openai / openai/codex

Codex is literally unusable, i always got prompt_cache_retention is not supported on this model

Open
#39,442 1 comment 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What issue are you seeing?

Always got this everytime sending message,

Error: OpenAI API error (400): {"message":"prompt_cache_retention is not supported on this
model","type":"invalid_request_error","param":"prompt_cache_retention","code":"invalid_parameter"}

Using pi harness with chatgpt subs, using gpt-5.6-luna max

it just start happening today, yesterday seems fine

What steps can reproduce the bug?

use codex like normal, this happen whenever use codex or pi

What is the expected behavior?

should continue to work without throwing those errors

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the error by sending a message through Codex or the pi harness, then trace where the OpenAI request includes prompt_cache_retention. Confirm which model configurations reject that parameter and verify that the affected workflow completes without the 400 error.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
api, cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.