Files
jobboard/tests/test_extract.py
T
WolfandClaude Fable 5.1 7db77e83a3 Extract is bounded to the ranking: pull → embed → score → extract → score → summarise
The free stages run first and their score bounds the two model stages.
Extract reads only the best extract.per_agent roles of each agent at
extract.min_score or more, then score runs again so the gates read what it
filled; summarise gets a min_score of its own. The cascade steps by
position, since score is in it twice.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 15:26:58 +02:00

210 lines
8.8 KiB
Python

"""The `extract` task, with the model call stubbed: what is offered, what an
answer writes, and what it may not touch. Nothing here reaches a model."""
from __future__ import annotations
from datetime import UTC, datetime
from pathlib import Path
from typing import Any
import pytest
from desk import modeltask
from desk.models import Item
from desk.tools import agent
from app.config import Config
from app.jobs import extract
from app.storage import Store
def posting(source_id: str, title: str = "Backend Engineer", **raw: object) -> Item:
item = Item(source_id=source_id, location=f"https://boards.example/{source_id}",
title=title, body="We pay 80.000-95.000 EUR. Hybrid in Berlin.",
published_at=datetime(2026, 9, 20, tzinfo=UTC), raw=dict(raw))
item.source = "ats"
return item
def answer(uid: str, **fields: Any) -> dict[str, Any]:
empty: dict[str, Any] = {
"place": "", "country": "", "remote": "", "seniority": "", "salary_min": None,
"salary_max": None, "currency": "", "function": "", "permit": "",
"languages_required": []}
return {"uid": uid, **empty, **fields}
class Model:
"""Stands in for `agent.ask_json`: records what it was asked and hands
back whatever `reply` builds from the batch."""
def __init__(self, reply: Any) -> None:
self.reply = reply
self.asked: list[list[dict[str, Any]]] = []
def __call__(self, settings: Any, **kwargs: Any) -> agent.Reply:
roles = kwargs["question"]["roles"]
self.asked.append(roles)
return agent.Reply(data={"roles": self.reply(roles)}, backend="api")
@pytest.fixture
def store(tmp_path: Path) -> Store:
return Store(tmp_path / "roledesk.db")
@pytest.fixture
def config(tmp_path: Path) -> Config:
return Config(database=str(tmp_path / "roledesk.db"), extract={"enabled": True})
def ranked(store: Store, *items: Item) -> None:
"""Score the roles for one enabled agent, best first, so they are in the
top extract reads. Every role given must already be stored."""
agents = store.agents()
agent_id = agents[0].id if agents else store.save_agent("Backend").id
store.replace_scores(agent_id, [(item.uid, 1.0 - n / 10, "")
for n, item in enumerate(items)])
def stub(monkeypatch: pytest.MonkeyPatch, reply: Any) -> Model:
model = Model(reply)
monkeypatch.setattr(agent, "backend", lambda settings: "api")
monkeypatch.setattr(agent, "ask_json", model)
return model
def test_a_batch_writes_the_columns_and_stamps_extracted_at(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
uid = posting("1").uid
store.upsert_role(posting("1"))
ranked(store, posting("1"))
stub(monkeypatch, lambda roles: [answer(
r["uid"], place="Berlin", country="de", remote="hybrid", seniority="senior",
salary_min=80000, salary_max=95000, currency="eur", function="engineering",
permit="sponsors", languages_required=["EN", "de", "xx-long"]) for r in roles])
result = modeltask.run(extract.TASK, config, store)
role = store.role(uid)
assert role is not None
assert (role.place, role.place_key, role.country, role.remote) == \
("Berlin", "berlin", "DE", "hybrid")
assert (role.seniority, role.function, role.permit) == ("senior", "engineering", "sponsors")
assert (role.salary_min, role.salary_max, role.currency) == (80000, 95000, "EUR")
assert role.languages == ["en", "de"]
assert role.extracted_at is not None
assert result["extracted"] == 1 and result["pending"] == 0
def test_an_empty_answer_never_blanks_and_a_board_field_is_never_replaced(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
item = posting("1", place="Berlin", remote="hybrid", salary_min=70000)
store.upsert_role(item)
ranked(store, item)
stub(monkeypatch, lambda roles: [answer(
r["uid"], place="Munich", remote="", salary_min=None, salary_max=90000,
country="DE") for r in roles])
modeltask.run(extract.TASK, config, store)
role = store.role(item.uid)
assert role is not None
assert (role.place, role.remote, role.salary_min) == ("Berlin", "hybrid", 70000)
assert (role.country, role.salary_max) == ("DE", 90000)
def test_the_next_upsert_keeps_what_extract_filled(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
store.upsert_role(posting("1"))
ranked(store, posting("1"))
stub(monkeypatch, lambda roles: [answer(r["uid"], country="DE", seniority="mid")
for r in roles])
modeltask.run(extract.TASK, config, store)
store.upsert_role(posting("1"))
role = store.role(posting("1").uid)
assert role is not None and (role.country, role.seniority) == ("DE", "mid")
def test_closed_and_answered_roles_are_not_offered(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
for sid in ("open", "closed", "done"):
store.upsert_role(posting(sid))
ranked(store, posting("open"), posting("closed"), posting("done"))
with store.transaction() as conn:
conn.execute("UPDATE roles SET closed_at = '2026-09-22T00:00:00+00:00' "
"WHERE source_id = 'closed'")
conn.execute("UPDATE roles SET extracted_at = '2026-09-22T00:00:00+00:00' "
"WHERE source_id = 'done'")
model = stub(monkeypatch, lambda roles: [answer(r["uid"]) for r in roles])
modeltask.run(extract.TASK, config, store)
assert [[r["uid"] for r in batch] for batch in model.asked] == [[posting("open").uid]]
def test_an_unknown_uid_is_ignored_and_the_role_left_out_is_charged(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
store.upsert_role(posting("1"))
ranked(store, posting("1"))
stub(monkeypatch, lambda roles: [answer("not-in-the-batch", country="DE")])
result = modeltask.run(extract.TASK, config, store)
role = store.role(posting("1").uid)
assert role is not None and role.country == "" and role.extracted_at is None
assert result["rejected"] == ["not-in-the-batch"]
assert store.extract_pending(500) == 1
modeltask.run(extract.TASK, config, store)
modeltask.run(extract.TASK, config, store)
assert store.extract_pending(500) == 0, "given up after three unanswered replies"
def test_only_the_best_of_each_agent_above_the_floor_is_read(
store: Store, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
"""The bound that keeps extract cheap: the top `per_agent` of an enabled
agent's scores at `min_score` or more, whatever the boards produced. A
role nobody ranks is never sent; a batch dealt a uid finishes it."""
for sid in ("best", "second", "low", "unscored", "gated"):
store.upsert_role(posting(sid))
one = store.save_agent("One")
two = store.save_agent("Two", enabled=False)
store.replace_scores(one.id, [(posting("best").uid, 0.9, ""),
(posting("second").uid, 0.8, ""),
(posting("low").uid, 0.2, ""),
(posting("gated").uid, 0.95, "country unknown")])
store.replace_scores(two.id, [(posting("unscored").uid, 0.99, "")])
config = Config(database=str(tmp_path / "x.db"),
extract={"enabled": True, "per_agent": 1, "min_score": 0.5})
model = stub(monkeypatch, lambda roles: [answer(r["uid"]) for r in roles])
assert store.extract_pending(1, 0.5) == 1
assert store.extract_pending(5, 0.5) == 2, "the floor holds the low one back"
assert store.extract_pending(5, 0.0) == 3, "the disabled agent's pick never counts"
modeltask.run(extract.TASK, config, store)
assert [[r["uid"] for r in batch] for batch in model.asked] == [[posting("best").uid]]
assert [r.uid for r in store.extract_waiting(10, 1, 0.5, uids=[posting("low").uid])] == \
[posting("low").uid], "a dealt uid is read whatever its rank"
def test_a_value_outside_the_vocabulary_is_dropped() -> None:
got = extract.fields(answer("u", remote="sometimes", seniority="Senior",
country="Germany", currency="€", function="ops",
permit="maybe", salary_min=-1, salary_max=True))
assert got["remote"] == "" and got["seniority"] == "senior"
assert got["country"] == "" and got["currency"] == "" and got["function"] == ""
assert got["permit"] == "" and got["salary_min"] is None and got["salary_max"] is None
def test_disabled_finds_nothing_and_asks_nobody(
store: Store, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
store.upsert_role(posting("1"))
model = stub(monkeypatch, lambda roles: [])
result = modeltask.run(extract.TASK, Config(database=str(tmp_path / "x.db")), store)
assert model.asked == [] and result["extracted"] == 0