signal-bot/tests/test_trust.py
Krzysztof kuhy Rudnicki dc1995b558 feat: the message event log, and the nightly report built on it
The tally was one integer per person, deleted after each post. Nothing
dated survived it, so weeks, months, records, streaks and weekday
averages were all unanswerable. This replaces it with an append-only
per-message log holding metadata only -- never a message body -- and
rebuilds the nightly report on top.

What changes for the group: a photo posted without a caption now counts
(it was worth zero), stickers count, the bot's own messages no longer
do, people who said nothing appear with a 0, and the report covers the
previous full calendar day in Europe/Warsaw instead of "since the last
post" -- which used to merge two days whenever a group went quiet.

Notable decisions, each with the trap it avoids:

- Events and people are PERMANENT_TABLES: neither forget_group nor a
  future SCHEMA_VERSION bump may drop them. Both paths used to cost a
  day's counter and would now cost the entire history, and forget_group
  fires on a listing that merely omits members.
- is_own comes from which envelope branch carried the payload, not from
  comparing identities. The account is spelled as a uuid on some frames
  and a +E.164 number on others, so any comparison misses one of them.
- The roster is stashed in refresh(), not _adopt(), which returns early
  once the watched set stops changing -- i.e. always, in the steady
  state.
- The roster matches on uuid OR number because /v1/groups spells kuhy as
  +48123456789 while his messages carry an ACI uuid. Joining on uuid
  alone would have listed him twice every night, once with 0.
- Members whose display name we have never seen are counted, not named:
  their only spellings are a uuid or a phone number.
- (group, uuid, sent_at_ms) is the primary key, so a websocket
  redelivery after a reconnect cannot inflate the counts.
- Days come from a stored Warsaw date string, never a timestamp range:
  2026-03-29 is 23 hours long and 2026-10-25 is 25.
- Polish number agreement is a real rule with a 12-14 exception, so
  "44 znaki" and "45 znaków" are both spelled correctly.

config.py and startup.py were two lines under the 250-line cap and both
had to grow, so config_env and startup_retry come out of them first, as
pure moves.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015d48t4qsQLBJnDwDeo2Nom
2026-08-30 19:14:43 +02:00

209 lines
8.0 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 httpx
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
async def test_an_adopted_group_is_never_un_watched_by_the_gate(
config: Config, store: Store
) -> None:
"""Adoption is itself the vouch; a later listing must not purge its state.
The listing spells a member as a phone number for a known contact and as
a bare uuid for everybody else, and the same group has been seen both
ways. If that flip could refuse an adopted group, _adopt would treat it
as a removal, drop its counts and log that the bot was removed from it --
all three of which would be false.
"""
listings = iter(
[
[row(WATCHED_GROUP, members=[TRUSTED_NUMBER])],
[row(WATCHED_GROUP, members=[STRANGER_NUMBER])],
]
)
client = httpx.AsyncClient(
transport=httpx.MockTransport(lambda request: httpx.Response(200, json=next(listings)))
)
found = GroupDirectory(config, client, store, InviteTrust((TRUSTED_NUMBER,)))
await found.refresh()
assert found.groups == (WATCHED_GROUP,)
store.record_use(WATCHED_GROUP, "uuid-alice", "cat", 100.0, "2026-09-01")
await found.refresh()
assert found.groups == (WATCHED_GROUP,)
assert store.last_used(WATCHED_GROUP, "uuid-alice", "cat") == 100.0