id = "creator"
version = "1.0.0"
name = "Creator Hand"
description = "AI media studio — generates images, videos, music, and speech from text prompts"

category = "content"
icon = "\U0001F3A8"
tools = [
  "image_generate",
  "video_generate",
  "video_status",
  "music_generate",
  "text_to_speech",
  "file_read",
  "file_write",
  "file_list",
  "web_fetch",
  "memory_store",
  "memory_recall",
]

[routing]
aliases = [
  "generate image",
  "create image",
  "make a picture",
  "generate video",
  "create video",
  "make a video",
  "generate music",
  "create music",
  "compose music",
  "text to speech",
  "generate speech",
  "voice over",
  "media generation",
]
weak_aliases = [
  "illustration",
  "artwork",
  "album cover",
  "background music",
  "jingle",
  "narration",
  "audio",
  "thumbnail",
  "poster",
  "banner",
]

# ---- Requirements ----------------------------------------------------------------

[[requires]]
key = "media_provider"
label = "At least one media provider API key must be set"
requirement_type = "any_env_var"
check_value = "OPENAI_API_KEY,MINIMAX_API_KEY"
description = "Creator Hand needs at least one configured media provider. OpenAI supports image and TTS; MiniMax supports image, TTS, video, and music."
optional = false

# ---- Settings --------------------------------------------------------------------

[[settings]]
key = "default_provider"
label = "Preferred Provider"
description = "Which provider to use by default. Auto will pick the first configured provider for each capability."
setting_type = "select"
default = "auto"

[[settings.options]]
value = "auto"
label = "Auto-detect (best available)"

[[settings.options]]
value = "openai"
label = "OpenAI (image, TTS)"
provider_env = "OPENAI_API_KEY"

[[settings.options]]
value = "minimax"
label = "MiniMax (image, TTS, video, music)"
provider_env = "MINIMAX_API_KEY"

[[settings]]
key = "image_model"
label = "Image Model"
description = "Model to use for image generation"
setting_type = "select"
default = "auto"

[[settings.options]]
value = "auto"
label = "Provider default"

[[settings.options]]
value = "gpt-image-1"
label = "GPT Image 1 (OpenAI)"

[[settings.options]]
value = "dall-e-3"
label = "DALL-E 3 (OpenAI)"

[[settings.options]]
value = "image-01"
label = "Image-01 (MiniMax)"

[[settings]]
key = "image_size"
label = "Default Image Size"
description = "Default resolution for generated images"
setting_type = "select"
default = "1024x1024"

[[settings.options]]
value = "1024x1024"
label = "1024x1024 (square)"

[[settings.options]]
value = "1792x1024"
label = "1792x1024 (landscape)"

[[settings.options]]
value = "1024x1792"
label = "1024x1792 (portrait)"

[[settings]]
key = "tts_voice"
label = "TTS Voice"
description = "Default voice for text-to-speech"
setting_type = "select"
default = "alloy"

[[settings.options]]
value = "alloy"
label = "Alloy (neutral)"

[[settings.options]]
value = "echo"
label = "Echo (male)"

[[settings.options]]
value = "fable"
label = "Fable (storytelling)"

[[settings.options]]
value = "nova"
label = "Nova (female)"

[[settings.options]]
value = "onyx"
label = "Onyx (deep male)"

[[settings.options]]
value = "shimmer"
label = "Shimmer (warm female)"

[[settings]]
key = "minimax_api_key"
label = "MiniMax API Key"
description = "API key from platform.minimaxi.com for video and music generation"
setting_type = "text"
env_var = "MINIMAX_API_KEY"
default = ""

# ---- Agent configuration ---------------------------------------------------------

[agents.main]
coordinator = true
name = "creator-hand"
description = "AI media studio — generates images, videos, music, and speech from natural language"
module = "builtin:chat"
provider = "default"
model = "default"
max_tokens = 8192
temperature = 0.5
max_iterations = 30
system_prompt = """You are Creator Hand — an AI media studio that generates images, videos, music, and speech from natural language requests.

## Available Tools

You have access to these media generation tools:

### image_generate
Generate images from text prompts.
- Parameters: `prompt` (required), `provider`, `model`, `width`, `height`, `count`, `quality`, `seed`
- Returns: URLs of generated images (served at /api/uploads/...)
- Providers: OpenAI (gpt-image-1, dall-e-3), MiniMax (image-01)

### text_to_speech
Convert text to spoken audio.
- Parameters: `text` (required), `provider`, `model`, `voice`, `speed`, `format`
- Returns: URL to the audio file
- Providers: OpenAI (tts-1, tts-1-hd), MiniMax (speech-2.8-hd)

### video_generate
Submit a video generation task (asynchronous).
- Parameters: `prompt` (required), `provider`, `model`, `duration_secs`, `resolution`
- Returns: `task_id` and `provider` — use video_status to poll for completion
- Providers: MiniMax (T2V-01, video-01)

### video_status
Check the status of a video generation task.
- Parameters: `task_id` (required), `provider` (required)
- Returns: status ("pending", "processing", "completed", "failed") and result URL when done

### music_generate
Generate music from a text prompt and/or lyrics.
- Parameters: `prompt`, `lyrics`, `provider`, `model`, `instrumental` (bool), `format`
- At least one of `prompt` or `lyrics` is required
- Returns: URL to the audio file
- Providers: MiniMax (music-2.5)

## Workflow Guidelines

1. **Clarify intent**: If the user's request is vague, ask what type of media they want and suggest options.

2. **Image generation**:
   - Be detailed in prompts — describe style, mood, composition, lighting
   - For multi-image requests, vary the prompts meaningfully
   - Default to 1024x1024 unless the user specifies otherwise

3. **Video generation** (async):
   - Always explain that video takes time (typically 1-3 minutes)
   - After calling video_generate, immediately poll with video_status
   - If status is "processing", wait 15-20 seconds and poll again
   - Keep the user informed of progress

4. **Music generation**:
   - For instrumental, set `instrumental: true`
   - For songs with vocals, provide both `prompt` (style description) and `lyrics`
   - Suggest genres and moods if the user doesn't specify

5. **TTS**:
   - Choose a voice that matches the content tone
   - For long text, break into paragraphs and generate separately if needed

6. **Combined workflows** — these are where you shine:
   - "Make a podcast intro" → generate music + TTS narration
   - "Create a social media post" → generate image + caption
   - "Make a video with narration" → generate video + TTS voice-over
   - Always present results together with all URLs

## User Configuration

Check the User Configuration section for:
- `default_provider` — use this provider unless the user overrides
- `image_model` — preferred image model (use if not "auto")
- `image_size` — default image dimensions
- `tts_voice` — default TTS voice

Apply these defaults but allow the user to override in any request.

## Important Rules

- Always show the result URLs to the user so they can access the generated media
- For video tasks, ALWAYS poll until completion or failure — don't leave the user hanging
- Track generation stats via memory_store:
  - `creator_hand_images_generated` — count
  - `creator_hand_videos_generated` — count
  - `creator_hand_music_generated` — count
  - `creator_hand_tts_generated` — count
- If a provider is not configured, suggest the user set up the API key
- Never fabricate URLs or results — only return actual tool output
"""

[agents.prompt_writer]
invoke_hint = "Creative prompt engineering — writing detailed, effective prompts for image, video, and music generation"
name = "prompt-writer"
description = "Prompt engineer that crafts detailed, effective prompts for media generation"
module = "builtin:chat"
provider = "default"
model = "default"
max_tokens = 4096
temperature = 0.8
system_prompt = """You are Prompt Writer, a creative prompt engineer within the Creator Hand.

Your job is to transform simple user requests into detailed, effective prompts for media generation models.

IMAGE PROMPTS:
- Specify art style (photorealistic, watercolor, digital art, anime, oil painting, etc.)
- Include composition details (wide shot, close-up, bird's eye view, etc.)
- Describe lighting (golden hour, studio lighting, dramatic shadows, etc.)
- Add mood/atmosphere (serene, chaotic, mysterious, vibrant, etc.)
- Include technical details when relevant (depth of field, lens type, etc.)

VIDEO PROMPTS:
- Describe the scene and action clearly
- Specify camera movement if desired (pan, zoom, dolly, tracking shot)
- Keep descriptions concise but vivid — video models work best with clear, focused prompts

MUSIC PROMPTS:
- Specify genre, tempo (BPM), and mood
- Describe instrumentation (piano, synth, acoustic guitar, etc.)
- Include structure hints (intro, verse, chorus, bridge)
- For songs with vocals, write lyrics with clear verse/chorus structure

Always present multiple prompt variations for the user to choose from."""

# ---- Dashboard metrics -----------------------------------------------------------

[dashboard]
[[dashboard.metrics]]
label = "Images Generated"
memory_key = "creator_hand_images_generated"
format = "number"

[[dashboard.metrics]]
label = "Videos Generated"
memory_key = "creator_hand_videos_generated"
format = "number"

[[dashboard.metrics]]
label = "Music Tracks"
memory_key = "creator_hand_music_generated"
format = "number"

[[dashboard.metrics]]
label = "TTS Audio"
memory_key = "creator_hand_tts_generated"
format = "number"

# ---- Metadata --------------------------------------------------------------------

[metadata]
frequency = "on-demand"
token_consumption = "low"
default_active = false

# ---- Internationalization --------------------------------------------------------

[i18n.zh]
name = "创作 Hand"
description = "AI 媒体工作室——根据文本提示生成图片、视频、音乐和语音"
category = "内容"

[i18n.zh.agents.main]
name = "创作工作室"
description = "AI 媒体工作室——通过自然语言生成图片、视频、音乐和语音"

[i18n.zh.agents.prompt_writer]
name = "提示词工程师"
description = "提示词工程师，为媒体生成模型编写详细、高效的提示词。"

[i18n.zh.settings.default_provider]
label = "首选提供商"
description = "默认使用哪个提供商。自动模式会为每种能力选择首个可用的提供商。"

[i18n.zh.settings.image_model]
label = "图像模型"
description = "用于图像生成的模型"

[i18n.zh.settings.image_size]
label = "默认图像尺寸"
description = "生成图像的默认分辨率"

[i18n.zh.settings.tts_voice]
label = "TTS 语音"
description = "文字转语音的默认声音"

[i18n.zh.settings.minimax_api_key]
label = "MiniMax API 密钥"
description = "来自 platform.minimaxi.com 的 API 密钥，用于视频和音乐生成"

[i18n.zh-TW]
description = "AI 媒體工作室——根據文字提示生成圖片、影片、音樂和語音"

[i18n.ja]
name = "クリエイター Hand"
description = "AIメディアスタジオ——テキストから画像、動画、音楽、音声を生成"
category = "コンテンツ"

[i18n.ja.settings.default_provider]
label = "優先プロバイダー"
description = "デフォルトで使用するプロバイダー。自動は各機能で最初に設定されたプロバイダーを選択。"

[i18n.ja.settings.image_model]
label = "画像モデル"
description = "画像生成に使用するモデル"

[i18n.ja.settings.image_size]
label = "デフォルト画像サイズ"
description = "生成画像のデフォルト解像度"

[i18n.ja.settings.tts_voice]
label = "TTS音声"
description = "テキスト読み上げのデフォルト音声"

[i18n.ja.settings.minimax_api_key]
label = "MiniMax APIキー"
description = "platform.minimaxi.comからのAPIキー。動画と音楽生成に使用。"

[i18n.ko]
name = "크리에이터 Hand"
description = "AI 미디어 스튜디오 — 텍스트 프롬프트로 이미지, 비디오, 음악, 음성 생성"
category = "콘텐츠"

[i18n.ko.settings.default_provider]
label = "기본 공급자"
description = "기본으로 사용할 공급자. 자동은 각 기능에 대해 첫 번째 구성된 공급자를 선택."

[i18n.ko.settings.image_model]
label = "이미지 모델"
description = "이미지 생성에 사용할 모델"

[i18n.ko.settings.image_size]
label = "기본 이미지 크기"
description = "생성 이미지의 기본 해상도"

[i18n.ko.settings.tts_voice]
label = "TTS 음성"
description = "텍스트-음성 변환의 기본 음성"

[i18n.ko.settings.minimax_api_key]
label = "MiniMax API 키"
description = "platform.minimaxi.com에서 발급한 API 키. 동영상 및 음악 생성에 사용."

[i18n.es]
name = "Hand Creador"
description = "Estudio de medios IA — genera imágenes, videos, música y voz a partir de texto"
category = "Contenido"

[i18n.fr]
name = "Hand Cr\u00e9ateur"
description = "Studio m\u00e9dia IA — g\u00e9n\u00e8re images, vid\u00e9os, musique et voix \u00e0 partir de texte"
category = "Contenu"

[i18n.de]
name = "Kreator-Hand"
description = "AI-Medienstudio — erzeugt Bilder, Videos, Musik und Sprache aus Textprompts"
category = "Inhalt"