_trusted_inviters({"TRUSTED_INVITERS": "kuhy"})
def test_an_empty_allowlist_trusts_everyone_but_says_so(
caplog: pytest.LogCaptureFixture,
) -> None:
with caplog.at_level(logging.WARNING):
trust = InviteTrust(())
assert "will be watched" in caplog.text
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[STRANGER_NUMBER])) is True
def test_a_trusted_member_vouches_for_the_group() -> None:
trust = InviteTrust((TRUSTED_NUMBER,))
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[TRUSTED_NUMBER])) is True
def test_a_trusted_uuid_vouches_too() -> None:
"""The listing spells an unknown contact as a uuid, not a number."""
trust = InviteTrust((OPERATOR_UUID,))
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[OPERATOR_UUID])) is True
def test_a_trusted_number_that_is_only_invited_does_not_vouch() -> None:
"""Bait: a stranger adds the operator, who has not accepted."""
trust = InviteTrust((TRUSTED_NUMBER,))
entry = row(WATCHED_GROUP, members=[STRANGER_NUMBER, TRUSTED_NUMBER], pending=[TRUSTED_NUMBER])
assert trust.allows(WATCHED_GROUP, entry) is False
def test_a_refusal_is_logged_once_and_names_the_members(
caplog: pytest.LogCaptureFixture,
) -> None:
trust = InviteTrust((TRUSTED_NUMBER,))
entry = row(WATCHED_GROUP, members=[STRANGER_NUMBER])
with caplog.at_level(logging.WARNING):
assert trust.allows(WATCHED_GROUP, entry) is False
assert trust.allows(WATCHED_GROUP, entry) is False
assert caplog.text.count("refusing group") == 1
assert STRANGER_NUMBER in caplog.text
def test_a_malformed_membership_field_refuses_rather_than_crashes() -> None:
trust = InviteTrust((TRUSTED_NUMBER,))
entry = group_entry(WATCHED_GROUP)
entry["members"] = "not-a-list"
assert trust.allows(WATCHED_GROUP, entry) is False
def test_an_update_from_a_trusted_number_vouches_in_either_spelling(
caplog: pytest.LogCaptureFixture,
) -> None:
"""The envelope carries the internal id; the listing carries group.<b64>."""
trust = InviteTrust((TRUSTED_NUMBER,))
with caplog.at_level(logging.INFO):
trust.note_update(WATCHED_INTERNAL, TRUSTED_NUMBER, "uuid-operator")
trust.note_update(WATCHED_INTERNAL, TRUSTED_NUMBER, "uuid-operator")
assert caplog.text.count("trusted inviter added the bot") == 1
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[STRANGER_NUMBER])) is True
def test_an_update_from_a_stranger_vouches_for_nothing() -> None:
trust = InviteTrust((TRUSTED_NUMBER,))
trust.note_update(WATCHED_INTERNAL, STRANGER_NUMBER, "uuid-stranger")
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[STRANGER_NUMBER])) is False
def test_an_update_by_a_trusted_uuid_vouches() -> None:
trust = InviteTrust((OPERATOR_UUID,))
trust.note_update(WATCHED_INTERNAL, "", OPERATOR_UUID)
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[STRANGER_NUMBER])) is True
async def test_the_directory_adopts_only_the_trusted_group(config: Config, store: Store) -> None:
client = listing_client(
[
row(WATCHED_GROUP, members=[TRUSTED_NUMBER]),
row(SECOND_GROUP, members=[STRANGER_NUMBER]),
]
)
found = GroupDirectory(config, client, store, InviteTrust((TRUSTED_NUMBER,)))
await found.refresh()
assert found.groups == (WATCHED_GROUP,)
async def test_a_pinned_group_bypasses_the_trust_gate(config: Config, store: Store) -> None:
"""GROUP_IDS is the operator naming a group by hand: vouch enough."""
pinned = replace(config, group_ids=(WATCHED_GROUP,))
client = listing_client([row(WATCHED_GROUP, members=[STRANGER_NUMBER])])
found = GroupDirectory(pinned, client, store, InviteTrust((TRUSTED_NUMBER,)))
await found.refresh()
assert found.groups == (WATCHED_GROUP,)
async def test_an_update_frame_lets_the_next_refresh_adopt_the_group(
config: Config, store: Store
) -> None:
"""The whole point: being added by the operator is still the whole setup."""
client = listing_client([row(WATCHED_GROUP, members=[STRANGER_NUMBER])])
found = GroupDirectory(config, client, store, InviteTrust((TRUSTED_NUMBER,)))
await found.refresh()
assert found.groups == ()
message = parse_envelope(update_envelope(group_id=WATCHED_INTERNAL))
assert message is not None
found.note_group_update(message)
await found.refresh()
assert found.groups == (WATCHED_GROUP,)
def test_ordinary_frames_vouch_for_nothing(config: Config, store: Store) -> None:
"""Only an UPDATE names an inviter; a chat message and a DM must not."""
trust = InviteTrust((TRUSTED_NUMBER,))
found = GroupDirectory(config, listing_client([]), store, trust)
for frame in (envelope(text="!cat"), envelope(text="hi", group_id=None)):
message = parse_envelope(frame)
assert message is not None
found.note_group_update(message)
assert trust.allows(WATCHED_GROUP, row(WATCHED_GROUP, members=[STRANGER_NUMBER])) is False