codex

fix: auth preflight (#18117 )

Fix app-server startup when `remote_control = true` is enabled without
ChatGPT auth.

Remote control now starts in a degraded/retrying state instead of
failing app-server initialization, so Desktop is not stranded before the
initial initialize handshake.

jif-oai · 2026-04-16 16:17:11 +01:00

76ea694db5

Stabilize Bazel tests (timeout tweaks and flake fixes) (#17791 )

David de Regt · 2026-04-16 07:57:51 -07:00

6adba99f4d

chore: unify memory drop endpoints (#18134 )

Unify all the memories drop behind a single implementation that drops
both the main memories and the extensions

jif-oai · 2026-04-16 15:44:23 +01:00

b33478c236

debug: windows flake (#18135 )

Make sure Bazel logs shows every errors so that we can debug flakes +
fix a small flake on Windows by updating the sleep command to a
`Start-Sleep` instead of a PowerShell nested command (otherwise we had
double nesting which is absurdely slow)

jif-oai · 2026-04-16 14:51:47 +01:00

de98b1d3e8

Fix MCP startup cancellation through app server (#18078 )

Addresses https://github.com/openai/codex/issues/17143

Problem: TUI interrupts without an active turn stopped cancelling slow
MCP startup after routing through the app-server APIs.

Solution: Route no-active-turn interrupts through app-server as startup
cancels, acknowledge them immediately, and emit cancelled MCP startup
updates.

Testing: I manually confirmed that MCP cancellation didn't work prior to
this PR and works after the fix was in place.

Eric Traut · 2026-04-16 00:03:50 -07:00

4cd85b28d2

Extract plugin loading and marketplace logic into codex-core-plugins (#18070 )

Split plugin loading, marketplace, and related infrastructure out of
core into codex-core-plugins, while keeping the core-facing
configuration and orchestration flow in codex-core.

---------

Co-authored-by: Codex <noreply@openai.com>

xl-openai · 2026-04-15 23:13:17 -07:00

48cf3ed7b0

[codex][mcp] Add resource uri meta to tool call item. (#17831 )

- [x] Add resource uri meta to tool call item so that the app-server
client can start prefetching resources immediately without loading mcp
server status.

Matthew Zeng · 2026-04-16 05:09:17 +00:00

224dad41ac

Async config loading (#18022 )

Parts of config will come from executor. Prepare for that by making
config loading methods async.

pakrym-oai · 2026-04-15 19:18:38 -07:00

bd61737e8a

[codex] Make command exec delta tests chunk tolerant (#17999 )

## Summary
- Make command/exec output-delta tests accumulate streamed chunks
instead of assuming complete logical output in a single notification.
- Collect stdout and stderr independently so stream interleaving does
not fail the pipe streaming test.

## Why
The command/exec protocol exposes output as deltas, so tests should not
rely on chunk boundaries being stable. A line like `out-start\n` may
arrive split across multiple notifications, and stdout/stderr
notifications may interleave.

## Validation
- `just fmt`
- `git diff --check`
- `cargo test -p codex-app-server suite::v2::command_exec`

Ruslan Nigmatullin · 2026-04-15 17:57:02 -07:00

f948690fc8

Clarify realtime v2 context and handoff messages (#17896 )

## Summary
- wrap realtime startup context in
`<startup_context>...</startup_context>` tags
- prefix V2 mirrored user text and relayed backend text with `[USER]` /
`[BACKEND]`
- remove the V2 progress suffix and replace the final V2 handoff output
with a short completion acknowledgement while preserving the existing V1
wrapper

## Testing
- cargo test -p codex-api
realtime_v2_session_update_includes_background_agent_tool_and_handoff_output_item
-- --exact
- cargo test -p codex-app-server webrtc_v2_background_agent_
- cargo test -p codex-app-server webrtc_v2_text_input_is_
- cargo test -p codex-core conversation_user_text_turn_is_

bxie-openai · 2026-04-15 16:26:20 -07:00

c2bdb7812c

[docs] Revert extra changes from PR 17848 (#18003 )

## Summary

1. Revert https://github.com/openai/codex/pull/17848 so the Bazel and
`BUILD` file changes leave `main`.
2. Prepare for a narrower follow up that restores only `SECURITY.md`.

## Validation

1. Reviewed the revert diff against `main`.
2. Ran a clean diff check before push.

evawong-oai · 2026-04-15 14:43:30 -07:00

17d94bd1e3

Dismiss stale app-server requests after remote resolution (#15134 )

Dismiss stale TUI app-server approvals after remote resolution

When an approval, user-input prompt, or elicitation request is resolved
by another client, the TUI now dismisses the matching local UI instead
of leaving stale prompts behind and emitting a misleading local
cancellation.

This change teaches pending app-server request tracking to map
`serverRequest/resolved` notifications back to the concrete request type
and stable request key, then propagates that resolved request into TUI
prompt state. Approval, request-user-input, and MCP elicitation overlays
now drop the resolved current or queued request quietly, advance to the
next queued request when present, and avoid emitting abort/cancel events
for stale UI.

The latest update also retires matching prompts while they are still
deferred behind active streaming and suppresses buffered active-thread
requests whose app-server request id has already been resolved before
drain. `ChatWidget` removes a resolved request from both the deferred
interrupt queue and the materialized bottom-pane stack, while
active-thread request handling verifies the app-server request is still
pending before showing a prompt. Lifecycle events such as exec begin/end
remain queued so approved work can still render normally.

Tests cover resolved-request mapping, overlay dismissal behavior,
deferred prompt pruning for same-turn user input, exec approval IDs,
lifecycle-event retention, and the buffered active-thread ordering
regression.

Validation:
- `just fmt`
- `git diff --check`
- `cargo test -p codex-tui
resolved_buffered_approval_does_not_become_actionable_after_drain`
- `cargo test -p codex-tui
enqueue_primary_thread_session_replays_buffered_approval_after_attach`
- `cargo test -p codex-tui chatwidget::interrupts`
- `just fix -p codex-tui`

---------

Co-authored-by: Codex <noreply@openai.com>

Eugene Brevdo · 2026-04-15 13:57:41 -07:00

bc969b6516

Migrate archive/unarchive to local ThreadStore (#17892 )

# Summary
- implement local ThreadStore archive/unarchive operations
- implement local ThreadStore read_thread operation
- break up the various ThreadStore local method implementations into
separate files
- migrate app-server archive/unarchive and core archive fixture to use
ThreadStore (but not all read operations yet!)
- use the ThreadStore's read operation as a proxy check for thread
persistence/existence in the app server code
- move all other filesystem operations related to archive (path
validation etc) into the local thread store.

# Tests
- add dedicated local store archive/unarchive tests

Tom · 2026-04-15 20:48:09 +00:00

50d3128269

[docs] Add security boundaries reference in SECURITY.md (#17848 )

## Summary
1. Add a Security Boundaries section to `SECURITY.md`.
2. Point readers to the Codex Agent approvals and security documentation
for sandboxing, approvals, and network controls.

## Validation
1. Reviewed the `SECURITY.md` diff in a clean worktree.
2. No tests run. Docs only change.

evawong-oai · 2026-04-15 20:12:46 +00:00

0bb438bca6

fix: propagate log db (#17953 )

It restores the TRACE logs in the DB and `/feedback`
Fix https://github.com/openai/codex/pull/16184 

Result:
https://openai.sentry.io/issues/6972946529/?project=4510195390611458&query=019d91e9-f931-7451-8852-c5240514a419&referrer=issue-stream

jif-oai · 2026-04-15 20:25:53 +01:00

7e7b35b4d2

app-server: track remote-control seq IDs per stream (#17902 )

## Summary

- Track outbound remote-control sequence IDs independently for each
client stream.
- Retain unacked outbound messages per stream using FIFO buffers.
- Require stream-scoped acks and update tests for contiguous per-stream
sequencing.

## Why

The remote-control peer uses outbound sequence gaps to detect lost
messages and re-initialize. A single global outbound sequence counter
can create apparent gaps on an individual stream when another stream
receives an interleaved message.

## Validation

- `just fmt`
- `cargo test -p codex-app-server remote_control`
- `just fix -p codex-app-server`
- `git diff --check`

Ruslan Nigmatullin · 2026-04-15 11:52:53 -07:00

83abf67d20

[codex] Add local thread store listing (#17824 )

Builds on top of #17659 

Move the filesystem + sqlite thread listing-related operations inside of
a local ThreadStore implementation and call ThreadStore from the places
that used to perform these filesystem/sqlite operations.

This is the first of a series of PRs that will implement the rest of the
local ThreadStore.

Testing:
- added unit tests for the thread store implementation
- adjusted some unit tests in the realtime + personality packages whose
callsites changed. Specifically I'm trying to hide ThreadMetadata inside
of the local implementation and make ThreadMetadata a sqlite
implementation detail concern rather than a public interface, preferring
the more generate StoredThread interface instead
- added a corner case test for the personality migration package that
wasn't covered by the existing test suite
- adjust the behavior of searched thread listing to run the existing
local rollout repair/backfill pass _before_ querying SQLite results, so
callers using ThreadStore::list_threads do not miss matches after a
partial metadata warm-up

Tom · 2026-04-15 11:34:27 -07:00

cdfcd2ca92

Register agent identities behind use_agent_identity (#17386 )

## Summary

Stack PR 2 of 4 for feature-gated agent identity support.

This PR adds agent identity registration behind
`features.use_agent_identity`. It keeps the app-server protocol
unchanged and starts registration after ChatGPT auth exists rather than
requiring a client restart.

## Stack

- PR1: https://github.com/openai/codex/pull/17385 - add
`features.use_agent_identity`
- PR2: https://github.com/openai/codex/pull/17386 - this PR
- PR3: https://github.com/openai/codex/pull/17387 - register agent tasks
when enabled
- PR4: https://github.com/openai/codex/pull/17388 - use `AgentAssertion`
downstream when enabled

## Validation

Covered as part of the local stack validation pass:

- `just fmt`
- `cargo test -p codex-core --lib agent_identity`
- `cargo test -p codex-core --lib agent_assertion`
- `cargo test -p codex-core --lib websocket_agent_task`
- `cargo test -p codex-api api_bridge`
- `cargo build -p codex-cli --bin codex`

## Notes

The full local app-server E2E path is still being debugged after PR
creation. The current branch stack is directionally ready for review
while that follow-up continues.

Adrian · 2026-04-15 10:08:27 -07:00

8e784bba2f

nit: doc (#17941 )

jif-oai · 2026-04-15 14:51:20 +01:00

ea13527961

register all mcp tools with namespace (#17404 )

stacked on #17402.

MCP tools returned by `tool_search` (deferred tools) get registered in
our `ToolRegistry` with a different format than directly available
tools. this leads to two different ways of accessing MCP tools from our
tool catalog, only one of which works for each. fix this by registering
all MCP tools with the namespace format, since this info is already
available.

also, direct MCP tools are registered to responsesapi without a
namespace, while deferred MCP tools have a namespace. this means we can
receive MCP `FunctionCall`s in both formats from namespaces. fix this by
always registering MCP tools with namespace, regardless of deferral
status.

make code mode track `ToolName` provenance of tools so it can map the
literal JS function name string to the correct `ToolName` for
invocation, rather than supporting both in core.

this lets us unify to a single canonical `ToolName` representation for
each MCP tool and force everywhere to use that one, without supporting
fallbacks.

sayan-oai · 2026-04-15 21:02:59 +08:00

0df7e9a820

chore: do not disable memories for past rollouts on reset (#17919 )

jif-oai · 2026-04-15 12:05:39 +01:00

5e544be3c9

feat: add endpoint to delete memories (#17913 )

jif-oai · 2026-04-15 10:35:06 +01:00

7579d5ad75

fix: add websocket capability token hash support (#17871 )

## Summary
- Allow app-server websocket capability auth to accept a precomputed
SHA-256 digest via `--ws-token-sha256`.
- Keep token-file support and enforce exactly one capability token
source.
- Document the new auth flag.

## Testing
- `just fmt`
- `cargo test -p codex-app-server transport::auth::tests`
- `cargo test -p codex-app-server
websocket_capability_token_sha256_args_parse`
- `cargo test -p codex-cli app_server_capability_token_flags_parse`
- `cargo clippy -p codex-app-server --all-targets -- -D warnings`
- `just fix -p codex-cli`

---------

Co-authored-by: Codex <noreply@openai.com>

viyatb-oai · 2026-04-14 22:06:39 -07:00

e4a3612f11

support plugins in external agent config migration (#17855 )

alexsong-oai · 2026-04-14 19:39:10 -07:00

ca650561d6

[codex] Support local marketplace sources (#17756 )

## Summary

- Port marketplace source support into the shared core marketplace-add
flow
- Support local marketplace directory sources
- Support direct `marketplace.json` URL sources
- Persist the new source types in config/schema and cover them in CLI
and app-server tests

## Validation

- `cargo test -p codex-core marketplace_add`
- `cargo test -p codex-cli marketplace_add`
- `cargo test -p codex-app-server marketplace_add`
- `just write-config-schema`
- `just fmt`
- `just fix -p codex-core`
- `just fix -p codex-cli`

## Context

Current `main` moved marketplace-add behavior into shared core code and
still assumed only git-backed sources. This change keeps that structure
but restores support for local directories and direct manifest URLs in
the shared path.

xli-oai · 2026-04-14 15:58:14 -07:00

3cc689fb23

Make skill loading filesystem-aware (#17720 )

Migrates skill loading to support reading repo skills from the remote
environment.

pakrym-oai · 2026-04-14 15:40:40 -07:00

96254a763a

fix: apply patch bin refresh (#17808 )

Make sure the link to apply patch binary (i.e. codex) does not die in
case of an update

Fix this:
https://openai.slack.com/archives/C08MGJXUCUQ/p1776183247771849

---------

Co-authored-by: Codex <noreply@openai.com>

jif-oai · 2026-04-14 22:27:47 +01:00

42166ba260

Spread AbsolutePathBuf (#17792 )

Mechanical change to promote absolute paths through code.

pakrym-oai · 2026-04-14 14:26:10 -07:00

dd1321d11b

[codex-analytics] enable general analytics by default (#17389 )

## Summary
- Make GeneralAnalytics stable and enabled by default.
- Update feature tests and app-server lifecycle fixtures for explicit
general_analytics=false.
- Keep app-server integration tests isolated from host managed config so
explicit feature fixtures are deterministic.

## Validation
- cargo test -p codex-features
- cargo test -p codex-app-server general_analytics (matched 0 tests)
- cargo test -p codex-app-server thread_start_
- cargo test -p codex-app-server thread_fork_
- cargo test -p codex-app-server thread_resume_
- cargo test -p codex-app-server
config_read_includes_system_layer_and_overrides

rhan-oai · 2026-04-14 13:20:46 -07:00

d6b13276c7

[codex] Fix app-server initialized request analytics build (#17830 )

Problem: PR #17372 moved initialized request handling into
`dispatch_initialized_client_request`, leaving analytics code that uses
`connection_id` without a local binding and breaking `codex-app-server`
builds.

Solution: Restore the `connection_id` binding from
`connection_request_id` before initialized request validation and
analytics tracking.

Eric Traut · 2026-04-14 13:11:04 -07:00

1fd9c33207

app-server: prepare to run initialized rpcs concurrently (#17372 )

## Summary

- Refactors `MessageProcessor` and per-connection session state so
initialized service RPC handling can be moved into spawned tasks in a
follow-up PR.
- Shares the processor and initialized session data with
`Arc`/`OnceLock` instead of mutable borrowed connection state.
- Keeps initialized request handling synchronous in this PR; it does
**not** call `tokio::spawn` for service RPCs yet.

## Testing

- `just fmt`
- `cargo test -p codex-app-server` *(fails on existing hardening gaps
covered by #17375, #17376, and #17377; the pipelined config regression
passed before the unrelated failures)*
- `just fix -p codex-app-server`

Ruslan Nigmatullin · 2026-04-14 11:24:34 -07:00

23d4098c0f

fix: Revert danger-full-access denylist-only mode (#17732 )

## Summary

- Reverts openai/codex#16946 and removes the danger-full-access
denylist-only network mode.
- Removes the corresponding config requirements, app-server
protocol/schema, config API, TUI debug output, and network proxy
behavior.
- Drops stale tests that depended on the reverted mode while preserving
newer managed allowlist-only coverage.

## Verification

- `just write-app-server-schema`
- `just fmt`
- `cargo test -p codex-config network_requirements`
- `cargo test -p codex-core network_proxy_spec`
- `cargo test -p codex-core
managed_network_proxy_decider_survives_full_access_start`
- `cargo test -p codex-app-server map_requirements_toml_to_api`
- `cargo test -p codex-tui debug_config_output`
- `cargo test -p codex-app-server-protocol`
- `just fix -p codex-config -p codex-core -p codex-app-server-protocol
-p codex-app-server -p codex-tui`
- `git diff --cached --check`

Not run: full workspace `cargo test` (repo instructions ask for
confirmation before that broader run).

viyatb-oai · 2026-04-14 09:50:14 -07:00

81c0bcc921

Moving updated-at timestamps to unique millisecond times (#17489 )

To allow the ability to have guaranteed-unique cursors, we make two
important updates:
* Add new updated_at_ms and created_at_ms columns that are in
millisecond precision
* Guarantee uniqueness -- if multiple items are inserted at the same
millisecond, bump the new one by one millisecond until it becomes unique

This lets us use single-number cursors for forwards and backwards paging
through resultsets and guarantee that the cursor is a fixed point to do
(timestamp > cursor) and get new items only.

This updated implementation is backwards-compatible since multiple
appservers can be running and won't handle the previous method well.

David de Regt · 2026-04-14 11:55:34 -04:00

4f2fc3e3fa

Add realtime output modality and transcript events (#17701 )

- Add outputModality to thread/realtime/start and wire text/audio output
selection through app-server, core, API, and TUI.\n- Rename the realtime
transcript delta notification and add a separate transcript done
notification that forwards final text from item done without correlating
it with deltas.

Ahmed Ibrahim · 2026-04-14 00:13:13 -07:00

2f6fc7c137

[codex-analytics] feature plumbing and emittance (#16640 )

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16640).
* #16870
* #16706
* #16641
* __->__ #16640

rhan-oai · 2026-04-13 23:11:49 -07:00

b704df85b8

Refactor plugin loading to async (#17747 )

Simplifies skills migration.

pakrym-oai · 2026-04-13 21:52:56 -07:00

3b24a9a532

[codex] Refactor marketplace add into shared core flow (#17717 )

## Summary

Move `codex marketplace add` onto a shared core implementation so the
CLI and app-server path can use one source of truth.

This change:
- adds shared marketplace-add orchestration in `codex-core`
- switches the CLI command to call that shared implementation
- removes duplicated CLI-only marketplace add helpers
- preserves focused parser and add-path coverage while moving the shared
behavior into core tests

## Why

The new `marketplace/add` RPC should reuse the same underlying
marketplace-add flow as the CLI. This refactor lands that consolidation
first so the follow-up app-server PR can be mostly protocol and handler
wiring.

## Validation

- `cargo test -p codex-core marketplace_add`
- `cargo test -p codex-cli marketplace_cmd`
- `just fix -p codex-core`
- `just fix -p codex-cli`
- `just fmt`

xli-oai · 2026-04-13 20:37:11 -07:00

ff584c5a4b

[codex] Add symlink flag to fs metadata (#17719 )

Add `is_symlink` to FsMetadata struct.

pakrym-oai · 2026-04-13 17:46:56 -07:00

f3cbe3d385

Add turn item injection API (#17703 )

## Summary
- Add `turn/inject_items` app-server v2 request support for appending
raw Responses API items to a loaded thread history without starting a
turn.
- Generate JSON schema and TypeScript protocol artifacts for the new
params and empty response.
- Document the new endpoint and include a request/response example.
- Preserve compatibility with the typo alias `turn/injet_items` while
returning the canonical method name.

## Testing
- Not run (not requested)

pakrym-oai · 2026-04-13 16:11:05 -07:00

d4be06adea

change realtime tool description (#17699 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

Ahmed Ibrahim · 2026-04-13 14:31:31 -07:00

0e31dc0d4a

app-server: Only unload threads which were unused for some time (#17398 )

Currently app-server may unload actively running threads once the last
connection disconnects, which is not expected.
Instead track when was the last active turn & when there were any
subscribers the last time, also add 30 minute idleness/no subscribers
timer to reduce the churn.

Ruslan Nigmatullin · 2026-04-13 12:25:26 -07:00

a5507b59c4

feat: disable memory endpoint (#17626 )

jif-oai · 2026-04-13 18:29:49 +01:00

46a266cd6a

Use AbsolutePathBuf in skill loading and codex_home (#17407 )

Helps with FS migration later

pakrym-oai · 2026-04-13 10:26:51 -07:00

ac82443d07

Do not fail thread start when trust persistence fails (#17595 )

Addresses #17593

Problem: A regression introduced in
https://github.com/openai/codex/pull/16492 made thread/start fail when
Codex could not persist trusted project state, which crashes startup for
users with read-only config.toml.

Solution: Treat trusted project persistence as best effort and keep the
current thread's config trusted in memory when writing config.toml
fails.

Eric Traut · 2026-04-13 10:03:21 -07:00

d25a9822a7

Suppress duplicate compaction and terminal wait events (#17601 )

Addresses #17514

Problem: PR #16966 made the TUI render the deprecated context-compaction
notification, while v2 could also receive legacy unified-exec
interaction items alongside terminal-interaction notifications, causing
duplicate "Context compacted" and "Waited for background terminal"
messages.

Solution: Suppress deprecated context-compaction notifications and
legacy unified-exec interaction command items from the app-server v2
projection, and render canonical context-compaction items through the
existing TUI info-event path.

Eric Traut · 2026-04-13 08:59:19 -07:00

7c797c6544

Run exec-server fs operations through sandbox helper (#17294 )

## Summary
- run exec-server filesystem RPCs requiring sandboxing through a
`codex-fs` arg0 helper over stdin/stdout
- keep direct local filesystem execution for `DangerFullAccess` and
external sandbox policies
- remove the standalone exec-server binary path in favor of top-level
arg0 dispatch/runtime paths
- add sandbox escape regression coverage for local and remote filesystem
paths

## Validation
- `just fmt`
- `git diff --check`
- remote devbox: `cd codex-rs && bazel test --bes_backend=
--bes_results_url= //codex-rs/exec-server:all` (6/6 passed)

---------

Co-authored-by: Codex <noreply@openai.com>

starr-openai · 2026-04-12 18:36:03 -07:00

d626dc3895

Add MCP tool wall time to model output (#17406 )

Include MCP wall time in the output so the model is aware of how long
it's calls are taking.

pakrym-oai · 2026-04-12 18:26:15 -07:00

7c1e41c8b6

Expose instruction sources (AGENTS.md) via app server (#17506 )

Addresses #17498

Problem: The TUI derived /status instruction source paths from the local
client environment, which could show stale <none> output or incorrect
paths when connected to a remote app server.

Solution: Add an app-server v2 instructionSources snapshot to thread
start/resume/fork responses, default it to an empty list when older
servers omit it, and render TUI /status from that server-provided
session data.

Additional context: The app-server field is intentionally named
instructionSources rather than AGENTS.md-specific terminology because
the loaded instruction sources can include global instructions, project
AGENTS.md files, AGENTS.override.md, user-defined instruction files, and
future dynamic sources.

Eric Traut · 2026-04-12 15:50:12 -07:00

46ab9974dc

Mirror user text into realtime (#17520 )

- Let typed user messages submit while realtime is active and mirror
accepted text into the realtime text stream.
- Add integration coverage and snapshot for outbound realtime text.

Ahmed Ibrahim · 2026-04-12 15:03:14 -07:00

d840b247d7

Add use_agent_identity feature flag (#17385 )

Adrian · 2026-04-11 09:52:06 -07:00

39cc85310f

785 Commits