app/backend/tests/test_artifacts.py

import os
import time
from datetime import UTC, datetime

import pytest
from fastapi.testclient import TestClient
from sqlmodel import Session, col, select

from fluksio.core.config import settings

from fluksio.core.db import engine as db_engine
from fluksio.flow.artifacts import ArtifactStore, VolatileStore
from fluksio.flow.runs import new_run_id, sweep_artifacts
from fluksio.flow.state import MemoryState
from fluksio.models import Run, RunArtifact


@pytest.fixture
def store(tmp_path) -> ArtifactStore:
    return ArtifactStore(tmp_path / "artifacts")


def _run_row(status: str, digest: str = "") -> str:
    """A run, and optionally the artifact it recorded. Returns its id."""
    run_id = new_run_id()
    with Session(db_engine) as session:
        session.add(
            Run(id=run_id, flow="f", status=status, created_at=datetime.now(UTC))
        )
        if digest:
            session.add(
                RunArtifact(
                    run_id=run_id,
                    name="f.out",
                    node="n",
                    digest=digest,
                    size=3,
                )
            )
        session.commit()
    return run_id


def _forget(run_id: str) -> None:
    with Session(db_engine) as session:
        rows = session.exec(
            select(RunArtifact).where(col(RunArtifact.run_id) == run_id)
        ).all()
        for row in rows:
            session.delete(row)
        session.delete(session.get(Run, run_id))
        session.commit()


def test_the_grace_window_spares_a_fresh_artifact(store):
    ref = store.put([b"new"])
    assert store.collect(set(), grace_s=3600) == 0
    assert store.path(ref["digest"]) is not None
    assert store.collect(set(), grace_s=0) == 1
    assert store.path(ref["digest"]) is None


def test_a_sweep_keeps_what_a_run_recorded_and_what_a_message_holds(store):
    recorded = store.put([b"kept by a run"])
    held = store.put([b"kept by a message"])
    nested = store.put([b"kept inside a payload"])
    orphan = store.put([b"referred to by nothing"])

    run_id = _run_row("ok", recorded["digest"])
    state = MemoryState()
    state.update(
        {
            "cam.frame": held,
            # A reference inside a json payload counts as much as a bare one.
            "cam.report": {"latest": {"clip": nested}},
            "cam.count": 3,
        }
    )

    try:
        assert sweep_artifacts(store, state) == 1
    finally:
        _forget(run_id)

    assert store.path(orphan["digest"]) is None
    for kept in (recorded, held, nested):
        assert store.path(kept["digest"]) is not None


def test_a_sweep_stands_aside_while_a_run_is_in_flight(store):
    orphan = store.put([b"mid-run checkpoint"])
    run_id = _run_row("running")
    try:
        assert sweep_artifacts(store, MemoryState()) == 0
    finally:
        _forget(run_id)
    assert store.path(orphan["digest"]) is not None


def test_a_streamed_chunk_falls_out_once_the_message_moves_on(store):
    """What makes a media stream affordable: only the current frame is held."""
    state = MemoryState()
    first = store.put([b"frame one"], media_type="image/png")
    state.update({"cam.frame": first})
    assert sweep_artifacts(store, state) == 0

    second = store.put([b"frame two"], media_type="image/png")
    state.update({"cam.frame": second})
    # Old enough to be swept: the sweep only spares what grace covers.
    os.utime(store.path(first["digest"]), (time.time() - 10, time.time() - 10))
    assert sweep_artifacts(store, state, grace_s=5) == 1
    assert store.path(first["digest"]) is None
    assert store.path(second["digest"]) is not None


def test_a_ring_drops_the_oldest_once_it_is_full(tmp_path):
    """What makes a camera affordable: the room is fixed, not the history."""
    ring = VolatileStore(tmp_path / "ring", limit_bytes=3000)
    refs = [ring.put([bytes([i]) * 1000], name=f"{i}.bin") for i in range(5)]

    held = [ref for ref in refs if ring.path(ref["digest"]) is not None]
    assert len(held) == 3
    # The newest three, in order: eviction is by age, not by chance.
    assert held == refs[2:]


def test_a_volatile_reference_resolves_like_any_other(tmp_path):
    """A frame is an ordinary reference, which is what keeps the rest honest.

    Everything that resolves a digest — serving one, checking a run's input,
    a panel's scope — goes through ``path``, so the ring has to answer there.
    """
    store = ArtifactStore(tmp_path / "artifacts")
    store.volatile = VolatileStore(tmp_path / "ring", limit_bytes=1_000_000)

    ref = store.put([b"frame"], name="f.png", media_type="image/png", volatile=True)

    assert store.path(ref["digest"]) is not None
    # In the ring, and not on the volume the sweep is about.
    assert not (store.root / ref["digest"][7:9]).exists()


def test_a_recorded_frame_is_copied_out_of_the_ring(tmp_path):
    """Emitted media is not kept; returned media is."""
    store = ArtifactStore(tmp_path / "artifacts")
    store.volatile = VolatileStore(tmp_path / "ring", limit_bytes=1_000_000)
    ref = store.put([b"kept"], name="f.png", volatile=True)

    assert store.adopt(ref["digest"]) is True

    store.volatile.collect(set())
    assert store.path(ref["digest"]) is not None
    assert store.adopt("sha256:" + "0" * 64) is False


def test_an_upload_may_ask_for_the_ring(
    client: TestClient, superuser_token_headers: dict[str, str]
) -> None:
    """A camera on another host publishes over HTTP and wants the ring too."""
    store = client.app.state.artifact_store
    previous = store.volatile
    store.volatile = VolatileStore(
        store.root.parent / "test-ring", limit_bytes=1_000_000
    )
    try:
        url = f"{settings.API_V1_STR}/artifacts"
        answer = client.put(
            f"{url}?name=f.png&media_type=image%2Fpng&volatile=1",
            headers=superuser_token_headers,
            content=b"\x89PNG-frame",
        )
        assert answer.status_code == 200, answer.text
        digest = answer.json()["digest"]

        assert store.volatile.path(digest) is not None
        assert not (store.root / digest[7:9]).exists()
        # And it is served back like anything else, which is what the widget
        # falls back on when the socket did not push it.
        served = client.get(f"{url}/{digest}", headers=superuser_token_headers)
        assert served.status_code == 200
        assert served.content == b"\x89PNG-frame"
    finally:
        store.volatile = previous