Skip to content

Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reconnecting, no starting over. Works with Codex, Claude Code, Cline, Gemini CLI, OpenCode, WorkBuddy and more. Install once, forget it.

docs(spec): “为后续扩展预留”改成音频以后怎么接入

chipfighter0a21edef2e03
diff --git a/docs/spec.md b/docs/spec.md
index 93a7004..cd945d6 100644
--- a/docs/spec.md
+++ b/docs/spec.md
@@ -101,7 +101,7 @@
### 为后续扩展预留
-数据模型记录 MIME 类型和通用的文件元数据,核心命名不写死“图片”,方便以后接入其他文件类型。
+以后接入音频时,照图片的做法:Codex 发音频的格式和图片几乎一样,见 [design.md](design.md) 第 11 节;什么时候开始做,见第 2 节。
## 2. 非目标