@kolbo/kolbo-code-linux-arm64-musl 2.1.4 → 2.1.6

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/kolbo-code-linux-arm64-musl",
-  "version": "2.1.4",
+  "version": "2.1.6",
   "os": [
     "linux"
   ],

package/skills/kolbo/SKILL.md

@@ -98,12 +98,36 @@ You have direct access to the Kolbo AI creative platform via MCP tools (auto-con
 
 ### Cost Awareness
 
-Creative generations bill against the user's Kolbo credit balance. Order of expense (rough):
-- **Cheap & fast**: speech (~5-30s), sound effects (~5-30s), image (~10-30s), transcription (by duration)
-- **Medium**: music (~30s-2min), 3D (~1-3min)
-- **Expensive**: video (~1-5min, highest credit cost), lipsync (~1-3min)
-
-Rule of thumb: confirm intent before firing off a video generation unless the user was explicit. For images, just generate.
+Creative generations bill against the user's Kolbo credit balance. **Billing units differ by type** — always apply the correct formula before generating.
+
+| Type | Billing unit | Credit range | Example |
+|------|-------------|-------------|---------|
+| **Image** | per image (flat) | 1–30 cr | Flux.1 Fast = 1 cr, Midjourney = 4 cr, 4K variants cost more |
+| **Image edit** | per image (flat) | 2–20 cr | |
+| **Video** | **cr/s × duration** | 2–30 cr/s | Kandinsky 5 Fast × 5s = 10 cr; Seedance 2.0 × 10s = 300 cr |
+| **Video from image** | **cr/s × duration** | 4–30 cr/s | Same per-second rule as text-to-video |
+| **Lipsync** | **cr/s × duration** | 5–20 cr/s | |
+| **Music** | per generation (flat) | 15–60 cr | Suno v5 = 15 cr; ElevenLabs Music = 60 cr |
+| **Speech (TTS)** | per 100 characters | 2–5 cr/100 chars | ElevenLabs (5) × 500 chars = 25 cr; Google (2) × 500 chars = 10 cr |
+| **Sound effects** | per generation (flat) | 4–7 cr | |
+| **3D model** | per model (flat) | 5–300 cr | Trellis = 5 cr; Meshy v6 = 150 cr; Marble 1.1 = 300 cr |
+| **Transcription (stt)** | per minute of audio | model.credit × duration_minutes | |
+
+**Calculation formulas — always apply before generating:**
+- **Video / Lipsync**: `total = model_credit_per_second × duration_seconds`
+  - Always call `list_models` first to get the exact `credit` value, then multiply by the requested duration.
+  - Never assume the credit shown is a flat per-generation cost for these types.
+- **Music**: flat per generation — `total = model_credit` (duration does not change the cost).
+- **TTS**: `total = model_credit × ceil(character_count / 100)`
+  - Count the actual characters in the text before estimating. 1000 chars with ElevenLabs = 50 credits.
+- **Images / 3D / Sound effects**: `total = model_credit × quantity`
+
+**When to confirm before generating:**
+- Any video or lipsync generation — always state the estimated credit cost before firing. Formula: `credit/s × seconds`.
+- Music — state the flat credit cost (from `list_models`) before generating.
+- TTS with more than 500 characters — mention the cost first.
+- 3D models with `credit ≥ 100` — confirm before generating.
+- Images: just generate unless the balance is low.
 
 ### Rate Limiting
 Kolbo enforces **10 generation requests per minute per user per tool type** (e.g. 10 image calls + 10 video calls = fine, but 11 image calls in 1 minute = rate limited). General media requests are capped at **300 per minute**.
@@ -158,24 +182,29 @@ The regular `srt_url` groups words into readable subtitle lines (default 12 word
 ### Long Content
 Transcription supports files up to 30 minutes. For longer content, split the file first or provide segments.
 
-### Visual Video/Audio Analysis (what's happening, not just what's said)
-`transcribe_audio` only extracts **speech**. If the user wants to understand **what's visually happening** in a video (scenes, actions, objects, on-screen text) or needs a multimodal AI to reason about the content, use `chat_send_message` with a video-capable model instead.
+### Visual Video/Audio/Image Analysis
+
+**DEFAULT RULE: When the user shares a video or image file without a specific instruction, always do visual analysis — never ask, never default to transcription.**
+
+`transcribe_audio` is ONLY for when the user explicitly says "transcribe", "subtitles", "SRT", or "what's being said". Everything else — "what do you see?", "describe this", "analyze this", "what's in this video?", "what prompts are shown?", or just pasting a file path with no instruction — is visual analysis via Gemini.
 
-**Video-capable models**: `gemini-2.5-pro`, `gemini-2.5-flash` — these can watch video and analyze visual content.
+**NEVER use ffmpeg, `ollama-vision`, or extract frames manually. NEVER ask the user whether to transcribe or analyze — just execute visual analysis.**
 
-**Workflow for visual analysis:**
-1. Upload the video with `upload_media` to get a stable CDN URL
-2. Call `chat_send_message` with the video URL in the message and a video-capable model (e.g. `gemini-2.5-pro`)
-3. Ask your analysis question: "Describe what happens in this video", "What products are shown?", "Summarize the key scenes"
+**Workflow for visual analysis (do this every time):**
+1. `upload_media({ source: "/absolute/local/path/to/file.mp4" })` → get CDN URL (skip if already a public URL)
+2. `chat_send_message({ message: "<your question>", model: "gemini-2.5-pro", media_urls: ["<cdn-url>"] })`
 
-**When to use which:**
+**Routing table — commit to an action, do not ask:**
 
-| User intent | Tool |
-|-------------|------|
-| "Transcribe this" / "What's being said?" | `transcribe_audio` |
-| "Generate subtitles" / "Word-by-word timing" | `transcribe_audio` |
-| "What's happening in this video?" / "Describe the scenes" | `chat_send_message` + Gemini |
-| "Analyze this video and transcribe it" | Both — `transcribe_audio` for text + `chat_send_message` for visual |
+| Trigger | Action |
+|---------|--------|
+| User says "transcribe" / "subtitles" / "SRT" / "what's being said" | `transcribe_audio` only |
+| User says "analyze" / "describe" / "what do you see" / "what's in this" / "what's happening" | Visual analysis — `upload_media` → `chat_send_message` + Gemini |
+| User shares a file path or video URL with no instruction | Visual analysis — `upload_media` → `chat_send_message` + Gemini |
+| User shares a video and asks about on-screen text / prompts / UI | Visual analysis — `upload_media` → `chat_send_message` + Gemini |
+| User wants both transcript AND visual description | Both — run `transcribe_audio` AND `chat_send_message` + Gemini |
+
+When in doubt, do visual analysis. Do not stop to ask.
 
 ---
 
@@ -405,6 +434,20 @@ When the user shares an image and asks about it:
 
 ---
 
+## Sharing HTML Artifacts
+
+When you generate an HTML, SVG, or Mermaid artifact in the chat, a **Share** button appears in the artifact preview toolbar (next to Desktop / Mobile). Clicking it:
+
+1. Uploads the artifact to Kolbo's hosting platform
+2. Copies a permanent public URL to the clipboard (e.g. `https://api.kolbo.ai/api/shared-artifact-raw/<token>`)
+3. Shows a toast confirming the link was copied
+
+Anyone with the URL can view the rendered page — no login required.
+
+**Requirements:** You must be logged in (`kolbo auth login`). The share button returns an error toast if you are not authenticated.
+
+---
+
 ## Kolbo Code Documentation
 
 Full public documentation for Kolbo Code (the CLI you are running inside) lives at **[docs.kolbo.ai/docs/kolbo-code](https://docs.kolbo.ai/docs/kolbo-code)**. If the user asks about installation, authentication, voice input, supported languages, commands, or how to uninstall, point them to the matching page below rather than guessing:

package/skills/ollama-vision/SKILL.md

@@ -1,105 +0,0 @@
----
-name: ollama-vision
-description: >
-  Batch image analysis using local Ollama + gemma4 (multimodal).
-  Use when the user needs to analyze, caption, classify, or extract text from images locally — 
-  free, offline, no rate limits, no API key needed.
-  Keywords: image analysis, batch images, captions, OCR, vision, gemma4, ollama, local AI
----
-
-# Ollama Vision — Batch Image Analysis with gemma4
-
-## Setup (already done on this machine)
-
-- Ollama installed and running (auto-starts on Windows boot)
-- Model: `gemma4` (9.6 GB, multimodal)
-- Python package: `ollama` v0.6.1 installed (pip, Python 3.10)
-- REST API available at `http://localhost:11434`
-
-## Core Pattern
-
-```python
-import ollama
-
-response = ollama.chat(model='gemma4', messages=[{
-    'role': 'user',
-    'content': 'Your prompt here',
-    'images': ['path/to/image.jpg']  # omit for text-only
-}])
-print(response['message']['content'])
-```
-
-## Batch Image Captioning Script
-
-```python
-import ollama
-from pathlib import Path
-import csv
-
-def caption_images(folder: str, prompt: str = "Write a short caption for this image.", output_csv: str = "captions.csv"):
-    images_dir = Path(folder)
-    extensions = {'.jpg', '.jpeg', '.png', '.webp', '.gif', '.bmp'}
-    image_files = [f for f in images_dir.iterdir() if f.suffix.lower() in extensions]
-    
-    results = []
-    for i, img_path in enumerate(image_files, 1):
-        print(f"[{i}/{len(image_files)}] Processing {img_path.name}...")
-        try:
-            response = ollama.chat(model='gemma4', messages=[{
-                'role': 'user',
-                'content': prompt,
-                'images': [str(img_path)]
-            }])
-            caption = response['message']['content'].strip()
-            results.append({'file': img_path.name, 'caption': caption})
-            print(f"  → {caption[:80]}...")
-        except Exception as e:
-            print(f"  ERROR: {e}")
-            results.append({'file': img_path.name, 'caption': f'ERROR: {e}'})
-    
-    with open(output_csv, 'w', newline='', encoding='utf-8') as f:
-        writer = csv.DictWriter(f, fieldnames=['file', 'caption'])
-        writer.writeheader()
-        writer.writerows(results)
-    
-    print(f"\nDone! Saved {len(results)} captions to {output_csv}")
-
-# Usage
-caption_images("./images", prompt="Describe this image in one sentence.")
-```
-
-## Common Prompts
-
-| Task | Prompt |
-|------|--------|
-| Caption | `"Write a short, descriptive caption for this image."` |
-| Alt text | `"Write alt text for this image for accessibility."` |
-| Classification | `"What category does this image belong to? Reply with one word."` |
-| OCR | `"Extract all text visible in this image."` |
-| Product description | `"Write a product description for the item shown in this image."` |
-| Social media | `"Write a catchy Instagram caption for this image."` |
-
-## REST API Alternative (no Python package needed)
-
-```python
-import requests, base64
-
-def analyze_image(image_path: str, prompt: str) -> str:
-    with open(image_path, "rb") as f:
-        img_b64 = base64.b64encode(f.read()).decode()
-    
-    response = requests.post("http://localhost:11434/api/generate", json={
-        "model": "gemma4",
-        "prompt": prompt,
-        "images": [img_b64],
-        "stream": False
-    })
-    return response.json()["response"]
-```
-
-## Tips
-
-- gemma4 handles JPG, PNG, WEBP, GIF, BMP
-- For large batches, add `time.sleep(0.5)` between requests to avoid overloading
-- Results are best when prompts are specific ("describe the main subject" vs "describe this")
-- Ollama must be running — check with `ollama list` in terminal