Context Attachment Manager

Context Attachment Manager

Choose which past images go to the model with your next message, in Codex and in Claude Desktop, without leaving the conversation.

English · 简体中文

New in 0.7: subagents and side chats in Codex follow Auto-select too. A side chat no longer resends the task's images, and a subagent leaves out the images of its own earlier turns; both fetch the ones they need by ID. The task's panel lists them, with a switch to turn this off. Earlier: since 0.6 Auto-select is on by default and the panel opens by itself in Claude Desktop, since 0.5 your selection survives compaction in Claude Code, and since 0.4 it works in Claude Desktop. Formerly Codex Attachment Manager; the project was renamed because it no longer works with Codex alone.

Why I built this

I was iterating on image generation with GPT in Codex. After a dozen or so images, the task started failing: the connection kept dropping, and the retries every few minutes never went through. Digging into it, I found that Codex sends every image in the task's history again with every request, and each request had grown to about 44 MB. The only way out was a new task, which meant losing the conversation.

So I wanted to keep the long conversation going and decide, turn by turn, which images the model still gets. Uncheck the ones you no longer need: from the next message on they become short placeholders, and the task and the conversation stay the same. Claude Code also sends the whole history with every request, so 0.4 brings the same panel to Claude Desktop.

Features

• Every image in one list: the panel lists every image in the task (in Codex) or session (in Claude Code), turn by turn: the ones you uploaded and the ones the model viewed or generated, with thumbnails, IDs and sizes. Click one to preview it. In Codex it's a Context Assets tab in the side panel; in Claude Desktop, /cam opens it in the built-in browser.
• Filter by source: with many images, show only some sources: your uploads, PDF pages you commented on in Codex (with the page number and the PDF's name), web page screenshots, and images the model viewed, got from a tool or generated. Filtering changes what you see, never what is sent.
• One click to leave an image out: unchecked images become a short placeholder from the next message on. Toggle single images or a whole turn.
• Duplicates handled: when an identical image is still being sent, the placeholder points to it.
• The model knows why: a note tells the model the images were left out by you to save context, so its earlier answers still stand and it doesn't make up details it can't see.
• The model asks, you decide: when it needs an image, it replies need IMG-xxx. The panel lists what it asked for and jumps to it in one click. A checked image goes back to its place in the conversation, marked with its ID.
• Or let the model pick (new in 0.3, on by default since 0.6): Auto-select at the bottom of the panel, per task or session. Images from earlier turns are then left out by default, and the model fetches the ones it needs by ID, for that turn only, several at once if it needs several. Images you check are pinned and go every turn. New tasks and sessions start with it on; switch it off to choose yourself. The panel shows what the model fetched in the latest turn.
• Subagents and side chats too (new in 0.7, Codex): a side chat you open in a task carries the task's who