docs: for unified thinking#7817
Conversation
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a92b8a4cb3
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | `GOOSE_MODEL` | Model to use (only known models are passed to CLI) | `gpt-5.2-codex` | | ||
| | `CODEX_COMMAND` | Path to the Codex CLI command | `codex` | | ||
| | `CODEX_REASONING_EFFORT` | Reasoning effort level: `low`, `medium`, `high`, or `xhigh` (`none` is only supported on non-codex models like `gpt-5.2`) | `high` | | ||
| | `GOOSE_THINKING_EFFORT` | Unified thinking effort (`off`, `low`, `medium`, `high`, `max`). Mapped to Codex CLI effort levels (`none/low/medium/high/xhigh`). | `high` | |
There was a problem hiding this comment.
Restore documented Codex effort env var name
This table now instructs users to configure GOOSE_THINKING_EFFORT, but the current implementation still only defines and reads CODEX_REASONING_EFFORT (crates/goose/src/config/base.rs:1012 and config.get_codex_reasoning_effort() in crates/goose/src/providers/codex.rs:620-623). As a result, users who follow this doc change will see their effort setting ignored and the provider will continue using the default high, which can skew behavior and experiment results.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
this is just because the other PR isn't merged yet
Signed-off-by: Cameron Yick <cameron.yick@datadoghq.com>
Summary
Updates documentation to reference the unified
GOOSE_THINKING_EFFORTenvironment variable across all providers. Related to #7628