mirror of
https://github.com/openai/codex.git
synced 2026-09-16 12:13:30 +00:00
39a6a84097
This PR adds support for loading [skills](https://developers.openai.com/codex/skills) from `.agents/skills/`. - Issue: https://github.com/agentskills/agentskills/issues/15 - Motivation: When skills live on the filesystem, sharing them across agents is awkward and often ends up requiring symlinks/duplication. A single location under `.agents/` makes it easier to share skills. - Loading from `.codex/skills/` will remain but will be deprecated soon. The change only applies to the [REPO scope](https://developers.openai.com/codex/skills#where-to-save-skills). - Documentation will be updated before this change is live. Testing with skills in two locations of this repo: <img width="960" height="152" alt="image" src="https://github.com/user-attachments/assets/28975ff9-7363-46dd-ad40-f4c7bfdb8234" /> When starting Codex with CWD in `$repo_root` (should only pick up at root): <img width="513" height="143" alt="image" src="https://github.com/user-attachments/assets/389e1ea7-020c-481e-bda0-ce58562db59f" /> When starting Codex with CWD in `$repo_root/codex-rs` (should pick up at cwd and crawl up to root): <img width="552" height="177" alt="image" src="https://github.com/user-attachments/assets/a5beb8de-11b4-45ed-8660-80707c77006a" />
codex-core config loader
This module is the canonical place to load and describe Codex configuration layers (user config, CLI/session overrides, managed config, and MDM-managed preferences) and to produce:
- An effective merged TOML config.
- Per-key origins metadata (which layer “wins” for a given key).
- Per-layer versions (stable fingerprints) used for optimistic concurrency / conflict detection.
Public surface
Exported from codex_core::config_loader:
load_config_layers_state(codex_home, cwd_opt, cli_overrides, overrides, cloud_requirements) -> ConfigLayerStackConfigLayerStackeffective_config() -> toml::Valueorigins() -> HashMap<String, ConfigLayerMetadata>layers_high_to_low() -> Vec<ConfigLayer>with_user_config(user_config) -> ConfigLayerStack
ConfigLayerEntry(one layer’s{name, config, version, disabled_reason};namecarries source metadata)LoaderOverrides(test/override hooks for managed config sources)merge_toml_values(base, overlay)(public helper used elsewhere)
Layering model
Precedence is top overrides bottom:
- MDM managed preferences (macOS only)
- System managed config (e.g.
managed_config.toml) - Session flags (CLI overrides, applied as dotted-path TOML writes)
- User config (
config.toml)
Layers with a disabled_reason are still surfaced for UI, but are ignored when
computing the effective config and origins metadata. This is what
ConfigLayerStack::effective_config() implements.
Typical usage
Most callers want the effective config plus metadata:
use codex_core::config_loader::{load_config_layers_state, LoaderOverrides};
use codex_utils_absolute_path::AbsolutePathBuf;
use toml::Value as TomlValue;
let cli_overrides: Vec<(String, TomlValue)> = Vec::new();
let cwd = AbsolutePathBuf::current_dir()?;
let layers = load_config_layers_state(
&codex_home,
Some(cwd),
&cli_overrides,
LoaderOverrides::default(),
None,
).await?;
let effective = layers.effective_config();
let origins = layers.origins();
let layers_for_ui = layers.layers_high_to_low();
Internal layout
Implementation is split by concern:
state.rs: public types (ConfigLayerEntry,ConfigLayerStack) + merge/origins convenience methods.layer_io.rs: readingconfig.toml, managed config, and managed preferences inputs.overrides.rs: CLI dotted-path overrides → TOML “session flags” layer.merge.rs: recursive TOML merge.fingerprint.rs: stable per-layer hashing and per-key origins traversal.macos.rs: managed preferences integration (macOS only).