Files
upbeatBytes/tests/test_api.py
T
thejayman77 a47a1504c8 Phase B1: multi-tag groupings model (backend)
Three-layer organization: primary topic (one per article, for ranking and
brief balance) + grouping tags (1-4 per article from a controlled vocabulary,
the organic "wandering" axis) + tonal flavor.

- taxonomy: add technology + learning topics; 4 calm tag families
  (Discovery & Wonder, People & Kindness, Solutions & Progress, Mind & Craft)
  defined in code, not the DB; ALLOWED_TAGS union + coerce_tags validation.
- db: article_tags(article_id, tag) join table + tag index.
- llm: tags added to the classifier json_schema (enum-constrained, maxItems 4)
  and system prompt; normalize_scores coerces tags; upsert_article_score
  replaces a row's tags atomically on every (re)classification.
- queries: feed gains a tag filter and exposes tags via group_concat; tag_counts.
- api: Article.tags, feed tag param, and /api/families with per-tag counts.
- tests: coerce/normalize/upsert/tag-filter/reclassify-replace/tag_counts +
  /api/families. 99 passing.

Corpus reclassify (re-tag + new primary topics) runs separately against the
local LLM. Frontend (B2) pairs with this; the live site is unchanged until then.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 18:35:25 +00:00

90 lines
3.1 KiB
Python

import json
import pytest
from fastapi.testclient import TestClient
from goodnews.db import connect, init_db
@pytest.fixture
def client(tmp_path, monkeypatch):
db = tmp_path / "test.sqlite3"
monkeypatch.setenv("GOODNEWS_DB", str(db))
conn = connect(db)
init_db(conn)
conn.execute("INSERT INTO sources (id, name, feed_url, trust_score) VALUES (1,'S','http://s/f',7)")
def add(aid, topic, flavor, title):
conn.execute(
"INSERT INTO articles (id, source_id, canonical_url, title, published_at, url_hash) "
"VALUES (?,1,?,?, '2026-05-30T10:00:00+00:00', ?)",
(aid, f"http://s/{aid}", title, f"h{aid}"),
)
conn.execute(
"INSERT INTO article_scores (article_id, constructive_score, agency_score, "
"human_benefit_score, cortisol_score, ragebait_score, pr_risk_score, accepted, topic, flavor) "
"VALUES (?, 7, 3, 4, 1, 0, 2, 1, ?, ?)",
(aid, topic, flavor),
)
add(1, "science", "discovery", "A quiet science discovery")
add(2, "health", "breakthrough", "Election season health update") # has avoid-able term
conn.execute("INSERT INTO daily_briefs (id, brief_date, title) VALUES (1,'2026-05-30','Brief')")
conn.execute("INSERT INTO daily_brief_items (brief_id, article_id, rank) VALUES (1,1,1),(1,2,2)")
conn.commit()
conn.close()
# Import after env is set so the app reads the temp DB.
from goodnews.api import create_app
return TestClient(create_app())
def _prefs(client, **kw):
return client.get("/api/feed", params={"prefs": json.dumps(kw)})
def test_bad_prefs_returns_200_and_full_feed(client):
r = client.get("/api/feed", params={"prefs": "not json at all"})
assert r.status_code == 200
assert r.json()["count"] == 2 # forgiving: bad blob ignored
def test_mute_topic_affects_feed(client):
r = _prefs(client, mute_topics=["science"])
topics = [i["topic"] for i in r.json()["items"]]
assert topics == ["health"]
def test_avoid_term_filters_feed(client):
r = _prefs(client, avoid_terms=["election"])
titles = [i["title"] for i in r.json()["items"]]
assert all("election" not in t.lower() for t in titles)
assert len(titles) == 1
def test_brief_filters_down_without_refill(client):
full = client.get("/api/brief").json()
assert len(full["items"]) == 2
muted = client.get("/api/brief", params={"prefs": json.dumps({"mute_topics": ["health"]})}).json()
assert [i["topic"] for i in muted["items"]] == ["science"]
def test_category_counts_match_filtered_feed(client):
counts = client.get("/api/category-counts", params={"prefs": json.dumps({"mute_topics": ["health"]})}).json()
assert all(c["topic"] != "health" for c in counts)
def test_feed_excludes_dismissed(client):
r = client.get("/api/feed", params={"exclude": "1"})
ids = [i["id"] for i in r.json()["items"]]
assert 1 not in ids
def test_families_endpoint(client):
fams = client.get("/api/families").json()
names = [f["name"] for f in fams]
assert "Discovery & Wonder" in names
assert all("tags" in f and isinstance(f["tags"], list) for f in fams)