context-attachment-manager

<p align="center"> <img src="plugin/assets/logo.png" width="96" height="96" alt=""> </p> <h1 align="center">Context Attachment Manager</h1> <p align="center"><b>Long image chats in Codex and Claude, without the lag.</b><br>The model manages its own images, pulling back only what it needs. And any image you made before is one search away: just describe what you remember.</p> <p align="center"> <a href="https://github.com/chipfighter/context-attachment-manager/actions/workflows/ci.yml"><img src="https://github.com/chipfighter/context-attachment-manager/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://github.com/chipfighter/context-attachment-manager/releases"><img src="https://img.shields.io/github/v/release/chipfighter/context-attachment-manager?include_prereleases" alt="Release"></a> <img src="https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux-lightgrey" alt="Platform: Windows, macOS, Linux"> <img src="https://img.shields.io/badge/Codex%20desktop-26.1013-339CFF" alt="Tested on Codex desktop 26.1013"> <img src="https://img.shields.io/badge/Claude%20Desktop-Claude%20Code%202.1.299-D97757" alt="Tested in Claude Desktop with Claude Code 2.1.299"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="License: MIT"></a> </p> <p align="center"><b>English</b> · <a href="README_CN.md">简体中文</a></p> <p align="center"> <img src="docs/images/loop.gif" alt="The panel on a task of period-drama keyframes. Turning on Auto-select grays out the earlier images one by one, and the next request drops from 7.5 MB to 1.7 MB, 77% less." width="100%"> </p> <p align="center"> <img src="docs/images/hero.png" alt="Three views of the panel on a task of period-drama keyframes. Auto-select: the model manages its own images, and the card shows the next request at 1.7 MB instead of 7.5 MB. Search: typing best face finds the close-up the user called the best face three turns ago. Preview: that close-up shown full size." width="100%"> </p>

Why I made this

I was iterating on images with GPT in Codex. After a dozen or so, the chat started failing: it kept reconnecting and never got through. Every message was sending every image in the conversation again, about 44 MB each time. The only way out was a new chat, and with it, losing everything we had built up.

So I made a panel that keeps the conversation and drops the weight.

What it does

• The model manages its own images. Earlier images stay out of your messages, and when the model needs one, it pulls that one back by itself. Nothing to set up. Pin the ones that matter, like a character reference, and they go with every message.
• Find any image by what you remember. Search "best face" or "rainy night", filter by place, or browse by turn. Click one to see it full size.
• It remembers every image. The model quietly notes what each image shows and what you said about it ("too dark", "best face"). Even far into a long chat, or after the chat is compacted, it picks the right one.
• Your chat stays light. No more slowdowns or endless reconnecting. In a 15-image task, a request that carried 24.9 MB went out at 212 KB.

How to use

• Codex: open Context Assets in a task's side panel.
• Claude Desktop: in the Code tab, the panel opens by itself next to your conversation once there are images. Type /cam to bring it back.

Then just keep chatting. From the start, the model picks earlier images on its own; to pin one, click it and check Send every turn. To choose yourself, turn off Auto-select at the bottom of the panel.

Using a gateway? Compatible Codex and Claude Code endpoints can use image management too. Requests continue to the endpoint you configured, with the client's model and credentials. The gateway must support the client's API format, image inputs and tool calls; see endpoint support.

Install

Paste this to Codex, or to Claude in Claude Desktop's Code tab:

Install the Context Attachment Manager plugin for me, following https://github.com/chipfighter/context-attachment-manager/blob/main/INSTALL.md

Then restart Codex, or start a new session in Claude. To install or uninstall it yourself, see INSTALL.md.

Privacy

Everything stays on your computer. The plugin sends nothing anywhere beyond the requests Codex and Claude already make.

How we tested

We ran a short-drama keyframe chat in Codex with and without the plugin: nine keyframes, about 32 MB of images. Without the plugin, every time Codex had to send the whole chat again (after a restart, and right after compacting it), the request was 42 MB and never got through. With the plugin, the same request was 0.12 MB, and in this test the model picked the right image both before and after compacting. The method, the numbers and how to run it yourself are in eval.

<p align="center">_{<a href="CHANGELOG.md">Changelog</a> · <a href="CONTRIBUTING.md">Contributing</a> · <a href="LICENSE">MIT License</a>}</p>