@kolbo/mcp 1.64.0 → 1.65.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.64.0",
+  "version": "1.65.1",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

package/skill/SKILL.md

@@ -99,7 +99,7 @@ Each `references/models/*.md` mirrors the matching skill prompt in `kolbo-api/sr
 | `generate_video` | Text-to-video. Does **not** support Visual DNA — use `generate_elements` for character-consistent video. |
 | `generate_video_from_image` | Animate a still. Prompt describes motion, not subject. |
 | `generate_video_from_video` | Restyle/transform an existing video. Keeps original motion. |
-| `generate_elements` | Reference-driven video. **Primary route for DNA → video.** |
+| `generate_elements` | Reference-driven video. **Primary route for DNA → video.** Supports `multi_shots` / `multi_shot_count` (badge/metadata/native flag only — never rewrites the prompt) and short `session_name`. Crafted demos: `enhance_prompt:false` + put shot structure in the prompt. |
 | `generate_first_last_frame` | Keyframe interpolation between two frames. |
 | `generate_lipsync` | Lipsync audio to an image or video face. |
 | `generate_music` | Music generation (Suno + variants). |

package/skill/references/models/seedance.md

@@ -9,6 +9,8 @@ Load this file when the user wants a **Seedance 2 / Seedance 2.0** (ByteDance) v
 
 **Kolbo MCP routing:** Seedance is a video model — call `generate_video` (text-to-video) or `generate_elements` (when video references / Visual DNA / first-last frames are involved). Run `list_models({ type: "text_to_video" })` and pick a Seedance variant by name.
 
+**Multishot (Elements):** Seedance has **no** native provider Multishot switch. Pass `multi_shots: true` on `generate_elements` (optional `multi_shot_count`) for the UI Multishot badge only — it does **not** rewrite or reshape your prompt. **Always send `enhance_prompt: false` for crafted demos** (MCP default) so the prompt stays RAW. Put shot structure in the prompt yourself (`Multishot ON`, `Total: … / N shots`, numbered shots). Optional `session_name` sets a short sidebar title (skips AI auto-name from boilerplate).
+
 ## Universal Rules (apply to EVERY Seedance prompt)
 
 - **First line ALWAYS declares shot structure**: total duration, shot count, aspect ratio. Example: `Total: 15s / 6 shots / 16:9`. Put it at the BOTTOM of the prompt too. For connected narrative sequences the proven phrasing is `N connected cinematic shots, 15 seconds total, 16:9, Multishot ON` — use it and keep `Multishot ON` for any multi-shot story.

package/skill/references/workflows/marketing-studio.md

@@ -123,7 +123,7 @@ If the user gives a **product URL** instead of a photo, see `workflows/research-
 
 ## Multi-Slot Board Method (structured shot specs + character consistency)
 
-For any multi-shot UGC / review / how-to where the SAME presenter must stay identical across shots, compose the prompt as explicit **slots** and lock identity with a **board-first** pass. This is a prompt-only convention — no special MCP mode; it uses `generate_image` (board) + `generate_elements` / `generate_video_from_image` (per-slot animate) that already exist.
+For any multi-shot UGC / review / how-to where the SAME presenter must stay identical across shots, compose the prompt as explicit **slots** and lock identity with a **board-first** pass. Prefer `generate_elements` with `multi_shots: true` (and a short `session_name`) when animating a single multi-cut Seedance spot; board-first still uses `generate_image` + `generate_elements` / `generate_video_from_image` per slot when you need separate clips.
 
 ### 1. Structured input slots
 

package/src/tools/generate.js

@@ -987,10 +987,13 @@ function registerGenerateTools(server, client, options = {}) {
         image_url: z.string().describe('Public URL of the keyframe image'),
         timestamp_seconds: z.number().describe('Moment on the OUTPUT timeline (seconds, 0 = first frame) where this image is pinned')
       })).optional().describe('Timeline-pinned keyframes for multi-keyframe models (e.g. "flux-3-keyframes", "luma-ray-3-2-storyboard"): the model generates the motion BETWEEN the pinned images. Only models with `supports_keyframes: true` in list_models accept this; cap = `max_keyframes` (FLUX 3: 10). Requires an explicit `duration` — timestamps beyond it are clamped. Ignored by ordinary elements models. OPTIONAL for flux-3-keyframes: if omitted, pass the images via reference_images instead — they are played through IN ORDER, timed from timing language in the prompt or spaced evenly. Pass explicit keyframes only when you need exact control.'),
+      multi_shots: z.boolean().optional().describe('Enable Multishot metadata/UI badge (and native provider flag when the model supportsMultiShot). Never rewrites or reshapes the prompt — craft shot structure yourself (`Multishot ON`, Total/SHOT lines). MCP default enhance_prompt=false keeps the prompt raw; multi_shots alone is badge/flag only. For crafted demos: enhance_prompt:false + multi_shots:true.'),
+      multi_shot_count: z.number().optional().describe('Explicit shot count when multi_shots=true (e.g. 2). Clamped to ~2 shots/sec of duration.'),
+      session_name: z.string().optional().describe('Short sidebar session title (max ~60 chars), e.g. "UGC — Hana bathroom light". When set, skips AI auto-naming from the prompt boilerplate.'),
       project_id: projectIdField,
       session_id: sessionIdField
     },
-    async ({ prompt, model, reference_images, reference_videos, reference_audio_urls, audio_url, files, duration, aspect_ratio, motion, preset_id, enhance_prompt = false, visual_dna_ids, resolution, keyframes, project_id, session_id }) => {
+    async ({ prompt, model, reference_images, reference_videos, reference_audio_urls, audio_url, files, duration, aspect_ratio, motion, preset_id, enhance_prompt = false, visual_dna_ids, resolution, keyframes, multi_shots, multi_shot_count, session_name, project_id, session_id }) => {
       model = await canonicalModelId(client, model, 'elements'); // lenient id resolution ("z-image" → "z-image/turbo")
       if (!prompt) throw new Error('prompt is required');
 
@@ -1013,6 +1016,9 @@ function registerGenerateTools(server, client, options = {}) {
         if (audio_url) form.append('audio_url', audio_url);
         if (resolution) form.append('resolution', resolution);
         if (keyframes) form.append('keyframes', JSON.stringify(keyframes));
+        if (multi_shots !== undefined) form.append('multi_shots', String(multi_shots));
+        if (multi_shot_count !== undefined) form.append('multi_shot_count', String(multi_shot_count));
+        if (session_name) form.append('session_name', session_name);
         if (project_id) form.append('project_id', project_id);
         if (session_id) form.append('session_id', session_id);
         for (const f of resolved) {
@@ -1022,7 +1028,7 @@ function registerGenerateTools(server, client, options = {}) {
       } else {
         // URL-only mode: plain JSON.
         startResponse = await client.post('/v1/generate/elements', {
-          prompt, model, reference_images, reference_videos, reference_audio_urls, audio_url, duration, aspect_ratio, motion, preset_id, enhance_prompt, visual_dna_ids, resolution, keyframes, project_id, session_id
+          prompt, model, reference_images, reference_videos, reference_audio_urls, audio_url, duration, aspect_ratio, motion, preset_id, enhance_prompt, visual_dna_ids, resolution, keyframes, multi_shots, multi_shot_count, session_name, project_id, session_id
         });
       }
 

package/src/tools/visual_dna.js

@@ -197,7 +197,7 @@ function registerVisualDnaTools(server, client, options = {}) {
     'Generate a reference sheet for a Visual DNA from 1+ reference image URLs — the same step the in-app Visual DNA wizard offers, for EVERY DNA type via `sheet_type`: character = multi-angle turnaround, product = angles + branding/material/construction close-ups, environment = location angles + one signature detail, style = a style board (the same look applied to six varied subjects). The sheet is the single strongest consistency booster for a DNA, and it always preserves the reference\'s original art style (2D stays 2D, photo stays photo). CHARGES CREDITS, so when the user is about to create a DNA, OFFER this first ("want me to generate a reference sheet for stronger consistency? it costs a few credits") and only run it on a yes. Returns `character_sheet_url` — pass it as `character_sheet_url` to `create_visual_dna` with the matching `dna_type`.',
     {
       image_urls: z.array(z.string()).min(1).describe('Reference image URLs of the subject (for characters: front/side/varied angles work best). Use generated-image URLs or upload_media output.'),
-      sheet_type: z.enum(['character', 'product', 'environment', 'style']).optional().describe('Which sheet layout to generate — match the DNA type it will be attached to. Defaults to character.')
+      sheet_type: z.enum(['character', 'character_headless', 'product', 'environment', 'style']).optional().describe('Sheet layout. character = front/back/face turnaround. character_headless = wardrobe/body refs with a headless front panel (use when clothing must change without fighting the face sheet). product / environment / style = matching DNA types. Defaults to character.')
     },
     async ({ image_urls, sheet_type }) => {
       const result = await client.post('/v1/visual-dna/character-sheet', { image_urls, ...(sheet_type ? { sheet_type } : {}) });