@thanhthi2895/luna-ai 2.16.2

package/agentic/antigravity/.agents/skills/ai-multimodal/.env.example

@@ -0,0 +1,214 @@
+# Google Gemini API Configuration
+#
+# ============================================================================
+# CENTRAL ENV NOTE
+# ============================================================================
+# GEMINI_API_KEY (and rotation keys GEMINI_API_KEY_2, _3, etc.) should be set
+# in ~/.gemini/antigravity/.env (central shared env), NOT in this file.
+# This file is for skill-specific tuning variables only.
+# See: docs/code-standards.md § Environment Variables Convention
+# ============================================================================
+
+# ============================================================================
+# OPTION 1: Google AI Studio (Default - Recommended for most users)
+# ============================================================================
+# Get your API key: https://aistudio.google.com/apikey
+# PREFER: Set GEMINI_API_KEY in ~/.gemini/antigravity/.env instead of here
+# GEMINI_API_KEY=your_api_key_here
+
+# ============================================================================
+# API Key Rotation (Optional - For high-volume usage)
+# ============================================================================
+# Add multiple API keys for automatic rotation on rate limit errors.
+# Free tier accounts are heavily rate-limited; rotation helps distribute load.
+#
+# Format: GEMINI_API_KEY_N where N is 2, 3, 4, etc.
+# The primary GEMINI_API_KEY is always used first.
+#
+# GEMINI_API_KEY_2=your_second_api_key
+# GEMINI_API_KEY_3=your_third_api_key
+# GEMINI_API_KEY_4=your_fourth_api_key
+#
+# Features:
+# - Auto-rotates on RESOURCE_EXHAUSTED / 429 errors
+# - 60-second cooldown per key after rate limit
+# - Logs rotation events with --verbose flag
+# - Backward compatible: single key still works
+
+# ============================================================================
+# OPTION 2: Vertex AI (Google Cloud Platform)
+# ============================================================================
+# Uncomment these lines to use Vertex AI instead of Google AI Studio
+# GEMINI_USE_VERTEX=true
+# VERTEX_PROJECT_ID=your-gcp-project-id
+# VERTEX_LOCATION=us-central1
+
+# ============================================================================
+# Model Selection (Optional)
+# ============================================================================
+# Override default models for specific capabilities
+# If not set, intelligent defaults are used based on task type
+
+# --- Image Generation ---
+# Used by: --task generate (image)
+# Default: gemini-2.5-flash-image (Nano Banana Flash - fast, cost-effective)
+# Alternative: imagen-4.0-generate-001 (production quality)
+# NOTE: All image generation requires billing - no free tier available (limit: 0)
+# Options:
+#   gemini-2.5-flash-image            - Nano Banana Flash: fast, ~$1/1M tokens (DEFAULT)
+#   gemini-3-pro-image-preview        - Nano Banana Pro: 4K text, reasoning (requires billing)
+#   imagen-4.0-generate-001           - Imagen 4 Standard: production quality (~$0.02/image)
+#   imagen-4.0-ultra-generate-001     - Imagen 4 Ultra: maximum quality (~$0.04/image)
+#   imagen-4.0-fast-generate-001      - Imagen 4 Fast: speed-optimized (~$0.01/image)
+# IMAGE_GEN_MODEL=gemini-2.5-flash-image
+
+# --- Video Generation ---
+# Used by: --task generate-video (new capability)
+# Default: veo-3.1-generate-preview
+# NOTE: Video generation requires billing - no free tier fallback available
+# Options:
+#   veo-3.1-generate-preview       - Latest, native audio, frame control (requires billing)
+#   veo-3.1-fast-generate-preview  - Speed-optimized for business (requires billing)
+#   veo-3.0-generate-001           - Stable, native audio, 8s videos (requires billing)
+#   veo-3.0-fast-generate-001      - Stable fast variant (requires billing)
+# VIDEO_GEN_MODEL=veo-3.1-generate-preview
+
+# --- Multimodal Analysis ---
+# Used by: --task analyze, transcribe, extract
+# Default: gemini-2.5-flash
+# Options:
+#   gemini-3-pro-preview           - Latest, agentic workflows, 1M context
+#   gemini-2.5-flash               - Best price/performance (recommended)
+#   gemini-2.5-pro                 - Highest quality
+# MULTIMODAL_MODEL=gemini-2.5-flash
+
+# --- Legacy Compatibility ---
+# Generic model override (use specific variables above instead)
+# GEMINI_MODEL=gemini-2.5-flash
+# GEMINI_IMAGE_GEN_MODEL=gemini-2.5-flash-image
+
+# ============================================================================
+# Rate Limiting Configuration (Optional)
+# ============================================================================
+# Requests per minute limit (adjust based on your tier)
+# GEMINI_RPM_LIMIT=15
+
+# Tokens per minute limit
+# GEMINI_TPM_LIMIT=4000000
+
+# Requests per day limit
+# GEMINI_RPD_LIMIT=1500
+
+# ============================================================================
+# Video Generation Options (Optional)
+# ============================================================================
+# Video duration in seconds (8s only for now)
+# VEO_DURATION=8
+
+# Video resolution: 720p or 1080p
+# VEO_RESOLUTION=1080p
+
+# Aspect ratio: 16:9, 9:16, 1:1 (16:9 is default)
+# VEO_ASPECT_RATIO=16:9
+
+# Frame rate: 24fps (fixed for now)
+# VEO_FPS=24
+
+# Enable native audio generation
+# VEO_AUDIO=true
+
+# ============================================================================
+# Image Generation Options (Optional)
+# ============================================================================
+# Number of images to generate (1-4)
+# IMAGEN_NUM_IMAGES=1
+
+# Image size: 1K or 2K (Ultra/Standard only)
+# IMAGEN_SIZE=1K
+
+# Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4
+# IMAGEN_ASPECT_RATIO=1:1
+
+# Enable person generation (restricted in EEA, CH, UK)
+# IMAGEN_PERSON_GENERATION=true
+
+# Add SynthID watermark (always enabled by default)
+# IMAGEN_WATERMARK=true
+
+# ============================================================================
+# Processing Options (Optional)
+# ============================================================================
+# Video resolution mode: default or low-res
+# low-res uses ~100 tokens/second vs ~300 for default
+# GEMINI_VIDEO_RESOLUTION=default
+
+# Audio quality: default (16 Kbps mono, auto-downsampled)
+# GEMINI_AUDIO_QUALITY=default
+
+# PDF processing mode: inline (<20MB) or file-api (>20MB, automatic)
+# GEMINI_PDF_MODE=auto
+
+# ============================================================================
+# Retry Configuration (Optional)
+# ============================================================================
+# Maximum retry attempts for failed requests
+# GEMINI_MAX_RETRIES=3
+
+# Initial retry delay in seconds (uses exponential backoff)
+# GEMINI_RETRY_DELAY=1
+
+# ============================================================================
+# Output Configuration (Optional)
+# ============================================================================
+# Default output directory for generated images
+# OUTPUT_DIR=./output
+
+# Image output format (png or jpeg)
+# IMAGE_FORMAT=png
+
+# Image quality for JPEG (1-100)
+# IMAGE_QUALITY=95
+
+# ============================================================================
+# Context Caching (Optional)
+# ============================================================================
+# Enable context caching for repeated queries on same file
+# GEMINI_ENABLE_CACHING=true
+
+# Cache TTL in seconds (default: 1800 = 30 minutes)
+# GEMINI_CACHE_TTL=1800
+
+# ============================================================================
+# Logging (Optional)
+# ============================================================================
+# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
+# LOG_LEVEL=INFO
+
+# Log file path
+# LOG_FILE=./logs/gemini.log
+
+# ============================================================================
+# Pricing Reference (as of 2025-11)
+# ============================================================================
+# Gemini 2.5 Flash: $1.00/1M input, $0.10/1M output
+# Gemini 2.5 Pro: $3.00/1M input, $12.00/1M output
+# Gemini 3 Pro: $2.00/1M input (<200k), $4.00 (>200k), $12/$18 output
+# Imagen 4: ~$0.01-$0.04 per image (varies by variant)
+# Veo 3: TBD (preview pricing)
+# Monitor: https://ai.google.dev/pricing
+
+# ============================================================================
+# Notes
+# ============================================================================
+# 1. Never commit API keys to version control
+# 2. Add .env to .gitignore
+# 3. API keys can be restricted in Google Cloud Console
+# 4. Monitor usage at: https://aistudio.google.com/apikey
+# 5. Free tier limits: 15 RPM, 1M-4M TPM, 1,500 RPD
+# 6. Vertex AI requires GCP authentication via gcloud CLI
+# 7. Model defaults (Dec 2025):
+#    - Image gen: gemini-2.5-flash-image (Nano Banana Flash - default)
+#    - Image gen: imagen-4.0-generate-001 (alternative for production)
+#    - Video gen: veo-3.1-generate-preview
+#    - Analysis: gemini-2.5-flash
+# 8. Preview models (veo-3.1, gemini-3) may have API changes

package/agentic/antigravity/.agents/skills/ai-multimodal/SKILL.md

@@ -0,0 +1,115 @@
+---
+name: lu:ai-multimodal
+description: Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.
+license: MIT
+allowed-tools:
+  - Bash
+  - Read
+  - Write
+  - Edit
+argument-hint: "[file-path] [prompt]"
+---
+
+# AI Multimodal
+
+Process audio, images, videos, documents, and generate images/videos using Google Gemini's multimodal API.
+
+## Setup
+
+```bash
+pip install google-genai python-dotenv pillow
+```
+
+### Environment Variables
+
+**Fallback env var names used by this skill:**
+
+| Variable | Required | Location | Description |
+|---|---|---|---|
+| `GEMINI_API_KEY` | yes | `agentic/antigravity/.env` → `~/.gemini/antigravity/.env` | Primary Gemini API key |
+| `GEMINI_API_KEY_2`, `_3`, ... | no | `agentic/antigravity/.env` → `~/.gemini/antigravity/.env` | Additional keys for rotation |
+
+Set `GEMINI_API_KEY` in the **central env** (`agentic/antigravity/.env`), which is symlinked to `~/.gemini/antigravity/.env` via `sync.sh`.
+
+```bash
+# agentic/antigravity/.env (synced to ~/.gemini/antigravity/.env)
+GEMINI_API_KEY=your-key  # Get from https://aistudio.google.com/apikey
+```
+
+### API Key Rotation (Optional)
+
+For high-volume usage or when hitting rate limits, add multiple keys in `agentic/antigravity/.env`:
+
+```bash
+GEMINI_API_KEY=key1
+GEMINI_API_KEY_2=key2
+GEMINI_API_KEY_3=key3
+```
+
+**Features:**
+- Auto-rotates on rate limit (429/RESOURCE_EXHAUSTED) errors
+- 60-second cooldown per key after rate limit
+- Logs rotation events with `--verbose` flag
+- Backward compatible: single key still works
+
+## Quick Start
+
+**Verify setup**: `python scripts/check_setup.py`
+**Analyze media**: `python scripts/gemini_batch_process.py --files <file> --task <analyze|transcribe|extract>`
+  - TIP: When you're asked to analyze an image, check if `gemini` command is available, then use `echo "<prompt to analyze image>" | gemini -y -m <gemini.model>` command (read model from `.claude/.luna.json`: `gemini.model`). If `gemini` command is not available, use `python scripts/gemini_batch_process.py --files <file> --task analyze` command.
+**Generate content**: `python scripts/gemini_batch_process.py --task <generate|generate-video> --prompt "description"`
+
+> **Stdin support**: You can pipe files directly via stdin (auto-detects PNG/JPG/PDF/WAV/MP3).
+> - `cat image.png | python scripts/gemini_batch_process.py --task analyze --prompt "Describe this"`
+> - `python scripts/gemini_batch_process.py --files image.png --task analyze` (traditional)
+
+## Models
+
+- **Image generation**: `imagen-4.0-generate-001` (standard), `imagen-4.0-ultra-generate-001` (quality), `imagen-4.0-fast-generate-001` (speed)
+- **Video generation**: `veo-3.1-generate-preview` (8s clips with audio)
+- **Analysis**: `gemini-2.5-flash` (recommended), `gemini-2.5-pro` (advanced)
+
+## Scripts
+
+- **`gemini_batch_process.py`**: CLI orchestrator for `transcribe|analyze|extract|generate|generate-video` that auto-resolves API keys, picks sensible default models per task, streams files inline vs File API, and saves structured outputs (text/JSON/CSV/markdown plus generated assets) for Imagen 4 + Veo workflows.
+- **`media_optimizer.py`**: ffmpeg/Pillow-based preflight tool that compresses/resizes/converts audio, image, and video inputs, enforces target sizes/bitrates, splits long clips into hour chunks, and batch-processes directories so media stays within Gemini limits.
+- **`document_converter.py`**: Gemini-powered converter that uploads PDFs/images/Office docs, applies a markdown-preserving prompt, batches multiple files, auto-names outputs under `docs/assets`, and exposes CLI flags for model, prompt, auto-file naming, and verbose logging.
+- **`check_setup.py`**: Interactive readiness checker that verifies directory layout, centralized env resolver, required Python deps, and GEMINI_API_KEY availability/format, then performs a live Gemini API call and prints remediation instructions if anything fails.
+
+Use `--help` for options.
+
+## References
+
+Load for detailed guidance:
+
+| Topic | File | Description |
+|-------|------|-------------|
+| Music | `references/music-generation.md` | Lyria RealTime API for background music generation, style prompts, real-time control, integration with video production. |
+| Audio | `references/audio-processing.md` | Audio formats and limits, transcription (timestamps, speakers, segments), non-speech analysis, File API vs inline input, TTS models, best practices, cost and token math, and concrete meeting/podcast/interview recipes. |
+| Images | `references/vision-understanding.md` | Vision capabilities overview, supported formats and models, captioning/classification/VQA, detection and segmentation, OCR and document reading, multi-image workflows, structured JSON output, token costs, best practices, and common product/screenshot/chart/scene use cases. |
+| Image Gen | `references/image-generation.md` | Imagen 4 and Gemini image model overview, generate_images vs generate_content APIs, aspect ratios and costs, text/image/both modalities, editing and composition, style and quality control, safety settings, best practices, troubleshooting, and common marketing/concept-art/UI scenarios. |
+| Video | `references/video-analysis.md` | Video analysis capabilities and supported formats, model/context choices, local/inline/YouTube inputs, clipping and FPS control, multi-video comparison, temporal Q&A and scene detection, transcription with visual context, token and cost guidance, and optimization/best-practice patterns. |
+| Video Gen | `references/video-generation.md` | Veo model matrix, text-to-video and image-to-video quick start, multi-reference and extension flows, camera and timing control, configuration (resolution, aspect, audio, safety), prompt design patterns, performance tips, limitations, troubleshooting, and cost estimates. |
+
+## Limits
+
+**Formats**: Audio (WAV/MP3/AAC, 9.5h), Images (PNG/JPEG/WEBP, 3.6k), Video (MP4/MOV, 6h), PDF (1k pages)
+**Size**: 20MB inline, 2GB File API
+**Important:** 
+- If you are going to generate a transcript of the audio, and the audio length is longer than 15 minutes, the transcript often gets truncated due to output token limits in the Gemini API response. To get the full transcript, you need to split the audio into smaller chunks (max 15 minutes per chunk) and transcribe each segment for a complete transcript.
+- If you are going to generate a transcript of the video and the video length is longer than 15 minutes, use ffmpeg to extract the audio from the video, truncate the audio to 15 minutes, transcribe all audio segments, and then combine the transcripts into a single transcript.
+**Transcription Output Requirements:**
+- Format: Markdown
+- Metadata: Duration, file size, generated date, description, file name, topics covered, etc.
+- Parts: from-to (e.g., 00:00-00:15), audio chunk name, transcript, status, etc.
+- Transcript format: 
+  ```
+  [HH:MM:SS -> HH:MM:SS] transcript content
+  [HH:MM:SS -> HH:MM:SS] transcript content
+  ...
+  ```
+
+## Resources
+
+- [API Docs](https://ai.google.dev/gemini-api/docs/)
+- [Pricing](https://ai.google.dev/pricing)