docs: reasoning effort levels for Codex provider (#6798)

Signed-off-by: Yusuke Shimizu <stm1051212@gmail.com>
This commit is contained in:
bruwbird
2026-02-13 02:59:44 +09:00
committed by GitHub
parent d2158fa3b4
commit dd98e8757b
+2 -2
View File
@@ -67,7 +67,7 @@ The Codex provider integrates with OpenAI's [Codex CLI tool](https://developers.
**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`)
- Optional skills support for enhanced capabilities
- JSON output parsing for structured responses
- Automatic filtering of goose extensions from system prompts
@@ -310,7 +310,7 @@ The following models are recognized and passed to the Claude CLI via the `--mode
| `GOOSE_PROVIDER` | Set to `codex` to use this provider | None |
| `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` |
| `CODEX_ENABLE_SKILLS` | Enable Codex skills: `true` or `false` | `true` |
| `CODEX_SKIP_GIT_CHECK` | Skip git repository requirement: `true` or `false` | `false` |