codex - 💡(How to fix) Fix Unknown parameter: 'prompt_cache_retention [3 comments, 4 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openai/codex#17815Fetched 2026-04-15 06:27:41
View on GitHub
Comments
3
Participants
4
Timeline
10
Reactions
0
Author
Timeline (top)
commented ×3labeled ×3cross-referenced ×2closed ×1

Error Message

■ Error running remote compact task: { "error": {

RAW_BUFFERClick to expand / collapse

What version of Codex CLI is running?

codex-cli 0.120.0

What subscription do you have?

pro

Which model were you using?

gpt-5.4 default

What platform is your computer?

Linux 6.14.8-2-pve x86_64 x86_64

What terminal emulator and version are you using (if applicable)?

gnome-terminal

What issue are you seeing?

prompts kept getting met with

■ Error running remote compact task: { "error": { "message": "Unknown parameter: 'prompt_cache_retention'.", "type": "invalid_request_error", "param": "prompt_cache_retention", "code": "unknown_parameter" } }

After a few minutes, it seems to have resolved, with "context compacted". Perhaps back end trouble?

What steps can reproduce the bug?

Uploaded thread: 019d8a4a-fe19-79d1-957c-3590eafb524e

What is the expected behavior?

No response

Additional information

No response

extent analysis

TL;DR

The issue is likely due to an unknown parameter 'prompt_cache_retention' in the request, which may be a temporary backend issue or a version compatibility problem.

Guidance

  • Verify the Codex CLI version (0.120.0) and check if there are any known issues or updates related to the 'prompt_cache_retention' parameter.
  • Review the uploaded thread (019d8a4a-fe19-79d1-957c-3590eafb524e) to see if there are any specific patterns or conditions that trigger the error.
  • Check the documentation for the gpt-5.4 default model to see if the 'prompt_cache_retention' parameter is supported or if there are any specific requirements for its usage.
  • Consider reaching out to the support team or checking the community forums for similar issues, as the error seems to be related to a temporary backend issue that resolved itself after a few minutes.

Notes

The issue seems to be related to a specific parameter and model, so the solution may depend on the specific use case and configuration. More information about the context and the specific request being made would be helpful to provide a more accurate solution.

Recommendation

Apply workaround: Try removing or modifying the 'prompt_cache_retention' parameter in the request to see if it resolves the issue, as the error message suggests that this parameter is unknown.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING