mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 18:17:02 +01:00
Krzysztof kuhy Rudnicki
405541be9b
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
79 lines
2.5 KiB
Python
79 lines
2.5 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""Turning one parsed message into one row of history."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
from signal_bot.counting import media_kind
|
|
from signal_bot.stats.events import MessageEvent
|
|
from signal_bot.stats.periods import MS_PER_SECOND, day_of, hour_of
|
|
|
|
if TYPE_CHECKING:
|
|
import datetime as dt
|
|
|
|
from signal_bot.models import IncomingMessage
|
|
from signal_bot.stats.events import EventStore
|
|
|
|
|
|
def sent_at_ms_of(message: IncomingMessage, now: dt.datetime) -> int:
|
|
"""When a message was sent, in milliseconds, for use as a key.
|
|
|
|
The timestamp falls back to the clock because ``models._timestamp``
|
|
returns 0 when neither the payload nor the envelope carried one. Zero is
|
|
not merely inaccurate: it is part of the primary key, so every
|
|
zero-timestamp frame from one sender would collide and the whole run
|
|
would be recorded as a single message.
|
|
|
|
One function rather than the same expression in two places, because
|
|
``message_events`` and ``command_events`` are joined on exactly this
|
|
value -- to say which command a counted message was, and to attach an
|
|
hour to a backfilled row. Two spellings that drifted would not fail
|
|
anything; they would quietly stop matching.
|
|
"""
|
|
return message.timestamp or int(now.timestamp() * MS_PER_SECOND)
|
|
|
|
|
|
def to_event(
|
|
group_id: str,
|
|
message: IncomingMessage,
|
|
now: dt.datetime,
|
|
*,
|
|
is_command: bool,
|
|
) -> MessageEvent:
|
|
"""Reduce a message to the metadata the statistics keep."""
|
|
sent_at_ms = sent_at_ms_of(message, now)
|
|
return MessageEvent(
|
|
group_id=group_id,
|
|
uuid=message.source_uuid,
|
|
display_name=message.source_name or message.source_uuid,
|
|
sent_at_ms=sent_at_ms,
|
|
day=day_of(sent_at_ms),
|
|
local_hour=hour_of(sent_at_ms),
|
|
media_kind=media_kind(message),
|
|
media_count=len(message.attachment_types) or int(message.has_sticker),
|
|
char_len=len(message.text or ""),
|
|
is_command=is_command,
|
|
is_reply=message.is_reply,
|
|
)
|
|
|
|
|
|
def record_message(
|
|
events: EventStore,
|
|
group_id: str,
|
|
message: IncomingMessage,
|
|
now: dt.datetime,
|
|
*,
|
|
is_command: bool,
|
|
) -> None:
|
|
"""Append a message to the history and refresh who its sender is."""
|
|
event = to_event(group_id, message, now, is_command=is_command)
|
|
events.record(event)
|
|
events.note_person(
|
|
group_id,
|
|
event.uuid,
|
|
event.display_name,
|
|
message.source_number,
|
|
event.day,
|
|
)
|