Make the system portable: split config from profile, remove hard-coding

Audit found three things compiled in that shouldn't have been: the User-Agent carried the author's domain, the cluster threshold and window were module constants the pipeline never overrode, and the embedding model was pinned -- which blocked the one change most likely to be wanted, swapping in a multilingual model for native-language sources. Configuration is now three files with distinct roles: config.toml (machinery), profile.toml (who the reader is), sources.toml (what to read). All are relocatable via NEWS_CONFIG_DIR. news/*.py now contains no interest, place name, feed URL, or personal identifier. tests/test_config.py keeps it that way: it builds a configuration for an invented reader and asserts none of the author's identity or preferences reaches the running code. Writing it immediately found a real bug -- CONFIG_DIR was resolved at import time, so NEWS_CONFIG_DIR silently did nothing if set after the module was first imported. Now resolved per instantiation. Documented the coupling that portability creates: [clustering].threshold and [scoring].veto_absolute are cosine constants calibrated against one corpus with one model, so changing [embedding].model invalidates both.
2026-09-08 15:31:43 -04:00
1 parent 6dc3694260
commit 863f5e20ac
@@ -0,0 +1,128 @@
+"""Configuration must actually drive behaviour.
+
+The point of these tests is portability: someone who is not the author should be
+able to run this by replacing the TOML files, without editing Python. Each test
+below asserts that a value in config reaches the code that uses it.
+"""
+
+from __future__ import annotations
+
+import textwrap
+
+import numpy as np
+import pytest
+
+from news import cluster, store
+from news.config import Config
+from news.embed import Embedder
+
+
+@pytest.fixture
+def cfgdir(tmp_path, monkeypatch):
+    (tmp_path / "config.toml").write_text(textwrap.dedent("""
+        [http]
+        user_agent = "someone-else/9.9 (+https://elsewhere.example)"
+        timeout_secs = 7
+        concurrency = 3
+        [embedding]
+        model = "intfloat/multilingual-e5-small"
+        dim = 512
+        [clustering]
+        threshold = 0.5
+        window_hours = 6
+        [scoring]
+        veto_absolute = 0.99
+    """))
+    (tmp_path / "sources.toml").write_text(textwrap.dedent("""
+        [defaults]
+        poll_interval_secs = 111
+        [[source]]
+        name = "Someone Else's Feed"
+        url = "https://elsewhere.example/rss"
+        bucket = "elsewhere"
+    """))
+    (tmp_path / "profile.toml").write_text(textwrap.dedent("""
+        [[interest]]
+        id = "trains"
+        weight = 0.4
+        probes = ["Rolling stock procurement and timetable changes."]
+        [delivery]
+        digest_hour = "19:00"
+    """))
+    monkeypatch.setenv("NEWS_CONFIG_DIR", str(tmp_path))
+    return tmp_path
+
+
+def test_no_authors_identity_leaks_into_a_fresh_config(cfgdir):
+    cfg = Config()
+    assert "rcjohnstone" not in cfg.user_agent
+    assert cfg.user_agent.startswith("someone-else/9.9")
+
+
+def test_machinery_values_are_read_from_config(cfgdir):
+    cfg = Config()
+    assert cfg.http["timeout_secs"] == 7
+    assert cfg.http["concurrency"] == 3
+    assert cfg.embedding == {"model": "intfloat/multilingual-e5-small", "dim": 512}
+    assert cfg.clustering == {"threshold": 0.5, "window_hours": 6}
+    assert cfg.scoring["veto_absolute"] == 0.99
+
+
+def test_embedder_takes_its_model_from_config_without_loading_it(cfgdir):
+    """A different reader can swap in a multilingual model from TOML alone."""
+    emb = Embedder.from_config(Config())
+    assert emb._model_name == "intfloat/multilingual-e5-small"
+    assert emb.encode([]).shape == (0, 512)   # honours the configured dim
+
+
+def test_reader_profile_is_entirely_data(cfgdir):
+    cfg = Config()
+    profile = cfg.profile()
+    ids = [b["id"] for b in profile["interest"]]
+    assert ids == ["trains"], "profile content must come only from TOML"
+    assert cfg.delivery["digest_hour"] == "19:00"
+
+
+def test_sources_come_from_config_with_defaults_applied(cfgdir):
+    srcs = Config().sources()
+    assert len(srcs) == 1
+    assert srcs[0]["name"] == "Someone Else's Feed"
+    assert srcs[0]["poll_interval_secs"] == 111     # from [defaults]
+    assert srcs[0]["kind"] == "rss" and srcs[0]["weight"] == 1.0
+
+
+def test_configured_cluster_threshold_changes_the_outcome(tmp_path):
+    """The calibrated 0.82 is a default, not a law: config must override it."""
+    con = store.connect(tmp_path / "t.db")
+    store.upsert_source(con, id="s1", name="A", url="http://a", kind="rss",
+                        bucket="a", weight=1.0, prominence=0, enabled=1,
+                        poll_interval_secs=900)
+
+    def add(i, when):
+        con.execute(
+            """INSERT INTO items (id,source_id,title,summary,url,canonical_url,
+                                  published_at,first_seen_at,content_hash)
+               VALUES (?,?,?,'',?,?,?,?,?)""",
+            (i, "s1", i, f"http://x/{i}", f"http://x/{i}", when, when, i))
+        return con.execute("SELECT * FROM items WHERE id=?", (i,)).fetchone()
+
+    rows = [add("i1", "2026-01-01T00:00:00+00:00"), add("i2", "2026-01-01T01:00:00+00:00")]
+    a, b = np.array([1, 0], np.float32), np.array([0.6, 0.8], np.float32)  # cosine 0.6
+    vecs = {"i1": a, "i2": b}
+
+    strict = cluster.assign(con, rows, vecs, threshold=0.9)
+    assert strict[0].cluster_id != strict[1].cluster_id
+
+    con2 = store.connect(tmp_path / "t2.db")
+    store.upsert_source(con2, id="s1", name="A", url="http://a", kind="rss",
+                        bucket="a", weight=1.0, prominence=0, enabled=1,
+                        poll_interval_secs=900)
+    for i, when in (("i1", "2026-01-01T00:00:00+00:00"), ("i2", "2026-01-01T01:00:00+00:00")):
+        con2.execute(
+            """INSERT INTO items (id,source_id,title,summary,url,canonical_url,
+                                  published_at,first_seen_at,content_hash)
+               VALUES (?,?,?,'',?,?,?,?,?)""",
+            (i, "s1", i, f"http://x/{i}", f"http://x/{i}", when, when, i))
+    rows2 = con2.execute("SELECT * FROM items ORDER BY published_at").fetchall()
+    loose = cluster.assign(con2, list(rows2), vecs, threshold=0.5)
+    assert loose[0].cluster_id == loose[1].cluster_id