@hienlh/ppm 0.9.79 → 0.9.81

package/.opencode/skills/ai-artist/scripts/search.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+AI Artist Search - BM25 search engine for prompt engineering
+Usage: python search.py "<query>" [--domain <domain>] [--max-results 3]
+       python search.py "<query>" --build-prompt [-p <platform>] [-s <style>]
+       python search.py "<query>" --llm-pattern [-o <output_format>]
+
+Domains: style, platform, subject, llm, quality, domain, examples
+Platforms: midjourney, dall-e, stable-diffusion, flux, nano-banana
+"""
+
+import argparse
+from core import CSV_CONFIG, AVAILABLE_DOMAINS, MAX_RESULTS, search, search_all_domains
+from prompt_builder import build_image_prompt, build_llm_prompt, format_prompt_report
+
+
+def format_output(result):
+    """Format results for Claude consumption (token-optimized)"""
+    if "error" in result:
+        return f"Error: {result['error']}"
+
+    output = []
+    output.append(f"## AI Artist Search Results")
+    output.append(f"**Domain:** {result['domain']} | **Query:** {result['query']}")
+    output.append(f"**Source:** {result['file']} | **Found:** {result['count']} results\n")
+
+    for i, row in enumerate(result['results'], 1):
+        output.append(f"### Result {i}")
+        for key, value in row.items():
+            value_str = str(value)
+            if len(value_str) > 300:
+                value_str = value_str[:300] + "..."
+            output.append(f"- **{key}:** {value_str}")
+        output.append("")
+
+    return "\n".join(output)
+
+
+def format_multi_output(results):
+    """Format multi-domain results"""
+    output = []
+    output.append("## AI Artist Multi-Domain Search\n")
+
+    for domain, result in results.items():
+        output.append(f"### {domain.upper()}")
+        for i, row in enumerate(result['results'], 1):
+            first_key = list(row.keys())[0]
+            output.append(f"- {row.get(first_key, 'Unknown')}")
+        output.append("")
+
+    return "\n".join(output)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="AI Artist Search")
+    parser.add_argument("query", help="Search query or subject for prompt building")
+    parser.add_argument("--domain", "-d", choices=AVAILABLE_DOMAINS, help="Search domain (auto-detected if not specified)")
+    parser.add_argument("--max-results", "-n", type=int, default=MAX_RESULTS, help="Max results (default: 3)")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    parser.add_argument("--all", "-a", action="store_true", help="Search all domains")
+
+    # Prompt building options
+    parser.add_argument("--build-prompt", "-bp", action="store_true", help="Build a complete image prompt")
+    parser.add_argument("--platform", "-p", type=str, default="midjourney", help="Target platform for prompt building")
+    parser.add_argument("--style", "-s", type=str, default=None, help="Visual style for prompt building")
+    parser.add_argument("--context", "-c", type=str, default=None, help="Domain context (marketing, gaming, etc.)")
+
+    # LLM pattern options
+    parser.add_argument("--llm-pattern", "-lp", action="store_true", help="Build an LLM prompt using patterns")
+    parser.add_argument("--pattern", type=str, default=None, help="Prompt pattern to use")
+    parser.add_argument("--output-format", "-o", type=str, default=None, help="Output format (json, markdown)")
+
+    # Output format
+    parser.add_argument("--format", "-f", choices=["ascii", "markdown"], default="ascii", help="Output format")
+
+    args = parser.parse_args()
+
+    # Prompt building takes priority
+    if args.build_prompt:
+        result = build_image_prompt(
+            subject=args.query,
+            style=args.style,
+            platform=args.platform,
+            context=args.context
+        )
+        print(format_prompt_report(result, args.format))
+
+    elif args.llm_pattern:
+        result = build_llm_prompt(
+            task=args.query,
+            pattern=args.pattern,
+            output_format=args.output_format
+        )
+        print(format_prompt_report(result, args.format))
+
+    elif args.all:
+        results = search_all_domains(args.query, args.max_results)
+        if args.json:
+            import json
+            print(json.dumps(results, indent=2, ensure_ascii=False))
+        else:
+            print(format_multi_output(results))
+
+    else:
+        result = search(args.query, args.domain, args.max_results)
+        if args.json:
+            import json
+            print(json.dumps(result, indent=2, ensure_ascii=False))
+        else:
+            print(format_output(result))

package/.opencode/skills/ai-multimodal/.env.example

@@ -0,0 +1,230 @@
+# Google Gemini API Configuration
+
+# ============================================================================
+# OPTION 1: Google AI Studio (Default - Recommended for most users)
+# ============================================================================
+# Get your API key: https://aistudio.google.com/apikey
+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
+
+# ============================================================================
+# MiniMax API Configuration (Optional - for image/video/speech/music generation)
+# ============================================================================
+# Get your API key: https://platform.minimax.io/user-center/basic-information/interface-key
+# MINIMAX_API_KEY=your_minimax_api_key_here
+
+# --- MiniMax Image Generation ---
+# Models: image-01 (standard), image-01-live (enhanced)
+# Cost: ~$0.03/image | Rate: 10 RPM
+# MINIMAX_IMAGE_MODEL=image-01
+
+# --- MiniMax Video Generation (Hailuo) ---
+# Models: MiniMax-Hailuo-2.3, MiniMax-Hailuo-2.3-Fast, MiniMax-Hailuo-02, S2V-01
+# Cost: $0.25-0.52/video | Rate: 5 RPM
+# MINIMAX_VIDEO_MODEL=MiniMax-Hailuo-2.3
+
+# --- MiniMax Speech/TTS ---
+# Models: speech-2.8-hd (best), speech-2.8-turbo (fast)
+# Cost: $30-50/1M chars | Rate: 60 RPM | 300+ voices, 40+ languages
+# MINIMAX_SPEECH_MODEL=speech-2.8-hd
+
+# --- MiniMax Music Generation ---
+# Models: music-2.5 (4-minute songs with vocals)
+# Cost: $0.03-0.075/gen | Rate: 120 RPM
+# MINIMAX_MUSIC_MODEL=music-2.5
+
+# ============================================================================
+# 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/.opencode/skills/ai-multimodal/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: ck:ai-multimodal
+description: Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4, Nano Banana 2, MiniMax), videos (Veo 3, Hailuo), speech (MiniMax TTS), music (MiniMax). 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 using Gemini. Generate images, videos, speech, music via Gemini + MiniMax.
+
+## Setup
+
+```bash
+# Google Gemini (analysis + image/video gen)
+export GEMINI_API_KEY="your-key"  # https://aistudio.google.com/apikey
+# MiniMax (image/video/speech/music gen)
+export MINIMAX_API_KEY="your-key"  # https://platform.minimax.io/user-center/basic-information/interface-key
+pip install google-genai python-dotenv pillow requests
+```
+
+### API Key Rotation (Optional)
+
+For high-volume Gemini usage, configure multiple keys:
+
+```bash
+export GEMINI_API_KEY="key1"
+export GEMINI_API_KEY_2="key2"  # auto-rotates on rate limit
+```
+
+## 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 `$HOME/.opencode/.ck.json`: `gemini.model`). If `gemini` command is not available, use `python scripts/gemini_batch_process.py --files <file> --task analyze` command.
+**Generate (Gemini)**: `python scripts/gemini_batch_process.py --task <generate|generate-video> --prompt "desc"`
+**Generate (MiniMax)**: `python scripts/minimax_cli.py --task <generate|generate-video|generate-speech|generate-music> --prompt "desc"`
+
+> **Stdin support**: Pipe files via stdin for Gemini analysis (auto-detects PNG/JPG/PDF/WAV/MP3).
+
+## Models
+
+### Google Gemini / Imagen
+- **Image gen**: `gemini-3.1-flash-image-preview` (Nano Banana 2 - DEFAULT), `gemini-2.5-flash-image` (Flash), `gemini-3-pro-image-preview` (Pro 4K), `imagen-4.0-generate-001` (standard), `imagen-4.0-ultra-generate-001` (quality), `imagen-4.0-fast-generate-001` (speed)
+- **Video gen**: `veo-3.1-generate-preview` (8s clips with audio)
+- **Analysis**: `gemini-2.5-flash` (recommended), `gemini-2.5-pro` (advanced)
+
+### MiniMax (NEW)
+- **Image gen**: `image-01` (standard), `image-01-live` (enhanced) - $0.03/image, 1-9 batch
+- **Video gen (Hailuo)**: `MiniMax-Hailuo-2.3` (1080p), `MiniMax-Hailuo-2.3-Fast` (50% cheaper), `MiniMax-Hailuo-02` (first+last frame), `S2V-01` (subject ref)
+- **Speech/TTS**: `speech-2.8-hd` (best), `speech-2.8-turbo` (fast) - 300+ voices, 40+ languages, emotion control
+- **Music**: `music-2.5` - 4-minute songs with vocals, synchronized lyrics
+
+## Scripts
+
+- **`gemini_batch_process.py`**: Gemini CLI for `transcribe|analyze|extract|generate|generate-video`. Auto-resolves API keys, Imagen 4 + Veo + Nano Banana workflows.
+- **`minimax_cli.py`**: MiniMax CLI for `generate|generate-video|generate-speech|generate-music`. Supports all MiniMax models.
+- **`minimax_generate.py`**: MiniMax generation functions (image, video, speech, music). Library for programmatic use.
+- **`minimax_api_client.py`**: MiniMax HTTP client, auth, async polling, file download utilities.
+- **`media_optimizer.py`**: ffmpeg/Pillow preflight: compress/resize/convert media to stay within API limits.
+- **`document_converter.py`**: Gemini-powered PDF/image/Office → markdown converter.
+- **`check_setup.py`**: Setup checker for API keys and dependencies.
+
+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. |
+| MiniMax | `references/minimax-generation.md` | MiniMax image (image-01), video (Hailuo 2.3), speech (TTS 2.8), and music (2.5) generation APIs. Endpoints, models, parameters, async workflows, pricing, rate limits, voice library, and examples. |
+
+## 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
+
+- [Gemini API Docs](https://ai.google.dev/gemini-api/docs/)
+- [Gemini Pricing](https://ai.google.dev/pricing)
+- [MiniMax API Docs](https://platform.minimax.io/docs/api-reference/api-overview)
+- [MiniMax Pricing](https://platform.minimax.io/pricing)