mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-11 12:57:32 +01:00
Krzysztof kuhy Rudnicki
6ec746fad2
An unrecognised "!word" was dropped in silence, which made a typo
indistinguishable from the bot being down and threw away the best available
list of commands worth writing. Three things now happen at the one place in
dispatcher.py that used to be a bare `return`.
A near miss is corrected -- "!cta" asks whether you meant "!kot". The
distance is optimal string alignment rather than difflib's ratio: a
transposition is the typo people actually make, it costs one edit here, and
it shreds the matching blocks a ratio counts ("!cta"/"!cat" scores 0.75 but
"!cta"/"!kot" scores 0.50, so no cutoff separates them on principle).
A word with no near miss points at !zaproponuj, which files an idea from
inside the group. Either way the word and the message are recorded, and the
management page grows an Ideas tab that lists them.
Three things stay silent, each for its own reason. "!kot ladny" is a real
trigger with words after it and always has been silent. "!!" is punctuation.
And a command claimed in some *other* group is neither answered nor recorded
-- the album's triggers are real people's names, and pack_scoping.yaml says
it out loud: a refusal would itself announce that the album exists. The
existence check is therefore global, which is what pack_add already asks.
Measured rather than guessed, against the shipped aliases.json:
- a minimum candidate length, because "!ja" is one edit from ~40 of the 676
two-letter words somebody could type; 69 of them got a suggestion before
the rule and 18 after.
- the two-edit budget starts at six characters, not five. At five it put
four pairs of *different* commands within reach of each other --
!pies/!popes, !days/!cats, !dzis/!dni, !mnie/!dni -- and costs nothing to
give up, because every real typo this was written for is one edit away.
test_no_two_commands_are_within_reach_of_each_other fails if a future
alias reopens the gap.
Both new tables are keyed on the envelope's own sent_at_ms, never the wall
clock: signal-cli replays undelivered frames on reconnect, and a clock-keyed
table collects a duplicate row per reconnect instead of ignoring one.
The branch is gated on should_count -- which excludes the bot's own envelope,
and that is the loop guard, since handle() checks is_own nowhere else -- and
wrapped in its own try/except, because it runs above the one that wraps a
handler and Bot.listen has no exception handling of its own.
Suggestions live in SQLite, not in a tracked file, and the export goes to the
state directory. check_personal_data learns the names it refuses from the
live database, so it catches a name somebody has typed and cannot catch a
misspelling of one -- and an unrecognised-command corpus is made of
misspellings. A group-writable file in a public tree is both a leak and a
wedge. The export therefore carries
deliberate !zaproponuj notes in full and unrecognised words as counts only;
bodies stay on the loopback-only page.
Verified on the live bot: restarted, both tables created with every existing
row count unchanged, !cta and !zaproponuj !pogoda delivered through
/_selftest, both rows read back out of the live database, and the journal
names neither the word nor the body.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01416TegJ3sa8xL5qGGgrygP
91 lines
3.8 KiB
Python
91 lines
3.8 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""The wish-list tables: what they keep, and what a redelivery does to them."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
from signal_bot.schema import EPHEMERAL_TABLES, PERMANENT_TABLES
|
|
|
|
if TYPE_CHECKING:
|
|
from signal_bot.store import Store
|
|
|
|
|
|
def test_nothing_collected_reads_as_nothing(store: Store) -> None:
|
|
"""Empty is a state, not an absence of tables."""
|
|
assert store.suggestions.filed() == []
|
|
assert store.suggestions.unknown() == []
|
|
|
|
|
|
def test_a_replayed_frame_does_not_become_a_second_row(store: Store) -> None:
|
|
"""signal-cli replays undelivered frames when the bot reconnects.
|
|
|
|
Keyed on the envelope's own timestamp rather than the wall clock, so a
|
|
replay collides with the row it already wrote and is ignored.
|
|
"""
|
|
for _ in range(3):
|
|
store.suggestions.record_unknown("g1", "!cta", "!cta", 500)
|
|
(row,) = store.suggestions.unknown()
|
|
assert row.hits == 1
|
|
|
|
|
|
def test_the_same_word_typed_again_later_counts_twice(store: Store) -> None:
|
|
"""A different message is a different row, which is what a tally is for."""
|
|
store.suggestions.record_unknown("g1", "!cta", "!cta", 500)
|
|
store.suggestions.record_unknown("g1", "!cta", "!cta znowu", 600)
|
|
(row,) = store.suggestions.unknown()
|
|
assert row.hits == 2
|
|
assert row.last_seen == 600
|
|
assert row.bodies == ("!cta", "!cta znowu")
|
|
|
|
|
|
def test_two_groups_never_share_a_tally(store: Store) -> None:
|
|
"""Every table in this schema is keyed by group first, and so is this one."""
|
|
store.suggestions.record_unknown("g1", "!cta", "!cta", 1)
|
|
store.suggestions.record_unknown("g2", "!cta", "!cta", 1)
|
|
assert {row.group_id for row in store.suggestions.unknown()} == {"g1", "g2"}
|
|
|
|
|
|
def test_tallies_come_back_most_tried_first(store: Store) -> None:
|
|
"""The page is a queue of work, so the loudest request sorts to the top."""
|
|
store.suggestions.record_unknown("g1", "!rare", "!rare", 1)
|
|
store.suggestions.record_unknown("g1", "!often", "!often", 2)
|
|
store.suggestions.record_unknown("g1", "!often", "!often", 3)
|
|
assert [row.word for row in store.suggestions.unknown()] == ["!often", "!rare"]
|
|
|
|
|
|
def test_suggestions_come_back_newest_first(store: Store) -> None:
|
|
"""The newest idea is the one most likely still worth acting on."""
|
|
store.suggestions.record_suggestion("g1", "!old", "stara", 1)
|
|
store.suggestions.record_suggestion("g1", "!new", "nowa", 2)
|
|
assert [row.command for row in store.suggestions.filed()] == ["!new", "!old"]
|
|
|
|
|
|
def test_two_people_can_ask_for_the_same_command(store: Store) -> None:
|
|
"""Different messages, so different rows -- twelve askers are twelve rows."""
|
|
store.suggestions.record_suggestion("g1", "!pogoda", "na jutro", 1)
|
|
store.suggestions.record_suggestion("g1", "!pogoda", "na tydzień", 2)
|
|
assert len(store.suggestions.filed()) == 2
|
|
|
|
|
|
def test_leaving_a_group_does_not_discard_the_wish_list(store: Store) -> None:
|
|
"""forget_group clears the ephemeral tables, and these are not among them.
|
|
|
|
A transient group listing that omits a member is the exact failure
|
|
discovery._permitted guards against, and it must not be able to delete
|
|
ideas nothing can recompute.
|
|
"""
|
|
store.suggestions.record_suggestion("g1", "!pogoda", "na jutro", 1)
|
|
store.suggestions.record_unknown("g1", "!cta", "!cta", 2)
|
|
store.forget_group("g1")
|
|
assert len(store.suggestions.filed()) == 1
|
|
assert len(store.suggestions.unknown()) == 1
|
|
|
|
|
|
def test_both_tables_are_declared_permanent() -> None:
|
|
"""The property above, asserted where it is actually configured."""
|
|
assert "suggestions" in PERMANENT_TABLES
|
|
assert "unknown_commands" in PERMANENT_TABLES
|
|
assert "suggestions" not in EPHEMERAL_TABLES
|
|
assert "unknown_commands" not in EPHEMERAL_TABLES
|