@kolbo/kolbo-code-linux-arm64-musl 2.4.0 → 2.4.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/kolbo-code-linux-arm64-musl",
-  "version": "2.4.0",
+  "version": "2.4.1",
   "os": [
     "linux"
   ],

package/skills/kolbo/SKILL.md

@@ -1,5 +1,5 @@
 ---
-version: 0.5.0
+version: 0.5.1
 name: kolbo
 description: |
   Generate, edit, or analyze creative media via the Kolbo AI MCP server:
@@ -35,7 +35,7 @@ Once per conversation, before any other Kolbo tool call:
 
 1. **Run `check_credits`.** If it fails with "Session expired" / "Not authenticated", ask the user to run `kolbo auth login` (or their branded CLI command like `sapir auth login`) and reload the editor.
 2. **If `list_models` returns empty**, MCP isn't wired — same fix.
-3. Remember the credit balance for the session; don't re-check on every turn.
+3. Use the balance ONLY for the low-balance check at this moment. **Never quote a "credits remaining" number later in the session** — coding/chat usage also deducts credits, so any remembered or computed balance is stale. Report only what each generation cost (`credits_used`); if the user asks what's left, run `check_credits` fresh right then.
 
 If the user is on a whitelabel build (`sapir`, etc.), they must use their branded command — not `kolbo`. See `references/workflows/troubleshooting.md`.
 
@@ -113,6 +113,7 @@ Each `references/models/*.md` mirrors the matching skill prompt in `kolbo-api/sr
 | `upload_media` / `list_media` / `get_media` / `get_media_stats` / `favorite_media` / `unfavorite_media` / `delete_media` / `restore_media` / `permanently_delete_media` / `move_media` / `bulk_*_media` / `*_media_folder` | Media library — see `workflows/media-library.md` |
 | `create_visual_dna` / `list_visual_dnas` / `get_visual_dna` / `delete_visual_dna` | Visual DNA — see `workflows/visual-dna.md` |
 | `list_moodboards` / `get_moodboard` / `list_presets` | Style overlays |
+| `search_stock_media` / `get_stock_sources` / `get_stock_categories` / `get_stock_collections` / `get_stock_asset` / `analyze_script_for_stock` / `import_stock_asset` | Stock library (free, no credits) — EXISTING photos / videos / 3D / SFX / music. For stock **music** use `search_stock_media` with `mediaType: "music"` (semantic vibe query, e.g. "uplifting corporate background") → `get_stock_asset` for downloads. The older `*_music_library` tools are deprecated adapters over this — prefer the stock tools. |
 | `chat_send_message` / `chat_list_conversations` / `chat_get_messages` | Kolbo chat with optional `media_urls` (up to 10 per call) |
 | `app_builder_*` (9 tools) | Full React app generation — see `workflows/app-builder.md` |
 | `publish_html_artifact` | Publish HTML / SVG / Mermaid to `sites.kolbo.ai`. Server dedupes by content hash. Strict CSP. |
@@ -149,12 +150,13 @@ A user-named tool — in any language — overrides every other rule. Recognized
 1. **Check credits** ONCE per conversation (Step 0). Skip if already checked.
 2. **Discover models** with `list_models` using a `type` filter — but **skip when the user names a specific model**.
 3. **Pick the model**:
-   - User named one → use it.
+   - User named one → use it. Model identifiers resolve leniently — shorthand like `"z-image"` or `"nano banana 2"` auto-resolves to the exact identifier, so don't over-engineer exact-id lookups (`list_models` is still authoritative for constraints, caps, and pricing).
    - Auto-select → only from "Auto-selectable" section (models with a `summary`). Cheapest fit. Prefer `[RECOMMENDED]` when cost is similar.
    - Never auto-select from "Named-only" section.
 4. **Validate inputs** against model caps — see `references/workflows/cost-and-validation.md`.
-5. **How calls work**: each tool blocks until generation is fully complete. Images: seconds. Video: minutes. Multiple tool calls in one response run concurrently. If a call times out, use `get_generation_status` with the returned generation ID.
-6. **Share the URL** after success. Never fabricate URLs.
+5. **How calls work**: each tool blocks until generation is fully complete. Images: seconds. Video: minutes. Multiple tool calls in one response run concurrently. On hosts with live widgets the tool instead returns `submitted` instantly — the card updates on its own; you only need `get_generation_status` when a follow-up step needs the output URLs.
+6. **Checking status — NEVER poll in a loop**: `get_generation_status` takes `wait=true` (blocks server-side until done, ~3 min) and `generation_ids` (check MANY generations in ONE call — returns `all_done` + which are still running). One `wait=true` call replaces any polling loop. If it comes back with some still processing, call it ONCE more with `wait=true` and the remaining ids.
+7. **Share the URL** after success. Never fabricate URLs.
 
 Model types for `list_models`: `text_to_img`, `image_editing`, `text_to_video`, `img_to_video`, `draw_to_video`, `video_to_video`, `elements`, `firstlastgenerations`, `lipsync-image`, `lipsync-video`, `music_gen`, `text_to_speech`, `text_to_sound`, `stt`, `text`, `3d_text_to_model`, `3d_image_to_model`, `3d_multi_image_to_model`, `3d_world`.
 
@@ -166,11 +168,13 @@ Full tables + formulas in `references/workflows/cost-and-validation.md`. Quick r
 - **Otherwise confirm** via the labeled-question card: the parameters + the credit cost, suggest a cheaper alternative if one fits, wait for the user's pick. Never fire on defaults the user didn't choose.
 - **Batch totalling 100+ credits**: run `check_credits` first.
 - **Quote real cost**: after firing, log `credits_used` (from the tool result) to `.kolbo/production.md` — never `base × count`.
+- **Never state "credits remaining" from arithmetic** (opening balance − generation costs). Coding/chat usage deducts credits too, so the math is always wrong. Report cost only; if the user asks for their balance, call `check_credits` fresh at that moment.
 
 ## Rate Limiting & Batch Generation
 
 - `generate_image`: 30/min. All other generation tools: 10/min per type. 300/min global. `upload_media`: 300/min, no credit cost.
-- **⚠️ NEVER re-fire a generation you already called.** Aborted / timed-out calls still process server-side. Run `get_generation_status` before retrying.
+- **⚠️ NEVER re-fire a generation you already called.** Aborted / timed-out calls still process server-side. Run `get_generation_status` (with `wait=true`) before retrying.
+- **Tracking a batch**: check ALL in-flight ids in ONE `get_generation_status` call with `generation_ids` + `wait=true`. Read `all_done` / `still_processing` from the response — do not check ids one by one, and never re-call without `wait`.
 - **Batch ≤10 items**: output ALL tool calls in one response — they run concurrently.
 - **Bulk >10 items**: real-world ceilings — `generate_image` 8–10 in-flight, image-edit 5–8, video tools 3–5, `generate_video_from_video` 3, music/speech/sound 5–8. Fire one batch → wait → fire next. Persist every `generation_id` in `.kolbo/production.md`.
 - **`upload_media` external URLs first.** `files`/`source_images`/`image_url` only accept Kolbo-hosted URLs reliably; external URLs cause `400`.
@@ -203,6 +207,8 @@ Existing video → modify → **single `generate_video_from_video` call** with s
 
 **Use a TRUE video-to-video model.** Image-to-video models reject with `WRONG_MODEL_TYPE`. Valid: `wan/2-7-videoedit`, `happyhorse/video-edit`, `kling-video/o3-video-to-video`, or any model whose DB `type` includes `video_to_video` (use `list_models({ type: "video_to_video" })`).
 
+**Motion-control / animate-move models invert the inputs**: `reference_images[0]` = the CHARACTER IMAGE to animate, `source_video` = the driving/reference video whose motion is transferred. Omitting the character image returns a `MOTION_CONTROL_INPUTS` error.
+
 **Do NOT** decompose into frames. **Do NOT** re-fire if the first call returned URLs.
 
 ## ⚠️ Character-Driven Video — Frames First, Then Animate (CRITICAL)
@@ -221,7 +227,7 @@ A generation can fail three ways. Treat ALL as failure:
 
 1. **Tool returns `error`** — explicit. Surface, suggest retry, log `generation_id`.
 2. **Tool returns `completed` but `urls` is empty** — silent failure (NSFW filter, model OOM, upstream 5xx). Tell user "completed without an output — retrying" and re-fire ONCE. Do NOT log to `.kolbo/production.md`. Do NOT claim it worked.
-3. **Tool hangs / never returns** — MCP poll timed out. Call `get_generation_status(generation_id)` IMMEDIATELY. The server might be done.
+3. **Tool hangs / never returns** — MCP poll timed out. Call `get_generation_status(generation_id, wait=true)` IMMEDIATELY. The server might be done.
 
 **Always:**
 - Don't celebrate before reading the result. Verify `urls` is non-empty.

package/skills/kolbo/VERSION

@@ -1 +1 @@
-0.5.0
+0.5.1

package/skills/kolbo/references/models/music.md

@@ -8,9 +8,12 @@ Load this file when the user wants AI-generated **music** — full songs, lyrics
 
 **Kolbo MCP routing:** call `generate_music`. Suno is a model option — use `list_models({ type: "music_gen" })` to see versions. Pass `instrumental` and `duration` as separate params; pass the Style/Description text as `style` and the Lyrics as `lyrics`.
 
+**Wants an EXISTING track, not a new song?** ("background music", "stock music", "royalty-free track") → don't generate. Use `search_stock_media` with `mediaType: "music"` (semantic vibe query — "tense cinematic pulse", "uplifting corporate background") → `get_stock_asset` for download URLs. Free, no credits. The older `*_music_library` tools are deprecated adapters over the stock library — prefer the stock tools.
+
 ## CRITICAL Kolbo Platform Rules
 
 - **Model version, duration, and instrumental toggle are MCP-tool params.** Don't write `v4.5`, `30 seconds`, or `instrumental: true` inside the prompt fields themselves.
+- **Exact track length = `duration_seconds`** (clamped 5–300s). Only length-controllable models honor it (e.g. ElevenLabs Music, `music-v1`) — without it those models default to a ~10s track, so ALWAYS pass it for jingles/beds on those models. Suno ignores it and picks its own length.
 - Suno generations have **two separate input fields**: a **Style / Description** field (`style` param) and a **Lyrics** field (`lyrics` param). Output your prompt as **TWO separate fenced code blocks** so the user (and the tool call) know exactly what goes where.
 - Tell the user to run the prompt multiple times — Suno output varies significantly between generations, that's a feature. Use `num_generations` if the tool supports it, or fire 2–4 parallel `generate_music` calls.
 
@@ -85,7 +88,7 @@ Use Suno's section tags to control structure. Each tag goes on its own line, con
 ### Jingle / ad music (15–30s)
 - `style`: short, punchy descriptor (`upbeat retail pop jingle, female vocal, claps, glossy production, summer energy`)
 - `lyrics`: 2–4 short lines max, often just chorus
-- Pass the shortest `duration` the tool supports.
+- Pass the shortest `duration` the tool supports — or, on a length-controllable model (ElevenLabs Music), pass the exact `duration_seconds` (e.g. `15` or `30`).
 
 ### Cinematic trailer / score
 - `style`: `cinematic orchestral trailer, swelling strings, taiko drums, hybrid choir, dramatic build, modern hybrid score`

package/skills/kolbo/references/workflows/cost-and-validation.md

@@ -48,6 +48,8 @@ Apply when confirming cost before firing:
 
 **Batch totalling 100+ credits:** run `check_credits` first and include the available balance in the summary.
 
+**After generating, report cost only — never "credits remaining".** Coding/chat usage also deducts credits, so any balance you compute (opening balance − generation costs) is wrong by the time you say it. Quote `credits_used` per generation / batch total; if the user asks what's left, run `check_credits` fresh at that moment and quote that number.
+
 ## ⚠️ Quote Real Cost, Never Estimates (CRITICAL)
 
 Pre-flight formulas above are for **preview only**. After firing, every generation returns `credits_used` (multiplier-adjusted total) and `credits_breakdown` (per-model attribution).

package/skills/kolbo/references/workflows/troubleshooting.md

@@ -30,6 +30,10 @@ This re-wires the MCP configuration automatically. Then restart the session.
 
 Wait 60s for the window to reset, retry only the failed calls. For batch image work prefer `generate_creative_director` over multiple `generate_image` calls. Full rate-limit details + retry sequence: see SKILL.md "Rate Limiting & Batch Generation".
 
+## Checking generation status without spinning
+
+`get_generation_status` supports `wait=true` (blocks server-side until the generation reaches a final state, up to ~3 min) and `generation_ids` (many ids in one call → returns `all_done`, `still_processing`, and per-generation results). **Never call it repeatedly in a loop** — one `wait=true` call replaces the loop. If some generations are still running after the wait window, call it ONCE more with `wait=true` and only the `still_processing` ids.
+
 ## Failure envelope from `get_generation_status`
 
 When a generation fails, `get_generation_status` returns a structured `failure` field alongside `error`: