signal-bot/tests/test_bot.py
Krzysztof kuhy Rudnicki 2f04d67f53 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

179 lines
6.5 KiB
Python

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""Command wiring, the daily report, and the listen loop."""
from __future__ import annotations
import datetime as dt
from dataclasses import dataclass
from typing import TYPE_CHECKING
import httpx
from signal_bot.bot import Bot, build_bot, now_local
from signal_bot.discovery import GroupDirectory
from signal_bot.liveness import Liveness
from signal_bot.stats.events import MessageEvent
from signal_bot.stats.periods import WARSAW
from signal_bot.transport_fake import FakeTransport
from signal_bot.trust import InviteTrust
from tests.conftest import (
SECOND_GROUP,
WATCHED_GROUP,
envelope,
group_entry,
listing_client,
mock_client,
)
if TYPE_CHECKING:
from signal_bot.config import Config
from signal_bot.store import Store
# The report covers the previous full day, so the tests freeze "now" and
# write their events into the day before it.
NOW = dt.datetime(2026, 9, 2, 21, 37, tzinfo=WARSAW)
YESTERDAY = "2026-09-01"
def _bot(config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory) -> Bot:
client = mock_client(lambda r: httpx.Response(200))
return build_bot(
config, client, store, transport, directory, Liveness(config, client), clock=lambda: NOW
)
def wrote(
store: Store, group_id: str, uuid: str, name: str, times: int, *, day: str = YESTERDAY
) -> None:
"""Put ``times`` messages from one person into one group on one day."""
for i in range(times):
store.events.record(
MessageEvent(
group_id=group_id,
uuid=uuid,
display_name=name,
sent_at_ms=i + 1,
day=day,
local_hour=12,
char_len=5,
)
)
store.events.note_person(group_id, uuid, name, "", day)
def test_now_local_is_timezone_aware() -> None:
assert now_local().tzinfo is not None
def test_build_bot_registers_the_animal_commands(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
bot = _bot(config, store, transport, directory)
assert bot.dispatcher.registry.resolve("!cat") is not None
assert bot.dispatcher.registry.resolve("!pies") is not None
async def test_publish_report_posts_each_group_its_own_tally(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
"""Every group gets its own counts, in its own chat, and only its own."""
wrote(store, WATCHED_GROUP, "u1", "Alice", 1)
wrote(store, SECOND_GROUP, "u2", "Bob", 2)
await _bot(config, store, transport, directory).publish_report()
assert [m.recipient for m in transport.sent] == [WATCHED_GROUP, SECOND_GROUP]
assert "Alice" in transport.texts[0]
assert "Bob" in transport.texts[1]
assert "Alice" not in transport.texts[1]
async def test_the_report_covers_yesterday_not_today(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
"""Today's traffic belongs to tomorrow's report, not tonight's."""
wrote(store, WATCHED_GROUP, "u1", "Alice", 1, day=YESTERDAY)
wrote(store, WATCHED_GROUP, "u2", "Bob", 9, day="2026-09-02")
await _bot(config, store, transport, directory).publish_report()
assert "Alice" in transport.texts[0]
assert "Bob" not in transport.texts[0]
async def test_nothing_is_deleted_after_publishing(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
"""The log is append-only; a second run renders the same day again."""
wrote(store, WATCHED_GROUP, "u1", "Alice", 3)
bot = _bot(config, store, transport, directory)
await bot.publish_report()
await bot.publish_report()
assert transport.texts[0] == transport.texts[1]
async def test_publish_report_falls_back_to_uuid_when_unnamed(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
wrote(store, WATCHED_GROUP, "u1", "u1", 1)
await _bot(config, store, transport, directory).publish_report()
assert "u1" in transport.texts[0]
async def test_listen_dispatches_every_frame(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
transport.queue([envelope(text="hello", group_id=WATCHED_GROUP)])
await _bot(config, store, transport, directory).listen()
row = store.events.connection.execute(
"SELECT COUNT(*) AS n FROM message_events WHERE group_id = ?", (WATCHED_GROUP,)
).fetchone()
assert row["n"] == 1
@dataclass
class RefusingTransport(FakeTransport):
"""A transport that rejects one group, the way a removal from it would."""
refuses: str = ""
async def send_text(self, text: str, recipient: str) -> None:
"""Record the send, unless this is the group that refuses them."""
if recipient == self.refuses:
msg = "removed from the group"
raise RuntimeError(msg)
await super().send_text(text, recipient)
async def test_one_group_failing_its_report_does_not_cost_the_others(
config: Config, store: Store, directory: GroupDirectory
) -> None:
"""A failed send must not skip the next group."""
wrote(store, WATCHED_GROUP, "u1", "Alice", 1)
wrote(store, SECOND_GROUP, "u2", "Bob", 1)
transport = RefusingTransport(refuses=WATCHED_GROUP)
await _bot(config, store, transport, directory).publish_report()
assert [m.recipient for m in transport.sent] == [SECOND_GROUP]
assert "Bob" in transport.texts[0]
async def test_a_quiet_group_is_logged_rather_than_posted_into(
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
) -> None:
"""The bot sits in every group it was added to; a nightly ping is noise."""
wrote(store, SECOND_GROUP, "u2", "Bob", 1)
await _bot(config, store, transport, directory).publish_report()
assert [m.recipient for m in transport.sent] == [SECOND_GROUP]
async def test_the_report_follows_the_live_group_set(
config: Config, store: Store, transport: FakeTransport
) -> None:
"""Groups come from the directory, not from .env, so a new one is included."""
client = listing_client([group_entry(WATCHED_GROUP), group_entry(SECOND_GROUP)])
directory = GroupDirectory(config, client, store, InviteTrust(()))
await directory.refresh()
wrote(store, WATCHED_GROUP, "u1", "Alice", 1)
wrote(store, SECOND_GROUP, "u2", "Bob", 1)
await _bot(config, store, transport, directory).publish_report()
assert [m.recipient for m in transport.sent] == [WATCHED_GROUP, SECOND_GROUP]