Files
FabledCurator/tests/test_gpu_jobs.py
T
bvandeusen b735432d02
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 19s
CI / backend-lint-and-test (push) Successful in 26s
CI / integration (push) Successful in 3m30s
feat(gpu): video-ready regions + the HTTP GPU-job queue engine (#114 slice 3)
Answers "how are videos/all media handled by the GPU worker": a job is per ITEM,
but the agent fans a VIDEO into per-frame instances (ffmpeg in the agent, the
existing cadence), each stored with a timestamp — so a video becomes a BAG of
frame embeddings (fixes the mean-embedding muddle) instead of one washed-out
vector. Stills → frame_time NULL; animated GIF/WebP treated like short video.

- image_region.frame_time (migration 0061, not yet deployed so folded in): the
  source frame's seconds for video/animated media; NULL for stills. RegionService
  passes it through. A whole frame is just kind='frame'.
- gpu_job + GpuJobService (migration 0062): the durable work list that keeps the
  desktop agent HTTP-only — enqueue (dedupes (image,task)) / lease (FOR UPDATE
  SKIP LOCKED, re-claims expired leases so the queue self-heals) / heartbeat /
  complete / fail (re-queues until MAX_ATTEMPTS then 'error'). The server enqueues;
  the agent leases+submits over the web API; Redis/Postgres stay private.

Tests: enqueue dedupe, lease-then-skip-when-held, expired-lease reclaim, scoped
heartbeat, complete, fail-requeue-then-error. region test now covers frame_time.

NEXT: the thin HTTP API (lease/submit/heartbeat) + bearer-token auth, then the
agent container + control UI.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
2026-06-29 11:18:28 -04:00

126 lines
3.9 KiB
Python

"""GPU-job queue engine (#114): enqueue dedupe + lease/heartbeat/complete/fail."""
from datetime import UTC, datetime, timedelta
import pytest
from sqlalchemy import select
from backend.app.models import GpuJob, ImageRecord
from backend.app.services.ml.gpu_jobs import GpuJobService
pytestmark = pytest.mark.integration
async def _img(db, sha) -> ImageRecord:
img = ImageRecord(
path=f"/images/{sha}.jpg", sha256=sha, size_bytes=1, mime="image/jpeg",
width=1, height=1, origin="imported_filesystem", integrity_status="unknown",
)
db.add(img)
await db.flush()
return img
@pytest.mark.asyncio
async def test_enqueue_dedupes_same_pair(db):
img = await _img(db, "a" * 64)
svc = GpuJobService(db)
first = await svc.enqueue(img.id, "ccip")
dup = await svc.enqueue(img.id, "ccip")
other = await svc.enqueue(img.id, "siglip_region")
await db.commit()
assert first is not None
assert dup is None # same (image, task) already queued
assert other is not None # different task is fine
@pytest.mark.asyncio
async def test_lease_claims_then_skips_when_held(db):
img = await _img(db, "b" * 64)
svc = GpuJobService(db)
await svc.enqueue(img.id, "ccip")
await db.commit()
leased = await svc.lease("agent-1", batch_size=8)
await db.commit()
assert len(leased) == 1
assert leased[0].status == "leased" and leased[0].lease_token == "agent-1"
assert leased[0].attempts == 1
# Already leased + not expired → a second agent gets nothing.
again = await svc.lease("agent-2", batch_size=8)
await db.commit()
assert again == []
@pytest.mark.asyncio
async def test_expired_lease_is_reclaimed(db):
img = await _img(db, "c" * 64)
svc = GpuJobService(db)
job = await svc.enqueue(img.id, "ccip")
await db.commit()
# Force the lease into the past.
job.status = "leased"
job.lease_token = "dead-agent"
job.lease_expires_at = datetime.now(UTC) - timedelta(minutes=10)
await db.commit()
leased = await svc.lease("agent-2", batch_size=8)
await db.commit()
assert len(leased) == 1
assert leased[0].lease_token == "agent-2"
assert leased[0].attempts == 1 # re-lease incremented from 0 (was set directly)
@pytest.mark.asyncio
async def test_heartbeat_extends_only_own_lease(db):
img = await _img(db, "d" * 64)
svc = GpuJobService(db)
await svc.enqueue(img.id, "ccip")
await db.commit()
job = (await svc.lease("agent-1"))[0]
await db.commit()
assert await svc.heartbeat("agent-1", [job.id]) == 1
assert await svc.heartbeat("someone-else", [job.id]) == 0
@pytest.mark.asyncio
async def test_complete_closes_job(db):
img = await _img(db, "e" * 64)
svc = GpuJobService(db)
await svc.enqueue(img.id, "ccip")
await db.commit()
job = (await svc.lease("agent-1"))[0]
await db.commit()
assert await svc.complete("wrong-token", job.id) is False
assert await svc.complete("agent-1", job.id) is True
await db.commit()
fresh = await db.get(GpuJob, job.id)
assert fresh.status == "done" and fresh.lease_token is None
@pytest.mark.asyncio
async def test_fail_requeues_until_cap(db):
img = await _img(db, "f" * 64)
svc = GpuJobService(db)
await svc.enqueue(img.id, "ccip")
await db.commit()
job = (await svc.lease("agent-1"))[0] # attempts -> 1
await db.commit()
# Under the cap → back to pending for a retry.
assert await svc.fail("agent-1", job.id, "boom") is True
await db.commit()
assert (await db.get(GpuJob, job.id)).status == "pending"
# At the attempt cap → terminal 'error'.
j = await db.get(GpuJob, job.id)
j.attempts = 3
j.status = "leased"
j.lease_token = "agent-1"
j.lease_expires_at = datetime.now(UTC) + timedelta(minutes=5)
await db.commit()
assert await svc.fail("agent-1", job.id, "boom again") is True
await db.commit()
assert (await db.get(GpuJob, job.id)).status == "error"