mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
Charley Cunningham
226241f035
## Summary - move `guardian_developer_instructions` from managed config into workspace-managed `requirements.toml` - have guardian continue using the override when present and otherwise fall back to the bundled local guardian prompt - keep the generalized prompt-quality improvements in the shared guardian default prompt - update requirements parsing, layering, schema, and tests for the new source of truth ## Context This replaces the earlier managed-config / MDM rollout plan. The intended rollout path is workspace-managed requirements, including cloud enterprise policies, rather than backend model metadata, Statsig, or Jamf-managed config. That keeps the default/fallback behavior local to `codex-rs` while allowing faster policy updates through the enterprise requirements plane. This is intentionally an admin-managed policy input, not a user preference: the guardian prompt should come either from the bundled `codex-rs` default or from enterprise-managed `requirements.toml`, and normal user/project/session config should not override it. ## Updating The OpenAI Prompt After this lands, the OpenAI-specific guardian prompt should be updated through the workspace Policies UI at `/codex/settings/policies` rather than through Jamf or codex-backend model metadata. Operationally: - open the workspace Policies editor as a Codex admin - edit the default `requirements.toml` policy, or a higher-precedence group-scoped override if we ever want different behavior for a subset of users - set `guardian_developer_instructions = """..."""` to the full OpenAI-specific guardian prompt text - save the policy; codex-backend stores the raw TOML and `codex-rs` fetches the effective requirements file from `/wham/config/requirements` When updating the OpenAI-specific prompt, keep it aligned with the shared default guardian policy in `codex-rs` except for intentional OpenAI-only additions. ## Testing - `cargo check --tests -p codex-core -p codex-config -p codex-cloud-requirements --message-format short` - `cargo run -p codex-core --bin codex-write-config-schema` - `cargo fmt` - `git diff --check` Co-authored-by: Codex <noreply@openai.com>
226241f035
·
2026-03-17 22:05:41 -07:00
History
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).