Codex Desktop Context Compact Error
Resolved 💬 2 comments Opened May 29, 2026 by xzltc Closed Jun 29, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of the Codex App are you using (From “About Codex” dialog)?
26.519.81530
What subscription do you have?
Plus
What platform is your computer?
Microsoft Windows NT 10.0.26100.0 x64
What issue are you seeing?
The same issue occurs every time the conversation context is automatically compressed. This appears to be a server-side problem.
Example 1Error running remote compact task: stream disconnected before completion: unknown variant auto, expected high or original at line 1 column 72088.
Example 2Error running remote compact task: stream disconnected before completion: unknown variant auto, expected high or original at line 1 column 96342
What steps can reproduce the bug?
When exceeding the default context length
What is the expected behavior?
<img width="722" height="798" alt="Image" src="https://github.com/user-attachments/assets/77a6b4f6-eb8e-4b61-8e5a-0d13d2a5705c" />
Additional information
_No response_
2 Comments
up
[ItemParam] [input[659]] [invalid_enum_value] Invalid value: 'context_compaction'. Supported values are: 'additional_tools', 'apply_patch_call', 'apply_patch_call_output', 'code_interpreter_call', 'compaction', 'compaction_trigger', 'computer_call', 'computer_call_output', 'custom_tool_call', 'custom_tool_call_output', 'file_search_call', 'function_call', 'function_call_output', 'image_generation_call', 'item_reference', 'local_shell_call', 'local_shell_call_output', 'mcp_approval_request', 'mcp_approval_response', 'mcp_call', 'mcp_list_tools', 'message', 'reasoning', 'shell_call', 'shell_call_output', 'tool_search_call', 'tool_search_output', and 'web_search_call'.
Thanks for reporting this problem. Until recently, Codex used a separate endpoint and server-side logic for compaction. We recently switched to a more robust approach where the compaction logic is moved locally using the same endpoint as normal turns. This eliminates "remote compaction" errors and increases the stability and reliability of compaction operations. If you see further problems with compaction, please use
/feedbackand open a new bug report.