feat: add dataset checkpoint sync for MCP

tests/test_dataset_versions.py

@@ -0,0 +1,88 @@
+from datetime import datetime, timezone
+
+from app.models import Employee
+from app.services.dataset_versions import get_or_create_current_version, sync_employees_payload
+
+
+def _employee(profile_key: str, checksum: str, *, status: str = "active") -> Employee:
+    return Employee(
+        profile_key=profile_key,
+        profile_type=profile_key.split(":", 1)[0],
+        profile_id=profile_key.split(":", 1)[1],
+        canonical_url=f"https://www.hse.ru/{profile_key}",
+        full_name=profile_key,
+        status=status,
+        first_seen_at=datetime.now(timezone.utc),
+        last_seen_at=datetime.now(timezone.utc),
+        current_data={"profile_key": profile_key},
+        current_checksum=checksum,
+    )
+
+
+def test_dataset_version_hash_is_stable_for_same_employee_state(db_session):
+    db_session.add(_employee("staff:alpha", "a" * 64))
+    db_session.commit()
+
+    first = get_or_create_current_version(db_session)
+    db_session.commit()
+    second = get_or_create_current_version(db_session)
+
+    assert second.id == first.id
+    assert second.hash == first.hash
+    assert second.employee_count == 1
+
+
+def test_dataset_version_hash_changes_when_employee_checksum_changes(db_session):
+    employee = _employee("staff:alpha", "a" * 64)
+    db_session.add(employee)
+    db_session.commit()
+    first = get_or_create_current_version(db_session)
+    db_session.commit()
+
+    employee.current_checksum = "b" * 64
+    db_session.commit()
+    second = get_or_create_current_version(db_session)
+
+    assert second.hash != first.hash
+    assert second.previous_hash == first.hash
+
+
+def test_sync_employees_diff_spans_multiple_intermediate_versions(db_session):
+    alpha = _employee("staff:alpha", "a" * 64)
+    db_session.add(alpha)
+    db_session.commit()
+    first = get_or_create_current_version(db_session)
+    db_session.commit()
+
+    beta = _employee("staff:beta", "b" * 64)
+    db_session.add(beta)
+    db_session.commit()
+    get_or_create_current_version(db_session)
+    db_session.commit()
+
+    alpha.current_checksum = "c" * 64
+    alpha.current_data = {"profile_key": "staff:alpha", "changed": True}
+    db_session.commit()
+
+    payload = sync_employees_payload(db_session, client_hash=first.hash, include_data=False)
+
+    assert payload["mode"] == "delta"
+    assert [item["profile_key"] for item in payload["changes"]["added"]] == ["staff:beta"]
+    assert [item["profile_key"] for item in payload["changes"]["updated"]] == ["staff:alpha"]
+    assert payload["changes"]["dismissed"] == []
+    assert payload["changes"]["removed"] == []
+
+
+def test_sync_employees_reports_dismissed_as_tombstone(db_session):
+    alpha = _employee("staff:alpha", "a" * 64)
+    db_session.add(alpha)
+    db_session.commit()
+    first = get_or_create_current_version(db_session)
+    db_session.commit()
+
+    alpha.status = "dismissed"
+    db_session.commit()
+    payload = sync_employees_payload(db_session, client_hash=first.hash, include_data=False)
+
+    assert payload["changes"]["dismissed"][0]["profile_key"] == "staff:alpha"
+    assert payload["changes"]["dismissed"][0]["status"] == "dismissed"