nicholasclark-openai
2bee37fe69
## Summary Some background. We're looking to instrument GA turns end to end. Right now a big gap is grouping mcp tool calls with their codex sessions. We send session id and turn id headers to the responses call but not the mcp/wham calls. Ideally we could pass the args as headers like with responses, but given the setup of the rmcp client, we can't send as headers without either changing the rmcp package upstream to allow per request headers or introducing a mutex which break concurrency. An earlier attempt made the assumption that we had 1 client per thread, which allowed us to set headers at the start of a turn. @pakrym mentioned that this assumption might break in the near future. So the solution now is to package the turn metadata/session id into the _meta field in the post body and pull out in codex-backend. - send turn metadata to MCP servers via `tools/call` `_meta` instead of assuming per-thread request headers on shared clients - preserve the existing `_codex_apps` metadata while adding `x-codex-turn-metadata` for all MCP tool calls - extend tests to cover both custom MCP servers and the codex apps search flow --------- Co-authored-by: Codex <noreply@openai.com>
codex-core
This crate implements the business logic for Codex. It is designed to be used by the various Codex UIs written in Rust.
Dependencies
Note that codex-core makes some assumptions about certain helper utilities being available in the environment. Currently, this support matrix is:
macOS
Expects /usr/bin/sandbox-exec to be present.
When using the workspace-write sandbox policy, the Seatbelt profile allows
writes under the configured writable roots while keeping .git (directory or
pointer file), the resolved gitdir: target, and .codex read-only.
Network access and filesystem read/write roots are controlled by
SandboxPolicy. Seatbelt consumes the resolved policy and enforces it.
Seatbelt also supports macOS permission-profile extensions layered on top of
SandboxPolicy:
- no extension profile provided:
keeps legacy default preferences read access (
user-preference-read). - extension profile provided with no
macos_preferencesgrant: does not add preferences access clauses. macos_preferences = "readonly": enables cfprefs read clauses anduser-preference-read.macos_preferences = "readwrite": includes readonly clauses plususer-preference-writeand cfprefs shm write clauses.macos_automation = true: enables broad Apple Events send permissions.macos_automation = ["com.apple.Notes", ...]: enables Apple Events send only to listed bundle IDs.macos_launch_services = true: enables LaunchServices lookups and open/launch operations.macos_accessibility = true: enablescom.apple.axservermach lookup.macos_calendar = true: enablescom.apple.CalendarAgentmach lookup.macos_contacts = "read_only": enables Address Book read access and Contacts read services.macos_contacts = "read_write": includes the readonly Contacts clauses plus Address Book writes and keychain/temp helpers required for writes.
Linux
Expects the binary containing codex-core to run the equivalent of codex sandbox linux (legacy alias: codex debug landlock) when arg0 is codex-linux-sandbox. See the codex-arg0 crate for details.
Legacy SandboxPolicy / sandbox_mode configs are still supported on Linux.
They can continue to use the legacy Landlock path when the split filesystem
policy is sandbox-equivalent to the legacy model after cwd resolution.
Split filesystem policies that need direct FileSystemSandboxPolicy
enforcement, such as read-only or denied carveouts under a broader writable
root, automatically route through bubblewrap. The legacy Landlock path is used
only when the split filesystem policy round-trips through the legacy
SandboxPolicy model without changing semantics. That includes overlapping
cases like /repo = write, /repo/a = none, /repo/a/b = write, where the
more specific writable child must reopen under a denied parent.
The Linux sandbox helper prefers /usr/bin/bwrap whenever it is available and
falls back to the vendored bubblewrap path otherwise. When /usr/bin/bwrap is
missing, Codex also surfaces a startup warning through its normal notification
path instead of printing directly from the sandbox helper.
Windows
Legacy SandboxPolicy / sandbox_mode configs are still supported on
Windows.
The elevated setup/runner backend supports legacy ReadOnlyAccess::Restricted
for read-only and workspace-write policies. Restricted read access honors
explicit readable roots plus the command cwd, and keeps writable roots
readable when workspace-write is used.
When include_platform_defaults = true, the elevated Windows backend adds
backend-managed system read roots required for basic execution, such as
C:\Windows, C:\Program Files, C:\Program Files (x86), and
C:\ProgramData. When it is false, those extra system roots are omitted.
The unelevated restricted-token backend still supports the legacy full-read Windows model only. Restricted read-only policies continue to fail closed there instead of running with weaker read enforcement.
New [permissions] / split filesystem policies remain supported on Windows
only when they round-trip through the legacy SandboxPolicy model without
changing semantics. Richer split-only carveouts still fail closed instead of
running with weaker enforcement.
All Platforms
Expects the binary containing codex-core to simulate the virtual apply_patch CLI when arg1 is --codex-run-as-apply-patch. See the codex-arg0 crate for details.