## Why
The TUI Vim composer currently diverges from normal Vim editing in two
common workflows: pressing `e` repeatedly can remain stuck at an
existing word end, and normal mode does not support `C` for changing
through the end of the line. The existing `D` behavior also removes the
newline when the cursor is already at the line boundary, which makes the
new `C` action and existing deletion action surprising in multiline
prompts.
Closes#23926.
Closes#24238.
## What Changed
- Make normal-mode `e` advance from the current word end to the next
word end, including for operator motions such as `de`.
- Add configurable Vim normal-mode `change_to_line_end` behavior, bound
to `C` by default, which deletes to the end of the current line and
enters Insert mode.
- Keep the newline intact when `D` or `C` is pressed at the end-of-line
boundary.
- Add regression coverage for repeated `e`, `de`, `C`, and the multiline
`C`/`D` boundary behavior.
- Regenerate the config schema and update the keymap picker snapshots
for the new Vim action.
## How to Test
1. Run Codex with Vim composer mode enabled:
```bash
cd codex-rs
cargo run --bin codex -- -c tui.vim_mode_default=true
```
2. Enter `alpha beta gamma`, press `Esc`, `0`, then press `e`
repeatedly.
Confirm the cursor advances through the ends of `alpha`, `beta`, and
`gamma`.
3. Enter `hello world`, press `Esc`, `0`, `w`, then `C`.
Confirm `world` is deleted and the composer enters Insert mode.
4. Enter a multiline prompt with `hello` above `world`, press `Esc`,
`k`, `$`, and then `D`.
Confirm the newline is preserved and the two lines do not join.
5. At the same boundary, press `C` and type `!`.
Confirm the composer enters Insert mode and yields `hello!` above
`world`, preserving the newline.
Targeted automated verification:
- `just fix -p codex-tui`
- `just argument-comment-lint-from-source -p codex-tui -p codex-config`
- `cargo insta pending-snapshots` reports no pending snapshots.
- `just test -p codex-tui` validates the new Vim and keymap snapshot
coverage, but the command remains red due to two reproducible unrelated
failures in `app::tests::update_feature_flags_disabling_guardian_*`.
## Validation Note
The workspace-wide `just argument-comment-lint` form is currently
blocked during Bazel analysis by the existing LLVM `compiler-rt` missing
`include/sanitizer/*.h` failure; package-scoped source linting for the
changed Rust crates passed.
## Why
Plugin and marketplace mutations are applied by the app server, but
several TUI follow-up paths still refreshed state from the TUI host
config. In remote workspace mode, that can leave plugin UI state tied to
stale client-local `config.toml` after the server has already applied
the mutation.
## What
- Stop reloading the TUI host config after app-server-owned plugin,
marketplace, skill, and app mutations.
- Use the same app-server-owned refresh path for local and remote
sessions: ask the app server to reload user config where the running
session needs it, then refetch plugin list/detail state from the app
server.
- Build plugin mention candidates from existing app-server `plugin/list`
and `plugin/read` data in both local and remote sessions instead of
TUI-host plugin config.
- Avoid the duplicate local config reload after `ReloadUserConfig` asks
the app server to reload config.
## Verification
Manually launched a local WebSocket app-server with a temp server
`CODEX_HOME`, launched the TUI with a separate temp host `CODEX_HOME`
and `--remote`, installed a sample plugin from a temp local marketplace
through `/plugins`, and confirmed the TUI refreshed to installed state
while only the server config gained `[plugins."sample@debug"]`. Trace
logs showed the TUI using app-server `plugin/list` and `plugin/read` for
the refresh path.
## Summary
- Change last-`n` fork truncation to start at the first fork-turn
boundary instead of returning the full rollout when the fork history is
shorter than the requested window.
- Add coverage for the startup-prefix case in both rollout truncation
tests and agent control spawn behavior.
- Ensure bounded forked children still rebuild context after the cached
prefix is truncated.
## Testing
- Added unit coverage for truncation behavior when the parent history is
under the requested fork-turn limit.
- Added an agent control test covering bounded fork spawn behavior with
startup context present.
- Not run (not requested).
## Why
Extensions can currently observe thread start, resume, and stop, but
they do not have a lifecycle point for the host to say that immediately
pending thread work has drained. That makes idle follow-up behavior
harder to express as extension-owned logic instead of host-specific
plumbing.
This adds an explicit idle lifecycle hook so an extension can react when
a thread becomes idle while the host keeps ownership of whether any
submitted follow-up input starts a turn, is queued, or is ignored.
## What changed
- Added `ThreadIdleInput` with access to the session-scoped and
thread-scoped extension stores.
- Added a default `on_thread_idle` method to
`ThreadLifecycleContributor`.
- Re-exported `ThreadIdleInput` from the extension API surface.
## Testing
Not run; this only extends the extension API trait surface with a
default hook and exported input type.
## Summary
- Add the missing additional_context field to the guardian review
Op::UserInput test initializer.
## Test plan
- just fmt
- just test -p codex-core guardian_review
- just test -p codex-core (compiles, then fails on local environment
issues: sandbox-exec Operation not permitted, missing test_stdio_server
helper binary, and unrelated timeouts)
## Why
The extracted goal runtime needs a host-callable path for turns that
stop because the workspace usage limit is reached. In that case, any
in-turn goal progress should be accounted before the goal becomes
terminal, and active goal accounting must be cleared so later
tool-finish or turn-stop handling does not keep charging usage to a
stopped goal.
## What changed
- Adds `GoalRuntimeHandle::usage_limit_active_goal_for_turn`, which
accounts current active-goal progress, marks the active or
budget-limited thread goal as `UsageLimited`, records terminal metrics
when the status changes, clears active goal accounting, and emits the
updated goal event.
- Covers both active and budget-limited goals in
`ext/goal/tests/goal_extension_backend.rs`, including the invariant that
later token/tool events do not add usage after the goal has been
usage-limited.
## Testing
- Added
`usage_limit_active_goal_accounts_progress_and_clears_accounting`.
- Added `usage_limit_budget_limited_goal_accounts_remaining_progress`.
This reverts commit 5381240f57. Gov cloud
should not be supported
# External (non-OpenAI) Pull Request Requirements
External code contributions are by invitation only. Please read the
dedicated "Contributing" markdown file for details:
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.
## Summary
Clear inherited legacy `notify` from Guardian review session config,
since we should not be passing auto review threads into `notify`
targets. Keeps legacy notify payload and hook runtime behavior unchanged
for normal user turns.
## Testing
- [x] add a Guardian config regression and dedicated Guardian
integration test so review sessions cannot inherit parent notify hooks
# Summary
The Codex standalone installers can pause after installation to ask
about an older managed install or launching Codex. That makes unattended
bootstrap and update flows hard to complete reliably.
This PR adds noninteractive installer control on macOS/Linux and Windows
through `CODEX_NON_INTERACTIVE=1`. Noninteractive operation is
environment-only, which gives automated callers one stable way to
suppress prompts. When a noninteractive install leaves an older npm,
bun, or brew-managed Codex installed, the standalone bin is configured
ahead of that command on `PATH` so the newly installed Codex is the one
future launches select. It also supports `CODEX_RELEASE` for callers
that select a release through environment variables while retaining the
existing explicit release inputs. Release selection accepts `latest`,
stable `x.y.z` versions, and Codex prereleases written as
`rust-v0.134.0-alpha.3`, `v0.134.0-alpha.3`, or `0.134.0-alpha.3`; it
validates that shape before constructing release requests.
# Stack
1. [#21567](https://github.com/openai/codex/pull/21567) - Adds release
and noninteractive environment controls to the installers. (current)
2. [#24637](https://github.com/openai/codex/pull/24637) - Runs
standalone updater installs with `CODEX_NON_INTERACTIVE=1`.
3. [#24639](https://github.com/openai/codex/pull/24639) - Removes
explicit release argument inputs in favor of `CODEX_RELEASE`.
# Evidence
| Before | After |
| --- | --- |
| 
| 
|
Environment-controlled macOS install with an existing npm-managed Codex
on `PATH`:
https://github.com/user-attachments/assets/442e0b5b-4a32-4bf5-996b-68784777380d
# Design decisions
Windows installs using the older standalone bin layout still require an
interactive migration confirmation. Noninteractive mode does not
auto-migrate that existing directory because replacing it is a
destructive transition for an early, limited-use layout; unattended
installs on that layout fail with an instruction to rerun interactively.
# Testing
Tests: installer syntax validation, release-selector acceptance and
rejection coverage including PowerShell `Latest` compatibility, macOS
live-terminal installer smoke testing with environment-controlled stable
and prerelease installation and competing PATH precedence, shell
rejection of the omitted noninteractive flag, and Windows ARM64
PowerShell smoke testing with environment-only noninteractive behavior,
retained release input, and competing PATH precedence through Parallels.
## Summary
- Bump the workspace Rust toolchain from `1.93.0` to `1.95.0` across
Cargo, Bazel, CI, release workflows, devcontainers, and the Codex
environment config.
- Refresh `MODULE.bazel.lock` so the Bazel Rust toolchain artifacts
match the new version.
- Leave purpose-specific toolchains unchanged, including the
`argument-comment-lint` nightly and the upstream `rusty_v8` `1.91.0`
build pin.
- Includes fixes for new lints from `just fix` and a few codex-authored
fixes for lints without a suggestion.
## Why
When a turn needs a follow-up request after tool output is recorded,
Codex can still appear stuck in `Thinking` before the next `/responses`
request is opened. The existing local trace showed the last completed
response and the absence of a new backend request, but it did not show
whether the stall was in tool-router preparation or later request setup.
Issue: N/A (internal incident investigation)
## What Changed
Added trace spans around the pre-stream tool-router handoff in
`core/src/session/turn.rs`, including the `built_tools` phase and the
MCP manager read lock.
Added per-server MCP tool-listing spans and trace breadcrumbs in
`codex-mcp/src/connection_manager.rs` with startup snapshot /
startup-complete state so a pending MCP client is visible in feedback
logs instead of looking like a silent hang.
## Verification
- `just fmt`
- `just test -p codex-mcp`
- `just test -p codex-core` (prior full rerun fails in this workspace on
unrelated integration tests: code-mode output length expectations, one
shell timeout formatting assertion, and shell snapshot timeouts; latest
review-fix rerun compiled and passed 1160 tests before I stopped the
abnormally slow unrelated suite)
add new `parse_tool_input_schema_without_compaction` to bypass the
existing compaction/trimming of client-provided tool schemas that are
over 4k bytes.
we want this for standalone web search to keep field guidance/metadata
on certain fields; this keeps us closer to parity with existing hosted
tool schema (which didnt go through this 4k byte filter).
## Why
`continuation_turn_id` was introduced to distinguish synthetic goal
continuation turns for the no-tool continuation suppression heuristic.
#20523 removed that heuristic, but left the marker behind. It is still
written and cleared without affecting any runtime decision.
## What Changed
- Remove `GoalRuntimeState::continuation_turn_id`.
- Remove the marker setter/clearer and their now-no-op start, finish,
and abort call sites.
## Testing
- Not run yet (deferred at request).
## Why
- Runtime analytics events report `thread_id`, which identifies the
individual thread emitting an event
- They don't report `session_id`, which identifies the shared session
for a root thread and its subagent threads
- Emitting both identifiers allows analytics to group related activity
## What Changed
- Adds `session_id` to relevant analytics events (thread_initalized,
turn, turn_steer, compaction, guardian_review)
- Tracks each thread's session ID in the analytics reducer so subsequent
thread scoped events emit the same value
- Carries the shared session ID through subagent initialization
## Verification
- `just test -p codex-analytics` validates event payloads and subagent
session grouping.
- Focused `codex-app-server` tests validate session IDs for thread,
turn, and steer events.
- Focused `codex-core` tests validate root and subagent session ID
propagation.
## Why
Older persisted rollouts can contain `input_image.detail` values of
`auto` or `low` from before `ImageDetail` was narrowed to
`high`/`original`. Current deserialization rejects those values, which
can make resume skip later compacted checkpoints and reconstruct an
oversized raw suffix before the next compaction attempt.
Confirmed Sentry reports fixed by this compatibility path:
- [CODEX-1H3F](https://openai.sentry.io/issues/7500642496/)
- [CODEX-1H6N](https://openai.sentry.io/issues/7501025347/)
- [CODEX-1JDP](https://openai.sentry.io/issues/7504549065/)
- [CODEX-1HW6](https://openai.sentry.io/issues/7503407986/)
## Background
[openai/codex#20693](https://github.com/openai/codex/pull/20693) added
image-detail plumbing for app-server `UserInput` so input images could
explicitly request `detail: original`. The Slack discussion behind that
PR was about ScreenSpot / bridge evals where user input images were
resized, while tool output images already had MCP/code-mode ways to
request image detail.
In review, the intended new API surface was narrowed to `high` and
`original`: default to `high`, allow `original` when callers need
unchanged image handling, and avoid encouraging new `auto` or `low`
usage. That policy still makes sense for newly emitted values.
The missing compatibility piece is persisted history. Older rollouts can
already contain `auto` and `low`, and resume reconstructs typed history
by deserializing those rollout records. Rejecting old values at that
boundary causes valid compacted checkpoints to be skipped. This PR
restores `auto` and `low` as real variants so old records deserialize
and round-trip without being rewritten as `high`, while product paths
can continue to default to `high` and avoid emitting `auto` for new
behavior.
## What changed
- Restored `ImageDetail::Auto` and `ImageDetail::Low` as first-class
protocol values.
- Preserved `auto`/`low` through rollout deserialization, MCP image
metadata, code-mode image output, and schema/type generation.
- Kept local image byte handling conservative: only `original` switches
to original-resolution loading; `auto`/`low`/`high` continue through the
resize-to-fit path while retaining their detail value.
- Added regression coverage for enum round-tripping and code-mode `low`
detail handling.
## Testing
- `just write-app-server-schema`
- `just test -p codex-protocol`
- `just test -p codex-tools`
- `just test -p codex-code-mode`
- `just test -p codex-app-server-protocol`
- `just test -p codex-core
suite::rmcp_client::stdio_image_responses_preserve_original_detail_metadata`
- `just test -p codex-core
suite::code_mode::code_mode_can_use_mcp_image_result_with_image_helper`
- Loaded broken rollouts on local fixed builds, and started/completed
new turns.
I also attempted `just test -p codex-core`; the local broad run did not
finish green: 2559 tests run, 2467 passed, 55 flaky, 91 failed, 1 timed
out. The failures were broad timeout/deadline failures across unrelated
areas; targeted changed-path core tests above passed.
## Why
Windows sandbox diagnostics are currently hard to recover from
`/feedback` even though they are often the most useful artifact when
debugging sandbox behavior. Now that sandbox logging uses daily rolling
files, feedback can safely include the current day's sandbox log without
uploading the old ever-growing legacy `sandbox.log`.
## What changed
- Add a `codex-windows-sandbox` helper that resolves the current daily
sandbox log from `codex_home`.
- When feedback is submitted with logs enabled on Windows, app-server
attaches today's sandbox log if it exists.
- Upload the attachment under the stable filename `windows-sandbox.log`,
independent of the dated on-disk filename.
- Keep existing raw `extra_log_files` behavior unchanged for rollout and
desktop log attachments.
## Verification
- `cargo fmt -p codex-app-server -p codex-windows-sandbox`
- `cargo test -p codex-windows-sandbox
current_log_file_path_for_codex_home_uses_sandbox_dir`
- `cargo test -p codex-app-server
windows_sandbox_log_attachment_uses_current_log`
- Manual CLI/TUI `/feedback` test confirmed Sentry received
`windows-sandbox.log`.
## Why
Remote image submissions currently wrap native `input_image` spans in
literal `<image>` and `</image>` text spans. Those extra prompt tokens
add structure without providing label or routing information.
## What Changed
- Serialize `UserInput::Image` directly as an `input_image` content
span.
- Preserve named local-image framing and legacy wrapper parsing for
labeled attachments and existing histories.
- Update existing request-shape expectations for drag-and-drop images,
model switching, and compaction.
## Validation
- `just test -p codex-protocol`
- Focused `codex-core` run covering
`drag_drop_image_persists_rollout_request_shape`,
`model_change_from_image_to_text_strips_prior_image_content`, and
`snapshot_request_shape_pre_turn_compaction_including_incoming_user_message`
## Notes
- A broader `just test -p codex-core` run was attempted; the affected
tests passed, while the overall run failed in unrelated CLI, MCP, and
tooling tests plus a `thread_manager` timeout.
## Why
The Windows sandbox runner still carried the old `SandboxPolicy`
compatibility path even though core now computes `PermissionProfile`.
That meant Windows command-runner execution could only see the legacy
projection, so profile-only filesystem rules such as deny globs were not
part of the runner input.
## What Changed
- Removed the Windows-local `SandboxPolicy` parser/export and deleted
`windows-sandbox-rs/src/policy.rs`.
- Changed restricted-token capture/session setup, elevated setup,
world-writable audit, read-root grant, and command-runner session APIs
to accept `PermissionProfile` plus the profile cwd.
- Bumped the elevated command-runner IPC protocol to version 2 because
`SpawnRequest` now carries `permission_profile` /
`permission_profile_cwd` instead of the legacy `policy_json_or_preset` /
`sandbox_policy_cwd` fields.
- Updated core exec, unified exec, debug-sandbox, TUI setup/grant flows,
and app-server setup to pass the actual effective `PermissionProfile`.
- Left regression coverage asserting the old IPC policy fields are
absent and the runner serializes tagged `PermissionProfile` JSON.
## Verification
- `cargo test -p codex-windows-sandbox`
- `cargo test -p codex-core windows_sandbox`
- `cargo test -p codex-app-server
request_processors::windows_sandbox_processor`
- `just fix -p codex-windows-sandbox -p codex-core -p codex-app-server
-p codex-cli -p codex-tui`
- `just fix -p codex-cli -p codex-tui`
- `just fix -p codex-windows-sandbox -p codex-tui`
- `rg "\\bSandboxPolicy\\b" codex-rs/windows-sandbox-rs` returned no
matches.
Note: `cargo test -p codex-cli` was attempted but did not reach crate
tests because local disk filled while compiling dependencies (`No space
left on device`). The targeted clippy pass compiled the affected CLI/TUI
surfaces afterward.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/23813).
* #24108
* __->__ #23813
Fixes#24249.
## Why
Codex already supports discovering marketplaces under both
`.agents/plugins/marketplace.json` and
`.claude-plugin/marketplace.json`. The Git marketplace auto-upgrade
no-op check only looked for the `.agents` layout. That meant an
installed `.claude-plugin` marketplace with matching revision metadata
still looked absent, so plugin list/startup upgrade work could stage and
re-activate the same marketplace again.
That matches the failure shape in #24249: the report called out repeated
marketplace sync/cache refresh logs and a large recently-touched
`.tmp/marketplaces/.staging` directory. This change makes the
auto-upgrade path recognize the installed `.claude-plugin` marketplace
as already current, which should remove that staging/activation feedback
loop.
## What changed
`codex-rs/core-plugins/src/marketplace_upgrade.rs` now uses the existing
supported marketplace manifest discovery helper when deciding whether an
installed Git marketplace is already current. Existing local plugin
source validation is unchanged; `source: "./"` still remains invalid.
## Confidence
Confidence is high that this fixes the repeated marketplace upgrade
path: the old hardcoded layout check was definitely wrong for installed
`.claude-plugin` marketplaces, and the reported staging churn points
directly at that path.
Confidence is not 100% because we do not have a CPU profile or a fully
re-run reporter repro. A malformed marketplace entry can still be logged
as invalid if another caller repeatedly lists plugins; this PR fixes the
staging/upgrade feedback loop that likely made the failure pathological,
not every possible source of repeated marketplace resolution.
## Summary
TUI plugin mention refresh still joined app-server plugin inventory with
client-local plugin config, which can diverge once plugin state is owned
by the app server.
This changes the TUI to mirror the GUI client: `plugin/list` is the
autocomplete source, and mention candidates are plugin-level entries
filtered to installed, enabled, and not disabled by admin. The TUI no
longer reads local plugin config or calls `plugin/read` while refreshing
plugin mention candidates.
## API shape and limitations
The current app-server API does not expose effective per-session plugin
capability summaries for mention autocomplete. As in the GUI,
autocomplete now trusts `plugin/list` metadata rather than proving which
plugin capabilities are loaded in the active session.
That avoids stale client-local reads and the cwd/remote detail gaps in
`plugin/read`, but intentionally accepts the same list-level tradeoff as
the app: if `plugin/list` reports a remote plugin before its local
bundle is materialized, the plugin can still appear as a mention
candidate.
## Why
When Codex calls responsesapi, we currently send `session_id`,
`thread_id`, and `turn_id` among other things as
`client_metadata["x-codex-turn-metadata"]`. This PR adds
`forked_from_thread_id` which helps explain the "lineage" of a forked
thread.
## What's changed
- Track the immediate history source copied into a forked thread through
thread/session creation, including subagent and review turn metadata
paths.
- Include `forked_from_thread_id` in Codex turn metadata while
preventing turn-scoped Responses API client metadata from overwriting
Codex-owned lineage fields.
- Add coverage for fork lineage in turn metadata and the app-server
Responses API request path.
Fixes#24186.
## Why
When the TUI resumes a thread through the local app-server daemon with a
selected workspace, `thread/resume` can hit an already-loaded but idle
cached thread. That path previously rejoined the cached `CodexThread`,
so cwd/config overrides in `ThreadResumeParams` were ignored and the
resumed session kept using the old cwd.
## What changed
App-server now treats a loaded-but-idle thread with no subscribers as a
cache entry when resume overrides differ: it unloads that cached thread
and lets the normal resume path rebuild it with the requested
cwd/config. Threads that still have subscribers, or active runtime work,
continue to rejoin the existing loaded thread so in-flight state remains
observable.
The existing thread teardown helper was generalized from
archive-specific cleanup to shared unload cleanup for this path.
## Why
When the app-server remote-control websocket path stalls during
connection setup or teardown, the existing logs do not show where the
task stopped, and several awaits can keep the task from returning
promptly. That makes offline or stale-host incidents hard to distinguish
from expected shutdown or disable flow.
Issue: N/A (internal incident investigation)
## What Changed
Added structured lifecycle and status logging around remote-control
enable/disable requests, websocket task startup and exit, connection
cycles, enrollment context, and status/environment transitions.
Bound websocket connect, transport-event forwarding, and
connection-worker shutdown waits. On timeout, the code logs the stalled
operation and stops or aborts workers so the loop can reconnect or exit
instead of waiting indefinitely. Ping sends now also observe shutdown
cancellation.
