### 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>
Bumps [tracing-subscriber](https://github.com/tokio-rs/tracing) from
0.3.19 to 0.3.20.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/tracing/releases">tracing-subscriber's
releases</a>.</em></p>
<blockquote>
<h2>tracing-subscriber 0.3.20</h2>
<p><strong>Security Fix</strong>: ANSI Escape Sequence Injection
(CVE-TBD)</p>
<h2>Impact</h2>
<p>Previous versions of tracing-subscriber were vulnerable to ANSI
escape sequence injection attacks. Untrusted user input containing ANSI
escape sequences could be injected into terminal output when logged,
potentially allowing attackers to:</p>
<ul>
<li>Manipulate terminal title bars</li>
<li>Clear screens or modify terminal display</li>
<li>Potentially mislead users through terminal manipulation</li>
</ul>
<p>In isolation, impact is minimal, however security issues have been
found in terminal emulators that enabled an attacker to use ANSI escape
sequences via logs to exploit vulnerabilities in the terminal
emulator.</p>
<h2>Solution</h2>
<p>Version 0.3.20 fixes this vulnerability by escaping ANSI control
characters in when writing events to destinations that may be printed to
the terminal.</p>
<h2>Affected Versions</h2>
<p>All versions of tracing-subscriber prior to 0.3.20 are affected by
this vulnerability.</p>
<h2>Recommendations</h2>
<p>Immediate Action Required: We recommend upgrading to
tracing-subscriber 0.3.20 immediately, especially if your
application:</p>
<ul>
<li>Logs user-provided input (form data, HTTP headers, query parameters,
etc.)</li>
<li>Runs in environments where terminal output is displayed to
users</li>
</ul>
<h2>Migration</h2>
<p>This is a patch release with no breaking API changes. Simply update
your Cargo.toml:</p>
<pre lang="toml"><code>[dependencies]
tracing-subscriber = "0.3.20"
</code></pre>
<h2>Acknowledgments</h2>
<p>We would like to thank <a href="http://github.com/zefr0x">zefr0x</a>
who responsibly reported the issue at
<code>security@tokio.rs</code>.</p>
<p>If you believe you have found a security vulnerability in any
tokio-rs project, please email us at <code>security@tokio.rs</code>.</p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="4c52ca5266"><code>4c52ca5</code></a>
fmt: fix ANSI escape sequence injection vulnerability (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3368">#3368</a>)</li>
<li><a
href="f71cebe41e"><code>f71cebe</code></a>
subscriber: impl Clone for EnvFilter (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3360">#3360</a>)</li>
<li><a
href="3a1f571102"><code>3a1f571</code></a>
Fix CI (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3361">#3361</a>)</li>
<li><a
href="e63ef57f3d"><code>e63ef57</code></a>
chore: prepare tracing-attributes 0.1.30 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3316">#3316</a>)</li>
<li><a
href="6e59a13b1a"><code>6e59a13</code></a>
attributes: fix tracing::instrument regression around shadowing (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3311">#3311</a>)</li>
<li><a
href="e4df761275"><code>e4df761</code></a>
tracing: update core to 0.1.34 and attributes to 0.1.29 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3305">#3305</a>)</li>
<li><a
href="643f392ebb"><code>643f392</code></a>
chore: prepare tracing-attributes 0.1.29 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3304">#3304</a>)</li>
<li><a
href="d08e7a6eea"><code>d08e7a6</code></a>
chore: prepare tracing-core 0.1.34 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3302">#3302</a>)</li>
<li><a
href="6e70c571d3"><code>6e70c57</code></a>
tracing-subscriber: count numbers of enters in <code>Timings</code> (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/2944">#2944</a>)</li>
<li><a
href="c01d4fd9de"><code>c01d4fd</code></a>
fix docs and enable CI on <code>main</code> branch (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3295">#3295</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/tokio-rs/tracing/compare/tracing-subscriber-0.3.19...tracing-subscriber-0.3.20">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
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
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
When using codex-tui on a linux system I was unable to run `cargo
clippy` inside of codex due to:
```
[pid 3548377] socketpair(AF_UNIX, SOCK_SEQPACKET|SOCK_CLOEXEC, 0, <unfinished ...>
[pid 3548370] close(8 <unfinished ...>
[pid 3548377] <... socketpair resumed>0x7ffb97f4ed60) = -1 EPERM (Operation not permitted)
```
And
```
3611300 <... recvfrom resumed>0x708b8b5cffe0, 8, 0, NULL, NULL) = -1 EPERM (Operation not permitted)
```
This PR:
* Fixes a bug that disallowed AF_UNIX to allow it on `socket()`
* Adds recvfrom() to the syscall allow list, this should be fine since
we disable opening new sockets. But we should validate there is not a
open socket inheritance issue.
* Allow socketpair to be called for AF_UNIX
* Adds tests for AF_UNIX components
* All of which allows running `cargo clippy` within the sandbox on
linux, and possibly other tooling using a fork server model + AF_UNIX
comms.
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 introduces some special behavior to the CLIs that are using the
`codex-arg0` crate where if `arg1` is `--codex-run-as-apply-patch`, then
it will run as if `apply_patch arg2` were invoked. This is important
because it means we can do things like:
```
SANDBOX_TYPE=landlock # or seatbelt for macOS
codex debug "${SANDBOX_TYPE}" -- codex --codex-run-as-apply-patch PATCH
```
which gives us a way to run `apply_patch` while ensuring it adheres to
the sandbox the user specified.
While it would be nice to use the `arg0` trick like we are currently
doing for `codex-linux-sandbox`, there is no way to specify the `arg0`
for the underlying command when running under `/usr/bin/sandbox-exec`,
so it will not work for us in this case.
Admittedly, we could have also supported this via a custom environment
variable (e.g., `CODEX_ARG0`), but since environment variables are
inherited by child processes, that seemed like a potentially leakier
abstraction.
This change, as well as our existing reliance on checking `arg0`, place
additional requirements on those who include `codex-core`. Its
`README.md` has been updated to reflect this.
While we could have just added an `apply-patch` subcommand to the
`codex` multitool CLI, that would not be sufficient for the standalone
`codex-exec` CLI, which is something that we distribute as part of our
GitHub releases for those who know they will not be using the TUI and
therefore prefer to use a slightly smaller executable:
https://github.com/openai/codex/releases/tag/rust-v0.10.0
To that end, this PR adds an integration test to ensure that the
`--codex-run-as-apply-patch` option works with the standalone
`codex-exec` CLI.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1702).
* #1705
* #1703
* __->__ #1702
* #1698
* #1697
Historically, we spawned the Seatbelt and Landlock sandboxes in
substantially different ways:
For **Seatbelt**, we would run `/usr/bin/sandbox-exec` with our policy
specified as an arg followed by the original command:
d1de7bb383/codex-rs/core/src/exec.rs (L147-L219)
For **Landlock/Seccomp**, we would do
`tokio::runtime::Builder::new_current_thread()`, _invoke
Landlock/Seccomp APIs to modify the permissions of that new thread_, and
then spawn the command:
d1de7bb383/codex-rs/core/src/exec_linux.rs (L28-L49)
While it is neat that Landlock/Seccomp supports applying a policy to
only one thread without having to apply it to the entire process, it
requires us to maintain two different codepaths and is a bit harder to
reason about. The tipping point was
https://github.com/openai/codex/pull/1061, in which we had to start
building up the `env` in an unexpected way for the existing
Landlock/Seccomp approach to continue to work.
This PR overhauls things so that we do similar things for Mac and Linux.
It turned out that we were already building our own "helper binary"
comparable to Mac's `sandbox-exec` as part of the `cli` crate:
d1de7bb383/codex-rs/cli/Cargo.toml (L10-L12)
We originally created this to build a small binary to include with the
Node.js version of the Codex CLI to provide support for Linux
sandboxing.
Though the sticky bit is that, at this point, we still want to deploy
the Rust version of Codex as a single, standalone binary rather than a
CLI and a supporting sandboxing binary. To satisfy this goal, we use
"the arg0 trick," in which we:
* use `std::env::current_exe()` to get the path to the CLI that is
currently running
* use the CLI as the `program` for the `Command`
* set `"codex-linux-sandbox"` as arg0 for the `Command`
A CLI that supports sandboxing should check arg0 at the start of the
program. If it is `"codex-linux-sandbox"`, it must invoke
`codex_linux_sandbox::run_main()`, which runs the CLI as if it were
`codex-linux-sandbox`. When acting as `codex-linux-sandbox`, we make the
appropriate Landlock/Seccomp API calls and then use `execvp(3)` to spawn
the original command, so do _replace_ the process rather than spawn a
subprocess. Incidentally, we do this before starting the Tokio runtime,
so the process should only have one thread when `execvp(3)` is called.
Because the `core` crate that needs to spawn the Linux sandboxing is not
a CLI in its own right, this means that every CLI that includes `core`
and relies on this behavior has to (1) implement it and (2) provide the
path to the sandboxing executable. While the path is almost always
`std::env::current_exe()`, we needed to make this configurable for
integration tests, so `Config` now has a `codex_linux_sandbox_exe:
Option<PathBuf>` property to facilitate threading this through,
introduced in https://github.com/openai/codex/pull/1089.
This common pattern is now captured in
`codex_linux_sandbox::run_with_sandbox()` and all of the `main.rs`
functions that should use it have been updated as part of this PR.
The `codex-linux-sandbox` crate added to the Cargo workspace as part of
this PR now has the bulk of the Landlock/Seccomp logic, which makes
`core` a bit simpler. Indeed, `core/src/exec_linux.rs` and
`core/src/landlock.rs` were removed/ported as part of this PR. I also
moved the unit tests for this code into an integration test,
`linux-sandbox/tests/landlock.rs`, in which I use
`env!("CARGO_BIN_EXE_codex-linux-sandbox")` as the value for
`codex_linux_sandbox_exe` since `std::env::current_exe()` is not
appropriate in that case.
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.
Some effects of this change:
- New formatting changes across many files. No functionality changes
should occur from that.
- Calls to `set_env` are considered unsafe, since this only happens in
tests we wrap them in `unsafe` blocks
I started this PR because I wanted to share the `format_duration()`
utility function in `codex-rs/exec/src/event_processor.rs` with the TUI.
The question was: where to put it?
`core` should have as few dependencies as possible, so moving it there
would introduce a dependency on `chrono`, which seemed undesirable.
`core` already had this `cli` feature to deal with a similar situation
around sharing common utility functions, so I decided to:
* make `core` feature-free
* introduce `common`
* `common` can have as many "special interest" features as it needs,
each of which can declare their own deps
* the first two features of common are `cli` and `elapsed`
In practice, this meant updating a number of `Cargo.toml` files,
replacing this line:
```toml
codex-core = { path = "../core", features = ["cli"] }
```
with these:
```toml
codex-core = { path = "../core" }
codex-common = { path = "../common", features = ["cli"] }
```
Moving `format_duration()` into its own file gave it some "breathing
room" to add a unit test, so I had Codex generate some tests and new
support for durations over 1 minute.
Taking a pass at building artifacts per platform so we can consider
different distribution strategies that don't require users to install
the full `cargo` toolchain.
Right now this grabs just the `codex-repl` and `codex-tui` bins for 5
different targets and bundles them into a draft release. I think a
clearly marked pre-release set of artifacts will unblock the next step
of testing.
This changes how instantiating `Config` works and also adds
`approval_policy` and `sandbox_policy` as fields. The idea is:
* All fields of `Config` have appropriate default values.
* `Config` is initially loaded from `~/.codex/config.toml`, so values in
`config.toml` will override those defaults.
* Clients must instantiate `Config` via
`Config::load_with_overrides(ConfigOverrides)` where `ConfigOverrides`
has optional overrides that are expected to be settable based on CLI
flags.
The `Config` should be defined early in the program and then passed
down. Now functions like `init_codex()` take fewer individual parameters
because they can just take a `Config`.
Also, `Config::load()` used to fail silently if `~/.codex/config.toml`
had a parse error and fell back to the default config. This seemed
really bad because it wasn't clear why the values in my `config.toml`
weren't getting picked up. I changed things so that
`load_with_overrides()` returns `Result<Config>` and verified that the
various CLIs print a reasonable error if `config.toml` is malformed.
Finally, I also updated the TUI to show which **sandbox** value is being
used, as we do for other key values like **model** and **approval**.
This was also a reminder that the various values of `--sandbox` are
honored on Linux but not macOS today, so I added some TODOs about fixing
that.
As stated in `codex-rs/README.md`:
Today, Codex CLI is written in TypeScript and requires Node.js 22+ to
run it. For a number of users, this runtime requirement inhibits
adoption: they would be better served by a standalone executable. As
maintainers, we want Codex to run efficiently in a wide range of
environments with minimal overhead. We also want to take advantage of
operating system-specific APIs to provide better sandboxing, where
possible.
To that end, we are moving forward with a Rust implementation of Codex
CLI contained in this folder, which has the following benefits:
- The CLI compiles to small, standalone, platform-specific binaries.
- Can make direct, native calls to
[seccomp](https://man7.org/linux/man-pages/man2/seccomp.2.html) and
[landlock](https://man7.org/linux/man-pages/man7/landlock.7.html) in
order to support sandboxing on Linux.
- No runtime garbage collection, resulting in lower memory consumption
and better, more predictable performance.
Currently, the Rust implementation is materially behind the TypeScript
implementation in functionality, so continue to use the TypeScript
implmentation for the time being. We will publish native executables via
GitHub Releases as soon as we feel the Rust version is usable.
