mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
## DISCLAIMER This is experimental and no production service must rely on this ## Why Built-in MCPs are product-owned runtime capabilities, but they were previously flattened into the same config-backed stdio path as user-configured servers. That made them depend on a hidden `codex builtin-mcp` re-exec path, exposed them through config-oriented CLI flows, and erased distinctions the runtime needs to preserve—most notably whether an MCP call should count as external context for memory-mode pollution. ## What changed - Model product-owned built-ins separately from config-backed MCP servers via `BuiltinMcpServer` and `EffectiveMcpServer`. - Launch built-ins in process through a reusable async transport instead of the hidden `builtin-mcp` stdio subcommand. - Keep config-oriented CLI operations such as `codex mcp list/get/login/logout` scoped to configured servers, while merging built-ins only into the effective runtime server set. - Retain server metadata after launch so parallel-tool support and context classification come from the live server set; built-in `memories` is now classified as local Codex state rather than external context. ## Test plan - `cargo test -p codex-mcp` - `cargo test -p codex-core --test suite builtin_memories_mcp_call_does_not_mark_thread_memory_mode_polluted_when_configured` --------- Co-authored-by: Codex <noreply@openai.com>
16 lines
388 B
Rust
16 lines
388 B
Rust
//! MCP access to Codex memories.
|
|
//!
|
|
//! This crate only exposes tools for discovering and reading memory files. The
|
|
//! policy that tells a model when to use those tools is injected elsewhere.
|
|
|
|
pub mod backend;
|
|
pub mod local;
|
|
|
|
mod schema;
|
|
mod server;
|
|
|
|
pub use local::LocalMemoriesBackend;
|
|
pub use server::MemoriesMcpServer;
|
|
pub use server::run_server;
|
|
pub use server::run_stdio_server;
|