ACE-Step v1's node-pack fragmentation turns out to be moot: ComfyUI ships
TextEncodeAceStepAudio/EmptyAceStepLatentAudio as native core nodes
(comfy_extras/nodes_ace.py), not a third-party pack, and Comfy-Org's own
workflow_templates repo has an official ACE-Step-v1 template built from
those plus long-stable core nodes. tools/_comfyui/workflows/ace-step-1-t2a.json
was built by cross-checking every node's class_type and input names against
ComfyUI's own source (nodes_ace.py, nodes_audio.py, nodes_latent.py,
nodes.py) rather than trusting the UI-format export directly.
comfyui_music now defaults to this bundled workflow: prompt maps to
ACE-Step's tags field (matching suno_music's "prompt = music description"
convention), lyrics/duration_seconds/steps/cfg/lyrics_strength/seed are all
patchable, and missing ace_step_v1_3.5b.safetensors surfaces through the
same missing_models contract as image/video. workflow_json/workflow_path +
output_node remains available for ACE-Step 1.5, other node packs, or
different audio models entirely.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resolves the "music generation" open question from the adapter plan.
Unlike comfyui_image/comfyui_video there is no bundled workflow: ACE-Step's
ComfyUI node interface isn't standardized across custom node packs
(AceStepModelLoader vs native TextEncodeAceStepAudio, etc.), so instead of
picking one pack and breaking for everyone else, comfyui_music always
requires a caller-supplied workflow_json/workflow_path + output_node --
the same override contract image/video offer as an alternative, just
mandatory here. prompt is provenance-only, never injected into the graph.
Routed through the existing registry.get_by_capability("music_generation")
path alongside suno_music/music_gen -- no dedicated selector needed.
ComfyUIClient.generate() now also reads the "audio" output key (what
ComfyUI's native SaveAudio node writes), and gets timeout/resume/websocket-
wait/multi-server support for free via the shared client. Duration is a
best-effort ffprobe probe of the downloaded file since a custom workflow
gives no other way to know it ahead of time.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resolves the "multi-server" open question from the adapter plan.
ComfyUIClient(capability="image"|"video") now resolves its server URL
from COMFYUI_IMAGE_SERVER_URL / COMFYUI_VIDEO_SERVER_URL first, falling
back to the shared COMFYUI_SERVER_URL and then the localhost default —
so comfyui_image and comfyui_video can point at separate ComfyUI
instances (different GPUs, different model sets) with zero extra config
for single-server setups. is_default_url/unavailable_reason() and the
setup_offer metadata account for the override.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resolves the "async generation" open question from the adapter plan.
generate() now watches ComfyUI's websocket events (executing/progress/
execution_error) and reacts immediately instead of sleeping between REST
polls, with an optional on_progress callback that comfyui_video uses to
print step progress on long renders. websocket-client is an optional
import; _wait() falls back to the original poll() loop (with the
remaining time budget, not a fresh one) when it's unavailable or the
connection drops, so resume_prompt_id recovery is unaffected either way.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Non-accelerated local-GPU workflows (e.g. Wan 1.3B at 832x480/81-97
frames) routinely took ~1360-1630s, so the old 900s default false-failed
real renders that were still completing server-side. Timeout is now a
configurable timeout_seconds input (default 3600s), and ComfyUIError
carries the prompt_id on error/timeout so a timed-out-but-still-running
job can be resumed via resume_prompt_id instead of resubmitted.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The env var added complexity without meaningful benefit — explicit model
selection via the "model" input parameter is sufficient for both image and
video TokenHub tools.
- tools/video/hunyuan_cloud_video.py: drop env var fallback from
_resolve_model(), remove mention from install_instructions
- tests/contracts/test_hunyuan_cloud_video.py: remove
test_resolve_model_from_env and test_resolve_model_input_overrides_env
- .env.example: move TENCENT_TOKENHUB_API_KEY to a dedicated "Tencent
Hunyuan TokenHub API" section, drop TENCENT_TOKENHUB_MODEL comment,
broaden description from "video generation" to generic "Tencent Hunyuan
via TokenHub API"
Introduce a new video generation provider backed by the Tencent TokenHub
API (tokenhub.tencentmaas.com), an OpenAI-compatible gateway for Tencent
Hunyuan video models with simple Bearer-token auth.
- Add hunyuan_cloud_video tool (submit → poll → download) supporting
both text-to-video (hy-video-1.5) and image-to-video (yt-video-2.0)
- Add env vars: TENCENT_TOKENHUB_API_KEY, TENCENT_TOKENHUB_MODEL
- Add contract tests for the new tool
- Document setup, API flow, model pricing, and schema constraints in
PROVIDERS.md
- Update provider tables and capability matrix throughout docs
Replace the play-button logo in both READMEs with animated SVG versions of
Monty, served via <picture> + prefers-color-scheme so the mark reads on
GitHub's light and dark themes. Motion uses SMIL animateTransform rather
than CSS keyframes so it survives the <img> rendering context without
depending on transform-box: view-box.
Rebuild the 1280x640 social preview around Monty in the ink/cream/terracotta
palette, and refresh its stat row to the current counts (12 pipelines,
100+ tools, 700+ agent skills). The card's source HTML ships alongside it so
future count updates are an edit and a re-screenshot.
- Require 'model' in the input schema and accept 'model_id' as a
selector-compatible alias (tts_selector exposes model_id); add a
selector-routing regression test
- Document s2.1-pro-free as promotional (free through end of July 2026,
Fair Use, no SLA, possible request retention, commercial-use
restrictions) in PROVIDERS.md and the Layer 3 skill; estimate_cost()
falls back to the paid s2.1-pro rate after the promo window
- Normalize voice_id/reference_id and model_id/model aliases before
computing the idempotency key, and include all output-affecting inputs
(bitrate, sample_rate, temperature, top_p, repetition_penalty, latency,
prosody, normalize, chunk_length) with API defaults applied
- Declare env:FISH_AUDIO_API_KEY in dependencies so registry metadata
reports the requirement
- Add fish_audio to the TTS provider set in the phase3 registry contract
test
- .env.example: replace removed speech-1.x mention with the actual
supported backends (s1 / s2-pro / s2.1-pro)
- docs/PROVIDERS.md: add fish.audio section (setup, backend models,
per-byte pricing incl. free s2.1-pro-free tier) plus entries in the
env var summary, Provider-to-Tool Mapping, and Capability Coverage
- skills/INDEX.md: list fish-audio-tts in the TTS & Audio Layer 3 row
Add FishAudioTTS (capability=tts) so tts_selector auto-discovers a new
high-quality, voice-clone-capable provider. Backend model is required per
call: s1 (previous flagship, kept for compatibility), s2-pro (first S2
generation), s2.1-pro (latest flagship — inline emotion tags, 80+
languages), s2.1-pro-free (free tier for drafts). s1-mini and the
speech-1.x tier have been removed from the current fish.audio API and are
no longer supported. Voice cloning via reference_id with voice_id as a
selector-compatible alias. Adds temperature/top_p/repetition_penalty
sampling controls, optional sample_rate, opus output format, and a "low"
latency tier. Cost is estimated per UTF-8 byte to match fish.audio
billing. Includes a Layer 3 skill, .env.example entry, and unit tests.
Verified end-to-end with s2.1-pro + reference_id: generated a 7-segment
Japanese narration successfully.
os.system(f"manimgl {__file__} ClassName") interpolates the script's own
path into a shell string. These templates are meant to be copied and
renamed per-scene by an agent, so a scene/folder name containing shell
metacharacters is a real injection path, not just malformed input.
Switched to subprocess.run() with an argument list (no shell=True), so
there's nothing left for a shell to interpret regardless of what the
path contains. Same fix applied in both duplicate locations
(.claude/skills and .agents/skills) since the files are identical.
Reviewed scripts/lib/tts.mjs's child_process usage as part of the same
report -- not included in this PR, it already passes args as a real
array with no shell:true anywhere in the call chain, so it isn't
actually exploitable.
Introduces CLA.md (individual CLA: contributors keep all rights to their
work, grant the project the right to offer contributions under additional
license terms; includes a written commitment in section 6 that the engine
remains open source) and a CLA Assistant Lite workflow that gates every PR
on a one-comment signature, with signatures stored in-repo on the
cla-signatures branch.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
