Files
jobboard/tests/test_extract.py
T
WolfandClaude Opus 5.5 d04ceae7e0 Prep stage: host words stored raw, mapped centrally in app/prep after every pull
upsert_role stores the host's own words (roles.*_host), the place texts
unresolved when they change, and the company key unresolved on insert, and
marks the role prep_due. app.prep maps seniority, employment, remote and
country through the host tables in app/prep/hosts, resolves places and
company aliases, lists unknown words in `unmapped`, remaps every open role
when the tables' fingerprint changes, and runs rebuild_dupes, which moves
out of the pull's settle. Migration 22 adds the columns and the table and
fills the host words from raw. Cascade: pull, prep, embed, score, enrich,
prep, embed, score, extract, score, summarise. `app prep [unmapped]
[--remap]`, /api/prep/unmapped and a fold on the Sources page.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 11:19:22 +02:00

312 lines
13 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.models import Limits
from app.storage import Store
from prepped import upsert
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", "python 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
upsert(store, 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)
upsert(store, 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:
upsert(store, 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)
upsert(store, 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"):
upsert(store, 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', "
"seniority_model = 'senior' 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:
upsert(store, 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() == 1
modeltask.run(extract.TASK, config, store)
modeltask.run(extract.TASK, config, store)
assert store.extract_pending() == 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 of an enabled agent's
scores, as deep and as low as that agent's own `limits` say, 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"):
upsert(store, posting(sid))
one = store.save_agent("One", "python backend",
limits=Limits(extract_top=1, extract_min=0.5))
two = store.save_agent("Two", "python backend", 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})
model = stub(monkeypatch, lambda roles: [answer(r["uid"]) for r in roles])
assert store.extract_pending() == 1
store.save_agent("One", "python backend", agent_id=one.id,
limits=Limits(extract_top=5, extract_min=0.5))
assert store.extract_pending() == 2, "the floor holds the low one back"
store.save_agent("One", "python backend", agent_id=one.id,
limits=Limits(extract_top=5, extract_min=0))
assert store.extract_pending() == 3, "the disabled agent's pick never counts"
store.save_agent("One", "python backend", agent_id=one.id,
limits=Limits(extract_top=1, extract_min=0.5))
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, 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:
upsert(store, 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
def test_a_role_read_before_without_a_level_is_read_again_for_it(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
item = posting("1", seniority="senior")
upsert(store, item)
ranked(store, item)
with store.transaction() as conn:
conn.execute("UPDATE roles SET extracted_at = '2026-09-22T00:00:00+00:00', "
"country = 'DE' WHERE source_id = '1'")
stub(monkeypatch, lambda roles: [answer(r["uid"], country="FR", seniority="staff")
for r in roles])
modeltask.run(extract.TASK, config, store)
role = store.role(item.uid)
assert role is not None
assert (role.seniority_model, role.seniority) == ("staff", "staff")
assert role.seniority_stated == "senior", "the host's word stays beside the model's"
assert role.country == "DE", "the other fields still only fill what is empty"
assert store.extract_pending() == 0
def test_the_prompt_carries_the_hints_and_the_teaser_when_there_is_no_text(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
withtext = posting("text", title="Senior Engineer", seniority="mid")
noText = posting("teaser", title="Analyst")
noText.body = ""
upsert(store, withtext)
upsert(store, noText)
with store.transaction() as conn:
conn.execute("UPDATE roles SET teaser = 'Join our analytics team' "
"WHERE source_id = 'teaser'")
ranked(store, withtext, noText)
model = stub(monkeypatch, lambda roles: [answer(r["uid"], seniority="mid") for r in roles])
modeltask.run(extract.TASK, config, store)
asked = {r["uid"]: r for batch in model.asked for r in batch}
one, two = asked[withtext.uid], asked[noText.uid]
assert (one["stated"], one["title_level"]) == ("mid", "senior") and "teaser" not in one
assert two["teaser"] == "Join our analytics team" and "text" not in two
assert "stated" not in two and "overrule" in extract.SYSTEM
schema = extract.SCHEMA["properties"]["roles"]["items"]["properties"]["seniority"]
assert "" not in schema["enum"], "the afterburner must pick a level"
def test_an_answer_with_no_level_is_charged_until_given_up(
store: Store, config: Config, monkeypatch: pytest.MonkeyPatch) -> None:
item = posting("1")
upsert(store, item)
ranked(store, item)
stub(monkeypatch, lambda roles: [answer(r["uid"], seniority="") for r in roles])
modeltask.run(extract.TASK, config, store)
assert store.extract_pending() == 1, "answered without a level: still waiting"
modeltask.run(extract.TASK, config, store)
modeltask.run(extract.TASK, config, store)
assert store.extract_pending() == 0
def test_each_agents_best_come_first_then_the_rest(store: Store) -> None:
items = [posting(s) for s in ("a1", "a2", "a3", "b1")]
for item in items:
upsert(store, item)
one = store.save_agent("One", "python backend")
two = store.save_agent("Two", "python backend")
store.replace_scores(one.id, [(items[0].uid, 0.9, ""), (items[1].uid, 0.8, ""),
(items[2].uid, 0.7, "")])
store.replace_scores(two.id, [(items[3].uid, 0.6, "")])
got = [r.uid for r in store.extract_waiting(10)]
assert got == [items[0].uid, items[3].uid, items[1].uid, items[2].uid]
def test_agreement_per_host(store: Store) -> None:
for sid, board, stated, model in [
("1", "personio", "senior", "senior"), ("2", "personio", "junior", "mid"),
("3", "lever", "mid", "mid"), ("4", "lever", "", "senior"),
("5", "lever", "senior", "")]:
upsert(store, posting(sid, board=board, seniority=stated))
with store.transaction() as conn:
conn.execute("UPDATE roles SET seniority_model = ? WHERE source_id = ?",
(model, sid))
got = {h["host"]: h for h in store.seniority_agreement()}
assert (got["personio"]["compared"], got["personio"]["agreed"], got["personio"]["rate"]) \
== (2, 1, 0.5)
assert (got["lever"]["compared"], got["lever"]["rate"], got["lever"]["stated_only"]) \
== (1, 1.0, 1)
assert [h["host"] for h in store.seniority_agreement()] == ["personio", "lever"]