@kolbo/mcp 1.96.1 → 1.96.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.96.1",
+  "version": "1.96.3",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

package/skill/GENERATED.md

@@ -1,6 +1,6 @@
 # AUTO-GENERATED — do not edit
 
-This tree is mirrored from kolbo-code@8d24f6e, the single source of truth.
+This tree is mirrored from kolbo-code@8dfe9b0, the single source of truth.
 Canonical source: packages/opencode/skills/kolbo/
 Distribution: .github/workflows/sync-skill-to-plugin.yml
 

package/skill/SKILL.md

@@ -467,6 +467,8 @@ If at this point you still don't know which `references/` file to load, default
 ## Media selection preferences
 Honor explicit models, presets, budget and inputs. Choose only eligible catalog candidates with all required capabilities. Use requested presets; otherwise use fitting presets when useful. For video generation, editing and lip-sync, when the user has not explicitly selected an output resolution, use the cheapest supported output resolution from the live catalog and pass it explicitly; do not inherit an expensive provider default. Preserve explicit user-selected resolution/settings. Finish fully, cinematic, professional, final, production and available credits are NOT permission to increase resolution. Never infer output resolution from reference media or export settings. A budget is a ceiling, not a spending target. Do not upscale or regenerate at a higher tier without explicit user authorization. If pricing or supported resolutions cannot be verified, inspect the catalog before dispatch; never invent a tier. Models with fixed output resolution use their native output. Never treat a policy refusal as a technical failure or route around safeguards.
 Default images and edits: GPT Image 2.5 Flare/Sunburst; medium for value, high for ordinary maximum quality. Reserve xhigh/max for exceptional dense or difficult multilingual text after medium/high prove insufficient; do not automatically spend on retries. Nano Banana 2 is secondary. Seedream 5.0 Pro favors cinematic aesthetics over complex instruction fidelity; Wan 2.7 Pro is another creative alternative. Z Image/P Image for cheap tests. Midjourney for artistic concepts only, never editing. Soul V2 for realistic people/UGC concepts; derive character sheets before registering finished Visual DNA. Mirage Film 2 for environments and cinematic inspiration.
+**Seedance 2.5 Draft:** explicitly pass `model: "seedance-2-5", resolution: "480p-draft"` on the matching video generation tool. Plain `480p` is regular video, never Draft. Use ordinary credits. Finalize a saved draft via `edit_video` `draft_quote` then authorized `draft_enhance`, with its video URL, original project and quoted supported resolution; do not regenerate the prompt. See `references/models/seedance25.md`.
+
 Default video: Seedance 2.5 for general cinematic work (not Hebrew speech). Kling specializes in controlled single-image and first/last-frame shots. Wan 3.0 specializes in motion graphics and animated typography — native Hebrew speech is poor; attached-audio lip-sync works well. MiniMax H3 offers higher resolution and strong attached-audio lip-sync; H3 Max favors speed at lower resolution with the same audio lip-sync strength. **Native Hebrew dialogue:** Gemini Omni Flash 1.1 or Gemini Omni 1 (best). Seedance 2 / 2.5 do not speak Hebrew — use Latin transliteration in quotes on Seedance, or switch to Gemini Omni. Grok Imagine 1.5 and Seedance 2.0 are non-Hebrew alternatives. P Video/Draft for cheap fast tests. Use base, edit or extend variants only with their required inputs.
 Existing-video lip-sync: Sync 3 for active-speaker handling; PixVerse for cartoons/2D and economical faster work. Portrait lip-sync: Veed Fabric or HeyGen Avatar; P Avatar for budget work. LTX Audio to Video for camera/environment motion with audio-driven performance.
 Default music: Suno v6. ElevenLabs Music is an alternative, especially for duration-directed scoring. Both accept custom duration requests; validate the selected tool schema and inspect actual output duration.

package/skill/references/models/seedance25.md

@@ -15,6 +15,14 @@ Load this file when the user wants a **Seedance 2.5** video (they said "2.5" / "
 
 **Use the cheapest supported tier unless the user selected an output resolution.** Resolution is a credit MULTIPLIER, not a flat rate. Relative to 720p: 480p ×0.44, 1080p ×2.25. A 30s pass costs ~540cr at 480p against ~1230cr at 720p and ~2770cr at 1080p. When no output resolution was selected and 480p is the cheapest supported tier, block the film at 480p, get the user's sign-off on staging, performance and timing, then re-run only the approved cut at a higher delivery resolution if the user explicitly authorizes that resolution increase. Approval of the creative cut alone does not authorize a more expensive resolution. If no output resolution was selected, use the cheapest supported tier from the live catalog even for final work; pass it explicitly.
 
+## Special Draft mode and full-quality rendering
+
+**Draft is a distinct generation mode, not a synonym for low resolution.** When the user requests Seedance 2.5 Draft, use the ordinary generation tool for their inputs (`generate_video`, `generate_video_from_image`, or `generate_elements`) with `model: "seedance-2-5"` and `resolution: "480p-draft"`. `resolution: "480p"` is a regular generation and cannot be presented as Draft. Do not silently substitute regular 480p when Draft was requested. Read the live catalog's `supported_resolutions` and draft capabilities; do not invent draft support for other models.
+
+Draft uses ordinary credits, not Unlimited. Keep the user's complete prompt, duration, aspect ratio, references, audio and shot settings. Tell the user which mode was actually submitted; the widget should say **480p Draft** for Draft. Choosing the cheapest pixel size alone does not select Draft.
+
+To turn an approved draft into full quality, use its saved output video URL and original project: call `edit_video` with `operation: "draft_quote"`, `video_url`, `project_id`, and the desired supported `resolution`. Read the exact credits, expiry and supported resolutions from that quote. Once the paid finalization is authorized, call `edit_video` with `operation: "draft_enhance"` and the same source/project/resolution. This is a dedicated render of the saved draft, not a new text-to-video generation or generic upscale. Never ask the user for provider task IDs or cache handles. If the draft has expired or cannot be finalized, explain that result before proposing a new paid generation.
+
 ## What's NEW in 2.5 (verified — never hedge)
 
 - **Duration 4–30 seconds**, whole seconds. 30s IS supported.

package/src/apps/theme.js

@@ -85,7 +85,7 @@ body {
 .k-prompt { color: var(--text-muted); font-size: 12.5px; margin-bottom: 4px; word-break: break-word;
   display: -webkit-box; -webkit-line-clamp: 2; -webkit-box-orient: vertical; overflow: hidden;
   user-select: text; -webkit-user-select: text; cursor: text; }
-.k-prompt.expanded { -webkit-line-clamp: unset; }
+.k-prompt.expanded { -webkit-line-clamp: unset; white-space: pre-wrap; }
 .k-text-tools { display: flex; gap: 2px; justify-content: flex-end; margin: 0 0 10px; }
 .k-text-btn {
   display: inline-flex; align-items: center; gap: 4px;

package/src/apps/widgets/generation.js

@@ -135,6 +135,8 @@ function makeExpandable(node, raw) {
   // Synchronous layout read — rAF would never fire in a hidden/backgrounded
   // iframe, leaving long prompts stuck without the expand affordance.
   var overflow = node.scrollHeight > node.clientHeight + 2 || node.scrollWidth > node.clientWidth + 2;
+  // Hidden host iframes report zero dimensions. Long prompts still need an expand button.
+  if (node.id === 'prompt' && text.length > 120) overflow = true;
   if (overflow) node.classList.add('k-clamped');
   var tools = document.createElement('div');
   tools.className = 'k-text-tools';
@@ -282,6 +284,15 @@ function displayKind(sc) {
   return kind || 'image';
 }
 
+function resolutionLabel(sc) {
+  var s = sc.settings || {};
+  var resolution = String(s.resolution || '');
+  var model = String(sc.model || '');
+  var draft = /-draft$/i.test(resolution) || /-draft$/i.test(model) || s.is_draft === true || sc.is_draft === true;
+  var pixels = resolution.replace(/-draft$/i, '');
+  return draft ? (pixels ? pixels + ' Draft' : 'Draft') : resolution;
+}
+
 function renderChips(sc) {
   var h = modelChipHTML(modelLabel(sc), sc.model_icon);
   var s = sc.settings || {};
@@ -293,7 +304,8 @@ function renderChips(sc) {
   var shotLabel = s.shots > 1 ? (s.shots + ' shots') : (s.multi_shot ? 'multishot' : '');
   if (s.duration) h += chip(ICONS.clock + ' ' + fmtDur(s.duration) + (shotLabel ? ' · ' + shotLabel : ''));
   else if (shotLabel) h += chip(shotLabel);
-  if (s.resolution) h += chip(esc(s.resolution));
+  var resolutionText = resolutionLabel(sc);
+  if (resolutionText) h += chip(esc(resolutionText));
   if (s.aspect_ratio) h += chip(esc(s.aspect_ratio));
   if (s.quality) h += chip(esc(s.quality) + ' quality');
   if (s.enhance_prompt) h += chip(ICONS.sparkle + ' enhanced');
@@ -1343,7 +1355,7 @@ function openPromptRow(placeholder, onSend) {
 var PRE_IMAGE_KEYS = ['source_images', 'reference_images', 'image_url', 'mask_image_url',
   'additional_images', 'first_frame', 'last_frame', 'seed_reference_image_url',
   'elements', 'files', 'keyframes', 'source'];
-var PRE_VIDEO_KEYS = ['source_video', 'reference_videos'];
+var PRE_VIDEO_KEYS = ['source_video', 'video_url', 'reference_videos'];
 var PRE_AUDIO_KEYS = ['audio', 'audio_url', 'reference_audio_urls', 'seed_reference_audio_urls'];
 
 // The card mounts the moment the tool is CALLED, so the only thing it knows is
@@ -1375,6 +1387,7 @@ function preRefSc(toolName, a) {
   PRE_AUDIO_KEYS.forEach(function (k) { take(a[k], aud); });
   return {
     tool: toolName,
+    is_draft: /-draft$/i.test(String(a.model || '')),
     kind: kindFromTool(toolName, null),
     count: a.num_images || (Array.isArray(a.prompts) ? a.prompts.length : 1),
     reference_images: img,

package/src/tools/generate.js

@@ -617,7 +617,7 @@ function registerGenerateTools(server, client, options = {}) {
   // retired textToVideoGeneration path and was stale.
   server.tool(
     'generate_video',
-    'Generate a video from a text prompt using Kolbo AI. For SEVERAL different videos, pass all their prompts in `prompts` in ONE call (one combined widget) — never a series of separate calls. For animating an existing still image into motion, use generate_video_from_image instead. For a coordinated multi-scene video campaign, use generate_creative_director with workflow_type="video". Supports reference images (for style/composition guidance) and Visual DNA for character consistency. Seedance 2/2.5 PERFORM quoted dialogue natively (synced voice, lip movement, room tone) — do not route scene dialogue to generate_speech or generate_lipsync; write it in ENGLISH or Latin transliteration of Hebrew ("shalom"), never Hebrew script — Seedance 2/2.5 do not speak Hebrew; prefer Gemini Omni Flash 1.1 or Gemini Omni 1 for native Hebrew. Resolution is a credit MULTIPLIER (vs 720p: 480p x0.44, 1080p x2.25, 4k x4.95), so draft at 480p and re-run only the approved cut at delivery resolution. ROUTE BEFORE CALLING: when reference images anchor IDENTITY (specific characters, a specific product, a location that must match) — especially 2+ of them — that is generate_elements, not this tool; reference_images here are loose style/composition hints. Decide the right tool FIRST: a mis-routed call still starts a PAID generation, and switching tools afterwards without cancel_generation leaves the user paying for both. Returns the final video URL when complete.',
+    'Generate a video from a text prompt using Kolbo AI. For SEVERAL different videos, pass all their prompts in `prompts` in ONE call (one combined widget) — never a series of separate calls. For animating an existing still image into motion, use generate_video_from_image instead. For a coordinated multi-scene video campaign, use generate_creative_director with workflow_type="video". Supports reference images (for style/composition guidance) and Visual DNA for character consistency. Seedance 2/2.5 PERFORM quoted dialogue natively (synced voice, lip movement, room tone) — do not route scene dialogue to generate_speech or generate_lipsync; write it in ENGLISH or Latin transliteration of Hebrew ("shalom"), never Hebrew script — Seedance 2/2.5 do not speak Hebrew; prefer Gemini Omni Flash 1.1 or Gemini Omni 1 for native Hebrew. Resolution is a credit MULTIPLIER (vs 720p: 480p x0.44, 1080p x2.25, 4k x4.95), so use a lower resolution for previews. For actual Seedance 2.5 Draft, explicitly pass resolution="480p-draft" with model="seedance-2-5", then use edit_video draft_quote/draft_enhance for paid finalization. Plain "480p" is a regular generation, not Draft. ROUTE BEFORE CALLING: when reference images anchor IDENTITY (specific characters, a specific product, a location that must match) — especially 2+ of them — that is generate_elements, not this tool; reference_images here are loose style/composition hints. Decide the right tool FIRST: a mis-routed call still starts a PAID generation, and switching tools afterwards without cancel_generation leaves the user paying for both. Returns the final video URL when complete.',
     {
       prompt: z.string().optional().describe('Text description of the video to generate. Required unless `prompts` is provided.'),
       prompts: promptsField('videos'),
@@ -1442,7 +1442,7 @@ function registerGenerateTools(server, client, options = {}) {
       preset_id: z.string().optional().describe('Preset ID from list_presets type="video" (optional)'),
       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 across outputs. **Cap: pass at most `max_visual_dna` IDs from list_models for the chosen model.**'),
-      resolution: z.string().optional().describe('Video resolution tier (vertical pixels): "720p" / "1080p" / "1440p" / "2160p". Model-dependent — call list_models and read supported_resolutions.'),
+      resolution: z.string().optional().describe('Video resolution or named tier: read supported_resolutions from list_models. For Seedance 2.5 Draft explicitly use model="seedance-2-5", resolution="480p-draft". Plain "480p" generates regular video, NOT Draft. Finalize an actual draft with edit_video operation="draft_quote" then "draft_enhance".'),
       sound_enabled: z.boolean().optional().describe('Enable (`true`) or disable (`false`) AI-generated synced audio on the output video. Honored by `sound_generation_type: "native"` models (Kling O3/V3, Veo 3.1, PixVerse V6). Omit to use `sound_enabled_by_default`. Enabling sound may apply `sound_credit_multiplier` to cost.'),
       keyframes: z.array(z.object({
         image_url: z.string().describe('Public URL of the keyframe image'),
@@ -1639,7 +1639,7 @@ function registerGenerateTools(server, client, options = {}) {
       aspect_ratio: z.string().optional().describe(aspectRatioDescribe('16:9') + ' Auto-detected from the first frame if omitted.'),
       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. **Cap: pass at most `max_visual_dna` IDs from list_models for the chosen model; if `supports_visual_dna: false`, DNA is silently ignored.**'),
-      resolution: z.string().optional().describe('Video resolution tier (vertical pixels): "720p" / "1080p" / "1440p" / "2160p". Model-dependent — call list_models and read supported_resolutions.'),
+      resolution: z.string().optional().describe('Video resolution or named tier: read supported_resolutions from list_models. For Seedance 2.5 Draft explicitly use model="seedance-2-5", resolution="480p-draft". Plain "480p" generates regular video, NOT Draft. Finalize an actual draft with edit_video operation="draft_quote" then "draft_enhance".'),
       sound_enabled: z.boolean().optional().describe('Enable (`true`) or disable (`false`) AI-generated synced audio on the output video. Honored by `sound_generation_type: "native"` models (Kling O3/V3, Veo 3.1, PixVerse V6). Omit to use `sound_enabled_by_default`. Enabling sound may apply `sound_credit_multiplier` to cost.'),
       project_id: projectIdField,
       session_id: sessionIdField
@@ -1850,7 +1850,7 @@ function registerGenerateTools(server, client, options = {}) {
       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'),
       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.**'),
-      resolution: z.string().optional().describe('Video resolution tier (vertical pixels): "720p" / "1080p" / "1440p" / "2160p". Model-dependent — call list_models and read supported_resolutions.'),
+      resolution: z.string().optional().describe('Video resolution or named tier: read supported_resolutions from list_models. For Seedance 2.5 Draft explicitly use model="seedance-2-5", resolution="480p-draft". Plain "480p" generates regular video, NOT Draft. Finalize an actual draft with edit_video operation="draft_quote" then "draft_enhance".'),
       reference_images: z.array(z.string()).optional().describe('Array of reference image URLs for models that support additional image inputs. **Cap: pass at most `max_images` URLs from list_models — if `max_images === 0` the model does not accept image refs.** Examples: character reference images for Kling O1/O3, style reference for Aleph/gen4_aleph, character image for WAN VACE video-edit.'),
       reference_videos: z.array(z.string()).optional().describe('Array of additional reference video URLs for models that support multiple video inputs. **Cap: pass at most `max_videos` URLs from list_models — if `max_videos <= 1` only the source_video is accepted.** Example: WAN 2.6 reference-to-video accepts 1–3 reference videos.'),
       elements: z.array(z.string()).optional().describe('Array of element image URLs. **Cap: pass at most `max_elements` URLs from list_models — if `max_elements === 0` the model does not accept elements.** Elements are style or character reference assets alongside the main video.'),