From 695eba21502c4ac1cb4d96bccd978e83dba8ebdc Mon Sep 17 00:00:00 2001 From: viettranx Date: Wed, 15 Apr 2026 00:01:34 +0700 Subject: [PATCH] docs: sync changelog + tools-system for audio manager Phase 03 --- docs/03-tools-system.md | 3 +-- docs/17-changelog.md | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 2 deletions(-) diff --git a/docs/03-tools-system.md b/docs/03-tools-system.md index 49732880..3e25da95 100644 --- a/docs/03-tools-system.md +++ b/docs/03-tools-system.md @@ -895,8 +895,7 @@ Never put credentials in tool settings JSON — backend does not validate. |------|---------| | `internal/tools/create_image.go` | create_image tool (OpenAI, Gemini, MiniMax, DashScope) | | `internal/tools/create_image_{dashscope,minimax}.go` | Provider-specific image generation | -| `internal/tools/create_audio.go` | create_audio tool (MiniMax, ElevenLabs, Suno) | -| `internal/tools/create_audio_{minimax,elevenlabs,suno}.go` | Provider-specific audio generation | +| `internal/tools/create_audio.go` | create_audio tool — delegates to `audio.Manager` for music/SFX (ElevenLabs, MiniMax) | | `internal/tools/create_video.go` | create_video tool (MiniMax) | | `internal/tools/tts.go` | tts tool: text-to-speech (OpenAI, ElevenLabs, Edge, MiniMax) | | `internal/tools/read_{image,audio,video,document}.go` | Media reading tools (vision, transcription, analysis) | diff --git a/docs/17-changelog.md b/docs/17-changelog.md index faf47762..bbab1d44 100644 --- a/docs/17-changelog.md +++ b/docs/17-changelog.md @@ -4,6 +4,30 @@ All notable changes to GoClaw Gateway are documented here. Format follows [Keep --- +## [Unreleased] — 2026-04-14 + +#### ElevenLabs Audio Manager Refactor — Phase 3 (2026-04-14) + +Music generation via ElevenLabs + MiniMax with fallback chain. Suno provider fully removed from codebase (no official API, ToS violation risk). + +### Added +- **ElevenLabs Music provider**: `internal/audio/elevenlabs/music.go` — POST `/v1/music`, model `music_v1`, binary MP3 response, 300s timeout, prompt + optional lyrics +- **MiniMax Music provider**: `internal/audio/minimax/music.go` — POST `{base}/music_generation`, 2-step URL-download pattern, 200 MB cap, optional instrumentation toggle + +### Changed +- **`create_audio` tool simplified**: Now thin Manager dispatcher (`NewCreateAudioTool(audioMgr *audio.Manager)`), removed inline provider logic + per-provider switch cases +- **`audio.Manager.GenerateMusic/GenerateSFX`**: Chain-based resolution (elevenlabs → minimax for music, elevenlabs-only for SFX) +- **`createAudio` builtin tool**: Unified dispatch via Manager instead of `providers.Registry` dependency injection + +### Removed +- **Suno provider**: Fully excised (10 atomic locations) — research confirms no official API + ToS violations. Files deleted: `create_audio_suno.go`, `create_audio_minimax.go`, `create_audio_elevenlabs.go` shim. HTTP route removed. TS schema entry removed. Config provider removed. + +### Types +- **`audio.MusicOptions`**: Added `Instrumental bool`, `Model string`, `TimeoutSec int` fields +- **`audio.AudioResult`**: Added `Provider string` field for observability (tool span metadata) + +--- + ## [v2.66.0] — 2026-04-05 ### Security