## Stack
This is PR 2 of the simplified HAI single-run-task stack:
- [#19047](https://github.com/openai/codex/pull/19047) Agent Identity
assertion and task-registration primitives, including the shared
run-task helper used by existing Agent Identity JWT auth.
- [#19049](https://github.com/openai/codex/pull/19049)
Disabled-by-default ChatGPT auth opt-in that provisions/reuses persisted
Agent Identity runtime auth and its single run task.
- [#19051](https://github.com/openai/codex/pull/19051) Run-scoped
provider auth that uses one backend-owned task id for first-party
inference and compaction requests.
[#19054](https://github.com/openai/codex/pull/19054) collapsed out of
the active stack because the simplified design no longer needs a
separate background/control-plane task helper.
## Summary
This PR adds the disabled-by-default path for normal ChatGPT-login Codex
sessions to obtain Agent Identity runtime auth through the Codex
backend. Existing Agent Identity JWT startup mode remains a separate
path and does not require the feature flag.
What changed:
- adds the experimental `use_agent_identity` feature flag and config
schema entry
- adds an explicit `AgentIdentityAuthPolicy` so call sites choose
`JwtOnly` or `ChatGptAuth` instead of passing a bare boolean
- stores standalone Agent Identity JWT credentials separately from
backend-registered Agent Identity records
- persists the registered Agent Identity record, private key, and single
run task id in `auth.json` so process restarts reuse the same identity
- derives the agent/task registration base URL from ChatGPT/Codex auth
config while keeping JWT JWKS lookup separate
- provisions and caches ChatGPT-derived Agent Identity runtime auth when
`use_agent_identity` is enabled
- reuses the shared run-task registration helper from PR1 rather than
adding a second task-registration path
This PR intentionally does not switch model inference over to
`AgentAssertion` auth. The provider-auth integration lands in the next
PR.
## Testing
- `just test -p codex-login`
## Summary
- remove the duplicated originator-specific connector ID denylists
- stop filtering connector directory/accessibility results and
live/cached Codex Apps MCP tools by hardcoded connector ID
- remove the now-unused `codex-login` dependency from
`codex-utils-plugins`
- update regression coverage so formerly blocked connector IDs are
preserved
## Why
The client-side policy was duplicated across crates, used opaque IDs
without ownership or expiry information, and could drift between app
listing and MCP tool behavior. Server-provided visibility,
authorization, plugin discoverability, accessibility, enabled-state
handling, and consequential-tool approval templates remain unchanged.
## Validation
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
- `git diff --check`
- confirmed the final diff contains no hardcoded denylist symbols
A targeted `codex-mcp` test build spent an unusually long time in local
compilation/linking. Its first attempt exposed a test-only `PartialEq`
assertion issue, which was corrected. A follow-up non-linking `cargo
check -p codex-mcp --tests` was still running when this draft was
opened; CI should provide the complete Rust validation.
Scope MCP sandbox metadata to the MCP server's owning environment.
Previously, `codex/sandbox-state-meta` always used the turn's primary
cwd and rebuilt a legacy sandbox policy from that cwd. That can be wrong
for MCP servers owned by a different execution environment.
This now sends the owning environment cwd as a `file:` URI in
`sandboxCwd`, keeps `permissionProfile` as the permission source of
truth, and omits sandbox-state metadata when a non-default server
environment is not selected for the turn. Local/default MCP servers keep
the existing fallback cwd behavior.
Tests:
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just test -p codex-mcp`
- `just test -p codex-core mcp_sandbox_cwd`
- `cargo build -p codex-rmcp-client --bin test_stdio_server`
- `just test -p codex-core
stdio_mcp_tool_call_includes_sandbox_state_meta`
## Why
This is the final PR in the Windows fs-helper sandbox stack and contains
the actual bug fix.
The exec-server filesystem helper is a direct-spawn path: it asks
`SandboxManager` for a `SandboxExecRequest`, then launches the returned
argv itself. That works on macOS and Linux because the transformed argv
is already a self-contained sandbox wrapper. On Windows, the transformed
request carried `WindowsRestrictedToken` metadata, but the direct-spawn
fs-helper runner still launched the helper argv directly.
That means Windows filesystem built-ins backed by the fs-helper could
run with the parent Codex process permissions instead of the configured
Windows sandbox. This PR makes the direct-spawn transform produce a
self-contained Windows wrapper argv before fs-helper launches it.
## What Changed
- Added `SandboxManager::transform_for_direct_spawn()` for callers that
launch the returned argv themselves.
- Wrapped Windows restricted-token direct-spawn requests with `codex.exe
--run-as-windows-sandbox` and then marked the outer request as
unsandboxed, matching the macOS/Linux wrapper argv shape.
- Updated `exec-server/src/fs_sandbox.rs` to use the direct-spawn
transform for fs-helper launches.
- Materialized the inner `codex.exe --codex-run-as-fs-helper` executable
into `.sandbox-bin` so the sandboxed user can run it.
- Carried runtime workspace roots through `FileSystemSandboxContext` as
`PathUri` values so `:workspace_roots` policies resolve correctly
without sending native client paths over exec-server JSON.
- Preserved wrapper setup identity environment needed by Windows sandbox
setup without changing the serialized inner helper environment.
## Verification
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just test -p codex-sandboxing transform_for_direct_spawn_windows`
- `just test -p codex-exec-server fs_sandbox::tests`
- `just fix -p codex-windows-sandbox -p codex-sandboxing -p
codex-exec-server -p codex-core -p codex-file-system`
Local note: `just fmt` completed Rust formatting, but this workstation
still fails the non-Rust formatter phases because uv cannot open its
cache and the local buildifier/dotslash path is missing.
Summary\n- Await endpoint recommendation selection while constructing
each authenticated turn, removing the first-turn cache race.\n- Snapshot
and filter endpoint candidates once per turn, then use that same set for
the bounded contextual user fragment, tool exposure, and exact install
validation.\n- Keep recommendation selection ephemeral: do not persist
recommendation state in or gate resumed threads on prior context.\n-
Hide the legacy list tool in endpoint mode and preserve legacy discovery
unchanged when the endpoint is disabled or unavailable.\n- Keep remote
plugin and connector app identities out of model-visible context and
attach them only to Codex-owned elicitation metadata.\n\nStack\n- 3/4,
based on #28400.\n- Endpoint client and cache: #28399.\n- Generalized
suggestion presentation: #28400.\n- Install-schema follow-up:
#28403.\n\nValidation\n- \n- \n- \n- \n- Full : 2,649 passed and 88
environment-dependent tests failed because this sandbox cannot write ,
nest Seatbelt, or locate auxiliary test binaries.
## Why
Codex Apps tools can mark arguments with `openai/fileParams`, but the
execution path resolved and opened those files directly on the host.
That bypassed the selected turn environment and prevented annotated file
arguments from working with remote environments.
## What changed
- resolve annotated file arguments against the primary turn environment
- read file metadata and contents through that environment's sandboxed
`ExecutorFileSystem`
- reject files over the 512 MiB limit from metadata before reading or
transferring them
- retain the buffered upload-size check as defense in depth
- make the OpenAI upload API accept a filename and buffered contents
instead of owning local filesystem access
- describe the model-visible argument as a path in the primary
environment
This builds on #27927, which added `size` to internal filesystem
metadata.
## Testing
- `just test -p codex-api upload_openai_file_returns_canonical_uri`
- `just test -p codex-mcp
tool_with_model_visible_input_schema_masks_file_params`
- `just test -p codex-core mcp_openai_file`
- `just test -p codex-core
codex_apps_file_params_upload_environment_files_before_mcp_tool_call`
## Why
`fs/readFile` buffers the entire file in one response, which makes large
remote reads expensive and prevents callers from applying backpressure.
We need an opt-in streaming path with bounded block sizes while
preserving the existing single-call API for small and sandboxed reads.
## What changed
- Add `ExecServerClient::stream`, returning a named `FileReadStream`
that implements `futures::Stream` and yields immutable 1 MiB byte
blocks.
- Add internal `fs/open`, `fs/readBlock`, and `fs/close` RPCs.
`fs/readBlock` accepts an explicit offset and length.
- Keep unsandboxed files open between block reads, cap open handles per
connection, and clean them up on EOF, error, stream drop, explicit
close, or connection shutdown.
- Reject platform-sandboxed streaming opens instead of turning the
one-shot sandbox helper into a persistent server. Existing `fs/readFile`
behavior is unchanged.
## Testing
- `just test -p codex-exec-server`
- Integration coverage for 1 MiB chunking, exact block-boundary EOF,
sandbox rejection, and continued reads from the opened file after path
replacement.
- Handle-manager coverage for non-sequential offsets, variable block
lengths, the 128-handle limit, and capacity release after close.
## Why
Clients running an app-server on one OS and an exec-server on another OS
need to be able to pass sandbox config to app-server that refers to
resources on the executor's foreign OS.
## What
`AbsolutePathBuf` can't represent these paths and we don't want users to
be exposed to `PathUri` yet, so this moves the public app-server API to
be expressed in terms of `ApiPathString`.
Stacked on #28165.
- change app-server v2 filesystem permission paths, including legacy
read/write roots, to `ApiPathString`
- localize API paths through `PathUri` when converting into the current
native core permission types
- make path-bearing permission conversions fallible and surface
localization failures instead of silently treating malformed grants as
ordinary denials
- propagate conversion failures through app-server and TUI approval
handling
- regenerate the app-server JSON and TypeScript schemas
- leave migration TODOs on native-path conversions so they can be
removed once core permission paths use `PathUri`
## Why
Progress towards letting app-server and exec-server run on different
platforms, specifically for sandbox configuration.
## What
- Make the filesystem path containment hierarchy generic, defaulting to
`AbsolutePathBuf` for now.
- Have clients specify `AbsolutePathBuf` or `PathUri` directly where
needed.
- Use `PathUri` throughout exec-server filesystem protocol and trait
boundaries.
- Implement `From` for conversion to path URIs and `TryFrom` for
fallible conversion to absolute paths through the generic type
hierarchy.
## Why
Rendezvous forwards traffic between the orchestrator and exec-server.
The endpoints need to authenticate each other and encrypt that traffic
without trusting Rendezvous with plaintext or endpoint keys.
## Changes
- Adds a hybrid Noise IK channel through Clatter using X25519,
ML-KEM-768, AES-256-GCM, and SHA-256.
- Binds each handshake to `environment_id`, `executor_registration_id`,
and `stream_id`.
- Pins the registry-provided executor key and carries the harness
authorization inside the encrypted handshake.
- Orders relay frames before consuming Noise nonces and fragments large
JSON-RPC messages into bounded records.
- Bounds handshake payloads, frames, streams, and message reassembly.
Runtime activation is in
[openai/codex#26245](https://github.com/openai/codex/pull/26245).
## Stack
1. **[openai/codex#26242](https://github.com/openai/codex/pull/26242)**:
Noise channel and relay transport
2. [openai/codex#26245](https://github.com/openai/codex/pull/26245):
remote registration and runtime activation
## Verification
- `just test -p codex-exec-server`
- Oversized initiator payload regression coverage
- `just fix -p codex-exec-server`
- `just bazel-lock-check`
- `cargo shear`
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- move `AppToolPolicyEvaluator` and the Apps config/requirements policy
logic from `codex-core` into `codex-connectors`
- resolve one immutable policy snapshot per exposure build and reuse it
across every Codex Apps MCP tool
- keep core as a thin adapter from MCP metadata to connector-owned
policy input while preserving the call-time defense-in-depth check
## Why
`build_mcp_tool_exposure` evaluates every Codex Apps tool on each
sampling request. The old path rebuilt effective Apps configuration for
every tool, and the policy implementation lived in the already-large
core crate even though it is connector-specific.
The connector-owned evaluator keeps the expensive config merge/decode
out of the loop and gives core only the effective policy result it
needs.
## Performance
With the real 557-tool Apps corpus, `build_mcp_tool_exposure` measured
3.74 ms and 3.33 ms after the extraction (3.54 ms mean). The original
path measured 807 ms mean, so the final result retains the 99.6%
reduction.
## Validation
- `cargo check -p codex-connectors -p codex-core`
- `just test -p codex-connectors` — 15 passed
- `just test -p codex-core --lib connectors` — 35 passed
- `just test -p codex-core --lib mcp_tool_exposure` — 5 passed
- `just test -p codex-core --lib mcp_tool_call` — 72 passed
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just fix -p codex-connectors`
- `just fix -p codex-core`
- `just fmt`
## Why
This is the second PR in the Windows fs-helper sandbox stack. The
fs-helper path needs a Windows sandbox launcher that has the same
argv-shaped contract as macOS `sandbox-exec` and `codex-linux-sandbox`,
but this PR only introduces that hidden launcher. It does not route
fs-helper through it yet.
The hidden launcher still needs to be policy-complete before later
direct-spawn callers use it. In particular, it has to carry the same
Windows sandbox policy details that the existing spawn paths already
understand: proxy enforcement, read/write root overrides, and
deny-read/deny-write overrides.
## What Changed
- Added the hidden `codex.exe --run-as-windows-sandbox` arg1 dispatch
path.
- Added `windows-sandbox-rs/src/wrapper.rs`, which parses the wrapper
argv, launches the requested command through the shared Windows sandbox
session runner from PR1, and forwards stdio.
- Added `create_windows_sandbox_command_args_for_permission_profile()`
so later direct-spawn callers can build the wrapper argv consistently.
- Made the wrapper argv round-trip the full Windows sandbox policy
surface it needs later: workspace roots, environment, permission
profile, sandbox level, private desktop, proxy enforcement, read/write
root overrides, and deny-read/deny-write overrides.
- Carried `proxy_enforced` through the shared Windows session request so
proxy-managed executions continue to use the offline/elevated sandbox
identity.
- Added wrapper argument round-trip coverage for the full policy fields.
## Verification
- `just test -p codex-windows-sandbox windows_wrapper_args_round_trip`
- `just test -p codex-arg0`
- `just test -p codex-core exec::tests::windows_`
- `just fix -p codex-windows-sandbox -p codex-core -p codex-cli`
Local note: the full `just fmt` command still fails on this workstation
in non-Rust formatter setup (`uv` cache access denied and missing
`dotslash`/buildifier), but the Rust formatter phase completed.
## Context
This is PR4 in the plugin auth-routing stack. The earlier PRs make
plugin surface projection auth-aware and narrow App/MCP conflicts by App
declaration name. This PR keeps connector listing paths aligned with
that projected plugin App set.
This means ChatGPT/SIWC users will still see plugin-provided Apps in
connector listing surfaces like the Apps/connector picker, while API-key
users will not see Apps they cannot use.
## Stack
- PR1: #27652 seed plugin manager auth at construction.
- PR2: #27459 route plugin surfaces by auth mode.
- PR3: #27607 dedupe plugin MCP servers by App declaration name.
- PR4: #27602 preserve plugin Apps in connector listings.
- PR5: #27461 skip install-time plugin MCP OAuth for matching App
routes.
## Summary
- Have app-server compute effective plugin Apps from the existing
PluginsManager and pass them into connector listing.
- Keep plugin Apps visible in Apps/connector listing for ChatGPT/SIWC
users.
- Keep API-key-style auth from surfacing plugin Apps in connector
listings.
## Validation
```bash
cargo test -p codex-chatgpt connectors::tests
cargo test -p codex-app-server list_apps_includes_plugin_apps_for_chatgpt_auth
git diff --check
```
## Why
**In short:** this PR discovers MCP registrations by reading a selected
plugin's `.mcp.json` on its executor. #27884 then resolves those
registrations in the shared catalog.
`thread/start.selectedCapabilityRoots` can select a plugin root owned by
an executor, and Codex can resolve that package through the executor
filesystem. MCP declarations inside the selected plugin are still
ignored.
This PR adds the source-specific discovery layer on top of the
selected-plugin catalog boundary in #27884:
```text
selected capability root
|
v
resolve the plugin through its executor filesystem
|
v
read and normalize its MCP config through the same filesystem
|
v
contribute stdio registrations bound to that environment ID
```
The existing MCP launcher and connection manager remain unchanged. MCP
config parsing is shared with local plugins through #27863.
## What changed
- Added an executor plugin MCP provider in the MCP extension.
- Retained only the exact filesystem capability used for package
resolution and reused it for the selected plugin's MCP config, with no
host-filesystem fallback or unrelated process/HTTP authority.
- Read either the manifest-declared MCP config or the default
`.mcp.json`; a missing default file means the plugin has no MCP servers.
- Accepted stdio servers only for this first vertical. Executor-owned
HTTP declarations are skipped with a warning until their placement
semantics are defined.
- Normalized stdio registrations with the owning environment's stable
logical ID and plugin-root working directory.
- Resolved environment-variable names on the owning executor and
rejected explicit local forwarding for non-local plugins.
- Froze discovered declarations once per active thread runtime, then
applied current managed plugin and MCP requirements when contributing
them.
- Carried the selected root ID, display name, and selection order into
the catalog contribution defined by #27884.
## Behavior and scope
There is intentionally no production behavior change yet. This PR
provides the executor provider and contribution boundary, but app-server
does not install it in this change. Existing local plugin MCP loading is
unchanged, and no MCP process is launched by this PR alone.
## Assumptions
- The selected root ID is the plugin policy identity; the manifest
display name is presentation metadata.
- An environment ID is a stable logical authority. Reconnection or
replacement under the same ID does not change ownership.
- Selected plugin packages and their manifests are trusted inputs.
- The selected package and MCP discovery snapshot remain frozen for the
active thread runtime.
## Follow-up
The next PR installs this contributor in app-server and adds an
end-to-end test proving that a selected plugin MCP tool launches on its
owning executor, can be called by the model, survives an explicit MCP
refresh, and is invisible when its root was not selected.
Resume, fork, environment removal or ID changes, dynamic catalog reload,
and executor-owned HTTP MCP placement remain separate lifecycle
decisions.
## Verification
Focused tests cover executor-only filesystem reads, missing and
malformed config, stdio filtering and normalization, managed
requirements, package attribution, and selection order. CI owns
execution of the test suite.
## Why
Next slice needed to make progress on the `remote_env_windows` test is
to support passing a Windows cwd for the remote environment and using
that environment's native shell. This lets the test run a real Windows
process instead of only recording an early path or shell mismatch.
## What
- change `TurnEnvironmentSelection.cwd` from `AbsolutePathBuf` to
`PathUri`
- convert local cwd values to URIs when constructing selections
- preserve a remote primary cwd instead of replacing it with the local
legacy fallback
- prefer the selected environment's discovered shell for unified exec,
falling back to the session shell when unavailable
- convert back to a host-native absolute path at current native-only
consumer boundaries
- reject or deny unsupported foreign cwd values at the existing
request-permissions boundary, with TODOs for its future migration
- extend the hermetic Wine test to execute Windows PowerShell in
`C:\windows` and verify successful process completion
- record the current app-server rejection against the same Wine-backed
remote Windows fixture when its cwd is supplied as a native Windows path
## Summary
Prevent dependency refreshes from silently downgrading Codex's bundled
SQLite to a release affected by the WAL-reset corruption bug.
SQLx 0.9 accepts a broad `libsqlite3-sys` range. An unrelated lock
refresh therefore moved Codex from `libsqlite3-sys 0.37.0` back to
`0.35.0`, changing the bundled SQLite runtime from 3.51.3 to 3.50.2.
SQLite documents the affected versions and fix in [The WAL Reset
Bug](https://www.sqlite.org/wal.html#the_wal_reset_bug) and the [SQLite
3.51.3 changelog](https://www.sqlite.org/changes.html#version_3_51_3).
## Why
This is the second-to-last place in the exec-server protocol that needs
to migrate to URIs to support cross-OS operation.
## What
- Change `ExecParams.cwd` to `PathUri`.
- Keep the cwd URI-shaped through core and rmcp producers, converting it
to `AbsolutePathBuf` only in `LocalProcess::start_process`.
- Reject non-native cwd URIs before launch and update the affected
protocol documentation and call sites.
## Summary
- Keep local plugin suggestions bounded to fallback and explicitly
configured plugins.
- Preserve app-overlap recommendations for remote plugins using cached
catalog metadata.
- Remove the WSL-specific local discovery exception and move
manager-owned discovery tests into `codex-core-plugins`.
## Why
Local curated marketplaces were allowlisted before plugin detail
loading, so every uninstalled candidate could be deep-read before its
app IDs were checked. That caused per-turn reads of candidate plugin
manifests, skills, app configs, hooks, and MCP configs, which is
especially expensive on slow disks.
Remote discovery does not need those local candidate reads because app
IDs are already available in the cached remote catalog. Installed local
plugins are still loaded when needed to determine the user's installed
app IDs.
## Validation
- `just fmt`
- `just test -p codex-core-plugins discoverable::tests` (13 passed)
- `just test -p codex-core plugins::discoverable::tests` (4 passed)
- `just bazel-lock-update`
- `just bazel-lock-check`
- `git diff --check`
## Why
`PathUri::from_abs_path` can fail for absolute paths that do not have a
normal `file:` URI representation, forcing filesystem call sites to
handle a conversion error even though the original path can be preserved
losslessly.
## What
Make `from_abs_path` infallible and migrate its callers. Unrepresentable
paths use `file:///%00/bad/path/<base64>`, encoding Unix bytes or
Windows UTF-16LE; `to_abs_path` validates and decodes that fallback. The
leading encoded null reserves a namespace that cannot collide with a
real Unix or Windows path, and fallback URIs remain opaque to lexical
path operations.
## Validation
Added path-URI coverage for Unix null and non-UTF-8 paths, Windows
device/verbatim and non-Unicode paths, serialization, malformed
fallbacks, opaque lexical operations, invalid native payloads, and
literal `/bad/path` collision resistance.
## Summary
- store MCP OAuth credentials in the configured auth credential backend
- support encrypted-local OAuth storage, including legacy keyring
migration
- propagate the credential backend through MCP refresh, session, CLI,
and app-server paths
## Stack
1. #27504 — config and feature flag
2. #27535 — auth-specific secret namespaces
3. #27539 — encrypted CLI auth storage
4. this PR — encrypted MCP OAuth storage
This is a parallel review stack; the original #17931 remains unchanged.
## Tests
- `just test -p codex-rmcp-client` (the transport round-trip test passed
after building the required `codex` binary and retrying)
- `just test -p codex-mcp`
- `just test -p codex-app-server
refresh_config_uses_latest_auth_keyring_backend`
- `just test -p codex-core
refresh_mcp_servers_is_deferred_until_next_turn`
- `just test -p codex-cli mcp`
- `just fix -p codex-rmcp-client -p codex-mcp -p codex-core -p codex-cli
-p codex-app-server -p codex-protocol`
- `just bazel-lock-check`
## Why
Windows Credential Manager limits generic credential blobs to 2,560
bytes. Large serialized ChatGPT auth payloads can exceed that limit, so
keyring-mode CLI auth needs a backend that keeps only the encryption key
in the OS keyring and stores the payload in Codex's encrypted
local-secrets file.
This is the third PR in the encrypted-auth stack:
1. #27504 — feature and config selection
2. #27535 — auth-specific local-secrets namespaces
3. This PR — CLI auth implementation and activation
4. MCP OAuth implementation and activation
## What Changed
- Added encrypted CLI-auth storage using the `CliAuth` secrets
namespace.
- Preserved direct keyring storage for platforms/configurations where it
remains selected.
- Selected the backend consistently for login, logout, refresh,
device-code login, auth loading, and login restrictions.
- Threaded resolved bootstrap/full config through CLI, exec, TUI,
app-server account handling, cloud config, and cloud tasks.
- Removed stale `auth.json` fallback data after successful encrypted
saves and removed encrypted, direct-keyring, and fallback data during
logout.
- Added storage and integration coverage for both direct and encrypted
keyring modes.
MCP OAuth persistence is intentionally left to the next PR.
## Validation
- `just test -p codex-login` — 131 passed
- `just test -p codex-cli` — 280 passed
- `just test -p codex-app-server v2::account` — 25 passed
- `just test -p codex-cloud-config service` — 21 passed, 7 skipped
- `just fix -p codex-login`
- `just fix -p codex-cli`
- `just fmt`
## Why
Removes the realtime audio support from TUI.
## What Changed
- Removed the TUI `/realtime` and realtime `/settings` command paths.
- Deleted TUI voice capture/playback, WebRTC session handling,
audio-device selection UI, and recording-meter code.
- Removed TUI realtime tests and snapshots that covered the deleted
surfaces.
- Dropped the TUI-only `cpal` and `codex-realtime-webrtc` dependencies
and refreshed the Rust/Bazel locks.
## Summary
- reuse the shared shell read parser for implicit skill doc invocation
detection
- add regression coverage for `nl -ba .../SKILL.md`
## Why
Desktop could render `Read User Context skill` for reads recognized by
the shared command parser, while implicit `skill_invocation` analytics
used a separate reader allowlist and missed cases such as `nl`.
## Validation
- `HOME=/private/tmp/codex-core-skills-home-pr
PATH=/Users/alexsong/.cache/cargo-home/bin:$PATH
CARGO_HOME=/Users/alexsong/.cache/cargo-home just test -p
codex-core-skills`
- `git diff --cached --check`
- `just fmt` attempted; Rust formatting completed, but the Python
formatters could not download uncached Ruff wheels because
`files.pythonhosted.org` is blocked in this sandbox.
- `bazel mod deps --lockfile_mode=update/error
--repo_env=ASPECT_TOOLS_TELEMETRY= --repo_env=DO_NOT_TRACK=1` evaluated
the module graph and produced no `MODULE.bazel.lock` diff, but Bazel
crashed on sandboxed `sysctl` during exit.
## Why
`codex login` previously persisted newly issued OAuth credentials and
only then attempted to revoke the superseded refresh token. The old
credential must be revoked before a replacement browser or device-code
flow starts, and successful login must not perform any post-login
revocation attempt.
## What changed
- Revoke and clear existing stored auth before browser or device-code
CLI login begins.
- Remove superseded-token detection and revocation from the shared token
persistence path; successful login now only saves the new credentials.
- Read the raw configured auth store during CLI cleanup so
environment-provided auth cannot mask the stored refresh token.
- Preserve `auto` storage fallback semantics when keyring deletion fails
by clearing the fallback auth file.
- Add a process-level CLI regression test that requires the revoke
request to precede every device-login request and occur exactly once.
If replacement login is canceled or fails, the previous local
credentials have already been cleared. Remote revocation remains best
effort, matching explicit logout behavior.
## Validation
### Process-level before/after reproduction
I compiled the real `codex` CLI from the pre-fix parent (`14df0e8833`)
and from the PR implementation (`25c002f23b`; the login behavior is
unchanged at the current head), then ran the same device-code flow
against a local HTTP mock OAuth authority.
Each run:
1. Used a fresh temporary `CODEX_HOME` configured with
`cli_auth_credentials_store = "file"`.
2. Seeded that temporary home with managed ChatGPT auth containing
`old-access` and `old-refresh` tokens.
3. Pointed `CODEX_REVOKE_TOKEN_URL_OVERRIDE` at the mock `/oauth/revoke`
endpoint.
4. Ran the compiled CLI as:
```shell
CODEX_HOME=<temporary-home> \
CODEX_REVOKE_TOKEN_URL_OVERRIDE=<mock-issuer>/oauth/revoke \
<compiled-codex> login --device-auth --experimental_issuer <mock-issuer>
```
5. Recorded every request received by the mock authority. The mock
marked `new-access` valid when `/oauth/token` issued it and invalidated
it if `/oauth/revoke` arrived afterward, reproducing the observed
session-invalidating failure mode. After login exited, the harness also
verified the persisted refresh token and probed a protected endpoint
with `new-access`.
| Build | Observed request order | CLI/persistence result | `new-access`
probe |
| --- | --- | --- | --- |
| Pre-fix | `usercode → device token → OAuth token →
revoke(old-refresh)` | Exit `0`; `new-refresh` persisted | `401` |
| PR | `revoke(old-refresh) → usercode → device token → OAuth token` |
Exit `0`; `new-refresh` persisted | `200` |
The PR run therefore issued exactly one revocation request, before any
request that initiated the replacement login, and issued no revocation
after token exchange.
### Regression coverage
`codex-rs/cli/tests/login.rs::device_login_revokes_existing_auth_before_requesting_new_tokens`
runs the real first-party `codex` binary against a `wiremock` OAuth
server with an isolated temporary `CODEX_HOME`. It asserts:
- the exact request sequence is `/oauth/revoke`,
`/api/accounts/deviceauth/usercode`, `/api/accounts/deviceauth/token`,
then `/oauth/token`;
- there is exactly one revoke request and its body contains
`old-refresh` with the `refresh_token` hint;
- the completed login persists `new-refresh`.
Local validation:
- `just test -p codex-login` — 130 passed
- `just test -p codex-cli` — 280 passed, including the new process-level
regression test
- `just bazel-lock-check`
## Why
Sandbox cwd values can cross app-server and exec-server host boundaries.
They should retain URI semantics until the receiving host validates them
instead of being interpreted early as native paths.
## What
- Carry `PathUri` through filesystem sandbox contexts, sandbox commands,
and transform inputs.
- Convert command and policy cwd once in `SandboxManager::transform`,
then keep launch requests native.
- Preserve sandbox cwd over remote filesystem transport and reject
non-native URIs without fallback.
- Cache paired native/URI turn-environment cwd values during migration,
with immutable access to keep them synchronized.
- Extend existing protocol, forwarding, transform, and core runtime
tests.
## Why
We want a thread-selected plugin to eventually expose stdio MCP servers
that run on the executor owning that plugin.
The existing plugin MCP parser lived inside `core-plugins` and was
coupled to the host filesystem loader. Reusing it from an executor
provider would either duplicate MCP normalization or make the plugin
package layer own MCP runtime semantics. This PR creates the shared
MCP-owned boundary first.
In simple terms:
```text
plugin .mcp.json
|
v
shared parser in codex-mcp
|
+-- Declared placement: preserve current local-plugin behavior
|
+-- Environment placement: produce config bound to one executor
```
This builds on the authority-bound plugin descriptors from #27692. It
intentionally does not discover, register, or launch executor MCP
servers yet.
## What changed
- Moved plugin MCP file parsing and normalization from `core-plugins`
into `codex-mcp`.
- Kept support for both existing file shapes: a top-level server map and
an object containing `mcpServers`.
- Kept per-server failure isolation: one invalid server does not discard
valid siblings, while malformed top-level JSON still fails the whole
file.
- Updated the existing local plugin loader to use `Declared` placement,
preserving its current transport, OAuth, relative `cwd`, and error
behavior.
- Added `Environment` placement for the next stacked PR:
- the selected environment ID overrides anything declared by the plugin;
- missing stdio `cwd` defaults to the plugin root;
- relative `cwd` is resolved beneath the plugin root and cannot traverse
outside it;
- bare or source-less environment-variable references resolve on a
non-local executor;
- explicit orchestrator environment-variable forwarding is rejected for
executor-owned plugins.
## User impact
None in this PR. Existing local plugin MCP loading follows the same
behavior through the shared parser. The executor placement mode is not
connected to thread startup until the follow-up registration PR.
## Assumptions
- A selected capability root's environment is authoritative. A plugin
cannot redirect its stdio process to the orchestrator or another
executor.
- Relative working directories belong under the plugin package root.
Explicit absolute working directories remain valid within the owning
environment.
- For a non-local executor, unqualified environment-variable names refer
to that executor. Reading an orchestrator variable requires an explicit
contract and is rejected for now.
- Parsing only produces normalized `McpServerConfig` values. Process
startup remains owned by the existing MCP runtime and connection
manager.
## Follow-ups
1. Add the executor MCP provider and catalog registration: read the
selected plugin's MCP config through the same executor filesystem,
support stdio only, freeze the result per active thread, apply managed
policy, and resolve name collisions as discovered plugin < selected
plugin < explicit config.
2. Install that provider in app-server and add an end-to-end test
proving `thread/start.selectedCapabilityRoots` launches and calls the
MCP tool on the selected executor, preserves the frozen registration
across refresh, and does not expose it to an unselected thread.
3. After the initial executor-stdio vertical, define
resume/fork/environment-replacement semantics, executor HTTP placement,
warning delivery, common MCP tool-context bounds, and move remaining MCP
source composition above core.
## Verification
- `cargo check -p codex-mcp -p codex-core-plugins --tests`
- `just bazel-lock-check`
- Added focused parser coverage for legacy local normalization, executor
authority, working-directory handling, and environment-variable
sourcing.
## Why
CCA can select a capability root that lives in an executor environment,
but
Codex only had a host-filesystem plugin loader. Before selected executor
plugins can contribute MCP servers, we need a small package boundary
that can
answer:
> Does this selected root contain a plugin, and if so, what does its
manifest
> declare?
The answer must come from the selected environment's filesystem. A
failed
executor lookup must never fall back to the orchestrator filesystem.
## What this changes
This PR introduces:
```rust
PluginProvider::resolve(root)
-> Result<Option<ResolvedPlugin>, Error>
```
`ExecutorPluginProvider` resolves one `SelectedCapabilityRoot` through
its
exact `environment_id`. It checks the recognized manifest locations,
reads the
manifest through that environment's `ExecutorFileSystem`, and returns an
inert
`ResolvedPlugin` containing:
- the opaque selected-root ID;
- the environment-bound plugin root;
- the authority-bound manifest resource;
- parsed metadata and authority-bound component locators.
Descriptor construction rejects manifest or component paths outside the
selected package root, so consumers cannot accidentally lose the package
boundary when they receive a resolved plugin.
If the root has no plugin manifest, resolution returns `None`, allowing
the
caller to treat it as a standalone capability such as a skill.
```text
selected root: repo -> env-1:/workspace/repo
|
| env-1 filesystem only
v
.codex-plugin/plugin.json
|
v
ResolvedPlugin { authority, root, manifest }
```
The existing host loader and the new executor provider now share the
same
manifest parser. Existing `codex-core-plugins::manifest` type paths
remain
available through re-exports, so host behavior and callers are
unchanged.
## Scope
This is intentionally a non-user-visible package-resolution PR. It does
not:
- parse or register plugin MCP server configurations;
- activate skills, connectors, hooks, or MCP servers;
- change app-server wiring;
- introduce host fallback, caching, or lifecycle behavior.
#27670 has merged, and this PR is now based directly on `main`. Together
with
the resolved MCP catalog from #27634, it establishes the inputs needed
for the
executor stdio MCP vertical without changing the existing MCP runtime.
## Follow-up
The next PR will consume `ResolvedPlugin`, read its declared/default MCP
config
through the same executor filesystem, bind supported stdio servers to
that
environment, and feed those registrations into the resolved MCP catalog.
An
app-server E2E will prove that selecting an executor plugin exposes and
invokes
its tool on the owning executor.
Resume/fork semantics, dynamic environment replacement, and non-stdio
placement remain separate lifecycle decisions.
## Validation
- `just fmt`
- `cargo check --tests -p codex-plugin -p codex-core-plugins`
- `just bazel-lock-check`
- `git diff --check`
Test targets were compiled but not executed locally; CI will run the
test and
Clippy suites.
This is phase 1 of a 4 phase stack:
1. **Add protocol and host crates for new IPC code mode implementation**
2. Create the new standalone binary
3. Create a new IPC `CodeModeSessionProvider` to use new binary
4. Remove v8 from core and only use IPC provider
## Add protocol and host crates for new IPC code mode implementation
Establish a clean process boundary without changing the existing
in-process behavior.
- Add the codex-code-mode-protocol crate for shared session, runtime,
response, and tool-definition types.
- Move protocol-facing code out of the V8-backed implementation.
- Add a buildable codex-code-mode-host crate as the foundation for the
standalone process.
- Keep the existing in-process runtime as the active implementation.
## Why
First-party async traits should expose their `Send` contracts explicitly
without requiring `async_trait`. This completes the migration pattern
established in #27303 and #27304.
## What changed
- Replaced the remaining first-party `async_trait` traits with native
return-position `impl Future + Send` where statically dispatched and
explicit boxed `Send` futures where object safety is required.
- Kept implementations behavior-preserving, outlining existing async
bodies into inherent methods where that keeps the diff reviewable.
- Removed all direct first-party `async-trait` dependencies and the
workspace dependency declaration.
- Added a cargo-deny policy that permits `async-trait` only through the
remaining transitive wrapper crates.
- Updated `rand` from 0.8.5 to 0.8.6 to resolve RUSTSEC-2026-0097 and
keep the full cargo-deny check passing.
## Validation
- `just test -p codex-exec-server`: 216 passed, 2 skipped.
- `just test -p codex-model-provider`: 39 passed.
- `just test -p codex-core` and `just test`: changed tests passed;
remaining failures are environment-sensitive suites unrelated to this
migration.
- `cargo deny check`
- `just fix`
- `just fmt`
- `cargo shear`
- `just bazel-lock-check`
## Why
`main` stopped compiling when #27498 passed an `AbsolutePathBuf` to the
`ExecutorFileSystem` API migrated to `PathUri` by #27653.
## What
Convert referenced image paths to `PathUri` before filesystem reads,
declare the internal path-URI dependency, and refresh `Cargo.lock`.
## Why
Image generation used `std::fs::read` for referenced image paths, which
did not support environment-backed filesystems or their sandbox context.
## What changed
- Expose optional turn environments to extension tool calls.
- Include each environment’s ID, working directory, filesystem, and
sandbox context.
- Read referenced images through the selected environment filesystem.
- Keep sandbox usage at the extension call site so extensions can choose
the appropriate access mode.
- Consolidate image request construction into one async function.
- Add coverage for successful environment reads and read failures.
## Validation
- `cargo check -p codex-image-generation-extension --tests`
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
`just test -p codex-image-generation-extension` could not complete
because the build exhausted available disk space.
## Why
We want to remove implicit use of `$CODEX_HOME` from `codex-core` and
make embedders responsible for supplying user-level instructions. This
also ensures user instructions load when no primary environment is
selected.
## What changed
Stacked on #27415, which makes `codex exec` surface thread-scoped
runtime warnings.
- Added `UserInstructionsProvider` to `codex-extension-api`, with
absolute source attribution and recoverable loading warnings.
- Added `codex-home` with the filesystem-backed provider for
`AGENTS.override.md` and `AGENTS.md`, preserving precedence, fallback,
trimming, lossy UTF-8 handling, and the existing uncapped global
instruction size.
- Removed global instruction loading from `Config` and require
`ThreadManager` callers to inject a provider.
- Load provider instructions once for each fresh root runtime, including
runtimes without a primary environment. Running sessions retain their
snapshot, while child agents inherit the parent snapshot without
invoking the provider.
- Keep provider instructions separate while loading project `AGENTS.md`,
then assemble the model-visible instructions with the existing ordering,
source attribution, warning, and turn-context behavior.
- Wired the Codex home provider through the CLI, app server, MCP server,
core facade, and thread-manager sample.
## Validation
- `just test -p codex-home -p codex-extension-api`
- `just test -p codex-core agents_md`
- `just test -p codex-core guardian`
- `just test -p codex-app-server
thread_start_without_selected_environment_includes_only_global_instruction_source`
- `just test -p codex-exec warning`
- `just bazel-lock-check`
## Why
We're moving exec-server to use PathUri for its internal path
representations.
## What
Move `ExecutorFileSystem` APIs to use `PathUri` instead of
`AbsolutePathBuf`. Future changes will convert higher-level parts of
exec-server.
## Why
`ext/skills` currently depends on `codex-core` for two host concerns:
reading the concrete `Config` type and borrowing core-owned
model-context fragment types. That coupling prevents the extension from
being assembled independently above core and leaves context that belongs
to the skills feature owned by core.
This stacked PR introduces the host boundary needed for the broader
extension migration while intentionally preserving existing skills
behavior. It is stacked on #27404.
## What changed
- Adds a small public `SkillsExtensionConfig` view and makes skills
installation generic over the host config type.
- Requires the host to map its config into that view; app-server
supplies the current `Config` values.
- Moves the available-skills and selected-skill context fragment
implementations into `ext/skills`, preserving their roles, markers, and
rendered bytes.
- Removes the direct `codex-core` dependency from
`codex-skills-extension`.
- Keeps local discovery, invocation, side effects, and the
`codex-core-skills` compatibility types unchanged for later staged PRs.
## Behavior
This adds no capability and is intended to have no user-visible or
model-visible behavior change. The install API and ownership boundary
change internally; emitted skills context remains byte-for-byte
compatible.
## Validation
- Updates the skills extension integration coverage to use a host-owned
test config.
- Asserts the complete rendered catalog and selected-skill fragments,
including their roles and markers.
- `just bazel-lock-check`
- Rust tests and Clippy were not run locally per request; CI will run
them.
## Why
PR #27387 makes backend plugin skills discoverable and invocable without
an executor, but resources referenced by those skills still sit behind
the generic MCP resource surface. The model needs a skills-owned API
that preserves the provider authority and package boundary instead of
treating remote resources like local files.
This is stacked on #27387.
## What
- Adds one `skills` namespace with bounded `list` and `read` tools for
remote skill providers.
- Revalidates `authority + package` against the live remote catalog on
every read, then routes the opaque resource ID back through that
provider.
- Allows the backend provider to read canonical child `skill://`
resources while rejecting cross-package, non-canonical, query, fragment,
and traversal-shaped URIs.
- Caps each serialized tool result at 8 KB. Lists are paginated; reads
return an opaque continuation cursor.
- Marks the JSON output as external context so memory generation can
apply its normal suppression policy.
- Deliberately does not add `skills.search`; that waits for a bounded
plugin-service search contract.
## Tool contract
Pseudo-Python matching the wire shape:
```python
from typing import Literal, NotRequired, TypedDict
class RemoteSkillAuthority(TypedDict):
kind: Literal["remote"]
id: str # e.g. "codex_apps"
class RemoteSkill(TypedDict):
authority: RemoteSkillAuthority
package: str # opaque provider-owned package ID
name: str
description: str
main_resource: str # opaque provider-owned SKILL.md ID
class SkillsListParams(TypedDict):
cursor: NotRequired[str]
class SkillsListResult(TypedDict):
skills: list[RemoteSkill]
next_cursor: str | None
warnings: list[str]
truncated: bool
class SkillsReadParams(TypedDict):
authority: RemoteSkillAuthority # copied from skills.list
package: str # copied from skills.list
resource: str # provider-owned child resource ID
cursor: NotRequired[str] # copy next_cursor to continue
class SkillsReadResult(TypedDict):
resource: str
contents: str
next_cursor: str | None
truncated: bool
class Skills:
def list(self, params: SkillsListParams) -> SkillsListResult: ...
def read(self, params: SkillsReadParams) -> SkillsReadResult: ...
```
There is one namespace for all remote skills, not one tool or MCP server
per skill. No resource ID is converted into a filesystem path.
## Backend dependency
`/ps/mcp` must support direct reads of child resources such as
`skill://plugin_demo/deploy/references/deploy.md`. This PR implements
and tests the Codex side of that contract; production child reads remain
dependent on the corresponding plugin-service support. Search remains
out of scope until that service exposes a bounded search/resource API.
## Validation
- Added an app-server integration test covering `skills.list` followed
by `skills.read` with no executor.
- Ran `just fmt`.
- Ran `just bazel-lock-update` and `just bazel-lock-check`.
- Did not run Rust tests or Clippy locally, per request; CI will run
them.
## Why
#27198 made the extension-owned `codex_apps` MCP connection the hosted
plugin runtime, but its `mcp/skill` resources still bypassed the skills
extension. App-server could list and read those resources through
generic MCP APIs, but a thread with no selected environment did not
expose them in the model's skills catalog or load their `SKILL.md`
through `$skill`.
Hosted skills should stay remote while using the same typed catalog,
source authority, deduplication, bounded contextual catalog, and
selected-skill prompt injection as host and executor skills. They should
not be downloaded or exposed as ambient filesystem paths.
## What changed
- Add a session-scoped `McpResourceClient` over the replaceable MCP
connection manager so resource list/read calls follow startup and
refresh replacements.
- Add a `BackendSkillProvider` that pages `codex_apps` resources,
accepts bounded and validated `mcp/skill` entries, and reads a selected
skill's `SKILL.md` through the same MCP connection.
- Register the remote provider in app-server and include it in the
skills catalog even when a thread has no selected capability roots or
executor.
- Contribute hosted skill metadata through the bounded
`AvailableSkillsInstructions` developer-context path, exclude remote
entries from per-turn catalog injection, and classify `<skills>`
messages as contextual developer content so rollback can trim and
rebuild them correctly.
## Testing
- Extend the app-server MCP resource integration test with
`environments: []` to exercise two-page discovery, filter a
non-`mcp/skill` resource, verify the escaped developer catalog entry and
user-role `<skill>` fragment containing the fetched `SKILL.md`, and
preserve generic MCP resource reads.
- Add core event-mapping coverage that classifies `<skills>` developer
messages as contextual history.
## Why
We're now [discouraging use of
`async_trait`](https://github.com/openai/codex/pull/20242).
Removing use of `async_trait` from `ToolExecutor` yields a `codex_core`
debug test build speedup of ~78% (from 227.5s to 50.3s) on my machine.
Stacked on #27299, this PR applies the trait change after the handler
bodies have been outlined.
## What
Changed `ToolExecutor::handle` to return an explicit boxed
`ToolExecutorFuture` instead of using `async_trait`.
Updated ToolExecutor implementors to return `Box::pin(...)`, reexported
the future alias through `codex-tools` and `codex-extension-api`, and
removed `codex-tools` direct `async-trait` dependency.
## Why
Extension contributors are registered behind `dyn Trait` objects, so
native `async fn`/RPITIT methods would make these traits
non-object-safe. Spell out the boxed, `Send` future contract directly so
`extension-api` no longer needs `async-trait` while retaining the
existing runtime model.
## What changed
- add a shared `ExtensionFuture` alias and use it for asynchronous
contributor methods
- migrate production and test implementations to return `Box::pin(async
move { ... })`
- remove `async-trait` dependencies where they are no longer used,
keeping it dev-only where unrelated test executors still require it
## Behavior
No behavior change is intended. Contributor futures remain boxed,
`Send`, dynamically dispatched, and lazily executed; cancellation and
callback ordering stay unchanged.
## Testing
- `just test -p codex-extension-api` (11 passed)
- affected extension crates (64 passed)
- targeted `codex-core` contributor tests (14 passed)
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
A broad local `codex-core` run compiled successfully but encountered
unrelated sandbox and missing test-binary fixture failures; CI will run
the full checks.
## Why
- Currently, there is no analytics event for `/goal` behavior
- Existing events cannot identify goal execution or its resulting
outcome
- The original update in
[#26182](https://github.com/openai/codex/pull/26182) was implemented
before `/goal` moved into `codex-goal-extension`.
## What Changed
- Adds `codex_goal_event` serialization and enrichment to
`codex-analytics`
- Emits goal events from the canonical `codex-goal-extension` mutation
and accounting paths:
- `created` when a new logical goal is persisted
- `usage_accounted` when cumulative goal usage is persisted
- `status_changed` when the stored goal status changes
- `cleared` when the goal is deleted
- Preserves causal `turn_id` for turn driven events and uses null
attribution for external or idle lifecycle events
- Changes goal deletion to return the deleted row so `cleared` retains
the stable goal ID
## Event Details
Includes standard analytics metadata along with goal specific fields:
- `goal_id`: Stable ID stored in the local SQLite goal row and shared
across the goal's events
- `event_kind`: Observed operation (see the 4 lifecycle events cited in
the above bullet)
- `goal_status`: Resulting or last stored status: `active`, `paused`,
`blocked`, `usage_limited`, etc.
- `has_token_budget`: Indicates whether a token budget is configured
- `turn_id`: Causal turn ID, or null when no causal turn exists
- `cumulative_tokens_accounted`: Cumulative tokens on `usage_accounted`
events; null otherwise
- `cumulative_time_accounted_seconds`: Cumulative active time on
`usage_accounted` events; null otherwise
## Validation
- `just test -p codex-analytics -p codex-state -p codex-goal-extension`
- `just test -p codex-core -E 'test(/goal/)'`
- `just test -p codex-app-server`
- `cargo build -p codex-analytics -p codex-core -p codex-state -p
codex-app-server`
## Why
Memory startup used hardcoded OpenAI model slugs for extraction and
consolidation. That works for the default OpenAI-compatible path, but
provider-specific backends can require different model identifiers. In
particular, Amazon Bedrock should use its Bedrock model ID for these
background memory requests instead of the OpenAI `gpt-5.4-mini` /
`gpt-5.4` slugs.
## What Changed
- Added provider-owned preferred memory model methods alongside
`approval_review_preferred_model`.
- Updated memory extraction and consolidation to resolve their default
model through the active `ModelProvider`.
- Added Amazon Bedrock overrides so both memory stages use
`openai.gpt-5.4` through Bedrock’s provider-specific model ID.
- Kept explicit `memories.extract_model` and
`memories.consolidation_model` config overrides taking precedence.
- Added startup coverage for default OpenAI and Bedrock memory model
selection.
#closes #26288
## Stack
- Base: #27184
- This PR is the second vertical and should be reviewed against
`jif/external-plugins-1`, not `main`.
## Why
CCA is moving toward a split runtime where the orchestrator may have no
filesystem or executor, but it still needs to activate remotely hosted
plugin components. HTTP MCP servers are the simplest complete example:
they need configuration and host authentication, but they do not need an
executor process.
The Apps MCP endpoint is currently synthesized by a special-purpose
loader inside the MCP runtime. That works locally, but it leaves hosted
MCP activation outside the extension model being established in #27184.
It also makes the Apps path a poor foundation for plugins whose skills,
MCP servers, connectors, and hooks may come from different sources or
execute in different places.
This PR moves that one behavior behind an extension-owned contribution
while preserving the existing local fallback. It deliberately does not
introduce a generic plugin activation framework.
## What changed
### MCP extension contribution
`codex-extension-api` gains an ordered `McpServerContributor` contract.
A contributor returns typed `Set` or `Remove` overlays for MCP server
configuration; later contributors win for the names they own.
The contract stays at the existing MCP configuration boundary.
Extensions do not create a second connection manager or transport
abstraction.
### Hosted Apps MCP extension
A new `codex-mcp-extension` contributes the reserved `codex_apps` server
from the existing Apps feature, ChatGPT base URL, path override, and
product SKU configuration.
When `apps_mcp_path_override` is enabled for `https://chatgpt.com`, the
resulting streamable HTTP endpoint is
`https://chatgpt.com/backend-api/ps/mcp`. The existing ChatGPT-auth gate
remains authoritative, so this server can run in an orchestrator-only
process without being exposed for API-key sessions.
### One resolved runtime view
`McpManager` now distinguishes three views:
- **configured:** config- and plugin-backed servers before extension
overlays;
- **runtime:** configured servers plus host-installed extension
contributions;
- **effective:** runtime servers after auth gating and compatibility
built-ins.
App-server installs the hosted MCP extension and uses the runtime view
for thread startup, refresh, status, threadless resource reads,
connector discovery, and MCP OAuth lookup. This keeps
`mcpServer/oauth/login` consistent with the servers exposed by the other
MCP APIs. The hosted Apps server itself continues to use existing
ChatGPT host authentication rather than MCP OAuth.
## Compatibility
Hosts that do not install the MCP extension retain the existing Apps MCP
synthesis path. This preserves current local-only, CLI, and
standalone-host behavior while app-server exercises the extension path.
Disabling Apps removes the reserved `codex_apps` entry, and losing
ChatGPT auth removes it from the effective runtime view. Executor
availability is not consulted for this HTTP transport.
## Follow-ups
The next vertical will resolve a manifest-declared stdio MCP server from
an executor-selected plugin root and execute it in the environment that
owns that root. Later verticals can add backend-owned skills, connector
metadata, hooks, durable selection semantics, and incremental local
convergence without changing the component-specific runtime boundaries
introduced here.
## Verification
Focused coverage was added for:
- contributing the hosted Apps MCP at `/backend-api/ps/mcp` without an
executor;
- requiring ChatGPT auth in the effective runtime view;
- removing a reserved configured Apps server when the Apps feature is
disabled.
`cargo check -p codex-app-server -p codex-mcp-extension -p
codex-extension-api -p codex-mcp` passed. Tests and Clippy were not run
locally under the current development instruction; CI provides the full
validation pass.
## Why
`codex-extension-api` defines contracts shared by extension crates and
their hosts, but it had no direct test suite. Host and feature tests
cover downstream behavior, while regressions in the API crate's own
typed state, registry ordering, and capability adapters could go
unnoticed.
## What
- Add public-surface integration tests for `ExtensionData`, including
concurrent initialization and poison recovery.
- Cover contributor registration order, approval short-circuiting, event
sink retention, no-op response injection, and closure-based agent
spawning.
- Add the test-only dependencies used by the suite.
## Validation
- `just test -p codex-extension-api`
- `just argument-comment-lint -p codex-extension-api`
- `just bazel-lock-check`
## Why
CCA is moving toward a split runtime where the orchestrator may not have
a filesystem, while executors can expose preinstalled plugins and
skills. A thread therefore needs to select capabilities without asking
app-server or core to interpret executor-owned paths through the
orchestrator's filesystem.
The longer-term model is broader than executor skills:
- A plugin is a bundle of skills, MCP servers, connectors/apps, and
hooks.
- A plugin root can be local, executor-owned, or hosted by a backend.
- Components inside one plugin can use different access and execution
mechanisms. A skill may be read from a filesystem or through backend
tools; an HTTP MCP server can run without an executor; a stdio MCP
server or hook needs an execution environment.
- Core should carry generic extension initialization data. The extension
that owns a component should discover it, expose it to the model, and
invoke it through the appropriate runtime.
This PR establishes that architecture through one complete vertical:
selecting a root on an executor, discovering the skills beneath it,
exposing those skills to the model, and reading an explicitly invoked
`SKILL.md` through the same executor.
## Contract
`thread/start` gains an experimental `selectedCapabilityRoots` field:
```json
{
"selectedCapabilityRoots": [
{
"id": "deploy-plugin@1",
"location": {
"type": "environment",
"environmentId": "workspace",
"path": "/opt/codex/plugins/deploy"
}
}
]
}
```
The root is intentionally not classified as a "plugin" or "skill" in the
API. It can point at a standalone skill, a directory containing several
skills, or a plugin containing skills and other components. This PR only
teaches the skills extension how to consume it; later extensions can
resolve MCP, connector, and hook components from the same selection.
The platform-supplied `id` is stable selection identity. The location
says which runtime owns the root and gives that runtime an opaque path.
App-server does not inspect or canonicalize the path.
## What changed
### Generic thread extension initialization
App-server converts selected roots into `ExtensionDataInit`. Core
carries that generic initialization value until the final thread ID is
known, then creates thread-scoped `ExtensionData` before lifecycle
contributors run.
This keeps `Session` and core independent of the capability-selection
contract. The initialization value is consumed during construction; it
is not retained as another long-lived `Session` field.
### Executor-backed skills
The skills extension now owns an `ExecutorSkillProvider` that:
- resolves the selected environment through `EnvironmentManager`
- discovers, canonicalizes, and reads skills through that environment's
`ExecutorFileSystem`
- contributes the bounded selected-skill catalog as stable developer
context
- reads an explicitly invoked skill body through the authority that
listed it
- warns when an environment or root is unavailable
- never falls back to the orchestrator filesystem for an executor-owned
root
Skill catalog and instruction fragments have hard byte bounds, which
also bound them below the 10K-token per-item context limit. If a
selected executor skill has the same name as a legacy local skill, the
executor selection owns that invocation and the local body is not
injected a second time.
Existing local and bundled skill loading remains in place. Omitting
`selectedCapabilityRoots` therefore preserves current local-only
behavior.
## Current semantics
- Only environment-owned locations are represented in this first
contract.
- Roots are resolved by the destination extension, not by app-server or
core.
- An unavailable executor or invalid root produces a warning and no
capabilities from that root; it does not trigger a local-filesystem
fallback.
- Selection applies to a newly started active thread.
- MCP servers, connectors, and hooks beneath a selected plugin root are
not activated yet.
- Selection is not yet persisted or inherited across resume, fork, or
subagent creation. Existing local capabilities continue to behave as
they do today in those flows.
## Planned vertical follow-ups
1. **Hosted HTTP MCP:** add an extension-backed HTTP MCP source that
works without an executor, then replace the special-purpose MCP plugins
loader with that implementation.
2. **Executor MCP:** register and execute stdio MCP servers through the
environment that owns the selected plugin root.
3. **Backend skills:** add a hosted skill source whose catalog and
bodies are accessed through extension tools rather than a filesystem.
4. **Connectors and hooks:** activate those components through their
owning extensions, using the same selected-root boundary and
component-specific runtime.
5. **Durable selection:** define the desired-selection lifecycle,
persist it, and make resume, fork, and subagent inheritance explicit
rather than accidental.
6. **Local convergence:** incrementally route existing local plugin,
skill, and MCP loading through the same extension model while preserving
current local behavior.
Each follow-up remains reviewable as an end-to-end capability. The
platform selects roots, generic thread extension data carries the
selection, and the owning extension resolves and operates its component.
## Verification
Coverage added for:
- app-server end-to-end discovery and explicit invocation of a skill
inside an executor-selected plugin root
- exclusive invocation when a selected executor skill collides with a
local skill name
- executor filesystem authority for discovery, canonicalization, and
reads
- thread extension initialization before lifecycle contributors run
- stable executor catalog context, explicit invocation, context
rebuilding, hidden skills, and preserved host/remote catalog behavior
Targeted protocol, core-skills, skills-extension, core lifecycle, and
app-server executor-skill tests were run during development.
## Why
Codex needs stable `file:` URI identifiers that can cross process and
operating-system boundaries without eagerly interpreting them as native
paths. Existing fields also need to keep accepting absolute path strings
during migration.
## What changed
- Add `codex-utils-path-uri` with a validated, immutable `PathUri`
wrapper that currently accepts only `file:` URLs.
- Expose URI-level `basename`, `parent`, and `join` operations that
preserve authorities and percent encoding without guessing the source
operating system.
- Keep native conversion explicit through `AbsolutePathBuf` and the
current host rules.
- Serialize as canonical URI text while accepting both URI text and
legacy absolute native paths during deserialization.
- Add adversarial coverage for Windows-looking and POSIX paths, UNC
authorities, encoded metadata characters, non-UTF-8 POSIX paths, URI
hierarchy operations, and legacy serde round trips.
## Why
Image edits should use the exact images selected by the model instead of
inferring edit inputs from conversation history.
## What changed
- Replaced the image tool's `action` argument with optional
`referenced_image_paths`.
- Treats omitted or empty references as generation and populated
references as editing.
- Reads referenced absolute image paths and packages them as image data
URLs for the edit request.
- Removed the previous history-selection and image-count heuristics.
- Updated direct and code-mode tool instructions and calls.
- Added an app-server integration test covering an attached image routed
to the image edit endpoint.
## Validation
- Tested end-to-end on local `just codex` with copy pasted image,
attached image, etc.
- `just test -p codex-image-generation-extension`
- `just test -p codex-app-server
standalone_image_edit_uses_attached_model_visible_image`
- `just fix -p codex-image-generation-extension`
- `just bazel-lock-check`
## Summary
Responses Lite does not execute hosted Responses tools, so models using
it must route web search and image generation through Codex-owned
executors & standalone Response's API endpoints.
This PR is stacked on #26487.
## Validation
- `cargo test -p codex-core responses_lite_ --lib`
- `cargo test -p codex-core
standalone_executors_remain_hidden_without_flags_or_responses_lite
--lib`
- `cargo test -p codex-core
hosted_tools_follow_provider_auth_model_and_config_gates --lib`
- `cargo test -p codex-web-search-extension -p
codex-image-generation-extension`
- `cargo test -p codex-app-server --test all standalone_`
- `cargo fmt --all -- --check`
## Stack
1. [#26547](https://github.com/openai/codex/pull/26547) - [1 of 2] Align
goal extension with core behavior
2. [#26548](https://github.com/openai/codex/pull/26548) - [2 of 2] Move
goal runtime to extension
## Why
This PR completes the switch of the goal behavior to the
extension-backed runtime and removes the old core goal implementation.
## What Changed
- Installs the goal extension for app-server `ThreadManager` sessions.
- Routes app-server thread goal `get`, `set`, and `clear` through
`GoalService`.
- Uses thread-idle lifecycle emission after goal resume and snapshot
ordering so the extension can decide whether to continue the goal.
- Forwards extension goal updates through a FIFO async app-server
notification path so backpressure does not drop them or reorder updates.
- Keeps review turns from enabling goal runtime behavior.
- Plans extension tools before dynamic tools so built-in goal tool names
keep their old precedence when goals are enabled.
- Removes the old core goal runtime, core goal tool handlers, and core
goal tool specs.
- Updates tests that were coupled to the core-owned goal runtime while
leaving the legacy `<goal_context>` compatibility path in core for old
threads.
- Removes the stale cargo-shear ignore now that `codex-goal-extension`
is used by the workspace.
- Keeps realtime event matching exhaustive after removing the old
goal-specific realtime text path.
## Validation
- Ran manual `/goal` runs in TUI. Validated time accounting matched
wall-clock time and goal lifecycle state transitions.
Adrian ·
Eric Ning ·
jif ·
iceweasel-oai ·
Alex Daley ·
pakrym-oai ·
Adam Perry @ OpenAI ·
viyatb-oai ·
Matthew Zeng ·
felixxia-oai ·
Gabriel Peal ·
xl-openai ·
Celia Chen ·
Eric Traut ·
alexsong-oai ·
cooper-oai ·
Channing Conger ·
Won Park ·
marksteinbrick-oai ·
Michael Bolin ·
rka-oai ·