DeepSeek Harness Plugin: dsh-llm-codex
`dsh-llm-codex` is a DeepSeek Harness plugin that integrates by mounting and registers Codex CLI as an LLM provider. It supports locally prioritized Codex invocation (reusing the existing login state) and falls back to OpenAI-compatible endpoints, exposing Codex as a text-generation route rather than an agent. The plugin reads the model list from the Codex cache and supports sandbox mode for permission control. It is enabled by configuring a mount after installation and is suitable for scenarios that require using Codex capabilities within DSH, although the limitations of macOS and nested sandbox environments should be noted.
Read Moredsh-llm-codex: DeepSeek Harness ChatGPT Codex Login and Model Directory Plugin
`dsh-llm-codex` is a DeepSeek Harness plugin developed by NOirBRight, aiming to integrate ChatGPT Codex's login, model directory, and capability management into a single module. Its core functions include: managing Codex sessions via OAuth (stored locally in `codex-oauth.json`); providing a Codex card on the settings page that displays usage limits; maintaining a default model directory containing the gpt-5.6 series and its Fast version, supporting acceleration via `service_tier: priority`; and supporting Picker rows for 1M or specific context suffixes (e.g., `-<n>k`) to adjust the compression budget. The plugin also offers optional capabilities that are disabled by default, such as Search.
Read More