Skip to content

DeepSeek integration with cc-switch: Codex deep integration feature request

Quick fix

This requests deep integration of DeepSeek with Codex. The original post has no verifiable solution; closure does not prove implementation.

Error output
DeepSeek 接入 cc-switch
English translation

DeepSeek integration with cc-switch

This is a feature request with no actual error reported. It states that Codex uses OpenAI Responses API while DeepSeek uses Chat Completions API, and proposes bidirectional conversion of requests and SSE responses at the proxy layer, including handling structural differences between tool_calls and function_call.

The request also includes preserving and caching reasoning_content, mapping reasoning/summary fields, retrieving model lists and configuring model mappings, plus Prompt caching, balance queries, streaming checks, and log tracing. The author references exploratory implementation work on the develop/ds-codex branch, but the original post provides no verification results or release version. The closed issue does not establish that these features are implemented.

  1. The original post provides no verifiable solution, so it cannot support a ready-to-use configuration for integrating DeepSeek with Codex.

  2. Follow the source discussion in issue #3187 to check the implementation and verification status of bidirectional API conversion, reasoning_content, and model mapping. The referenced branch and commits are exploratory implementation work only.

ToolCodex
VersionUnknown
PlatformsUnknown

This page is distilled from 1 real issues

(No FAQ yet)

This is an unofficial community wiki with no affiliation to the cc-switch authors or the project itself. Its content is compiled from the project's public GitHub issues. This site distributes no software.