codex

codex debug 7 (guardian approved) (#17123 )

Removes lines 43-49 from core/templates/agents/orchestrator.md.

jif-oai · 2026-04-08 14:10:34 +01:00

cb77bbfed0

codex debug 5 (guardian approved) (#17121 )

Removes lines 29-35 from core/templates/agents/orchestrator.md.

jif-oai · 2026-04-08 14:10:28 +01:00

5f1363d6d0

codex debug 3 (guardian approved) (#17119 )

Removes lines 15-21 from core/templates/agents/orchestrator.md.

jif-oai · 2026-04-08 14:10:22 +01:00

8558e8aa51

codex debug 1 (guardian approved) (#17117 )

Removes lines 1-7 from core/templates/agents/orchestrator.md.

jif-oai · 2026-04-08 14:10:15 +01:00

22c1fc0131

Render namespace description for tools (#16879 )

Vivian Fang · 2026-04-08 02:39:40 -07:00

d47b755aa2

Render function attribute descriptions (#16880 )

Vivian Fang · 2026-04-08 02:10:45 -07:00

9091999c83

Support anyOf and enum in JsonSchema (#16875 )

This brings us into better alignment with the JSON schema subset that is
supported in
<https://developers.openai.com/api/docs/guides/structured-outputs#supported-schemas>,
and also allows us to render richer function signatures in code mode
(e.g., anyOf{null, OtherObjectType})

Vivian Fang · 2026-04-08 01:07:55 -07:00

ea516f9a40

fix: refresh network proxy settings when sandbox mode changes (#17040 )

## Summary

Fix network proxy sessions so changing sandbox mode recomputes the
effective managed network policy and applies it to the already-running
per-session proxy.

## Root Cause

`danger_full_access_denylist_only` injects `"*"` only while building the
proxy spec for Full Access. Sessions built that spec once at startup, so
a later permission switch to Full Access left the live proxy in its
original restricted policy. Switching back needed the same recompute
path to remove the synthetic wildcard again.

## What Changed

- Preserve the original managed network proxy config/requirements so the
effective spec can be recomputed for a new sandbox policy.
- Refresh the current session proxy when sandbox settings change, then
reapply exec-policy network overlays.
- Add an in-place proxy state update path while rejecting
listener/port/SOCKS changes that cannot be hot-reloaded.
- Keep runtime proxy settings cheap to snapshot and update.
- Add regression coverage for workspace-write -> Full Access ->
workspace-write.

viyatb-oai · 2026-04-08 03:07:55 +00:00

3c1adbabcd

Use model metadata for Fast Mode status (#16949 )

Fast Mode status was still tied to one model name in the TUI and
model-list plumbing. This changes the model metadata shape so a model
can advertise additional speed tiers, carries that field through the
app-server model list, and uses it to decide when to show Fast Mode
status.

For people using Codex, the behavior is intended to stay the same for
existing models. Fast Mode still requires the existing signed-in /
feature-gated path; the difference is that the UI can now recognize any
model the model list marks as Fast-capable, instead of requiring a new
client-side slug check.

pash-openai · 2026-04-07 17:55:40 -07:00

80ebc80be5

[codex] Apply patches through executor filesystem (#17048 )

## Summary
- run apply_patch through the executor filesystem when a remote
environment is present instead of shelling out to the local process
- thread the executor FileSystem into apply_patch interception and keep
existing local behavior for non-remote turns
- make the apply_patch integration harness use the executor filesystem
for setup/assertions
- add remote-aware skips for turn-diff coverage that still reads the
test-runner filesystem

## Why
Remote apply_patch needed to mutate the remote workspace instead of the
local checkout. The tests also needed to seed and assert workspace state
through the same filesystem abstraction so local and remote runs
exercise the same behavior.

## Validation
- `just fmt`
- `git diff --check`
- `cargo check -p core_test_support --tests`
- `cargo test -p codex-core --test all
suite::shell_serialization::apply_patch_custom_tool_call -- --nocapture`
- `cargo test -p codex-core --test all
suite::apply_patch_cli::apply_patch_cli_updates_file_appends_trailing_newline
-- --nocapture`
- remote `cargo test -p codex-core --test all apply_patch_cli --
--nocapture` (229 passed)

pakrym-oai · 2026-04-07 16:35:02 -07:00

600c3e49e0

Add WebRTC transport to realtime start (#16960 )

Adds WebRTC startup to the experimental app-server
`thread/realtime/start` method with an optional transport enum. The
websocket path remains the default; WebRTC offers create the realtime
session through the shared start flow and emit the answer SDP via
`thread/realtime/sdp`.

---------

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

Ahmed Ibrahim · 2026-04-07 15:43:38 -07:00

fb3dcfde1d

fix(app-server) revert null instructions changes (#17047 )

Dylan Hurd · 2026-04-07 15:18:34 -07:00

6c36e7d688

[codex] Migrate apply_patch to executor filesystem (#17027 )

- Migrate apply-patch verification and application internals to use the
async `ExecutorFileSystem` abstraction from `exec-server`.
- Convert apply-patch `cwd` handling to `AbsolutePathBuf` through the
verifier/parser/handler boundary.

Doesn't change how the tool itself works.

pakrym-oai · 2026-04-07 21:20:22 +00:00

e9702411ab

fix(core) revert Command line in unified exec output (#17031 )

## Summary
https://github.com/openai/codex/pull/13860 changed the serialized output
format of Unified Exec. This PR reverts those changes and some related
test changes

## Testing
- [x] Update tests

---------

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

Dylan Hurd · 2026-04-07 13:35:40 -07:00

d45513ce5a

[codex] Fix unified exec test build (#17032 )

## Summary
- Remove the stale `?` after `AbsolutePathBuf::join` in the unified exec
integration test helper.

## Root Cause
- `AbsolutePathBuf::join` was made infallible, but
`core/tests/suite/unified_exec.rs` still treated it as a `Result`, which
broke the Windows test build for the `all` integration test target.

## Validation
- `just fmt`
- `cargo test -p codex-core --test all
unified_exec_resolves_relative_workdir`

pakrym-oai · 2026-04-07 12:01:06 -07:00

8614f92fc4

Add full-ci branch trigger (#16980 )

Allow branches to trigger full ci (helpful to run remote tests)

pakrym-oai · 2026-04-07 11:33:35 -07:00

470b3592e6

[codex] Make unified exec tests remote aware (#16977 )

## Summary
- Convert unified exec integration tests that can run against the remote
executor to use the remote-aware test harness.
- Create workspace directories through the executor filesystem for
remote runs.
- Install `python3` and `zsh` in the remote test container so restored
Python/zsh-based test commands work in fresh Ubuntu containers.

## Validation
- `just fmt`
- `cargo test -p codex-core --test all unified_exec_defaults_to_pipe`
- `cargo test -p codex-core --test all unified_exec_can_enable_tty`
- `cargo test -p codex-core --test all unified_exec`
- Remote on `codex-remote`: `source scripts/test-remote-env.sh && cd
codex-rs && cargo test -p codex-core --test all unified_exec`
- `just fix -p codex-core`

pakrym-oai · 2026-04-07 10:56:08 -07:00

365154d5da

[codex] Make AbsolutePathBuf joins infallible (#16981 )

Having to check for errors every time join is called is painful and
unnecessary.

pakrym-oai · 2026-04-07 10:52:08 -07:00

f1a2b920f9

fix(guardian): don't throw away transcript when over budget (#16956 )

## Description

This PR changes guardian transcript compaction so oversized
conversations no longer collapse into a nearly empty placeholder.

Before this change, if the retained user history alone exceeded the
message budget, guardian would replace the entire transcript with
`<transcript omitted to preserve budget for planned action>`!

That meant approvals, especially network approvals, could lose the
recent tool call and tool result that explained what guardian was
actually reviewing. Now we keep a compact but usable transcript instead
of dropping it all.

### Before
```
The following is the Codex agent history whose request action you are assessing...
>>> TRANSCRIPT START
<transcript omitted to preserve budget for planned action>
>>> TRANSCRIPT END

Conversation transcript omitted due to size.

The Codex agent has requested the following action:
>>> APPROVAL REQUEST START
Retry reason:
Sandbox blocked outbound network access.

Assess the exact planned action below. Use read-only tool checks when local state matters.
Planned action JSON:
{
  "tool": "network_access",
  "target": "https://example.com:443",
  "host": "example.com",
  "protocol": "https",
  "port": 443
}
>>> APPROVAL REQUEST END
```

### After
```
The following is the Codex agent history whose request action you are assessing...
>>> TRANSCRIPT START
[1] user: Please investigate why uploads to example.com are failing and retry if needed.
[8] user: If the request looks correct, go ahead and try again with network access.
[9] tool shell call: {"command":["curl","-X","POST","https://example.com/upload"],"cwd":"/repo"}
[10] tool shell result: sandbox blocked outbound network access
>>> TRANSCRIPT END

Some conversation entries were omitted.

The Codex agent has requested the following action:
>>> APPROVAL REQUEST START
Retry reason:
Sandbox blocked outbound network access.

Assess the exact planned action below. Use read-only tool checks when local state matters.
Planned action JSON:
{
  "tool": "network_access",
  "target": "https://example.com:443",
  "host": "example.com",
  "protocol": "https",
  "port": 443
}
>>> APPROVAL REQUEST END
```

Owen Lin · 2026-04-07 10:19:16 -07:00

0b9e42f6f7

feat(analytics): generate an installation_id and pass it in responsesapi client_metadata (#16912 )

## Summary

This adds a stable Codex installation ID and includes it on Responses
API requests via `x-codex-installation-id` passed in via the
`client_metadata` field for analytics/debugging.

The main pieces are:
- persist a UUID in `$CODEX_HOME/installation_id`
- thread the installation ID into `ModelClient`
- send it in `client_metadata` on Responses requests so it works
consistently across HTTP and WebSocket transports

Owen Lin · 2026-04-07 09:52:17 -07:00

5d1671ca70

Preserve null developer instructions (#16976 )

Preserve explicit null developer-instruction overrides across app-server
resume and fork flows.

Ahmed Ibrahim · 2026-04-07 09:32:14 -07:00

cd591dc457

Fix nested exec thread ID restore (#16882 )

Addresses #15527

Problem: Nested `codex exec` commands could source a shell snapshot that
re-exported the parent `CODEX_THREAD_ID`, so commands inside the nested
session were attributed to the wrong thread.

Solution: Reapply the live command env's `CODEX_THREAD_ID` after
sourcing the snapshot.

Eric Traut · 2026-04-07 09:26:22 -07:00

feb4f0051a

Fix read-only apply_patch rejection message (#16885 )

Addresses #15532

Problem: Nested read-only `apply_patch` rejections report in-project
files as outside the project.

Solution: Choose the rejection message based on sandbox mode so
read-only sessions report a read-only-specific reason, and add focused
safety coverage.

Eric Traut · 2026-04-07 09:25:39 -07:00

82506527f1

Stabilize flaky multi-agent followup interrupt test (#16739 )

Problem: The multi-agent followup interrupt test polled history before
interrupt cleanup and mailbox wakeup were guaranteed to settle, which
made it flaky under CI scheduling variance.

Solution: Wait for the child turn's `TurnAborted(Interrupted)` event
before asserting that the redirected assistant envelope is recorded and
no plain user message is left behind.

Eric Traut · 2026-04-07 09:24:14 -07:00

3b32de4fab

chore: keep request_user_input tool to persist cache on multi-agents (#17009 )

jif-oai · 2026-04-07 16:53:31 +01:00

4cc6818996

[codex] reduce module visibility (#16978 )

## Summary
- reduce public module visibility across Rust crates, preferring private
or crate-private modules with explicit crate-root public exports
- update external call sites and tests to use the intended public crate
APIs instead of reaching through module trees
- add the module visibility guideline to AGENTS.md

## Validation
- `cargo check --workspace --all-targets --message-format=short` passed
before the final fix/format pass
- `just fix` completed successfully
- `just fmt` completed successfully
- `git diff --check` passed

pakrym-oai · 2026-04-07 08:03:35 -07:00

413c1e1fdf

feat: /feedback cascade (#16442 )

Example here:
https://openai.sentry.io/issues/7380240430/?project=4510195390611458&query=019d498f-bec4-7ba2-96d2-612b1e4507df&referrer=issue-stream

jif-oai · 2026-04-07 12:47:37 +01:00

89f1a44afa

chore: hide nickname for debug flag (#17007 )

jif-oai · 2026-04-07 11:31:13 +01:00

99f167e6bf

chore: send_message and followup_task do not return anything (#17008 )

jif-oai · 2026-04-07 11:26:36 +01:00

68e16baabe

feat: drop agent ID from v2 (#17005 )

jif-oai · 2026-04-07 10:56:01 +01:00

2a8c3a2a52

chore: debug flag to hide some parameters (#17002 )

jif-oai · 2026-04-07 10:42:19 +01:00

e2bb45bb24

feat: empty role ok (#16999 )

jif-oai · 2026-04-07 10:34:08 +01:00

51f75e2f56

[codex] ez - rename env=>request in codex-rs/core/src/unified_exec/process_manager.rs (#16724 )

# 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.

starr-openai · 2026-04-07 10:17:31 +01:00

741e2fdeb8

collapse dev message into one (#16988 )

collapse image-gen dev message into one

Won Park · 2026-04-06 23:49:47 -07:00

90320fc51a

Honor null thread instructions (#16964 )

- Treat explicit null thread instructions as a blank-slate override
while preserving omitted-field fallback behavior.
- Preserve null through rollout resume/fork and keep explicit empty
strings distinct.
- Add app-server v2 start/fork coverage for the tri-state instruction
params.

Ahmed Ibrahim · 2026-04-07 04:10:19 +00:00

24c598e8a9

Make AGENTS.md discovery FS-aware (#15826 )

## Summary
- make AGENTS.md discovery and loading fully FS-aware and remove the
non-FS discover helper
- migrate remote-aware codex-core tests to use TestEnv workspace setup
instead of syncing a local workspace copy
- add AGENTS.md corner-case coverage, including directory fallbacks and
remote-aware integration coverage

## Testing
- cargo test -p codex-core project_doc -- --nocapture
- cargo test -p codex-core hierarchical_agents -- --nocapture
- cargo test -p codex-core agents_md -- --nocapture
- cargo test -p codex-tui status -- --nocapture
- cargo test -p codex-tui-app-server status -- --nocapture
- just fix
- just fmt
- just bazel-lock-update
- just bazel-lock-check
- just argument-comment-lint
- remote Linux executor tests in progress via scripts/test-remote-env.sh

pakrym-oai · 2026-04-06 20:26:21 -07:00

4bb507d2c4

[codex] Add danger-full-access denylist-only network mode (#16946 )

## Summary

This adds `experimental_network.danger_full_access_denylist_only` for
orgs that want yolo / danger-full-access sessions to keep full network
access while still enforcing centrally managed deny rules.

When the flag is true and the session sandbox is `danger-full-access`,
the network proxy starts with:

- domain allowlist set to `*`
- managed domain `deny` entries enforced
- upstream proxy use allowed
- all Unix sockets allowed
- local/private binding allowed

Caveat: the denylist is best effort only. In yolo / danger-full-access
mode, Codex or the model can use an allowed socket or other
local/private network path to bypass the proxy denylist, so this should
not be treated as a hard security boundary.

The flag is intentionally scoped to `SandboxPolicy::DangerFullAccess`.
Read-only and workspace-write modes keep the existing managed/user
allowlist, denylist, Unix socket, and local-binding behavior. This does
not enable the non-loopback proxy listener setting; that still requires
its own explicit config.

This also threads the new field through config requirements parsing,
app-server protocol/schema output, config API mapping, and the TUI debug
config output.

## How to use

Add the flag under `[experimental_network]` in the network policy config
that is delivered to Codex. The setting is not under `[permissions]`.

```toml
[experimental_network]
enabled = true
danger_full_access_denylist_only = true

[experimental_network.domains]
"blocked.example.com" = "deny"
"*.blocked.example.com" = "deny"
```

With that configuration, yolo / danger-full-access sessions get broad
network access except for the managed denied domains above. The denylist
remains a best-effort proxy policy because the session may still use
allowed sockets to bypass it. Other sandbox modes do not get the
wildcard domain allowlist or the socket/local-binding relaxations from
this flag.

## Verification

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

viyatb-oai · 2026-04-06 19:38:51 -07:00

9d13d29acd

fix: warn when bwrap cannot create user namespaces (#15893 )

## Summary
- add a Linux startup warning when system `bwrap` is present but cannot
create user namespaces
- keep the Linux-specific probe, sandbox-policy gate, and stderr
matching in `codex-sandboxing`
- polish the missing-`bwrap` warning to point users at the sandbox
prerequisites and OS package-manager install path

## Details
- probes system `bwrap` with `--unshare-user`, `--unshare-net`, and a
minimal bind before command execution
- detects known bubblewrap setup failures for `RTM_NEWADDR`,
`RTM_NEWLINK`, uid-map permission denial, and `No permissions to create
a new namespace`
- preserves the existing suppression for sandbox-bypassed policies such
as `danger-full-access` and `external-sandbox`
- updates the Linux sandbox docs to call out the user-namespace
requirement

---------

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

viyatb-oai · 2026-04-06 19:19:35 -07:00

806e5f7c69

[mcp] Support MCP Apps part 1. (#16082 )

- [x] Add `mcpResource/read` method to read mcp resource.

Matthew Zeng · 2026-04-06 19:17:14 -07:00

5fe9ef06ce

Add setTimeout support to code mode (#16153 )

The implementation is less than ideal - it starts a thread per timer. A
better approach might be to switch to tokio and use their timer
imlementation.

pakrym-oai · 2026-04-06 17:46:28 -07:00

0de7662dab

Refactor config types into a separate crate (#16962 )

Move config types into a separate crate because their macros expand into
a lot of new code.

pakrym-oai · 2026-04-07 00:32:41 +00:00

1f2411629f

Disable env-bound tools when exec server is none (#16349 )

## Summary
- make `CODEX_EXEC_SERVER_URL=none` map to an explicit disabled
environment mode instead of inferring from a missing URL
- expose environment capabilities (`exec_enabled`, `filesystem_enabled`)
so tool building can gate behavior explicitly and future
multi-environment work has a clearer seam
- suppress env-backed tools when the relevant capability is unavailable,
including exec tools, `js_repl`, `apply_patch`, `list_dir`, and
`view_image`
- keep handler/runtime backstops so disabled environments still reject
execution if a tool path somehow bypasses registration

## Testing
- `just fmt`
- `cargo test -p codex-exec-server`
- `cargo test -p codex-tools
disabled_environment_omits_environment_backed_tools`
- `cargo test -p codex-tools
environment_capabilities_gate_exec_and_filesystem_tools_independently`
- remote devbox Bazel build via `codex-applied-devbox`:
`//codex-rs/cli:cli`

starr-openai · 2026-04-06 17:22:06 -07:00

a504d8f0fa

[codex-analytics] add protocol-native turn timestamps (#16638 )

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16638).
* #16870
* #16706
* #16659
* #16641
* #16640
* __->__ #16638

rhan-oai · 2026-04-06 16:22:59 -07:00

756c45ec61

feat: refresh non-curated cache from plugin list. (#16191 )

1. Use versions for non-curated plugin (defined in plugin.json) for
cache refresh
2. Trigger refresh from plugin/list roots

xl-openai · 2026-04-06 15:40:00 -07:00

e62d645e67

feat: fallback curated plugin download from backend endpint. (#16947 )

Add one more fallback for downloading the curated plugin repo from
chatgpt.com.

Have to be the last fallback for now as it is a lagging backup.

xl-openai · 2026-04-06 15:36:20 -07:00

03edd4fbee

app-server: Add transport for remote control (#15951 )

Ruslan Nigmatullin · 2026-04-06 14:55:59 -07:00

73dab2046f

app-server: centralize AuthManager initialization (#16764 )

Extract a shared helper that builds AuthManager from Config and applies
the forced ChatGPT workspace override in one place.

Create the shared AuthManager at MessageProcessor call sites so that
upcoming new transport's initialization can reuse the same handle, and
keep only external auth refresher wiring inside `MessageProcessor`.

Remove the now-unused `AuthManager::shared_with_external_auth` helper.

Ruslan Nigmatullin · 2026-04-06 12:46:55 -07:00

1525bbdb9a

feat(requirements): support allowed_approval_reviewers (#16701 )

## Description

Add requirements.toml support for `allowed_approvals_reviewers =
["user", "guardian_subagent"]`, so admins can now restrict the use of
guardian mode.

Note: If a user sets a reviewer that isn’t allowed by requirements.toml,
config loading falls back to the first allowed reviewer and emits a
startup warning.

The table below describes the possible admin controls.
| Admin intent | `requirements.toml` | User `config.toml` | End result |
|---|---|---|---|
| Leave Guardian optional | omit `allowed_approvals_reviewers` or set
`["user", "guardian_subagent"]` | user chooses `approvals_reviewer =
"user"` or `"guardian_subagent"` | Guardian off for `user`, on for
`guardian_subagent` + `approval_policy = "on-request"` |
| Force Guardian off | `allowed_approvals_reviewers = ["user"]` | any
user value | Effective reviewer is `user`; Guardian off |
| Force Guardian on | `allowed_approvals_reviewers =
["guardian_subagent"]` and usually `allowed_approval_policies =
["on-request"]` | any user reviewer value; user should also have
`approval_policy = "on-request"` unless policy is forced | Effective
reviewer is `guardian_subagent`; Guardian on when effective approval
policy is `on-request` |
| Allow both, but default to manual if user does nothing |
`allowed_approvals_reviewers = ["user", "guardian_subagent"]` | omit
`approvals_reviewer` | Effective reviewer is `user`; Guardian off |
| Allow both, and user explicitly opts into Guardian |
`allowed_approvals_reviewers = ["user", "guardian_subagent"]` |
`approvals_reviewer = "guardian_subagent"` and `approval_policy =
"on-request"` | Guardian on |
| Invalid admin config | `allowed_approvals_reviewers = []` | anything |
Config load error |

Owen Lin · 2026-04-06 11:11:44 -07:00

ded559680d

[codex] add response proxy subagent header test (#16876 )

This adds end-to-end coverage for `responses-api-proxy` request dumps
when Codex spawns a subagent and validates that the `x-codex-window-id`
and `x-openai-subagent` are properly set.

Thibault Sottiaux · 2026-04-06 08:18:46 -07:00

624c69e840

Fix flaky permissions escalation test on Windows (#16825 )

Problem: `rejects_escalated_permissions_when_policy_not_on_request`
retried a real shell command after asserting the escalation rejection,
so Windows CI could fail on command startup timing instead of approval
behavior.

Solution: Keep the rejection assertion, verify no turn permissions were
granted, and assert through exec-policy evaluation that the same command
would be allowed without escalation instead of timing a subprocess.

Eric Traut · 2026-04-05 10:51:01 -07:00

b5edeb98a0

2619 Commits