mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-11 18:03:49 +01:00
Two gaps kuhy pointed at, both about not losing messages the bot was not awake for. Missed *counts* already worked and now have a test saying so: an event is keyed by Signal's own send timestamp, signal-cli keeps receiving in json-rpc mode while the bot is down, and the replay on reconnect is absorbed by the primary key. Messages sent during an outage come back filed under the day they were actually sent. Missed *reports* did not. A bot that was down at 21:37 never posted that day and never went back for it. The last day reported is now written down per group, so returning from an outage posts every day it owes, oldest first, bounded at a week. A day nobody spoke on is marked settled rather than reconsidered forever; a day whose send *failed* is deliberately left unmarked so the next run retries it. The pre-0.1.0 counter is carried over rather than discarded: 342 messages across four groups, 319 of them in the real group. What the counter cannot say is when, so before assuming, four places were checked for a real inbound timestamp -- journald (commands only), signal-cli's account.db (19 tables, none inbound; message_send_log is the bot's own outgoing resend buffer), Signal Desktop (unlinked, empty, and it does not backfill on link), and signal-api/attachments (the one dated artifact). The attachment mtimes put 12 files on 29 Aug against 79 on 30 Aug inside the counter's window, which is why the whole counter is filed under 30 Aug rather than split. That day is marked in group_meta, and a marked day claims no average message length -- those messages have a count but no lengths, so "średnio 0 znaków" would be a measurement nobody took. The mark is also what will keep the day out of personal records: a merged 22-hour day would otherwise hand somebody a record they never set. render_day's options move into a DayView value object; the keyword list had reached eight and this renderer is about to be shared by several commands that each want a different subset. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015d48t4qsQLBJnDwDeo2Nom
185 lines
6.6 KiB
Python
185 lines
6.6 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""The bot object itself: the command wiring and the two loops it owns.
|
|
|
|
Split out of app.py, which had grown to the 250-line cap with the ASGI
|
|
entrypoint, the object graph and the startup sequence all in one file. This
|
|
half is "what the bot does"; startup.py is "how it comes up".
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import datetime as dt
|
|
import logging
|
|
from collections.abc import Callable
|
|
from dataclasses import dataclass
|
|
from typing import TYPE_CHECKING
|
|
|
|
from signal_bot.animals import register_animal_commands
|
|
from signal_bot.announce import announce_all
|
|
from signal_bot.changelog import load as load_changelog
|
|
from signal_bot.decorators import cooldown
|
|
from signal_bot.dispatcher import Dispatcher
|
|
from signal_bot.http_client import ImageFetcher
|
|
from signal_bot.popes_command import register_pope_command
|
|
from signal_bot.portraits import PortraitCache
|
|
from signal_bot.registry import CommandRegistry
|
|
from signal_bot.stats import periods
|
|
from signal_bot.stats.backfill import backfilled_day
|
|
from signal_bot.stats.nightly import days_to_report, mark_reported
|
|
from signal_bot.stats.queries_day import day_rows, day_totals, with_silent
|
|
from signal_bot.stats.render_day import DayView, render_day
|
|
from signal_bot.versioning import POPE, __version__
|
|
|
|
if TYPE_CHECKING:
|
|
import httpx
|
|
|
|
from signal_bot.config import Config
|
|
from signal_bot.discovery import GroupDirectory
|
|
from signal_bot.liveness import Liveness
|
|
from signal_bot.store import Store
|
|
from signal_bot.transport_base import Transport
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
Clock = Callable[[], dt.datetime]
|
|
|
|
COOLDOWN_MESSAGE = "BEEP BOOP POCZEKAJ {seconds} SEKUND."
|
|
|
|
|
|
def now_local() -> dt.datetime:
|
|
"""Current Warsaw time -- the group's day, not the host's.
|
|
|
|
One definition of "day" for the whole bot. The daily scheduler fires
|
|
against this, ``CommandContext.day`` keys the daily limits off it, and
|
|
every event is filed under it, so a host in another timezone (or a
|
|
container on UTC) cannot make those three disagree.
|
|
"""
|
|
return periods.now()
|
|
|
|
|
|
@dataclass
|
|
class Bot:
|
|
"""The wired-up bot and its two long-running loops."""
|
|
|
|
config: Config
|
|
store: Store
|
|
transport: Transport
|
|
directory: GroupDirectory
|
|
dispatcher: Dispatcher
|
|
liveness: Liveness
|
|
# The same clock the dispatcher files events against. One clock, so
|
|
# "which day is it" cannot differ between writing an event and reporting
|
|
# on it -- which is precisely the drift the old reset-after-post had.
|
|
clock: Clock = now_local
|
|
|
|
async def publish_report(self) -> None:
|
|
"""Post each group's report for the last full day.
|
|
|
|
Yesterday, not "since the last post". The old scheme reset a counter
|
|
after publishing, so a group nobody spoke in was never reset and its
|
|
next report silently covered two days. A day is now a property of
|
|
when a message was sent, which cannot drift.
|
|
|
|
Nothing is deleted afterwards. Each group is isolated on purpose: one
|
|
group refusing the report -- the bot removed from it, a transient send
|
|
failure -- must not cost every other group its report.
|
|
"""
|
|
latest = periods.previous_day(self.clock())
|
|
for group_id in self.directory.groups:
|
|
for day in days_to_report(self.store, group_id, latest):
|
|
if not await self._report_one(group_id, day):
|
|
# Left unmarked on purpose, so the next run retries it
|
|
# rather than skipping the day forever.
|
|
break
|
|
mark_reported(self.store, group_id, day)
|
|
|
|
async def _report_one(self, group_id: str, day: str) -> bool:
|
|
"""Post one group's report for one day. False means try again later."""
|
|
rows = day_rows(self.store.events, group_id, day)
|
|
if not rows:
|
|
# Settled, not pending. The bot is in every group it was ever
|
|
# added to, so posting "nobody spoke" would mean a nightly ping
|
|
# into every quiet group, forever.
|
|
logger.info("no messages in %s on %s; not posting a report", group_id, day)
|
|
return True
|
|
named = self.store.events.roster(group_id, self.directory.member_identities(group_id))
|
|
with_zeros = with_silent(rows, [(p.uuid, p.display_name) for p in named])
|
|
text = render_day(
|
|
day,
|
|
with_zeros,
|
|
day_totals(with_zeros),
|
|
DayView(
|
|
since=self.store.events.first_day(group_id),
|
|
approximate=backfilled_day(self.store, group_id) == day,
|
|
),
|
|
)
|
|
try:
|
|
await self.transport.send_text(text, group_id)
|
|
except Exception:
|
|
logger.exception("daily report failed for group %s", group_id)
|
|
return False
|
|
return True
|
|
|
|
async def announce_release(self) -> None:
|
|
"""Tell every watched group about a version it has not seen yet."""
|
|
await announce_all(
|
|
self.transport,
|
|
self.store,
|
|
list(self.directory.groups),
|
|
load_changelog(),
|
|
__version__,
|
|
POPE.name,
|
|
)
|
|
|
|
async def listen(self) -> None:
|
|
"""Consume frames forever, handing each to the dispatcher."""
|
|
async for frame in self.transport.receive():
|
|
# Every frame counts, including receipts and typing indicators:
|
|
# the question this answers is "can anything still reach us?",
|
|
# not "did anybody address the bot?".
|
|
self.liveness.note_envelope()
|
|
await self.dispatcher.handle(frame)
|
|
|
|
|
|
def build_bot(
|
|
config: Config,
|
|
client: httpx.AsyncClient,
|
|
store: Store,
|
|
transport: Transport,
|
|
directory: GroupDirectory,
|
|
liveness: Liveness,
|
|
clock: Clock = now_local,
|
|
) -> Bot:
|
|
"""Assemble the object graph from its injected dependencies."""
|
|
registry = CommandRegistry()
|
|
fetcher = ImageFetcher(client)
|
|
rate_limit = cooldown(config.cooldown_seconds, COOLDOWN_MESSAGE)
|
|
register_animal_commands(
|
|
registry,
|
|
fetcher,
|
|
decorate=rate_limit,
|
|
endpoints=config.image_api_urls,
|
|
)
|
|
register_pope_command(
|
|
registry,
|
|
PortraitCache(fetcher, config.commons_api_url),
|
|
decorate=rate_limit,
|
|
)
|
|
dispatcher = Dispatcher(
|
|
config=config,
|
|
directory=directory,
|
|
registry=registry,
|
|
store=store,
|
|
transport=transport,
|
|
clock=clock,
|
|
)
|
|
return Bot(
|
|
config=config,
|
|
store=store,
|
|
transport=transport,
|
|
directory=directory,
|
|
dispatcher=dispatcher,
|
|
liveness=liveness,
|
|
clock=clock,
|
|
)
|