signal-bot/tests/test_fake_server.py
Krzysztof kuhy Rudnicki 08599e6056 feat: two commands that answer with somebody else's work
!sztuka posts a work of art, skewed 60% Polish; !wiersz posts one short
public-domain Polish poem, whole. Both follow the rule the rest of the bot
already keeps: the repository commits identifiers, and the words arrive over
the wire when somebody asks.

!wiersz was written the other way first, and the gate caught it. A pack of
short public-domain poems was harvested, name-filtered and committed, and
check_personal_data.sh refused it: three lines carried a real group member's
given name, and two still did after a filter that had discarded 31% of the
corpus. That is structural, not a tuning problem -- Polish verse capitalises
every line, so a line-initial capital carries no signal, and that is exactly
where a name sits. The pack now holds Wolne Lektury slugs; the poem, its
title and its author are fetched at post time and appear nowhere in git.
It is also the better version: with no name filter there are no false
positives, so the pool is larger and the attribution is a full name again.

The gate then refused the art category list too, over a painter whose given
name is somebody's. That is the popes.json case exactly, so it takes the
same answer: a file-scoped allowlist entry, still refused everywhere else.

The Commons harvest is now three modules by what they are, not by where the
line count fell: commons_api is the conversation with Commons, commons_harvest
turns categories into a pool of licensed page ids, commons_cache makes an
interrupted run resumable. Along the way it gained licences in the same
request that lists a category (the second pass was 1,500 requests at 2.3s
each), maxlag instead of a guessed sleep, 5xx retries because one 504 used to
destroy a whole run, and Wikidata for works by creators of Polish
citizenship: the Polish pool grew 15,221 -> 20,092.

Batching categories through CirrusSearch looked like a further 6x and was
measured out again: 2,404 files where the authoritative enumeration returns
2,429, a different ~1% missing on every run.

The offline run is 19s where it was four minutes, almost all of it the
deafness gate waiting out three thirty-second liveness probes to prove
something provable in three; the tick is configuration now, and e2e enforces
a 40s budget on itself so that never silently comes back.
2026-08-31 21:32:07 +02:00

169 lines
7.0 KiB
Python

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""The fake Signal server's own behaviour."""
from __future__ import annotations
import base64
import pytest
from fastapi.testclient import TestClient
from fake_signal.server import create_app, default_state
from fake_signal.state import PIXEL_PNG, State
from signal_bot.wolnelektury import parse
@pytest.fixture
def state() -> State:
return State(base_url="http://testserver")
@pytest.fixture
def client(state: State) -> TestClient:
return TestClient(create_app(state))
def test_about_reports_a_websocket_mode(client: TestClient) -> None:
body = client.get("/v1/about").json()
assert body["mode"] == "json-rpc"
def test_qrcodelink_returns_a_png(client: TestClient) -> None:
"""The real endpoint returns an image, which is why the runbook opens it."""
response = client.get("/v1/qrcodelink", params={"device_name": "bot"})
assert response.headers["content-type"] == "image/png"
assert response.headers["X-Device-Name"] == "bot"
assert response.content == PIXEL_PNG
def test_send_is_captured_and_mints_attachment_ids(client: TestClient, state: State) -> None:
client.post("/v2/send", json={"message": "hi", "recipients": ["g"]})
client.post("/v2/send", json={"base64_attachments": ["A"], "recipients": ["g"]})
assert len(state.sent) == 2
assert state.attachments == ["attach-2-0"]
def test_attachments_can_be_listed_and_deleted(client: TestClient) -> None:
client.post("/v2/send", json={"base64_attachments": ["A"], "recipients": ["g"]})
listed = client.get("/v1/attachments").json()
assert listed == ["attach-1-0"]
assert client.delete(f"/v1/attachments/{listed[0]}").status_code == 204
assert client.get("/v1/attachments").json() == []
def test_deleting_an_unknown_attachment_is_a_noop(client: TestClient) -> None:
assert client.delete("/v1/attachments/nope").status_code == 204
def test_reset_clears_captured_state(client: TestClient, state: State) -> None:
client.post("/v2/send", json={"base64_attachments": ["A"], "recipients": ["g"]})
client.post("/_control/reset")
assert state.sent == []
assert state.attachments == []
def test_websocket_subscribes_and_receives_injected_frames(client: TestClient) -> None:
with client.websocket_connect("/v1/receive/+15550000000") as socket:
assert socket.receive_json()["envelope"]["subscribed"] == "+15550000000"
assert client.get("/_control/ready").json() == {"sockets": 1}
assert client.post("/_control/inject", json={"raw": "FRAME"}).json() == {"delivered": 1}
assert socket.receive_text() == "FRAME"
def test_socket_is_forgotten_after_disconnect(client: TestClient) -> None:
with client.websocket_connect("/v1/receive/+1") as socket:
socket.receive_json()
assert client.get("/_control/ready").json() == {"sockets": 0}
def test_inject_with_no_listeners_delivers_nothing(client: TestClient) -> None:
assert client.post("/_control/inject", json={"raw": "x"}).json() == {"delivered": 0}
def test_fixture_apis_mirror_the_real_response_shapes(client: TestClient) -> None:
cat = client.get("/_fixtures/cat-api").json()
dog = client.get("/_fixtures/dog-api").json()
gecko = client.get("/_fixtures/gecko-api").json()
assert cat[0]["url"].endswith("/_fixtures/image.png")
assert dog["message"].endswith("/_fixtures/image.png")
assert gecko["results"][0]["photos"][0]["url"].endswith("/_fixtures/photos/square.png")
commons = client.get("/_fixtures/commons-api", params={"titles": "File:8-St.jpg"}).json()
page = commons["query"]["pages"][0]
# thumburl only, never url: the bot must ask for a bounded thumbnail.
# One committed portrait is 37 MB, which is not a Signal attachment.
assert page["imageinfo"][0]["thumburl"].endswith("/_fixtures/image.png")
assert "url" not in page["imageinfo"][0]
assert page["title"] == "File:8-St.jpg"
poem = client.get("/_fixtures/poem-text", params={"slug": "impas"})
# Wolne Lektury serves text/plain in a fixed shape, and poem_command
# refuses anything without the public-domain sentence -- so the fixture
# has to carry it or !wiersz answers nothing and the scenario would fail
# for a reason that looks like the bot's fault.
assert poem.headers["content-type"].startswith("text/plain")
parsed = parse(poem.text)
assert parsed is not None
# The slug is echoed back as the title, so a scenario proves the bot
# asked for the poem it drew rather than a hard-coded one.
assert parsed.title == "impas"
assert parsed.author == "Adam Testowy"
assert "linijka wiersza" in parsed.text
assert client.get("/_fixtures/image.png").content == PIXEL_PNG
# The square URL is deliberately absent: the bot must rewrite it.
assert client.get("/_fixtures/photos/large.png").content == PIXEL_PNG
assert client.get("/_fixtures/photos/square.png").status_code == 404
def test_create_app_makes_its_own_state_when_none_given() -> None:
with TestClient(create_app()) as client:
assert client.get("/v1/about").status_code == 200
def test_default_state_reads_the_port_from_the_environment(
monkeypatch: pytest.MonkeyPatch,
) -> None:
monkeypatch.setenv("FAKE_PORT", "9123")
assert default_state().base_url.endswith(":9123")
def test_control_sent_exposes_captured_payloads(client: TestClient) -> None:
client.post("/v2/send", json={"message": "hi", "recipients": ["R=="]})
assert client.get("/_control/sent").json() == [{"message": "hi", "recipients": ["R=="]}]
def test_an_inbound_attachment_can_be_stored_and_fetched(client: TestClient) -> None:
"""Without this the fake could name an attachment but never hand it over."""
payload = b"\xff\xd8\xffphoto"
stored = client.post(
"/_control/attachment",
json={"id": "att-1", "base64": base64.b64encode(payload).decode("ascii")},
)
assert stored.status_code == 200
assert client.get("/_control/attachments").json() == ["att-1"]
assert client.get("/v1/attachments/att-1").content == payload
assert client.get("/v1/attachments").json() == ["att-1"]
def test_fetching_an_attachment_that_is_not_there_is_a_404(client: TestClient) -> None:
assert client.get("/v1/attachments/nope").status_code == 404
def test_deleting_an_attachment_takes_its_bytes_too(client: TestClient) -> None:
""" "The second copy is gone" has to be assertable, not assumed."""
client.post(
"/_control/attachment",
json={"id": "att-1", "base64": base64.b64encode(b"\xff\xd8\xffx").decode("ascii")},
)
assert client.delete("/v1/attachments/att-1").status_code == 204
assert client.get("/_control/attachments").json() == []
assert client.get("/v1/attachments/att-1").status_code == 404
def test_uploading_the_same_id_twice_does_not_duplicate_the_listing(
client: TestClient,
) -> None:
body = {"id": "att-1", "base64": base64.b64encode(b"\xff\xd8\xffx").decode("ascii")}
client.post("/_control/attachment", json=body)
client.post("/_control/attachment", json=body)
assert client.get("/v1/attachments").json() == ["att-1"]