Files
FabledCurator/agent/fc_agent/media.py
T
bvandeusen 713a11e394
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 19s
CI / backend-lint-and-test (push) Successful in 25s
CI / integration (push) Successful in 3m25s
fix(agent): server-side rate metrics + killable-on-stop ffmpeg
Two follow-ups from live debugging of "work/min never populates" and
"stopped never reached".

1) jobs/min + downloads/min are now computed in the BACKEND on a fixed
   cadence (_rate_loop, EWMA) and reported ready-to-show. The rates were
   derived client-side from poll deltas with a dt<30s guard — but a
   backgrounded/unfocused browser tab throttles its timers to ~1/min, so
   every delta exceeded 30s and the guard blanked the rates forever. A
   server-side rate is independent of how often the tab polls. Frontend just
   displays s.jobs_per_min / s.downloads_per_min. VERSION → .9.

2) ffmpeg video sampling is now killable on Stop. A downloader stuck in a
   slow/reconnecting decode (observed: 47s, 230s for one video) couldn't see
   the stop signal until ffmpeg returned, so Stop detached still-running
   threads and work kept flowing long after — "stopped" that wasn't really
   stopped. sample_frames_from_url now runs ffmpeg via Popen and polls a
   `should_stop` callback every 0.5s, terminating (then killing) the process
   at once on Stop or the per-video timeout. A stop-killed job is handed back
   (transient), not failed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 16:51:26 -04:00

163 lines
6.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Image + video handling. Stills load directly; videos are sampled into frames
(ffmpeg) at the cadence FC sends — so a video becomes a bag of per-frame
instances, each with a timestamp."""
import io
import os
import subprocess
import tempfile
import time
from PIL import Image, ImageFile
# Load slightly-truncated images (a few missing trailing bytes) instead of
# raising — matches the server embedder. These are common in scraped libraries
# and would otherwise fail the job 3× then error (operator-flagged 2026-06-30).
ImageFile.LOAD_TRUNCATED_IMAGES = True
# Disable PIL's decompression-bomb guard: this is a TRUSTED local library, not an
# untrusted upload surface, so a legitimately huge image (high-res scans/prints,
# 90M+ pixels) must load. The default 89M-pixel limit only WARNS, but PIL raises
# DecompressionBombError at 2× (~179M px) — which would fail those jobs outright
# (operator-flagged 2026-06-30, images of 9095M px).
Image.MAX_IMAGE_PIXELS = None
def is_video(mime: str) -> bool:
return bool(mime) and (mime.startswith("video/") or mime in {"image/gif"})
def _dhash(img: Image.Image, size: int = 8) -> int:
"""Difference hash: compare adjacent pixels of a (size+1 × size) grayscale
thumbnail → a `size*size`-bit fingerprint. Cheap (64 comparisons on a 72-px
thumbnail) and robust to scaling/compression noise — near-identical frames
hash within a few bits, a real scene change moves many."""
small = img.convert("L").resize((size + 1, size))
px = list(small.getdata())
bits = 0
for row in range(size):
base = row * (size + 1)
for col in range(size):
bits = (bits << 1) | int(px[base + col] > px[base + col + 1])
return bits
def dedupe_frames(
frames: list[tuple[float, Image.Image]], min_distance: int
) -> list[tuple[float, Image.Image]]:
"""Drop visually near-duplicate frames. A near-static video sampled into many
frames re-runs the WHOLE detect→CCIP→SigLIP chain on ~identical frames — the
dominant video load. Greedy perceptual-hash dedup: keep a frame only if its
dHash differs from every already-kept frame by >= min_distance bits (Hamming),
so a static run collapses to one frame while genuinely distinct scenes all
survive. Order + timestamps preserved. CPU-only (64-bit int XORs), so it runs
in the decode stage and spares the GPU the skipped frames entirely.
min_distance is the coarseness dial: higher keeps more frames (safer for brief
localized changes an 8×8 hash can miss), 0 disables. The first frame is always
kept (nothing to compare against)."""
if min_distance <= 0 or len(frames) <= 1:
return frames
kept: list[tuple[float, Image.Image]] = []
hashes: list[int] = []
for t, frame in frames:
h = _dhash(frame)
if all(bin(h ^ k).count("1") >= min_distance for k in hashes):
hashes.append(h)
kept.append((t, frame))
return kept
def to_rgb(img: Image.Image) -> Image.Image:
"""RGB, flattening any transparency onto white first. A naive convert('RGB')
on a palette-with-transparency image (common for character PNGs on a clear
background) lets PIL guess the transparent pixels — usually black artifacts
that bleed into the crop + the embedding (and the "should be converted to
RGBA" warning). Compositing over white gives a clean, consistent background."""
if img.mode in ("RGBA", "LA", "PA") or (
img.mode == "P" and "transparency" in img.info
):
img = img.convert("RGBA")
bg = Image.new("RGBA", img.size, (255, 255, 255, 255))
return Image.alpha_composite(bg, img).convert("RGB")
return img.convert("RGB")
def load_image(data: bytes) -> Image.Image:
return to_rgb(Image.open(io.BytesIO(data)))
# ffmpeg reconnect flags — resume a dropped HTTP transfer (a slow/contended media
# store can cut a long stream) instead of failing the whole job. Relies only on
# HTTP + Range, which every FC deployment serves → environment-agnostic.
_RECONNECT = [
"-reconnect", "1", "-reconnect_streamed", "1",
"-reconnect_on_network_error", "1", "-reconnect_delay_max", "5",
]
def _collect_frames(
tmp: str, interval: float, cap: int
) -> list[tuple[float, Image.Image]]:
out: list[tuple[float, Image.Image]] = []
names = sorted(n for n in os.listdir(tmp) if n.startswith("f_"))
for i, name in enumerate(names[:cap]):
with Image.open(os.path.join(tmp, name)) as im:
out.append((round(i * interval, 2), to_rgb(im)))
return out
def _terminate(proc: subprocess.Popen) -> None:
"""Stop an ffmpeg cleanly, then hard-kill if it ignores SIGTERM."""
proc.terminate()
try:
proc.wait(timeout=2)
except subprocess.TimeoutExpired:
proc.kill()
try:
proc.wait(timeout=2)
except subprocess.TimeoutExpired:
pass
def sample_frames_from_url(
url: str, interval_seconds: float, max_frames: int,
*, headers: str = "", timeout: float = 1200.0, should_stop=None,
) -> list[tuple[float, Image.Image]]:
"""Sample frames by pointing ffmpeg STRAIGHT at the media URL — it Range-reads
only the video index + up to max_frames worth of content, so the agent never
downloads the whole file (VR/4K originals run 800MB+ and would buffer ~1GB in
RAM and get cut off mid-download). Reconnect flags resume a dropped transfer;
the timeout is the per-video ceiling (a slow/reconnecting stream can otherwise
run for minutes). `should_stop` is polled while ffmpeg runs so a Stop KILLS the
subprocess at once — otherwise a downloader stuck in a long decode keeps the
agent "working" long after Stop. Empty on failure / stop / timeout."""
interval = max(0.5, float(interval_seconds or 4.0))
cap = max(1, int(max_frames or 64))
hdr = ["-headers", headers] if headers else []
with tempfile.TemporaryDirectory() as tmp:
pattern = os.path.join(tmp, "f_%05d.jpg")
cmd = ["ffmpeg", "-nostdin", "-loglevel", "error", *_RECONNECT, *hdr,
"-i", url, "-vf", f"fps=1/{interval}", "-frames:v", str(cap),
"-q:v", "3", pattern]
try:
proc = subprocess.Popen(
cmd, stdin=subprocess.DEVNULL,
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
)
except (OSError, ValueError):
return []
# Poll rather than block, so a Stop (or the per-video timeout) can kill a
# slow/wedged ffmpeg promptly instead of waiting it out.
start = time.monotonic()
while True:
try:
proc.wait(timeout=0.5)
break
except subprocess.TimeoutExpired:
if (should_stop and should_stop()) or (time.monotonic() - start > timeout):
_terminate(proc)
return []
if proc.returncode != 0:
return []
return _collect_frames(tmp, interval, cap)