### 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.
Adds web_search tool, enabling the model to use Responses API web_search
tool.
- Disabled by default, enabled by --search flag
- When --search is passed, exposes web_search_request function tool to
the model, which triggers user approval. When approved, the model can
use the web_search tool for the remainder of the turn
<img width="1033" height="294" alt="image"
src="https://github.com/user-attachments/assets/62ac6563-b946-465c-ba5d-9325af28b28f"
/>
---------
Co-authored-by: easong-openai <easong@openai.com>
This PR adds a central `AuthManager` struct that manages the auth
information used across conversations and the MCP server. Prior to this,
each conversation and the MCP server got their own private snapshots of
the auth information, and changes to one (such as a logout or token
refresh) were not seen by others.
This is especially problematic when multiple instances of the CLI are
run. For example, consider the case where you start CLI 1 and log in to
ChatGPT account X and then start CLI 2 and log out and then log in to
ChatGPT account Y. The conversation in CLI 1 is still using account X,
but if you create a new conversation, it will suddenly (and
unexpectedly) switch to account Y.
With the `AuthManager`, auth information is read from disk at the time
the `ConversationManager` is constructed, and it is cached in memory.
All new conversations use this same auth information, as do any token
refreshes.
The `AuthManager` is also used by the MCP server's GetAuthStatus
command, which now returns the auth method currently used by the MCP
server.
This PR also includes an enhancement to the GetAuthStatus command. It
now accepts two new (optional) input parameters: `include_token` and
`refresh_token`. Callers can use this to request the in-use auth token
and can optionally request to refresh the token.
The PR also adds tests for the login and auth APIs that I recently added
to the MCP server.
The existing `wire_format.rs` should share more types with the
`codex-protocol` crate (like `AskForApproval` instead of maintaining a
parallel `CodexToolCallApprovalPolicy` enum), so this PR moves
`wire_format.rs` into `codex-protocol`, renaming it as
`mcp-protocol.rs`. We also de-dupe types, where appropriate.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2423).
* #2424
* __->__ #2423
## Summary
We've been seeing a number of issues and reports with our synthetic
`apply_patch` tool, e.g. #802. Let's make this a real tool - in my
anecdotal testing, it's critical for GPT-OSS models, but I'd like to
make it the standard across GPT-5 and codex models as well.
## Testing
- [x] Tested locally
- [x] Integration test
This PR does two things because after I got deep into the first one I
started pulling on the thread to the second:
- Makes `ConversationManager` the place where all in-memory
conversations are created and stored. Previously, `MessageProcessor` in
the `codex-mcp-server` crate was doing this via its `session_map`, but
this is something that should be done in `codex-core`.
- It unwinds the `ctrl_c: tokio::sync::Notify` that was threaded
throughout our code. I think this made sense at one time, but now that
we handle Ctrl-C within the TUI and have a proper `Op::Interrupt` event,
I don't think this was quite right, so I removed it. For `codex exec`
and `codex proto`, we now use `tokio::signal::ctrl_c()` directly, but we
no longer make `Notify` a field of `Codex` or `CodexConversation`.
Changes of note:
- Adds the files `conversation_manager.rs` and `codex_conversation.rs`
to `codex-core`.
- `Codex` and `CodexSpawnOk` are no longer exported from `codex-core`:
other crates must use `CodexConversation` instead (which is created via
`ConversationManager`).
- `core/src/codex_wrapper.rs` has been deleted in favor of
`ConversationManager`.
- `ConversationManager::new_conversation()` returns `NewConversation`,
which is in line with the `new_conversation` tool we want to add to the
MCP server. Note `NewConversation` includes `SessionConfiguredEvent`, so
we eliminate checks in cases like `codex-rs/core/tests/client.rs` to
verify `SessionConfiguredEvent` is the first event because that is now
internal to `ConversationManager`.
- Quite a bit of code was deleted from
`codex-rs/mcp-server/src/message_processor.rs` since it no longer has to
manage multiple conversations itself: it goes through
`ConversationManager` instead.
- `core/tests/live_agent.rs` has been deleted because I had to update a
bunch of tests and all the tests in here were ignored, and I don't think
anyone ever ran them, so this was just technical debt, at this point.
- Removed `notify_on_sigint()` from `util.rs` (and in a follow-up, I
hope to refactor the blandly-named `util.rs` into more descriptive
files).
- In general, I started replacing local variables named `codex` as
`conversation`, where appropriate, though admittedly I didn't do it
through all the integration tests because that would have added a lot of
noise to this PR.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2240).
* #2264
* #2263
* __->__ #2240
## Summary
In collaboration with @gpeal: upgrade the onboarding flow, and persist
user settings.
---------
Co-authored-by: Gabriel Peal <gabriel@openai.com>
Previous to this PR, `ShutdownComplete` was not being handled correctly
in `codex exec`, so it always ended up printing the following to stderr:
```
ERROR codex_exec: Error receiving event: InternalAgentDied
```
Because we were not breaking out of the loop for `ShutdownComplete`,
inevitably `codex.next_event()` would get called again and
`rx_event.recv()` would fail and the error would get mapped to
`InternalAgentDied`:
ea7d3f27bd/codex-rs/core/src/codex.rs (L190-L197)
For reference, https://github.com/openai/codex/pull/1647 introduced the
`ShutdownComplete` variant.
This PR started as an investigation with the goal of eliminating the use
of `unsafe { std::env::set_var() }` in `ollama/src/client.rs`, as
setting environment variables in a multithreaded context is indeed
unsafe and these tests were observed to be flaky, as a result.
Though as I dug deeper into the issue, I discovered that the logic for
instantiating `OllamaClient` under test scenarios was not quite right.
In this PR, I aimed to:
- share more code between the two creation codepaths,
`try_from_oss_provider()` and `try_from_provider_with_base_url()`
- use the values from `Config` when setting up Ollama, as we have
various mechanisms for overriding config values, so we should be sure
that we are always using the ultimate `Config` for things such as the
`ModelProviderInfo` associated with the `oss` id
Once this was in place,
`OllamaClient::try_from_provider_with_base_url()` could be used in unit
tests for `OllamaClient` so it was possible to create a properly
configured client without having to set environment variables.
This adds support for easily running Codex backed by a local Ollama
instance running our new open source models. See
https://github.com/openai/gpt-oss for details.
If you pass in `--oss` you'll be prompted to install/launch ollama, and
it will automatically download the 20b model and attempt to use it.
We'll likely want to expand this with some options later to make the
experience smoother for users who can't run the 20b or want to run the
120b.
Co-authored-by: Michael Bolin <mbolin@openai.com>
This adds a tool the model can call to update a plan. The tool doesn't
actually _do_ anything but it gives clients a chance to read and render
the structured plan. We will likely iterate on the prompt and tools
exposed for planning over time.
## Summary
Adds a new mcp tool call, `codex-reply`, so we can continue existing
sessions. This is a first draft and does not yet support sessions from
previous processes.
## Testing
- [x] tested with mcp client
This is designed to facilitate programmatic use of Codex in a more
lightweight way than using `codex mcp`.
Passing `--json` to `codex exec` will print each event as a line of JSON
to stdout. Note that it does not print the individual tokens as they are
streamed, only full messages, as this is aimed at programmatic use
rather than to power UI.
<img width="1348" height="1307" alt="image"
src="https://github.com/user-attachments/assets/fc7908de-b78d-46e4-a6ff-c85de28415c7"
/>
I changed the existing `EventProcessor` into a trait and moved the
implementation to `EventProcessorWithHumanOutput`. Then I introduced an
alternative implementation, `EventProcessorWithJsonOutput`. The `--json`
flag determines which implementation to use.
On a high-level, we try to design `config.toml` so that you don't have
to "comment out a lot of stuff" when testing different options.
Previously, defining a sandbox policy was somewhat at odds with this
principle because you would define the policy as attributes of
`[sandbox]` like so:
```toml
[sandbox]
mode = "workspace-write"
writable_roots = [ "/tmp" ]
```
but if you wanted to temporarily change to a read-only sandbox, you
might feel compelled to modify your file to be:
```toml
[sandbox]
mode = "read-only"
# mode = "workspace-write"
# writable_roots = [ "/tmp" ]
```
Technically, commenting out `writable_roots` would not be strictly
necessary, as `mode = "read-only"` would ignore `writable_roots`, but
it's still a reasonable thing to do to keep things tidy.
Currently, the various values for `mode` do not support that many
attributes, so this is not that hard to maintain, but one could imagine
this becoming more complex in the future.
In this PR, we change Codex CLI so that it no longer recognizes
`[sandbox]`. Instead, it introduces a top-level option, `sandbox_mode`,
and `[sandbox_workspace_write]` is used to further configure the sandbox
when when `sandbox_mode = "workspace-write"` is used:
```toml
sandbox_mode = "workspace-write"
[sandbox_workspace_write]
writable_roots = [ "/tmp" ]
```
This feels a bit more future-proof in that it is less tedious to
configure different sandboxes:
```toml
sandbox_mode = "workspace-write"
[sandbox_read_only]
# read-only options here...
[sandbox_workspace_write]
writable_roots = [ "/tmp" ]
[sandbox_danger_full_access]
# danger-full-access options here...
```
In this scheme, you never need to comment out the configuration for an
individual sandbox type: you only need to redefine `sandbox_mode`.
Relatedly, previous to this change, a user had to do `-c
sandbox.mode=read-only` to change the mode on the command line. With
this change, things are arguably a bit cleaner because the equivalent
option is `-c sandbox_mode=read-only` (and now `-c
sandbox_workspace_write=...` can be set separately).
Though more importantly, we introduce the `-s/--sandbox` option to the
CLI, which maps directly to `sandbox_mode` in `config.toml`, making
config override behavior easier to reason about. Moreover, as you can
see in the updates to the various Markdown files, it is much easier to
explain how to configure sandboxing when things like `--sandbox
read-only` can be used as an example.
Relatedly, this cleanup also made it straightforward to add support for
a `sandbox` option for Codex when used as an MCP server (see the changes
to `mcp-server/src/codex_tool_config.rs`).
Fixes https://github.com/openai/codex/issues/1248.
This PR reworks `assess_command_safety()` so that the combination of
`AskForApproval::Never` and `SandboxPolicy::DangerFullAccess` ensures
that commands are run without _any_ sandbox and the user should never be
prompted. In turn, it adds support for a new
`--dangerously-bypass-approvals-and-sandbox` flag (that cannot be used
with `--approval-policy` or `--full-auto`) that sets both of those
options.
Fixes https://github.com/openai/codex/issues/1254
This is a major redesign of how sandbox configuration works and aims to
fix https://github.com/openai/codex/issues/1248. Specifically, it
replaces `sandbox_permissions` in `config.toml` (and the
`-s`/`--sandbox-permission` CLI flags) with a "table" with effectively
three variants:
```toml
# Safest option: full disk is read-only, but writes and network access are disallowed.
[sandbox]
mode = "read-only"
# The cwd of the Codex task is writable, as well as $TMPDIR on macOS.
# writable_roots can be used to specify additional writable folders.
[sandbox]
mode = "workspace-write"
writable_roots = [] # Optional, defaults to the empty list.
network_access = false # Optional, defaults to false.
# Disable sandboxing: use at your own risk!!!
[sandbox]
mode = "danger-full-access"
```
This should make sandboxing easier to reason about. While we have
dropped support for `-s`, the way it works now is:
- no flags => `read-only`
- `--full-auto` => `workspace-write`
- currently, there is no way to specify `danger-full-access` via a CLI
flag, but we will revisit that as part of
https://github.com/openai/codex/issues/1254
Outstanding issue:
- As noted in the `TODO` on `SandboxPolicy::is_unrestricted()`, we are
still conflating sandbox preferences with approval preferences in that
case, which needs to be cleaned up.
This PR introduces a `hide_agent_reasoning` config option (that defaults
to `false`) that users can enable to make the output less verbose by
suppressing reasoning output.
To test, verified that this includes agent reasoning in the output:
```
echo hello | just exec
```
whereas this does not:
```
echo hello | just exec --config hide_agent_reasoning=false
```
Fixes:
* Instantiate `EventProcessor` earlier in `lib.rs` so
`print_config_summary()` can be an instance method of it and leverage
its various `Style` fields to ensure it honors `with_ansi` properly.
* After printing the config summary, print out user's prompt with the
heading `User instructions:`. As noted in the comment, now that we can
read the instructions via stdin as of #1178, it is helpful to the user
to ensure they know what instructions were given to Codex.
* Use same colors/bold/italic settings for headers as the TUI, making
the output a bit easier to read.
This attempts to make `codex exec` more flexible in how the prompt can
be passed:
* as before, it can be passed as a single string argument
* if `-` is passed as the value, the prompt is read from stdin
* if no argument is passed _and stdin is a tty_, prints a warning to
stderr that no prompt was specified an exits non-zero.
* if no argument is passed _and stdin is NOT a tty_, prints `Reading
prompt from stdin...` to stderr to let the user know that Codex will
wait until it reads EOF from stdin to proceed. (You can repro this case
by doing `yes | just exec` since stdin is not a TTY in that case but it
also never reaches EOF).
This PR introduces support for `-c`/`--config` so users can override
individual config values on the command line using `--config
name=value`. Example:
```
codex --config model=o4-mini
```
Making it possible to set arbitrary config values on the command line
results in a more flexible configuration scheme and makes it easier to
provide single-line examples that can be copy-pasted from documentation.
Effectively, it means there are four levels of configuration for some
values:
- Default value (e.g., `model` currently defaults to `o4-mini`)
- Value in `config.toml` (e.g., user could override the default to be
`model = "o3"` in their `config.toml`)
- Specifying `-c` or `--config` to override `model` (e.g., user can
include `-c model=o3` in their list of args to Codex)
- If available, a config-specific flag can be used, which takes
precedence over `-c` (e.g., user can specify `--model o3` in their list
of args to Codex)
Now that it is possible to specify anything that could be configured in
`config.toml` on the command line using `-c`, we do not need to have a
custom flag for every possible config option (which can clutter the
output of `--help`). To that end, as part of this PR, we drop support
for the `--disable-response-storage` flag, as users can now specify `-c
disable_response_storage=true` to get the equivalent functionality.
Under the hood, this works by loading the `config.toml` into a
`toml::Value`. Then for each `key=value`, we create a small synthetic
TOML file with `value` so that we can run the TOML parser to get the
equivalent `toml::Value`. We then parse `key` to determine the point in
the original `toml::Value` to do the insert/replace. Once all of the
overrides from `-c` args have been applied, the `toml::Value` is
deserialized into a `ConfigToml` and then the `ConfigOverrides` are
applied, as before.
https://github.com/openai/codex/pull/1086 is a work-in-progress to make
Linux sandboxing work more like Seatbelt where, for the command we want
to sandbox, we build up the command and then hand it, and some sandbox
configuration flags, to another command to set up the sandbox and then
run it.
In the case of Seatbelt, macOS provides this helper binary and provides
it at `/usr/bin/sandbox-exec`. For Linux, we have to build our own and
pass it through (which is what #1086 does), so this makes the new
`codex_linux_sandbox_exe` available on `Config` so that it will later be
available in `exec.rs` when we need it in #1086.
Now the `exec` output starts with something like:
```
--------
workdir: /Users/mbolin/code/codex/codex-rs
model: o3
provider: openai
approval: Never
sandbox: SandboxPolicy { permissions: [DiskFullReadAccess, DiskWritePlatformUserTempFolder, DiskWritePlatformGlobalTempFolder, DiskWriteCwd, DiskWriteFolder { folder: "/Users/mbolin/.pyenv/shims" }] }
--------
```
which makes it easier to reason about when looking at logs.
This introduces an experimental `--output-last-message` flag that can be
used to identify a file where the final message from the agent will be
written. Two use cases:
- Ultimately, we will likely add a `--quiet` option to `exec`, but even
if the user does not want any output written to the terminal, they
probably want to know what the agent did. Writing the output to a file
makes it possible to get that information in a clean way.
- Relatedly, when using `exec` in CI, it is easier to review the
transcript written "normally," (i.e., not as JSON or something with
extra escapes), but getting programmatic access to the last message is
likely helpful, so writing the last message to a file gets the best of
both worlds.
I am calling this "experimental" because it is possible that we are
overfitting and will want a more general solution to this problem that
would justify removing this flag.
This introduces a much-needed "profile" concept where users can specify
a collection of options under one name and then pass that via
`--profile` to the CLI.
This PR introduces the `ConfigProfile` struct and makes it a field of
`CargoToml`. It further updates
`Config::load_from_base_config_with_overrides()` to respect
`ConfigProfile`, overriding default values where appropriate. A detailed
unit test is added at the end of `config.rs` to verify this behavior.
Details on how to use this feature have also been added to
`codex-rs/README.md`.
This is a substantial PR to add support for the chat completions API,
which in turn makes it possible to use non-OpenAI model providers (just
like in the TypeScript CLI):
* It moves a number of structs from `client.rs` to `client_common.rs` so
they can be shared.
* It introduces support for the chat completions API in
`chat_completions.rs`.
* It updates `ModelProviderInfo` so that `env_key` is `Option<String>`
instead of `String` (for e.g., ollama) and adds a `wire_api` field
* It updates `client.rs` to choose between `stream_responses()` and
`stream_chat_completions()` based on the `wire_api` for the
`ModelProviderInfo`
* It updates the `exec` and TUI CLIs to no longer fail if the
`OPENAI_API_KEY` environment variable is not set
* It updates the TUI so that `EventMsg::Error` is displayed more
prominently when it occurs, particularly now that it is important to
alert users to the `CodexErr::EnvVar` variant.
* `CodexErr::EnvVar` was updated to include an optional `instructions`
field so we can preserve the behavior where we direct users to
https://platform.openai.com if `OPENAI_API_KEY` is not set.
* Cleaned up the "welcome message" in the TUI to ensure the model
provider is displayed.
* Updated the docs in `codex-rs/README.md`.
To exercise the chat completions API from OpenAI models, I added the
following to my `config.toml`:
```toml
model = "gpt-4o"
model_provider = "openai-chat-completions"
[model_providers.openai-chat-completions]
name = "OpenAI using Chat Completions"
base_url = "https://api.openai.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"
```
Though to test a non-OpenAI provider, I installed ollama with mistral
locally on my Mac because ChatGPT said that would be a good match for my
hardware:
```shell
brew install ollama
ollama serve
ollama pull mistral
```
Then I added the following to my `~/.codex/config.toml`:
```toml
model = "mistral"
model_provider = "ollama"
```
Note this code could certainly use more test coverage, but I want to get
this in so folks can start playing with it.
For reference, I believe https://github.com/openai/codex/pull/247 was
roughly the comparable PR on the TypeScript side.
Sets submodules to use workspace lints. Added denying unwrap as a
workspace level lint, which found a couple of cases where we could have
propagated errors. Also manually labeled ones that were fine by my eye.
This is the first step in supporting other model providers in the Rust
CLI. Specifically, this PR adds support for the new entries in `Config`
and `ConfigOverrides` to specify a `ModelProviderInfo`, which is the
basic config needed for an LLM provider. This PR does not get us all the
way there yet because `client.rs` still categorically appends
`/responses` to the URL and expects the endpoint to support the OpenAI
Responses API. Will fix that next!
https://github.com/openai/codex/pull/800 made `cwd` a property of
`Config` and made it so the `cwd` is not necessarily
`std::env::current_dir()`. As such, `is_inside_git_repo()` should check
`Config.cwd` rather than `std::env::current_dir()`.
This PR updates `is_inside_git_repo()` to take `Config` instead of an
arbitrary `PathBuf` to force the check to operate on a `Config` where
`cwd` has been resolved to what the user specified.
In order to expose Codex via an MCP server, I realized that we should be
taking `cwd` as a parameter rather than assuming
`std::env::current_dir()` as the `cwd`. Specifically, the user may want
to start a session in a directory other than the one where the MCP
server has been started.
This PR makes `cwd: PathBuf` a required field of `Session` and threads
it all the way through, though I think there is still an issue with not
honoring `workdir` for `apply_patch`, which is something we also had to
fix in the TypeScript version: https://github.com/openai/codex/pull/556.
This also adds `-C`/`--cd` to change the cwd via the command line.
To test, I ran:
```
cargo run --bin codex -- exec -C /tmp 'show the output of ls'
```
and verified it showed the contents of my `/tmp` folder instead of
`$PWD`.
