From 1f5638b0f315b1fc1ad523105b975a1851b37b28 Mon Sep 17 00:00:00 2001 From: Michael Bolin Date: Tue, 19 Aug 2025 11:39:31 -0700 Subject: [PATCH] docs: document writable_roots for sandbox_workspace_write (#2464) As discovered on https://github.com/openai/codex/issues/2444, this was missing from the docs. --- codex-rs/config.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/codex-rs/config.md b/codex-rs/config.md index 80ef1466..8c2a7831 100644 --- a/codex-rs/config.md +++ b/codex-rs/config.md @@ -149,6 +149,7 @@ approval_policy = "untrusted" ``` If you want to be notified whenever a command fails, use "on-failure": + ```toml # If the command fails when run in the sandbox, Codex asks for permission to # retry the command outside the sandbox. @@ -156,12 +157,14 @@ approval_policy = "on-failure" ``` If you want the model to run until it decides that it needs to ask you for escalated permissions, use "on-request": + ```toml # The model decides when to escalate approval_policy = "on-request" ``` Alternatively, you can have the model run until it is done, and never ask to run a command with escalated permissions: + ```toml # User is never prompted: if the command fails, Codex will automatically try # something out. Note the `exec` subcommand always uses this mode. @@ -278,6 +281,9 @@ sandbox_mode = "workspace-write" exclude_tmpdir_env_var = false exclude_slash_tmp = false +# Optional list of _additional_ writable roots beyond $TMPDIR and /tmp. +writable_roots = ["/Users/YOU/.pyenv/shims"] + # Allow the command being run inside the sandbox to make outbound network # requests. Disabled by default. network_access = false @@ -495,10 +501,12 @@ hide_agent_reasoning = true # defaults to false Surfaces the model’s raw chain-of-thought ("raw reasoning content") when available. Notes: + - Only takes effect if the selected model/provider actually emits raw reasoning content. Many models do not. When unsupported, this option has no visible effect. - Raw reasoning may include intermediate thoughts or sensitive context. Enable only if acceptable for your workflow. Example: + ```toml show_raw_agent_reasoning = true # defaults to false ```