siftlode/backend/tests/test_migration_0109.py

"""Migration 0109's data step, DB-lane: the audit log's run rows move into `job_runs` with their
outcome intact, and leave the audit log; an admin action stays where it was. The downgrade moves
them back."""

import json
from datetime import timedelta

from alembic import command
from alembic.config import Config
from sqlalchemy import text

from app.db import engine


def _audit(conn, actor, action, target, after):
    conn.execute(
        text(
            "INSERT INTO audit_log (actor_id, action, target_type, target_id, summary, after,"
            " created_at) VALUES (:a, :act, 'job', :t, 's', CAST(:after AS json),"
            " CAST('2026-10-01T03:00:00+00:00' AS timestamptz))"
        ),
        {"a": actor, "act": action, "t": target, "after": json.dumps(after)},
    )


def test_the_audit_logs_runs_move_into_the_run_table_and_back(db, make_user):
    uid = make_user().id
    cfg = Config("alembic.ini")
    command.downgrade(cfg, "0108_folder_links")
    try:
        with engine.begin() as conn:
            _audit(
                conn,
                None,
                "job_run",
                "rss_poll",
                {"status": "ok", "summary": "new=3", "result": {"new": 3}},
            )
            _audit(
                conn,
                uid,
                "job_run",
                "rss_poll",
                {"status": "error", "summary": "boom", "result": {"failure": "rss_all_failed"}},
            )
            _audit(
                conn, uid, "job_run", "backfill", {"status": "skipped", "summary": "sync paused"}
            )
            _audit(conn, uid, "config_set", None, {"key": "x"})
    finally:
        command.upgrade(cfg, "head")

    with engine.connect() as conn:
        runs = conn.execute(
            text(
                "SELECT job, trigger, actor_id, status, summary, result, error, failure,"
                " to_char(started_at AT TIME ZONE 'UTC', 'MM-DD HH24'), finished_at = started_at"
                " FROM job_runs ORDER BY id"
            )
        ).all()
        left = conn.execute(text("SELECT action FROM audit_log")).scalars().all()
    assert [tuple(r) for r in runs] == [
        ("rss_poll", "scheduled", None, "ok", "new=3", {"new": 3}, None, None, "10-01 03", True),
        (
            "rss_poll",
            "manual",
            uid,
            "error",
            None,
            None,
            "boom",
            {"failure": "rss_all_failed"},
            "10-01 03",
            True,
        ),
        ("backfill", "manual", uid, "skipped", "sync paused", None, None, None, "10-01 03", True),
    ]
    assert left == ["config_set"]

    command.downgrade(cfg, "0108_folder_links")
    try:
        with engine.connect() as conn:
            back = conn.execute(
                text(
                    "SELECT actor_id, target_id, after::jsonb FROM audit_log"
                    " WHERE action = 'job_run' ORDER BY id"
                )
            ).all()
    finally:
        command.upgrade(cfg, "head")

    # What the audit row has no column for rides along, so the next upgrade restores it.
    def run(trigger: str) -> dict:
        return {"trigger": trigger, "quota_units": 0, "started_at": "2026-10-01T03:00:00+00:00"}

    assert [tuple(r) for r in back] == [
        (
            None,
            "rss_poll",
            {"status": "ok", "summary": "new=3", "result": {"new": 3}, **run("scheduled")},
        ),
        (
            uid,
            "rss_poll",
            {
                "status": "error",
                "summary": "boom",
                "result": {"failure": "rss_all_failed"},
                **run("manual"),
            },
        ),
        (uid, "backfill", {"status": "skipped", "summary": "sync paused", **run("manual")}),
    ]


def test_a_down_and_up_round_trip_keeps_every_run(db, make_user):
    """A rollback then a redeploy: an interrupted run, a run caught mid-way and a user's run of one
    channel come back as runs — not stranded in the audit log under an action no code knows."""
    uid = make_user().id
    with engine.begin() as conn:
        conn.execute(
            text(
                "INSERT INTO job_runs (job, trigger, actor_id, target, status, started_at,"
                " finished_at, quota_units) VALUES"
                " ('backfill', 'scheduled', NULL, NULL, 'interrupted', now(), now(), 0),"
                " ('maintenance', 'manual', :u, NULL, 'running', now(), NULL, 0),"
                " ('channel_backfill', 'ad_hoc', :u, 'UC_x', 'ok', now(), now(), 0),"
                # Its admin is gone (SET NULL): only the row itself still says it was manual.
                " ('enrich', 'manual', NULL, NULL, 'ok',"
                "  '2026-10-01 10:00+00', '2026-10-01 10:30+00', 42)"
            ),
            {"u": uid},
        )
    cfg = Config("alembic.ini")
    command.downgrade(cfg, "0108_folder_links")
    command.upgrade(cfg, "head")
    with engine.connect() as conn:
        runs = conn.execute(
            text("SELECT job, trigger, actor_id, target, status FROM job_runs ORDER BY id")
        ).all()
        kept = conn.execute(
            text("SELECT quota_units, finished_at - started_at FROM job_runs WHERE job = 'enrich'")
        ).one()
        stranded = conn.execute(
            text("SELECT count(*) FROM audit_log WHERE action = 'job_run'")
        ).scalar()
    assert [tuple(r) for r in runs] == [
        ("backfill", "scheduled", None, None, "interrupted"),
        ("maintenance", "manual", uid, None, "interrupted"),  # the rollback stopped it
        ("channel_backfill", "ad_hoc", uid, "UC_x", "ok"),
        ("enrich", "manual", None, None, "ok"),
    ]
    assert tuple(kept) == (42, timedelta(minutes=30))
    assert stranded == 0