feat(videogen): canonical video-generation surface + llama-swap client
New videogen/ contract package (ADR-0019): Request/Result/Model/Provider
with the imagegen conventions. Text-to-video and image-to-video are one
surface (Request.InitImage, nil = t2v) since hybrid checkpoints like
Wan 2.2 TI2V serve both from one model; Result carries a single clip.
provider/llamaswap gains VideoModel(id) targeting the blocking
POST {base}/v1/videos/sync (multipart, model-routed by the fork's new
video routes): vLLM-Omni parameter names, OpenAI-style input_reference
file part, optional fields stay off the wire so per-model launch-flag
defaults apply. CLAUDE.md package map picks up audio/ (missed in #12)
and videogen/.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj
This commit is contained in:
@@ -34,6 +34,11 @@ majordomo Registry, Parse, env-DSN loading, chain executor, re-exports
|
||||
Tool/Toolbox, Capabilities, Stream, Model, Provider, errors
|
||||
imagegen/ canonical text-to-image contract: Request/Result/Model/
|
||||
Provider (separate from llm; Image = llm.ImagePart) (ADR-0016)
|
||||
audio/ canonical speech contracts: SpeechModel (TTS) +
|
||||
TranscriptionModel (STT), same conventions (ADR-0017)
|
||||
videogen/ canonical video-generation contract: one Model for
|
||||
text-to-video + image-to-video (InitImage), single-clip
|
||||
Result (Image = llm.ImagePart) (ADR-0019)
|
||||
health/ clock-injected health tracker (bench/backoff)
|
||||
media/ image normalization to target capabilities (sniff real
|
||||
format, downscale, transcode, byte ladder; ErrUnsupported
|
||||
@@ -44,7 +49,8 @@ majordomo Registry, Parse, env-DSN loading, chain executor, re-exports
|
||||
provider/ollama/ one native /api/chat client serving the ollama,
|
||||
ollama-cloud, and foreman built-ins via presets
|
||||
provider/llamaswap/ llama-swap proxy: chat delegates to provider/openai,
|
||||
plus management methods + imagegen image client (ADR-0015)
|
||||
plus management methods + imagegen/audio/videogen
|
||||
clients (ADR-0015..0019)
|
||||
provider/google/ Gemini on google.golang.org/genai (the one approved
|
||||
dependency; lazy client, raw-JSON-schema tools,
|
||||
ThinkingLevel reasoning, iter.Pull2 streaming)
|
||||
|
||||
Reference in New Issue
Block a user