@sogni-ai/sogni-intelligence-client 2.1.0

package/dist-esm/tools/definitions/dance-montage/definition.js

@@ -0,0 +1,42 @@
+import { DANCE_PRESETS } from './dances.js';
+const danceEnum = DANCE_PRESETS.map(d => d.id);
+const danceParamDesc = DANCE_PRESETS
+    .map(d => `"${d.id}": ${d.title} (${d.description}, max ${d.maxDuration}s).`)
+    .join(' ');
+export const definition = {
+    type: 'function',
+    function: {
+        name: 'dance_montage',
+        description: 'REQUIRED for ALL dance video requests — do NOT use animate_photo or generate_video for dances. Uses real choreography reference videos to transfer dance motion onto a photo via WAN 2.2 Animate Move. Output is always 9:16 480p portrait. Do NOT use this for bare TikTok/Reels/Shorts/social-video requests unless the user explicitly asks for a dance, choreography, dance trend, or named dance preset. UPLOADED PHOTO: When the user asks for a dance "using this photo" or "with this photo", call dance_montage directly on the uploaded photo; do NOT call edit_image/generate_image first just to prepare, stylize, restyle, reframe, make full-body, or reinterpret the subject. Words that identify a dance preset or vibe, such as "Barbie", "Metric", "Black Sheep", "Rasputin", or "TikTok dance trend", are NOT requests for image prep. Only create image prep first when the user explicitly asks for a new look, outfit, variation set, multiple characters, or loaded persona identity preservation. IMAGE PREP: When generating images for dance (via edit_image or generate_image), ALWAYS use aspectRatio="9:16". CRITICAL — IMAGE COUNT: Generate exactly 1 image (numberOfVariations=1) for dance requests UNLESS the user explicitly asks for variations, different looks, or multiple characters (e.g. "4 different outfits", "alternate between a cat and a dog"). A single consistent image is used for ALL video segments to ensure visual consistency in the final stitched dance video. When the user DOES request multiple variations, batch them into ONE tool call using numberOfVariations + Dynamic Prompts — never split into multiple batches. PERSONAS: When personas are loaded, ALWAYS generate images via edit_image FIRST (using the persona reference photos for identity preservation), then call dance_montage — it will automatically use all generated images. Never use imagePrompt for persona dance requests — edit_image with persona context photos produces far better likeness. USING GENERATED IMAGES: When images have already been generated earlier in the conversation, simply call dance_montage WITHOUT sourceImageIndex — all previously generated images are used automatically as alternating montage segments. Do NOT tell the user to "upload" images that were already generated. Requires at least one uploaded photo, previously generated image, or loaded personas. Best results with photos of people.',
+        parameters: {
+            type: 'object',
+            properties: {
+                dance: {
+                    type: 'string',
+                    enum: danceEnum,
+                    description: `Which dance choreography to use. ${danceParamDesc}.`,
+                },
+                duration: {
+                    type: 'number',
+                    description: 'Total video duration in seconds. Range: 8-30. OMIT this parameter unless the user explicitly requests a specific length — the handler defaults to the chosen dance\'s reference video length (capped at 30s) so the full choreography plays through. Each dance has its own max based on its reference video; the handler caps automatically.',
+                    minimum: 8,
+                    maximum: 30,
+                },
+                sourceImageIndex: {
+                    type: 'number',
+                    description: 'Which previously generated result image to use (0-based index). Use -1 for the original uploaded image. When omitted, all previously generated images are used automatically as alternating montage segments.',
+                },
+                imagePrompt: {
+                    type: 'string',
+                    description: 'Creative style/look for auto-generated images when no pre-generated images are available and no personas are loaded. For persona requests, always generate images via edit_image first — it preserves identity far better. This is a fallback only. If omitted, uses a default full-body portrait style.',
+                },
+                singleClip: {
+                    type: 'boolean',
+                    description: 'When true, renders the entire dance as one continuous clip (no stitching). Only works for durations ≤ 20s. Use when the user explicitly asks for a single video or one unbroken clip. Default: false (splits into segments for faster concurrent rendering).',
+                },
+            },
+            required: ['dance'],
+        },
+    },
+};
+//# sourceMappingURL=definition.js.map

package/dist-esm/tools/definitions/dance-montage/definition.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/dance-montage/definition.ts"],"names":[],"mappings":"AAMA,OAAO,EAAE,aAAa,EAAE,MAAM,aAAa,CAAC;AAE5C,MAAM,SAAS,GAAG,aAAa,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;AAE/C,MAAM,cAAc,GAAG,aAAa;KACjC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,WAAW,SAAS,CAAC,CAAC,WAAW,KAAK,CAAC;KAC5E,IAAI,CAAC,GAAG,CAAC,CAAC;AAEb,MAAM,CAAC,MAAM,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,eAAe;QACrB,WAAW,EACT,m1EAAm1E;QACr1E,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,oCAAoC,cAAc,GAAG;iBACnE;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,+UAA+U;oBACjV,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,+MAA+M;iBAClN;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,0SAA0S;iBAC7S;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,8PAA8P;iBACjQ;aACF;YACD,QAAQ,EAAE,CAAC,OAAO,CAAC;SACpB;KACF;CACF,CAAC"}

package/dist-esm/tools/definitions/edit-image/definition.js

@@ -0,0 +1,125 @@
+import { LITERAL_PROMPT_OVERRIDE } from '../../../contracts/promptOverrideMarker.js';
+import { ASPECT_RATIO_DESCRIPTION } from '../../../media/index.js';
+export const definition = {
+    type: 'function',
+    function: {
+        name: 'edit_image',
+        description: 'Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Flux.2 up to 6 images, and Qwen up to 3 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific model is requested. Exception: explicit Z-image/Z-image Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because edit_image does not expose Z-image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model — do not fall back to generate_image, which has no access to the upload at all. For direct edits (remove objects, enhance), use restore_photo or refine_result unless the user explicitly requested Z-image.',
+        parameters: {
+            type: 'object',
+            properties: {
+                prompt: {
+                    type: 'string',
+                    description: `Edit instruction describing what to generate using the reference images as guidance. 50-200 words recommended.
+
+${LITERAL_PROMPT_OVERRIDE}
+
+PROMPT CONSTRUCTION ORDER — build the prompt in this sequence:
+1. IDENTITY LOCK — state which picture owns the person's identity (GOLDEN RULE: never leave identity ambiguous when editing a person)
+2. REQUESTED EDIT — describe only what CHANGES (the delta), not the whole image
+3. REFERENCE ROLE MAPPING — assign each picture ONE primary role: base_identity (face/person), pose_reference, outfit_reference, style_reference, background_reference, or color_reference
+4. POSE / COMPOSITION — pose, framing, camera angle (omit if unchanged)
+5. STYLE — artistic style, genre, era (omit if unchanged)
+6. LIGHTING / REALISM — "maintain realistic anatomy, perspective, and lighting integration"
+7. PRESERVE clause — always end with "preserve all unmentioned details"
+
+IDENTITY LOCK (required when a person is in any reference image):
+"Preserve the exact facial likeness from picture N — face structure, eye shape, nose shape, mouth shape, jawline, skin tone, hairline, apparent age, and overall recognizability."
+Never let a style, pose, or clothing reference silently override the face. If multiple images are provided, explicitly state "identity comes only from picture N — do not borrow identity from other pictures."
+
+MINIMAL-CHANGE PRINCIPLE: The base image already contains the subject, composition, camera angle, expression, lighting, and background. Describe only the delta. Use positive constraints ("preserve exact facial likeness") not negative ones ("don't change the face").
+
+SINGLE-IMAGE PATTERN:
+"Preserve the exact facial likeness and recognizability of the person from picture 1. [Describe only the requested change]. Keep the same pose, framing, camera angle, and expression unless the user specifically requests changes to these. Preserve all unmentioned details."
+
+MULTI-IMAGE PATTERN:
+"Use the person from picture 1 as the final subject and preserve their exact facial likeness. [Requested edit]. Identity comes only from picture 1. Pose from picture 2. Outfit from picture 3. Do not borrow identity from pictures 2 or 3. Maintain realistic anatomy, perspective, and lighting integration. Preserve all unmentioned details."
+
+CREATIVE TRANSFORMATIONS — be vivid and reference-specific, name the artist, franchise, or era, but always anchor identity first:
+  - "Preserve the exact facial likeness from picture 1. Transform them into a Renaissance oil painting in the style of Vermeer — rich warm tones, dramatic chiaroscuro lighting, ornate period clothing. Maintain realistic anatomy. Preserve all unmentioned details."
+  - "Preserve the exact facial likeness from picture 1. Reimagine them as a Marvel superhero — cinematic dramatic lighting, heroic pose, detailed costume with cape, glowing energy effects. Preserve all unmentioned details."
+  - "Preserve the exact facial likeness from picture 1. Transform them into a Studio Ghibli anime character — soft watercolor backgrounds, gentle Ghibli-style rendering, whimsical atmosphere. Preserve all unmentioned details."
+  - "Preserve the exact facial likeness from picture 1. Place them into a Star Wars scene — Jedi robes, lightsaber glow, dramatic sci-fi backdrop. Preserve all unmentioned details."
+  - "Preserve the exact facial likeness from picture 1. Turn them into a GTA loading screen character — bold outlines, saturated colors, attitude-filled pose, urban backdrop. Preserve all unmentioned details."
+
+FAILURE MODES TO AVOID:
+- Face drift: identity source not specified, or style/pose reference overrides the face
+- Over-editing: for simple edits, prompt rewrites the entire image instead of describing the delta (creative transformations may intentionally change more)
+- Reference confusion: multiple images provided without explicit role mapping
+
+CHARACTER / MASCOT SHEETS: When the user asks for a character sheet, mascot sheet, model sheet, turnaround, expression sheet, or reusable character reference board using uploaded references, create ONE comprehensive professional reference-board image, not separate variations. Map reference roles clearly first (for example: picture 1 = character identity/style reference, picture 2 = logo/brand asset) and keep the character identity consistent across every panel. Include a large hero pose, front / 3/4 / side / back turnaround views, an expression row, action/personality poses, accessories or props, color palette swatches, and compact notes such as personality, fun facts, or brand usage when appropriate. Preserve exact user-provided brand names, slogans, logo text, and requested copy verbatim; incidental tiny notes may be generated by the image model if the user did not provide exact wording. Use clean readable typography.
+
+BATCH VARIATIONS: When numberOfVariations > 1, the prompt must describe ONE subject in ONE scene — never mention counts, "versions", "different", or "multiple" in the prompt text. NEVER describe multiple copies or duplicates of the subject in a single image (no grids, collages, or side-by-side). Use Dynamic Prompt syntax to vary ONE dimension across separate images. For personas: vary scene, activity, expression, or environment — never vary identity. Example: user asks "4 versions at the beach" → numberOfVariations=4, prompt="[persona] at the beach {building a sandcastle|surfing a wave|reading under a palm tree|flying a kite}" — each output is ONE person doing ONE activity. For direct edits: vary the approach, e.g., numberOfVariations=3, prompt="make the sky {a vibrant sunset|stormy and dramatic|clear blue}". Preserve any requested orientation, aspect ratio, or exact pixel dimensions across every variation.
+
+SELECTION-GATED IMAGE STAGES: If the user asks for multiple reference-guided image options/takes/versions and says they will pick one before a later dance, animation, or video, this edit_image call is still the first step. Generate the complete image batch now with sourceImageIndex set to the relevant reference, the exact requested count, Dynamic Prompt options for each output, and the final video/image aspect ratio. Do not ask the user to choose before the images exist, and do not call video tools until after the user selects an image.
+
+LINKED VARIANTS: If multiple details must stay paired per output — visual style, identity cues, outfit, label text, symbols, setting, character, prop, location, or before/after keyframe details — use ONE top-level Dynamic Prompt branch with one complete prompt per output. Do NOT use separate Dynamic Prompt groups for details that must stay together; unpaired groups can mix attributes. If the user asks for per-variant facial, identity, or appearance changes, repeat that guidance inside EVERY option while also preserving recognizability. When the user names a subject or character, write that name or stable role inside every Dynamic Prompt option; a shared prefix outside the branch is not enough because each option must stand alone as a complete identity contract.
+
+Each option must be a fully concrete description — name the actual garment or styling, the actual setting, the actual accessories, and the literal text or symbol shown on screen when requested. Never use meta-placeholder phrasing such as "style-specific outfit", "variant-specific background", "include the requested symbol", "include a humorous alternate name", or "bake the name and symbol into the image" — those describe the task instead of the image.
+
+ORIGINAL + VARIANT BATCHES: When one option is a remade/preserved original and the other options are themed variants, the original option still needs a concrete visual contract. Say to preserve the original clothing/wardrobe/outfit and original background/setting, then name any requested added text, label, flag, logo, symbol, or prop for that original option. Do not leave the original option as only "unmodified original person"; it must be as fully specified as every themed option.
+
+NEW SETTING PER OPTION: When the variant theme implies a new place, culture, era, or context, every option must name its own setting (location, props, lighting). Do NOT carry the source background forward, do NOT write "in the same pose and placement as the original photo" without also naming the new background, and do NOT rely on "preserve all unmentioned details" to handle the setting — the new setting IS a mentioned detail.
+
+RECOGNIZABILITY OVER FEATURE LOCK: For ethnic / age / character / art-style transformations, do NOT paste the strict IDENTITY LOCK feature list ("face structure, eye shape, nose shape, mouth shape, jawline, skin tone, hairline") inside each option — that list contradicts the requested face change and the source face will pass through unchanged. Anchor recognizability per option through apparent age, signature hair silhouette, build, posture, and expression, and explicitly allow skin tone, facial features, and proportions to shift toward the target.
+
+Correct shape (each option self-contained, concrete, with a fresh setting and a recognizability anchor instead of a strict feature lock):
+"{The subject wearing [specific garment, color, cut, and material], standing in [specific NEW setting with props and lighting — never the source background], bold text at the bottom reads [literal requested text], [specific requested visual symbol] appears as a sign or prop, [requested per-variant facial or appearance shift, e.g. "skin tone, eye shape, and bone structure shift toward <target> features"], recognizable through apparent age, signature hair silhouette, build, posture, and expression|The subject wearing [second specific garment, color, cut, and material], standing in [second specific NEW setting with props and lighting], bold text at the bottom reads [second literal requested text], [second requested visual symbol] appears as a sign or prop, [second requested facial or appearance shift], recognizable through apparent age, signature hair silhouette, build, posture, and expression|...}"
+
+Wrong shape (placeholder labels masquerading as prompts):
+"{First variant with variant-specific facial features, placeholder wardrobe, alternate name, and requested symbol baked in|Second variant with different variant-specific facial features, placeholder wardrobe, alternate name, and requested symbol baked in|...}"
+
+Also wrong (strict feature lock + no new setting — the source face and source background pass through unchanged):
+"{Preserve the exact facial likeness — face structure, eye shape, nose shape, mouth shape, jawline, skin tone, hairline. Reimagine as <variant>: [garment description], standing in the exact same pose and placement as the original photo. Preserve all unmentioned details.|Preserve the exact facial likeness — [same strict lock]. Reimagine as <other variant>: [other garment], standing in the exact same pose and placement as the original photo. Preserve all unmentioned details.|...}"
+
+SCREENPLAY / STORYBOARD BATCHES: For multi-scene story, commercial, or longer-form video keyframes, use one Dynamic Prompt branch with one full scene prompt per option. Recurring characters must keep stable names and repeated visual anchors in every scene option where they appear: face/identity source if available, age range, build, hairstyle, outfit silhouette, color palette, signature prop/accessory, posture, and role. Do not let style, scene changes, or pose references alter identity. Include screenplay-style speaker tags when dialogue matters, e.g. CHARACTER: "We made it."
+
+COMPOSITE GPT IMAGE 2 STORYBOARD SHEETS: When numberOfVariations=1 and the user asks for one composite video storyboard/keyframe sheet using uploaded or generated references, the prompt must be a compiled storyboard prompt, not a concept summary. Include a SCENES: section with exactly the requested number of concrete entries named SCENE_01, SCENE_02, etc. Every scene entry must include Visual/Action, Camera/Motion, Dialogue/VO (or [no dialogue]), Audio/SFX, and any visible text or reference usage for that scene. Do not provide only the source brief or generic layout instructions; malformed compiled storyboard prompts are blocked by quality audit.`,
+                },
+                model: {
+                    type: 'string',
+                    enum: ['gpt-image-2', 'qwen-lightning', 'qwen', 'flux2'],
+                    description: 'DO NOT SET THIS PARAMETER unless the user names a specific edit model, asks for a very complex reference-guided image render, or asks for a video storyboard/storyboard sheet/contact sheet/panel layout image using references. The app auto-selects based on quality settings. Set "gpt-image-2" when the user asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 reference-guided image/edit/model, or by default for complex single-image renders that need dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Z-image and Z-image Turbo are not edit_image models; route those explicit uploaded-image enhancement requests to generate_image with sourceImageIndex and starting_image_strength. If the user names another edit/image model, honor that requested model instead. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity.',
+                },
+                sourceImageIndex: {
+                    type: 'number',
+                    description: 'Index of the primary image to use as the main reference. For follow-up edits when generated image results already exist, use the 0-based generated image result index; for example, editing the latest generated storyboard/image should use that generated result index so the model modifies the existing image instead of redrawing from uploads. When no generated image results exist, use sourceImageIndex=-1 to use the uploaded image references. The primary image and any additional uploaded images are passed as context images to guide generation.',
+                },
+                numberOfVariations: {
+                    type: 'number',
+                    description: 'Number of variations (1-16). Pass the user\'s EXACT requested count in ONE call — never split into multiple calls and never call edit_image again to "add more". "4 variations" → numberOfVariations=4 in a single call. Use the exact requested count for reference-guided images that will feed a later video after the user picks one. For screenplay/storyboard batches, the prompt must contain one Dynamic Prompt branch with one full scene prompt per scene; never set numberOfVariations=N with only scene 1\'s prompt. Use 1 unless the user explicitly asks for multiple. Default: 1.',
+                    minimum: 1,
+                    maximum: 16,
+                },
+                width: {
+                    type: 'number',
+                    description: 'Output image width in pixels. Defaults to the context image width. Supported range is 256-2560 for Qwen/Flux.2 edit models. For gpt-image-2, dimensions are flexible up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400; the renderer snaps to the nearest valid multiple-of-16 size. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., "1280 wide", "1280x720", "720p", "3840x2160"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels.',
+                },
+                height: {
+                    type: 'number',
+                    description: 'Output image height in pixels. Defaults to the context image height. Supported range is 256-2560 for Qwen/Flux.2 edit models. For gpt-image-2, dimensions are flexible up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400; the renderer snaps to the nearest valid multiple-of-16 size. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., "720 high", "1280x720", "720p", "2160x3840"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels.',
+                },
+                aspectRatio: {
+                    type: 'string',
+                    description: `${ASPECT_RATIO_DESCRIPTION}\n\nSet this whenever the user specifies an image or downstream video orientation/aspect ratio such as 9:16, 16:9, portrait, vertical, landscape, widescreen, TikTok/Reels/Shorts, or exact pixels. This includes selection-gated reference-guided image batches that will feed a later video or dance after the user picks one. For GPT Image 2 exact size requests, preserve exact pixel intent when possible and prefer popular GPT sizes such as 1536x1024, 1024x1536, 2048x1152, 3840x2160, and 2160x3840. GPT Image 2 does not support transparent-background output; do not promise a transparent result for this model.`,
+                },
+                gptImageQuality: {
+                    type: 'string',
+                    enum: ['low', 'medium', 'high', 'auto'],
+                    description: 'Optional GPT Image 2 rendering quality. Only set with model="gpt-image-2" when the user explicitly asks for low/fast, medium/balanced, high/final, or auto quality. Otherwise omit it and let the host app media quality setting map Fast to low, HQ to medium, and Pro to high.',
+                },
+                outputFormat: {
+                    type: 'string',
+                    enum: ['png', 'jpg', 'jpeg', 'webp'],
+                    description: 'Optional output file format for generated images. Set only when the user explicitly requests PNG, JPG/JPEG, or WebP. Hosts should normalize "jpeg" to the Sogni project format "jpg".',
+                },
+                personaName: {
+                    type: 'string',
+                    description: 'RARE — only set this when the user EXPLICITLY asks for solo images of one specific person ("a portrait of just [name]", "4 solos of [name] alone"). When set, the handler filters context to ONLY that persona\'s reference photo, so any other personas in your prompt will be missing their reference. DEFAULT for multi-persona requests is to OMIT this and put both faces in one combined call. Never set this for "make us as X", "the two of us", "my wife and I", or any phrasing that puts both personas in the same scene — that\'s a single combined call with no personaName.',
+                },
+            },
+            required: ['prompt'],
+        },
+    },
+};
+//# sourceMappingURL=definition.js.map

package/dist-esm/tools/definitions/edit-image/definition.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/edit-image/definition.ts"],"names":[],"mappings":"AAMA,OAAO,EAAE,uBAAuB,EAAE,MAAM,4CAA4C,CAAC;AACrF,OAAO,EAAE,wBAAwB,EAAE,MAAM,yBAAyB,CAAC;AAEnE,MAAM,CAAC,MAAM,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,YAAY;QAClB,WAAW,EACT,8kCAA8kC;QAChlC,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uBAAuB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;+oBA8DsnB;iBACtoB;gBACD,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,aAAa,EAAE,gBAAgB,EAAE,MAAM,EAAE,OAAO,CAAC;oBACxD,WAAW,EACT,miCAAmiC;iBACtiC;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,kiBAAkiB;iBACriB;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,kkBAAkkB;oBACpkB,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,qzBAAqzB;iBACxzB;gBACD,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,uzBAAuzB;iBAC1zB;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,GAAG,wBAAwB,imBAAimB;iBAC/nB;gBACD,eAAe,EAAE;oBACf,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC;oBACvC,WAAW,EACT,kRAAkR;iBACrR;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,CAAC;oBACpC,WAAW,EACT,uLAAuL;iBAC1L;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,2jBAA2jB;iBAC9jB;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}

package/dist-esm/tools/definitions/extend-video/definition.js

@@ -0,0 +1,48 @@
+export const definition = {
+    type: 'function',
+    function: {
+        name: 'extend_video',
+        description: 'Extend a video by adding new time to the end. Works on BOTH videos previously rendered in this session AND user-uploaded videos — set videoIndex to a negative number (e.g. -1) to target an uploaded video when no prior render exists. The base video is auto-selected from the most recent video in this session unless videoIndex is set. ' +
+            'For LTX-2.3 base clips, the tool extracts the last frame and renders an image-to-video continuation. ' +
+            'For Seedance base clips, the tool extracts a trailing reference segment and renders a video-to-video continuation. ' +
+            'Returns both the standalone new segment and a spliced composite (base + new segment).' +
+            ' Use when the user asks to "make it longer", "extend the video", "add another N seconds", "continue the scene", "add an outro/bumper to the end", etc.' +
+            ' Prefer this over generate_image+animate_photo+stitch_video for "add a bumper/outro to this video" — extend_video preserves the original base bytes, audio, and timing instead of re-encoding them.' +
+            ' Do not use this tool to render fresh videos from scratch — call generate_video or animate_photo for that.' +
+            ' Output durations follow each model\'s native limits (LTX 2-20s, Seedance 4-15s) for the new segment alone.',
+        parameters: {
+            type: 'object',
+            properties: {
+                prompt: {
+                    type: 'string',
+                    description: 'What should happen during the extension — describe motion, action, dialogue, and audio for the appended seconds, NOT the entire video. ' +
+                        'For LTX continuations, preserve user-provided spoken dialogue in double quotes; if speech is requested without exact words, describe the delivery without inventing quoted dialogue. ' +
+                        'If the user did not specify what should happen, write a brief continuation that preserves the existing tone (e.g. "the scene continues with the same camera and pacing").',
+                },
+                duration: {
+                    type: 'number',
+                    description: 'Length in seconds of the new appended segment (NOT total final length). LTX 2-20, Seedance 4-15. Default: 5.',
+                    minimum: 2,
+                    maximum: 20,
+                },
+                videoIndex: {
+                    type: 'number',
+                    description: 'Which video result to extend. Default: -1 (most recent video in this session). ' +
+                        'Use 0-based non-negative indices for prior tool result videos. Use negative indices for uploaded videos: -1 = most recent video result OR first uploaded video when no prior render exists.',
+                },
+                videoModel: {
+                    type: 'string',
+                    enum: ['auto', 'ltx23', 'seedance2', 'seedance2-fast'],
+                    description: 'Which model to use for the new segment. Default: "auto" — detect from the base video\'s producer (Seedance base → Seedance, otherwise LTX-2.3). ' +
+                        'Override only when the user explicitly requests a different model.',
+                },
+                keepOriginalAudio: {
+                    type: 'boolean',
+                    description: 'Has no effect for extend_video (the new segment is appended after the base, so the base audio is always preserved through the original portion and the new segment carries its own audio). Reserved for parity with replace_video_segment.',
+                },
+            },
+            required: ['duration'],
+        },
+    },
+};
+//# sourceMappingURL=definition.js.map

package/dist-esm/tools/definitions/extend-video/definition.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/extend-video/definition.ts"],"names":[],"mappings":"AAaA,MAAM,CAAC,MAAM,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,cAAc;QACpB,WAAW,EACT,gVAAgV;YAChV,uGAAuG;YACvG,qHAAqH;YACrH,uFAAuF;YACvF,wJAAwJ;YACxJ,qMAAqM;YACrM,4GAA4G;YAC5G,6GAA6G;QAC/G,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,yIAAyI;wBACzI,uLAAuL;wBACvL,2KAA2K;iBAC9K;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8GAA8G;oBAChH,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,iFAAiF;wBACjF,6LAA6L;iBAChM;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,MAAM,EAAE,OAAO,EAAE,WAAW,EAAE,gBAAgB,CAAC;oBACtD,WAAW,EACT,kJAAkJ;wBAClJ,oEAAoE;iBACvE;gBACD,iBAAiB,EAAE;oBACjB,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,4OAA4O;iBAC/O;aACF;YACD,QAAQ,EAAE,CAAC,UAAU,CAAC;SACvB;KACF;CACF,CAAC"}

package/dist-esm/tools/definitions/generate-image/definition.js

@@ -0,0 +1,104 @@
+import { LITERAL_PROMPT_OVERRIDE } from '../../../contracts/promptOverrideMarker.js';
+import { ASPECT_RATIO_DESCRIPTION } from '../../../media/index.js';
+export const definition = {
+    type: 'function',
+    function: {
+        name: 'generate_image',
+        description: 'Generate a new image from a text description. Usually this is text-only: do NOT use this tool when the user expects an existing image to be reused or preserved in the result. That includes (a) people from My Personas, and (b) uploaded assets such as logos, brand marks, mascots, product shots, photos, screenshots, sketches, character designs, or other reference images they want carried through. Use edit_image with sourceImageIndex=-1 (or the appropriate generated index) instead. Exception: when the user explicitly requests Z-image, Z Image, or Z-image Turbo for an uploaded-image enhancement/image-to-image request, use this tool with model="z-turbo" or model="z-image", sourceImageIndex=-1, and starting_image_strength because edit_image does not expose Z-image models.',
+        parameters: {
+            type: 'object',
+            properties: {
+                prompt: {
+                    type: 'string',
+                    description: `Text description of the image (50-200 words). POSITIVE phrasing only. Be specific and vivid — reference real artists, franchises, and aesthetics by name.
+
+${LITERAL_PROMPT_OVERRIDE}
+
+PROMPT ORDER (follow this structure): [SUBJECT] → [ATTRIBUTES] → [ACTION/POSE] → [CAMERA/FRAMING] → [ENVIRONMENT] → [LIGHTING] → [STYLE/MEDIUM] → [MATERIALS/TEXTURES] → [SECONDARY DETAILS]. Always lead with the main subject and its concrete, observable attributes — never start with mood or atmosphere. Put the most visually decisive details early.
+
+SPECIFICITY: Use concrete nouns and observable adjectives ("weathered leather jacket", not "cool outfit"). Specify framing (close-up, medium shot, full body, wide shot), angle (eye level, low angle, high angle, overhead), lighting type ("soft overcast daylight", "warm golden-hour sunlight", "moody neon spill with deep shadows"), and medium/style ("photorealistic editorial photography", "cinematic still frame", "clean anime illustration"). Include materials and textures when relevant ("brushed aluminum", "wet asphalt reflections", "heavy wool texture").
+
+DEFAULTS (fill in when user is underspecified): Framing: medium shot for portraits, wide shot for environments, full-body for fashion/outfits. Angle: eye level unless dramatic perspective requested. Lighting: soft natural light for realism, clean studio light for product shots. Style: photorealistic for realistic models, matching the model's native style for stylized models (e.g. anime illustration for pony/animagine). Reference real artists and franchises by name ("in the style of Monet's Water Lilies", "Wes Anderson symmetrical pastel composition", "cyberpunk Blade Runner neon city", "shot on 85mm f/1.4 with shallow depth of field").
+
+AVOID: Starting with abstract mood words alone. Burying the subject after a long style preamble. Stacking incompatible styles. Overloading with competing focal points. Vague phrases like "very cool" or "epic vibes".
+
+CHARACTER / MASCOT SHEETS: When the user asks for a character sheet, mascot sheet, model sheet, turnaround, expression sheet, or reusable character reference board, create ONE comprehensive professional reference-board image, not separate variations. Include a large hero pose, front / 3/4 / side / back turnaround views, an expression row, action/personality poses, accessories or props, color palette swatches, and compact notes such as personality, fun facts, or brand usage when appropriate. Preserve exact user-provided brand names, slogans, logo text, and requested copy verbatim; incidental tiny notes may be generated by the image model if the user did not provide exact wording. Keep the character consistent across every panel and use clean readable typography.
+
+BATCH VARIATIONS: When numberOfVariations > 1, the prompt must describe ONE subject in ONE scene — never mention counts, "versions", "different", or "multiple" in the prompt text. NEVER describe multiple copies or duplicates of the subject in a single image (no grids, collages, or side-by-side). Use Dynamic Prompt syntax to vary ONE dimension across separate images. Example: user asks "4 cats in different spots" → numberOfVariations=4, prompt="a black cat {lounging in a sunlit window|prowling through autumn leaves|sitting on a vintage bookshelf|curled up by a fireplace}" — each output is ONE cat in ONE spot. Vary setting, style, lighting, expression, or composition — never override what the user specified. Preserve any requested orientation, aspect ratio, or exact pixel dimensions across every variation.
+
+SELECTION-GATED IMAGE STAGES: If the user asks for multiple image options/takes/versions and says they will pick one before a later dance, animation, or video, this tool call is still the first step. Generate the complete image batch now with the exact requested count, Dynamic Prompt options for each output, and the final video/image aspect ratio. Do not ask the user to choose before the images exist, and do not call video tools until after the user selects an image.
+
+LINKED VARIANTS: If multiple details must stay paired per output — visual style, outfit, label text, symbol, setting, character, prop, location, or before/after keyframe details — use ONE top-level Dynamic Prompt branch with one complete prompt per output. Do NOT use separate Dynamic Prompt groups for details that must stay together; unpaired groups can mix attributes. If the user asks for per-variant facial, identity, or appearance changes, repeat that guidance inside EVERY option. When the user names a subject or character, write that name or stable role inside every Dynamic Prompt option; a shared prefix outside the branch is not enough because each option must stand alone. Correct shape: "{full prompt for variant 1 with all paired details|full prompt for variant 2 with all paired details|...}".
+
+SCREENPLAY / STORYBOARD BATCHES: For multi-scene commercials, storyboards, or shot lists, numberOfVariations must equal the scene count and the prompt MUST be a SINGLE top-level dynamic branch containing one full scene prompt per option, e.g. "{scene 1 full prompt|scene 2 full prompt|scene 3 full prompt}". This is the required way to batch scenes with materially different content while still rendering one image per scene. If recurring characters appear, use stable character names and repeat the same visual anchors in every scene option where they appear (age range, build, hairstyle, outfit silhouette, color palette, signature prop/accessory, posture). Do not rename, merge, redesign, or drift characters between scene keyframes unless the user asks. Include speaker-tagged dialogue details when dialogue affects the keyframe, e.g. CHARACTER: "We made it." NEVER set numberOfVariations=N with only scene 1's prompt — that creates N duplicate versions of scene 1, not N scenes. If the scene count is 16 or fewer, do it in ONE call. Do NOT generate scene 1 first or split into smaller batches unless the user explicitly asks.
+
+COMPOSITE GPT IMAGE 2 STORYBOARD SHEETS: When numberOfVariations=1 and the user asks for one composite video storyboard/keyframe sheet, the prompt must be a compiled storyboard prompt, not a concept summary. Include a SCENES: section with exactly the requested number of concrete entries named SCENE_01, SCENE_02, etc. Every scene entry must include Visual/Action, Camera/Motion, Dialogue/VO (or [no dialogue]), Audio/SFX, and any visible text or reference usage for that scene. Do not provide only the source brief or generic layout instructions; malformed compiled storyboard prompts are blocked by quality audit.
+
+VIDEO KEYFRAMES: When generating images intended as first+last frames for video (animate_photo with frameRole="both"), use numberOfVariations=2 with Dynamic Prompts to create both frames in one call. Make each frame a distinct scene that creates a compelling transition. The video handler will inspect both generated frames and build a scene-aware transition prompt, so focus this image prompt on producing strong start/end visuals. Example: "a serene lake {at dawn with mist rising and soft pink sky|at dusk with fireflies and deep blue twilight}".`,
+                },
+                model: {
+                    type: 'string',
+                    enum: [
+                        'gpt-image-2',
+                        'z-turbo', 'z-image', 'chroma-v46-flash', 'chroma-detail', 'flux1-krea', 'flux2', 'pony-v7',
+                        'qwen-2512', 'qwen-2512-lightning',
+                        'albedo-xl', 'animagine-xl', 'anima-pencil-xl', 'art-universe-xl', 'hyphoria-real',
+                        'analog-madness-xl', 'cyberrealistic-xl', 'real-dream-xl', 'faetastic-xl',
+                        'zavychroma-xl', 'pony-faetality', 'dreamshaper-xl',
+                    ],
+                    description: 'DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, or explicitly asks for Z-image/Z-image Turbo image-to-image. The app auto-selects based on quality settings. Set "gpt-image-2" when the user asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for complex single-image renders that need dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set "z-turbo" when the user asks for Z-image Turbo; set "z-image" when they ask for Z-image without Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: "gpt-image-2"/"flux2"/"flux1-krea" CANNOT do nudity — use "pony-v7", "chroma-detail", "chroma-v46-flash", or "z-turbo" instead.',
+                },
+                width: {
+                    type: 'number',
+                    description: 'Output image width in pixels. Default: 1024. Supported range is 256-2560 for default Z/Qwen/Flux.2 image models and 256-2048 for legacy/specialized image models. For gpt-image-2, dimensions are flexible up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400; the renderer snaps to the nearest valid multiple-of-16 size. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., "1280 wide", "1280x720", "720p", "1080x1920", "3840x2160"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds, so do not ask the user to adjust by a few pixels.',
+                },
+                height: {
+                    type: 'number',
+                    description: 'Output image height in pixels. Default: 1024. Supported range is 256-2560 for default Z/Qwen/Flux.2 image models and 256-2048 for legacy/specialized image models. For gpt-image-2, dimensions are flexible up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400; the renderer snaps to the nearest valid multiple-of-16 size. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., "720 high", "1280x720", "720p", "1080x1920", "2160x3840"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds, so do not ask the user to adjust by a few pixels.',
+                },
+                numberOfVariations: {
+                    type: 'number',
+                    description: 'Number of variations (1-16). Use the user\'s exact requested count in one call whenever they ask for multiple images/options/takes/versions, including images that will feed a later video after the user picks one. For screenplay/storyboard batches, this must equal the scene count AND the prompt must contain one Dynamic Prompt branch with one full scene prompt per scene; never set numberOfVariations=N with only one scene prompt. Default: 1.',
+                    minimum: 1,
+                    maximum: 16,
+                },
+                negativePrompt: {
+                    type: 'string',
+                    description: 'Things to avoid in the generated image. Only set when the user explicitly mentions what to avoid. E.g., "no watermarks, no text, no blurry edges".',
+                },
+                starting_image_strength: {
+                    type: 'number',
+                    description: 'Image-to-image strength (0.0-1.0). Only used when a source image is available and model supports img2img. Higher values = more deviation from the source image. 0.35 = conservative enhancement, 0.5 = balanced, 0.8 = creative. Set this with sourceImageIndex when the user explicitly requests Z-image/Z-image Turbo enhancement or any supported img2img starting-image workflow.',
+                },
+                sourceImageIndex: {
+                    type: 'number',
+                    description: 'Which result image to use as starting image for img2img (0-based index). -1 = original upload. Omit to auto-select latest result. Only relevant when starting_image_strength is set.',
+                },
+                seed: {
+                    type: 'integer',
+                    description: 'Random seed for reproducibility. Use -1 for random (default). Set a specific seed when the user wants to reproduce a previous result.',
+                },
+                guidance: {
+                    type: 'number',
+                    description: 'Guidance scale override. Higher values = more prompt adherence. Model-specific defaults are used if omitted. Only set when the user explicitly requests a guidance value.',
+                },
+                gptImageQuality: {
+                    type: 'string',
+                    enum: ['low', 'medium', 'high', 'auto'],
+                    description: 'Optional GPT Image 2 rendering quality. Only set with model="gpt-image-2" when the user explicitly asks for low/fast, medium/balanced, high/final, or auto quality. Otherwise omit it and let the host app media quality setting map Fast to low, HQ to medium, and Pro to high.',
+                },
+                outputFormat: {
+                    type: 'string',
+                    enum: ['png', 'jpg', 'jpeg', 'webp'],
+                    description: 'Optional output file format for generated images. Set only when the user explicitly requests PNG, JPG/JPEG, or WebP. Hosts should normalize "jpeg" to the Sogni project format "jpg".',
+                },
+                aspectRatio: {
+                    type: 'string',
+                    description: `${ASPECT_RATIO_DESCRIPTION}\n\nSet this whenever the user specifies an image or downstream video orientation/aspect ratio such as 9:16, 16:9, portrait, vertical, landscape, widescreen, TikTok/Reels/Shorts, or exact pixels. This includes selection-gated image batches that will feed a later video or dance after the user picks one. For GPT Image 2 exact size requests, preserve exact pixel intent when possible and prefer popular GPT sizes such as 1536x1024, 1024x1536, 2048x1152, 3840x2160, and 2160x3840. GPT Image 2 does not support transparent-background output; do not promise a transparent result for this model.`,
+                },
+            },
+            required: ['prompt'],
+        },
+    },
+};
+//# sourceMappingURL=definition.js.map

package/dist-esm/tools/definitions/generate-image/definition.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/generate-image/definition.ts"],"names":[],"mappings":"AAMA,OAAO,EAAE,uBAAuB,EAAE,MAAM,4CAA4C,CAAC;AACrF,OAAO,EAAE,wBAAwB,EAAE,MAAM,yBAAyB,CAAC;AAEnE,MAAM,CAAC,MAAM,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,ywBAAywB;QAC3wB,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uBAAuB;;;;;;;;;;;;;;;;;;;;;;siBAsB6gB;iBAC7hB;gBACD,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE;wBACJ,aAAa;wBACb,SAAS,EAAE,SAAS,EAAE,kBAAkB,EAAE,eAAe,EAAE,YAAY,EAAE,OAAO,EAAE,SAAS;wBAC3F,WAAW,EAAE,qBAAqB;wBAClC,WAAW,EAAE,cAAc,EAAE,iBAAiB,EAAE,iBAAiB,EAAE,eAAe;wBAClF,mBAAmB,EAAE,mBAAmB,EAAE,eAAe,EAAE,cAAc;wBACzE,eAAe,EAAE,gBAAgB,EAAE,gBAAgB;qBACpD;oBACD,WAAW,EACT,ouCAAouC;iBACvuC;gBACD,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,2yBAA2yB;iBAC9yB;gBACD,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4yBAA4yB;iBAC/yB;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4bAA4b;oBAC9b,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,oJAAoJ;iBACvJ;gBACD,uBAAuB,EAAE;oBACvB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,uXAAuX;iBAC1X;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,sLAAsL;iBACzL;gBACD,IAAI,EAAE;oBACJ,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,uIAAuI;iBAC1I;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,2KAA2K;iBAC9K;gBACD,eAAe,EAAE;oBACf,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC;oBACvC,WAAW,EACT,kRAAkR;iBACrR;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,CAAC;oBACpC,WAAW,EACT,uLAAuL;iBAC1L;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,GAAG,wBAAwB,glBAAglB;iBAC9mB;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}

package/dist-esm/tools/definitions/generate-music/definition.js

@@ -0,0 +1,72 @@
+import { LITERAL_PROMPT_OVERRIDE } from '../../../contracts/promptOverrideMarker.js';
+export const definition = {
+    type: 'function',
+    function: {
+        name: 'generate_music',
+        description: 'Generate music from a text description. Creates original songs with optional lyrics, BPM, key signature, and duration control. Use when the user wants to create music, a song, a beat, a melody, background music, or any audio content.',
+        parameters: {
+            type: 'object',
+            properties: {
+                prompt: {
+                    type: 'string',
+                    description: `Genre, mood, and style description for the music. Be specific about musical characteristics.
+
+${LITERAL_PROMPT_OVERRIDE}
+
+Examples:
+- "upbeat electronic dance music with driving bass and synth arpeggios"
+- "mellow jazz ballad with soft piano, brushed drums, and walking bass"
+- "epic orchestral soundtrack with soaring strings and powerful brass"
+- "lo-fi hip hop beat with vinyl crackle, muted keys, and chill vibes"
+- "acoustic folk song with fingerpicked guitar and warm harmonies"
+
+Include:
+- Genre (rock, jazz, electronic, classical, hip-hop, etc.)
+- Mood (happy, melancholic, energetic, relaxing, epic, etc.)
+- Instruments (piano, guitar, drums, synth, strings, etc.)
+- Style descriptors (driving, mellow, atmospheric, punchy, etc.)
+
+BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary ONE dimension across separate tracks. Lock in any genre/mood/instruments the user specified, vary the rest. Example: "{lo-fi hip hop beat with muted keys|jazz piano trio with brushed drums|ambient electronic with soft pads} with warm reverb and vinyl texture".`,
+                },
+                duration: {
+                    type: 'number',
+                    description: 'Duration in seconds. Default: 30. Range: 10-600 (10 seconds to 10 minutes). Short clips: 10-30s. Standard songs: 120-300s.',
+                    minimum: 10,
+                    maximum: 600,
+                },
+                bpm: {
+                    type: 'number',
+                    description: 'Beats per minute / tempo. Default: 120. Range: 30-300. Slow ballad: 60-80. Mid-tempo: 90-120. Upbeat: 120-140. Fast dance: 140-180. Very fast: 180+.',
+                    minimum: 30,
+                    maximum: 300,
+                },
+                keyscale: {
+                    type: 'string',
+                    description: 'Musical key and scale. E.g., "C major", "A minor", "F# minor", "Bb major". Default: "C major". Only set when the user specifies a key or when a particular mood calls for it (minor keys for sad/dark, major for happy/bright).',
+                },
+                lyrics: {
+                    type: 'string',
+                    description: 'Song lyrics. Optional — omit for instrumental music. Format: write lyrics naturally with line breaks. The model will attempt to sing these lyrics with the generated music. Works best with clear, rhythmic phrasing that matches the BPM.',
+                },
+                model: {
+                    type: 'string',
+                    enum: ['turbo', 'sft'],
+                    description: 'ACE-Step model variant. "turbo" (default): Higher quality audio generation with 4-16 steps and half the cost. Always use turbo unless the user explicitly requests the SFT model. "sft": Experimental model with lower audio quality but very strong lyric handling. 10-200 steps, full cost. Only use when the user specifically asks for SFT. Default: "turbo".',
+                },
+                timesig: {
+                    type: 'number',
+                    enum: [2, 3, 4, 6],
+                    description: 'Time signature (beats per measure). 4 = 4/4 time (default, most common). 3 = 3/4 time (waltz). 2 = 2/4 time (march). 6 = 6/8 time (compound). Default: 4.',
+                },
+                numberOfVariations: {
+                    type: 'number',
+                    description: 'Number of variations (1-16). Use 1 unless user requests multiple. Default: 1.',
+                    minimum: 1,
+                    maximum: 16,
+                },
+            },
+            required: ['prompt'],
+        },
+    },
+};
+//# sourceMappingURL=definition.js.map

package/dist-esm/tools/definitions/generate-music/definition.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/generate-music/definition.ts"],"names":[],"mappings":"AAMA,OAAO,EAAE,uBAAuB,EAAE,MAAM,4CAA4C,CAAC;AAErF,MAAM,CAAC,MAAM,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,2OAA2O;QAC7O,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uBAAuB;;;;;;;;;;;;;;;sVAe6T;iBAC7U;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4HAA4H;oBAC9H,OAAO,EAAE,EAAE;oBACX,OAAO,EAAE,GAAG;iBACb;gBACD,GAAG,EAAE;oBACH,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,sJAAsJ;oBACxJ,OAAO,EAAE,EAAE;oBACX,OAAO,EAAE,GAAG;iBACb;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,iOAAiO;iBACpO;gBACD,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4OAA4O;iBAC/O;gBACD,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,OAAO,EAAE,KAAK,CAAC;oBACtB,WAAW,EACT,mWAAmW;iBACtW;gBACD,OAAO,EAAE;oBACP,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC;oBAClB,WAAW,EACT,2JAA2J;iBAC9J;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,+EAA+E;oBACjF,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}

package/dist-esm/tools/definitions/generate-video/definition.js

@@ -0,0 +1,117 @@
+import { GENERATE_VIDEO_SKIP_PROMPT_PROCESSING_DESCRIPTION, LITERAL_VIDEO_PROMPT_OVERRIDE, SEEDANCE_EXPAND_PROMPT_DESCRIPTION, SEEDANCE_TOOL_MULTIMODAL_REFERENCE_GUIDANCE, } from '../../../contracts/toolPromptMarkers.js';
+import { ASPECT_RATIO_DESCRIPTION } from '../../../media/index.js';
+export const definition = {
+    type: "function",
+    function: {
+        name: "generate_video",
+        description: 'Generate a video from text or Seedance multimodal references. LTX 2.3 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 (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 or seedance2-fast, default to exactly one 4-15s video 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, preserve the requested total duration in the prompt/context; chat orchestration should split it into supported segment renders and stitch them instead of clamping it to a 15s 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" instead of this tool. 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.',
+        parameters: {
+            type: "object",
+            properties: {
+                prompt: {
+                    type: "string",
+                    description: `Write one flowing paragraph like a cinematographer describing a shot. Present tense, specific natural language. Longer clips need longer prompts; close-ups need more detail than wide shots.
+
+${LITERAL_VIDEO_PROMPT_OVERRIDE}
+
+STRUCTURE: shot/style → subject (age, clothing, hairstyle, distinguishing details) → environment, lighting, atmosphere → action beat by beat → camera movement → audio and dialogue.
+
+CAST CONTINUITY: For screenplay, script, storyboard, commercial, series, or other longer-form video tasks with recurring characters, use stable character names and repeat the same visual anchors every time they appear (age range, build, hairstyle, outfit silhouette, color palette, signature prop/accessory, posture, voice). Do not rename, merge, redesign, or drift characters between scenes unless the user asks.
+
+MOTION PACING: Scale complexity to duration. <=6s: 1 main action beat + 1 simple camera move. Around 10s: 2-3 clear action beats + 1 camera move. >10s: up to 4 action beats in clear sequence. Prefer fewer readable beats over dense micro-actions, especially in short clips.
+
+BLOCKING: Direct the layout like scene blocking. State left/right placement, foreground/background, facing toward/away, and relative distance when multiple subjects or important objects are involved.
+
+ACTION: Drive motion with concrete verbs. Specify who moves, what moves, how it moves, and what the camera does. Avoid generic phrases like "comes alive."
+
+DIALOGUE: Put user-provided spoken lines in double quotes. For screenplay-style or longer-form tasks, prefix each spoken line with a stable speaker tag outside the quotes, e.g. CHARACTER: "We made it." Break long speech into short quoted phrases with acting beats between them (gestures, pauses, glances). If the user asks for speech but provides no exact words, describe the visible delivery, voice quality, and emotion without inventing quoted dialogue; ask only when exact wording is the point of the request. Never write placeholders such as "while speaking", "dialogue begins", "explaining", or "final line lands". Show emotion through visible behavior — not "she is sad", instead "she looks down, pauses, and her voice cracks". QUOTING RULE: ONLY use double quotes for spoken dialogue. Never quote on-screen text, overlay text, titles, captions, signs, or any visual text — describe them without quotes.
+
+STORYBOARD TEXT: For storyboard references, structural headings, section numbers, slide titles, panel titles, and captions may become short audio-only narration/voiceover or key-message beats, but they are not subtitles, title cards, lower thirds, or visible overlays unless the user explicitly asks for visible text/on-screen text/title card/subtitle/lower third/signage/CTA. Do not concatenate storyboard labels into run-on voiceover; use separate brief phrases with pauses.
+
+AUDIO: Prompt sound intentionally — voice quality, volume, room tone, ambience, music, weather, footsteps. Include language or accent if relevant. Useful voice/volume anchors: whisper, mutter, shout, scream, energetic announcer, resonant voice with gravitas, distorted radio-style, robotic monotone, childlike curiosity.
+
+CAMERA: Cinematic terms — close-up, tracking shot, dolly in, handheld, slow arc, static frame. Describe movement relative to subject.
+
+For specific characters (movies, TV): describe visual appearance — don't rely on names alone.
+
+For complex/creative scenes (characters, dialogue, skits): capture the full creative intent. The system auto-expands into a detailed prompt.
+
+AVOID: Vague prompts, too many characters at once, conflicting lighting logic, readable text or logos, abstract emotions with no visible behavior, rigid numeric constraints (exact angles, counts, speeds).
+
+BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax. Lock in any camera/subject/style the user specified, vary the rest. Example: "slow dolly in on a city street {at dawn with golden light|during a rainstorm|at night with neon reflections}".`,
+                },
+                expandPrompt: {
+                    type: "boolean",
+                    description: SEEDANCE_EXPAND_PROMPT_DESCRIPTION,
+                },
+                skipPromptProcessing: {
+                    type: "boolean",
+                    description: GENERATE_VIDEO_SKIP_PROMPT_PROCESSING_DESCRIPTION,
+                },
+                duration: {
+                    type: "number",
+                    description: "Video duration in seconds. Default: 5. Range: 2-20. Use when the user explicitly requests a specific length.",
+                    minimum: 2,
+                    maximum: 20,
+                },
+                negativePrompt: {
+                    type: "string",
+                    description: "Non-Seedance only. Optional negative prompt for video models that expose a separate negative-prompt field. Do not set for seedance2 or seedance2-fast; rewrite user-provided Seedance avoid/ban/no-X requests as positive visual instructions in prompt.",
+                },
+                videoModel: {
+                    type: "string",
+                    enum: ["ltx23", "wan22", "seedance2", "seedance2-fast"],
+                    description: 'Video model. "ltx23" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. "wan22": Fast 4-step, simple motion, no audio. Default: "ltx23". For ordinary Seedance 2.0 video requests, use seedance2-fast by default: 720p unless Default Media Quality is Fast, which should use 480p. Use seedance2 when the user explicitly asks for 1080p / the non-standard full-quality version, or whenever a generated/uploaded video storyboard image is the Seedance reference unless the user explicitly asks for a draft or the Seedance fast model/version. Storyboard-reference Seedance requests default to High Quality: set targetResolution 720 even when Default Media Quality is Fast, unless the user explicitly asks for another named resolution such as 480p. Default Media Quality Pro alone is not an explicit 1080p request; keep default Seedance resolution at 720p unless the user asks for 1080p or another resolution. ' +
+                        SEEDANCE_TOOL_MULTIMODAL_REFERENCE_GUIDANCE,
+                },
+                generateAudio: {
+                    type: "boolean",
+                    description: "Seedance only. Whether Seedance should generate a native audio track. Omit by default; set false only when the user explicitly asks for silent output or no audio.",
+                },
+                referenceImageIndices: {
+                    type: "array",
+                    items: { type: "number" },
+                    description: "Seedance only. Image references for @Image tags. Use negative indices for uploaded images (-1 first upload, -2 second upload) and non-negative indices for generated image results. Omit by default: uploaded images are auto-forwarded as @Image references. Anchor frame intent in the prompt with @Image tags: \"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.\" Do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance.",
+                },
+                referenceVideoIndices: {
+                    type: "array",
+                    items: { type: "number" },
+                    description: 'Seedance only. Optional loose video references. Use negative indices for uploaded videos (-1 first uploaded video, -2 second uploaded video) and non-negative indices for generated video results. Omit by default: uploaded videos are auto-forwarded as @Video references. Set to choose a subset or include previously generated video URLs. Do not use this for uploaded source-video transforms, upscales, enhancements, restyles, or remasters; use video_to_video with controlMode="seedance-v2v" instead.',
+                },
+                referenceAudioIndices: {
+                    type: "array",
+                    items: { type: "number" },
+                    description: 'Seedance only. Optional loose audio references. Use negative indices for uploaded audio files (-1 first uploaded audio, -2 second uploaded audio) and non-negative indices for generated audio results. Omit by default: uploaded audio is auto-forwarded as @Audio references when the Seedance request also has an image or video reference. Use this only for loose background, mood, timing, or style references under an image/video-anchored Seedance shot. 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" instead. Audio-only Seedance requests are unsupported; use sound_to_video for uploaded-audio-only workflows.',
+                },
+                width: {
+                    type: "number",
+                    description: 'Video width in pixels. LTX 2.3: 640-3840. WAN: 480-1536. Default resolution depends on model and quality tier: LTX Fast about 720p and High/Pro about 1080p; WAN Fast uses 480p short side and High/Pro uses 720p short side. Set width only when the user specifies an exact width or orientation-qualified exact pixels. A bare named resolution like "720p resolution" is a short-side target, not an instruction to make landscape 1280x720. If the user gives only one exact dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested exact dimensions override the default media quality. Mappings when orientation is explicit: 480p landscape=854x480, 480p portrait=480x854, 720p landscape=1280x720, 720p portrait=720x1280, 1080p landscape=1920x1080, 1080p portrait=1080x1920, 4K landscape=3840x2160. Non-step values are accepted when in bounds; LTX snaps to the nearest 64px step and WAN snaps to the nearest 16px step internally, so do not ask the user to adjust by a few pixels.',
+                },
+                height: {
+                    type: "number",
+                    description: 'Video height in pixels. LTX 2.3: 640-3840. WAN: 480-1536. Set height only when the user specifies an exact height or orientation-qualified exact pixels. A bare named resolution like "720p resolution" is a short-side target; do not convert it to landscape dimensions unless the user says landscape/horizontal/widescreen. If the user gives only one exact dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested exact dimensions override Default Media Quality, including Pro. Non-step values are accepted when in bounds; LTX snaps to the nearest 64px step and WAN snaps to the nearest 16px step internally, so do not ask the user to adjust by a few pixels.',
+                },
+                targetResolution: {
+                    type: "number",
+                    description: 'Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as "480p", "720p", or "1080p" without exact pixels or an output orientation. Also set for default Seedance 2.0 requests: 480 when Default Media Quality is Fast, otherwise 720, including Pro unless the user explicitly asks for 1080p or another resolution. For generated/uploaded storyboard images used as Seedance references, default to 720 even when Default Media Quality is Fast; only use 480 when the user explicitly asks for 480p. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says "720p portrait" or "720p landscape", use exact width/height/aspectRatio instead.',
+                },
+                numberOfVariations: {
+                    type: "number",
+                    description: "Number of variations (1-16). Use 1 unless user explicitly requests multiple separate video outputs. For Seedance, default to 1 because each variation is an expensive separate render.",
+                    minimum: 1,
+                    maximum: 16,
+                },
+                aspectRatio: {
+                    type: "string",
+                    description: ASPECT_RATIO_DESCRIPTION,
+                },
+                voicePersonaName: {
+                    type: "string",
+                    description: 'ONLY when the user explicitly requests a registered/reference persona voice clip. Name of the persona whose voice clip to use as referenceAudioIdentity. Set this when the narrator/speaker is a different persona than the one described in the video (e.g. "David" narrates a scene featuring Aleyna), or to explicitly select a requested voice when multiple personas with voice clips are resolved. Do NOT set this for ordinary character dialogue, inferred voices, or personas without a voice clip — LTX 2.3 generates voice natively from the text prompt instead. Requires ltx23.',
+                },
+            },
+            required: ["prompt"],
+        },
+    },
+};
+//# sourceMappingURL=definition.js.map