Codex / AI Coding Tools

Codex Context Compaction Fails with Unknown Parameter 'prompt_cache_retention'

Fix Codex context compaction error unknown parameter prompt_cache_retention Includes evidence for Codex troubleshooting demand.

Source-backed Last updated May 14, 2026 3 sources Needs local verification

Category: AI Coding Tools
Error signature: Unknown parameter: 'prompt_cache_retention'
Quick fix: Compare the failing environment with a known working setup, then change one configuration value at a time.
Updated: May 14, 2026
Verification status: Source-backed
Evidence: 3 public source URLs

Before you change production

This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.

Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for Codex, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.

What this error means

Unknown parameter: 'prompt_cache_retention' is a Codex failure pattern reported for developers trying to fix codex context compaction error unknown parameter prompt_cache_retention. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

38 comments on #17809. Error occurs in both macOS app and CLI. API returns invalid_request_error with code 'unknown_parameter' for prompt_cache_retention. Also affects third-party proxies (new-api #4462). Affects ChatGPT Pro users.

Common causes

Codex is OpenAI's paid coding tool (ChatGPT Pro/Plus). Context compaction is a core feature that breaks on all threads, preventing long sessions. The error is an API-level incompatibility that users cannot fix themselves.
38 comments on #17809. Error occurs in both macOS app and CLI. API returns invalid_request_error with code 'unknown_parameter' for prompt_cache_retention. Also affects third-party proxies (new-api #4462). Affects ChatGPT Pro users.

Quick fixes

Confirm the exact error signature matches Unknown parameter: 'prompt_cache_retention'.
Check the Codex account, local tool state, and provider configuration involved in the failing workflow.
Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

Verify the command, editor, extension, or API client that produced the error.
Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

Capture the exact error message and the command, editor action, or request that triggered it.
Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
Review the source evidence below and compare it with your environment.
Apply one change at a time and rerun the smallest failing action.
Keep the working fix documented for the team or deployment environment.

How to prevent it

Keep provider/tool configuration documented.
Record non-secret diagnostics such as tool version, provider name, model name, and command path.
Add a lightweight check before CI or production workflows depend on the tool.

Diagnostic flow for this page

Match Unknown parameter: 'prompt_cache_retention' exactly before applying the quick fix.
Compare the failing environment with Codex versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.

FAQ

What does Unknown parameter: 'prompt_cache_retention' mean in Codex?

Unknown parameter: 'prompt_cache_retention' indicates the workflow described by "Codex Context Compaction Fails with Unknown Parameter 'prompt_cache_retention'" failed in a AI Coding Tools context. Start by confirming the exact signature and the component that emitted it.

What should I check first for Unknown parameter: 'prompt_cache_retention'?

Check whether this cause matches your environment: Codex is OpenAI's paid coding tool (ChatGPT Pro/Plus). Context compaction is a core feature that breaks on all threads, preventing long sessions. The error is an API-level incompatibility that users cannot fix themselves.

Is the Unknown parameter: 'prompt_cache_retention' guidance source-backed?

The "Codex Context Compaction Fails with Unknown Parameter 'prompt_cache_retention'" page is labeled source-backed. It has 3 public source URLs from github.com, so use that evidence status when deciding how much additional verification you need.

When should I avoid the quick fix for Unknown parameter: 'prompt_cache_retention'?

For "Codex Context Compaction Fails with Unknown Parameter 'prompt_cache_retention'", avoid applying "Compare the failing environment with a known working setup, then change one configuration value at a time." when the error text differs, the affected version or provider is different, or the change would touch credentials, billing, DNS, production deploy settings, or irreversible data.

What should I collect before debugging Unknown parameter: 'prompt_cache_retention'?

For "Codex Context Compaction Fails with Unknown Parameter 'prompt_cache_retention'", collect the failing Codex command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.