Files
ely-eye/backend/tests/test_memory_conflicts.py
T
ZacharyZhang-NY 3d131e6a7e Stop a stale server from answering for this tree
The smoke script's build fingerprint asserted on the MCP reply, but the Go
layer decodes the HTTP answer into its own struct and re-emits a missing field
as zero, so a server from before the memory tiers still passed. Point the
fingerprint at the Python answer instead: /api/memory/working answers 404 on
4c6af87 and 200 here, both measured by starting each build myself.

Record the miss side of the rename rule. Whether a bare number renames its
subject depends on that memory's own sentence, so 「温度」 and 「温度24」 never
compare and an update goes unnoticed; both memories stay on the answer page,
so the miss costs a notice rather than a wrong number. Pin it with a test and
keep the mechanism, since comparing an unrenamed subject as a fallback would
put room numbers back in the ring as readings.

Correct the direction of the rule in the record: the rename slot is the token
after the subject word, not before it. A leading number becomes the subject
rather than fusing forward, which 「3 room holds 22 degrees」 shows by taking
「3」 as its subject.

门禁:pytest 384 passed;六文件 83(conflicts 27);三文件 35;ruff clean;
filesize clean;audit 32/2/6 clean;mypy 冷缓存 24 errors / 9 files(净 0);
pyright 0;go 全套 + gofmt 空;npm 产物未变;smoke PASS。
2026-10-09 12:54:06 -04:00

334 lines
15 KiB
Python

"""Two memories cannot both be true: the store notices, answers with the newer side, and waits.
Settling a disagreement is the holder's act. Until then the store chooses, but it records that
it chose, and it keeps both sides so the choice can be undone.
"""
from __future__ import annotations
from datetime import UTC, datetime
from ely_eye.config import Settings
from ely_eye.db import Database
from ely_eye.memory import MemoryService
from ely_eye.retrieval import RetrievalService
from ely_eye.schemas import MemoryOrigin, SearchFilters
NOW = datetime(2026, 5, 1, 12, 0, tzinfo=UTC)
OLD = "恒温器放在书房,设定 22 度"
NEW = "恒温器调到 24 度"
def _pair(tmp_path, *, scenario: str = "home", newer_holder: str = "wife") -> tuple[MemoryService, Database, list[str]]:
settings = Settings(home=tmp_path, default_holder="wife")
database = Database(settings)
database.init()
service = MemoryService(settings=settings, database=database)
older = service.remember(OLD, holder_id="wife", origin=MemoryOrigin.self_, scenario=scenario).atom_id
newer = service.remember(NEW, holder_id=newer_holder, origin=MemoryOrigin.self_, scenario=scenario).atom_id
return service, database, [older, newer]
def test_a_number_that_changed_leaves_a_conflict_naming_both_sides(tmp_path) -> None:
service, _, ids = _pair(tmp_path)
clashes = service.conflicts("wife")
assert len(clashes) == 1
record = clashes[0]
assert (record.older_atom_id, record.newer_atom_id) == (ids[0], ids[1])
assert record.older_value == "22" and record.newer_value == "24"
assert record.terms, "the record names what the two memories disagree about"
assert record.resolved_at is None
def test_repeating_the_same_statement_adds_no_memory_and_no_conflict(tmp_path) -> None:
service, database, _ = _pair(tmp_path)
before = len(service.conflicts("wife"))
service.remember(NEW, holder_id="wife", origin=MemoryOrigin.self_, scenario="home")
assert database.atom_count() == 2, "the same holder stating the same sentence holds one memory"
assert len(service.conflicts("wife")) == before, (
"a repeat cannot manufacture a second disagreement"
)
def test_a_memory_that_agrees_leaves_nothing_to_settle(tmp_path) -> None:
settings = Settings(home=tmp_path, default_holder="wife")
database = Database(settings)
database.init()
service = MemoryService(settings=settings, database=database)
service.remember(OLD, holder_id="wife", origin=MemoryOrigin.self_, scenario="home")
service.remember("恒温器设定 22 度", holder_id="wife", origin=MemoryOrigin.self_, scenario="home")
assert service.conflicts("wife") == [], (
"restating the same reading in other words is agreement, and the rule must not flinch at it"
)
def test_two_holders_who_disagree_are_not_a_conflict_in_one_memory(tmp_path) -> None:
service, _, _ = _pair(tmp_path, newer_holder="husband")
assert service.conflicts("wife") == [], "the husband changing his own mind is not the wife's contradiction"
def test_a_change_in_another_scenario_is_a_different_question(tmp_path) -> None:
settings = Settings(home=tmp_path, default_holder="wife")
database = Database(settings)
database.init()
service = MemoryService(settings=settings, database=database)
service.remember(OLD, holder_id="wife", origin=MemoryOrigin.self_, scenario="home")
service.remember(NEW, holder_id="wife", origin=MemoryOrigin.self_, scenario="office")
assert service.conflicts("wife") == [], (
"the office thermostat and the home thermostat are two thermostats"
)
def test_a_supersede_already_chose_a_side_and_records_no_conflict(tmp_path) -> None:
service, _, ids = _pair(tmp_path, scenario="")
before = len(service.conflicts("wife"))
service.supersede(ids[0], text="恒温器调到 26 度", holder_id="wife")
assert len(service.conflicts("wife")) == before, (
"a replacement is a decision, not a disagreement waiting to be settled"
)
def test_a_disagreement_about_words_rather_than_numbers_is_left_alone(tmp_path) -> None:
settings = Settings(home=tmp_path, default_holder="wife")
database = Database(settings)
database.init()
service = MemoryService(settings=settings, database=database)
service.remember("钥匙在玄关抽屉里", holder_id="wife", origin=MemoryOrigin.self_, scenario="home")
service.remember("钥匙在车里", holder_id="wife", origin=MemoryOrigin.self_, scenario="home")
assert service.conflicts("wife") == [], (
"the numeric rule is the one that can be checked; a reworded sentence would fire on every paraphrase"
)
def test_an_open_conflict_makes_the_store_answer_with_the_newer_side(tmp_path) -> None:
_, database, ids = _pair(tmp_path)
retrieval = RetrievalService(settings=Settings(home=tmp_path, default_holder="wife"), database=database)
hits = retrieval.search("恒温器", filters=SearchFilters(as_holder="wife")).hits
assert [hit.atom.atom_id for hit in hits] == [ids[1]], (
"both memories match the words; only the disagreement decides which one answers"
)
def test_settling_a_conflict_gives_both_sides_back(tmp_path) -> None:
service, database, ids = _pair(tmp_path)
retrieval = RetrievalService(settings=Settings(home=tmp_path, default_holder="wife"), database=database)
clash = service.conflicts("wife")[0]
assert service.resolve_conflicts([clash.conflict_id], at=NOW) == 1
assert service.conflicts("wife") == []
hits = retrieval.search("恒温器", filters=SearchFilters(as_holder="wife")).hits
assert {hit.atom.atom_id for hit in hits} == set(ids), (
"a settled disagreement stops the store from choosing; both memories are current again"
)
assert database.get_atoms(ids)[0].valid_to is None, "settling is not the same as superseding"
def test_a_conflict_belongs_to_the_memory_it_was_found_in(tmp_path) -> None:
service, _, ids = _pair(tmp_path)
assert service.conflicts("wife"), "the disagreement exists before the forget"
forgotten = service.forget(atom_id=ids[1], reason="the reading was wrong")
assert forgotten.atoms_deleted == 1
assert service.conflicts("wife") == [], (
"one side is gone, so there is nothing left to settle and no ghost row to list"
)
def _lane(tmp_path, texts: list[str], *, scenario: str = "home") -> tuple[MemoryService, Database]:
settings = Settings(home=tmp_path, default_holder="wife")
database = Database(settings)
database.init()
service = MemoryService(settings=settings, database=database)
for text in texts:
service.remember(text, holder_id="wife", origin=MemoryOrigin.self_, scenario=scenario)
return service, database
def _search(tmp_path, database: Database, query: str) -> list[str]:
retrieval = RetrievalService(settings=Settings(home=tmp_path, default_holder="wife"), database=database)
return [hit.atom.text for hit in retrieval.search(query, filters=SearchFilters(as_holder="wife")).hits]
def test_two_rooms_each_keep_their_own_number(tmp_path) -> None:
service, database = _lane(tmp_path, ["客厅的恒温器调到 22 度", "卧室的恒温器调到 24 度"])
assert service.conflicts("wife") == [], "they share the verb 调到 and disagree about nothing"
assert _search(tmp_path, database, "客厅") == ["客厅的恒温器调到 22 度"], (
"asking about the living room must not answer with the bedroom's reading"
)
def test_two_people_each_keep_their_own_count(tmp_path) -> None:
service, _ = _lane(tmp_path, ["她买了 3 本书", "他买了 5 本书"])
assert service.conflicts("wife") == [], "two buyers are two facts, not one moving count"
def test_one_router_moving_its_counter_is_a_conflict(tmp_path) -> None:
service, _ = _lane(tmp_path, ["The router forwards 220 packets", "The router forwards 240 packets"])
clashes = service.conflicts("wife")
assert len(clashes) == 1
assert clashes[0].terms == ["router"], "the subject both memories lead with is what the pair disagrees about"
assert (clashes[0].older_value, clashes[0].newer_value) == ("220", "240")
def test_the_same_subject_measuring_two_things_still_reads_as_one_quantity(tmp_path) -> None:
service, _ = _lane(tmp_path, ["恒温器设定 22 度", "恒温器功率 100 瓦"])
assert len(service.conflicts("wife")) == 1, (
"the store compares labels, not meanings: 设定 and 功率 both hang off 恒温, so this pair is "
"recorded as one moving quantity and the holder is the one who settles it"
)
def test_two_memories_that_are_only_a_number_do_not_name_the_same_thing(tmp_path) -> None:
service, _ = _lane(tmp_path, ["22 度", "24 度"])
assert service.conflicts("wife") == [], (
"each number becomes its own subject — 「22」 and 「24」 — so these are two different things "
"to the store, not one quantity that moved; it finds a subject, it just is not the same one"
)
def test_a_qualifier_on_the_subject_reads_as_a_different_thing(tmp_path) -> None:
service, _ = _lane(tmp_path, ["恒温器调到 22 度", "客厅的恒温器调到 24 度"])
assert service.conflicts("wife") == [], (
"the store compares labels, not meanings: adding 客厅 moves the subject, so the update is "
"kept as a second fact rather than noticed as a disagreement — nothing is hidden, and "
"supersede is still how the holder says which one stands"
)
def test_a_year_that_leads_a_memory_names_the_thing_it_counts(tmp_path) -> None:
service, _ = _lane(tmp_path, ["2026 saw 3 releases", "2027 saw 5 releases"])
assert service.conflicts("wife") == [], (
"the year is what the count belongs to, not the quantity that moved: 2026 and 2027 are two "
"records, and comparing their counts would call every timeline a disagreement"
)
def test_the_same_year_counting_differently_is_a_conflict(tmp_path) -> None:
service, _ = _lane(tmp_path, ["2026 saw 3 releases", "2026 saw 5 releases"])
found = service.conflicts("wife")
assert [conflict.terms for conflict in found] == [["saw"]], (
"one year, two counts: the year names the record and the count standing behind it is the "
"quantity that moved, which is what the holder asked to be told about"
)
assert [(conflict.older_value, conflict.newer_value) for conflict in found] == [("3", "5")]
def test_room_numbers_name_the_room_rather_than_measure_it(tmp_path) -> None:
service, database = _lane(tmp_path, ["Room 3 holds 22 degrees", "Room 4 holds 24 degrees"])
assert service.conflicts("wife") == [], (
"a number written onto the subject is part of its name: Room 3 and Room 4 are two rooms, "
"each steady at its own temperature, and suppressing one would throw away a real fact"
)
assert sorted(_search(tmp_path, database, "Room")) == sorted(
["Room 3 holds 22 degrees", "Room 4 holds 24 degrees"]
), "both rooms stay findable"
def test_two_routers_keep_their_own_counters(tmp_path) -> None:
service, _ = _lane(tmp_path, ["The router 1 forwards 220 packets", "The router 2 forwards 240 packets"])
assert service.conflicts("wife") == [], (
"the counter that identifies the router is not the counter it reports, so each router keeps "
"its own number the way each room keeps its own temperature"
)
def test_a_number_past_a_word_is_still_the_value_that_moved(tmp_path) -> None:
service, _ = _lane(tmp_path, ["The rent is 2200 dollars", "The rent is 2400 dollars"])
found = service.conflicts("wife")
assert [conflict.terms for conflict in found] == [["rent"]], (
"a number standing past a word measures the subject instead of naming it, which is what "
"keeps the ordinary case — a rent that changed — reaching the holder"
)
assert [(conflict.older_value, conflict.newer_value) for conflict in found] == [
("2200", "2400")
]
def test_a_letter_qualifier_does_not_rename_the_room(tmp_path) -> None:
service, _ = _lane(tmp_path, ["Room A holds 22 degrees", "Room B holds 24 degrees"])
assert len(service.conflicts("wife")) == 1, (
"only a number written onto the subject renames it, so Room A and Room B still read as one "
"room whose reading moved — the pair is recorded for the holder to settle rather than "
"silently resolved, and this is the boundary the rule does not cross"
)
def test_a_short_chinese_reading_is_a_value_and_not_part_of_a_name(tmp_path) -> None:
service, _ = _lane(tmp_path, ["温度 22 度", "温度 24 度"])
found = service.conflicts("wife")
assert [conflict.terms for conflict in found] == [["温度"]], (
"「温度 22 度」 has nothing behind the 22 but the unit, so the 22 is the reading and not the "
"name of a thing called 温度22 — renaming it would leave the memory stating no quantity at "
"all, and the most common Chinese phrasing would never be noticed as an update"
)
assert [(conflict.older_value, conflict.newer_value) for conflict in found] == [("22", "24")]
def test_a_budget_that_changed_is_recorded(tmp_path) -> None:
service, _ = _lane(tmp_path, ["预算 5000 元", "预算 8000 元"])
found = service.conflicts("wife")
assert [(conflict.terms, conflict.older_value, conflict.newer_value) for conflict in found] == [
(["预算"], "5000", "8000")
], "a two-character subject is the common case, not an edge case: the number after it moves"
def test_a_latin_reading_with_nothing_after_it_is_a_value_too(tmp_path) -> None:
service, _ = _lane(tmp_path, ["The thermostat 22 degrees", "The thermostat 24 degrees"])
assert len(service.conflicts("wife")) == 1, (
"the same rule has to hold in both scripts or it is a rule about Chinese, not about memories"
)
def test_an_identifier_with_no_reading_after_it_reads_as_a_quantity(tmp_path) -> None:
service, _ = _lane(tmp_path, ["Room 3 is big", "Room 4 is big"])
assert len(service.conflicts("wife")) == 1, (
"a label cannot tell an identifier from a reading: with no second number in the sentence the "
"3 and 4 are compared as one quantity that moved, so this pair is recorded and the holder "
"settles it — the boundary the rule does not cross, and the price of not hiding a disagreement"
)
def test_a_second_number_in_one_memory_hides_the_update(tmp_path) -> None:
service, database = _lane(tmp_path, ["温度 22 度", "温度 24 度 湿度 40"])
assert service.conflicts("wife") == [], (
"whether a bare number renames its subject depends on that memory's own sentence, so 「温度」 "
"and 「温度24」 never compare — the temperature moved and the store did not notice"
)
assert sorted(_search(tmp_path, database, "温度")) == ["温度 22 度", "温度 24 度 湿度 40"], (
"the fail-closed side of the boundary: nothing is suppressed, the reader sees both readings "
"and decides for themselves"
)