news/tests/test_delivery.py

"""Delivery: ntfy actions, the feedback endpoint, and the digest page.

The feedback endpoint is the most important route in the system -- it is the
only way the taste model ever learns. The old system collected 32 labels in a
week because it did not work.
"""

from __future__ import annotations

import os
from datetime import UTC, datetime

import pytest
from starlette.testclient import TestClient

from news import store
from news.digest import _extract_json_object, push_summary
from news.notify import NtfyConfig, build_actions, missing_button_reason, sign, verify

SECRET = "test-secret"


# --------------------------------------------------------------- signing ----

def test_token_is_scoped_to_one_cluster_and_one_kind():
    """A leaked URL must authorise one vote on one story, not act as a bearer
    token for the whole model."""
    t = sign(SECRET, "c1", "interested")
    assert verify(SECRET, "c1", "interested", t)
    assert not verify(SECRET, "c1", "not_interested", t)
    assert not verify(SECRET, "c2", "interested", t)
    assert not verify("other-secret", "c1", "interested", t)


def test_verify_rejects_empty_and_none_tokens():
    assert not verify(SECRET, "c1", "interested", "")
    assert not verify(SECRET, "c1", "interested", None)


# ---------------------------------------------------------------- actions ---

def test_buttons_are_built_when_the_api_is_reachable_and_signed():
    cfg = NtfyConfig(url="https://n", topic="t", api_base="https://news.example", secret=SECRET)
    actions = build_actions(cfg, "c1", "https://story")
    assert actions[0].startswith("view, Read, https://story")
    assert any("More like this" in a and "/interested/" in a for a in actions)
    assert any("Less" in a and "/not_interested/" in a for a in actions)
    assert missing_button_reason(cfg) is None


@pytest.mark.parametrize("cfg,needle", [
    (NtfyConfig(url="https://n", topic="t", secret=SECRET), "NEWS_API_BASE_URL"),
    (NtfyConfig(url="https://n", topic="t", api_base="https://x"), "NEWS_FEEDBACK_SECRET"),
])
def test_buttons_are_dropped_loudly_not_silently(cfg, needle):
    """v0.2 dropped them behind one boot WARN and nobody noticed for a week."""
    assert build_actions(cfg, "c1", "https://story") == ["view, Read, https://story"]
    assert needle in missing_button_reason(cfg)


# ----------------------------------------------------------------- digest ---

def test_push_summary_is_short_and_points_elsewhere():
    """The push must never carry the digest: ntfy turns a long message into a
    .md attachment, which is what made the old report unreadable on a phone."""
    stories = [{"headline": "Lead story", "topic": "urbanism"}] + [
        {"headline": f"s{i}", "topic": "space-aerospace"} for i in range(20)]
    title, body = push_summary(stories)
    assert title == "Daily briefing"
    assert body.count("\n") <= 2
    assert len(body) < 300
    assert "20 more" in body


def test_push_summary_handles_an_empty_day():
    title, body = push_summary([])
    assert "No digest" in title


@pytest.mark.parametrize("raw", [
    '{"briefing":"hello"}',
    '```json\n{"briefing":"hello"}\n```',
    'Sure! Here you go: {"briefing":"hello"} — hope that helps',
])
def test_json_survives_code_fences_and_prose(raw):
    assert _extract_json_object(raw)["briefing"] == "hello"


def test_malformed_model_output_raises_rather_than_returning_garbage():
    with pytest.raises(ValueError):
        _extract_json_object("no object here")


# -------------------------------------------------------------------- web ---

@pytest.fixture
def client(tmp_path, monkeypatch):
    monkeypatch.setenv("NEWS_DB", str(tmp_path / "w.db"))
    monkeypatch.setenv("NEWS_FEEDBACK_SECRET", SECRET)
    con = store.connect(tmp_path / "w.db")
    store.upsert_source(con, id="s1", name="BBC", url="http://b", kind="rss", bucket="bbc",
                        weight=1.0, prominence=0, enabled=1, poll_interval_secs=900)
    now = datetime.now(UTC)
    con.execute("""INSERT INTO items (id,source_id,title,summary,url,canonical_url,
                   published_at,first_seen_at,content_hash) VALUES
                   ('i1','s1','Council votes on transit','','http://b/1','http://b/1',?,?,'h')""",
                (now.isoformat(), now.isoformat()))
    con.execute("""INSERT INTO clusters (id,centroid,size,first_seen_at,last_seen_at,lead_item_id)
                   VALUES ('c1',?,1,?,?,'i1')""",
                (store.to_blob(__import__("numpy").zeros(3, dtype="float32")),
                 now.isoformat(), now.isoformat()))
    con.execute("INSERT INTO cluster_members VALUES ('c1','i1',?)", (now.isoformat(),))
    con.execute("""INSERT INTO notification_log (cluster_id,lane,score,created_at)
                   VALUES ('c1','alert:interest',3.0,?)""", (now.isoformat(),))
    con.execute("""INSERT INTO digest_prose (day,briefing,model,created_at)
                   VALUES (?,'The council met.','m',?)""",
                (now.date().isoformat(), now.isoformat()))
    from news import web
    return TestClient(web.app), now


def test_feedback_button_records_a_label(client):
    c, _ = client
    token = sign(SECRET, "c1", "interested")
    r = c.post(f"/api/feedback/c1/interested/{token}")
    assert r.status_code == 200 and r.json()["ok"] is True
    con = store.connect(os.environ["NEWS_DB"])
    row = con.execute("SELECT cluster_id,kind,source FROM feedback").fetchone()
    assert (row["cluster_id"], row["kind"], row["source"]) == ("c1", "interested", "ntfy")


def test_feedback_rejects_a_forged_token(client):
    c, _ = client
    assert c.post("/api/feedback/c1/interested/deadbeef").status_code == 403
    con = store.connect(os.environ["NEWS_DB"])
    assert con.execute("SELECT COUNT(*) n FROM feedback").fetchone()["n"] == 0


def test_feedback_rejects_an_unknown_kind(client):
    c, _ = client
    token = sign(SECRET, "c1", "sideways")
    assert c.post(f"/api/feedback/c1/sideways/{token}").status_code == 400


def test_digest_page_renders_stories_and_briefing(client):
    c, now = client
    r = c.get(f"/digest/{now.date().isoformat()}")
    assert r.status_code == 200
    assert "Council votes on transit" in r.text
    assert "The council met." in r.text
    assert "BBC" in r.text


def test_digest_page_handles_a_day_with_nothing(client):
    c, _ = client
    r = c.get("/digest/2020-01-01")
    assert r.status_code == 200 and "Nothing cleared the bar" in r.text


def test_bad_date_is_rejected(client):
    c, _ = client
    assert c.get("/digest/not-a-date").status_code == 400