bvandeusen
c6f38b0dac
Lift recall on small/local concepts (glasses, cum, stomach-bulge, xray, lactation) that the whole-image SigLIP vector washes out: the GPU agent now embeds figure crops with SigLIP too, stored as kind='concept' regions, and the suggestion rail scores each image as a BAG (whole-image + every concept crop), taking each head's MAX over the bag. The whole-image vector is always in the bag, so this can never score lower than before. Model-agnostic by construction: the server ANNOUNCES the embedding model (HF name + version) in the lease, so the agent loads whatever the heads were trained in and stays in lock-step — a model swap is a server setting + a re-embed migration, never an agent change. - agent: model-agnostic CropEmbedder (torch/transformers get_image_features, fp16 on CUDA, inference-locked); worker branches on job.task — 'ccip' emits figure(CCIP)+concept(SigLIP) in one pass, 'siglip' emits concept-only so the back-catalogue backfill never churns figure/CCIP regions; torch cu124 + transformers in the image. - server: lease announces embed_model_name/embed_version; score_image is max-over-bag (version-filtered region embeddings); enqueue_gpu_backfill 'siglip' gates on a missing concept region (drains the back-catalogue, retries failures, no double-enqueue); daily siglip-backfill beat; UI button; /api/ccip/overview reports images_with_concept_siglip. - v1 scope: suggestion rail only — auto-apply stays whole-image (conservative; heads' thresholds were calibrated on whole-image). Bulk-apply bag = follow-up. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
198 lines
6.5 KiB
Python
198 lines
6.5 KiB
Python
"""GPU-job queue engine (#114): enqueue dedupe + lease/heartbeat/complete/fail."""
|
|
from datetime import UTC, datetime, timedelta
|
|
|
|
import pytest
|
|
from sqlalchemy import func, select
|
|
|
|
from backend.app.models import GpuJob, ImageRecord, ImageRegion
|
|
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_siglip_backfill_gates_on_concept_region(db):
|
|
# 'siglip' backfill enqueues images that lack a concept region (the
|
|
# back-catalogue) and skips ones that already have one — and never double-
|
|
# enqueues an image that already has a pending siglip job.
|
|
from backend.app.tasks.ml import enqueue_gpu_backfill
|
|
|
|
need = await _img(db, "e1" * 32) # no concept region → wants one
|
|
have = await _img(db, "e2" * 32) # already embedded → skip
|
|
db.add(ImageRegion(
|
|
image_record_id=have.id, kind="concept", rx=0.0, ry=0.0, rw=1.0, rh=1.0,
|
|
siglip_embedding=[0.0] * 1152, embedding_version="siglip-test",
|
|
))
|
|
await db.commit()
|
|
|
|
assert enqueue_gpu_backfill("siglip") >= 1
|
|
|
|
queued = {
|
|
j.image_record_id for j in (
|
|
await db.execute(select(GpuJob).where(GpuJob.task == "siglip"))
|
|
).scalars()
|
|
}
|
|
assert need.id in queued
|
|
assert have.id not in queued
|
|
|
|
# Idempotent: the now-pending job means a second run doesn't re-enqueue it.
|
|
enqueue_gpu_backfill("siglip")
|
|
n_for_need = (
|
|
await db.execute(
|
|
select(func.count()).select_from(GpuJob).where(
|
|
GpuJob.task == "siglip", GpuJob.image_record_id == need.id
|
|
)
|
|
)
|
|
).scalar_one()
|
|
assert n_for_need == 1
|
|
|
|
|
|
@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"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_release_returns_to_pending(db):
|
|
img = await _img(db, "01" + "a" * 62)
|
|
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.release("other", [job.id]) == 0 # not this token's lease
|
|
assert await svc.release("agent-1", [job.id]) == 1 # graceful hand-back
|
|
await db.commit()
|
|
fresh = await db.get(GpuJob, job.id)
|
|
assert fresh.status == "pending" and fresh.lease_token is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_recover_orphaned_resets_only_expired(db):
|
|
img1 = await _img(db, "02" + "a" * 62)
|
|
img2 = await _img(db, "03" + "a" * 62)
|
|
svc = GpuJobService(db)
|
|
await svc.enqueue(img1.id, "ccip")
|
|
await svc.enqueue(img2.id, "ccip")
|
|
await db.commit()
|
|
expired, fresh = await svc.lease("dead", batch_size=2)
|
|
# One lease is in the past (orphaned), the other still valid.
|
|
expired.lease_expires_at = datetime.now(UTC) - timedelta(minutes=10)
|
|
await db.commit()
|
|
|
|
assert await svc.recover_orphaned() == 1
|
|
await db.commit()
|
|
assert (await db.get(GpuJob, expired.id)).status == "pending"
|
|
assert (await db.get(GpuJob, fresh.id)).status == "leased" # untouched
|