mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 18:07:29 +01:00
One row per command attempt, not two aggregates written only on success. command_uses holds last-use only and daily_uses counts successes; both are rate-limiter state and both are written by store.record_use, which the dispatcher calls only when a handler returns cleanly. A gate refusal and a crash returned before it, so a command that failed every time looked exactly like one nobody ran, and nothing knew which command a counted message was. command_events now takes every attempt with its outcome, its duration and the item it served; upstream_calls takes every outbound request made while serving one. The two writes stay separate on purpose -- recording a refusal as a use is what slid the cooldown window forward every time somebody was told to wait -- and test_dispatcher_outcomes asserts last_used does not move. Backfilled from journald joined against message_events, with daily_uses filling the residual so the two sources cannot double-count. Two things were wrong on the first attempt and both were found by measuring rather than by reasoning: the window has to be symmetric, because sent_at_ms comes from the sender's phone and the journal stamp from this host (194 of 299 lines landed *before* their own message, by up to 3.2 s); and matching has to be a global closest-pair assignment, because per-row greedy cannot separate two commands seconds apart. Together those took the dropped rows from 137 to zero, and recovered 418 invocations back to 29 August. Also: !analityka in the group, twelve Polish lines, naming at most three people and only ones whose display name has been seen; an Analytics tab with Nivo charts; and continuous latency measurement, which answers the open question in DOCS-latency.md -- a text send is 235 ms and an image send about 2.2 s, so the upload really is where the time goes. EPHEMERAL_TABLES was doing two unrelated jobs and is now two tuples: what a schema bump rebuilds, and what leaving a group clears. daily_uses left the first (it is a backfill source now) and stayed in the second, and _drop_reshaped took over the repair a bump used to do for it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01T4QTp3h5Q3MvfrwGV8xqPf
165 lines
6.5 KiB
Python
165 lines
6.5 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""The !wiersz command: one short public-domain Polish poem, whole.
|
|
|
|
Shaped exactly like !pułapka, and for the same reason. The repository commits
|
|
a pool of **identifiers** -- Commons page ids there, Wolne Lektury slugs here
|
|
-- and the words arrive over the wire at the moment somebody asks. What
|
|
``commons.caption_for`` says is the rule the whole bot follows:
|
|
|
|
The text is fetched at run time and posted to the group; none of it is
|
|
ever written into this repository, which is why it may be free text
|
|
where traps.json may not.
|
|
|
|
This command was written the other way first, committing the poems
|
|
themselves, and that is worth recording because it looked entirely
|
|
reasonable and failed hard. ``scripts/check_personal_data.py`` refused the
|
|
pack: three lines carried a real group member's name, and two still did after
|
|
a filter that had already discarded 31% of the corpus. The names were at the
|
|
start of a line, and a filter cannot reject those -- Polish verse capitalises
|
|
every line, so a line-initial capital is the norm and not a signal. Committing
|
|
several hundred Polish poems means committing several hundred Polish given
|
|
names, and one collision refuses every commit on the maintainer's machine
|
|
while CI, which has no private data to compare against, stays green.
|
|
|
|
Slugs fixed that structurally rather than by degree, and the version that
|
|
survived is also the better one: no name filter means no false positives, so
|
|
the pool is far larger and poems that were being thrown away for containing
|
|
an ordinary word come back.
|
|
|
|
There is no cap on the rendered message, which is a decision rather than an
|
|
oversight. ``commons.CAPTION_LIMIT`` bounds a caption at 220 characters
|
|
because a caption is a label on a picture. A poem is the message, truncating
|
|
one was ruled out when the length filter was chosen, and the worst case is
|
|
bounded anyway by the caps the harvest applied: 24 lines and 1200 characters,
|
|
plus a title, an author and a link.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import secrets
|
|
from pathlib import Path
|
|
from typing import TYPE_CHECKING, Final
|
|
|
|
from signal_bot.analytics import probe
|
|
from signal_bot.animals import load_aliases
|
|
from signal_bot.wolnelektury import CATALOGUE, parse
|
|
|
|
if TYPE_CHECKING:
|
|
from collections.abc import Sequence
|
|
|
|
from signal_bot.context import CommandContext
|
|
from signal_bot.decorators import Decorator
|
|
from signal_bot.http_client import ImageFetcher
|
|
from signal_bot.registry import CommandRegistry, Handler
|
|
from signal_bot.wolnelektury import Poem
|
|
|
|
COMMAND_NAME: Final = "poem"
|
|
DESCRIPTION: Final = "losowy wiersz"
|
|
POEMS_FILE: Final = Path(__file__).with_name("poems.json")
|
|
|
|
# Whole poems only, never an excerpt: a truncated poem is worse than no poem,
|
|
# so these reject at harvest time rather than cutting at post time. They live
|
|
# here rather than in the generator because they are the promise the pack
|
|
# makes -- every committed slug is a poem this short -- and the tests assert
|
|
# the shipped pack against them.
|
|
MAX_LINES: Final = 24
|
|
MAX_CHARS: Final = 1200
|
|
|
|
|
|
def load_slugs(path: Path = POEMS_FILE) -> tuple[str, ...]:
|
|
"""Read the slug pool.
|
|
|
|
The file holds Wolne Lektury slugs and nothing else, which is checked
|
|
here rather than assumed -- the whole privacy argument for this command
|
|
rests on the pack carrying no poem text, and this is the guard that keeps
|
|
it that way when somebody regenerates it.
|
|
|
|
Args:
|
|
path: Where to read the pool from. Defaults to the shipped file.
|
|
|
|
Returns:
|
|
Every slug in the pool.
|
|
|
|
Raises:
|
|
ValueError: If the pool is empty or holds anything but non-empty
|
|
strings.
|
|
"""
|
|
document = json.loads(path.read_text(encoding="utf-8"))
|
|
slugs = document["poems"]
|
|
if not slugs or not all(isinstance(slug, str) and slug for slug in slugs):
|
|
msg = f"{path} must hold a non-empty list of Wolne Lektury slugs"
|
|
raise ValueError(msg)
|
|
return tuple(slugs)
|
|
|
|
|
|
def random_slug(slugs: Sequence[str]) -> str:
|
|
"""Return one slug, uniformly at random.
|
|
|
|
No memory of what came before, the same as !pułapka and for the same
|
|
reason: a pool this size is not one a group works through, so a
|
|
no-repeat window would be bookkeeping that never changes an answer.
|
|
|
|
secrets rather than random for the reason animals.paged_url gives: the
|
|
choice is not security-sensitive, but ruff's ALL rule set flags `random`
|
|
and this repository forbids the noqa that would silence it.
|
|
"""
|
|
return slugs[secrets.randbelow(len(slugs))]
|
|
|
|
|
|
def render(poem: Poem, slug: str) -> str:
|
|
"""The message as the group reads it: title, poem, who wrote it, where.
|
|
|
|
The author's full name is safe to post and would not have been safe to
|
|
commit -- see the module docstring. Posting it is the whole point of
|
|
fetching it.
|
|
"""
|
|
return f"{poem.title}\n\n{poem.text}\n\n— {poem.author}\n{CATALOGUE.format(slug=slug)}"
|
|
|
|
|
|
def poem_handler(
|
|
fetcher: ImageFetcher,
|
|
text_url: str,
|
|
slugs: Sequence[str] | None = None,
|
|
) -> Handler:
|
|
"""Build the handler that posts one random poem.
|
|
|
|
Raises:
|
|
ValueError: If Wolne Lektury served something that is not the poem
|
|
the harvest committed. The dispatcher logs and stays silent, the
|
|
same as any other upstream failure -- a half-parsed poem is not
|
|
something to post.
|
|
"""
|
|
pool = load_slugs() if slugs is None else tuple(slugs)
|
|
|
|
async def handler(ctx: CommandContext) -> None:
|
|
slug = random_slug(pool)
|
|
# The Wolne Lektury slug, which is what the pool holds and all
|
|
# it holds -- the poem, its title and its author arrive over the
|
|
# wire and are never written down. See DOCS-privacy.md.
|
|
probe.note_item(slug)
|
|
poem = parse(await fetcher.fetch_text(text_url.format(slug=slug)))
|
|
if poem is None:
|
|
msg = f"wolnelektury.pl no longer serves a usable poem at {slug!r}"
|
|
raise ValueError(msg)
|
|
await ctx.reply(render(poem, slug))
|
|
|
|
return handler
|
|
|
|
|
|
def register_poem_command(
|
|
registry: CommandRegistry,
|
|
fetcher: ImageFetcher,
|
|
text_url: str,
|
|
*,
|
|
decorate: Decorator | None = None,
|
|
aliases: dict[str, list[str]] | None = None,
|
|
slugs: Sequence[str] | None = None,
|
|
) -> None:
|
|
"""Register !wiersz under every trigger aliases.json gives it."""
|
|
table = load_aliases() if aliases is None else aliases
|
|
handler = poem_handler(fetcher, text_url, slugs)
|
|
if decorate is not None:
|
|
handler = decorate(handler)
|
|
registry.register(COMMAND_NAME, table[COMMAND_NAME], handler, DESCRIPTION)
|