dsh-codex: Run Codex Models in DeepSeek Harness with Your ChatGPT Subscription

dsh-codex is a model/inference DSH plugin for DeepSeek Harness that lets you use your existing ChatGPT subscription through OpenAI's Codex sign-in flow, without requiring an OpenAI Platform API key or any dsh source patch. It solves the problem of subscription users not being able to directly use DSH, and provides a full Codex model catalog, streaming, tool calls, reasoning replay, prompt caching, and dsh compaction. The plugin is maintained by Yan-Zero, licensed under Apache-2.0, and last updated in 2026-08.

What core features does the dsh-codex DSH plugin support?

• ChatGPT OAuth from the dsh Settings panel or a standalone CLI, with automatic token refresh.
• The Codex GPT catalog, including vision-capable models when the account offers them.
• Streaming, tool calls, reasoning replay, prompt caching, and dsh compaction through the normal LLM service.
• Codex standalone web search through dsh's existing web_search tool.
• Optional HTTP(S) URL input added to Harness's existing read_image tool.
• An imagegen tool backed by gpt-image-2, with workspace or conversation reference images and automatic workspace output.
• Browser image input through dsh's existing paste and drop controls.

How do I install dsh-codex?

Install the prebuilt bundle from npm into the selected dsh profile:

dsh plugin --profile web add github:Yan-Zero/dsh-codex
dsh web

From a DeepSeek Harness source checkout, use pnpm dsh plugin --profile web add dsh-codex. A local plugin checkout can still be installed with link:/absolute/path/to/dsh-codex for development.

How do I sign in to my ChatGPT account with dsh-codex?

Open Settings → OpenAI Codex → Sign in with ChatGPT. The plugin opens OpenAI's authorization page and completes the localhost callback. The account page shows live Codex quota bars and exact remaining percentages; exact credit balances or workspace limits appear only when the account API supplies them.

For terminal and headless installations, the CLI remains available:

dsh plugin --profile web exec dsh-openai-codex login
dsh plugin --profile web exec dsh-openai-codex login --device-code
dsh plugin --profile web exec dsh-openai-codex status
dsh plugin --profile web exec dsh-openai-codex logout

How do I use dsh-codex in dsh-tui?

For dsh-tui, install the bundle into the same profile:

dsh plugin --profile dsh-tui add dsh-codex

After restarting the TUI, /model lists the openai-codex catalog. With no explicit route or saved selection, the TUI adopts the bundle's gpt-5.6-sol default. Use /codex status|login|logout|usage|config for the account and live settings; the four boolean settings can be changed with /codex set <read-image|imagegen-other-models|websocket-context|native-compaction> <on|off>. Browser login shares the same dsh credential file used by the Web profile.

What image features does dsh-codex support?

Image support uses dsh's durable attachment path:

• paste an image into the Web composer with <kbd>Ctrl</kbd>+<kbd>V</kbd>, or drag and drop it;
• on Windows, paste a clipboard image with <kbd>Ctrl</kbd>+<kbd>V</kbd> in the adapted dsh-tui, or enter @relative/image.png; clipboard images go straight to the attachment store, while path images use the active workspace filesystem;
• ask the model to call read_image with either file_path for a workspace image or url for an HTTP(S) image;
• PNG, JPEG, WebP, and GIF are accepted within the active dsh attachment limits;
• only a model that explicitly advertises image input may receive an image.

imagegen is available to any vision-capable conversation model. The current model writes an ordinary prompt and may select either referenced_image_paths or num_last_images_to_include; the plugin reads these and generates images.

See more DSH plugins at dsh-plugin.org