@sogni-ai/sogni-protocol 1.0.0-alpha.2

package/schemas/tools/extend_video.schema.json

@@ -0,0 +1,42 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/extend_video.schema.json",
+  "title": "extend_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "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.",
+  "type": "object",
+  "additionalProperties": false,
+  "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"
+  ]
+}

package/schemas/tools/generate_image.schema.json

@@ -0,0 +1,104 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/generate_image.schema.json",
+  "title": "generate_image arguments",
+  "schemaVersion": "2026-04-27.1",
+  "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.",
+  "type": "object",
+  "additionalProperties": false,
+  "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.\n\nLITERAL PROMPT OVERRIDE: If the user explicitly says not to modify the prompt, or to use it exactly/verbatim/as-is, copy the identified prompt text verbatim instead of applying these construction rules unless a hard requirement is missing.\n\nPROMPT 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.\n\nSPECIFICITY: 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\").\n\nDEFAULTS (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\").\n\nAVOID: 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\".\n\nCHARACTER / 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.\n\nBATCH 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.\n\nSELECTION-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.\n\nLINKED 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|...}\".\n\nSCREENPLAY / 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.\n\nCOMPOSITE 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.\n\nVIDEO 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": "Do NOT set unless the user explicitly requests an aspect ratio, format, orientation, or exact pixel dimensions. When a reference/source image is used and the user did not ask to change its shape, omit this field so the handler preserves the selected source image's own ratio.\n\nFormats: \"16:9\", \"9:16\", \"4:5\", \"1:1\", \"4:3\", \"3:2\", \"21:9\", or exact pixels like \"1920x1080\".\n\nCRITICAL: When the user specifies exact pixel dimensions (e.g., \"1280x720\", \"1080x1920\", \"1920x1080\", \"3840x2160\") or an orientation-qualified named resolution (e.g., \"720p landscape\", \"720p portrait\"), use the exact pixel format, NOT a ratio like \"16:9\" or \"9:16\". Exact user-requested dimensions override the selected default media quality, including Pro/HQ defaults. A bare named video resolution like \"720p resolution\" is only a resolution tier/short-side request; do not turn it into landscape pixels and do not set aspectRatio unless the user also states landscape, portrait, vertical, horizontal, or exact pixels. If requested pixels are in bounds but not on the model's pixel step, still pass the user's exact pixel request; the handler snaps to the nearest supported size internally. Only use ratio format when the user says a generic format name without pixel dimensions.\n\nMappings (use ONLY when user does NOT specify pixel dimensions): landscape/widescreen/YouTube/cinematic → \"16:9\". portrait → \"9:16\". TikTok/Reels/IG Reels → \"1080x1920\". ultrawide/cinema scope → \"21:9\". Instagram post → \"4:5\". square → \"1:1\". standard/TV → \"4:3\". 720p landscape → \"1280x720\". 720p portrait → \"720x1280\". 1080p landscape → \"1920x1080\". 1080p portrait/HD portrait → \"1080x1920\". 4K landscape → \"3840x2160\". 4K portrait → \"2160x3840\". Never set for generic requests like \"make a video\".\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"
+  ]
+}

package/schemas/tools/generate_music.schema.json

@@ -0,0 +1,62 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/generate_music.schema.json",
+  "title": "generate_music arguments",
+  "schemaVersion": "2026-04-27.1",
+  "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.",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "prompt": {
+      "type": "string",
+      "description": "Genre, mood, and style description for the music. Be specific about musical characteristics.\n\nLITERAL PROMPT OVERRIDE: If the user explicitly says not to modify the prompt, or to use it exactly/verbatim/as-is, copy the identified prompt text verbatim instead of applying these construction rules unless a hard requirement is missing.\n\nExamples:\n- \"upbeat electronic dance music with driving bass and synth arpeggios\"\n- \"mellow jazz ballad with soft piano, brushed drums, and walking bass\"\n- \"epic orchestral soundtrack with soaring strings and powerful brass\"\n- \"lo-fi hip hop beat with vinyl crackle, muted keys, and chill vibes\"\n- \"acoustic folk song with fingerpicked guitar and warm harmonies\"\n\nInclude:\n- Genre (rock, jazz, electronic, classical, hip-hop, etc.)\n- Mood (happy, melancholic, energetic, relaxing, epic, etc.)\n- Instruments (piano, guitar, drums, synth, strings, etc.)\n- Style descriptors (driving, mellow, atmospheric, punchy, etc.)\n\nBATCH 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"
+  ]
+}

package/schemas/tools/generate_video.schema.json

@@ -0,0 +1,97 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/generate_video.schema.json",
+  "title": "generate_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "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.",
+  "type": "object",
+  "additionalProperties": false,
+  "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.\n\nLITERAL PROMPT OVERRIDE: If the user explicitly says not to modify the prompt, or to use it exactly/verbatim/as-is, copy the identified prompt text verbatim instead of applying these construction rules unless a hard requirement is missing. Set skipPromptProcessing=true; for Seedance also set expandPrompt=false.\n\nSTRUCTURE: shot/style → subject (age, clothing, hairstyle, distinguishing details) → environment, lighting, atmosphere → action beat by beat → camera movement → audio and dialogue.\n\nCAST 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.\n\nMOTION 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.\n\nBLOCKING: 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.\n\nACTION: Drive motion with concrete verbs. Specify who moves, what moves, how it moves, and what the camera does. Avoid generic phrases like \"comes alive.\"\n\nDIALOGUE: 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.\n\nSTORYBOARD 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.\n\nAUDIO: 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.\n\nCAMERA: Cinematic terms — close-up, tracking shot, dolly in, handheld, slow arc, static frame. Describe movement relative to subject.\n\nFor specific characters (movies, TV): describe visual appearance — don't rely on names alone.\n\nFor complex/creative scenes (characters, dialogue, skits): capture the full creative intent. The system auto-expands into a detailed prompt.\n\nAVOID: 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).\n\nBATCH 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 only. Whether to run the shared Seedance prompt shaper before dispatch. Defaults to true; set false only when the user explicitly asks to submit the compact prompt directly or not modify the prompt."
+    },
+    "skipPromptProcessing": {
+      "type": "boolean",
+      "description": "Bypass automatic prompt shaping/refinement and voice-identity prompt formatting so the prompt text is sent unchanged to the video model. Set true ONLY when the user explicitly says not to modify/rewrite/enhance/expand/change/improve the prompt, or to use/send it exactly, verbatim, or as-is, AND the provided prompt already satisfies the tool requirements. Continue to set non-prompt parameters such as model, duration, count, aspect ratio, and seed. For Seedance literal prompt requests, also set expandPrompt=false. Do not set for ordinary underspecified requests."
+    },
+    "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 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."
+    },
+    "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": "Do NOT set unless the user explicitly requests an aspect ratio, format, orientation, or exact pixel dimensions. When a reference/source image is used and the user did not ask to change its shape, omit this field so the handler preserves the selected source image's own ratio.\n\nFormats: \"16:9\", \"9:16\", \"4:5\", \"1:1\", \"4:3\", \"3:2\", \"21:9\", or exact pixels like \"1920x1080\".\n\nCRITICAL: When the user specifies exact pixel dimensions (e.g., \"1280x720\", \"1080x1920\", \"1920x1080\", \"3840x2160\") or an orientation-qualified named resolution (e.g., \"720p landscape\", \"720p portrait\"), use the exact pixel format, NOT a ratio like \"16:9\" or \"9:16\". Exact user-requested dimensions override the selected default media quality, including Pro/HQ defaults. A bare named video resolution like \"720p resolution\" is only a resolution tier/short-side request; do not turn it into landscape pixels and do not set aspectRatio unless the user also states landscape, portrait, vertical, horizontal, or exact pixels. If requested pixels are in bounds but not on the model's pixel step, still pass the user's exact pixel request; the handler snaps to the nearest supported size internally. Only use ratio format when the user says a generic format name without pixel dimensions.\n\nMappings (use ONLY when user does NOT specify pixel dimensions): landscape/widescreen/YouTube/cinematic → \"16:9\". portrait → \"9:16\". TikTok/Reels/IG Reels → \"1080x1920\". ultrawide/cinema scope → \"21:9\". Instagram post → \"4:5\". square → \"1:1\". standard/TV → \"4:3\". 720p landscape → \"1280x720\". 720p portrait → \"720x1280\". 1080p landscape → \"1920x1080\". 1080p portrait/HD portrait → \"1080x1920\". 4K landscape → \"3840x2160\". 4K portrait → \"2160x3840\". Never set for generic requests like \"make a video\"."
+    },
+    "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"
+  ]
+}

package/schemas/tools/manage_memory.schema.json

@@ -0,0 +1,28 @@
+{
+  "title": "manage_memory tool schema",
+  "schemaVersion": "2026-05-17.1",
+  "description": "Save, read, or delete user preferences and facts that persist across conversations. Call with action \"write\" when user states a preference (\"I like watercolor style\", \"always use 16:9\"). Call with action \"read\" to recall preferences before generating. Call with action \"delete\" to remove a preference. Do NOT save transient requests — only persistent preferences.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["action"],
+  "properties": {
+    "action": {
+      "type": "string",
+      "enum": ["read", "write", "delete"],
+      "description": "Action to perform. \"read\": list all saved memories. \"write\": save or update a preference. \"delete\": remove a preference by key."
+    },
+    "key": {
+      "type": "string",
+      "description": "Unique key for the memory (e.g. \"preferred_style\", \"aspect_ratio\", \"quality_preference\"). Required for write and delete."
+    },
+    "value": {
+      "type": "string",
+      "description": "Value to save. Required for write action. Be concise but specific."
+    },
+    "category": {
+      "type": "string",
+      "enum": ["preference", "fact", "context"],
+      "description": "Memory category. \"preference\": style/format preferences. \"fact\": user facts (name, location). \"context\": project context. Default: \"preference\"."
+    }
+  }
+}

package/schemas/tools/orbit_video.schema.json

@@ -0,0 +1,70 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/orbit_video.schema.json",
+  "title": "orbit_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "description": "Create a 360-degree orbit video around a subject. This is a SELF-CONTAINED pipeline — it automatically generates angle views (via change_angle), creates transition video clips, and stitches them into one seamless looping video. You only need ONE source image as the front view — either an uploaded image or a previously generated result. If the user uploaded an image, call this tool directly without generating anything first. Do NOT pre-generate multiple angles or variations — this tool handles everything internally. Use when the user asks for a \"360 pan\", \"orbit\", \"rotate around\", \"spin around\", or \"turntable\" view.",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "elevation": {
+      "type": "string",
+      "enum": [
+        "low-angle shot",
+        "eye-level shot",
+        "elevated shot",
+        "high-angle shot"
+      ],
+      "description": "Camera elevation for all angles. Default: \"eye-level shot\"."
+    },
+    "distance": {
+      "type": "string",
+      "enum": [
+        "close-up",
+        "medium shot",
+        "wide shot"
+      ],
+      "description": "Camera distance for all angles. Default: \"medium shot\"."
+    },
+    "prompt": {
+      "type": "string",
+      "description": "Describe the SUBJECT and ambient environment (for example, a concise description of the visible subject, location, weather, props, and ambience). Do NOT describe camera motion, rotation, panning, orbiting, or 360-degree movement — camera motion is handled automatically. Do NOT put spoken dialogue here — use the dialogue parameter instead. Music is automatically suppressed — use generate_music separately."
+    },
+    "dialogue": {
+      "type": "string",
+      "description": "Spoken dialogue or narration for a SINGLE segment of the orbit video. This is applied ONLY to the segment specified by dialogueSegment (default: first segment). All other segments get foley/ambient audio only. Keep it brief — each segment is 2.5 seconds (~6 words max). If the user asks for dialogue in \"just the first segment\" or \"only at the start\", put the speech here and leave prompt for motion/foley only. If the user asks for dialogue in multiple/every segment, use dialogues instead."
+    },
+    "dialogues": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      },
+      "description": "Per-segment spoken dialogue lines for multiple orbit transitions. Use this when the user asks for dialogue in multiple segments, every turn, or before each 90-degree turn. With the default standard 360° orbit there are 4 transitions, so provide exactly 4 short lines in order. Each line should be brief enough for a 2.5 second segment (~6 words max). Preserve real names from the request or prior generated image; never invent placeholder speakers. For \"us\"/\"we\"/couple requests, make the named people speak together. Omit entries or use an empty string for segments that should have foley/ambient audio only. Do NOT also put these dialogue lines in prompt."
+    },
+    "dialogueSegment": {
+      "type": "number",
+      "description": "Which transition segment receives the dialogue (0-based index into the transition sequence). 0 = first transition (default), last index = wrap-back to front. With default angles there are 4 transitions (0-3). With custom angles the count equals angles.length + 1. Only used when dialogue is provided."
+    },
+    "angles": {
+      "type": "array",
+      "items": {
+        "type": "string",
+        "enum": [
+          "front-right quarter view",
+          "right side view",
+          "back-right quarter view",
+          "back view",
+          "back-left quarter view",
+          "left side view",
+          "front-left quarter view"
+        ]
+      },
+      "description": "OMIT THIS PARAMETER for standard 360° orbits — the default (3 angles at 90° increments: right, back, left + source as front = 4 transitions) works for nearly all requests. Only provide this when the user explicitly asks for specific angles, a partial orbit, or extra-smooth rotation. Each additional angle costs extra credits and generation time. Values are clockwise azimuths between the source (front) and wrap-back."
+    },
+    "sourceImageIndex": {
+      "type": "number",
+      "description": "Which result image to orbit around (0-based). If the user picked a 1-based image number, subtract 1 and set this explicitly (number 3 -> 2). Omit only when the user did not choose a specific prior result; then the tool uses the latest result or original upload."
+    }
+  },
+  "required": []
+}

package/schemas/tools/overlay_video.schema.json

@@ -0,0 +1,126 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/overlay_video.schema.json",
+  "title": "overlay_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "description": "Burn text and/or logo/watermark image overlays onto a previously rendered or uploaded video. Use when the user asks to add a title, caption, label, watermark, brand logo, sponsor mark, lower-third, tagline, sticker, or any persistent text/graphic over the existing video frames. Multiple overlays can be supplied in one call (e.g. a corner logo plus a top-center title). Each overlay can optionally be limited to a [startSeconds, endSeconds] time range. When the user asks for an overlay to appear for a specific window (for example \"2 seconds in the middle\"), set startSeconds/endSeconds on the overlay item in the same call. Negative startSeconds/endSeconds are relative to the end of the base video, so startSeconds=-2 with omitted endSeconds means \"the last 2 seconds\". When replacing a video time window with an uploaded still image or screenshot, use an image overlay with widthPct=100 and fit=\"cover\" for that window. This is a pure ffmpeg post-production op — it does not regenerate the video. Do not use for generative intro/outro/bumper/end-card/start-card requests; those add or regenerate video time and should use extend_video or replace_video_segment. Do not call it again just to refine default size/placement after it succeeds; finalize and wait for user feedback. Do not use for animated typography, kinetic captions, or moving stickers; this lays down static overlays only.",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "sourceVideoIndex": {
+      "type": "number",
+      "description": "Which video to overlay onto. Omit to use the most recent generated video, or the first uploaded video when no generated video exists. Non-negative values are 0-based indices into prior generated video results. Negative values reference uploaded videos: -1 = first uploaded video, -2 = second, etc., falling back to the most recent generated video when no uploads exist."
+    },
+    "overlays": {
+      "type": "array",
+      "minItems": 1,
+      "description": "Ordered list of overlays to burn in. Each overlay is rendered on top of all previous overlays. Either kind=\"text\" (with `text` and styling) or kind=\"image\" (with `sourceImageIndex`).",
+      "items": {
+        "type": "object",
+        "properties": {
+          "kind": {
+            "type": "string",
+            "enum": [
+              "text",
+              "image"
+            ],
+            "description": "Overlay kind. \"text\" renders drawtext; \"image\" composites an existing image asset."
+          },
+          "position": {
+            "type": "string",
+            "enum": [
+              "top-left",
+              "top-center",
+              "top-right",
+              "center",
+              "bottom-left",
+              "bottom-center",
+              "bottom-right"
+            ],
+            "description": "Anchor position on the frame. Pixel offsets nudge inward; the renderer pads each anchor by a small safe margin so overlays do not touch the frame edge."
+          },
+          "offsetX": {
+            "type": "number",
+            "description": "Optional horizontal offset in pixels. Positive = inward from the anchor edge."
+          },
+          "offsetY": {
+            "type": "number",
+            "description": "Optional vertical offset in pixels. Positive = inward from the anchor edge."
+          },
+          "startSeconds": {
+            "type": "number",
+            "description": "Show the overlay from this time. Default 0 (show from the start). Negative values are relative to the end of the base video; startSeconds=-2 means start 2 seconds before the end."
+          },
+          "endSeconds": {
+            "type": "number",
+            "description": "Hide the overlay at this time. Default = full video duration. Negative values are relative to the end of the base video."
+          },
+          "text": {
+            "type": "string",
+            "description": "Overlay text. Required when kind=\"text\". Use plain text; line breaks are honored."
+          },
+          "fontSizePct": {
+            "type": "number",
+            "minimum": 1,
+            "maximum": 30,
+            "description": "Font size as a percentage of the video height. Default: 6 (≈ 43px on a 720p frame). Only valid when kind=\"text\"."
+          },
+          "color": {
+            "type": "string",
+            "description": "Text fill color (CSS hex like \"#FFFFFF\" or named ffmpeg color). Default \"#FFFFFF\". Only valid when kind=\"text\"."
+          },
+          "outlineColor": {
+            "type": "string",
+            "description": "Text outline color. Default \"#000000\" with a thin stroke for legibility. Only valid when kind=\"text\"."
+          },
+          "backgroundColor": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "description": "Optional rgba background pill behind the text (e.g. \"rgba(0,0,0,0.5)\"). null = no box. Only valid when kind=\"text\"."
+          },
+          "fontWeight": {
+            "type": "string",
+            "enum": [
+              "normal",
+              "bold"
+            ],
+            "description": "Default \"normal\". Only valid when kind=\"text\"."
+          },
+          "sourceImageIndex": {
+            "type": "number",
+            "description": "Which image to overlay. Required when kind=\"image\". Non-negative values are 0-based indices into prior generated image results. Negative values reference uploaded images in image-only order: -1 = first uploaded image, -2 = second, etc. If the user uploaded one video and one logo image, the logo is sourceImageIndex=-1."
+          },
+          "widthPct": {
+            "type": "number",
+            "minimum": 1,
+            "maximum": 100,
+            "description": "Logo width as a percentage of the video width. Default: 15. Only valid when kind=\"image\"."
+          },
+          "opacity": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 1,
+            "description": "Image overlay opacity, 0..1. Default 1.0 (fully opaque). Only valid when kind=\"image\"."
+          },
+          "fit": {
+            "type": "string",
+            "enum": [
+              "contain",
+              "cover"
+            ],
+            "description": "Image sizing mode. Default \"contain\" scales by widthPct and preserves the full overlay image. \"cover\" scales/crops the image to cover the full video frame; use with widthPct=100 for screenshot/still-frame replacement windows."
+          }
+        },
+        "required": [
+          "kind",
+          "position"
+        ]
+      }
+    }
+  },
+  "required": [
+    "overlays"
+  ]
+}