@kolbo/mcp 1.118.2 → 1.118.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.118.2",
+  "version": "1.118.3",
   "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

@@ -1631,11 +1631,11 @@ function registerGenerateTools(server, client, options = {}) {
       prompt: z.string().optional().describe('Optional ONLY for kolbo-morphious-* and higgsfield-genjutsu-* models (the server analyzes the media). For other models, 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. EVERY attached reference must also be tagged by its 1-based array position — `@Image 1`/`@Image 2` (reference_images), `@Video 1` (reference_videos), `@Audio 1` (reference_audio_urls) — and its job stated ("@Image 1 defines the character\'s face and wardrobe", "@Video 1 defines the camera move"). An untagged attachment is ignored by the engine even though it was uploaded and billed.'),
       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.). Tag each one in the prompt text by its 1-based position here — item 1 is `@Image 1`, item 2 is `@Image 2` — or the engine ignores it. 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. Tag each one in the prompt text by its 1-based position here — `@Video 1`, `@Video 2` — stating what it defines (motion, camera move, pacing), or the engine ignores it. 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 its nominal duration to combined-second billing: encoder padding within 0.15s of an integer snaps to it; larger fractions round up.'),
-      reference_audio_urls: z.array(z.string()).optional().describe('Array of reference audio tracks for models that accept audio inputs. Tag each one in the prompt text by its 1-based position here — `@Audio 1`, `@Audio 2` — stating what it carries (dialogue, ambience, music), or the engine ignores it. 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.'),
+      reference_videos: z.array(z.string()).optional().describe('Array of reference videos for models that accept video inputs. Tag each one in the prompt text by its 1-based position here — `@Video 1`, `@Video 2` — stating what it defines (motion, camera move, pacing), or the engine ignores it. 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. When `elements_max_video_seconds_total` is set, all clips COMBINED must stay within it (Wan 3.0: 15s total). When `elements_input_plus_output_max_seconds` is set, reference-video seconds + `duration` must stay within it (Wan 3.0: 30s — e.g. 10s of refs leaves at most 20s of output). Exceeding either is a deterministic 400.** If `video_input_credit` is present, every attached video contributes its nominal duration to combined-second billing: encoder padding within 0.15s of an integer snaps to it; larger fractions round up.'),
+      reference_audio_urls: z.array(z.string()).optional().describe('Array of reference audio tracks for models that accept audio inputs. Tag each one in the prompt text by its 1-based position here — `@Audio 1`, `@Audio 2` — stating what it carries (dialogue, ambience, music), or the engine ignores it. 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; when `elements_max_audio_seconds_total` is set, all audio clips COMBINED must stay within it (Wan 3.0: 15s total). Audio does NOT reduce the output-duration budget — only reference VIDEO does.** `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.**'),
-      duration: z.number().optional().describe('Output duration in seconds. Must be in `supported_durations` from list_models, OR within `min_output_duration`-`max_output_duration`. Default: 5'),
+      duration: z.number().optional().describe('Output duration in seconds. Must be in `supported_durations` from list_models, OR within `min_output_duration`-`max_output_duration`. When the model publishes `elements_input_plus_output_max_seconds` AND the call carries reference_videos, the effective max is that cap minus the combined reference-video seconds (Wan 3.0: cap 30 — 12s of refs → duration ≤ 18). Default: 5'),
       aspect_ratio: z.string().optional().describe(aspectRatioDescribe('16:9')),
       motion: z.string().optional().describe('Motion style / intensity hint (optional)'),
       preset_id: z.string().optional().describe('Preset ID from list_presets type="video" (optional)'),
@@ -2063,7 +2063,7 @@ function registerGenerateTools(server, client, options = {}) {
       prompt: z.string().optional().describe('Text description of the desired restyle / transformation. Required by most video-to-video models; omit for prompt-less models (VEED Subtitles, Act Two, Wan Animate, Kling Motion Control, kolbo-morphious-*, higgsfield-genjutsu-motion-transfer, higgsfield-genjutsu-object-swap).'),
       model: z.string().optional().describe('Model identifier. Use list_models type="video_to_video" to see options and check max_images / max_videos / max_elements / max_video_duration per model. Pick a SPECIFIC model — do NOT omit (omitting = Smart Select auto-pick, which we avoid); call list_models for this type and choose the model that best fits the user\'s intent.'),
       aspect_ratio: z.string().optional().describe(aspectRatioDescribe() + ' Default: matches source.'),
-      duration: z.number().optional().describe('Output duration in seconds. Must be in `supported_durations` from list_models, OR within `min_output_duration`-`max_output_duration`. Default: matches source'),
+      duration: z.number().optional().describe('Output duration in seconds. Must be in `supported_durations` from list_models, OR within `min_output_duration`-`max_output_duration`. When the model publishes `elements_input_plus_output_max_seconds` (Wan 3.0 / Wan 3.0 Prime video-to-video: 30), source-video seconds + duration must stay within it — a 15s source leaves at most 15s of output, 10s leaves 20s. Exceeding it is a deterministic 400. Default: matches source'),
       enhance_prompt: z.boolean().optional().describe('Enhance the prompt. Default: false — only pass true if the user explicitly asks to enhance/improve the prompt.'),
       visual_dna_ids: z.array(z.string()).optional().describe('Array of Visual DNA profile IDs to apply for character/style consistency. **Cap: pass at most `max_visual_dna` IDs from list_models for the chosen model; if `supports_visual_dna: false`, DNA is silently ignored.**'),
       style_id: z.string().optional().describe('Morphious Styles only (kolbo-morphious-motion or kolbo-morphious-swap; Standard only, the Lite modes refuse a style): id of a look from list_morphious_styles (Kolbo catalog or a custom style the user made). Restyles the WHOLE video in that look; the style counts as reference image 1, so no reference_images are needed. Prompt optional.'),