@kolbo/mcp 1.93.1 → 1.93.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.93.1",
+  "version": "1.93.3",
   "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@b066208, the single source of truth.
+This tree is mirrored from kolbo-code@be5ba3e, the single source of truth.
 Canonical source: packages/opencode/skills/kolbo/
 Distribution: .github/workflows/sync-skill-to-plugin.yml
 

package/skill/SKILL.md

@@ -104,7 +104,7 @@ For multi-scene / batch work this pairs with `generate_creative_director` (see b
 | Inspect or change a connected **Blender** scene, render, import Kolbo media, or run approved Blender Python | `references/workflows/blender.md` |
 | Inspect or edit an open **Premiere Pro / After Effects** project — timeline, Kolbo media, sequences, captions, After Effects edits and titles | `references/workflows/adobe.md` |
 | Build **motion graphics** in After Effects — shape layers, animated text, effects, expressions, logo reveals | `references/workflows/after-effects-motion.md` |
-| Edit, grade or render Kolbo media in **DaVinci Resolve** (Studio 21.1+, Blackmagic's MCP) | `references/workflows/davinci-resolve.md` |
+| Edit, title, grade or render Kolbo media in **DaVinci Resolve** (Studio) — Kolbo Resolve plugin (`resolve_*`, any agent) or Blackmagic's MCP (local) | `references/workflows/davinci-resolve.md` |
 | Create or edit a saved **Video Editor** timeline, clips, trims, speed or captions | `references/workflows/video-editor.md` |
 
 Each `references/models/*.md` mirrors the matching skill prompt in `kolbo-api/src/config/systemPrompt.js` — same battle-tuned rules that power Kolbo's web-app help widget. Keep parity (see `packages/opencode/CLAUDE.md` "MCP & Skill Sync Rule").
@@ -163,6 +163,7 @@ Font tools (when exposed by the installed MCP): `list_fonts`, `get_font`, `uploa
 | `publish_html_artifact` | Publish HTML / SVG / Mermaid to `sites.kolbo.ai`. Server dedupes by content hash. Strict CSP. |
 | `blender_list_sessions` / `blender_get_scene` / `blender_search_docs` / `blender_capture_viewport` / `blender_apply_operations` / `blender_import_media` / `blender_render` / `blender_undo` / `blender_file_operation` / `blender_execute_python` / `blender_get_command_status` | Connected Blender control through the Kolbo extension. Every tool crosses into an external desktop host; read `workflows/blender.md` before the first call. |
 | `adobe_list_sessions` / `adobe_get_project` / `adobe_get_timeline` / `adobe_import_media` / `adobe_place_on_timeline` / `adobe_create_sequence` / `adobe_import_captions` / `adobe_edit_composition` / `adobe_run_script` / `adobe_capture_frame` / `adobe_get_command_status` | Connected Premiere Pro / After Effects control through the Kolbo panel. Every change needs the editor's approval in the panel; read `workflows/adobe.md` before the first call and `workflows/after-effects-motion.md` before any motion-graphics script. |
+| `resolve_list_sessions` / `resolve_get_project` / `resolve_get_timeline` / `resolve_import_media` / `resolve_edit_timeline` / `resolve_run_script` / `resolve_capture_frame` / `resolve_get_command_status` | Connected DaVinci Resolve Studio control through the Kolbo Resolve plugin: timeline edits, Fusion titles, scripts and frame checks. Every change needs the editor's approval in the plugin; read `workflows/davinci-resolve.md` before the first call. |
 
 ## ⚠️ Edit in place — never delete+recreate (HARD RULE — always on)
 
@@ -220,11 +221,25 @@ A URL from `generate_*`, `list_media`, `get_media`, or a prior `upload_media` is
 - `upload_media` is only for a **local disk path** or an **external** (non-Kolbo) URL — `files`/`source_images`/`image_url` reject unknown hosts with `400`; a Kolbo URL passes through as-is.
 - Same rule after compaction: pull the URL from `.kolbo/production.md` and reuse it. Never download-then-reupload.
 
-## ⚠️ Assets Before Shots (HARD RULE)
+## ⚠️ Route video per use case (decide — do not cargo-cult)
 
-For any film / ad / scene / episode / campaign the order is **Map → Create → Confirm → Shoot** (the directing guide — load `references/workflows/production-planning.md` + `filmmaking.md` before creating anything). Crack the concept first. Then every character, location, and prop becomes a Visual DNA **from a sheet** (`list_presets` search → `generate_image` with that `preset_id` → `create_visual_dna`). Do **not** register a DNA from a single portrait and skip the sheet. Publish the session plan (`Cast` / `Locations` / `Scene NN — slug`). Get a GATE lock on the asset set. **Only then** video. A shot against an unapproved cast is waste.
+Pick the cheapest route that actually controls what the brief needs. Do not invent a pipeline.
 
-Scene dialogue is **never** `generate_speech` or `generate_lipsync`. Seedance 2 / 2.5 performs quoted lines written into the shot beat itself — English only. Full flow: `references/workflows/production-planning.md`.
+**1. Recurring identity (cast / product / location must match across shots)**  
+Map → Visual DNA sheets → Confirm → `generate_elements` (or DNA-locked Multishot). Asset sheets earn their cost here.
+
+**2. Composition must be locked before motion** (deliberate framing, Pixar-like kids beats, specific staging, hero product plate, user-approved look)  
+Generate the needed keyframe still(s) first, then animate with `generate_video_from_image` / first-last / Elements **using those images as real inputs**. Stills without attaching them to the video call are waste.
+
+**3. Pure text-to-video / Multishot Locked Intro — only when keyframes are 100% unnecessary**  
+Use for generic b-roll, ambient motion, simple stock-like scenes, or any brief where the video model inventing composition is fine and stills would not improve control. If you are not sure keyframes add nothing, prefer route 2.
+
+**Anti-patterns (HARD)**  
+- Do not generate N stills and then run a Multishot T2V that never attaches them.  
+- Do not default every "make a video" to keyframes (generic b-roll does not need them).  
+- Do not default every narration-only brief to T2V when the user asked for tightly designed cute/controlled shots — those often need keyframes.
+
+Scene dialogue is **never** `generate_speech` or `generate_lipsync` on a Seedance shoot. Seedance 2 / 2.5 perform quoted lines written into the shot beat — English or Latin transliteration of Hebrew (`"shalom"`), never Hebrew script. For native Hebrew speech, prefer Gemini Omni Flash 1.1 or Gemini Omni 1. Full flow: `references/workflows/production-planning.md`.
 
 ## ⚠️ Load the matching skill BEFORE generating (HARD RULE)
 
@@ -451,7 +466,7 @@ 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.
-Default video: Seedance 2.5. Kling specializes in controlled single-image and first/last-frame shots. Wan 3.0 specializes in motion graphics and Hebrew/dialogue work. MiniMax H3 offers higher resolution; H3 Max favors speed at lower resolution. Gemini Omni Flash is a secondary Hebrew option (up to 10 seconds); Grok Imagine 1.5 and Seedance 2.0 are alternatives. P Video/Draft for cheap fast tests. Use base, edit or extend variants only with their required inputs.
+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/seedance.md

@@ -13,7 +13,7 @@ Load this file when the user wants a **Seedance 2 / Seedance 2.0** (ByteDance) v
 
 ## Creative direction takes precedence
 
-The current user brief overrides template defaults and illustrative examples. Keep the two-layer organization, but include only relevant locks. State concrete camera trajectory and visible action prominently; optics numbers, equipment names, repetition and word counts are not guarantees of fidelity. Preserve a continuous-shot exception even when other scenes are multishot. For one shot use `Single continuous shot`, `Total: Xs / 1 shot / AR`, one SHOT heading and `multi_shots: false`; for multiple shots use `Multishot ON` and matching counts. AR comes from the brief, never a copied example. Keep dialogue in the user's requested language or phonetic spelling; test pronunciation rather than claiming guaranteed support or impossibility. Narration reserved for post does not belong in the generation prompt.
+The current user brief overrides template defaults and illustrative examples. Keep the two-layer organization, but include only relevant locks. State concrete camera trajectory and visible action prominently; optics numbers, equipment names, repetition and word counts are not guarantees of fidelity. Preserve a continuous-shot exception even when other scenes are multishot. For one shot use `Single continuous shot`, `Total: Xs / 1 shot / AR`, one SHOT heading and `multi_shots: false`; for multiple shots use `Multishot ON` and matching counts. AR comes from the brief, never a copied example. Seedance does not speak Hebrew — use Latin transliteration in quotes or route native Hebrew to Gemini Omni. Narration reserved for post does not belong in the generation prompt.
 
 ## Universal Rules (apply to EVERY Seedance / Elements prompt)
 
@@ -142,7 +142,7 @@ Appearance locks WHO. Persona locks HOW THEY BEHAVE — without it Seedance rend
 ## Dialogue & expression
 
 - **Dialogue is PERFORMED by the model, never by a TTS tool.** Quoted lines in the prompt come back as synced speech with lip movement and room tone, together with the SFX you name in AUDIO. Scene dialogue therefore never routes through `generate_speech` or `generate_lipsync` — write the line in quotes inside its shot beat and let Seedance act it.
-- **Preserve requested dialogue and its language.** If the user requests Hebrew in Latin letters, preserve that phonetic text as dialogue, not an English translation. Native pronunciation and lip-sync require actual output inspection. Do not promise success or claim the language is impossible without current evidence. Offer a separately authorized dubbing pass only when needed; keep narration reserved for post out of the prompt.
+- **Hebrew (HARD):** Seedance 2 / 2.5 do **not** speak Hebrew. Never put Hebrew-script dialogue in the prompt. Use Latin transliteration in quotes (`שלום` → `"shalom"`), or recommend Gemini Omni Flash 1.1 / Gemini Omni 1 for native Hebrew. Do not promise Seedance Hebrew success. Attached-audio lip-sync on 2.5 is unreliable unless audio length matches the clip and the prompt has no Hebrew script. Keep narration reserved for post out of the prompt.
 - `list_models` reports `sound_generation_type: "none"` for Seedance 2 / 2.5 because there is no in-app sound toggle (`sound_baked_in: true`). That field does NOT mean the model is silent. Do not read it as a reason to add TTS.
 - For silent tension, deliver it as expression, not speech: `He does not speak. His expression clearly says: "…"`.
 

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 follows the user.** Preserve requested Hebrew or Hebrew-in-Latin transliteration; do not translate it into English or change the spoken content. Pronunciation and lip-sync must be inspected in the generated output, not guaranteed from the prompt. Keep post-production VO out of the generation prompt. Asset tags always retain their exact stored spelling, including `@אביב` / `#ישראל` literally.
+**Hebrew (HARD):** Seedance 2.5 does **not** speak Hebrew. Never put Hebrew-script dialogue in the prompt. Use Latin transliteration in quotes per speaker (`שלום` → `"shalom"`), or route native Hebrew speech to Gemini Omni Flash 1.1 / Gemini Omni 1. Attached-audio lip-sync sometimes works when audio length matches the clip exactly and the prompt has no Hebrew script; Kolbo accepts native audio uploads (no black-video workaround). Asset tags always retain their exact stored spelling, including `@אביב` / `#ישראל` literally. Keep post-production VO out of the generation prompt.
 
 **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.
 

package/skill/references/workflows/davinci-resolve.md

@@ -1,19 +1,67 @@
 # DaVinci Resolve Workflow
 
-Use this when the user wants Kolbo media edited, graded or rendered in DaVinci Resolve. Kolbo generates and hosts the media; **Blackmagic's own DaVinci Resolve MCP server** drives Resolve. The agent uses both connectors side by side.
+Use this when the user wants Kolbo media edited, cut, titled, graded or rendered in DaVinci Resolve. There are two ways to reach Resolve; pick by what is connected.
 
-Everything below was run against DaVinci Resolve Studio 21.1.0.17 through Blackmagic's server.
+| Path | Works from | Use it for |
+|---|---|---|
+| **Kolbo Resolve plugin** (`resolve_*` tools, this server) | Any agent, including ChatGPT and claude.ai | Reading the project, importing Kolbo media, building timeline edits, titles, frame checks - every change approved by the editor |
+| **Blackmagic's DaVinci Resolve MCP** (their own server) | Local agents only (Claude Desktop, Claude Code, Codex) | Deep scripting, colour, LUTs/DCTLs, rendering |
 
-## Requirements - check before promising anything
+Both need **DaVinci Resolve Studio**; the free edition has no plugins and no external scripting. If `resolve_list_sessions` returns a session, prefer the Kolbo plugin.
+
+## Kolbo Resolve plugin
+
+Everything in this section was run end to end through Kolbo MCP against DaVinci Resolve Studio 21.1.
+
+### Connect and target safely
+
+1. Call `resolve_list_sessions` before the first Resolve action.
+2. If no session is listed, ask the user to open **Workspace → Workflow Integrations → Kolbo AI** in Resolve Studio and sign in with the same Kolbo account as this connector. **AI agents** in the plugin header connects automatically; if its dot is not green, ask them to click it.
+3. One session: `session_id` may be omitted. Several: show each and ask. Keep the chosen `session_id` on every later call; re-list after Resolve or the plugin restarts.
+
+Every tool except `resolve_list_sessions` and `resolve_get_command_status` returns a command record. Poll `resolve_get_command_status` until `succeeded`, `failed`, `denied` or `canceled`. Reads run without approval; everything else waits for **Allow once / Allow for this session / Deny** in the plugin window. `awaiting_approval` is not a polling state: tell the user to approve in the Kolbo AI window (it may be behind Resolve), then check again. `denied` is final.
+
+### Tools
+
+| Goal | Tool |
+|---|---|
+| Project name, timelines, frame rate, resolution, playhead | `resolve_get_project` |
+| Clips on every track (position, start/end seconds), markers | `resolve_get_timeline` |
+| Kolbo media into the Media Pool only | `resolve_import_media` |
+| Build or change an edit | `resolve_edit_timeline` |
+| Anything else in Resolve's scripting API | `resolve_run_script` |
+| See the result | `resolve_capture_frame` → look at the returned `url` |
+
+### Timeline edits (`resolve_edit_timeline`)
+
+- Up to 100 operations run in order and stop at the first failure; earlier operations stay applied. Fix the failing one and continue - do not replay the batch.
+- Start new work with `timeline.create` so the user's existing timelines stay untouched. It uses the project's frame rate and resolution.
+- Times are seconds from the timeline start. `clip.append`: `record_seconds` = where it lands (default: end of that track), `trim_start_seconds` = seconds skipped at the head of the source, `duration_seconds` = length on the timeline (stills default to 5 s). media_type "video" keeps a clip's audio off the timeline; audio files always go to audio tracks. Missing tracks are added.
+- Clips are addressed by track plus position (1 = leftmost media clip on that track; transitions do not count) or exact clip name. Clip names are file names, and a file imported again gets a short prefix, so prefer positions. Positions change after inserts and deletes - re-read with `resolve_get_timeline` when unsure.
+- `clip.transition` needs handles: trim the head of the next shot (`trim_start_seconds` ≥ half the transition) or the transition will be refused.
+- `audio.fade` is for clips on audio tracks. `title.add` builds the title inside that clip's Fusion comp (`position` [0.5, 0.5] = centre, y grows upward) with a fade in and out; keep it inside title-safe (x and y between 0.1 and 0.9).
+- `clip.delete` is destructive; only delete what the user asked for.
+- The Kolbo AI window must stay open while you work; it can sit behind Resolve.
+
+### Scripts (`resolve_run_script`)
+
+- `code` is an **async JavaScript function body** with `resolve`, `project`, `timeline` and `log(...)` in scope. Every Resolve call returns a promise - `await` each one - and `return` a JSON-serialisable result.
+- The editor reads the exact code before approving. Give a plain `purpose`. Never touch files, the network or other projects unless the user asked for exactly that.
+
+## Blackmagic's DaVinci Resolve MCP
+
+Verified against DaVinci Resolve Studio 21.1.0.17.
+
+### Requirements - check before promising anything
 
 - **DaVinci Resolve Studio 21.1 or later.** The free edition has no MCP server and no external scripting.
-- A **local** agent: Claude Desktop, Claude Code or Codex on the same computer as Resolve. Browser ChatGPT and claude.ai can generate media with Kolbo but cannot reach Resolve.
+- A **local** agent: Claude Desktop, Claude Code or Codex on the same computer as Resolve. Browser ChatGPT and claude.ai cannot reach this server; use the Kolbo Resolve plugin from there.
 - Connect Resolve's server from **File → Setup AI Assistants** in Resolve, and set **Preferences → System → General → External scripting using** to **Local**.
 - Resolve must be running; the server's `launch_resolve` tool can start it.
 
-If the Resolve tools are missing from the conversation, say so and give these steps. Do not try to control Resolve any other way.
+If neither the Kolbo plugin session nor Blackmagic's tools are available, say so and give the setup steps for the path that fits the user. Do not try to control Resolve any other way.
 
-## Blackmagic's tools (not Kolbo's)
+### Blackmagic's tools (not Kolbo's)
 
 | Tool | Use |
 |---|---|
@@ -26,7 +74,7 @@ If the Resolve tools are missing from the conversation, say so and give these st
 
 Scripts get `resolve` and the current `project` pre-injected and return data by assigning `result`.
 
-## Workflow
+### Workflow
 
 1. **Generate or find media with Kolbo** (`generate_video`, `generate_music`, `list_media`, …) and wait for success.
 2. **Get the files onto disk.** In Claude Code or Codex, download the Kolbo URLs with the shell. In Claude Desktop, download inside `run_script_unsafe` with `urllib.request`. Only download Kolbo-hosted URLs.
@@ -35,7 +83,7 @@ Scripts get `resolve` and the current `project` pre-injected and return data by
 5. **Verify visually.** Set the playhead and call `project.ExportCurrentFrameAsStill(path)` at representative times, then look at the stills before reporting.
 6. Optionally render (`AddRenderJob` / `StartRendering`) and upload the result back to Kolbo with `upload_media` so it lands in the user's library.
 
-## Verified gotchas
+### Verified gotchas
 
 - **`MediaPool.ImportMedia` needs plain path strings.** The dict form in the 21.1 stubs (`[{"FilePath": ...}]`) returned `None`. On Windows, backslash paths worked.
 - **File import fails in `run_script`**; use `run_script_unsafe` for anything that touches files.
@@ -43,7 +91,7 @@ Scripts get `resolve` and the current `project` pre-injected and return data by
 - `AppendToTimeline` `startFrame` / `endFrame` are **source frames** at the clip's own frame rate (`GetClipProperty("FPS")`). `recordFrame` is a timeline frame; timelines start at `timeline.GetStartFrame()` (86400 = 01:00:00:00 at 24 fps).
 - New projects default to 24 fps and UHD output.
 
-## Recipe: cut, transition, music fade, title
+### Recipe: cut, transition, music fade, title
 
 ```python
 pm = resolve.GetProjectManager()
@@ -109,7 +157,7 @@ resolve.GetProjectManager().LoadProject("<original project name>")
 result = {"still": ok}
 ```
 
-## Completion proof
+### Completion proof
 
 - Look at exported stills at the title, the transition and the end before reporting.
 - Report which project and timeline you built, that the original project was saved and restored, and where any render landed.

package/skill/references/workflows/production-planning.md

@@ -9,10 +9,13 @@ starts here, **before** a single video credit is spent. Most users do not know
 this flow exists; they ask for a film and expect a film. Walk them through it
 rather than jumping to a prompt.
 
-Skip it only for a genuine one-off: a single clip, no recurring subject, nothing
-that has to match anything else.
+**Skip asset mapping** only when keyframes and DNA are **100% unnecessary**: generic b-roll,
+ambient motion, simple stock-like scenes where the video model inventing composition is fine.
+For tightly designed kids/educational beats, Pixar-like staging, or any brief where composition
+must be locked, generate keyframes (or DNA) first and attach them to the video call — do not
+invent stills and then run a Multishot T2V that ignores them.
 
-## The order is not negotiable
+## The order is not negotiable (when cast/product identity must lock)
 
 1. **Map** every element the script needs — including the **session plan** (names).
 2. **Create** each one as an asset (Visual DNA), grouped into the planned sessions.

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 (other languages, Hebrew included, do not perform reliably). 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 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.',
     {
       prompt: z.string().optional().describe('Text description of the video to generate. Required unless `prompts` is provided.'),
       prompts: promptsField('videos'),
@@ -1427,7 +1427,7 @@ function registerGenerateTools(server, client, options = {}) {
   // ─── generate_elements ─────────────────────────────────────
   server.tool(
     'generate_elements',
-    'Generate a video from reference elements (images, videos, and/or audio) + a text prompt. Use when the user wants to animate specific uploaded/referenced assets — e.g. "animate this product", "put these 3 characters into a scene". PRIMARY ROUTE FOR A DNA-ANCHORED MULTI-SHOT FILM: one call can carry the whole sequence — seedance-2-5 takes 4-30s, up to 30 shots and 20 Visual DNAs in a SINGLE generation (seedance-2: 4-15s, 9 DNAs) — instead of a stack of separate clips. DIALOGUE IS PERFORMED NATIVELY: quoted dialogue in the prompt comes back as synced voices with lip movement, room tone and the SFX named in the AUDIO block — never route scene dialogue to generate_speech or generate_lipsync. Write dialogue in ENGLISH; other languages (Hebrew included) do not perform reliably. COST: resolution is a multiplier. When list_models publishes `video_input_credit` and this call carries videos, charge that rate against nominal input seconds + nominal output seconds; MP4 padding within 0.15s of an integer snaps to that integer and larger fractions round up. Otherwise use the normal output-second rate. PROMPT CONTRACT (Seedance / Elements): Locked Intro only — Total line, then [GLOBAL LOOK] / [CAST] / [LOCATION] / SHOT N. Do NOT write SCENE CONTEXT / OPTICS / ACTION department packs. Every Visual DNA in visual_dna_ids MUST also appear in the prompt as @ExactDNAName (e.g. "@Zohar walks…") — never "Zohar\'s" or "the man on the left" as a substitute. IMPORTANT: different models accept different numbers and durations of inputs — call list_models type="elements" and read elements_max_images / elements_max_videos / elements_max_audio plus min_video_duration / max_video_duration before generating. For text-only → video use generate_video instead. For animating a single still image use generate_video_from_image. Returns the final video URL when complete.',
+    'Generate a video from reference elements (images, videos, and/or audio) + a text prompt. Use when the user wants to animate specific uploaded/referenced assets — e.g. "animate this product", "put these 3 characters into a scene". PRIMARY ROUTE FOR A DNA-ANCHORED MULTI-SHOT FILM: one call can carry the whole sequence — seedance-2-5 takes 4-30s, up to 30 shots and 20 Visual DNAs in a SINGLE generation (seedance-2: 4-15s, 9 DNAs) — instead of a stack of separate clips. DIALOGUE IS PERFORMED NATIVELY: quoted dialogue in the prompt comes back as synced voices with lip movement, room tone and the SFX named in the AUDIO block — never route scene dialogue to generate_speech or generate_lipsync. Write dialogue in ENGLISH or Latin transliteration of Hebrew ("shalom"), never Hebrew script — Seedance does not speak Hebrew; prefer Gemini Omni Flash 1.1 or Gemini Omni 1 for native Hebrew. COST: resolution is a multiplier. When list_models publishes `video_input_credit` and this call carries videos, charge that rate against nominal input seconds + nominal output seconds; MP4 padding within 0.15s of an integer snaps to that integer and larger fractions round up. Otherwise use the normal output-second rate. PROMPT CONTRACT (Seedance / Elements): Locked Intro only — Total line, then [GLOBAL LOOK] / [CAST] / [LOCATION] / SHOT N. Do NOT write SCENE CONTEXT / OPTICS / ACTION department packs. Every Visual DNA in visual_dna_ids MUST also appear in the prompt as @ExactDNAName (e.g. "@Zohar walks…") — never "Zohar\'s" or "the man on the left" as a substitute. IMPORTANT: different models accept different numbers and durations of inputs — call list_models type="elements" and read elements_max_images / elements_max_videos / elements_max_audio plus min_video_duration / max_video_duration before generating. For text-only → video use generate_video instead. For animating a single still image use generate_video_from_image. Returns the final video URL when complete.',
     {
       prompt: z.string().describe('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).'),