**Motivation**
- Bring `codex exec resume` to parity with top‑level flags so global
options (git check bypass, json, model, sandbox toggles) work after the
subcommand, including when outside a git repo.
**Description**
- Exec CLI: mark `--skip-git-repo-check`, `--json`, `--model`,
`--full-auto`, and `--dangerously-bypass-approvals-and-sandbox` as
global so they’re accepted after `resume`.
- Tests: add `exec_resume_accepts_global_flags_after_subcommand` to
verify those flags work when passed after `resume`.
**Testing**
- `just fmt`
- `cargo test -p codex-exec` (pass; ran with elevated perms to allow
network/port binds)
- Manual: exercised `codex exec resume` with global flags after the
subcommand to confirm behavior.
`load_config_layers_state()` should load config from a
`.codex/config.toml` in any folder between the `cwd` for a thread and
the project root. Though in order to do that,
`load_config_layers_state()` needs to know what the `cwd` is, so this PR
does the work to thread the `cwd` through for existing callsites.
A notable exception is the `/config` endpoint in app server for which a
`cwd` is not guaranteed to be associated with the query, so the `cwd`
param is `Option<AbsolutePathBuf>` to account for this case.
The logic to make use of the `cwd` will be done in a follow-up PR.
This adds support for `allowed_sandbox_modes` in `requirements.toml` and
provides legacy support for constraining sandbox modes in
`managed_config.toml`. This is converted to `Constrained<SandboxPolicy>`
in `ConfigRequirements` and applied to `Config` such that constraints
are enforced throughout the harness.
Note that, because `managed_config.toml` is deprecated, we do not add
support for the new `external-sandbox` variant recently introduced in
https://github.com/openai/codex/pull/8290. As noted, that variant is not
supported in `config.toml` today, but can be configured programmatically
via app server.
This PR does various types of cleanup before I can proceed with more
ambitious changes to config loading.
First, I noticed duplicated code across these two methods:
774bd9e432/codex-rs/core/src/config/mod.rs (L314-L324)774bd9e432/codex-rs/core/src/config/mod.rs (L334-L344)
This has now been consolidated in
`load_config_as_toml_with_cli_overrides()`.
Further, I noticed that `Config::load_with_cli_overrides()` took two
similar arguments:
774bd9e432/codex-rs/core/src/config/mod.rs (L308-L311)
The difference between `cli_overrides` and `overrides` was not
immediately obvious to me. At first glance, it appears that one should
be able to be expressed in terms of the other, but it turns out that
some fields of `ConfigOverrides` (such as `cwd` and
`codex_linux_sandbox_exe`) are, by design, not configurable via a
`.toml` file or a command-line `--config` flag.
That said, I discovered that many callers of
`Config::load_with_cli_overrides()` were passing
`ConfigOverrides::default()` for `overrides`, so I created two separate
methods:
- `Config::load_with_cli_overrides(cli_overrides: Vec<(String,
TomlValue)>)`
- `Config::load_with_cli_overrides_and_harness_overrides(cli_overrides:
Vec<(String, TomlValue)>, harness_overrides: ConfigOverrides)`
The latter has a long name, as it is _not_ what should be used in the
common case, so the extra typing is designed to draw attention to this
fact. I tried to update the existing callsites to use the shorter name,
where possible.
Further, in the cases where `ConfigOverrides` is used, usually only a
limited subset of fields are actually set, so I updated the declarations
to leverage `..Default::default()` where possible.
Constrain `approval_policy` through new `admin_policy` config.
This PR will:
1. Add a `admin_policy` section to config, with a single field (for now)
`allowed_approval_policies`. This list constrains the set of
user-settable `approval_policy`s.
2. Introduce a new `Constrained<T>` type, which combines a current value
and a validator function. The validator function ensures disallowed
values are not set.
3. Change the type of `approval_policy` on `Config` and
`SessionConfiguration` from `AskForApproval` to
`Constrained<AskForApproval>`. The validator function is set by the
values passed into `allowed_approval_policies`.
4. `GenericDisplayRow`: add a `disabled_reason: Option<String>`. When
set, it disables selection of the value and indicates as such in the
menu. This also makes it unselectable with arrow keys or numbers. This
is used in the `/approvals` menu.
Follow ups are:
1. Do the same thing to `sandbox_policy`.
2. Propagate the allowed set of values through app-server for the
extension (though already this should prevent app-server from setting
this values, it's just that we want to disable UI elements that are
unsettable).
Happy to split this PR up if you prefer, into the logical numbered areas
above. Especially if there are parts we want to gavel on separately
(e.g. admin_policy).
Disabled full access:
<img width="1680" height="380" alt="image"
src="https://github.com/user-attachments/assets/1fb61c8c-1fcb-4dc4-8355-2293edb52ba0"
/>
Disabled `--yolo` on startup:
<img width="749" height="76" alt="image"
src="https://github.com/user-attachments/assets/0a1211a0-6eb1-40d6-a1d7-439c41e94ddb"
/>
CODEX-4087
- Make Config.model optional and centralize default-selection logic in
ModelsManager, including a default_model helper (with
codex-auto-balanced when available) so sessions now carry an explicit
chosen model separate from the base config.
- Resolve `model` once in `core` and `tui` from config. Then store the
state of it on other structs.
- Move refreshing models to be before resolving the default model
### Description
- codex exec --json resume --last "<prompt>" bailed out because clap
treated the prompt as SESSION_ID. I removed the conflicts_with flag and
reinterpret that positional as a prompt when
--last is set, so the flow now keeps working in JSON mode.
(codex-rs/exec/src/cli.rs:84-104, codex-rs/exec/src/lib.rs:75-130)
- Added a regression test that exercises resume --last in JSON mode to
ensure the prompt is accepted and the rollout file is updated.
(codex-rs/exec/tests/suite/resume.rs:126-178)
### Testing
- just fmt
- cargo test -p codex-exec
- just fix -p codex-exec
- cargo test -p codex-exec
#6717
Signed-off-by: Dmitri Khokhlov <dkhokhlov@cribl.io>
## Overview
Adds LM Studio OSS support. Closes#1883
### Changes
This PR enhances the behavior of `--oss` flag to support LM Studio as a
provider. Additionally, it introduces a new flag`--local-provider` which
can take in `lmstudio` or `ollama` as values if the user wants to
explicitly choose which one to use.
If no provider is specified `codex --oss` will auto-select the provider
based on whichever is running.
#### Additional enhancements
The default can be set using `oss-provider` in config like:
```
oss_provider = "lmstudio"
```
For non-interactive users, they will need to either provide the provider
as an arg or have it in their `config.toml`
### Notes
For best performance, [set the default context
length](https://lmstudio.ai/docs/app/advanced/per-model) for gpt-oss to
the maximum your machine can support
---------
Co-authored-by: Matt Clayton <matt@lmstudio.ai>
Co-authored-by: Eric Traut <etraut@openai.com>
## Summary
Adds support for specifying additional directories in the TypeScript SDK
through a new `additionalDirectories` option in `ThreadOptions`.
## Changes
- Added `additionalDirectories` parameter to `ThreadOptions` interface
- Updated `CodexExec` to accept and pass through additional directories
via the `--config` flag for `sandbox_workspace_write.writable_roots`
- Added comprehensive test coverage for the new functionality
## Test plan
- Added test case that verifies `additionalDirectories` is correctly
passed as repeated flags
- Existing tests continue to pass
---------
Co-authored-by: Claude <noreply@anthropic.com>
There's still some debate about whether we want to expose
`tools.view_image` or `feature.view_image` so those are left unchanged
for now, but this old `include_view_image_tool` config is good-to-go.
Also updated the doc to reflect that `view_image` tool is now by default
true.
Addresses https://github.com/openai/codex/issues/5773
Testing: I tested that images work (regardless of order that they are
associated with the task prompt) in both the CLI and Extension. Also
verified that conversations in CLI and extension with images can be
resumed.
This PR is a follow-up to #5591. It allows users to choose which auth
storage mode they want by using the new
`cli_auth_credentials_store_mode` config.
Because conversations that use the Responses API can have encrypted
reasoning messages, trying to resume a conversation with a different
provider could lead to confusing "failed to decrypt" errors. (This is
reproducible by starting a conversation using ChatGPT login and resuming
it as a conversation that uses OpenAI models via Azure.)
This changes `ListConversationsParams` to take a `model_providers:
Option<Vec<String>>` and adds `model_provider` on each
`ConversationSummary` it returns so these cases can be disambiguated.
Note this ended up making changes to
`codex-rs/core/src/rollout/tests.rs` because it had a number of cases
where it expected `Some` for the value of `next_cursor`, but the list of
rollouts was complete, so according to this docstring:
bcd64c7e72/codex-rs/app-server-protocol/src/protocol.rs (L334-L337)
If there are no more items to return, then `next_cursor` should be
`None`. This PR updates that logic.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/5658).
* #5803
* #5793
* __->__ #5658
This PR adds support for a model-based summary and risk assessment for
commands that violate the sandbox policy and require user approval. This
aids the user in evaluating whether the command should be approved.
The feature works by taking a failed command and passing it back to the
model and asking it to summarize the command, give it a risk level (low,
medium, high) and a risk category (e.g. "data deletion" or "data
exfiltration"). It uses a new conversation thread so the context in the
existing thread doesn't influence the answer. If the call to the model
fails or takes longer than 5 seconds, it falls back to the current
behavior.
For now, this is an experimental feature and is gated by a config key
`experimental_sandbox_command_assessment`.
Here is a screen shot of the approval prompt showing the risk assessment
and summary.
<img width="723" height="282" alt="image"
src="https://github.com/user-attachments/assets/4597dd7c-d5a0-4e9f-9d13-414bd082fd6b"
/>
## Summary
- make the plan tool available by default by removing the feature flag
and always registering the handler
- drop plan-tool CLI and API toggles across the exec, TUI, MCP server,
and app server code paths
- update tests and configs to reflect the always-on plan tool and guard
workspace restriction tests against env leakage
## Testing
Manually tested the extension.
------
https://chatgpt.com/codex/tasks/task_i_68f67a3ff2d083209562a773f814c1f9
Adds a new ItemStarted event and delivers UserMessage as the first item
type (more to come).
Renames `InputItem` to `UserInput` considering we're using the `Item`
suffix for actual items.
Add a `--add-dir` CLI flag so sessions can use extra writable roots in
addition to the ones specified in the config file. These are ephemerally
added during the session only.
Fixes#3303Fixes#2797
## Summary
- ensure the TypeScript SDK sets CODEX_INTERNAL_ORIGINATOR_OVERRIDE to
codex_sdk_ts when spawning the Codex CLI
- extend the responses proxy test helper to capture request headers for
assertions
- add coverage that verifies Codex threads launched from the TypeScript
SDK send the codex_sdk_ts originator header
## Testing
- Not Run (not requested)
------
https://chatgpt.com/codex/tasks/task_i_68e561b125248320a487f129093d16e7
## Summary
This PR is an alternative approach to #4711, but instead of changing our
storage, parses out shell calls in the client and reserializes them on
the fly before we send them out as part of the request.
What this changes:
1. Adds additional serialization logic when the
ApplyPatchToolType::Freeform is in use.
2. Adds a --custom-apply-patch flag to enable this setting on a
session-by-session basis.
This change is delicate, but is not meant to be permanent. It is meant
to be the first step in a migration:
1. (This PR) Add in-flight serialization with config
2. Update model_family default
3. Update serialization logic to store turn outputs in a structured
format, with logic to serialize based on model_family setting.
4. Remove this rewrite in-flight logic.
## Test Plan
- [x] Additional unit tests added
- [x] Integration tests added
- [x] Tested locally
## Summary
- Factor `load_config_as_toml` into `core::config_loader` so config
loading is reusable across callers.
- Layer `~/.codex/config.toml`, optional `~/.codex/managed_config.toml`,
and macOS managed preferences (base64) with recursive table merging and
scoped threads per source.
## Config Flow
```
Managed prefs (macOS profile: com.openai.codex/config_toml_base64)
▲
│
~/.codex/managed_config.toml │ (optional file-based override)
▲
│
~/.codex/config.toml (user-defined settings)
```
- The loader searches under the resolved `CODEX_HOME` directory
(defaults to `~/.codex`).
- Managed configs let administrators ship fleet-wide overrides via
device profiles which is useful for enforcing certain settings like
sandbox or approval defaults.
- For nested hash tables: overlays merge recursively. Child tables are
merged key-by-key, while scalar or array values replace the prior layer
entirely. This lets admins add or tweak individual fields without
clobbering unrelated user settings.
This updates `codex exec` so that, by default, most of the agent's
activity is written to stderr so that only the final agent message is
written to stdout. This makes it easier to pipe `codex exec` into
another tool without extra filtering.
I introduced `#![deny(clippy::print_stdout)]` to help enforce this
change and renamed the `ts_println!()` macro to `ts_msg()` because (1)
it no longer calls `println!()` and (2), `ts_eprintln!()` seemed too
long of a name.
While here, this also adds `-o` as an alias for `--output-last-message`.
Fixes https://github.com/openai/codex/issues/1670
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
### Title
## otel
Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.
```toml
[otel]
environment = "staging" # defaults to "dev"
exporter = "none" # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false # defaults to false; redact prompt text unless explicitly enabled
```
Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.
### Event catalog
Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.
With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):
- `codex.api_request`
- `cf_ray` (optional)
- `attempt`
- `duration_ms`
- `http.response.status_code` (optional)
- `error.message` (failures)
- `codex.sse_event`
- `event.kind`
- `duration_ms`
- `error.message` (failures)
- `input_token_count` (completion only)
- `output_token_count` (completion only)
- `cached_token_count` (completion only, optional)
- `reasoning_token_count` (completion only, optional)
- `tool_token_count` (completion only)
- `codex.user_prompt`
- `prompt_length`
- `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
- `tool_name`
- `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
- `source` (`config` or `user`)
- `codex.tool_result`
- `tool_name`
- `call_id`
- `arguments`
- `duration_ms` (execution time for the tool)
- `success` (`"true"` or `"false"`)
- `output`
### Choosing an exporter
Set `otel.exporter` to control where events go:
- `none` – leaves instrumentation active but skips exporting. This is
the
default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
endpoint, protocol, and headers your collector expects:
```toml
[otel]
exporter = { otlp-http = {
endpoint = "https://otel.example.com/v1/logs",
protocol = "binary",
headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
}}
```
- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
metadata headers:
```toml
[otel]
exporter = { otlp-grpc = {
endpoint = "https://otel.example.com:4317",
headers = { "x-otlp-meta" = "abc123" }
}}
```
If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.
If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.
---------
Co-authored-by: Anton Panasenko <apanasenko@openai.com>
This pull request add a new experimental format of JSON output.
You can try it using `codex exec --experimental-json`.
Design takes a lot of inspiration from Responses API items and stream
format.
# Session and items
Each invocation of `codex exec` starts or resumes a session.
Session contains multiple high-level item types:
1. Assistant message
2. Assistant thinking
3. Command execution
4. File changes
5. To-do lists
6. etc.
# Events
Session and items are going through their life cycles which is
represented by events.
Session is `session.created` or `session.resumed`
Items are `item.added`, `item.updated`, `item.completed`,
`item.require_approval` (or other item types like `item.output_delta`
when we need streaming).
So a typical session can look like:
<details>
```
{
"type": "session.created",
"session_id": "01997dac-9581-7de3-b6a0-1df8256f2752"
}
{
"type": "item.completed",
"item": {
"id": "itm_0",
"item_type": "assistant_message",
"text": "I’ll locate the top-level README and remove its first line. Then I’ll show a quick summary of what changed."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_1",
"item_type": "command_execution",
"command": "bash -lc ls -la | sed -n '1,200p'",
"aggregated_output": "pyenv: cannot rehash: /Users/pakrym/.pyenv/shims isn't writable\ntotal 192\ndrwxr-xr-x@ 33 pakrym staff 1056 Sep 24 14:36 .\ndrwxr-xr-x 41 pakrym staff 1312 Sep 24 09:17 ..\n-rw-r--r--@ 1 pakrym staff 6 Jul 9 16:16 .codespellignore\n-rw-r--r--@ 1 pakrym staff 258 Aug 13 09:40 .codespellrc\ndrwxr-xr-x@ 5 pakrym staff 160 Jul 23 08:26 .devcontainer\n-rw-r--r--@ 1 pakrym staff 6148 Jul 22 10:03 .DS_Store\ndrwxr-xr-x@ 15 pakrym staff 480 Sep 24 14:38 .git\ndrwxr-xr-x@ 12 pakrym staff 384 Sep 2 16:00 .github\n-rw-r--r--@ 1 pakrym staff 778 Jul 9 16:16 .gitignore\ndrwxr-xr-x@ 3 pakrym staff 96 Aug 11 09:37 .husky\n-rw-r--r--@ 1 pakrym staff 104 Jul 9 16:16 .npmrc\n-rw-r--r--@ 1 pakrym staff 96 Sep 2 08:52 .prettierignore\n-rw-r--r--@ 1 pakrym staff 170 Jul 9 16:16 .prettierrc.toml\ndrwxr-xr-x@ 5 pakrym staff 160 Sep 14 17:43 .vscode\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:37 2025-09-11\n-rw-r--r--@ 1 pakrym staff 5505 Sep 18 09:28 AGENTS.md\n-rw-r--r--@ 1 pakrym staff 92 Sep 2 08:52 CHANGELOG.md\n-rw-r--r--@ 1 pakrym staff 1145 Jul 9 16:16 cliff.toml\ndrwxr-xr-x@ 11 pakrym staff 352 Sep 24 13:03 codex-cli\ndrwxr-xr-x@ 38 pakrym staff 1216 Sep 24 14:38 codex-rs\ndrwxr-xr-x@ 18 pakrym staff 576 Sep 23 11:01 docs\n-rw-r--r--@ 1 pakrym staff 2038 Jul 9 16:16 flake.lock\n-rw-r--r--@ 1 pakrym staff 1434 Jul 9 16:16 flake.nix\n-rw-r--r--@ 1 pakrym staff 10926 Jul 9 16:16 LICENSE\ndrwxr-xr-x@ 465 pakrym staff 14880 Jul 15 07:36 node_modules\n-rw-r--r--@ 1 pakrym staff 242 Aug 5 08:25 NOTICE\n-rw-r--r--@ 1 pakrym staff 578 Aug 14 12:31 package.json\n-rw-r--r--@ 1 pakrym staff 498 Aug 11 09:37 pnpm-lock.yaml\n-rw-r--r--@ 1 pakrym staff 58 Aug 11 09:37 pnpm-workspace.yaml\n-rw-r--r--@ 1 pakrym staff 2402 Jul 9 16:16 PNPM.md\n-rw-r--r--@ 1 pakrym staff 4393 Sep 12 14:36 README.md\ndrwxr-xr-x@ 4 pakrym staff 128 Sep 18 09:28 scripts\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:34 tmp\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_2",
"item_type": "reasoning",
"text": "**Reviewing README.md file**\n\nI've located the README.md file at the root, and it’s 4393 bytes. Now, I need to remove the first line, but first, I should check its content to make sure I’m patching it correctly. I’ll use sed to display the first 20 lines. By reviewing those lines, I can determine exactly what needs to be removed before I proceed with the editing. Let's do this carefully!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_3",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,40p' README.md",
"aggregated_output": "<h1 align=\"center\">OpenAI Codex CLI</h1>\n\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n```shell\nnpm install -g @openai/codex\n```\n\nAlternatively, if you use Homebrew:\n\n```shell\nbrew install codex\n```\n\nThen simply run `codex` to get started:\n\n```shell\ncodex\n```\n\n<details>\n<summary>You can also go to the <a href=\"https://github.com/openai/codex/releases/latest\">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_4",
"item_type": "reasoning",
"text": "**Updating README file**\n\nThe user wants to update the README by removing the first line, which is an HTML h1 tag. I'll proceed to delete that line while keeping the rest intact. To do this, I need to use the apply_patch tool and create a patch in the diff format. I’ll take care to include context lines around the change. After removing the header, I’m considering whether to delete the following blank line as well to keep it tidy."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_5",
"item_type": "reasoning",
"text": "**Crafting the patch**\n\nThe user has asked to remove just the first line, without mentioning the blank lines. Technically, leaving a blank line at the start is acceptable, but it's not ideal. Ideally, I'd prefer to remove the first line while maintaining the subsequent blank line. However, if I can also remove that blank line, it could tidy things up even more. Still, since the user's request is strictly to remove only the first line, I'll stick to that and craft the patch accordingly."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_6",
"item_type": "assistant_message",
"text": "Applying the change by removing the first line from `README.md`."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_7",
"item_type": "file_change",
"changes": [
{
"path": "/Users/pakrym/code/codex/README.md",
"kind": "update"
}
],
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_8",
"item_type": "reasoning",
"text": "**Validating README Update**\n\nI updated the README.md and now I need to validate that the first line has been successfully removed. To do this, I'll check the first 10 lines of the document to ensure everything looks correct. It’s always good to double-check these kinds of changes, so I’m going to take that extra step to make sure the update was executed properly. Let's see what those initial lines say!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_9",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,20p' README.md",
"aggregated_output": "\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_10",
"item_type": "assistant_message",
"text": "- Updated `README.md:1` by removing the opening H1 line.\n- The README now starts with the install instructions paragraph.\n\nWant me to also remove the leading blank line at the top?"
}
}
```
</details>
The idea is to give users fully formatted items they can use directly in
their rendering/application logic and avoid having them building up
items manually based on events (unless they want to for streaming).
This PR implements only the `item.completed` payload for some event
types, more event types and item types to come.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
### Summary
Sometimes in exec runs, we want to allow the model to use the
`update_plan` tool, but that's not easily configurable. This change adds
a feature flag for this, and formats the output so it's human-readable
## Test Plan
<img width="1280" height="354" alt="Screenshot 2025-09-11 at 12 39
44 AM"
src="https://github.com/user-attachments/assets/72e11070-fb98-47f5-a784-5123ca7333d9"
/>
Adding the ability to resume conversations.
we have one verb `resume`.
Behavior:
`tui`:
`codex resume`: opens session picker
`codex resume --last`: continue last message
`codex resume <session id>`: continue conversation with `session id`
`exec`:
`codex resume --last`: continue last conversation
`codex resume <session id>`: continue conversation with `session id`
Implementation:
- I added a function to find the path in `~/.codex/sessions/` with a
`UUID`. This is helpful in resuming with session id.
- Added the above mentioned flags
- Added lots of testing
## 📝 Review Mode -- Core
This PR introduces the Core implementation for Review mode:
- New op `Op::Review { prompt: String }:` spawns a child review task
with isolated context, a review‑specific system prompt, and a
`Config.review_model`.
- `EnteredReviewMode`: emitted when the child review session starts.
Every event from this point onwards reflects the review session.
- `ExitedReviewMode(Option<ReviewOutputEvent>)`: emitted when the review
finishes or is interrupted, with optional structured findings:
```json
{
"findings": [
{
"title": "<≤ 80 chars, imperative>",
"body": "<valid Markdown explaining *why* this is a problem; cite files/lines/functions>",
"confidence_score": <float 0.0-1.0>,
"priority": <int 0-3>,
"code_location": {
"absolute_file_path": "<file path>",
"line_range": {"start": <int>, "end": <int>}
}
}
],
"overall_correctness": "patch is correct" | "patch is incorrect",
"overall_explanation": "<1-3 sentence explanation justifying the overall_correctness verdict>",
"overall_confidence_score": <float 0.0-1.0>
}
```
## Questions
### Why separate out its own message history?
We want the review thread to match the training of our review models as
much as possible -- that means using a custom prompt, removing user
instructions, and starting a clean chat history.
We also want to make sure the review thread doesn't leak into the parent
thread.
### Why do this as a mode, vs. sub-agents?
1. We want review to be a synchronous task, so it's fine for now to do a
bespoke implementation.
2. We're still unclear about the final structure for sub-agents. We'd
prefer to land this quickly and then refactor into sub-agents without
rushing that implementation.
This PR does the following:
* Adds the ability to paste or type an API key.
* Removes the `preferred_auth_method` config option. The last login
method is always persisted in auth.json, so this isn't needed.
* If OPENAI_API_KEY env variable is defined, the value is used to
prepopulate the new UI. The env variable is otherwise ignored by the
CLI.
* Adds a new MCP server entry point "login_api_key" so we can implement
this same API key behavior for the VS Code extension.
<img width="473" height="140" alt="Screenshot 2025-09-04 at 3 51 04 PM"
src="https://github.com/user-attachments/assets/c11bbd5b-8a4d-4d71-90fd-34130460f9d9"
/>
<img width="726" height="254" alt="Screenshot 2025-09-04 at 3 51 32 PM"
src="https://github.com/user-attachments/assets/6cc76b34-309a-4387-acbc-15ee5c756db9"
/>
The previous config approach had a few issues:
1. It is part of the config but not designed to be used externally
2. It had to be wired through many places (look at the +/- on this PR
3. It wasn't guaranteed to be set consistently everywhere because we
don't have a super well defined way that configs stack. For example, the
extension would configure during newConversation but anything that
happened outside of that (like login) wouldn't get it.
This env var approach is cleaner and also creates one less thing we have
to deal with when coming up with a better holistic story around configs.
One downside is that I removed the unit test testing for the override
because I don't want to deal with setting the global env or spawning
child processes and figuring out how to introspect their originator
header. The new code is sufficiently simple and I tested it e2e that I
feel as if this is still worth it.
When item ids are sent to Responses API it will load them from the
database ignoring the provided values. This adds extra latency.
Not having the mode to store requests also allows us to simplify the
code.
## Breaking change
The `disable_response_storage` configuration option is removed.
