@kolbo/mcp 1.96.1 → 1.96.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.96.1",
+  "version": "1.96.2",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

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.'),