@sogni-ai/sogni-intelligence-client 3.12.6 → 3.12.7

package/dist/schemas/tools/generate_video.schema.json

@@ -3,7 +3,7 @@
   "$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, seedance2-mini, 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-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render the composite board, audit it, generate per-scene GPT Image 2 keyframes, then render Seedance scene clips and stitch them. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent.",
+  "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, seedance2-mini, seedance2-fast, or seedance2-5, default to exactly one video (4-15s on 2.0/Mini/Fast, 4-30s on seedance2-5) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one Seedance prompt within the selected model's per-clip limit are still one video. If the user requests one continuous Seedance video longer than 15s, prefer \"seedance2-5\", which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini/Fast) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance generate_video call by default; do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render the composite board, audit it, generate per-scene GPT Image 2 keyframes, then render Seedance scene clips and stitch them. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent.",
   "type": "object",
   "additionalProperties": false,
   "properties": {
@@ -21,9 +21,9 @@
     },
     "duration": {
       "type": "number",
-      "description": "Video duration in seconds. Default: 5. Range: 2-20. Use when the user explicitly requests a specific length. MiniMax H3 is quantized to a 17-frame grid at a fixed 24 fps and renders 124-362 frames, so an H3 clip runs 5.17-15.08 seconds and a requested length outside that window snaps to the nearest valid H3 length.",
+      "description": "Video duration in seconds. Default: 5. Range: 2-30; the usable window is per-model and the host clamps to it. LTX 2.3 and WAN accept 2-20, Seedance 2.0/Mini/Fast accept 4-15, and Seedance 2.5 accepts 4-30 — only \"seedance2-5\" can use the 16-30s part of this range. MiniMax H3 is quantized to a 17-frame grid at a fixed 24 fps and renders 124-362 frames, so an H3 clip runs 5.17-15.08 seconds and a requested length outside that window snaps to the nearest valid H3 length. Use when the user explicitly requests a specific length.",
       "minimum": 2,
-      "maximum": 20
+      "maximum": 30
     },
     "negativePrompt": {
       "type": "string",
@@ -37,13 +37,15 @@
         "seedance2",
         "seedance2-mini",
         "seedance2-fast",
+        "seedance2-5",
         "minimax-h3-t2v",
+        "minimax-h3-t2v-turbo",
         "happyhorse-1.1-t2v",
         "happyhorse-1.1-i2v",
         "happyhorse-1.1-r2v",
         "minimax-h3-r2v"
       ],
-      "description": "Video model. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx23\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 text-to-video uses \"minimax-h3-t2v\". H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\", a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one reference image is required — reference videos and audio are additions to the image set, never replacements for it. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. 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."
+      "description": "Video model. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx23\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. There is no H3 Turbo r2v selector. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\", a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
     },
     "generateAudio": {
       "type": "boolean",
@@ -54,21 +56,21 @@
       "items": {
         "type": "number"
       },
-      "description": "Image references for Seedance (@Image tags), HappyHorse 1.1 r2v, and MiniMax H3 r2v. Use negative indices for uploaded images (-1 first upload, -2 second upload) and non-negative indices for generated image results. For Seedance, 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. For HappyHorse 1.1 r2v, pass 1-9 image references. For MiniMax H3 r2v, at least one image reference is required (up to 9); H3 references are loose references, not locked frames, and are addressed in the prompt as <Picture 1>, <Picture 2>, and so on in selection order."
+      "description": "Image references for Seedance (@Image tags), HappyHorse 1.1 r2v, and MiniMax H3 r2v. Use negative indices for uploaded images (-1 first upload, -2 second upload) and non-negative indices for generated image results. For Seedance, 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. For HappyHorse 1.1 r2v, pass 1-9 image references. For MiniMax H3 r2v, up to 9 images are accepted; at least one image or video reference is required, and H3 references are loose references, not locked frames, and are addressed in the prompt as <Picture 1>, <Picture 2>, and so on in selection order."
     },
     "referenceVideoIndices": {
       "type": "array",
       "items": {
         "type": "number"
       },
-      "description": "Optional loose video references for Seedance and MiniMax H3 r2v. Use negative indices for uploaded videos (-1 first uploaded video, -2 second uploaded video) and non-negative indices for generated video results. For Seedance, 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. For MiniMax H3 r2v, up to 3 reference videos (24 fps, 2-15s each, optional soundtrack), addressed as <Video 1>, <Video 2>, and so on in selection order; they supplement the required H3 image reference."
+      "description": "Optional loose video references for Seedance and MiniMax H3 r2v. Use negative indices for uploaded videos (-1 first uploaded video, -2 second uploaded video) and non-negative indices for generated video results. For Seedance, 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. For MiniMax H3 r2v, up to 3 reference videos (24 fps, 2-15s each, optional soundtrack), addressed as <Video 1>, <Video 2>, and so on in selection order; they can satisfy the required visual reference without an image."
     },
     "referenceAudioIndices": {
       "type": "array",
       "items": {
         "type": "number"
       },
-      "description": "Optional loose audio references for Seedance and MiniMax H3 r2v. Use negative indices for uploaded audio files (-1 first uploaded audio, -2 second uploaded audio) and non-negative indices for generated audio results. For Seedance, 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-mini\" instead unless the user asks for full Seedance. Audio-only Seedance requests are unsupported; use sound_to_video for uploaded-audio-only workflows. For MiniMax H3 r2v, up to 3 standalone audio tracks, addressed as <Audio 1>, <Audio 2>, and so on in selection order — a reference video's own soundtrack takes its Audio number before standalone tracks; they supplement the required H3 image reference and cannot replace it."
+      "description": "Optional loose audio references for Seedance and MiniMax H3 r2v. Use negative indices for uploaded audio files (-1 first uploaded audio, -2 second uploaded audio) and non-negative indices for generated audio results. For Seedance, 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-mini\" instead unless the user asks for full Seedance. Audio-only Seedance requests are unsupported; use sound_to_video for uploaded-audio-only workflows. For MiniMax H3 r2v, up to 3 standalone audio tracks, addressed as <Audio 1>, <Audio 2>, and so on in selection order — a reference video's own soundtrack takes its Audio number before standalone tracks; they supplement a required image or video reference and cannot be the sole input."
     },
     "width": {
       "type": "number",
@@ -80,7 +82,7 @@
     },
     "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\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-fast\"). Seedance 2.0 full supports 4K; Seedance Mini and Fast support 480p/720p only. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, the host uses the selected model default. 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\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
+      "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-fast\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini, Fast, and Seedance 2.5 support 480p/720p only, so never set 1080p or 4K for \"seedance2-5\". Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, the host uses the selected model default. 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\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
     },
     "numberOfVariations": {
       "type": "number",

package/dist/schemas/tools/replace_video_segment.schema.json

@@ -45,9 +45,10 @@
         "wan22",
         "seedance2",
         "seedance2-mini",
-        "seedance2-fast"
+        "seedance2-fast",
+        "seedance2-5"
       ],
-      "description": "Which model to use for the new segment. Default: \"auto\" — detect from the base video's producer (Seedance base → Seedance, Wan base → Wan 2.2, otherwise LTX-2.3). Override only when the user explicitly requests a different model."
+      "description": "Which model to use for the new segment. Default: \"auto\" — detect from the base video's producer (Seedance base → the same Seedance model, Wan base → Wan 2.2, otherwise LTX-2.3). Override only when the user explicitly requests a different model. \"seedance2-5\" is the Seedance 2.5 editing path: 480p/720p only, 4-30s replacement windows at 24 fps with native audio."
     },
     "keepOriginalAudio": {
       "type": "boolean",

package/dist/schemas/tools/sound_to_video.schema.json

@@ -3,7 +3,7 @@
   "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/sound_to_video.schema.json",
   "title": "sound_to_video arguments",
   "schemaVersion": "2026-04-27.1",
-  "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx23-ia2v; for lip-sync with a face image, use wan-s2v; if no image, use ltx23-a2v. If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.3 generates audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video instead. LONG AUDIO ON SEEDANCE: Seedance caps each clip at 15s. When the user uploads audio longer than 15s and Seedance is selected (seedance2, seedance2-mini, or seedance2-fast), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them.",
+  "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx23-ia2v; for lip-sync with a face image, use wan-s2v; if no image, use ltx23-a2v. If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.3 generates audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video instead. LONG AUDIO ON SEEDANCE: Seedance 2.0, Mini, and Fast cap each clip at 15s; Seedance 2.5 caps each clip at 30s, so prefer \"seedance2-5\" for 16-30s audio instead of splitting. When uploaded audio exceeds the selected Seedance model's per-clip cap, do NOT clamp and drop the rest — split the run into multiple sound_to_video calls in the same turn using 15s segments for seedance2/seedance2-mini/seedance2-fast or 30s segments for seedance2-5, then finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them.",
   "type": "object",
   "additionalProperties": false,
   "properties": {
@@ -30,9 +30,9 @@
     },
     "duration": {
       "type": "number",
-      "description": "Video duration in seconds. Default: 5. Range: 2-20. For music videos, use the MAXIMUM duration (20) since the audio is always longer than the video limit. Use when the user explicitly requests a specific length.",
+      "description": "Video duration in seconds. Default: 5. Range: 2-30; the usable window is per-model and the host clamps to it. LTX 2.3 and WAN accept 2-20, Seedance 2.0/Mini/Fast accept 4-15, and Seedance 2.5 accepts 4-30. For music videos, use the MAXIMUM duration the selected model allows (20 for LTX/WAN, 30 for \"seedance2-5\") since the audio is always longer than the video limit. Use when the user explicitly requests a specific length.",
       "minimum": 2,
-      "maximum": 20
+      "maximum": 30
     },
     "videoModel": {
       "type": "string",
@@ -41,10 +41,11 @@
         "seedance2",
         "seedance2-mini",
         "seedance2-fast",
+        "seedance2-5",
         "ltx23-ia2v",
         "ltx23-a2v"
       ],
-      "description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"ltx23-a2v\" (default when no image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s; this tool supplies the audio plus a required reference image because Seedance text+audio without image/video is unsupported. \"seedance2-mini\": Seedance 2.0 Mini for faster, lower-cost 720p iteration. \"seedance2-fast\": legacy Seedance 2.0 Fast. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster draft/lower-cost Seedance unless the user explicitly says Seedance Fast, pick \"seedance2-fast\" when the user says Seedance Fast / seedance-fast, and pick \"seedance2\" for full/non-fast Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present."
+      "description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"ltx23-a2v\" (default when no image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s; this tool supplies the audio plus a required reference image because Seedance text+audio without image/video is unsupported. \"seedance2-mini\": Seedance 2.0 Mini for faster, lower-cost 720p iteration. \"seedance2-fast\": legacy Seedance 2.0 Fast. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster draft/lower-cost Seedance unless the user explicitly says Seedance Fast, pick \"seedance2-fast\" when the user says Seedance Fast / seedance-fast, and pick \"seedance2\" for full/non-fast Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
     },
     "generateAudio": {
       "type": "boolean",

package/dist/schemas/tools/video_to_video.schema.json

@@ -9,7 +9,7 @@
   "properties": {
     "prompt": {
       "type": "string",
-      "description": "Describe the TARGET appearance (not the transformation process). 2-4 present-tense sentences.\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. For Seedance, set expandPrompt=false.\n\nFor LTX-2.3 canny/depth/pose modes, the source video preserves composition, depth, or motion. Spend prompt detail on style, atmosphere, lighting, surface texture, color palette, scale, and pacing.\n\nExamples by mode:\n- animate-move (DEFAULT — WAN 2.2 Animate Move: applies camera/motion from source video to reference image): \"Smooth cinematic camera movement following the subject through the scene.\"\n- animate-replace (WAN 2.2 Animate Replace: replaces the subject in the source video with the reference image): \"The person from the reference photo performing the actions from the video.\"\n- canny (LTX-2.3 — edge-detection restyle): \"Hand-drawn watercolor anime style with soft ink edges, muted teal and coral palette, rain mist, neon reflections, warm rim light, preserving original silhouettes and composition.\"\n- pose (LTX-2.3 — tracks skeleton, replace person): \"A glossy cartoon robot with exaggerated proportions, brushed metal texture, glowing cyan joints, energetic stage lighting, preserving the original dance timing and pose.\"\n- depth (LTX-2.3 — depth-map restyle): \"A misty alpine valley at golden hour, expansive scale, volumetric haze, cool blue shadows, warm rim light, cinematic depth, lingering continuous shot.\"\n- detailer (LTX-2.3 — enhance quality): DESCRIBE THE SOURCE, do not request changes. Append quality qualifiers only. E.g. \"The same scene, ultra-sharp and clean, crisp high-resolution detail, preserving all original content, composition, and color.\" Avoid words like \"enhanced textures\", \"restyled\", or any new subjects/objects — they cause drift.\n- seedance-v2v (BytePlus Dreamina Seedance 2.0 V2V): \"Restyle the source clip in a watercolor look with soft ink edges, while preserving its motion and composition.\" Use natural prose; Seedance reads the reference video holistically rather than via control-net constraints, so describe target style/mood/dialogue rather than control strength.\n\nPresent tense. Positive phrasing. Concrete visual details.\n\nBATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary the artistic treatment while keeping control mode and structural intent consistent. Example: \"transform to {watercolor with soft edges|oil painting with bold strokes|anime with clean lines} style\"."
+      "description": "Describe the TARGET appearance (not the transformation process). 2-4 present-tense sentences.\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. For Seedance, set expandPrompt=false.\n\nFor LTX-2.3 canny/depth/pose modes, the source video preserves composition, depth, or motion. Spend prompt detail on style, atmosphere, lighting, surface texture, color palette, scale, and pacing.\n\nExamples by mode:\n- animate-move (DEFAULT — WAN 2.2 Animate Move: applies camera/motion from source video to reference image): \"Smooth cinematic camera movement following the subject through the scene.\"\n- animate-replace (WAN 2.2 Animate Replace: replaces the subject in the source video with the reference image): \"The person from the reference photo performing the actions from the video.\"\n- canny (LTX-2.3 — edge-detection restyle): \"Hand-drawn watercolor anime style with soft ink edges, muted teal and coral palette, rain mist, neon reflections, warm rim light, preserving original silhouettes and composition.\"\n- pose (LTX-2.3 — tracks skeleton, replace person): \"A glossy cartoon robot with exaggerated proportions, brushed metal texture, glowing cyan joints, energetic stage lighting, preserving the original dance timing and pose.\"\n- depth (LTX-2.3 — depth-map restyle): \"A misty alpine valley at golden hour, expansive scale, volumetric haze, cool blue shadows, warm rim light, cinematic depth, lingering continuous shot.\"\n- detailer (LTX-2.3 — enhance quality): DESCRIBE THE SOURCE, do not request changes. Append quality qualifiers only. E.g. \"The same scene, ultra-sharp and clean, crisp high-resolution detail, preserving all original content, composition, and color.\" Avoid words like \"enhanced textures\", \"restyled\", or any new subjects/objects — they cause drift.\n- seedance-v2v (BytePlus Dreamina Seedance V2V): \"Restyle the source clip in a watercolor look with soft ink edges, while preserving its motion and composition.\" Use natural prose; Seedance reads the reference video holistically rather than via control-net constraints, so describe target style/mood/dialogue rather than control strength.\n\nPresent tense. Positive phrasing. Concrete visual details.\n\nBATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary the artistic treatment while keeping control mode and structural intent consistent. Example: \"transform to {watercolor with soft edges|oil painting with bold strokes|anime with clean lines} style\"."
     },
     "expandPrompt": {
       "type": "boolean",
@@ -30,11 +30,11 @@
         "detailer",
         "seedance-v2v"
       ],
-      "description": "How the source video and (optional) reference image interact. Pick by user intent:\n• \"animate-move\" (DEFAULT) — WAN 2.2 Animate Move. Applies camera movement and motion from the source video to the reference image, bringing a still photo to life. Requires sourceImageIndex.\n• \"animate-replace\" — WAN 2.2 Animate Replace. Replaces the subject in the source video with the person/character from the reference image, keeping the video's background and motion. Requires sourceImageIndex.\n• \"canny\" — LTX-2.3 edge-detection control. Best for restyling while preserving exact composition and silhouettes (e.g. \"make this footage look like anime / oil painting / watercolor\"). Use for subjects with crisp edges — people, objects, graphics. Video-only; no reference image needed.\n• \"pose\" — LTX-2.3 skeletal tracking. Best for replacing a person while keeping their motion (e.g. \"turn this dancer into a robot\"). Image optional — if provided, controls appearance; otherwise the prompt drives appearance. Requires person-centric motion.\n• \"depth\" — LTX-2.3 depth-map control. Best for restyling scenes with perspective, camera movement, or volumetric content (landscapes, interiors, camera pans). Preserves 3D spatial layout rather than 2D edges; more forgiving than canny when edges are noisy. Video-only.\n• \"detailer\" — LTX-2.3 quality enhancement. Sharpens detail and texture WITHOUT restyling. The prompt must DESCRIBE THE ORIGINAL scene with quality qualifiers (sharp, clean, high-resolution) — never request content changes, new textures, or a new look. Pick this when the user asks to \"improve quality\", \"enhance\", \"upscale\", or \"sharpen\" without a creative transformation.\n• \"seedance-v2v\" — BytePlus Dreamina Seedance 2.0 video-to-video. Use only when the user explicitly asks for Seedance on the uploaded source video, such as Seedance Fast upscale, enhance, remaster, restyle, or transform. High-fidelity quality, native audio, time-coded scene control. Seedance V2V reads @Video1 holistically. Use it for restyling, motion transfer, extension, subject replacement, or scene transformation, and assign @Video1 a clear role such as source clip, camera movement, action timing, edit rhythm, or continuation anchor. Distinct from canny/depth/pose which use control-net constraints — Seedance treats the reference video holistically.\nCanny vs depth: canny preserves silhouettes and fine outlines — pick it for subject-led scenes and graphic restyles. Depth preserves 3D structure — pick it for scenes where the camera moves or spatial layout matters more than edge fidelity. Default: \"animate-move\"."
+      "description": "How the source video and (optional) reference image interact. Pick by user intent:\n• \"animate-move\" (DEFAULT) — WAN 2.2 Animate Move. Applies camera movement and motion from the source video to the reference image, bringing a still photo to life. Requires sourceImageIndex.\n• \"animate-replace\" — WAN 2.2 Animate Replace. Replaces the subject in the source video with the person/character from the reference image, keeping the video's background and motion. Requires sourceImageIndex.\n• \"canny\" — LTX-2.3 edge-detection control. Best for restyling while preserving exact composition and silhouettes (e.g. \"make this footage look like anime / oil painting / watercolor\"). Use for subjects with crisp edges — people, objects, graphics. Video-only; no reference image needed.\n• \"pose\" — LTX-2.3 skeletal tracking. Best for replacing a person while keeping their motion (e.g. \"turn this dancer into a robot\"). Image optional — if provided, controls appearance; otherwise the prompt drives appearance. Requires person-centric motion.\n• \"depth\" — LTX-2.3 depth-map control. Best for restyling scenes with perspective, camera movement, or volumetric content (landscapes, interiors, camera pans). Preserves 3D spatial layout rather than 2D edges; more forgiving than canny when edges are noisy. Video-only.\n• \"detailer\" — LTX-2.3 quality enhancement. Sharpens detail and texture WITHOUT restyling. The prompt must DESCRIBE THE ORIGINAL scene with quality qualifiers (sharp, clean, high-resolution) — never request content changes, new textures, or a new look. Pick this when the user asks to \"improve quality\", \"enhance\", \"upscale\", or \"sharpen\" without a creative transformation.\n• \"seedance-v2v\" — BytePlus Dreamina Seedance video-to-video. Use only when the user explicitly asks for Seedance on the uploaded source video, such as Seedance Fast upscale, enhance, remaster, restyle, or transform. High-fidelity quality, native audio, time-coded scene control. Seedance V2V reads @Video1 holistically. Use it for restyling, motion transfer, extension, subject replacement, or scene transformation, and assign @Video1 a clear role such as source clip, camera movement, action timing, edit rhythm, or continuation anchor. Distinct from canny/depth/pose which use control-net constraints — Seedance treats the reference video holistically.\nCanny vs depth: canny preserves silhouettes and fine outlines — pick it for subject-led scenes and graphic restyles. Depth preserves 3D structure — pick it for scenes where the camera moves or spatial layout matters more than edge fidelity. Default: \"animate-move\"."
     },
     "negativePrompt": {
       "type": "string",
-      "description": "Non-Seedance only. Optional negative prompt for LTX/Wan video-to-video models. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-fast; rewrite user-provided Seedance avoid/ban/no-X requests as positive prompt instructions."
+      "description": "Non-Seedance only. Optional negative prompt for LTX/Wan video-to-video models. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-fast/seedance2-5; rewrite user-provided Seedance avoid/ban/no-X requests as positive prompt instructions."
     },
     "videoModel": {
       "type": "string",
@@ -43,9 +43,10 @@
         "wan22-animate",
         "seedance2",
         "seedance2-mini",
-        "seedance2-fast"
+        "seedance2-fast",
+        "seedance2-5"
       ],
-      "description": "Model selector for this video-to-video request. Usually omit; controlMode chooses the non-Seedance model. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance V2V unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for full/non-fast Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro or from 480p/720p resolution requests alone."
+      "description": "Model selector for this video-to-video request. Usually omit; controlMode chooses the non-Seedance model. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance V2V unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for full/non-fast Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro or from 480p/720p resolution requests alone. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
     },
     "generateAudio": {
       "type": "boolean",
@@ -53,7 +54,7 @@
     },
     "targetResolution": {
       "type": "number",
-      "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p. Preserve the source video shape instead of forcing landscape pixels."
+      "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini, Fast, and Seedance 2.5 support 480p and 720p only. Preserve the source video shape instead of forcing landscape pixels."
     },
     "sourceImageIndex": {
       "type": "number",
@@ -61,9 +62,9 @@
     },
     "duration": {
       "type": "number",
-      "description": "Output video duration in seconds. Range: 2-20 for WAN/LTX modes and 4-15 for controlMode=\"seedance-v2v\". If omitted, the tool matches the uploaded source video duration when available (capped to the selected model range); otherwise it falls back to 10s for WAN Animate Move/Replace and 5s for LTX-2.3/Seedance modes. For long stitched/bulk WAN Animate Move/Replace work with no explicit per-clip length, prefer about 10s clips rather than 5s chunks. Only pass this when the user explicitly requests a different length.",
+      "description": "Output video duration in seconds. Range: 2-20 for WAN/LTX modes, 4-15 for controlMode=\"seedance-v2v\" on \"seedance2\"/\"seedance2-mini\"/\"seedance2-fast\", and 4-30 for controlMode=\"seedance-v2v\" on \"seedance2-5\". If omitted, the tool matches the uploaded source video duration when available (capped to the selected model range); otherwise it falls back to 10s for WAN Animate Move/Replace and 5s for LTX-2.3/Seedance modes. For long stitched/bulk WAN Animate Move/Replace work with no explicit per-clip length, prefer about 10s clips rather than 5s chunks. Only pass this when the user explicitly requests a different length.",
       "minimum": 2,
-      "maximum": 20
+      "maximum": 30
     },
     "numberOfVariations": {
       "type": "number",

package/dist/tools/shared/_catalogs.generated.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"_catalogs.generated.d.ts","sourceRoot":"","sources":["../../../src/tools/shared/_catalogs.generated.ts"],"names":[],"mappings":"AAKA,eAAO,MAAM,8BAA8B,EAAE,OAQ5C,CAAC"}
+{"version":3,"file":"_catalogs.generated.d.ts","sourceRoot":"","sources":["../../../src/tools/shared/_catalogs.generated.ts"],"names":[],"mappings":"AAKA,eAAO,MAAM,8BAA8B,EAAE,OAkC5C,CAAC"}

package/dist/tools/shared/_catalogs.generated.js

@@ -2,12 +2,38 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.seedanceReferenceLimitsCatalog = void 0;
 exports.seedanceReferenceLimitsCatalog = {
-    "description": "Maximum loose-reference assets accepted per Seedance 2.0 video generation request. SDKs use this catalog to validate user input client-side and to render UI affordances (e.g. disable an upload button once the per-modality cap or the combined-total cap is reached). The numbers mirror the BytePlus Dreamina Seedance 2.0 platform limits and are the same values previously hard-coded in sogni-chat's orchestration. Per-video request: at most `images` image refs (start frame + end frame + loose `referenceImageUrls`), `videos` video refs, and `audios` audio refs, with at most `assets` total ref files across all three modalities.",
+    "description": "Maximum loose-reference assets accepted per Seedance video generation request. SDKs use this catalog to validate user input client-side and to render UI affordances (e.g. disable an upload button once the per-modality cap or the combined-total cap is reached). The numbers mirror the BytePlus Dreamina Seedance platform limits and are the same values previously hard-coded in sogni-chat's orchestration. Per-video request: at most `images` image refs (start frame + end frame + loose `referenceImageUrls`), `videos` video refs, and `audios` audio refs, with at most `assets` total ref files across all three modalities. The caps are per-model: model-aware consumers should read `perModel[<canonical model id>]` and reject unknown model IDs rather than guessing. `limits` intentionally remains the backwards-compatible default for consumers that do not select a model and carries the Seedance 2.0 family numbers so an SDK built against an older protocol under-permits rather than over-permits.",
     "limits": {
         "images": 9,
         "videos": 3,
         "audios": 3,
         "assets": 12
+    },
+    "perModel": {
+        "seedance-2-0": {
+            "images": 9,
+            "videos": 3,
+            "audios": 3,
+            "assets": 12
+        },
+        "seedance-2-0-mini": {
+            "images": 9,
+            "videos": 3,
+            "audios": 3,
+            "assets": 12
+        },
+        "seedance-2-0-fast": {
+            "images": 9,
+            "videos": 3,
+            "audios": 3,
+            "assets": 12
+        },
+        "seedance-2-5": {
+            "images": 30,
+            "videos": 10,
+            "audios": 10,
+            "assets": 30
+        }
     }
 };
 //# sourceMappingURL=_catalogs.generated.js.map

package/dist/tools/shared/_catalogs.generated.js.map

@@ -1 +1 @@
-{"version":3,"file":"_catalogs.generated.js","sourceRoot":"","sources":["../../../src/tools/shared/_catalogs.generated.ts"],"names":[],"mappings":";;;AAKa,QAAA,8BAA8B,GAAY;IACrD,aAAa,EAAE,qnBAAqnB;IACpoB,QAAQ,EAAE;QACR,QAAQ,EAAE,CAAC;QACX,QAAQ,EAAE,CAAC;QACX,QAAQ,EAAE,CAAC;QACX,QAAQ,EAAE,EAAE;KACb;CACF,CAAC"}
+{"version":3,"file":"_catalogs.generated.js","sourceRoot":"","sources":["../../../src/tools/shared/_catalogs.generated.ts"],"names":[],"mappings":";;;AAKa,QAAA,8BAA8B,GAAY;IACrD,aAAa,EAAE,k+BAAk+B;IACj/B,QAAQ,EAAE;QACR,QAAQ,EAAE,CAAC;QACX,QAAQ,EAAE,CAAC;QACX,QAAQ,EAAE,CAAC;QACX,QAAQ,EAAE,EAAE;KACb;IACD,UAAU,EAAE;QACV,cAAc,EAAE;YACd,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,EAAE;SACb;QACD,mBAAmB,EAAE;YACnB,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,EAAE;SACb;QACD,mBAAmB,EAAE;YACnB,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,CAAC;YACX,QAAQ,EAAE,EAAE;SACb;QACD,cAAc,EAAE;YACd,QAAQ,EAAE,EAAE;YACZ,QAAQ,EAAE,EAAE;YACZ,QAAQ,EAAE,EAAE;YACZ,QAAQ,EAAE,EAAE;SACb;KACF;CACF,CAAC"}