@kolbo/mcp 1.87.2 → 1.87.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.87.2",
+  "version": "1.87.4",
   "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@b38e38c, the single source of truth.
+This tree is mirrored from kolbo-code@f666a9c, the single source of truth.
 Canonical source: packages/opencode/skills/kolbo/
 Distribution: .github/workflows/sync-skill-to-plugin.yml
 

package/skill/references/models/seedance.md

@@ -15,7 +15,7 @@ Load this file when the user wants a **Seedance 2 / Seedance 2.0** (ByteDance) v
 
 - **NO MUSIC BY DEFAULT (HARD):** Unless the user explicitly asks for music, every final Seedance prompt—including every Elements/reference-driven prompt—must explicitly say `No music. No musical score.` Keep requested dialogue, synchronized production sound, ambience, and SFX; "no music" does not mean "no audio." If the user explicitly requests music, describe that music instead and omit the no-music lock. Never invent background music from cinematic tone alone.
 - **NO FAMOUS NAMES OR IP IN PROMPTS (HARD):** Never put celebrity/public-figure names, real directors or artists, copyrighted character/franchise/IP names, famous campaign names or slogans, or famous studio/company names into a final Seedance or Elements prompt. Translate user-supplied references into concrete visual traits—medium, shape language, palette, lighting, texture, camera behavior, pacing, and mood—without repeating the famous name. Preserve exact user-owned Visual DNA and asset tags.
-- **Visual DNA names are immutable anchors:** when `visual_dna_ids` is passed, every DNA MUST appear in the prompt as the exact literal `@DNA_name` (CAST + every shot it is in). Never "Zohar's", "the left man", "the man on the LEFT", a nickname, or a Visual DNA anchors paragraph without `@tags`.
+- **Visual DNA names are immutable anchors:** when `visual_dna_ids` is passed, every DNA MUST appear in the prompt as the exact literal `@DNA_name` (CAST + every shot it is in). Never "Zohar's", "the left man", "the man on the LEFT", a nickname, or a Visual DNA anchors paragraph without `@tags`. English-only control-language and dialogue rules NEVER apply to asset identifiers: a stored Hebrew name such as `אביב` must remain `@אביב` literally in CAST and every applicable shot; never strip, translate, transliterate, or ASCII-normalize it.
 - **Rewrites never thin out or rename anchors.** "`@X anchors Odysseus`" is NOT a reference line, and `Odysseus` must never replace `@X` later. Every referenced asset keeps its exact literal tag plus a full role line on every rewrite. Re-use the exact DNA tag in every shot it participates in. A compile that dropped `@gal_suit` / `@yonatan` / `#Board` is a failed turn.
 - **DURATION + SHOT STRUCTURE (HARD — same as help widget):** every text-to-video / Elements prompt MUST open AND close with total duration, shot count, and aspect. Omit only for video-edit tasks (source duration is locked). Required first lines:
   1. `N connected cinematic shots, Xs total, AR, Multishot ON`

package/skill/references/models/seedance25.md

@@ -11,7 +11,7 @@ Load this file when the user wants a **Seedance 2.5** video (they said "2.5" / "
 
 **Audio:** Seedance 2.5 emits real synced audio. `list_models` shows `sound_generation_type: none` only because there is no in-app toggle (`sound_baked_in: true`) — it does NOT mean the model is silent, and it is never a reason to reach for TTS. Quoted dialogue is PERFORMED (synced voices, lip movement, room tone) alongside the SFX named in AUDIO, so scene dialogue never goes through `generate_speech` or `generate_lipsync`; write the lines in quotes inside their shot beats.
 
-**Dialogue language: English.** Other languages are not reliably performed, and Hebrew does not work — it returns accented gibberish or English-shaped mouth movement. Never offer a user "Hebrew dialogue directly". See `models/seedance.md` for the three honest alternatives.
+**Dialogue language: English.** Other languages are not reliably performed, and Hebrew does not work — it returns accented gibberish or English-shaped mouth movement. Never offer a user "Hebrew dialogue directly". This restriction applies to rendered dialogue/prose only, never to binding identifiers: preserve an exact stored Hebrew Visual DNA or moodboard tag such as `@אביב` / `#ישראל` literally. See `models/seedance.md` for the three honest alternatives.
 
 **Draft at 480p.** 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. Block the film at 480p, get the user's sign-off on staging, performance and timing, then re-run only the approved cut at delivery resolution.
 

package/src/apps/widgets/generation.js

@@ -808,10 +808,15 @@ function renderResult(sc) {
   // voice that actually ran, so the finished card must not keep the guess.
   renderChips(sc);
   setPhaseChip('', false);
-  if (sc.kind === 'status' && Array.isArray(sc.items)) return renderStatusGrid(sc);
   if (sc.batch && sc.scenes && sc.scenes.length) return renderBatchGrid(sc);
   if (sc.kind === 'scenes' && sc.scenes && sc.scenes.length) return renderScenes(sc);
   var urls = preferKolbo(sc.urls || []);
+  // Key the per-item grid on items[], not on kind === 'status': a host bridge
+  // (Kolbo Code's shaped()) rewrites kind from the TOOL name before the payload
+  // reaches this iframe, so a finished prompts[] batch arrived as kind:'image'
+  // with eight completed items and no top-level urls — and painted
+  // "No output received / Failed" over generations that had completed and billed.
+  if (Array.isArray(sc.items) && sc.items.length && (sc.kind === 'status' || !urls.length)) return renderStatusGrid(sc);
   var kind = displayKind(Object.assign({}, sc, { urls: urls }));
   if (!urls.length) return renderError('No output received');
   if (kind === 'image') renderImages(sc, urls);

package/src/tools/generate.js

@@ -99,9 +99,12 @@ async function pollBatch(client, batch, { interval, timeout }, toolName) {
     generations,
     failed_submissions: batch.failed.length ? batch.failed : undefined
   }, null, 2);
+  // Name the model that actually ran — every id in one batch ran the same one.
+  const modelsRan = [...new Set(polls.filter((p) => !p.timedOut).map((p) => p.result.result && p.result.result.model).filter(Boolean))];
   return uiCompleted({
     tool: toolName, kind: 'status', client,
-    model: 'Generations', gen: { generation_id: batch.ids[0], session_id: batch.ok[0].gen.session_id },
+    model: modelsRan.length === 1 ? modelsRan[0] : 'Generations',
+    gen: { generation_id: batch.ids[0], session_id: batch.ok[0].gen.session_id },
     settings: {},
     items: generations.map(g => ({
       id: g.generation_id,