mirror of
https://github.com/openai/codex.git
synced 2026-09-17 12:23:33 +00:00
043a059919
This adds config.toml-defined model aliases that map to provider model slugs while applying alias-specific context settings for the active session. - added custom_models config entries plus schema and docs coverage - taught ModelsManager to resolve aliases to a provider-facing request_model while preserving the user-facing alias slug - applied alias-specific context_window and model_auto_compact_token_limit overrides during model info resolution - updated session/test plumbing and added regression coverage for alias resolution with local and remote model catalogs Model selection and per-session context overrides already flow through ModelsManager and Config. Resolving aliases there keeps the provider slug separate from the user-facing alias while reusing the existing override plumbing. - just write-config-schema - just fmt - cargo test -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server - cargo test -p codex-tui - cargo test -p codex-protocol -p codex-core (same two existing seatbelt failures remained in this environment: create_seatbelt_args_with_read_only_git_pointer_file and create_seatbelt_args_with_read_only_git_and_codex_subpaths) - just fix -p codex-core -p codex-protocol -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server -p codex-tui
68 lines
2.7 KiB
Markdown
68 lines
2.7 KiB
Markdown
# Configuration
|
|
|
|
For basic configuration instructions, see [this documentation](https://developers.openai.com/codex/config-basic).
|
|
|
|
For advanced configuration instructions, see [this documentation](https://developers.openai.com/codex/config-advanced).
|
|
|
|
For a full configuration reference, see [this documentation](https://developers.openai.com/codex/config-reference).
|
|
|
|
## Connecting to MCP servers
|
|
|
|
Codex can connect to MCP servers configured in `~/.codex/config.toml`. See the configuration reference for the latest MCP server options:
|
|
|
|
- https://developers.openai.com/codex/config-reference
|
|
|
|
## Apps (Connectors)
|
|
|
|
Use `$` in the composer to insert a ChatGPT connector; the popover lists accessible
|
|
apps. The `/apps` command lists available and installed apps. Connected apps appear first
|
|
and are labeled as connected; others are marked as can be installed.
|
|
|
|
## Notify
|
|
|
|
Codex can run a notification hook when the agent finishes a turn. See the configuration reference for the latest notification settings:
|
|
|
|
- https://developers.openai.com/codex/config-reference
|
|
|
|
When Codex knows which client started the turn, the legacy notify JSON payload also includes a top-level `client` field. The TUI reports `codex-tui`, and the app server reports the `clientInfo.name` value from `initialize`.
|
|
|
|
## JSON Schema
|
|
|
|
The generated JSON Schema for `config.toml` lives at `codex-rs/core/config.schema.json`.
|
|
|
|
## SQLite State DB
|
|
|
|
Codex stores the SQLite-backed state DB under `sqlite_home` (config key) or the
|
|
`CODEX_SQLITE_HOME` environment variable. When unset, WorkspaceWrite sandbox
|
|
sessions default to a temp directory; other modes default to `CODEX_HOME`.
|
|
|
|
## Notices
|
|
|
|
Codex stores "do not show again" flags for some UI prompts under the `[notice]` table.
|
|
|
|
## Plan mode defaults
|
|
|
|
`plan_mode_reasoning_effort` lets you set a Plan-mode-specific default reasoning
|
|
effort override. When unset, Plan mode uses the built-in Plan preset default
|
|
(currently `medium`). When explicitly set (including `none`), it overrides the
|
|
Plan preset. The string value `none` means "no reasoning" (an explicit Plan
|
|
override), not "inherit the global default". There is currently no separate
|
|
config value for "follow the global default in Plan mode".
|
|
|
|
## Custom model aliases
|
|
|
|
You can add aliases to the model picker via `custom_models` in `~/.codex/config.toml`.
|
|
Each alias maps to a provider-facing model slug and can override context settings:
|
|
|
|
```toml
|
|
[custom_models."gpt-5.4 1m"]
|
|
model = "gpt-5.4"
|
|
model_context_window = 1000000
|
|
model_auto_compact_token_limit = 900000
|
|
```
|
|
|
|
When selected, Codex sends `model = "gpt-5.4"` to the backend while using your
|
|
alias-specific context overrides for that session.
|
|
|
|
Ctrl+C/Ctrl+D quitting uses a ~1 second double-press hint (`ctrl + c again to quit`).
|