configuring-vision

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Configuring vision

配置视觉功能

Watch Skill's agent surface and model backend are separate choices. Claude Code, Codex, Cursor, OpenClaw, framework agents, and REST clients all call the same engine; the engine can send selected frames to any supported vision provider.

Watch Skill的代理界面与模型后端是独立选择的。Claude Code、Codex、Cursor、OpenClaw、框架代理以及REST客户端均调用同一引擎；该引擎可将选定的画面帧发送至任何受支持的视觉服务提供商。

Supported providers

支持的提供商

bash

watch-skill setup-vision --provider anthropic --api-key <KEY>
watch-skill setup-vision --provider openai --api-key <KEY>
watch-skill setup-vision --provider gemini --api-key <KEY>
watch-skill setup-vision --provider openrouter --api-key <KEY>
watch-skill setup-vision --provider ollama

Prefer a key the user already has. Do not claim Ollama is required, and do not ask the user to reveal a secret in chat. They can set the matching environment variable or run the command privately in their terminal.

bash

watch-skill setup-vision --provider anthropic --api-key <KEY>
watch-skill setup-vision --provider openai --api-key <KEY>
watch-skill setup-vision --provider gemini --api-key <KEY>
watch-skill setup-vision --provider openrouter --api-key <KEY>
watch-skill setup-vision --provider ollama

优先使用用户已有的密钥。不要声称必须使用Ollama，也不要要求用户在聊天中透露密钥。用户可以设置对应的环境变量，或在终端中私密运行上述命令。

Route bulk work and verification separately

批量任务与验证任务分开路由

One model can serve both tiers:

bash

watch-skill setup-vision --provider openai --api-key <KEY> --model <vision-model>

Or use a cheaper model for scene descriptions and a stronger model for uncertain answers and loop critiques:

bash

watch-skill setup-vision --provider openrouter --api-key <KEY> \
  --cheap-model <fast-vision-model> --strong-model <strong-vision-model>

Add

--verify

to make one live probe call. If it fails, report the structured error and its

fix

; never echo the key.

可使用单个模型同时处理两个层级的任务：

bash

watch-skill setup-vision --provider openai --api-key <KEY> --model <vision-model>

或者使用性价比更高的模型生成场景描述，使用性能更强的模型处理不确定的答案和循环校验：

bash

watch-skill setup-vision --provider openrouter --api-key <KEY> \
  --cheap-model <fast-vision-model> --strong-model <strong-vision-model>

添加

--verify

参数可发起一次实时探测调用。如果调用失败，需返回结构化错误信息及其修复方案；绝对不要回显密钥。

No provider is also valid

不配置提供商同样有效

Without a vision API, Watch Skill still acquires video, reads captions, runs local transcription and OCR, indexes evidence, and searches it. Visual synthesis degrades to timestamped evidence instead of guessing.

在没有视觉API的情况下，Watch Skill仍可获取视频、读取字幕、运行本地转录与OCR、索引证据并进行搜索。视觉合成功能会降级为基于时间戳的证据展示，而非进行猜测。