steve
f16ac83790
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.
executus-skills
Skill packs for executus
harnesses (mort, gadfly, …), in the SKILL.md "agent-skills" format. Each pack is
its own subfolder with a SKILL.md manifest plus any bundled helper files.
executus-skills/
gif/
SKILL.md # instructions the agent loads on demand
scripts/encode.py # bundled helper the agent runs in its sandbox
Packs
gif— make a funny animated GIF or MP4 for Discord from a description. Plans scenes, keeps recurring people/props consistent via a reusable cast, renders frames in Python, and lets a bundledencode.pypick the format: a GIF for short loops, or an H.264 MP4 (that Discord plays inline) for long bits or when a GIF comes out too big. Adapted from mort's builtinanimateskill. Handles multi-minute pieces.
Using a pack from mort
Each subfolder is a separate subscription (pinned by content digest):
.set skillpacks.enabled true # then restart mort (boot-read)
.set skillpacks.allowed_sources git:https://gitea.stevedudenhoeffer.com/steve/
.skillpack subscribe git https://gitea.stevedudenhoeffer.com/steve/executus-skills subpath=gif ref=main
Then attach the pack to an agent that already has the tools the pack uses (the
pack supplies instructions, not tools). For gif, the agent needs
code_exec, image_describe, send_attachments, file_get_metadata, and
think in its toolset, a generous max_runtime with critic_enabled: true
(long renders run for minutes), and a sandbox image with ffmpeg (plus
gifski/gifsicle for nicer GIFs). Add it in the agent's YAML:
low_level_tools: [code_exec, image_describe, send_attachments, file_get_metadata, think]
skill_packs: [gif]
When the pack is updated upstream, .skillpack check reports it and
.skillpack apply gif re-pins — nothing an agent runs changes until you apply.