docs: reasoning effort levels for Codex provider#6798
Merged
blackgirlbytes merged 1 commit intoblock:mainfrom Feb 12, 2026
Merged
docs: reasoning effort levels for Codex provider#6798blackgirlbytes merged 1 commit intoblock:mainfrom
blackgirlbytes merged 1 commit intoblock:mainfrom
Conversation
Add 'xhigh' reasoning effort level to Codex CLI documentation Signed-off-by: Yusuke Shimizu <stm1051212@gmail.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Updates Codex CLI provider documentation to reflect the newly supported xhigh reasoning effort level and clarify model-specific support for none.
Changes:
- Expand the Codex “Features” section to include
xhighand note conditional support fornone. - Update the
CODEX_REASONING_EFFORTenvironment variable documentation to includexhighand mentionnoneconstraints.
| **Features:** | ||
| - Uses OpenAI's GPT-5 series models (gpt-5.2-codex, gpt-5.2, gpt-5.1-codex-max, gpt-5.1-codex-mini) | ||
| - Configurable reasoning effort levels (low, medium, high) | ||
| - Configurable reasoning effort levels (`low`, `medium`, `high`, `xhigh`; `none` is only supported on non-codex models like `gpt-5.2`) |
There was a problem hiding this comment.
This note about none being “only supported on non-codex models” is incomplete/inaccurate relative to the current provider behavior: none on *-codex models is treated as invalid and goose falls back to high with a warning, so the docs should explicitly describe the fallback to avoid user confusion.
Suggested change
| - Configurable reasoning effort levels (`low`, `medium`, `high`, `xhigh`; `none` is only supported on non-codex models like `gpt-5.2`) | |
| - Configurable reasoning effort levels (`low`, `medium`, `high`, `xhigh`; `none` is only supported on non-codex models like `gpt-5.2` and will be treated as invalid on `*-codex` models, where goose falls back to `high` with a warning) |
| | `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`, or `high` | `high` | | ||
| | `CODEX_REASONING_EFFORT` | Reasoning effort level: `low`, `medium`, `high`, or `xhigh` (`none` is only supported on non-codex models like `gpt-5.2`) | `high` | |
There was a problem hiding this comment.
The description for CODEX_REASONING_EFFORT implies none is simply unsupported on codex models, but the implementation falls back to high (with a warning) when none is set for a *-codex model; documenting that fallback behavior here would make the config outcome unambiguous.
Suggested change
| | `CODEX_REASONING_EFFORT` | Reasoning effort level: `low`, `medium`, `high`, or `xhigh` (`none` is only supported on non-codex models like `gpt-5.2`) | `high` | | |
| | `CODEX_REASONING_EFFORT` | Reasoning effort level: `low`, `medium`, `high`, or `xhigh` (`none` is supported on non-codex models like `gpt-5.2`; on `*-codex` models it is accepted but falls back to `high` with a warning) | `high` | |
blackgirlbytes
approved these changes
Feb 12, 2026
tlongwell-block
added a commit
that referenced
this pull request
Feb 12, 2026
…provenance * origin/main: (68 commits) Upgraded npm packages for latest security updates (#7183) docs: reasoning effort levels for Codex provider (#6798) Fix speech local (#7181) chore: add .gooseignore to .gitignore (#6826) Improve error message logging from electron (#7130) chore(deps): bump jsonwebtoken from 9.3.1 to 10.3.0 (#6924) docs: standalone mcp apps and apps extension (#6791) workflow: auto-update cli-commands on release (#6755) feat(apps): Integrate AppRenderer from @mcp-ui/client SDK (#7013) fix(MCP): decode resource content (#7155) feat: reasoning_content in API for reasoning models (#6322) Fix/configure add provider custom headers (#7157) fix: handle keyring fallback as success (#7177) Update process-wrap to 9.0.3 (9.0.2 is yanked) (#7176) feat: support extra field in chatcompletion tool_calls for gemini openai compat (#6184) fix: replace panic with proper error handling in get_tokenizer (#7175) Lifei/smoke test for developer (#7174) fix text editor view broken (#7167) docs: White label guide (#6857) Add PATH detection back to developer extension (#7161) ... # Conflicts: # .github/workflows/nightly.yml
jh-block
added a commit
that referenced
this pull request
Feb 13, 2026
* origin/main: (21 commits) nit: show dir in title, and less... jank (#7138) feat(gemini-cli): use stream-json output and re-use session (#7118) chore(deps): bump qs from 6.14.1 to 6.14.2 in /documentation (#7191) Switch jsonwebtoken to use aws-lc-rs (already used by rustls) (#7189) chore(deps): bump qs from 6.14.1 to 6.14.2 in /evals/open-model-gym/mcp-harness (#7184) Add SLSA build provenance attestations to release workflows (#7097) fix save and run recipe not working (#7186) Upgraded npm packages for latest security updates (#7183) docs: reasoning effort levels for Codex provider (#6798) Fix speech local (#7181) chore: add .gooseignore to .gitignore (#6826) Improve error message logging from electron (#7130) chore(deps): bump jsonwebtoken from 9.3.1 to 10.3.0 (#6924) docs: standalone mcp apps and apps extension (#6791) workflow: auto-update cli-commands on release (#6755) feat(apps): Integrate AppRenderer from @mcp-ui/client SDK (#7013) fix(MCP): decode resource content (#7155) feat: reasoning_content in API for reasoning models (#6322) Fix/configure add provider custom headers (#7157) fix: handle keyring fallback as success (#7177) ...
katzdave
added a commit
that referenced
this pull request
Feb 13, 2026
…ntext * 'main' of github.com:block/goose: feat: add onFallbackRequest handler to McpAppRenderer (#7208) feat: add streaming support for Claude Code CLI provider (#6833) fix: The detected filetype is PLAIN_TEXT, but the provided filetype was HTML (#6885) Add prompts (#7212) Add testing instructions for speech to text (#7185) Diagnostic files copying (#7209) fix: allow concurrent tool execution within the same MCP extension (#7202) fix: handle missing arguments in MCP tool calls to prevent GUI crash (#7143) Filter Apps page to only show standalone Goose Apps (#6811) opt: use static for Regex (#7205) nit: show dir in title, and less... jank (#7138) feat(gemini-cli): use stream-json output and re-use session (#7118) chore(deps): bump qs from 6.14.1 to 6.14.2 in /documentation (#7191) Switch jsonwebtoken to use aws-lc-rs (already used by rustls) (#7189) chore(deps): bump qs from 6.14.1 to 6.14.2 in /evals/open-model-gym/mcp-harness (#7184) Add SLSA build provenance attestations to release workflows (#7097) fix save and run recipe not working (#7186) Upgraded npm packages for latest security updates (#7183) docs: reasoning effort levels for Codex provider (#6798)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
xhighreasoning effort level to Codex CLI documentationrelated: #6522.
Summary
Type of Change