@kolbo/mcp 1.84.0 → 1.84.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.84.0",
+  "version": "1.84.2",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

package/src/apps/index.js

@@ -88,6 +88,17 @@ const WIDGET_CSP = {
     'https://assets.sketchfab.com',
     'https://sketchfab-prod-media.s3.amazonaws.com',
 
+    // Voice PREVIEW audio hosts. list_voices ships every voice with a
+    // preview_url and the card renders a real <audio> for it, but 150 of the
+    // 864 production voices store that preview on a provider host rather than a
+    // Kolbo bucket: 138 google voices on storage.googleapis.com and 12 on
+    // api.us.elevenlabs.io. media-src blocked both, so every google voice — the
+    // entire Hebrew set — rendered a player stuck at 0:00 / 0:00 with no error
+    // anywhere. The Spaces-hosted previews come free via HOST_MAP above; these
+    // two do not, because they are not ours.
+    'https://storage.googleapis.com',
+    'https://api.us.elevenlabs.io',
+
     // Default SYNCI catalog project. Any production override must be reviewed
     // and added here as an exact hostname before deployment.
     'https://gfbpxdkripkbbrcvoyeh.supabase.co',

package/src/apps/widgets/mediaGrid.js

@@ -48,17 +48,17 @@ function boot(sc) {
   var audioItems = sc.items.filter(function (i) { return i.media_type === 'audio'; });
   var visualItems = sc.items.filter(function (i) { return i.media_type !== 'audio'; });
   var h = '';
+  // Render everything currently in state — each PAGE is already capped
+  // server-side (GRID_CAP), so this grows one page per Load more instead of
+  // being pinned forever. The old hard slices (24 visual / 12 audio) meant an
+  // appended page could never actually appear, and the count below tallied all
+  // items while only 36 were drawn, so the button also lied about the total.
   if (visualItems.length) {
-    h += '<div class="k-grid">' + visualItems.slice(0, 24).map(cellHTML).join('') + '</div>';
+    h += '<div class="k-grid">' + visualItems.map(cellHTML).join('') + '</div>';
   }
   if (audioItems.length) {
-    h += audioItems.slice(0, 12).map(audioRowHTML).join('');
+    h += audioItems.map(audioRowHTML).join('');
   }
-  // Only a fixed page ever renders here (24 visual + 12 audio) — with a library
-  // in the thousands there was no way to reach the rest short of asking in
-  // chat. A visible "Load more" turns that into one click; it sends a message
-  // rather than calling the tool directly, since the widget has no host API
-  // to invoke a tool itself — same mechanism every other "Use" action here uses.
   var shown = visualItems.length + audioItems.length;
   if (sc.total != null && sc.total > shown) {
     h += '<button class="k-btn" id="load-more" style="width:100%;margin-top:10px">Load more (' +
@@ -145,13 +145,50 @@ function wire() {
   });
   var loadMore = el('load-more');
   if (loadMore) {
-    loadMore.onclick = function () {
-      window.kolbo.sendMessage('Show me the next page of this same media search (already saw ' +
-        (state.items.length) + ' of ' + state.total + ' results).');
-    };
+    loadMore.onclick = function () { fetchNextPage(loadMore); };
   }
 }
 
+// Fetch the next page IN the widget and append it.
+//
+// This used to sendMessage() a request for "the next page of this same media
+// search", on the stated belief that a widget has no way to invoke a tool. It
+// does — window.kolbo.callTool, the same bridge call every generation card
+// polls status with. And the message could not have worked anyway: the payload
+// carried no page number and none of the filters, so the model had nothing to
+// reconstruct the query from and would re-run page 1 or something else. The
+// button appeared to do nothing.
+function fetchNextPage(btn) {
+  if (!state || !state.page_tool || btn.disabled) return;
+  var next = (state.page || 1) + 1;
+  btn.disabled = true;
+  var label = btn.textContent;
+  btn.innerHTML = '<span class="k-spin"></span> Loading';
+  var args = {};
+  var q = state.query || {};
+  for (var k in q) { if (q[k] !== undefined && q[k] !== null && q[k] !== '') args[k] = q[k]; }
+  args.page = next;
+  if (state.page_size) args.page_size = state.page_size;
+
+  window.kolbo.callTool(state.page_tool, args).then(function (res) {
+    var sc = structured(res);
+    var more = (sc && sc.items) || [];
+    if (!more.length) {
+      // Nothing came back: say so rather than restoring a button that still
+      // looks like it has pages behind it.
+      btn.textContent = 'No more results';
+      return;
+    }
+    state.items = (state.items || []).concat(more);
+    state.page = (sc && sc.page) || next;
+    if (sc && sc.total != null) state.total = sc.total;
+    boot(state);            // re-renders the grid + a fresh Load more button
+  }).catch(function () {
+    btn.disabled = false;
+    btn.textContent = label;
+  });
+}
+
 function useItem(i) {
   var item = state.items[i];
   if (!item || !item.id) return;

package/src/tools/_shared.js

@@ -851,6 +851,18 @@ async function uiCompleted(p, textPayload, extraContent) {
     // above which assume everything finished together. Only set when the
     // caller actually has this shape; every existing caller is unaffected.
     ...(Array.isArray(p.items) ? { items: p.items } : {}),
+    // Transcription payload. get_generation_status is the ONLY way the live
+    // transcript widget learns its result, and it reads text/srt_url/txt_url off
+    // this object — but uiCompleted is shaped for the generation card and
+    // dropped every one, so a finished transcription rendered "(empty
+    // transcript)" with no SRT/TXT buttons while the text sat in the status
+    // response. structuredContent SHADOWS the text block on widget hosts, so
+    // omitting a field here is the same as deleting it.
+    ...(typeof p.text === 'string' ? { text: p.text } : {}),
+    ...(p.srt_url ? { srt_url: p.srt_url } : {}),
+    ...(p.word_by_word_srt_url ? { word_by_word_srt_url: p.word_by_word_srt_url } : {}),
+    ...(p.txt_url ? { txt_url: p.txt_url } : {}),
+    ...(p.audio_url ? { audio_url: p.audio_url } : {}),
     // The voice, by name and portrait. uiGenerating has carried this since the
     // chips were introduced; uiCompleted never did, so it silently dropped a
     // resolved voice its caller had already looked up — every FINISHED speech

package/src/tools/generate.js

@@ -1118,6 +1118,14 @@ function registerGenerateTools(server, client, options = {}) {
           state: single.state,
           urls: done ? urls : undefined,
           thumbnail_url: res.thumbnail_url,
+          // Transcription results ride the same status tool as media
+          // generations; without these the transcript widget merges a payload
+          // with no transcript in it and renders "(empty transcript)".
+          text: typeof res.text === 'string' ? res.text : undefined,
+          srt_url: res.srt_url || undefined,
+          word_by_word_srt_url: res.word_by_word_srt_url || undefined,
+          txt_url: res.txt_url || undefined,
+          audio_url: res.audio_url || undefined,
           // The refs the server actually conditioned on (reference_details) —
           // the live card merges this payload over its submit-time state, so
           // the finished card shows every reference, including server-side

package/src/tools/media.js

@@ -303,7 +303,17 @@ function registerMediaTools(server, client, options = {}) {
         title: 'Media Library',
         items,
         total: totalItems != null ? totalItems : media.length,
-        shown: Math.min(media.length, GRID_CAP)
+        shown: Math.min(media.length, GRID_CAP),
+        // Everything "Load more" needs to fetch page N+1 ITSELF. The button used
+        // to send a chat message asking the model to run the next page, on the
+        // belief that a widget cannot invoke a tool — it can
+        // (window.kolbo.callTool, the same call every generation card polls
+        // with). Worse, the payload carried no page and no filters, so the model
+        // could not reconstruct the query either and typically re-ran page 1.
+        page_tool: 'list_media',
+        page: page || 1,
+        page_size: page_size || 50,
+        query: { project_id, folder_id, type, category, source_type, sort, search }
       });
     }
   );

package/src/tools/visual_dna.js

@@ -28,6 +28,7 @@ function registerVisualDnaTools(server, client, options = {}) {
       name: z.string().describe('Name of the Visual DNA profile. **Pick a short, lowercase, no-space single token** (e.g. `maya`, `tokyo_neon`, `brand_red`, `esther_model`) — never names with spaces (`Sarah Johnson` ❌). The user/LLM types this as `@<name>` inside generation prompts, and the @ parser stops at the first space, so `@Sarah Johnson` matches only `Sarah` and the binding silently drops. Multi-word concepts should use underscores or be a single token. Names are case-insensitive on lookup, but **reserved** values rejected on creation: `Image1`, `Image2`, …, `Video1`, …, `Audio1`, … (any-language characters allowed; max 100 chars).'),
       dna_type: z.string().optional().describe('Type: "character", "style", "product", "scene", "environment". Default: "character"'),
       prompt_helper: z.string().optional().describe('Optional description/notes to guide DNA extraction'),
+      description: z.string().optional().describe('Alias for `prompt_helper`. Accepted because every tool here REPORTS this field as `description`, so callers round-trip that name back in; without the alias zod stripped it and the notes were silently lost. Ignored when `prompt_helper` is also given.'),
       images: z.array(z.string()).optional().describe('Array of image sources (URLs or absolute local paths). Max 4. All of them can reach the model on later gens — same subject, same vibe only; no extra heroes on character DNAs, no main characters on environment DNAs.'),
       video: z.string().optional().describe('Optional video source (URL or absolute local path)'),
       audio: z.string().optional().describe('Optional audio source (URL or absolute local path) — the character\'s voice, 5-30s of clean speech. Stored on the DNA and used two ways: (1) as REFERENCE AUDIO in video generation — attaching this DNA to an image-to-video generation on a model with audio slots (Seedance 2.x, Wan 3.0) auto-attaches the clip and tells the model it is that character\'s voice; (2) as the source for a real speaking voice, but ONLY when you ask for one — see `voice_source`.'),
@@ -35,7 +36,8 @@ function registerVisualDnaTools(server, client, options = {}) {
       assigned_voice_id: z.string().optional().describe('Voice to attach when voice_source="assign" — a `custom_<id>` from the user\'s clones or a voice_id from `list_voices`.'),
       character_sheet_url: z.string().optional().describe('URL of a reference sheet (from `generate_character_sheet`, any sheet_type) to set as the DNA\'s primary reference. Works for ALL DNA types — character turnaround, product detail sheet, location sheet, or style board — and is the single biggest consistency booster. Omit only when the user declines.')
     },
-    async ({ name, dna_type, prompt_helper, images, video, audio, voice_source, assigned_voice_id, character_sheet_url }) => {
+    async ({ name, dna_type, prompt_helper, description, images, video, audio, voice_source, assigned_voice_id, character_sheet_url }) => {
+      const helper = prompt_helper !== undefined ? prompt_helper : description;
       if (!name || !name.trim()) {
         throw new Error('name is required');
       }
@@ -58,7 +60,7 @@ function registerVisualDnaTools(server, client, options = {}) {
       const form = new FormData();
       form.append('name', name);
       if (dna_type) form.append('dnaType', dna_type);
-      if (prompt_helper) form.append('promptHelper', prompt_helper);
+      if (helper) form.append('promptHelper', helper);
       if (character_sheet_url) form.append('characterSheetUrl', character_sheet_url);
       // Omitted stays omitted: the server infers 'clone' from a present audio clip, which is the
       // long-standing behaviour older installs depend on. Only an explicit choice is forwarded.
@@ -193,6 +195,7 @@ function registerVisualDnaTools(server, client, options = {}) {
       name: z.string().optional().describe('New name. Same no-space single-token rule as create_visual_dna — @Name binding stops at the first space.'),
       dna_type: z.string().optional().describe('Type: "character", "style", "product", "scene", "environment". Changing type re-analyzes the profile.'),
       prompt_helper: z.string().optional().describe('New description / intent notes. Replaces the old ones and re-synthesizes the DNA analysis when the text actually changes. Pass "" to clear.'),
+      description: z.string().optional().describe('Alias for `prompt_helper`. Accepted because every tool here REPORTS this field as `description`, so callers round-trip that name back in; without the alias zod stripped it and the edit silently did nothing. Ignored when `prompt_helper` is also given.'),
       images: z.array(z.string()).optional().describe('Full replacement still set (URLs or absolute local paths). Max 4. Omit to keep current stills. Same purity rules as create: one identity, one vibe.'),
       video: z.string().optional().describe('Replacement video source (URL or absolute local path).'),
       audio: z.string().optional().describe('Replacement audio source (URL or absolute local path).'),
@@ -208,14 +211,15 @@ function registerVisualDnaTools(server, client, options = {}) {
       specific_age: z.number().optional().describe('Character attribute (character DNAs).')
     },
     async ({
-      visual_dna_id, name, dna_type, prompt_helper, images, video, audio,
+      visual_dna_id, name, dna_type, prompt_helper, description, images, video, audio,
       character_sheet_url, remove_character_sheet,
       gender, ethnicity, body_type, hair_color, eye_color, skin_tone, age_range, specific_age
     }) => {
+      const helper = prompt_helper !== undefined ? prompt_helper : description;
       const imageList = Array.isArray(images) ? images.filter(Boolean) : [];
       if (imageList.length > 4) throw new Error('Maximum 4 images allowed');
       const hasMedia = imageList.length > 0 || !!video || !!audio;
-      const hasMeta = name !== undefined || dna_type !== undefined || prompt_helper !== undefined
+      const hasMeta = name !== undefined || dna_type !== undefined || helper !== undefined
         || character_sheet_url !== undefined || remove_character_sheet !== undefined
         || gender !== undefined || ethnicity !== undefined || body_type !== undefined
         || hair_color !== undefined || eye_color !== undefined || skin_tone !== undefined
@@ -240,7 +244,7 @@ function registerVisualDnaTools(server, client, options = {}) {
         const body = { ...attrs };
         if (name !== undefined) body.name = name;
         if (dna_type !== undefined) body.dna_type = dna_type;
-        if (prompt_helper !== undefined) body.prompt_helper = prompt_helper;
+        if (helper !== undefined) body.prompt_helper = helper;
         if (character_sheet_url !== undefined) body.character_sheet_url = character_sheet_url;
         if (remove_character_sheet !== undefined) body.remove_character_sheet = remove_character_sheet;
         const result = await client.put(path, body);
@@ -264,7 +268,7 @@ function registerVisualDnaTools(server, client, options = {}) {
       const form = new FormData();
       if (name !== undefined) form.append('name', name);
       if (dna_type) form.append('dnaType', dna_type);
-      if (prompt_helper !== undefined) form.append('promptHelper', prompt_helper);
+      if (helper !== undefined) form.append('promptHelper', helper);
       if (character_sheet_url) form.append('characterSheetUrl', character_sheet_url);
       if (remove_character_sheet !== undefined) {
         form.append('removeCharacterSheet', remove_character_sheet ? 'true' : 'false');