b0bdc04c30
It's pretty amazing we have gotten here without the ability for the model to see image content from MCP tool calls. This PR builds off of 4391 and fixes #4819. I would like @KKcorps to get adequete credit here but I also want to get this fix in ASAP so I gave him a week to update it and haven't gotten a response so I'm going to take it across the finish line. This test highlights how absured the current situation is. I asked the model to read this image using the Chrome MCP <img width="2378" height="674" alt="image" src="https://github.com/user-attachments/assets/9ef52608-72a2-4423-9f5e-7ae36b2b56e0" /> After this change, it correctly outputs: > Captured the page: image dhows a dark terminal-style UI labeled `OpenAI Codex (v0.0.0)` with prompt `model: gpt-5-codex medium` and working directory `/codex/codex-rs` (and more) Before this change, it said: > Took the full-page screenshot you asked for. It shows a long, horizontally repeating pattern of stylized people in orange, light-blue, and mustard clothing, holding hands in alternating poses against a white background. No text or other graphics-just rows of flat illustration stretching off to the right. Without this change, the Figma, Playwright, Chrome, and other visual MCP servers are pretty much entirely useless. I tested this change with the openai respones api as well as a third party completions api
codex-protocol
This crate defines the "types" for the protocol used by Codex CLI, which includes both "internal types" for communication between codex-core and codex-tui, as well as "external types" used with codex app-server.
This crate should have minimal dependencies.
Ideally, we should avoid "material business logic" in this crate, as we can always introduce Ext-style traits to add functionality to types in other crates.