Files

T

Roko f71f3ce4be 🎉 initial: vision-analyze.py v2 — clean ABC architecture

- Two backends: RouterAI (gpt-4o-mini) + LocalGemma (Jan API)
- Smart emoji routing (🌶️/🔞/🤫 → local Gemma, NSFW never hits cloud)
- argparse with --help, --local, --model, --prompt
- ImagePreprocessor with ffmpeg resize
- ProxyHandler({}) for local server bypass
- logging, try/finally cleanup, HTTPError/URLError handling
- Zero shell injection, zero keys in /tmp
- SKILL.md with full documentation for other agents

2026-07-06 17:05:42 +07:00

2.7 KiB

Raw Blame History

Vision Analyze — Image Analysis Skill for AI Agents

Analyze images with two backends: fast cloud (RouterAI gpt-4o-mini) or private local (Gemma 4B via Jan API). Smart routing via emoji flags — NSFW content never touches cloud APIs.

Requirements

Python 3.10+
ffmpeg (for image resize)
API key in ~/.openclaw/openclaw.json → models.providers["routerai-ru"].apiKey
(optional) Local Jan server (http://192.168.88.183:1337)

Usage

python3 vision-analyze.py <image_path>

Arguments

Flag	Description
(none)	RouterAI gpt-4o-mini, default prompt
`--local`	Local Gemma (private, no censorship)
`--model=X`	RouterAI model override
`--prompt="..."`	Custom prompt
`--prompt="🌶 ..."`	Emoji triggers auto-routing to local Gemma

Default Prompt

Дай последовательное описание композиции: передний план, задний план,
элементы на изображении, люди или персонажи. Пиши живым, человеческим
языком, 3-5 предложений.

Routing Rules

No flags → RouterAI gpt-4o-mini (fast, ~2-10s, cheap)
--local → Local Gemma (~30-90s, free, no filters)
--model=X → RouterAI with model X
🌶️ / 🔞 / 🤫 in --prompt → Local Gemma (NSFW never touches RouterAI!)
No auto-fallback! Error → log & message, never silently route to other backend

Architecture

Backend (ABC)
├── RouterAIBackend   — RouterAI API via urllib, HTTPError/URLError handling
└── LocalGemmaBackend — Anthropic /messages, ProxyHandler({}) bypass, 1 retry

ImagePreprocessor    — ffmpeg resize, tempfile, finally cleanup

Safety

API keys never written to /tmp world-readable
No curl, no bash -c, no shell injection vectors
ProxyHandler({}) for local requests (bypasses V2Ray)

Known Limitations

Local Gemma: Only one concurrent request. Never interrupt/kill — causes hang.
Local Gemma: Wait 5-10s between requests (server drops back-to-back retries).
Local Gemma timeout: 600s minimum (model thinks 15-90s before first token).
DeepSeek models cannot see images — do not pass base64 images to them.

For Other Agents

Clone this repo and symlink or copy vision-analyze.py into your workspace:

git clone https://git.hidosi.ru/Hidosi/agent-scripts-vision-analyze.git /path/to/skill
ln -s /path/to/skill/vision-analyze.py /usr/local/bin/vision-analyze

Then follow the usage examples above.

Created 2026-07-06 by Roko (OpenClaw agent) with OpenCode (kimi-k2.7-code). Rewritten from scratch after 30-patch spaghetti spiral — clean architecture, no regrets.

2.7 KiB Raw Blame History