CodeX v0.148.0 cannot use GPT-5.6 Sol

OpenAI's Codex CLI version 0.148.0 breaks every turn when using the gpt-5.6-sol model because it still sends the unsupported prompt_cache_retention parameter, causing an invalid_request_error. A user reported that 0.147.0 worked flawlessly with 45 turns and 0 errors from Aug 14-18, while 0.148.0 produced 3 errors in 3 turns on Aug 19. The issue is filed on GitHub as #39397, and the workaround is to downgrade to 0.147.0 or switch to gpt-5.5.

- Notifications /login?return to=%2Fopenai%2Fcodex You must be signed in to change notification settings - Fork 16.2k /login?return to=%2Fopenai%2Fcodex 0.148.0 sends prompt cache retention on gpt-5.6-sol and every turn fails 39397 CLIIssues related to the Codex CLI https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22CLI%22 Issues related to the Codex CLI bugSomething isn't working https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22bug%22 Something isn't working configIssues involving config.toml, config keys, config merging, or config updates https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22config%22 Issues involving config.toml, config keys, config merging, or config updates windows-osIssues related to Codex on Windows systems https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22windows-os%22 Issues related to Codex on Windows systems Description I updated to 0.148.0 today and every single turn now fails with the below. { "error": { "message": "prompt cache retention is not supported on this model", "type": "invalid request error", "param": "prompt cache retention", "code": "invalid parameter" } } Codex is still sending prompt cache retention on gpt-5.6-sol. That model does not accept it anymore. I checked my own rollout logs. Same machine, same model, same config, same auth. The only thing that changed is the version. 0.147.0 + gpt-5.6-sol = 10 sessions, 45 turns, 0 errors Aug 14-18 0.148.0 + gpt-5.6-sol = 1 session, 3 turns, 3 errors Aug 19 On the failing day my update check finished at 02:12Z, the first 0.148.0 session started at 02:14Z, and all 3 of its turns errored at 02:16Z, 02:34Z and 02:41Z. To reproduce: 1- npm install -g @openai/codex@0.148.0 2- set model = "gpt-5.6-sol" in config.toml 3- send any prompt Environment: Codex CLI 0.148.0 from npm, win32-x64, Windows 11 10.0.26200, Node v22.22.3, model reasoning effort xhigh, ChatGPT account auth and not an API key. Default ChatGPT backend, I did not test Azure or a custom model provider. Just to be clear this is NOT the 0.120.0 compaction bug 17809 https://github.com/openai/codex/issues/17809 to 17819 https://github.com/openai/codex/issues/17819 , all closed . Those said "Unknown parameter" and only happened during compaction. Mine says "is not supported on this model" and it happens on every normal turn. My first failure was at 154k tokens in a 258k window so there was no compaction involved. One thing that makes this confusing to diagnose. When a turn has already started tool calls the work still finishes, but the final message never comes back, so it reads as stuck instead of failed. A turn with no tool calls dies in 4 seconds. The fix is to gate prompt cache retention on the model instead of always sending it. Your own repo already says this in codex-rs/skills/src/assets/samples/openai-docs/references/upgrading-to-gpt-5p6-sol.md: Treat the older prompt cache retention shape as deprecated Same pattern as 31882 https://github.com/openai/codex/issues/31882 where use responses lite and multi agent version are hardcoded for sol/terra/luna. A shared capability table would close both. Workaround for anyone else hitting this, downgrade with npm install -g @openai/codex@0.147.0. Switching to gpt-5.5 also works because that model still accepts the parameter. 0.149.0-alpha.1 was cut at 2026-08-19T00:54Z and I do not see a related commit on main, so I expect it is still broken. Related: 31882 https://github.com/openai/codex/issues/31882 , 25604 https://github.com/openai/codex/issues/25604 , 35300 https://github.com/openai/codex/issues/35300 . Thank you Metadata Metadata Assignees Labels CLIIssues related to the Codex CLI https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22CLI%22 Issues related to the Codex CLI bugSomething isn't working https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22bug%22 Something isn't working configIssues involving config.toml, config keys, config merging, or config updates https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22config%22 Issues involving config.toml, config keys, config merging, or config updates windows-osIssues related to Codex on Windows systems https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22windows-os%22 Issues related to Codex on Windows systems