feat(agent): desktop GPU agent container — CCIP + figure crops over HTTP (#114)
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 19s
CI / backend-lint-and-test (push) Successful in 27s
CI / integration (push) Successful in 3m32s

The last piece: a Dockerised desktop-GPU worker that talks to FC ONLY over HTTP
(lease → fetch pixels → detect figures + CCIP-embed → submit), so Redis/Postgres
stay private. New top-level agent/ (outside CI scope — verified by running it):
- fc_agent/worker.py: the lease/compute/submit loop, concurrency 1, start/pause/
  stop (stop frees the card; unprocessed leases expire + re-queue).
- fc_agent/models.py: imgutils wrappers — detect_person (figures) + CCIP embed.
  The two API seams to verify against the installed dghs-imgutils (flagged).
- fc_agent/media.py: stills + video frame sampling (ffmpeg) at FC's cadence →
  per-frame instances (the bag).
- fc_agent/crops.py: vendored crop primitive. client.py: the FC HTTP client.
- fc_agent/app.py: FastAPI localhost control UI (start/pause/stop + progress +
  queue depth). Dockerfile (CUDA + onnxruntime-gpu + ffmpeg) + requirements +
  README (token → build → run --gpus all → Start; CPU-fallback path).

This completes the CCIP pipeline end to end: agent produces region CCIP vectors →
RegionService stores → matcher suggests characters → rail. Verified by running on
the desktop (not CI). README calls out the imgutils API + model-string checks.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
This commit is contained in:
2026-06-29 14:03:01 -04:00
parent 60f26247e9
commit 8419ebd761
11 changed files with 527 additions and 0 deletions
+127
View File
@@ -0,0 +1,127 @@
"""The lease → fetch → detect+embed → submit loop, with start/pause/stop control.
Concurrency is 1 (one image at a time) so the GPU footprint stays small and a
stop frees the card promptly. Stop halts leasing + finishes the current item;
unprocessed leases expire and the server re-queues them — nothing is lost.
"""
import threading
import time
from . import media, models
from .client import FcClient
from .config import Config
from .crops import crop_region
class Worker:
def __init__(self, cfg: Config):
self.cfg = cfg
self.client = FcClient(cfg.fc_url, cfg.token, cfg.agent_id)
self._state = "idle" # idle | running | paused | stopping
self._lock = threading.Lock()
self._thread: threading.Thread | None = None
self.processed = 0
self.errors = 0
self.current = None
# --- control -----------------------------------------------------------
def start(self):
with self._lock:
if self._state in ("running", "paused"):
self._state = "running"
return
self._state = "running"
self._thread = threading.Thread(target=self._run, daemon=True)
self._thread.start()
def pause(self):
with self._lock:
if self._state == "running":
self._state = "paused"
def resume(self):
with self._lock:
if self._state == "paused":
self._state = "running"
def stop(self):
with self._lock:
if self._state in ("running", "paused"):
self._state = "stopping"
def status(self) -> dict:
with self._lock:
state = self._state
return {
"state": state, "processed": self.processed,
"errors": self.errors, "current": self.current,
}
# --- loop --------------------------------------------------------------
def _run(self):
while True:
with self._lock:
st = self._state
if st == "stopping":
break
if st == "paused":
time.sleep(1)
continue
try:
jobs = self.client.lease(self.cfg.batch_size)
except Exception:
time.sleep(self.cfg.poll_idle_seconds)
continue
if not jobs:
time.sleep(self.cfg.poll_idle_seconds)
continue
ids = [j["job_id"] for j in jobs]
for job in jobs:
with self._lock:
if self._state == "stopping":
break
self._process(job)
self.client.heartbeat(ids) # keep the rest of the batch alive
with self._lock:
self._state = "idle"
def _process(self, job: dict):
self.current = job.get("image_id")
try:
data = self.client.fetch_image(job["image_url"])
if media.is_video(job.get("mime", "")):
frames = media.sample_frames(
data, job.get("frame_interval_seconds", 4.0),
job.get("max_frames", 64),
) or [(None, media.load_image(data))]
else:
frames = [(None, media.load_image(data))]
regions = []
ev = self.cfg.ccip_model or "ccip-default"
dv = f"person-{self.cfg.detector_level}"
for t, frame in frames:
figs = models.detect_figures(frame, self.cfg.detector_level)
if not figs:
figs = [((0.0, 0.0, 1.0, 1.0), None)] # whole-frame fallback
for bbox, score in figs:
crop = crop_region(frame, bbox)
if crop is None:
continue
vec = models.ccip_vector(crop, self.cfg.ccip_model or None)
regions.append({
"kind": "figure",
"bbox": list(bbox),
"frame_time": t,
"score": score,
"ccip_embedding": vec,
"embedding_version": ev,
"detector_version": dv,
})
self.client.submit(job["job_id"], regions, ["figure", "face"])
self.processed += 1
except Exception as exc: # noqa: BLE001 — report + move on
self.errors += 1
self.client.fail(job["job_id"], str(exc)[:500])
finally:
self.current = None