@sogni-ai/sogni-intelligence-client 3.25.4 → 3.26.0

package/dist/openai-tools/_manifests.generated.js

@@ -19,7 +19,14 @@ exports.appToolsManifest = {
                         },
                         "analysisType": {
                             "type": "string",
-                            "enum": ["describe", "ocr", "objects", "document", "compare", "general"],
+                            "enum": [
+                                "describe",
+                                "ocr",
+                                "objects",
+                                "document",
+                                "compare",
+                                "general"
+                            ],
                             "description": "Type of analysis. Use general when answering the user's specific question."
                         },
                         "sourceImageIndex": {
@@ -35,7 +42,9 @@ exports.appToolsManifest = {
                             "description": "Whether to provide a more detailed analysis."
                         }
                     },
-                    "required": ["query"]
+                    "required": [
+                        "query"
+                    ]
                 }
             }
         },
@@ -53,7 +62,14 @@ exports.appToolsManifest = {
                         },
                         "analysisType": {
                             "type": "string",
-                            "enum": ["summary", "timeline", "scene", "action", "ocr", "general"],
+                            "enum": [
+                                "summary",
+                                "timeline",
+                                "scene",
+                                "action",
+                                "ocr",
+                                "general"
+                            ],
                             "description": "Type of analysis. Use general when answering the user's specific question."
                         },
                         "sourceVideoIndex": {
@@ -65,7 +81,9 @@ exports.appToolsManifest = {
                             "description": "Whether to sample more context and provide a more detailed analysis."
                         }
                     },
-                    "required": ["query"]
+                    "required": [
+                        "query"
+                    ]
                 }
             }
         },
@@ -79,7 +97,11 @@ exports.appToolsManifest = {
                     "properties": {
                         "mediaType": {
                             "type": "string",
-                            "enum": ["image", "video", "audio"],
+                            "enum": [
+                                "image",
+                                "video",
+                                "audio"
+                            ],
                             "description": "Media type to inspect. Omit when the available context makes it unambiguous."
                         },
                         "sourceImageIndex": {
@@ -119,7 +141,9 @@ exports.appToolsManifest = {
                             "description": "Short telemetry tag explaining why clarification is needed."
                         }
                     },
-                    "required": ["question"]
+                    "required": [
+                        "question"
+                    ]
                 }
             }
         },
@@ -137,11 +161,19 @@ exports.appToolsManifest = {
                         },
                         "outcome": {
                             "type": "string",
-                            "enum": ["success", "partial", "asked_user", "failed", "no_action"],
+                            "enum": [
+                                "success",
+                                "partial",
+                                "asked_user",
+                                "failed",
+                                "no_action"
+                            ],
                             "description": "How the turn ended."
                         }
                     },
-                    "required": ["outcome"]
+                    "required": [
+                        "outcome"
+                    ]
                 }
             }
         },
@@ -165,7 +197,11 @@ exports.appToolsManifest = {
                                     },
                                     "type": {
                                         "type": "string",
-                                        "enum": ["image", "video", "audio"],
+                                        "enum": [
+                                            "image",
+                                            "video",
+                                            "audio"
+                                        ],
                                         "description": "Asset media type."
                                     },
                                     "description": {
@@ -178,12 +214,16 @@ exports.appToolsManifest = {
                                     },
                                     "must_preserve": {
                                         "type": "array",
-                                        "items": { "type": "string" },
+                                        "items": {
+                                            "type": "string"
+                                        },
                                         "description": "Features to preserve when regenerating from this asset."
                                     },
                                     "avoid": {
                                         "type": "array",
-                                        "items": { "type": "string" },
+                                        "items": {
+                                            "type": "string"
+                                        },
                                         "description": "Features to avoid."
                                     },
                                     "asset_id": {
@@ -191,11 +231,16 @@ exports.appToolsManifest = {
                                         "description": "Optional stable id override."
                                     }
                                 },
-                                "required": ["user_label", "type"]
+                                "required": [
+                                    "user_label",
+                                    "type"
+                                ]
                             }
                         }
                     },
-                    "required": ["assets"]
+                    "required": [
+                        "assets"
+                    ]
                 }
             }
         },
@@ -241,12 +286,16 @@ exports.appToolsManifest = {
                         },
                         "must_preserve": {
                             "type": "array",
-                            "items": { "type": "string" },
+                            "items": {
+                                "type": "string"
+                            },
                             "description": "Replacement preserve list."
                         },
                         "avoid": {
                             "type": "array",
-                            "items": { "type": "string" },
+                            "items": {
+                                "type": "string"
+                            },
                             "description": "Replacement avoid list."
                         },
                         "url": {
@@ -254,7 +303,9 @@ exports.appToolsManifest = {
                             "description": "Replacement URL. Empty string clears it."
                         }
                     },
-                    "required": ["asset_id"]
+                    "required": [
+                        "asset_id"
+                    ]
                 }
             }
         },
@@ -271,7 +322,9 @@ exports.appToolsManifest = {
                             "description": "Target model identifier."
                         }
                     },
-                    "required": ["model_id"]
+                    "required": [
+                        "model_id"
+                    ]
                 }
             }
         },
@@ -292,7 +345,10 @@ exports.appToolsManifest = {
                             "description": "Prompt text to validate."
                         }
                     },
-                    "required": ["model_id", "prompt"]
+                    "required": [
+                        "model_id",
+                        "prompt"
+                    ]
                 }
             }
         }
@@ -316,18 +372,78 @@ exports.compositionToolsManifest = {
                 "parameters": {
                     "type": "object",
                     "additionalProperties": false,
-                    "required": ["prompt", "target_output", "destination_model"],
+                    "required": [
+                        "prompt",
+                        "target_output",
+                        "destination_model"
+                    ],
                     "properties": {
-                        "prompt": { "type": "string", "description": "The source prompt, rough idea, or prompt revision request to enhance." },
-                        "target_output": { "type": "string", "enum": ["image_prompt", "video_prompt", "edit_prompt", "model_prompt"], "description": "The model-specific prompt artifact to produce. Use model_prompt only when destination_model unambiguously identifies the modality." },
-                        "destination_model": { "type": "string", "description": "Required exact active destination model selector, such as seedance2, ltx25, ltx23, wan22, minimax-h3-turbo, qwen, gpt-image-2, krea-2-turbo, chroma-v46-flash, or sdxl. Unknown and sunset models fail closed." },
-                        "destination_tool": { "type": "string", "description": "Optional downstream generation tool, such as generate_image, edit_image, generate_video, animate_photo, sound_to_video, or video_to_video." },
-                        "prompting_type": { "type": "string", "enum": ["flux", "sdxl", "sd15", "pony", "fast", "sd3", "editing", "video"], "description": "Deprecated compatibility metadata. It never selects or overrides the prompt grammar; destination_model is authoritative." },
-                        "model_title": { "type": "string", "description": "Deprecated compatibility label. It never selects or overrides the prompt grammar; destination_model is authoritative." },
-                        "style_prompt": { "type": "string", "description": "Optional current style, brand, or prompt context to complement without repeating." },
-                        "prompt_mode": { "type": "string", "enum": ["auto", "preserve", "expand", "compress", "validate", "payload"], "description": "Optional model prompt adaptation mode." },
-                        "duration_seconds": { "type": "number", "minimum": 1, "maximum": 300, "description": "Requested runtime when authoring a video prompt." },
-                        "aspect_ratio": { "type": "string", "description": "Optional target aspect ratio, such as 16:9, 9:16, 1:1, 4:5, or 21:9." },
+                        "prompt": {
+                            "type": "string",
+                            "description": "The source prompt, rough idea, or prompt revision request to enhance."
+                        },
+                        "target_output": {
+                            "type": "string",
+                            "enum": [
+                                "image_prompt",
+                                "video_prompt",
+                                "edit_prompt",
+                                "model_prompt"
+                            ],
+                            "description": "The model-specific prompt artifact to produce. Use model_prompt only when destination_model unambiguously identifies the modality."
+                        },
+                        "destination_model": {
+                            "type": "string",
+                            "description": "Required exact active destination model selector, such as seedance2, ltx25, ltx23, wan22, minimax-h3-turbo, qwen, gpt-image-2, krea-2-turbo, chroma-v46-flash, or sdxl. Unknown and sunset models fail closed."
+                        },
+                        "destination_tool": {
+                            "type": "string",
+                            "description": "Optional downstream generation tool, such as generate_image, edit_image, generate_video, animate_photo, sound_to_video, or video_to_video."
+                        },
+                        "prompting_type": {
+                            "type": "string",
+                            "enum": [
+                                "flux",
+                                "sdxl",
+                                "sd15",
+                                "pony",
+                                "fast",
+                                "sd3",
+                                "editing",
+                                "video"
+                            ],
+                            "description": "Deprecated compatibility metadata. It never selects or overrides the prompt grammar; destination_model is authoritative."
+                        },
+                        "model_title": {
+                            "type": "string",
+                            "description": "Deprecated compatibility label. It never selects or overrides the prompt grammar; destination_model is authoritative."
+                        },
+                        "style_prompt": {
+                            "type": "string",
+                            "description": "Optional current style, brand, or prompt context to complement without repeating."
+                        },
+                        "prompt_mode": {
+                            "type": "string",
+                            "enum": [
+                                "auto",
+                                "preserve",
+                                "expand",
+                                "compress",
+                                "validate",
+                                "payload"
+                            ],
+                            "description": "Optional model prompt adaptation mode."
+                        },
+                        "duration_seconds": {
+                            "type": "number",
+                            "minimum": 1,
+                            "maximum": 300,
+                            "description": "Requested runtime when authoring a video prompt."
+                        },
+                        "aspect_ratio": {
+                            "type": "string",
+                            "description": "Optional target aspect ratio, such as 16:9, 9:16, 1:1, 4:5, or 21:9."
+                        },
                         "assets": {
                             "type": "array",
                             "maxItems": 50,
@@ -335,17 +451,47 @@ exports.compositionToolsManifest = {
                             "items": {
                                 "type": "object",
                                 "additionalProperties": false,
-                                "required": ["media_type"],
+                                "required": [
+                                    "media_type"
+                                ],
                                 "properties": {
-                                    "id": { "type": "string" },
-                                    "label": { "type": "string" },
-                                    "media_type": { "type": "string", "enum": ["image", "video", "audio"] },
-                                    "role": { "type": "string", "enum": ["first_frame", "last_frame", "reference", "identity", "style", "motion", "audio", "source_video"] },
-                                    "url": { "type": "string" }
+                                    "id": {
+                                        "type": "string"
+                                    },
+                                    "label": {
+                                        "type": "string"
+                                    },
+                                    "media_type": {
+                                        "type": "string",
+                                        "enum": [
+                                            "image",
+                                            "video",
+                                            "audio"
+                                        ]
+                                    },
+                                    "role": {
+                                        "type": "string",
+                                        "enum": [
+                                            "first_frame",
+                                            "last_frame",
+                                            "reference",
+                                            "identity",
+                                            "style",
+                                            "motion",
+                                            "audio",
+                                            "source_video"
+                                        ]
+                                    },
+                                    "url": {
+                                        "type": "string"
+                                    }
                                 }
                             }
                         },
-                        "constraints": { "type": "object", "description": "Optional production, brand, model, or user constraints to preserve." }
+                        "constraints": {
+                            "type": "object",
+                            "description": "Optional production, brand, model, or user constraints to preserve."
+                        }
                     }
                 }
             }
@@ -358,12 +504,28 @@ exports.compositionToolsManifest = {
                 "parameters": {
                     "type": "object",
                     "additionalProperties": false,
-                    "required": ["prompt"],
+                    "required": [
+                        "prompt"
+                    ],
                     "properties": {
-                        "prompt": { "type": "string", "description": "The song topic, mood, genre, scene, campaign, or lyric request." },
-                        "language": { "type": "string", "description": "Optional language code or language name for the lyrics." },
-                        "music_prompt": { "type": "string", "description": "Optional musical style context, genre, instrumentation, mood, or production direction." },
-                        "duration_seconds": { "type": "number", "minimum": 10, "maximum": 600, "description": "Optional desired song duration in seconds." }
+                        "prompt": {
+                            "type": "string",
+                            "description": "The song topic, mood, genre, scene, campaign, or lyric request."
+                        },
+                        "language": {
+                            "type": "string",
+                            "description": "Optional language code or language name for the lyrics."
+                        },
+                        "music_prompt": {
+                            "type": "string",
+                            "description": "Optional musical style context, genre, instrumentation, mood, or production direction."
+                        },
+                        "duration_seconds": {
+                            "type": "number",
+                            "minimum": 10,
+                            "maximum": 600,
+                            "description": "Optional desired song duration in seconds."
+                        }
                     }
                 }
             }
@@ -376,11 +538,24 @@ exports.compositionToolsManifest = {
                 "parameters": {
                     "type": "object",
                     "additionalProperties": false,
-                    "required": ["prompt"],
+                    "required": [
+                        "prompt"
+                    ],
                     "properties": {
-                        "prompt": { "type": "string", "description": "The instrumental music topic, mood, genre, scene, campaign, or composition request." },
-                        "music_prompt": { "type": "string", "description": "Optional musical style context, instrumentation, mood, or production direction." },
-                        "duration_seconds": { "type": "number", "minimum": 10, "maximum": 600, "description": "Optional desired track duration in seconds." }
+                        "prompt": {
+                            "type": "string",
+                            "description": "The instrumental music topic, mood, genre, scene, campaign, or composition request."
+                        },
+                        "music_prompt": {
+                            "type": "string",
+                            "description": "Optional musical style context, instrumentation, mood, or production direction."
+                        },
+                        "duration_seconds": {
+                            "type": "number",
+                            "minimum": 10,
+                            "maximum": 600,
+                            "description": "Optional desired track duration in seconds."
+                        }
                     }
                 }
             }
@@ -393,21 +568,82 @@ exports.compositionToolsManifest = {
                 "parameters": {
                     "type": "object",
                     "additionalProperties": false,
-                    "required": ["brief"],
+                    "required": [
+                        "brief"
+                    ],
                     "properties": {
-                        "brief": { "type": "string", "description": "The creative writing brief, story idea, product concept, video idea, or revision request." },
-                        "script_type": { "type": "string", "enum": ["video_prompt", "screenplay", "storyboard", "ad_script", "trailer", "social_short", "talking_head", "campaign", "revision"], "description": "The kind of script or creative writing artifact to produce." },
-                        "destination_model": { "type": "string", "description": "Optional destination video model selector, such as ltx23, wan22, or seedance2." },
-                        "destination_tool": { "type": "string", "description": "Optional downstream tool, such as generate_video, animate_photo, sound_to_video, or video_to_video." },
-                        "duration_seconds": { "type": "number", "minimum": 1, "maximum": 300, "description": "Requested runtime for a video prompt, social short, ad, or talking-head script." },
-                        "scene_count": { "type": "integer", "minimum": 1, "maximum": 12, "description": "Requested number of scenes, shots, beats, or storyboard panels." },
-                        "aspect_ratio": { "type": "string", "description": "Optional target aspect ratio, such as 16:9, 9:16, 1:1, 4:5, or 21:9." },
-                        "platform": { "type": "string", "description": "Optional target platform or context, such as TikTok, YouTube Shorts, Instagram Reels, broadcast, landing page, game trailer, or pitch deck." },
-                        "style": { "type": "string", "description": "Optional style, genre, tone, visual treatment, or brand voice to preserve." },
-                        "first_frame_description": { "type": "string", "description": "Optional description of the starting frame when composing an image-to-video prompt without attached vision content." },
-                        "first_frame_data_url": { "type": "string", "description": "Optional inline image data URI for the starting frame when composing an image-to-video or first-frame video prompt." },
-                        "last_frame_data_url": { "type": "string", "description": "Optional inline image data URI for the ending frame when composing an image-to-video transition prompt." },
-                        "return_format": { "type": "string", "enum": ["script", "markdown", "json"], "description": "Requested output format. Use script unless structured planning output is explicitly needed." }
+                        "brief": {
+                            "type": "string",
+                            "description": "The creative writing brief, story idea, product concept, video idea, or revision request."
+                        },
+                        "script_type": {
+                            "type": "string",
+                            "enum": [
+                                "video_prompt",
+                                "screenplay",
+                                "storyboard",
+                                "ad_script",
+                                "trailer",
+                                "social_short",
+                                "talking_head",
+                                "campaign",
+                                "revision"
+                            ],
+                            "description": "The kind of script or creative writing artifact to produce."
+                        },
+                        "destination_model": {
+                            "type": "string",
+                            "description": "Optional destination video model selector, such as ltx23, wan22, or seedance2."
+                        },
+                        "destination_tool": {
+                            "type": "string",
+                            "description": "Optional downstream tool, such as generate_video, animate_photo, sound_to_video, or video_to_video."
+                        },
+                        "duration_seconds": {
+                            "type": "number",
+                            "minimum": 1,
+                            "maximum": 300,
+                            "description": "Requested runtime for a video prompt, social short, ad, or talking-head script."
+                        },
+                        "scene_count": {
+                            "type": "integer",
+                            "minimum": 1,
+                            "maximum": 12,
+                            "description": "Requested number of scenes, shots, beats, or storyboard panels."
+                        },
+                        "aspect_ratio": {
+                            "type": "string",
+                            "description": "Optional target aspect ratio, such as 16:9, 9:16, 1:1, 4:5, or 21:9."
+                        },
+                        "platform": {
+                            "type": "string",
+                            "description": "Optional target platform or context, such as TikTok, YouTube Shorts, Instagram Reels, broadcast, landing page, game trailer, or pitch deck."
+                        },
+                        "style": {
+                            "type": "string",
+                            "description": "Optional style, genre, tone, visual treatment, or brand voice to preserve."
+                        },
+                        "first_frame_description": {
+                            "type": "string",
+                            "description": "Optional description of the starting frame when composing an image-to-video prompt without attached vision content."
+                        },
+                        "first_frame_data_url": {
+                            "type": "string",
+                            "description": "Optional inline image data URI for the starting frame when composing an image-to-video or first-frame video prompt."
+                        },
+                        "last_frame_data_url": {
+                            "type": "string",
+                            "description": "Optional inline image data URI for the ending frame when composing an image-to-video transition prompt."
+                        },
+                        "return_format": {
+                            "type": "string",
+                            "enum": [
+                                "script",
+                                "markdown",
+                                "json"
+                            ],
+                            "description": "Requested output format. Use script unless structured planning output is explicitly needed."
+                        }
                     }
                 }
             }
@@ -420,25 +656,76 @@ exports.compositionToolsManifest = {
                 "parameters": {
                     "type": "object",
                     "additionalProperties": false,
-                    "required": ["brief"],
+                    "required": [
+                        "brief"
+                    ],
                     "properties": {
-                        "brief": { "type": "string", "description": "Creative brief describing what the workflow should produce. Free-form natural language. Required." },
-                        "scene_count": { "type": "integer", "minimum": 1, "maximum": 12, "description": "Suggested number of distinct shots/scenes. The planner may produce more steps than scenes (e.g., keyframe + clip per scene)." },
-                        "duration_seconds": { "type": "number", "minimum": 1, "maximum": 120, "description": "Target total duration in seconds for video-bearing plans." },
-                        "aspect_ratio": { "type": "string", "enum": ["1:1", "4:3", "3:4", "16:9", "9:16", "21:9"], "description": "Output aspect ratio." },
-                        "style": { "type": "string", "description": "Optional stylistic guidance (e.g., 'cinematic, neon, low-key', 'whiteboard illustration')." },
+                        "brief": {
+                            "type": "string",
+                            "description": "Creative brief describing what the workflow should produce. Free-form natural language. Required."
+                        },
+                        "scene_count": {
+                            "type": "integer",
+                            "minimum": 1,
+                            "maximum": 12,
+                            "description": "Suggested number of distinct shots/scenes. The planner may produce more steps than scenes (e.g., keyframe + clip per scene)."
+                        },
+                        "duration_seconds": {
+                            "type": "number",
+                            "minimum": 1,
+                            "maximum": 120,
+                            "description": "Target total duration in seconds for video-bearing plans."
+                        },
+                        "aspect_ratio": {
+                            "type": "string",
+                            "enum": [
+                                "1:1",
+                                "4:3",
+                                "3:4",
+                                "16:9",
+                                "9:16",
+                                "21:9"
+                            ],
+                            "description": "Output aspect ratio."
+                        },
+                        "style": {
+                            "type": "string",
+                            "description": "Optional stylistic guidance (e.g., 'cinematic, neon, low-key', 'whiteboard illustration')."
+                        },
                         "destination_models": {
                             "type": "object",
                             "additionalProperties": false,
                             "properties": {
-                                "image": { "type": "string", "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')." },
-                                "video": { "type": "string", "description": "Preferred video model (e.g., 'ltx23', 'wan22', 'seedance2')." },
-                                "music": { "type": "string", "description": "Preferred music model." }
+                                "image": {
+                                    "type": "string",
+                                    "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')."
+                                },
+                                "video": {
+                                    "type": "string",
+                                    "description": "Preferred video model (e.g., 'ltx23', 'wan22', 'seedance2')."
+                                },
+                                "music": {
+                                    "type": "string",
+                                    "description": "Preferred music model."
+                                }
                             }
                         },
-                        "max_estimated_capacity_units": { "type": "integer", "minimum": 1, "description": "If set, the planner attempts to keep total estimated cost at or below this value and returns `fits_budget: false` if it cannot." },
-                        "include_audio": { "type": "boolean", "description": "If true, include a music generation step. Defaults to false." },
-                        "return_format": { "type": "string", "enum": ["json"], "description": "Currently `json` is the only supported value. Reserved for future." }
+                        "max_estimated_capacity_units": {
+                            "type": "integer",
+                            "minimum": 1,
+                            "description": "If set, the planner attempts to keep total estimated cost at or below this value and returns `fits_budget: false` if it cannot."
+                        },
+                        "include_audio": {
+                            "type": "boolean",
+                            "description": "If true, include a music generation step. Defaults to false."
+                        },
+                        "return_format": {
+                            "type": "string",
+                            "enum": [
+                                "json"
+                            ],
+                            "description": "Currently `json` is the only supported value. Reserved for future."
+                        }
                     }
                 }
             }
@@ -451,13 +738,47 @@ exports.compositionToolsManifest = {
                 "parameters": {
                     "type": "object",
                     "additionalProperties": false,
-                    "required": ["brief", "name"],
+                    "required": [
+                        "brief",
+                        "name"
+                    ],
                     "properties": {
-                        "brief": { "type": "string", "description": "Creative brief describing what the workflow should produce. Free-form natural language. Required." },
-                        "name": { "type": "string", "minLength": 1, "maxLength": 200, "description": "Human-readable template name (e.g. \"My Plastic Dream — TikTok/Reels\"). Required." },
-                        "description": { "type": "string", "description": "Optional template description. If omitted, the planner may derive one from the brief." },
-                        "category": { "type": "string", "enum": ["portrait", "video-social", "makeover", "cinematic", "music", "analysis", "custom", "other"], "description": "Optional category for surfacing the template in the library. Defaults to 'custom' when omitted." },
-                        "visibility": { "type": "string", "enum": ["private", "public"], "description": "Persistence visibility. Defaults to 'private'. The 'team' visibility is reserved for a later milestone." },
+                        "brief": {
+                            "type": "string",
+                            "description": "Creative brief describing what the workflow should produce. Free-form natural language. Required."
+                        },
+                        "name": {
+                            "type": "string",
+                            "minLength": 1,
+                            "maxLength": 200,
+                            "description": "Human-readable template name (e.g. \"My Plastic Dream — TikTok/Reels\"). Required."
+                        },
+                        "description": {
+                            "type": "string",
+                            "description": "Optional template description. If omitted, the planner may derive one from the brief."
+                        },
+                        "category": {
+                            "type": "string",
+                            "enum": [
+                                "portrait",
+                                "video-social",
+                                "makeover",
+                                "cinematic",
+                                "music",
+                                "analysis",
+                                "custom",
+                                "other"
+                            ],
+                            "description": "Optional category for surfacing the template in the library. Defaults to 'custom' when omitted."
+                        },
+                        "visibility": {
+                            "type": "string",
+                            "enum": [
+                                "private",
+                                "public"
+                            ],
+                            "description": "Persistence visibility. Defaults to 'private'. The 'team' visibility is reserved for a later milestone."
+                        },
                         "inputs": {
                             "type": "array",
                             "maxItems": 16,
@@ -465,56 +786,149 @@ exports.compositionToolsManifest = {
                             "items": {
                                 "type": "object",
                                 "additionalProperties": false,
-                                "required": ["name", "type"],
+                                "required": [
+                                    "name",
+                                    "type"
+                                ],
                                 "properties": {
-                                    "name": { "type": "string", "minLength": 1, "maxLength": 64, "description": "Input name; used as the placeholder key (e.g. $inputs.motion_source_video)." },
-                                    "type": { "type": "string", "enum": ["image", "audio", "video", "text", "number", "select", "boolean"], "description": "Input value type. URL string for image/audio/video; primitive for the rest." },
-                                    "required": { "type": "boolean", "description": "Whether the input must be supplied at run time. Defaults to false." },
-                                    "description": { "type": "string", "description": "Human-readable description shown in the launcher UI." },
-                                    "default": { "description": "Optional default value. Type must match `type`." },
+                                    "name": {
+                                        "type": "string",
+                                        "minLength": 1,
+                                        "maxLength": 64,
+                                        "description": "Input name; used as the placeholder key (e.g. $inputs.motion_source_video)."
+                                    },
+                                    "type": {
+                                        "type": "string",
+                                        "enum": [
+                                            "image",
+                                            "audio",
+                                            "video",
+                                            "text",
+                                            "number",
+                                            "select",
+                                            "boolean"
+                                        ],
+                                        "description": "Input value type. URL string for image/audio/video; primitive for the rest."
+                                    },
+                                    "required": {
+                                        "type": "boolean",
+                                        "description": "Whether the input must be supplied at run time. Defaults to false."
+                                    },
+                                    "description": {
+                                        "type": "string",
+                                        "description": "Human-readable description shown in the launcher UI."
+                                    },
+                                    "default": {
+                                        "description": "Optional default value. Type must match `type`."
+                                    },
                                     "options": {
                                         "type": "array",
                                         "description": "Allowed enum values for `select` inputs.",
                                         "items": {
                                             "type": "object",
                                             "additionalProperties": false,
-                                            "required": ["value", "label"],
+                                            "required": [
+                                                "value",
+                                                "label"
+                                            ],
                                             "properties": {
-                                                "value": { "type": "string" },
-                                                "label": { "type": "string" }
+                                                "value": {
+                                                    "type": "string"
+                                                },
+                                                "label": {
+                                                    "type": "string"
+                                                }
                                             }
                                         }
                                     },
                                     "multiple": {
                                         "type": "object",
                                         "additionalProperties": false,
-                                        "required": ["min", "max"],
+                                        "required": [
+                                            "min",
+                                            "max"
+                                        ],
                                         "description": "Set when the input accepts an array of values.",
                                         "properties": {
-                                            "min": { "type": "integer", "minimum": 0 },
-                                            "max": { "type": "integer", "minimum": 1 }
+                                            "min": {
+                                                "type": "integer",
+                                                "minimum": 0
+                                            },
+                                            "max": {
+                                                "type": "integer",
+                                                "minimum": 1
+                                            }
                                         }
                                     },
-                                    "internal": { "type": "boolean", "description": "Internal inputs are seeded at run-create time and hidden from the launcher UI." }
+                                    "internal": {
+                                        "type": "boolean",
+                                        "description": "Internal inputs are seeded at run-create time and hidden from the launcher UI."
+                                    }
                                 }
                             }
                         },
-                        "scene_count": { "type": "integer", "minimum": 1, "maximum": 12, "description": "Suggested number of distinct shots/scenes. The planner may produce more steps than scenes (e.g., keyframe + clip per scene)." },
-                        "duration_seconds": { "type": "number", "minimum": 1, "maximum": 120, "description": "Target total duration in seconds for video-bearing plans." },
-                        "aspect_ratio": { "type": "string", "enum": ["1:1", "4:3", "3:4", "16:9", "9:16", "21:9"], "description": "Output aspect ratio." },
-                        "style": { "type": "string", "description": "Optional stylistic guidance (e.g., 'cinematic, neon, low-key', 'whiteboard illustration')." },
+                        "scene_count": {
+                            "type": "integer",
+                            "minimum": 1,
+                            "maximum": 12,
+                            "description": "Suggested number of distinct shots/scenes. The planner may produce more steps than scenes (e.g., keyframe + clip per scene)."
+                        },
+                        "duration_seconds": {
+                            "type": "number",
+                            "minimum": 1,
+                            "maximum": 120,
+                            "description": "Target total duration in seconds for video-bearing plans."
+                        },
+                        "aspect_ratio": {
+                            "type": "string",
+                            "enum": [
+                                "1:1",
+                                "4:3",
+                                "3:4",
+                                "16:9",
+                                "9:16",
+                                "21:9"
+                            ],
+                            "description": "Output aspect ratio."
+                        },
+                        "style": {
+                            "type": "string",
+                            "description": "Optional stylistic guidance (e.g., 'cinematic, neon, low-key', 'whiteboard illustration')."
+                        },
                         "destination_models": {
                             "type": "object",
                             "additionalProperties": false,
                             "properties": {
-                                "image": { "type": "string", "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')." },
-                                "video": { "type": "string", "description": "Preferred video model (e.g., 'ltx23', 'wan22', 'seedance2')." },
-                                "music": { "type": "string", "description": "Preferred music model." }
+                                "image": {
+                                    "type": "string",
+                                    "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')."
+                                },
+                                "video": {
+                                    "type": "string",
+                                    "description": "Preferred video model (e.g., 'ltx23', 'wan22', 'seedance2')."
+                                },
+                                "music": {
+                                    "type": "string",
+                                    "description": "Preferred music model."
+                                }
                             }
                         },
-                        "max_estimated_capacity_units": { "type": "integer", "minimum": 1, "description": "If set, the planner attempts to keep total estimated cost at or below this value and returns `fits_budget: false` if it cannot." },
-                        "include_audio": { "type": "boolean", "description": "If true, include a music generation step. Defaults to false." },
-                        "return_format": { "type": "string", "enum": ["json"], "description": "Currently `json` is the only supported value. Reserved for future." },
+                        "max_estimated_capacity_units": {
+                            "type": "integer",
+                            "minimum": 1,
+                            "description": "If set, the planner attempts to keep total estimated cost at or below this value and returns `fits_budget: false` if it cannot."
+                        },
+                        "include_audio": {
+                            "type": "boolean",
+                            "description": "If true, include a music generation step. Defaults to false."
+                        },
+                        "return_format": {
+                            "type": "string",
+                            "enum": [
+                                "json"
+                            ],
+                            "description": "Currently `json` is the only supported value. Reserved for future."
+                        },
                         "existing_template": {
                             "type": "object",
                             "additionalProperties": true,
@@ -681,7 +1095,7 @@ exports.generationToolsManifest = {
             "type": "function",
             "function": {
                 "name": "generate_video",
-                "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, or seedance2-5, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance generate_video call by default; do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render the composite board, audit it, generate per-scene GPT Image 2 keyframes, then render Seedance scene clips and stitch them. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode.",
+                "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, or seedance2-5, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance generate_video call by default; do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render the composite board, audit it, generate per-scene GPT Image 2 keyframes, then render Seedance scene clips and stitch them. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
                 "parameters": {
                     "type": "object",
                     "properties": {
@@ -721,15 +1135,15 @@ exports.generationToolsManifest = {
                         },
                         "watermark": {
                             "type": "boolean",
-                            "description": "Wan 3 only. Add Alibaba's visible watermark. Defaults to false."
+                            "description": "Alibaba wan3.0-video only. Add the visible watermark. Defaults to false."
                         },
                         "referenceFileUrl": {
                             "type": "string",
-                            "description": "Wan 3 only. One public HTTPS document URL for context (DOCX/DOC/XLSX/XLS/PPTX/PPT/PDF/TXT/KEY/PAGES/NUMBERS/Markdown, up to 100 MB; PDF/DOCX/DOC/PPTX/PPT/KEY/PAGES up to 50 pages). Mutually exclusive with referenceLinkUrl and first/last-frame inputs."
+                            "description": "Alibaba wan3.0-video only. One public HTTPS document URL for context (DOCX/DOC/XLSX/XLS/PPTX/PPT/PDF/TXT/KEY/PAGES/NUMBERS/Markdown, up to 100 MB; PDF/DOCX/DOC/PPTX/PPT/KEY/PAGES up to 50 pages). Mutually exclusive with referenceLinkUrl and first/last-frame inputs."
                         },
                         "referenceLinkUrl": {
                             "type": "string",
-                            "description": "Wan 3 only. One public HTTPS webpage URL for context. Mutually exclusive with referenceFileUrl and first/last-frame inputs."
+                            "description": "Alibaba wan3.0-video only. One public HTTPS webpage URL for context. Mutually exclusive with referenceFileUrl and first/last-frame inputs."
                         },
                         "negativePrompt": {
                             "type": "string",
@@ -751,9 +1165,10 @@ exports.generationToolsManifest = {
                                 "happyhorse-1.1-r2v",
                                 "minimax-h3-r2v",
                                 "minimax-h3-r2v-turbo",
-                                "wan3.0-video"
+                                "wan3.0-video",
+                                "wan3.0-spicy-video"
                             ],
-                            "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": 4-step Turbo text-to-video. Both use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. Both accept up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, and use \"seedance2\" for the full Seedance 2.0 model, explicit full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft or Mini. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance supports multimodal loose reference assets: images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3: one canonical premium-vendor model for text, first/last frames, loose multimodal references, audio-driven generation, and document/web context. It renders 2-30s or smart duration at fixed 30 fps with optional native audio, prompt expansion control, optional watermark, 480p/720p/1080p, and adaptive/16:9/4:3/1:1/3:4/9:16 ratios. It accepts up to 10 images, 5 videos, 5 audios, one file, or one webpage. Do not send negativePrompt. Use animate_photo for native first/last frames, generate_video for text or loose references, and sound_to_video when audio drives timing. Video references provide loose conditioning for a new result, not source-video editing or extension."
+                            "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": 4-step Turbo text-to-video. Both use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. Both accept up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, and use \"seedance2\" for the full Seedance 2.0 model, explicit full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft or Mini. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance supports multimodal loose reference assets: images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s or smart duration at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
                         },
                         "generateAudio": {
                             "type": "boolean",
@@ -1156,7 +1571,7 @@ exports.generationToolsManifest = {
             "type": "function",
             "function": {
                 "name": "animate_photo",
-                "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, or seedance2-5. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\".",
+                "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, or seedance2-5. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
                 "parameters": {
                     "type": "object",
                     "properties": {
@@ -1184,9 +1599,10 @@ exports.generationToolsManifest = {
                                 "minimax-h3-i2v-turbo",
                                 "minimax-h3-flf2v",
                                 "minimax-h3-flf2v-turbo",
-                                "wan3.0-video"
+                                "wan3.0-video",
+                                "wan3.0-spicy-video"
                             ],
-                            "description": "\"ltx25\" (default): LTX 2.5 I2V or first/last-frame video with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Which video model to use. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio, up to 10s. \"minimax-h3-i2v\" and \"minimax-h3-i2v-turbo\": standard and 4-step Turbo MiniMax H3 from one first frame. \"minimax-h3-flf2v\" and \"minimax-h3-flf2v-turbo\": standard and 4-step Turbo MiniMax H3 between required first and last frames; use frameRole=\"both\" and provide the end frame. H3 generates native audio at fixed 24fps for 5.17-15.08s and has no negative-prompt input. H3 Base and Turbo prompts use the exact three-field contract and the official mode-specific alignment line. Do not set Seedance here; use generate_video with Seedance references. \"wan3.0-video\" is Alibaba Wan 3: one canonical premium-vendor model for text-to-video, first-frame and first+last-frame animation, loose multimodal references, and audio-driven generation. It renders 2-30s at fixed 30 fps with optional native audio, supports 480p/720p/1080p and 16:9/4:3/1:1/3:4/9:16, accepts up to 10 reference images, 5 reference videos, and 5 reference audios, and uses plain per-type prompt labels Image 1, Video 1, and Audio 1. Do not send negativePrompt. Use animate_photo for native first/last frames, generate_video for text or loose references, and sound_to_video when audio is the primary driver. Video references are loose conditioning, not source-video edit or extend modes."
+                            "description": "\"ltx25\" (default): LTX 2.5 I2V or first/last-frame video with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Which video model to use. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio, up to 10s. \"minimax-h3-i2v\" and \"minimax-h3-i2v-turbo\": standard and 4-step Turbo MiniMax H3 from one first frame. \"minimax-h3-flf2v\" and \"minimax-h3-flf2v-turbo\": standard and 4-step Turbo MiniMax H3 between required first and last frames; use frameRole=\"both\" and provide the end frame. H3 generates native audio at fixed 24fps for 5.17-15.08s and has no negative-prompt input. H3 Base and Turbo prompts use the exact three-field contract and the official mode-specific alignment line. Do not set Seedance here; use generate_video with Seedance references. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s or smart duration at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
                         },
                         "negativePrompt": {
                             "type": "string",
@@ -1218,7 +1634,7 @@ exports.generationToolsManifest = {
                         },
                         "watermark": {
                             "type": "boolean",
-                            "description": "Wan 3 only. Add Alibaba's visible watermark. Defaults to false."
+                            "description": "Alibaba wan3.0-video only. Add the visible watermark. Defaults to false."
                         },
                         "targetResolution": {
                             "type": "number",
@@ -1624,7 +2040,7 @@ exports.generationToolsManifest = {
             "type": "function",
             "function": {
                 "name": "sound_to_video",
-                "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, or seedance2-5), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video.",
+                "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, or seedance2-5), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports smart duration, adaptive ratios, and provider prompt expansion.",
                 "parameters": {
                     "type": "object",
                     "properties": {
@@ -1677,15 +2093,15 @@ exports.generationToolsManifest = {
                         },
                         "watermark": {
                             "type": "boolean",
-                            "description": "Wan 3 only. Add Alibaba's visible watermark. Defaults to false."
+                            "description": "Alibaba wan3.0-video only. Add the visible watermark. Defaults to false."
                         },
                         "referenceFileUrl": {
                             "type": "string",
-                            "description": "Wan 3 only. One public HTTPS document URL for additional audio-driven context (DOCX/DOC/XLSX/XLS/PPTX/PPT/PDF/TXT/KEY/PAGES/NUMBERS/Markdown, up to 100 MB; PDF/DOCX/DOC/PPTX/PPT/KEY/PAGES up to 50 pages). Mutually exclusive with referenceLinkUrl."
+                            "description": "Alibaba wan3.0-video only. One public HTTPS document URL for additional audio-driven context (DOCX/DOC/XLSX/XLS/PPTX/PPT/PDF/TXT/KEY/PAGES/NUMBERS/Markdown, up to 100 MB; PDF/DOCX/DOC/PPTX/PPT/KEY/PAGES up to 50 pages). Mutually exclusive with referenceLinkUrl."
                         },
                         "referenceLinkUrl": {
                             "type": "string",
-                            "description": "Wan 3 only. One public HTTPS webpage URL for additional audio-driven context. Mutually exclusive with referenceFileUrl."
+                            "description": "Alibaba wan3.0-video only. One public HTTPS webpage URL for additional audio-driven context. Mutually exclusive with referenceFileUrl."
                         },
                         "videoModel": {
                             "type": "string",
@@ -1698,9 +2114,10 @@ exports.generationToolsManifest = {
                                 "ltx25-a2v",
                                 "ltx23-ia2v",
                                 "ltx23-a2v",
-                                "wan3.0-video"
+                                "wan3.0-video",
+                                "wan3.0-spicy-video"
                             ],
-                            "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3: one canonical premium-vendor model for text-to-video, first-frame and first+last-frame animation, loose multimodal references, and audio-driven generation. It renders 2-30s at fixed 30 fps with optional native audio, supports 480p/720p/1080p and 16:9/4:3/1:1/3:4/9:16, accepts up to 10 reference images, 5 reference videos, and 5 reference audios, and uses plain per-type prompt labels Image 1, Video 1, and Audio 1. Do not send negativePrompt. Use animate_photo for native first/last frames, generate_video for text or loose references, and sound_to_video when audio is the primary driver. Video references are loose conditioning, not source-video edit or extend modes."
+                            "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s or smart duration at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
                         },
                         "generateAudio": {
                             "type": "boolean",