fix(gif): correct the streaming threshold and three encode-path hazards

This repo has no CI and no adversarial reviewer, so these come from reading the
harness back against the production sandbox contract rather than from a bot.

The size estimate was wrong by ~1000x in the wrong direction. `width * height *
9e-5` was never MiB — for a 640x480 frame it yields 27.6, so a trivial 2-second
GIF "projected" 800+ MiB and every render would have tripped the streaming
branch and come back as an MP4. The bench missed it because it bind-mounted
/workspace from the host disk, where statvfs reports hundreds of GB and the
threshold never fires; production mounts a 64 MiB tmpfs, where it always would
have. Replaced with a named PNG_BYTES_PER_PIXEL = 0.29, measured (86 KiB per
busy 640x480 frame). Verified against the real tmpfs: a 6s piece now estimates
7.6 MiB against a 38 MiB budget and stays a GIF, while a 90s piece streams.

Three smaller ones on the streaming path:

- ffmpeg's stderr was a pipe nobody drained until the encode finished, so a
  chatty encoder could fill the 64 KiB buffer, block, stop reading stdin, and
  deadlock a long render halfway. It writes to a file now.
- _close_pipe assumed a live pipe; if ffmpeg had already died, closing stdin
  raised BrokenPipeError and buried the real exit code and log.
- A failed encode could leave a half-written /workspace/final.* behind, which
  still comes back as a files_out file_id — a broken artifact that looks
  deliverable is worse than none, so it's removed on the way out.
This commit is contained in:
2026-07-24 19:05:19 -04:00
parent 7906a1ab4c
commit f16ac83790
+34 -7
View File
@@ -60,6 +60,12 @@ import numpy as np # noqa: E402,F401
GIF_MAX_SECONDS = 20
# Keep a GIF comfortably under Discord's ~10 MiB inline limit.
GIF_MAX_BYTES = 9 * 1024 * 1024
# Measured on busy 640x480 matplotlib frames in this sandbox: ~86 KiB per PNG at
# compress_level=1, i.e. 88064 / 307200 px. This decides whether a render streams
# instead of staging frames on disk, so it must not read low — erring low
# reintroduces the ENOSPC this harness exists to prevent, and erring high only
# turns a borderline short piece into an MP4.
PNG_BYTES_PER_PIXEL = 0.29
_FONT_CANDIDATES = [
"/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf",
@@ -212,8 +218,7 @@ class Animation:
total_s = sum(s.seconds + s.hold for s in self._scenes)
est_frames = int(total_s * self.fps)
# ~90 KiB per 640x480 PNG at compress_level=1; budget 60% of free space.
est_mb = est_frames * (self.width * self.height * 9e-5)
est_mb = est_frames * self.width * self.height * PNG_BYTES_PER_PIXEL / 1048576
# A piece too long for a GIF is an MP4 anyway, and an MP4 can be encoded
# in one streaming pass — so pipe the frames into ffmpeg and keep NOTHING
@@ -276,7 +281,17 @@ class Animation:
"that differs by a character) and re-run the whole program in a "
"fresh code_exec call, remembering gifsmith.py in files_in.")
try:
art = self._encode(total_s, long_edge, force, audio)
except Exception: # noqa: BLE001
# A half-written final.* at the top of /workspace still comes back as
# a files_out file_id, and a broken artifact that LOOKS deliverable is
# worse than none — the agent would ship it. Take it with us.
for leftover in ("/workspace/final.mp4", "/workspace/final.gif"):
if os.path.exists(leftover):
os.remove(leftover)
shutil.rmtree(self._scratch, ignore_errors=True)
raise
self._contact_sheet()
broken = [f"{i}:{s.title!r}" for i, s in enumerate(self._scenes) if s.error]
print(f"[gifsmith] {self._count} frames, scratch "
@@ -297,7 +312,11 @@ class Animation:
# ------------------------------------------------------------------ encoding
def _open_pipe(self, out, long_edge, audio):
"""ffmpeg reading a PNG stream on stdin — the streaming MP4 path."""
"""ffmpeg reading a PNG stream on stdin — the streaming MP4 path.
stderr goes to a FILE, not a pipe: nobody drains a stderr pipe until the
encode is done, so a chatty ffmpeg would fill the 64 KiB pipe buffer,
block, stop reading stdin, and deadlock the render halfway through."""
cmd = ["ffmpeg", "-y", "-loglevel", "error",
"-f", "image2pipe", "-framerate", str(self.fps), "-i", "-"]
if audio:
@@ -305,15 +324,23 @@ class Animation:
cmd += ["-c:v", "libx264", "-pix_fmt", "yuv420p", "-crf", "23",
"-vf", f"scale='min({long_edge},iw)':-2:flags=lanczos",
"-movflags", "+faststart", out]
self._pipe_err = open(os.path.join(self._scratch, "ffmpeg.log"), "w+b")
return subprocess.Popen(cmd, stdin=subprocess.PIPE,
stdout=subprocess.DEVNULL, stderr=subprocess.PIPE)
stdout=subprocess.DEVNULL, stderr=self._pipe_err)
def _close_pipe(self):
try:
self._pipe.stdin.close()
err = self._pipe.stderr.read().decode(errors="replace")
if self._pipe.wait() != 0:
raise RuntimeError(f"ffmpeg (streaming) failed:\n{err[-2000:]}")
except OSError:
# ffmpeg already died; its exit code + log below say why.
pass
rc = self._pipe.wait()
self._pipe_err.seek(0)
err = self._pipe_err.read().decode(errors="replace")
self._pipe_err.close()
self._pipe = None
if rc != 0:
raise RuntimeError(f"ffmpeg (streaming) exited {rc}:\n{err[-2000:]}")
def _encode(self, seconds, long_edge, force, audio=None):
gif, mp4 = "/workspace/final.gif", "/workspace/final.mp4"