resume-agent/backend/tests/test_session_identity_lookup.py

from __future__ import annotations

from datetime import UTC, datetime
import os
from pathlib import Path
from typing import Any
from uuid import uuid4

import pytest
from sqlalchemy import create_engine, text, update

from app.database import Database
from app.postgres_database import PostgresDatabase


_INITIAL_TURN = {
    "role": "assistant",
    "content": None,
    "composer_mode": "ui_only",
    "blocks": [],
}
_TARGET_USER_ID = "2081575100391407617"


def _profile(
    user_id: str | None = _TARGET_USER_ID, *, provider: str = "offerpai"
) -> dict[str, Any]:
    if user_id is None:
        return {}
    return {
        "external_account": {
            "provider": provider,
            "user_id": user_id,
        }
    }


def _session_cases() -> list[tuple[str, dict[str, Any], datetime, datetime]]:
    first = datetime(2026, 1, 1, tzinfo=UTC)
    second = datetime(2026, 1, 2, tzinfo=UTC)
    latest = datetime(2026, 1, 3, tzinfo=UTC)
    excluded_latest = datetime(2026, 1, 4, tzinfo=UTC)
    return [
        ("session-old", _profile(), first, first),
        # updated_at wins first; created_at then beats this lexically larger id.
        ("session-z-created-old", _profile(), first, latest),
        ("session-a", _profile(), second, latest),
        # Same timestamps as session-a: id is the final deterministic tie-breaker.
        ("session-c", _profile(), second, latest),
        (
            "session-other-provider",
            _profile(provider="another-provider"),
            excluded_latest,
            excluded_latest,
        ),
        (
            "session-other-user",
            _profile("another-user"),
            excluded_latest,
            excluded_latest,
        ),
        ("session-anonymous", _profile(None), excluded_latest, excluded_latest),
    ]


def _create_sessions(database: Any) -> None:
    for session_id, profile, _created_at, _updated_at in _session_cases():
        database.create_session(
            session_id,
            "PRIVACY_CONSENT",
            profile,
            _INITIAL_TURN,
        )


def test_sqlite_finds_latest_offerpai_session_with_deterministic_order(
    tmp_path: Path,
) -> None:
    database = Database(tmp_path / "identity-lookup.db")
    database.initialize()
    _create_sessions(database)
    with database.transaction(immediate=True) as connection:
        for session_id, _profile_value, created_at, updated_at in _session_cases():
            connection.execute(
                "UPDATE sessions SET created_at = ?, updated_at = ? WHERE id = ?",
                (created_at.isoformat(), updated_at.isoformat(), session_id),
            )

    found = database.find_latest_session_by_external_user_id(
        f"  {_TARGET_USER_ID}\t"
    )

    assert found is not None
    assert found["id"] == "session-c"
    assert database.find_latest_session_by_external_user_id("missing-user") is None


def test_sqlite_ignores_blank_external_user_id(tmp_path: Path) -> None:
    database = Database(tmp_path / "identity-lookup-blank.db")
    database.initialize()

    for external_user_id in ("", " ", "\t\r\n"):
        assert database.find_latest_session_by_external_user_id(external_user_id) is None


@pytest.fixture
def postgres_database() -> Any:
    database_url = os.environ["RESUME_AGENT_TEST_DATABASE_URL"]
    schema = f"test_session_identity_{uuid4().hex}"
    database = PostgresDatabase(database_url, schema=schema)
    database.initialize()
    try:
        yield database
    finally:
        database.engine.dispose()
        cleanup_engine = create_engine(database_url)
        try:
            with cleanup_engine.begin() as connection:
                connection.execute(text(f'DROP SCHEMA IF EXISTS "{schema}" CASCADE'))
        finally:
            cleanup_engine.dispose()


def test_postgres_finds_latest_offerpai_session_with_deterministic_order(
    postgres_database: PostgresDatabase,
) -> None:
    _create_sessions(postgres_database)
    sessions = postgres_database.tables["sessions"]
    with postgres_database.transaction() as connection:
        for session_id, _profile_value, created_at, updated_at in _session_cases():
            connection.execute(
                update(sessions)
                .where(sessions.c.id == session_id)
                .values(created_at=created_at, updated_at=updated_at)
            )

    found = postgres_database.find_latest_session_by_external_user_id(
        f"  {_TARGET_USER_ID}\t"
    )

    assert found is not None
    assert found["id"] == "session-c"
    assert (
        postgres_database.find_latest_session_by_external_user_id("missing-user")
        is None
    )


def test_postgres_ignores_blank_external_user_id(
    postgres_database: PostgresDatabase,
) -> None:
    for external_user_id in ("", " ", "\t\r\n"):
        assert (
            postgres_database.find_latest_session_by_external_user_id(
                external_user_id
            )
            is None
        )