112 Commits

Author SHA1 Message Date
calesthio
9e43f90e2b Merge remote-tracking branch 'origin/main' into codex/add-gemini-seedance-minimax-models
# Conflicts:
#	docs/PROVIDERS.md
2026-08-13 12:48:49 -07:00
calesthio
8cdd37f523 feat: add Gemini Omni, Seedance 2.5, and MiniMax H3 routes 2026-08-13 12:48:24 -07:00
Calesthio
494a95e62a Merge pull request #501 from calesthio/codex/atlas-media-model-expansion
Add Atlas Cloud media model gateway
2026-08-13 12:20:20 -07:00
calesthio
1267066bc4 Merge commit 'f72efb53d3cea7cce0943d5dc4e55e33e4e59af3' into codex/repair-pr-353
# Conflicts:
#	AGENT_GUIDE.md
#	docs/PROVIDERS.md
2026-08-13 11:40:09 -07:00
calesthio
dceea45387 Merge remote-tracking branch 'origin/main' into codex/repair-pr-353
# Conflicts:
#	docs/PROVIDERS.md
2026-08-13 11:20:19 -07:00
calesthio
00e4902348 Merge remote-tracking branch 'origin/main' into codex/repair-pr-371
# Conflicts:
#	docs/PROVIDERS.md
2026-08-13 11:20:19 -07:00
calesthio
9f50874656 Merge remote-tracking branch 'origin/main' into codex/repair-pr-353
# Conflicts:
#	tests/contracts/test_phase3_contracts.py
2026-08-13 11:11:48 -07:00
calesthio
329628a22b Merge remote-tracking branch 'origin/main' into codex/repair-pr-371 2026-08-13 11:11:02 -07:00
calesthio
e2a9e35c40 Merge remote-tracking branch 'origin/main' into codex/repair-pr-442 2026-08-13 11:11:02 -07:00
calesthio
ae9a74f1a2 feat: add Atlas Cloud media model gateway 2026-08-13 10:40:29 -07:00
calesthio
6b722ab56e Merge remote-tracking branch 'origin/main' into codex/repair-pr-458
# Conflicts:
#	tools/graphics/image_selector.py
2026-08-13 10:38:22 -07:00
Calesthio
0adcc23f44 Merge pull request #457 from wulongshe/feat/gemini-flash-image
feat: add gemini-2.5-flash-image backend to google_imagen
2026-08-13 10:36:12 -07:00
calesthio
a5c9d789be Merge remote-tracking branch 'origin/main' into codex/repair-pr-458
# Conflicts:
#	tools/graphics/image_selector.py
2026-08-13 10:17:12 -07:00
calesthio
700046d33c Merge remote-tracking branch 'origin/main' into codex/repair-pr-482
# Conflicts:
#	docs/PROVIDERS.md
2026-08-13 10:17:12 -07:00
calesthio
4e5bd8d5fa Merge remote-tracking branch 'origin/main' into codex/repair-pr-457
# Conflicts:
#	tools/graphics/image_selector.py
2026-08-13 10:17:11 -07:00
calesthio
3b966b06cf Merge remote-tracking branch 'origin/main' into codex/repair-pr-353 2026-08-13 10:15:44 -07:00
calesthio
be8cf96861 Merge remote-tracking branch 'origin/main' into codex/repair-pr-371 2026-08-13 10:15:43 -07:00
calesthio
0bb4c266d7 Merge remote-tracking branch 'origin/main' into codex/repair-pr-442 2026-08-13 10:15:35 -07:00
Calesthio
5fcea90d71 Merge pull request #483 from ikohu-66/add_seedream_tools
Add seedream tools
2026-08-13 10:08:25 -07:00
calesthio
f21e86570d Merge remote-tracking branch 'origin/main' into codex/repair-pr-458 2026-08-13 09:44:58 -07:00
calesthio
6b75448a0f Merge remote-tracking branch 'origin/main' into codex/repair-pr-483 2026-08-13 09:44:57 -07:00
calesthio
3f2898c77e Merge remote-tracking branch 'origin/main' into codex/repair-pr-495 2026-08-13 09:44:57 -07:00
calesthio
e614c9d4c4 Merge remote-tracking branch 'origin/main' into codex/repair-pr-457 2026-08-13 09:44:56 -07:00
calesthio
7f43667dfd fix: refresh Fish Audio promotion and schema 2026-08-13 09:32:54 -07:00
calesthio
7052f3999b Merge remote-tracking branch 'origin/main' into codex/repair-pr-353
# Conflicts:
#	.env.example
2026-08-13 09:28:52 -07:00
calesthio
078eb7eecd fix: integrate Azure TTS with shared selector 2026-08-13 09:27:32 -07:00
calesthio
a3c45aa3bf Merge remote-tracking branch 'origin/main' into codex/repair-pr-371
# Conflicts:
#	.env.example
2026-08-13 09:23:46 -07:00
calesthio
cffc18308f fix: scope fal providers and Google TTS networking 2026-08-13 09:22:11 -07:00
calesthio
b3434affe3 Merge remote-tracking branch 'origin/main' into codex/repair-pr-482
# Conflicts:
#	skills/pipelines/animation/asset-director.md
2026-08-13 09:20:01 -07:00
calesthio
8143266ead fix: complete Hunyuan image provider integration 2026-08-13 09:18:49 -07:00
calesthio
171866dbbf fix: complete Seedream provider integration 2026-08-13 09:12:00 -07:00
calesthio
bf55d498fb Merge remote-tracking branch 'origin/main' into codex/repair-pr-442
# Conflicts:
#	.env.example
2026-08-13 09:07:59 -07:00
calesthio
b1aefb364a fix: complete MiniMax image provider contracts 2026-08-13 09:02:22 -07:00
calesthio
579bf053e7 fix: route Gemini image models through selector 2026-08-13 08:58:27 -07:00
calesthio
04571cfe8e test: make Blender doctor contract portable 2026-08-13 07:56:45 -07:00
calesthio
2702362c24 feat: add production 3D world pipeline 2026-08-13 07:48:38 -07:00
octo-patch
9c2850f02e feat: add MiniMax image generation tool 2026-08-12 22:46:06 +08:00
蓝友和
63fd646717 add seedreamm tools 2026-08-09 00:25:44 +08:00
Codex
21d51ab9c8 add fal ElevenLabs speech and secure audio routing 2026-08-08 13:02:07 +00:00
Codex
6b4c73c6df scope Google TTS credentials safely 2026-08-07 15:01:59 +00:00
calesthio
9482eddeff fix: recover bounded defects from PR backlog 2026-08-03 02:14:01 -07:00
clarkh
00745a5f6d feat: add Hunyuan Image Generation 3.0 (混元生图) via TokenHub API
Async text-to-image tool using Tencent TokenHub (hy-image-v3.0).
Parameters mirror upstream SubmitTextToImageJob API: prompt, resolution,
seed, revise, logo_add, logo_param, and reference images via Images.N.

- tools/graphics/hunyuan_image.py: submit → poll → download flow,
  matching hunyuan_cloud_video.py code style
- tests/tools/test_hunyuan_image.py: 32 unit tests covering payload
  building, image resolution, API error handling, and mocked e2e flow
2026-07-30 11:38:33 +08:00
shewulong
5d152e4699 feat: add gemini-2.5-flash-image backend to google_imagen 2026-07-29 20:52:05 -05:00
zzzxtnt
b71f9b1f3e feat(video): add direct Volcengine Ark Seedance 2.0 provider 2026-07-27 11:24:07 +08:00
Tomofumi Yagi
990d7f9a2c fix: address selector contract, promo pricing, idempotency, and registry metadata review
- 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
2026-07-22 19:00:46 +09:00
Tomofumi Yagi
d40c32441c feat: add fish.audio TTS provider
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.
2026-07-22 18:51:05 +09:00
Calesthio
888fe5a73c Merge pull request #337 from 0xDevNinja/fix/green-screen-chromakey-1x1-collapse
fix(green_screen): scale chromakey background to frame size, not 1x1
2026-07-21 14:57:37 -07:00
Calesthio
33c7000e68 Merge pull request #374 from ShiroKSH/fix/hyperframes-relative-output-path
fix: resolve relative HyperFrames output paths
2026-07-17 18:53:52 -07:00
Calesthio
2a6bf1e039 Merge pull request #391 from tianrking/agent/fix-delayed-audio-fades
fix(audio): schedule delayed track fades correctly
2026-07-17 18:51:56 -07:00
tianrking
5e21f1b78a fix(audio): schedule delayed track fades correctly 2026-07-16 13:33:17 +08:00