git404hub

what is cpa-plugin-codexcomp fr?

uf-hy/cpa-plugin-codexcomp — explained in plain English

Analysis updated 2026-05-18

74GoAudience · developerComplexity · 4/5LicenseSetup · moderate

tl;dr

A Go plugin for CLIProxyAPI that detects when certain GPT-5.5 models cut off their reasoning mid-thought and automatically continues them.

vibe map

mindmap
  root((CodexComp))
    What it does
      Detects reasoning truncation
      Auto-continues the model
      Folds rounds into one response
    Tech stack
      Go
      CLIProxyAPI
    Use cases
      Fix gpt-5.5 truncation
      Reduce degraded answers
      Benchmark truncation fixes
    Audience
      CLIProxyAPI users
      AI agent developers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Automatically fix truncated reasoning output from gpt-5.5 and related models in a CLIProxyAPI setup

VIBE 2

Reduce cases where an AI coding agent gives a worse answer because its reasoning was cut short

VIBE 3

Benchmark whether reasoning truncation is affecting your own model responses

VIBE 4

Route OpenAI and Anthropic-format client requests through a single proxy with this fix applied

what's the stack?

GoCLIProxyAPI

how it stacks up fr

uf-hy/cpa-plugin-codexcompchojs23/lazyagentgastownhall/wasteland
Stars747376
LanguageGoGoGo
Last pushed2026-06-20
MaintenanceMaintained
Setup difficultymoderatemoderate
Complexity4/52/53/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · moderate time til it works · 30min

Requires an existing CLIProxyAPI installation, the plugin is installed into it rather than run standalone.

MIT license: free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.

in plain english

CodexComp is a plugin for CLIProxyAPI, a proxy tool that sits between AI coding agents and language model providers. Its job is to detect and fix a specific technical problem where certain models, by default gpt-5.5 and two related variants called luna and terra, sometimes cut off their internal reasoning at an oddly precise token count. The README explains that when this cutoff happens, the model's answers can become noticeably worse, since it was not actually finished thinking through the problem. The plugin works by watching streaming responses from these models. If it detects that the model's reasoning stopped at the telltale truncated point, and the response includes reusable encrypted reasoning content, it automatically sends a follow up request that replays the original question along with everything the model already thought, asking it to continue from where it left off. It can do this up to three times by default. All of these extra rounds are combined into what looks like a single normal response, so the client application calling the model never sees anything unusual happen. Because some of these models can take up to thirty seconds to produce their first piece of output when reasoning hard, and many client tools time out well before that, the plugin uses an asynchronous streaming approach. It returns response headers immediately and forwards each piece of the model's output to the client as soon as it arrives from the upstream provider. The plugin only intercepts streaming requests for the configured models, and only when the request format matches certain conditions, so it stays out of the way of unrelated requests. It compares itself in the README to two earlier Python based tools that solve a similar problem, noting that this version is written in Go and loads directly inside CLIProxyAPI as a plugin, rather than running as its own separate proxy process. It is distributed under the MIT license, is installable through the CLIProxyAPI plugin store or as a manually downloaded binary, and includes a benchmark script for testing whether it is actually fixing the truncation problem on your setup.

prompts (copy fr)

prompt 1
Explain what it means for a language model's reasoning to be truncated mid-response
prompt 2
Help me install and configure a CLIProxyAPI plugin from a GitHub releases zip file
prompt 3
Show me how to write a Go plugin that intercepts streaming HTTP responses using a C ABI shared library
prompt 4
Walk me through setting up an async streaming proxy that forwards SSE events to a client as they arrive

Frequently asked questions

what is cpa-plugin-codexcomp fr?

A Go plugin for CLIProxyAPI that detects when certain GPT-5.5 models cut off their reasoning mid-thought and automatically continues them.

What language is cpa-plugin-codexcomp written in?

Mainly Go. The stack also includes Go, CLIProxyAPI.

What license does cpa-plugin-codexcomp use?

MIT license: free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.

How hard is cpa-plugin-codexcomp to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is cpa-plugin-codexcomp for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.