@kolbo/mcp 1.83.1 → 1.83.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.83.1",
+  "version": "1.83.2",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

package/src/tools/generate.js

@@ -1254,12 +1254,12 @@ function registerGenerateTools(server, client, options = {}) {
   // ─── generate_elements ─────────────────────────────────────
   server.tool(
     'generate_elements',
-    'Generate a video from reference elements (images, videos, and/or audio) + a text prompt. Use when the user wants to animate specific uploaded/referenced assets — e.g. "animate this product", "put these 3 characters into a scene". PRIMARY ROUTE FOR A DNA-ANCHORED MULTI-SHOT FILM: one call can carry the whole sequence — seedance-2-5 takes 4-30s, up to 30 shots and 20 Visual DNAs in a SINGLE generation (seedance-2: 4-15s, 9 DNAs) — instead of a stack of separate clips. DIALOGUE IS PERFORMED NATIVELY: quoted dialogue in the prompt comes back as synced voices with lip movement, room tone and the SFX named in the AUDIO block — never route scene dialogue to generate_speech or generate_lipsync. Write dialogue in ENGLISH; other languages (Hebrew included) do not perform reliably. COST: resolution is a MULTIPLIER, not a flat fee (vs 720p: 480p x0.44, 1080p x2.25, 4k x4.95) — run blocking/draft passes at 480p and re-run only the approved cut at delivery resolution. PROMPT CONTRACT (Seedance / Elements): Locked Intro only — Total line, then [GLOBAL LOOK] / [CAST] / [LOCATION] / SHOT N. Do NOT write SCENE CONTEXT / OPTICS / ACTION department packs. Every Visual DNA in visual_dna_ids MUST also appear in the prompt as @ExactDNAName (e.g. "@Zohar walks…") — never "Zohar\'s" or "the man on the left" as a substitute. IMPORTANT: different models accept different numbers of inputs — call list_models type="elements" and read elements_max_images / elements_max_videos / elements_max_audio on the chosen model before generating. For text-only → video use generate_video instead. For animating a single still image use generate_video_from_image. Returns the final video URL when complete.',
+    'Generate a video from reference elements (images, videos, and/or audio) + a text prompt. Use when the user wants to animate specific uploaded/referenced assets — e.g. "animate this product", "put these 3 characters into a scene". PRIMARY ROUTE FOR A DNA-ANCHORED MULTI-SHOT FILM: one call can carry the whole sequence — seedance-2-5 takes 4-30s, up to 30 shots and 20 Visual DNAs in a SINGLE generation (seedance-2: 4-15s, 9 DNAs) — instead of a stack of separate clips. DIALOGUE IS PERFORMED NATIVELY: quoted dialogue in the prompt comes back as synced voices with lip movement, room tone and the SFX named in the AUDIO block — never route scene dialogue to generate_speech or generate_lipsync. Write dialogue in ENGLISH; other languages (Hebrew included) do not perform reliably. COST: resolution is a multiplier. When list_models publishes `video_input_credit` and this call carries videos, charge that rate against `sum(ceil(each input video duration)) + output duration`; otherwise use the normal output-second rate. PROMPT CONTRACT (Seedance / Elements): Locked Intro only — Total line, then [GLOBAL LOOK] / [CAST] / [LOCATION] / SHOT N. Do NOT write SCENE CONTEXT / OPTICS / ACTION department packs. Every Visual DNA in visual_dna_ids MUST also appear in the prompt as @ExactDNAName (e.g. "@Zohar walks…") — never "Zohar\'s" or "the man on the left" as a substitute. IMPORTANT: different models accept different numbers and durations of inputs — call list_models type="elements" and read elements_max_images / elements_max_videos / elements_max_audio plus min_video_duration / max_video_duration before generating. For text-only → video use generate_video instead. For animating a single still image use generate_video_from_image. Returns the final video URL when complete.',
     {
       prompt: z.string().describe('Locked Intro prompt (Seedance/Elements): Total line, [GLOBAL LOOK], [CAST] with @ExactDNAName for every visual_dna_ids entry, [LOCATION], then SHOT N. Not SCENE CONTEXT/OPTICS/ACTION packs. Never substitute "the left man" or "Zohar\'s" for @Name.'),
       model: z.string().optional().describe('Model identifier. If the user already named a family (Grok / Kling / Veo / Seedance / …), pass THAT family — never default to Seedance because Elements often uses it. Use list_models type="elements" for exact ids and elements_max_* caps. Do NOT omit (omitting = Smart Select).'),
       reference_images: z.array(z.string()).optional().describe('Array of image references (product shots, character references, etc.). Accepts a public URL (forwarded as-is; if the API rejects an external URL as untrusted, it is auto-rehosted into the media library and retried once) OR an absolute local path, which is uploaded for you. **Cap: pass at most `elements_max_images` URLs from list_models for the chosen model — exceeding it is a deterministic 400.**'),
-      reference_videos: z.array(z.string()).optional().describe('Array of reference videos for models that accept video inputs. Accepts a public URL (forwarded as-is; if the API rejects an external URL as untrusted, it is auto-rehosted into the media library and retried once) OR an absolute local path, which is uploaded for you. **Cap: pass at most `elements_max_videos` URLs from list_models — if the cap is 0 the model rejects videos.**'),
+      reference_videos: z.array(z.string()).optional().describe('Array of reference videos for models that accept video inputs. Accepts a public URL (forwarded as-is; if the API rejects an external URL as untrusted, it is auto-rehosted into the media library and retried once) OR an absolute local path, which is uploaded for you. **Cap: pass at most `elements_max_videos` URLs and keep every clip within `min_video_duration`-`max_video_duration` from list_models.** If `video_input_credit` is present, every attached video contributes `ceil(its duration)` to combined-second billing, in addition to output duration.'),
       reference_audio_urls: z.array(z.string()).optional().describe('Array of reference audio tracks for models that accept audio inputs. Accepts a public URL (forwarded as-is; if the API rejects an external URL as untrusted, it is auto-rehosted into the media library and retried once) OR an absolute local path, which is uploaded for you. **Cap: pass at most `elements_max_audio` URLs from list_models.** `audio_url` remains supported as the legacy single-track form.'),
       audio_url: z.string().optional().describe('A single reference audio track — legacy form of reference_audio_urls. Accepts a public URL (forwarded as-is; if the API rejects an external URL as untrusted, it is auto-rehosted into the media library and retried once) OR an absolute local path, which is uploaded for you. **Audio constraints: `elements_max_audio` from list_models gates whether audio is accepted at all; audio duration must fall within `min_audio_duration`-`max_audio_duration`; format must be in `supported_audio_formats` (if specified).**'),
       files: z.array(z.string()).optional().describe('Untyped catch-all for mixed media — images, videos AND audio, each a URL or an absolute local path. The kind is detected from the file extension and the item is routed to the matching reference list, so a local .mp4 is sent as a video and a local .mp3 as audio. Prefer the typed lists (reference_images / reference_videos / reference_audio_urls) when you already know the kind; they accept local paths too. URLs given here are forwarded as URLs, never re-uploaded. **Caps still apply per kind: `elements_max_images` / `elements_max_videos` / `elements_max_audio` from list_models. Local uploads are capped at 200MB each.**'),

package/src/tools/models.js

@@ -106,6 +106,7 @@ const identifierRow = (m) => ({
   name: m.name,
   types: m.types,
   credit: m.credit,
+  ...(m.video_input_credit != null ? { video_input_credit: m.video_input_credit } : {}),
   ...(m.recommended ? { recommended: true } : {}),
   ...(m.new_model ? { new_model: true } : {}),
 });
@@ -115,7 +116,7 @@ function registerModelTools(server, client, options = {}) {
   // ─── list_models ───────────────────────────────────────────
   server.tool(
     'list_models',
-    'List available AI models on Kolbo. Filter by `type` to narrow to a generation type, and pass `format: "json"` to enumerate the catalog with exact identifiers — `format: "json"` + `type` returns the full raw model documents (every constraint field, for programmatic comparison / cap validation before submitting a generation); `format: "json"` alone returns a compact index of EVERY model and its identifier. Default `format: "text"` returns the human-readable summary. NEVER guess a model identifier: call this tool. ⚠️ COST: for any model whose type is video / firstlast / elements / motion_graphic / cast, `credit` is a PER-SECOND rate, not a per-clip price — multiply by the requested `duration` before quoting cost to the user (e.g. `credit: 9` at `duration: 8` is 72 credits, not 9). This is the universal rule, not a per-model exception. The one carve-out is a model with `flat_credit_by_resolution` set — those charge the flat rate regardless of duration. Every other model type (image, audio, 3D, per-token text) already bills flat per generation as `credit` states.',
+    'List available AI models on Kolbo. Filter by `type` to narrow to a generation type, and pass `format: "json"` to enumerate the catalog with exact identifiers — `format: "json"` + `type` returns the full raw model documents (every constraint field, for programmatic comparison / cap validation before submitting a generation); `format: "json"` alone returns a compact index of EVERY model and its identifier. Default `format: "text"` returns the human-readable summary. NEVER guess a model identifier: call this tool. ⚠️ COST: video / firstlast / elements / motion_graphic / cast rates are normally per output second. If a model publishes `video_input_credit` and the request includes one or more input videos, use that alternate rate and bill `sum(ceil(each input video duration)) + output duration`; each input rounds separately. A `flat_credit_by_resolution` model instead charges the flat tier regardless of duration. Every other model type (image, audio, 3D, per-token text) bills as its catalog fields state.',
     {
       type: z.string().optional().describe('Filter by DB type name. Generation: "text_to_img", "image_editing", "text_to_video", "img_to_video", "draw_to_video", "video_to_video", "elements", "firstlastgenerations", "lipsync-image", "lipsync-video", "music_gen", "text_to_speech", "text_to_sound", "stt", "text". Image-edit engines: "image_upscale", "image_reframe", "image_zoom_out", "inpaint", "erase", "face_swap", "background_remove", "background_replace", "skin_enhancer", "graphics_enhance". Video-edit engines: "video_upscale", "video_reframe", "video_background_removal", "video_to_sound", "video_face_swap", "video_watermark_removal", "video_extend", "video_inpaint", "video_retake". For edit_image/edit_video, query the operation-specific type and pass a CONCRETE returned identifier; never submit a kolbo_gateway_* row, because those are web-navigation aliases rather than AI engines. Legacy aliases also accepted: "image", "image_edit", "video", "video_from_image", "video_from_video", "music", "speech", "sound", "chat", "lipsync", "three_d", "first_last_frame", "transcription". Omit for all models.'),
       format: z.enum(['text', 'json']).optional().describe('Output format. "text" (default) returns a human-readable summary with the most-used caps. "json" is the source of truth for identifiers and caps: with `type` it returns the raw model documents from the API (identifier, credit, supported_durations, supported_resolutions, supported_aspect_ratios, max_reference_images, max_visual_dna, max_video_duration, …) for EVERY model of that type; without `type` it returns a compact index of every model in the catalog and its exact identifier. Use it whenever you need an identifier you have not seen listed, or must verify a cap before passing a value that might exceed a model-specific limit.'),
@@ -213,6 +214,14 @@ function registerModelTools(server, client, options = {}) {
           );
         }
 
+        if (m.video_input_credit != null) {
+          const vm = m.video_input_resolution_multipliers || {};
+          const tiers = Object.keys(vm).length
+            ? ' · ' + Object.entries(vm).map(([r, mult]) => `${r} (${mult}×)`).join(' · ')
+            : '';
+          parts.push(`video_input_price: ${m.video_input_credit} credits/combined-second${tiers} · bill sum(ceil(each input video)) + output`);
+        }
+
         // Output durations (video gen output, not source video)
         if (Array.isArray(m.supported_durations) && m.supported_durations.length) {
           const ds = m.supported_durations;
@@ -369,7 +378,7 @@ function registerModelTools(server, client, options = {}) {
       const cost = m => (m.output_token_rate != null
         ? `${m.input_token_rate ?? '?'}/${m.output_token_rate} credits per 1K tokens (in/out)`
         : isPerSecondVideo(m)
-          ? `${m.credit} credits/second (× requested duration — NOT a flat per-clip price)`
+          ? `${m.credit} credits/output-second${m.video_input_credit != null ? `; ${m.video_input_credit} credits/combined-second with video input` : ''}`
           : `${m.credit} credits`);
       const formatModel = m =>
         `${m.identifier} (${m.name}) - ${cost(m)}${m.recommended ? ' [RECOMMENDED]' : ''}${m.new_model ? ' [NEW]' : ''}${m.summary ? ` — ${detailed ? m.summary : brief(m.summary)}` : ''}${detailed ? formatSpecs(m) : ''}`;