Compare commits

...

505 Commits

Author SHA1 Message Date
aibrahim-oai
2c4a8a38cb Merge branch 'summary_op' into compact_cmd 2025-07-30 16:18:15 -07:00
Ahmed Ibrahim
c85369db78 compact 2025-07-30 16:14:19 -07:00
aibrahim-oai
d9c45b5347 Merge branch 'summary_op' into compact_cmd 2025-07-30 15:48:17 -07:00
Ahmed Ibrahim
00fba9047c new prompt 2025-07-30 15:48:01 -07:00
aibrahim-oai
31c09e08e1 Merge branch 'summary_op' into compact_cmd 2025-07-30 15:36:20 -07:00
Ahmed Ibrahim
5626a47042 revive 2025-07-30 15:08:44 -07:00
aibrahim-oai
5568c191d8 Merge branch 'main' into summary_op 2025-07-30 15:02:38 -07:00
pakrym-oai
301ec72107 Add login status command (#1716)
Print the current login mode, sanitized key and return an appropriate
status.
2025-07-30 14:09:26 -07:00
pakrym-oai
e0e245cc1c Send AGENTS.md as a separate user message (#1737) 2025-07-30 13:56:24 -07:00
aibrahim-oai
2f5557056d moving input item from MCP Protocol back to core Protocol (#1740)
- Currently we have duplicate input item. Let's have one source of truth
in the core.
- Used Requestid type
2025-07-30 13:43:08 -07:00
pakrym-oai
ea01a5ffe2 Add support for a separate chatgpt auth endpoint (#1712)
Adds a `CodexAuth` type that encapsulates information about available
auth modes and logic for refreshing the token.
Changes `Responses` API to send requests to different endpoints based on
the auth type.
Updates login_with_chatgpt to support API-less mode and skip the key
exchange.
2025-07-30 19:40:15 +00:00
aibrahim-oai
93341797c4 fix ci (#1739)
I think this commit broke the CI because it changed the
`McpToolCallBeginEvent` type:
347c81ad00
2025-07-30 11:32:38 -07:00
Jeremy Rose
347c81ad00 remove conversation history widget (#1727)
this widget is no longer used.
2025-07-30 10:05:40 -07:00
aibrahim-oai
3823b32b7a Mcp protocol (#1715)
- Add typed MCP protocol surface in
`codex-rs/mcp-server/src/mcp_protocol.rs` for `requests`, `responses`,
and `notifications`
- Requests: `NewConversation`, `Connect`, `SendUserMessage`,
`GetConversations`
- Message content parts: `Text`, `Image` (`ImageUrl`/`FileId`, optional
`ImageDetail`), File (`Url`/`Id`/`inline Data`)
- Responses: `ToolCallResponseEnvelope` with optional `isError` and
`structuredContent` variants (`NewConversation`, `Connect`,
`SendUserMessageAccepted`, `GetConversations`)
- Notifications: `InitialState`, `ConnectionRevoked`, `CodexEvent`,
`Cancelled`
- Uniform `_meta` on `notifications` via `NotificationMeta`
(`conversationId`, `requestId`)
- Unit tests validate JSON wire shapes for key
`requests`/`responses`/`notifications`
2025-07-29 20:14:41 -07:00
pakrym-oai
6b10e22eb3 Trim bash lc and run with login shell (#1725)
include .zshenv, .zprofile by running with the `-l` flag and don't start
a shell inside a shell when we see the typical `bash -lc` invocation.
2025-07-29 16:49:02 -07:00
Gabriel Peal
8828f6f082 Add an experimental plan tool (#1726)
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.
2025-07-29 14:22:02 -04:00
easong-openai
f8fcaaaf6f Relative instruction file (#1722)
Passing in an instruction file with a bad path led to silent failures,
also instruction relative paths were handled in an unintuitive fashion.
2025-07-29 10:06:05 -07:00
Jeremy Rose
fc85f4812f feat: map ^U to kill-line-to-head (#1711)
see
[discussion](https://github.com/rhysd/tui-textarea/issues/51#issuecomment-3021191712),
it's surprising that ^U behaves this way. IMO the undo/redo
functionality in tui-textarea isn't good enough to be worth preserving,
but if we do bring it back it should probably be on C-z / C-S-z / C-y.
2025-07-29 09:40:26 -07:00
easong-openai
efe7f3c793 alternate login wording? (#1723)
Co-authored-by: Jeremy Rose <172423086+nornagon-openai@users.noreply.github.com>
2025-07-29 16:23:09 +00:00
Jeremy Rose
f66704a88f replace login screen with a simple prompt (#1713)
Perhaps there was an intention to make the login screen prettier, but it
feels quite silly right now to just have a screen that says "press q",
so replace it with something that lets the user directly login without
having to quit the app.

<img width="1283" height="635" alt="Screenshot 2025-07-28 at 2 54 05 PM"
src="https://github.com/user-attachments/assets/f19e5595-6ef9-4a2d-b409-aa61b30d3628"
/>
2025-07-28 17:25:14 -07:00
Dylan
094d7af8c3 [mcp-server] Populate notifications._meta with requestId (#1704)
## Summary
Per the [latest MCP
spec](https://modelcontextprotocol.io/specification/2025-06-18/basic#meta),
the `_meta` field is reserved for metadata. In the [Typescript
Schema](0695a497eb/schema/2025-06-18/schema.ts (L37-L40)),
`progressToken` is defined as a value to be attached to subsequent
notifications for that request.

The
[CallToolRequestParams](0695a497eb/schema/2025-06-18/schema.ts (L806-L817))
extends this definition but overwrites the params field. This ambiguity
makes our generated type definitions tricky, so I'm going to skip
`progressToken` field for now and just send back the `requestId`
instead.
 
In a future PR, we can clarify, update our `generate_mcp_types.py`
script, and update our progressToken logic accordingly.

## Testing
- [x] Added unit tests
- [x] Manually tested with mcp client
2025-07-28 13:32:09 -07:00
Jeremy Rose
2d2df891bb fix: long lines incorrectly wrapped (#1710)
fix to #1685.
2025-07-28 12:19:03 -07:00
easong-openai
80c19ea77c Fix approval workflow (#1696)
(Hopefully) temporary solution to the invisible approvals problem -
prints commands to history when they need approval and then also prints
the result of the approval. In the near future we should be able to do
some fancy stuff with updating commands before writing them to permanent
history.

Also, ctr-c while in the approval modal now acts as esc (aborts command)
and puts the TUI in the state where one additional ctr-c will exit.
2025-07-28 19:00:06 +00:00
aibrahim-oai
19bef7659f Serializing the eventmsg type to snake_case (#1709)
This was an abrupt change on our clients. We need to serialize as
snake_case.
2025-07-28 10:26:27 -07:00
Michael Bolin
5ebb7dd34c chore: split apply_patch logic out of codex.rs and into apply_patch.rs (#1703)
This is a straight refactor, moving apply-patch-related code from
`codex.rs` and into the new `apply_patch.rs` file. The only "logical"
change is inlining `#[allow(clippy::unwrap_used)]` instead of declaring
`#![allow(clippy::unwrap_used)]` at the top of the file (which is
currently the case in `codex.rs`).

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1703).
* #1705
* __->__ #1703
* #1702
* #1698
* #1697
2025-07-28 09:51:22 -07:00
Michael Bolin
d76f96ce79 fix: support special --codex-run-as-apply-patch arg (#1702)
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
2025-07-28 09:26:44 -07:00
Michael Bolin
fcd197d596 fix: use std::env::args_os instead of std::env::args (#1698)
Apparently `std::env::args()` will panic during iteration if any
argument to the process is not valid Unicode:

https://doc.rust-lang.org/std/env/fn.args.html

Let's avoid the risk and just go with `std::env::args_os()`.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1698).
* #1705
* #1703
* #1702
* __->__ #1698
* #1697
2025-07-28 08:52:18 -07:00
Michael Bolin
9102255854 fix: move arg0 handling out of codex-linux-sandbox and into its own crate (#1697) 2025-07-28 08:31:24 -07:00
Jeremy Rose
7ecd3153a8 fix: correctly wrap history items (#1685)
The overall idea here is: skip ratatui for writing into scrollback,
because its primitives are wrong. We want to render full lines of text,
that will be wrapped natively by the terminal, and which we never plan
to update using ratatui (so the `Buffer` struct is overhead and in fact
an inhibition).

Instead, we use ANSI scrolling regions (link reference doc to come).
Essentially, we:
1. Define a scrolling region that extends from the top of the prompt
area all the way to the top of scrollback
2. Scroll that region up by N < (screen_height - viewport_height) lines,
in this PR N=1
3. Put our cursor at the top of the newly empty region
4. Print out our new text like normal

The terminal interactions here (write_spans and its dependencies) are
mostly extracted from ratatui.
2025-07-28 14:45:49 +00:00
Michael Bolin
2405c40026 chore: update Codex::spawn() to return a struct instead of a tuple (#1677)
Also update `init_codex()` to return a `struct` instead of a tuple, as well.
2025-07-27 20:01:35 -07:00
easong-openai
58bed77ba7 Remove tab focus switching (#1694)
Previously pressing tab would switch TUI focus to the history scrollbox - no longer necessary.
2025-07-27 11:04:09 -07:00
aibrahim-oai
5a0079fea2 Changing method in MCP notifications (#1684)
- Changing the codex/event type
2025-07-26 10:35:49 -07:00
Jeremy Rose
c66c99c5b5 fix: crash on resize (#1683)
Without this, resizing the terminal prints "Error: The cursor position
could not be read within a normal duration" and quits the app.
2025-07-25 14:23:38 -07:00
Jeremy Rose
75b4008094 fix: paste with newlines (#1682)
This fixes an issue where pasting multi-line content would break the
composer.
2025-07-25 19:26:40 +00:00
pakrym-oai
7ee87123a6 Optionally run using user profile (#1678) 2025-07-25 11:45:23 -07:00
Michael Bolin
994c9a874d chore: use one write call per item in rollout_writer() (#1679)
Most of the time, we expect the `String` returned by
`serde_json::to_string()` to have extra capacity, so `push('\n')` is
unlikely to allocate, which seems cheaper than an extra `write(2)` call,
on average?
2025-07-25 10:43:36 -07:00
easong-openai
480e82b00d Easily Selectable History (#1672)
This update replaces the previous ratatui history widget with an
append-only log so that the terminal can handle text selection and
scrolling. It also disables streaming responses, which we'll do our best
to bring back in a later PR. It also adds a small summary of token use
after the TUI exits.
2025-07-25 01:56:40 -07:00
Pavel Bezglasny
508abbe990 Update render name in tui for approval_policy to match with config values (#1675)
Currently, codex on start shows the value for the approval policy as
name of
[AskForApproval](2437a8d17a/codex-rs/core/src/protocol.rs (L128))
enum, which differs from
[approval_policy](2437a8d17a/codex-rs/config.md (approval_policy))
config values.
E.g. "untrusted" becomes "UnlessTrusted", "on-failure" -> "OnFailure",
"never" -> "Never".
This PR changes render names of the approval policy to match with
configuration values.
2025-07-24 14:17:57 -07:00
Michael Bolin
a1641743a8 feat: expand the set of commands that can be safely identified as "trusted" (#1668)
This PR updates `is_known_safe_command()` to account for "safe
operators" to expand the set of commands that can be run without
approval. This concept existed in the TypeScript CLI, and we are
[finally!] porting it to the Rust one:


c9e2def494/codex-cli/src/approvals.ts (L531-L541)

The idea is that if we have `EXPR1 SAFE_OP EXPR2` and `EXPR1` and
`EXPR2` are considered safe independently, then `EXPR1 SAFE_OP EXPR2`
should be considered safe. Currently, `SAFE_OP` includes `&&`, `||`,
`;`, and `|`.

In the TypeScript implementation, we relied on
https://www.npmjs.com/package/shell-quote to parse the string of Bash,
as it could provide a "lightweight" parse tree, parsing `'beep || boop >
/byte'` as:

```
[ 'beep', { op: '||' }, 'boop', { op: '>' }, '/byte' ]
```

Though in this PR, we introduce the use of
https://crates.io/crates/tree-sitter-bash for parsing (which
incidentally we were already using in
[`codex-apply-patch`](c9e2def494/codex-rs/apply-patch/Cargo.toml (L18))),
which gives us a richer parse tree. (Incidentally, if you have never
played with tree-sitter, try the
[playground](https://tree-sitter.github.io/tree-sitter/7-playground.html)
and select **Bash** from the dropdown to see how it parses various
expressions.)

As a concrete example, prior to this change, our implementation of
`is_known_safe_command()` could verify things like:

```
["bash", "-lc", "grep -R \"Cargo.toml\" -n"]
```

but not:

```
["bash", "-lc", "grep -R \"Cargo.toml\" -n || true"]
```

With this change, the version with `|| true` is also accepted.

Admittedly, this PR does not expand the safety check to support
subshells, so it would reject, e.g. `bash -lc 'ls || (pwd && echo hi)'`,
but that can be addressed in a subsequent PR.
2025-07-24 14:13:30 -07:00
Michael Bolin
c9e2def494 fix: add true,false,nl to the list of trusted commands (#1676)
`nl` is a line-numbering tool that should be on the _trusted _ list, as
there is nothing concerning on https://gtfobins.github.io/gtfobins/nl/
that would merit exclusion.

`true` and `false` are also safe, though not particularly useful given
how `is_known_safe_command()` works today, but that will change with
https://github.com/openai/codex/pull/1668.
2025-07-24 12:59:36 -07:00
Michael Bolin
7af9cedbd7 fix: create separate test_support crates to eliminate #[allow(dead_code)] (#1667)
Because of a quirk of how implementation tests work in Rust, we had a
number of `#[allow(dead_code)]` annotations that were misleading because
the functions _were_ being used, just not by all integration tests in a
`tests/` folder, so when compiling the test that did not use the
function, clippy would complain that it was unused.

This fixes things by create a "test_support" crate under the `tests/`
folder that is imported as a dev dependency for the respective crate.
2025-07-24 12:19:46 -07:00
vishnu-oai
2437a8d17a Record Git metadata to rollout (#1598)
# Summary

- Writing effective evals for codex sessions requires context of the
overall repository state at the moment the session began
- This change adds this metadata (git repository, branch, commit hash)
to the top of the rollout of the session (if available - if not it
doesn't add anything)
- Currently, this is only effective on a clean working tree, as we can't
track uncommitted/untracked changes with the current metadata set.
Ideally in the future we may want to track unclean changes somehow, or
perhaps prompt the user to stash or commit them.

# Testing
- Added unit tests
- `cargo test && cargo clippy --tests && cargo fmt -- --config
imports_granularity=Item`

### Resulting Rollout
<img width="1243" height="127" alt="Screenshot 2025-07-17 at 1 50 00 PM"
src="https://github.com/user-attachments/assets/68108941-f015-45b2-985c-ea315ce05415"
/>
2025-07-24 11:35:28 -07:00
dependabot[bot]
d2be0720b5 chore(deps): bump toml from 0.9.1 to 0.9.2 in /codex-rs (#1562)
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.1 to 0.9.2.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="c28f9ac30f"><code>c28f9ac</code></a>
chore: Release</li>
<li><a
href="f3a2299148"><code>f3a2299</code></a>
docs: Update changelog</li>
<li><a
href="69f09d3093"><code>69f09d3</code></a>
fix(lex): Don't loop over ')' for forever (<a
href="https://redirect.github.com/toml-rs/toml/issues/1003">#1003</a>)</li>
<li><a
href="cc68ae4f42"><code>cc68ae4</code></a>
fix(lex): Don't loop over ')' for forever</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.1...toml-v0.9.2">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=toml&package-manager=cargo&previous-version=0.9.1&new-version=0.9.2)](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>
2025-07-23 17:22:05 -07:00
dependabot[bot]
173386eeac chore(deps): bump tree-sitter from 0.25.6 to 0.25.8 in /codex-rs (#1561)
Bumps [tree-sitter](https://github.com/tree-sitter/tree-sitter) from
0.25.6 to 0.25.8.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f2f197b6b2"><code>f2f197b</code></a>
0.25.8</li>
<li><a
href="8bb33f7d8c"><code>8bb33f7</code></a>
perf: reorder conditional operands</li>
<li><a
href="6f944de32f"><code>6f944de</code></a>
fix(generate): propagate node types error</li>
<li><a
href="c15938532d"><code>c159385</code></a>
0.25.7</li>
<li><a
href="94b55bfcdc"><code>94b55bf</code></a>
perf: reorder expensive conditional operand</li>
<li><a
href="bcb30f7951"><code>bcb30f7</code></a>
fix(generate): use topological sort for subtype map</li>
<li><a
href="3bd8f7df8e"><code>3bd8f7d</code></a>
perf: More efficient computation of used symbols</li>
<li><a
href="d7529c3265"><code>d7529c3</code></a>
perf: reserve <code>Vec</code> capacities where appropriate</li>
<li><a
href="bf4217f0ff"><code>bf4217f</code></a>
fix(web): wasm export paths</li>
<li><a
href="bb7b339ae2"><code>bb7b339</code></a>
Fix 'extra' field generation for node-types.json</li>
<li>Additional commits viewable in <a
href="https://github.com/tree-sitter/tree-sitter/compare/v0.25.6...v0.25.8">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=tree-sitter&package-manager=cargo&previous-version=0.25.6&new-version=0.25.8)](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>
2025-07-23 16:59:05 -07:00
dependabot[bot]
4a57afaaf2 chore(deps): bump strum_macros from 0.27.1 to 0.27.2 in /codex-rs (#1638)
Bumps [strum_macros](https://github.com/Peternator7/strum) from 0.27.1
to 0.27.2.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/Peternator7/strum/releases">strum_macros's
releases</a>.</em></p>
<blockquote>
<h2>v0.27.2</h2>
<h2>What's Changed</h2>
<ul>
<li>Adding support for doc comments on <code>EnumDiscriminants</code>
generated type… by <a
href="https://github.com/linclelinkpart5"><code>@​linclelinkpart5</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/141">Peternator7/strum#141</a></li>
<li>Drop needless <code>rustversion</code> dependency by <a
href="https://github.com/paolobarbolini"><code>@​paolobarbolini</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/446">Peternator7/strum#446</a></li>
<li>Upgrade <code>phf</code> to v0.12 by <a
href="https://github.com/paolobarbolini"><code>@​paolobarbolini</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/448">Peternator7/strum#448</a></li>
<li>allow discriminants on empty enum by <a
href="https://github.com/crop2000"><code>@​crop2000</code></a> in <a
href="https://redirect.github.com/Peternator7/strum/pull/435">Peternator7/strum#435</a></li>
<li>Remove broken link to EnumTable docs by <a
href="https://github.com/schneems"><code>@​schneems</code></a> in <a
href="https://redirect.github.com/Peternator7/strum/pull/427">Peternator7/strum#427</a></li>
<li>Change enum table callbacks to FnMut. by <a
href="https://github.com/ClaytonKnittel"><code>@​ClaytonKnittel</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/443">Peternator7/strum#443</a></li>
<li>Add <code>#[automatically_derived]</code> to the <code>impl</code>s
by <a
href="https://github.com/dandedotdev"><code>@​dandedotdev</code></a> in
<a
href="https://redirect.github.com/Peternator7/strum/pull/444">Peternator7/strum#444</a></li>
<li>Implement a <code>suffix</code> attribute for serialization of enum
variants by <a
href="https://github.com/amogh-dambal"><code>@​amogh-dambal</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/440">Peternator7/strum#440</a></li>
<li>Expound upon use_phf docs by <a
href="https://github.com/Peternator7"><code>@​Peternator7</code></a> in
<a
href="https://redirect.github.com/Peternator7/strum/pull/449">Peternator7/strum#449</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/paolobarbolini"><code>@​paolobarbolini</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/446">Peternator7/strum#446</a></li>
<li><a href="https://github.com/crop2000"><code>@​crop2000</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/435">Peternator7/strum#435</a></li>
<li><a href="https://github.com/schneems"><code>@​schneems</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/427">Peternator7/strum#427</a></li>
<li><a
href="https://github.com/ClaytonKnittel"><code>@​ClaytonKnittel</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/443">Peternator7/strum#443</a></li>
<li><a
href="https://github.com/dandedotdev"><code>@​dandedotdev</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/444">Peternator7/strum#444</a></li>
<li><a
href="https://github.com/amogh-dambal"><code>@​amogh-dambal</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/440">Peternator7/strum#440</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/Peternator7/strum/compare/v0.27.1...v0.27.2">https://github.com/Peternator7/strum/compare/v0.27.1...v0.27.2</a></p>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/Peternator7/strum/blob/master/CHANGELOG.md">strum_macros's
changelog</a>.</em></p>
<blockquote>
<h2>0.27.2</h2>
<ul>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/141">#141</a>:
Adding support for doc comments on <code>EnumDiscriminants</code>
generated type.</p>
<ul>
<li>The doc comment will be copied from the variant on the type
itself.</li>
</ul>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/435">#435</a>:allow
discriminants on empty enum.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/443">#443</a>:
Change enum table callbacks to FnMut.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/444">#444</a>:
Add <code>#[automatically_derived]</code> to the <code>impl</code>s by
<a href="https://github.com/dandedotdev"><code>@​dandedotdev</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/444">Peternator7/strum#444</a></p>
<ul>
<li>This should make the linter less noisy with warnings in generated
code.</li>
</ul>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/440">#440</a>:
Implement a <code>suffix</code> attribute for serialization of enum
variants.</p>
<pre lang="rust"><code>#[derive(strum::Display)]
#[strum(suffix=&quot;.json&quot;)]
#[strum(serialize_all=&quot;snake_case&quot;)]
enum StorageConfiguration {
  PostgresProvider,
  S3StorageProvider,
  AzureStorageProvider,
}
<p>fn main() {
let response = SurveyResponse::Other(&quot;It was good&quot;.into());
println!(&quot;Loading configuration from: {}&quot;,
StorageConfiguration::PostgresProvider);
// prints: Loaded Configuration from: postgres_provider.json
}
</code></pre></p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/446">#446</a>:
Drop needless <code>rustversion</code> dependency.</p>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="38f66210e7"><code>38f6621</code></a>
Expound upon use_phf docs (<a
href="https://redirect.github.com/Peternator7/strum/issues/449">#449</a>)</li>
<li><a
href="bb1339026b"><code>bb13390</code></a>
Implement a <code>suffix</code> attribute for serialization of enum
variants (<a
href="https://redirect.github.com/Peternator7/strum/issues/440">#440</a>)</li>
<li><a
href="c9e52bfd28"><code>c9e52bf</code></a>
Add <code>#[automatically_derived]</code> to the <code>impl</code>s (<a
href="https://redirect.github.com/Peternator7/strum/issues/444">#444</a>)</li>
<li><a
href="1b00f899e5"><code>1b00f89</code></a>
Change enum table callbacks to FnMut. (<a
href="https://redirect.github.com/Peternator7/strum/issues/443">#443</a>)</li>
<li><a
href="6e2ca25fba"><code>6e2ca25</code></a>
Remove broken link to EnumTable docs (<a
href="https://redirect.github.com/Peternator7/strum/issues/427">#427</a>)</li>
<li><a
href="9503781141"><code>9503781</code></a>
allow discriminants on empty enum (<a
href="https://redirect.github.com/Peternator7/strum/issues/435">#435</a>)</li>
<li><a
href="8553ba2845"><code>8553ba2</code></a>
Upgrade <code>phf</code> to v0.12 (<a
href="https://redirect.github.com/Peternator7/strum/issues/448">#448</a>)</li>
<li><a
href="2eba5c2a5c"><code>2eba5c2</code></a>
Drop needless <code>rustversion</code> dependency (<a
href="https://redirect.github.com/Peternator7/strum/issues/446">#446</a>)</li>
<li><a
href="f301b67d91"><code>f301b67</code></a>
Merge branch 'linclelinkpart5-master-2'</li>
<li><a
href="455b2bf859"><code>455b2bf</code></a>
Merge branch 'master' of <a
href="https://github.com/linclelinkpart5/strum">https://github.com/linclelinkpart5/strum</a>
into lincle...</li>
<li>See full diff in <a
href="https://github.com/Peternator7/strum/compare/v0.27.1...v0.27.2">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=strum_macros&package-manager=cargo&previous-version=0.27.1&new-version=0.27.2)](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>
2025-07-23 16:34:16 -07:00
dependabot[bot]
9f645353e9 chore(deps): bump strum from 0.27.1 to 0.27.2 in /codex-rs (#1639)
Bumps [strum](https://github.com/Peternator7/strum) from 0.27.1 to
0.27.2.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/Peternator7/strum/releases">strum's
releases</a>.</em></p>
<blockquote>
<h2>v0.27.2</h2>
<h2>What's Changed</h2>
<ul>
<li>Adding support for doc comments on <code>EnumDiscriminants</code>
generated type… by <a
href="https://github.com/linclelinkpart5"><code>@​linclelinkpart5</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/141">Peternator7/strum#141</a></li>
<li>Drop needless <code>rustversion</code> dependency by <a
href="https://github.com/paolobarbolini"><code>@​paolobarbolini</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/446">Peternator7/strum#446</a></li>
<li>Upgrade <code>phf</code> to v0.12 by <a
href="https://github.com/paolobarbolini"><code>@​paolobarbolini</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/448">Peternator7/strum#448</a></li>
<li>allow discriminants on empty enum by <a
href="https://github.com/crop2000"><code>@​crop2000</code></a> in <a
href="https://redirect.github.com/Peternator7/strum/pull/435">Peternator7/strum#435</a></li>
<li>Remove broken link to EnumTable docs by <a
href="https://github.com/schneems"><code>@​schneems</code></a> in <a
href="https://redirect.github.com/Peternator7/strum/pull/427">Peternator7/strum#427</a></li>
<li>Change enum table callbacks to FnMut. by <a
href="https://github.com/ClaytonKnittel"><code>@​ClaytonKnittel</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/443">Peternator7/strum#443</a></li>
<li>Add <code>#[automatically_derived]</code> to the <code>impl</code>s
by <a
href="https://github.com/dandedotdev"><code>@​dandedotdev</code></a> in
<a
href="https://redirect.github.com/Peternator7/strum/pull/444">Peternator7/strum#444</a></li>
<li>Implement a <code>suffix</code> attribute for serialization of enum
variants by <a
href="https://github.com/amogh-dambal"><code>@​amogh-dambal</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/440">Peternator7/strum#440</a></li>
<li>Expound upon use_phf docs by <a
href="https://github.com/Peternator7"><code>@​Peternator7</code></a> in
<a
href="https://redirect.github.com/Peternator7/strum/pull/449">Peternator7/strum#449</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/paolobarbolini"><code>@​paolobarbolini</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/446">Peternator7/strum#446</a></li>
<li><a href="https://github.com/crop2000"><code>@​crop2000</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/435">Peternator7/strum#435</a></li>
<li><a href="https://github.com/schneems"><code>@​schneems</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/427">Peternator7/strum#427</a></li>
<li><a
href="https://github.com/ClaytonKnittel"><code>@​ClaytonKnittel</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/443">Peternator7/strum#443</a></li>
<li><a
href="https://github.com/dandedotdev"><code>@​dandedotdev</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/444">Peternator7/strum#444</a></li>
<li><a
href="https://github.com/amogh-dambal"><code>@​amogh-dambal</code></a>
made their first contribution in <a
href="https://redirect.github.com/Peternator7/strum/pull/440">Peternator7/strum#440</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/Peternator7/strum/compare/v0.27.1...v0.27.2">https://github.com/Peternator7/strum/compare/v0.27.1...v0.27.2</a></p>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/Peternator7/strum/blob/master/CHANGELOG.md">strum's
changelog</a>.</em></p>
<blockquote>
<h2>0.27.2</h2>
<ul>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/141">#141</a>:
Adding support for doc comments on <code>EnumDiscriminants</code>
generated type.</p>
<ul>
<li>The doc comment will be copied from the variant on the type
itself.</li>
</ul>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/435">#435</a>:allow
discriminants on empty enum.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/443">#443</a>:
Change enum table callbacks to FnMut.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/444">#444</a>:
Add <code>#[automatically_derived]</code> to the <code>impl</code>s by
<a href="https://github.com/dandedotdev"><code>@​dandedotdev</code></a>
in <a
href="https://redirect.github.com/Peternator7/strum/pull/444">Peternator7/strum#444</a></p>
<ul>
<li>This should make the linter less noisy with warnings in generated
code.</li>
</ul>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/440">#440</a>:
Implement a <code>suffix</code> attribute for serialization of enum
variants.</p>
<pre lang="rust"><code>#[derive(strum::Display)]
#[strum(suffix=&quot;.json&quot;)]
#[strum(serialize_all=&quot;snake_case&quot;)]
enum StorageConfiguration {
  PostgresProvider,
  S3StorageProvider,
  AzureStorageProvider,
}
<p>fn main() {
let response = SurveyResponse::Other(&quot;It was good&quot;.into());
println!(&quot;Loading configuration from: {}&quot;,
StorageConfiguration::PostgresProvider);
// prints: Loaded Configuration from: postgres_provider.json
}
</code></pre></p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/446">#446</a>:
Drop needless <code>rustversion</code> dependency.</p>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="38f66210e7"><code>38f6621</code></a>
Expound upon use_phf docs (<a
href="https://redirect.github.com/Peternator7/strum/issues/449">#449</a>)</li>
<li><a
href="bb1339026b"><code>bb13390</code></a>
Implement a <code>suffix</code> attribute for serialization of enum
variants (<a
href="https://redirect.github.com/Peternator7/strum/issues/440">#440</a>)</li>
<li><a
href="c9e52bfd28"><code>c9e52bf</code></a>
Add <code>#[automatically_derived]</code> to the <code>impl</code>s (<a
href="https://redirect.github.com/Peternator7/strum/issues/444">#444</a>)</li>
<li><a
href="1b00f899e5"><code>1b00f89</code></a>
Change enum table callbacks to FnMut. (<a
href="https://redirect.github.com/Peternator7/strum/issues/443">#443</a>)</li>
<li><a
href="6e2ca25fba"><code>6e2ca25</code></a>
Remove broken link to EnumTable docs (<a
href="https://redirect.github.com/Peternator7/strum/issues/427">#427</a>)</li>
<li><a
href="9503781141"><code>9503781</code></a>
allow discriminants on empty enum (<a
href="https://redirect.github.com/Peternator7/strum/issues/435">#435</a>)</li>
<li><a
href="8553ba2845"><code>8553ba2</code></a>
Upgrade <code>phf</code> to v0.12 (<a
href="https://redirect.github.com/Peternator7/strum/issues/448">#448</a>)</li>
<li><a
href="2eba5c2a5c"><code>2eba5c2</code></a>
Drop needless <code>rustversion</code> dependency (<a
href="https://redirect.github.com/Peternator7/strum/issues/446">#446</a>)</li>
<li><a
href="f301b67d91"><code>f301b67</code></a>
Merge branch 'linclelinkpart5-master-2'</li>
<li><a
href="455b2bf859"><code>455b2bf</code></a>
Merge branch 'master' of <a
href="https://github.com/linclelinkpart5/strum">https://github.com/linclelinkpart5/strum</a>
into lincle...</li>
<li>See full diff in <a
href="https://github.com/Peternator7/strum/compare/v0.27.1...v0.27.2">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=strum&package-manager=cargo&previous-version=0.27.1&new-version=0.27.2)](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>
2025-07-23 16:07:33 -07:00
Gabriel Peal
db84722080 Fix flaky test (#1664)
Co-authored-by: aibrahim-oai <aibrahim@openai.com>
2025-07-23 18:40:00 -04:00
dependabot[bot]
6e1838e0d8 chore(deps): bump rand from 0.9.1 to 0.9.2 in /codex-rs (#1637)
Bumps [rand](https://github.com/rust-random/rand) from 0.9.1 to 0.9.2.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/rust-random/rand/blob/master/CHANGELOG.md">rand's
changelog</a>.</em></p>
<blockquote>
<h2>[0.9.2 — 2025-07-20]</h2>
<h3>Deprecated</h3>
<ul>
<li>Deprecate <code>rand::rngs::mock</code> module and
<code>StepRng</code> generator (<a
href="https://redirect.github.com/rust-random/rand/issues/1634">#1634</a>)</li>
</ul>
<h3>Additions</h3>
<ul>
<li>Enable <code>WeightedIndex&lt;usize&gt;</code> (de)serialization (<a
href="https://redirect.github.com/rust-random/rand/issues/1646">#1646</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="d3dd415705"><code>d3dd415</code></a>
Prepare rand_core 0.9.2 (<a
href="https://redirect.github.com/rust-random/rand/issues/1605">#1605</a>)</li>
<li><a
href="99fabd20e9"><code>99fabd2</code></a>
Prepare rand_core 0.9.2</li>
<li><a
href="c7fe1c43b5"><code>c7fe1c4</code></a>
rand: re-export <code>rand_core</code> (<a
href="https://redirect.github.com/rust-random/rand/issues/1604">#1604</a>)</li>
<li><a
href="db2b1e0bb4"><code>db2b1e0</code></a>
rand: re-export <code>rand_core</code></li>
<li><a
href="ee1d96f9f5"><code>ee1d96f</code></a>
rand_core: implement reborrow for <code>UnwrapMut</code> (<a
href="https://redirect.github.com/rust-random/rand/issues/1595">#1595</a>)</li>
<li><a
href="e0eb2ee0fc"><code>e0eb2ee</code></a>
rand_core: implement reborrow for <code>UnwrapMut</code></li>
<li><a
href="975f602f5d"><code>975f602</code></a>
fixup clippy 1.85 warnings</li>
<li><a
href="775b05be1b"><code>775b05b</code></a>
Relax <code>Sized</code> requirements for blanket impls (<a
href="https://redirect.github.com/rust-random/rand/issues/1593">#1593</a>)</li>
<li>See full diff in <a
href="https://github.com/rust-random/rand/compare/rand_core-0.9.1...rand_core-0.9.2">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=rand&package-manager=cargo&previous-version=0.9.1&new-version=0.9.2)](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>
2025-07-23 15:36:08 -07:00
dependabot[bot]
4fc4e410bd chore(deps-dev): bump @types/node from 24.0.13 to 24.0.15 in /.github/actions/codex (#1636)
[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=@types/node&package-manager=bun&previous-version=24.0.13&new-version=24.0.15)](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>
2025-07-23 15:32:31 -07:00
dependabot[bot]
6dd62ffa3b chore(deps-dev): bump @types/bun from 1.2.18 to 1.2.19 in /.github/actions/codex (#1635)
[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=@types/bun&package-manager=bun&previous-version=1.2.18&new-version=1.2.19)](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>
2025-07-23 15:20:47 -07:00
aibrahim-oai
b4ab7c1b73 Flaky CI fix (#1647)
Flushing before sending `TaskCompleteEvent` and ending the submission
loop to avoid race conditions.
2025-07-23 15:03:26 -07:00
Gabriel Peal
084236f717 Add call_id to patch approvals and elicitations (#1660)
Builds on https://github.com/openai/codex/pull/1659 and adds call_id to
a few more places for the same reason.
2025-07-23 15:55:35 -04:00
Gabriel Peal
bc944e77f5 Improve messages emitted for exec failures (#1659)
1. Emit call_id to exec approval elicitations for mcp client convenience
2. Remove the `-retry` from the call id for the same reason as above but
upstream the reset behavior to the mcp client
2025-07-23 14:43:53 -04:00
pakrym-oai
591cb6149a Always send entire request context (#1641)
Always store the entire conversation history.
Request encrypted COT when not storing Responses.
Send entire input context instead of sending previous_response_id
2025-07-23 10:37:45 -07:00
Michael Bolin
d6c4083f98 feat: support dotenv (including ~/.codex/.env) (#1653)
This PR adds a `load_dotenv()` helper function to the `codex-common`
crate that is available when the `cli` feature is enabled. The function
uses [`dotenvy`](https://crates.io/crates/dotenvy) to update the
environment from:

- `$CODEX_HOME/.env`
- `$(pwd)/.env`

To test:

- ran `printenv OPENAI_API_KEY` to verify the env var exists in my
environment
- ran `just codex exec hello` to verify the CLI uses my `OPENAI_API_KEY`
- ran `unset OPENAI_API_KEY`
- ran `just codex exec hello` again and got **ERROR: Missing environment
variable: `OPENAI_API_KEY`**, as expected
- created `~/.codex/.env` and added `OPENAI_API_KEY=sk-proj-...` (also
ran `chmod 400 ~/.codex/.env` for good measure)
- ran `just codex exec hello` again and it worked, verifying it picked
up `OPENAI_API_KEY` from `~/.codex/.env`

Note this functionality was available in the TypeScript CLI:
https://github.com/openai/codex/pull/122 and was recently requested over
on https://github.com/openai/codex/issues/1262#issuecomment-3093203551.
2025-07-22 15:54:33 -07:00
Michael Bolin
3ef544fb95 chore: for release build, build specific targets instead of --all-targets (#1656)
I noticed that releases have taken longer and longer to build.
Originally, I think I did `--all-targets` to be confident that
everything builds cleanly, but that's really the job of CI that runs on
`main`, so we're spending a lot of time in `rust-release.yml` for not
that much additional signal.
2025-07-22 14:35:50 -07:00
aibrahim-oai
01c0896f0f Adding interrupt Support to MCP (#1646) 2025-07-22 20:33:49 +00:00
Michael Bolin
4082246f6a chore: install an extension for TOML syntax highlighting in the devcontainer (#1650)
Small quality-of-life improvement when doing devcontainer development.
2025-07-22 10:58:09 -07:00
pakrym-oai
6d82907082 Add support for custom base instructions (#1645)
Allows providing custom instructions file as a config parameter and
custom instruction text via MCP tool call.
2025-07-22 09:42:22 -07:00
pakrym-oai
ed206d5687 Log response.failed error message and request-id (#1649)
To help with diagnosing failures.
2025-07-22 09:28:00 -07:00
Michael Bolin
d51654822f fix: use PR_SET_PDEATHSIG so to ensure child processes are killed in a timely manner (#1626)
Some users have reported issues where child processes are not cleaned up
after Codex exits (e.g., https://github.com/openai/codex/issues/1570).

This is generally a tricky issue on operating systems: if a parent
process receives `SIGKILL`, then it terminates immediately and cannot
communicate with the child.

**It only helps on Linux**, but this PR introduces the use of `prctl(2)`
so that if the parent process dies, `SIGTERM` will be delivered to the
child process. Whereas previously, I believe that if Codex spawned a
long-running process (like `tsc --watch`) and the Codex process received
`SIGKILL`, the `tsc --watch` process would be reparented to the init
process and would never be killed. Now with the use of `prctl(2)`, the
`tsc --watch` process should receive `SIGTERM` in that scenario.

We still need to come up with a solution for macOS. I've started to look
at `launchd`, but I'm researching a number of options.
2025-07-22 00:41:27 -07:00
Gabriel Peal
710f728124 Add an elicitation for approve patch and refactor tool calls (#1642)
1. Added an elicitation for `approve-patch` which is very similar to
`approve-exec`.
2. Extracted both elicitations to their own files to prevent
`codex_tool_runner` from blowing up in size.
2025-07-22 02:58:41 -04:00
Michael Bolin
6cf4b96f9d fix: check flags to ripgrep when deciding whether the invocation is "trusted" (#1644)
With this change, if any of `--pre`, `--hostname-bin`, `--search-zip`, or `-z` are used with a proposed invocation of `rg`, do not auto-approve.
2025-07-21 22:38:50 -07:00
Dylan
18b2b30841 [mcp-server] Add reply tool call (#1643)
## 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
2025-07-21 21:01:56 -07:00
aibrahim-oai
1b7fea5396 Merge branch 'summary_op' into compact_cmd 2025-07-21 20:20:58 -07:00
aibrahim-oai
b86cb8f642 Merge branch 'main' into summary_op 2025-07-21 20:20:52 -07:00
Michael Bolin
d49d802b06 test: add integration test for MCP server (#1633)
This PR introduces a single integration test for `cargo mcp`, though it
also introduces a number of reusable components so that it should be
easier to introduce more integration tests going forward.

The new test is introduced in `codex-rs/mcp-server/tests/elicitation.rs`
and the reusable pieces are in `codex-rs/mcp-server/tests/common`.

The test itself verifies new functionality around elicitations
introduced in https://github.com/openai/codex/pull/1623 (and the fix
introduced in https://github.com/openai/codex/pull/1629) by doing the
following:

- starts a mock model provider with canned responses for
`/v1/chat/completions`
- starts the MCP server with a `config.toml` to use that model provider
(and `approval_policy = "untrusted"`)
- sends the `codex` tool call which causes the mock model provider to
request a shell call for `git init`
- the MCP server sends an elicitation to the client to approve the
request
- the client replies to the elicitation with `"approved"`
- the MCP server runs the command and re-samples the model, getting a
`"finish_reason": "stop"`
- in turn, the MCP server sends the final response to the original
`codex` tool call
- verifies that `git init` ran as expected

To test:

```
cargo test shell_command_approval_triggers_elicitation
```

In writing this test, I discovered that `ExecApprovalResponse` does not
conform to `ElicitResult`, so I added a TODO to fix that, since I think
that should be updated in a separate PR. As it stands, this PR does not
update any business logic, though it does make a number of members of
the `mcp-server` crate `pub` so they can be used in the test.

One additional learning from this PR is that
`std::process::Command::cargo_bin()` from the `assert_cmd` trait is only
available for `std::process::Command`, but we really want to use
`tokio::process::Command` so that everything is async and we can
leverage utilities like `tokio::time::timeout()`. The trick I came up
with was to use `cargo_bin()` to locate the program, and then to use
`std::process::Command::get_program()` when constructing the
`tokio::process::Command`.
2025-07-21 10:27:07 -07:00
Michael Bolin
8a6c6cee88 fix: address review feedback on #1621 and #1623 (#1631)
- formalizes `ExecApprovalElicitRequestParams`
- adds some defensive logic when messages fail to parse
- fixes a typo in a comment
2025-07-20 14:42:11 -07:00
Gabriel Peal
8b590105de Don't drop sessions on elicitation responses (#1629) 2025-07-20 13:31:19 -04:00
Michael Bolin
018003e52f feat: leverage elicitations in the MCP server (#1623)
This updates the MCP server so that if it receives an
`ExecApprovalRequest` from the `Codex` session, it in turn sends an [MCP
elicitation](https://modelcontextprotocol.io/specification/draft/client/elicitation)
to the client to ask for the approval decision. Upon getting a response,
it forwards the client's decision via `Op::ExecApproval`.

Admittedly, we should be doing the same thing for
`ApplyPatchApprovalRequest`, but this is our first time experimenting
with elicitations, so I'm inclined to defer wiring that code path up
until we feel good about how this one works.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1623).
* __->__ #1623
* #1622
* #1621
* #1620
2025-07-19 01:32:03 -04:00
Michael Bolin
11fd3123be chore: introduce OutgoingMessageSender (#1622)
Previous to this change, `MessageProcessor` had a
`tokio::sync::mpsc::Sender<JSONRPCMessage>` as an abstraction for server
code to send a message down to the MCP client. Because `Sender` is cheap
to `clone()`, it was straightforward to make it available to tasks
scheduled with `tokio::task::spawn()`.

This worked well when we were only sending notifications or responses
back down to the client, but we want to add support for sending
elicitations in #1623, which means that we need to be able to send
_requests_ to the client, and now we need a bit of centralization to
ensure all request ids are unique.

To that end, this PR introduces `OutgoingMessageSender`, which houses
the existing `Sender<OutgoingMessage>` as well as an `AtomicI64` to mint
out new, unique request ids. It has methods like `send_request()` and
`send_response()` so that callers do not have to deal with
`JSONRPCMessage` directly, as having to set the `jsonrpc` for each
message was a bit tedious (this cleans up `codex_tool_runner.rs` quite a
bit).

We do not have `OutgoingMessageSender` implement `Clone` because it is
important that the `AtomicI64` is shared across all users of
`OutgoingMessageSender`. As such, `Arc<OutgoingMessageSender>` must be
used instead, as it is frequently shared with new tokio tasks.

As part of this change, we update `message_processor.rs` to embrace
`await`, though we must be careful that no individual handler blocks the
main loop and prevents other messages from being handled.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1622).
* #1623
* __->__ #1622
* #1621
* #1620
2025-07-19 00:30:56 -04:00
Michael Bolin
e78ec00e73 chore: support MCP schema 2025-06-18 (#1621)
This updates the schema in `generate_mcp_types.py` from `2025-03-26` to
`2025-06-18`, regenerates `mcp-types/src/lib.rs`, and then updates all
the code that uses `mcp-types` to honor the changes.

Ran

```
npx @modelcontextprotocol/inspector just codex mcp
```

and verified that I was able to invoke the `codex` tool, as expected.


---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1621).
* #1623
* #1622
* __->__ #1621
2025-07-19 00:09:34 -04:00
Michael Bolin
a06d4f58e4 chore: clean up generate_mcp_types.py so codegen matches existing output (#1620) 2025-07-18 21:40:39 -04:00
aibrahim-oai
83eefb55fb Add session loading support to Codex (#1602)
## Summary
- extend rollout format to store all session data in JSON
- add resume/write helpers for rollouts
- track session state after each conversation
- support `LoadSession` op to resume a previous rollout
- allow starting Codex with an existing session via
`experimental_resume` config variable

We need a way later for exploring the available sessions in a user
friendly way.

## Testing
- `cargo test --no-run` *(fails: `cargo: command not found`)*

------
https://chatgpt.com/codex/tasks/task_i_68792a29dd5c832190bf6930d3466fba

This video is outdated. you should use `-c experimental_resume:<full
path>` instead of `--resume <full path>`


https://github.com/user-attachments/assets/7a9975c7-aa04-4f4e-899a-9e87defd947a
2025-07-18 17:04:04 -07:00
aibrahim-oai
9846adeabf Refactor env settings into config (#1601)
## Summary
- add OpenAI retry and timeout fields to Config
- inject these settings in tests instead of mutating env vars
- plumb Config values through client and chat completions logic
- document new configuration options

## Testing
- `cargo test -p codex-core --no-run`

------
https://chatgpt.com/codex/tasks/task_i_68792c5b04cc832195c03050c8b6ea94

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-07-18 19:12:39 +00:00
aibrahim-oai
d5a2148deb Fix ctrl+c interrupt while streaming (#1617)
Interrupting while streaming now causes is broken because we aren't
clearing the delta buffer.
2025-07-18 12:08:25 -07:00
Michael Bolin
cc874c9205 chore: use AtomicBool instead of Mutex<bool> (#1616) 2025-07-18 11:13:34 -07:00
pakrym-oai
6f2b01bb6b feat: ensure session ID header is sent in Response API request (#1614)
Include the current session id in Responses API requests.
2025-07-18 09:59:07 -07:00
aibrahim-oai
9cedeadf6a change the default debounce rate to 10ms (#1606)
changed the default debounce rate to 10ms because typing was laggy.

Before:


https://github.com/user-attachments/assets/e5d15fcb-6a2b-4837-b2b4-c3dcb4cc3409

After



https://github.com/user-attachments/assets/6f0005eb-fd49-4130-ba68-635ee0f2831f
2025-07-17 17:00:17 -07:00
pakrym-oai
327e2254f6 chore: rename toolchain file (#1604)
Rename toolchain file so older versions of cargo can pick it up.
2025-07-17 15:36:15 -07:00
Michael Bolin
e16657ca45 feat: add --json flag to codex exec (#1603)
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.
2025-07-17 15:10:15 -07:00
aibrahim-oai
bb30ab9e96 Implement redraw debounce (#1599)
## Summary
- debouce redraw events so repeated requests don't overwhelm the
terminal
- add `RequestRedraw` event and schedule redraws after 100ms

## Testing
- `cargo clippy --tests`
- `cargo test` *(fails: Sandbox Denied errors in landlock tests)*

------
https://chatgpt.com/codex/tasks/task_i_68792a65b8b483218ec90a8f68746cd8

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-07-17 12:54:55 -07:00
pakrym-oai
6949329a7f chore: auto format code on save and add more details to AGENTS.md (#1582)
Adds a default vscode config with generally applicable settings.
Adds more entrypoints to justfile both  for environment setup and to help
agents better verify changes.
2025-07-17 11:40:00 -07:00
pakrym-oai
b95a010e86 fix: trim MCP tool names to fit into tool name length limit (#1571)
Store fully qualified names along with tool entries so we don't have to re-parse them.

Fixes: https://github.com/openai/codex/issues/1289
2025-07-17 11:35:38 -07:00
aibrahim-oai
fcbcc40f51 Storing the sessions in a more organized way for easier look up. (#1596)
now storing the sessions in `~/.codex/sessions/YYYY/MM/DD/<file>`
2025-07-17 10:12:15 -07:00
aibrahim-oai
4005e3708a Merge branch 'summary_op' into compact_cmd 2025-07-16 22:31:42 -07:00
aibrahim-oai
a026e1e41c Merge branch 'main' into summary_op 2025-07-16 22:30:24 -07:00
aibrahim-oai
643ab1f582 Add streaming to exec and tui (#1594)
Added support for streaming in `tui`
Added support for streaming in `exec`


https://github.com/user-attachments/assets/4215892e-d940-452c-a1d0-416ed0cf14eb
2025-07-16 22:26:31 -07:00
Michael Bolin
d3dbc10479 fix: update bin/codex.js so it listens for exit on the child process (#1590)
When Codex CLI is installed via `npm`, we use a `.js` wrapper script to
launch the Rust binary.

- Previously, we were not listening for signals to ensure that killing
the Node.js process would also kill the underlying Rust process.
- We also did not have a proper `exit` handler in place on the child
process to ensure we exited from the Node.js process.

This PR fixes these things and hopefully addresses
https://github.com/openai/codex/issues/1570.

This also adds logic so that Windows falls back to the TypeScript CLI
again, which should address https://github.com/openai/codex/issues/1573.
2025-07-16 16:35:29 -07:00
Preet 🚀
0bc7ee9193 Added mcp-server name validation (#1591)
This PR implements server name validation for MCP (Model Context
Protocol) servers to ensure they conform to the required pattern
^[a-zA-Z0-9_-]+$. This addresses the TODO comment in
mcp_connection_manager.rs:82.

+ Added validation before spawning MCP client tasks
+ Invalid server names are added to errors map with descriptive messages

I have read the CLA Document and I hereby sign the CLA

---------

Co-authored-by: Michael Bolin <bolinfest@gmail.com>
2025-07-16 16:00:39 -07:00
aibrahim-oai
2bd3314886 support deltas in core (#1587)
- Added support for message and reasoning deltas
- Skipped adding the support in the cli and tui for later
- Commented a failing test (wrong merge) that needs fix in a separate
PR.

Side note: I think we need to disable merge when the CI don't pass.
2025-07-16 15:11:18 -07:00
Michael Bolin
5b820c5ce7 feat: ctrl-d only exits when there is no user input (#1589)
While this does make it so that `ctrl-d` will not exit Codex when the
composer is not empty, `ctrl-d` will still exit Codex if it is in the
"working" state.

Fixes https://github.com/openai/codex/issues/1443.
2025-07-16 08:59:26 -07:00
aibrahim-oai
005511d1dc Merge branch 'summary_op' into compact_cmd 2025-07-14 15:36:44 -07:00
aibrahim-oai
2bc78ea18b Merge branch 'main' into summary_op 2025-07-14 15:35:30 -07:00
aibrahim-oai
12722251d4 Merge branch 'summary_op' into compact_cmd 2025-07-14 15:35:07 -07:00
Ahmed Ibrahim
184abe9f12 adressing reviews 2025-07-14 15:32:52 -07:00
aibrahim-oai
ccac930606 Merge branch 'main' into compact_cmd 2025-07-14 15:26:04 -07:00
aibrahim-oai
f14b5adabf Add SSE Response parser tests (#1541)
## Summary
- add `tokio-test` dev dependency
- implement response stream parsing unit tests

## Testing
- `cargo clippy -p codex-core --tests -- -D warnings`
- `cargo test -p codex-core -- --nocapture`

------
https://chatgpt.com/codex/tasks/task_i_687163f3b2208321a6ce2adbef3fbc06
2025-07-14 14:51:32 -07:00
Michael Bolin
9c0b413fd1 docs: clarify the build process for the npm release (#1568)
It appears that `0.5.0` was built with `stage_release.sh` instead of
`stage_rust_release.py`, so add docs to clarify this and recommend
running `--version` on the release candidate to verify the right thing
was built.
2025-07-14 09:41:11 -07:00
aibrahim-oai
3777e18243 Add CLI streaming integration tests (#1542)
## Summary
- add integration test for chat mode streaming via CLI using wiremock
- add integration test for Responses API streaming via fixture
- call `cargo run` to invoke the CLI during tests

## Testing
- `cargo test -p codex-core --test cli_stream -- --nocapture`
- `cargo clippy --all-targets --all-features -- -D warnings`


------
https://chatgpt.com/codex/tasks/task_i_68715980bbec8321999534fdd6a013c1
2025-07-12 18:05:58 -07:00
aibrahim-oai
0f8ac92390 Allow deadcode in test_support (#1555)
#1546 Was pushed while not passing the clippy integration tests. This is
fixing it.
2025-07-12 17:20:35 -07:00
aibrahim-oai
c46bb67d77 Improve SSE tests (#1546)
## Summary
- support fixture-based SSE data in tests
- add helpers to load SSE JSON fixtures
- add table-driven SSE unit tests
- let integration tests use fixture loading
- fix clippy errors from format! calls

## Testing
- `cargo clippy --tests`
- `cargo test --workspace --exclude codex-linux-sandbox`


------
https://chatgpt.com/codex/tasks/task_i_68717468c3e48321b51c9ecac6ba0f09
2025-07-12 16:53:55 -07:00
Michael Bolin
94f5cad895 fix: when invoking Codex via MCP, use the request id as the Submission id (#1554)
Small quality-of-life improvement when using `codex mcp`.
2025-07-12 16:22:02 -07:00
aibrahim-oai
72504f1d9c Add paste summarization to Codex TUI (#1549)
## Summary
- introduce `Paste` event to avoid per-character paste handling
- collapse large pasted blocks to `[Pasted Content X lines]`
- store the real text so submission still includes it
- wire paste handling through `App`, `ChatWidget`, `BottomPane`, and
`ChatComposer`

## Testing
- `cargo test -p codex-tui`


------
https://chatgpt.com/codex/tasks/task_i_6871e24abf80832184d1f3ca0c61a5ee


https://github.com/user-attachments/assets/eda7412f-da30-4474-9f7c-96b49d48fbf8
2025-07-12 15:32:00 -07:00
Ahmed Ibrahim
3e74a0d173 progress
review

review

warnings

addressing reviews

Reset codex-rs/core/ to match origin/summary_op

Reset codex-rs/core/ to match origin/main

restore
2025-07-12 12:58:19 -07:00
Ahmed Ibrahim
c1bc12ab01 adding tests 2025-07-12 12:37:48 -07:00
aibrahim-oai
80c5891740 Merge branch 'main' into summary_op 2025-07-12 11:32:33 -07:00
Ahmed Ibrahim
f30e25aa11 warnings 2025-07-12 11:26:22 -07:00
dependabot[bot]
fa6d507c51 chore(deps-dev): bump @types/bun from 1.2.13 to 1.2.18 in /.github/actions/codex (#1509)
[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=@types/bun&package-manager=bun&previous-version=1.2.13&new-version=1.2.18)](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>
2025-07-12 10:29:37 -07:00
dependabot[bot]
a52a2fe7a9 chore(deps-dev): bump @types/node from 22.15.21 to 24.0.12 in /.github/actions/codex (#1507)
[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=@types/node&package-manager=bun&previous-version=22.15.21&new-version=24.0.12)](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>
2025-07-12 09:56:54 -07:00
Ahmed Ibrahim
133ad67ce0 review 2025-07-11 17:26:02 -07:00
Ahmed Ibrahim
f8d6e97450 review 2025-07-11 17:23:45 -07:00
Ahmed Ibrahim
99df99d006 progress 2025-07-11 16:19:55 -07:00
Gabriel Peal
bfeb8c92a5 Add codex apply to apply a patch created from the Codex remote agent (#1528)
In order to to this, I created a new `chatgpt` crate where we can put
any code that interacts directly with ChatGPT as opposed to the OpenAI
API. I added a disclaimer to the README for it that it should primarily
be modified by OpenAI employees.


https://github.com/user-attachments/assets/bb978e33-d2c9-4d8e-af28-c8c25b1988e8
2025-07-11 13:30:11 -04:00
Ahmed Ibrahim
f77fab3d2d adding tests 2025-07-10 20:53:07 -07:00
Ahmed Ibrahim
f12ee08378 tui compact 2025-07-10 20:21:48 -07:00
Ahmed Ibrahim
658d69e1a4 add summary operation 2025-07-10 19:37:50 -07:00
Michael Bolin
9e58076cf5 chore: read model field off of Config instead of maintaining the parallel field (#1525)
https://github.com/openai/codex/pull/1524 introduced the new `config`
field on `ModelClient`, so this does the post-PR cleanup to remove the
now-unnecessary `model` field.
2025-07-10 14:37:04 -07:00
Michael Bolin
8a424fcfa3 feat: add new config option: model_supports_reasoning_summaries (#1524)
As noted in the updated docs, this makes it so that you can set:

```toml
model_supports_reasoning_summaries = true
```

as a way of overriding the existing heuristic for when to set the
`reasoning` field on a sampling request:


341c091c5b/codex-rs/core/src/client_common.rs (L152-L166)
2025-07-10 14:30:33 -07:00
dependabot[bot]
341c091c5b chore(deps-dev): bump prettier from 3.5.3 to 3.6.2 in /.github/actions/codex (#1508)
[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=prettier&package-manager=bun&previous-version=3.5.3&new-version=3.6.2)](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>
2025-07-10 12:13:59 -07:00
dependabot[bot]
6b1e4a6846 chore(deps): bump node from 22-slim to 24-slim in /codex-cli (#1505)
Bumps node from 22-slim to 24-slim.


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=node&package-manager=docker&previous-version=22-slim&new-version=24-slim)](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>
2025-07-10 12:11:44 -07:00
dependabot[bot]
75fa65e054 chore(deps): bump toml from 0.9.0 to 0.9.1 in /codex-rs (#1514)
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.0 to 0.9.1.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="8c8ef44ea1"><code>8c8ef44</code></a>
chore: Release</li>
<li><a
href="b60ac5bfe9"><code>b60ac5b</code></a>
fix(toml): Correct minimal version for indexmap (<a
href="https://redirect.github.com/toml-rs/toml/issues/998">#998</a>)</li>
<li><a
href="966bd40511"><code>966bd40</code></a>
fix(toml): Correct minimal version for indexmap</li>
<li><a
href="2ed2af6519"><code>2ed2af6</code></a>
docs(readme): Mention additional crates</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.0...toml-v0.9.1">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=toml&package-manager=cargo&previous-version=0.9.0&new-version=0.9.1)](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>
2025-07-10 11:34:37 -07:00
Michael Bolin
16eafd02ad fix: remove reference to /compact until it is implemented (#1503)
Do not mention `/compact` until
https://github.com/openai/codex/issues/1257 is addressed.
2025-07-10 11:23:35 -07:00
Michael Bolin
c8051b906f chore: drop codex-cli from dependabot (#1523)
We are not actively developing `codex-cli`, so I would rather leave the
existing `pnpm-lock.yaml` files as-is.
2025-07-10 11:23:24 -07:00
Rene Leonhardt
82b0cebe8b chore(rs): update dependencies (#1494)
### Chores
- Update cargo dependencies
- Remove unused cargo dependencies
- Fix clippy warnings
- Update Dockerfile (package.json requires node 22)
- Let Dependabot update bun, cargo, devcontainers, docker,
github-actions, npm (nix still not supported)

### TODO
- Upgrade dependencies with breaking changes

```shell
$ cargo update --verbose
   Unchanged crossterm v0.28.1 (available: v0.29.0)
   Unchanged schemars v0.8.22 (available: v1.0.4)
```
2025-07-10 11:08:16 -07:00
pchuri
3a23a86f4b Add Android platform support for Codex CLI (#1488)
## Summary
Add Android platform support to Codex CLI

## What?
- Added `android` to the list of supported platforms in
`codex-cli/bin/codex.js`
- Treats Android as Linux for binary compatibility

## Why?
- Fixes "Unsupported platform: android (arm64)" error on Termux
- Enables Codex CLI usage on Android devices via Termux
- Improves platform compatibility without affecting other platforms

## How?
- Modified the platform detection switch statement to include `case
"android":`
- Android falls through to the same logic as Linux, using appropriate
ARM64 binaries
- Minimal change with no breaking effects on existing functionality

## Testing
- Tested on Android/Termux environment
- Verified the fix resolves the platform detection error
- Confirmed no impact on other platforms

## Related Issues
Fixes the "Unsupported platform: android (arm64)" error reported by
Termux users
2025-07-09 22:06:55 -07:00
Michael Bolin
268267b59e fix: the completion subcommand should assume the CLI is named codex, not codex-cli (#1496)
Current 0.4.0 release:

```
~/code/codex2/codex-rs$ codex completion | head
_codex-cli() {
    local i cur prev opts cmd
    COMPREPLY=()
    if [[ "${BASH_VERSINFO[0]}" -ge 4 ]]; then
        cur="$2"
    else
        cur="${COMP_WORDS[COMP_CWORD]}"
    fi
    prev="$3"
    cmd=""
```

with this change:

```
~/code/codex2/codex-rs$ just codex completion | head
cargo run --bin codex -- "$@"
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.82s
     Running `target/debug/codex completion`
_codex() {
    local i cur prev opts cmd
    COMPREPLY=()
    if [[ "${BASH_VERSINFO[0]}" -ge 4 ]]; then
        cur="$2"
    else
        cur="${COMP_WORDS[COMP_CWORD]}"
    fi
    prev="$3"
    cmd=""
```
2025-07-09 14:08:35 -07:00
Michael Bolin
4a15ebc1ca feat: add codex completion to generate shell completions (#1491)
Once this lands, we can update our brew formula to use
`generate_completions_from_executable()` like so:


905238ff7f/Formula/h/hgrep.rb (L21-L25)
2025-07-08 21:43:27 -07:00
Michael Bolin
8d35ad0ef7 feat: honor OPENAI_BASE_URL for the built-in openai provider (#1487)
Some users have proxies or other setups where they are ultimately
hitting OpenAI endpoints, but need a custom `base_url` rather than the
default value of `"https://api.openai.com/v1"`. This PR makes it
possible to override the `base_url` for the `openai` provider via the
`OPENAI_BASE_URL` environment variable.
2025-07-08 12:39:52 -07:00
Michael Bolin
cc58f1086d docs: document support for model_reasoning_effort and model_reasoning_summary in profiles (#1486)
Documents the new functionality added in
https://github.com/openai/codex/pull/1484.
2025-07-08 12:26:05 -07:00
Yusuf Eren
e444a50cf0 feat: add reasoning fields to profile settings (#1484) 2025-07-08 12:05:22 -07:00
Michael Bolin
f80fc86f18 chore: default to the latest version of the Codex CLI in the GitHub Action (#1485)
Now we no longer have to update the default value of `codex_release_tag`
in the GitHub Action going forward.
2025-07-08 12:00:13 -07:00
Michael Bolin
0b9cb2b9e7 chore: create a release script for the Rust CLI (#1479)
This is a stopgap solution before migrating the build for the npm
release to GitHub Actions (which is ultimately what should be done to
ensure hermetic builds).

The idea is that instead of continuing to create PRs like
https://github.com/openai/codex/pull/1472 where I have to check in a
change to the `WORKFLOW_URL`, this script uses `gh run list` to get the
`WORKFLOW_URL` dynamically and then threads the value through to
`install_native_deps.sh`.

To create the 0.3.0 release on npm, I ran:

```shell
./codex-cli/scripts/stage_rust_release.py --release-version 0.3.0
```

and then did `npm publish --dry-run` followed by `npm publish` in the
temp directory created by `stage_rust_release.py`.
2025-07-07 23:51:34 -07:00
Michael Bolin
e0c08cea4f feat: add support for --sandbox flag (#1476)
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.
2025-07-07 22:31:30 -07:00
Michael Bolin
0a44c42533 docs: update README to include npm install again (#1475)
v0.2.0 of https://www.npmjs.com/package/@openai/codex now runs the Rust
CLI, so it makes sense to bring back the instructions to use `npm i -g
@openai/codex`.

In most places, I list `npm install` before `brew install` because I
believe `npm` is more readily available, though I in the more detailed
part of the documentation, I note that `brew install` will download
fewer bytes, and in that sense, is preferred.
2025-07-07 17:44:26 -07:00
Michael Bolin
a9bed68947 chore: normalize repository.url in package.json (#1474)
I got this as a warning when doing `npm publish --dry-run`, so I ran
`npm pkg fix` to create this PR, as instructed.
2025-07-07 16:33:06 -07:00
ryozi
fd67a0086c Fix Unicode handling in chat_composer "@" token detection (#1467)
## Issues Fixed

- **Primary Issue (#1450)**: Unicode cursor positioning was incorrect
due to mixing character positions with byte positions
- **Additional Issue**: Full-width spaces (CJK whitespace like " ")
weren't properly handled as token boundaries
- ref:
https://doc.rust-lang.org/std/primitive.char.html#method.is_whitespace

---------

Co-authored-by: Michael Bolin <bolinfest@gmail.com>
2025-07-07 13:43:31 -07:00
Michael Bolin
c221eab0b5 feat: support custom HTTP headers for model providers (#1473)
This adds support for two new model provider config options:

- `http_headers` for hardcoded (key, value) pairs
- `env_http_headers` for headers whose values should be read from
environment variables

This also updates the built-in `openai` provider to use this feature to
set the following headers:

- `originator` => `codex_cli_rs`
- `version` => [CLI version]
- `OpenAI-Organization` => `OPENAI_ORGANIZATION` env var
- `OpenAI-Project` => `OPENAI_PROJECT` env var

for consistency with the TypeScript implementation:


bd5a9e8ba9/codex-cli/src/utils/agent/agent-loop.ts (L321-L329)

While here, this also consolidates some logic that was duplicated across
`client.rs` and `chat_completions.rs` by introducing
`ModelProviderInfo.create_request_builder()`.

Resolves https://github.com/openai/codex/discussions/1152
2025-07-07 13:09:16 -07:00
Michael Bolin
bd5a9e8ba9 chore: update release scripts for the TypeScript CLI (#1472)
This introduces two changes to make a quick fix so we can deploy the
Rust CLI for `0.2.0` of `@openai/codex` on npm:

- Updates `WORKFLOW_URL` to point to
https://github.com/openai/codex/actions/runs/15981617627, which is the
GitHub workflow run used to create the binaries for the `0.2.0` release
we published to Homebrew.
- Adds a `--version` option to `stage_release.sh` to specify what the
`version` field in the `package.json` will be.

Locally, I ran the following:

```
./codex-cli/scripts/stage_release.sh --native --version 0.2.0
```

Previously, we only used the `--native` flag to publish to the `native`
tag of `@openai/codex` (e.g., `npm publish --tag native`), but we should
just publish this as the default tag for `0.2.0` to be consistent with
what is in Homebrew.

We can still publish one "final" version of the TypeScript CLI as 0.1.x
later.

Under the hood, this release will still contain `dist/cli.js`,
`bin/codex-linux-sandbox-x64`, and `bin/codex-x86_64-apple-darwin`,
which are not strictly necessary, but we'll fix that in `0.3.0`.
2025-07-07 09:43:03 -07:00
Michael Bolin
abcca30d93 docs: update documentation to reflect Rust CLI release (#1440)
As promised on https://github.com/openai/codex/discussions/1405, we are
making the first official release of the Rust CLI as v0.2.0. As part of
this move, we are making it available in Homebrew:

https://github.com/Homebrew/homebrew-core/pull/228615

Ultimately, we also plan to continue to make the CLI available in npm,
as well, though brew is a bit nicer in that `brew install` will download
only the binary for your platform whereas an npm module is expected to
contain the binaries for _all_ supported platforms, so it is a bit more
heavyweight.

A big part of this change is updating the root `README.md` to document
the behavior of the Rust CLI, which differs in a number of ways from the
TypeScript CLI. The existing `README.md` is moved to
`codex-cli/README.md` as part of this PR, as it is still applicable to
that folder.

As this is still early days for the Rust CLI, I encourage folks to
provide feedback on the command line flags and configuration options.
2025-07-01 15:00:31 -07:00
Michael Bolin
4cb3c76798 fix: softprops/action-gh-release@v2 should use existing tag instead of creating a new tag (#1436)
https://github.com/Homebrew/homebrew-core/pull/228521 details the issues
I was having with the **Source code (tar.gz)** artifact for our GitHub
releases not being quite right. I landed these PRs as stabs in the dark
to fix this:

- https://github.com/openai/codex/pull/1423
- https://github.com/openai/codex/pull/1430

Based on the insights from
https://github.com/Homebrew/homebrew-core/pull/228521, I think those
were wrong and the real problem was this:


6dad5c3b17/.github/workflows/rust-release.yml (L162)

That is, I was manufacturing a new tag name on the fly instead of using
the existing one.

This PR reverts #1423 and #1430 and hopefully fixes how `tag_name` is
set for the `softprops/action-gh-release@v2` step so the **Source code
(tar.gz)** includes the correct files. Assuming this works, this should
make the Homebrew formula straightforward.
2025-06-30 12:10:48 -07:00
Michael Bolin
6dad5c3b17 feat: add query_params option to ModelProviderInfo to support Azure (#1435)
As discovered in https://github.com/openai/codex/issues/1365, the Azure
provider needs to be able to specify `api-version` as a query param, so
this PR introduces a generic `query_params` option to the
`model_providers` config so that an Azure provider can be defined as
follows:

```toml
[model_providers.azure]
name = "Azure"
base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"
env_key = "AZURE_OPENAI_API_KEY"
query_params = { api-version = "2025-04-01-preview" }
```

This PR also updates the docs with this example.

While here, we also update `wire_api` to default to `"chat"`, as that is
likely the common case for someone defining an external provider.

Fixes https://github.com/openai/codex/issues/1365.
2025-06-30 11:39:54 -07:00
Michael Bolin
cd2d84d496 fix: need to check out the branch, not the tag (#1430)
This should have been done in https://github.com/openai/codex/pull/1423.
2025-06-29 10:18:50 -07:00
Michael Bolin
688100f7f4 chore: fix Rust release process so generated .tar.gz source works with Homebrew (#1423)
Looking at existing releases such as
https://github.com/openai/codex/releases/tag/codex-rs-b289c9207090b2e27494545d7b5404e063bd86f3-1-rust-v0.1.0-alpha.4,
the `.tar.gz` for the source code still seems to have `0.0.0` as the
`version` in `codex-rs/Cargo.toml` instead of what the tag seems to say
it should have:


b289c92070/codex-rs/Cargo.toml (L21)

ChatGPT claims:

> When GitHub generates the Source code (tar.gz) archive for a tag:
	•	It uses the commit the tag points to.
• But in some cases (e.g., shallow clones, GitHub CI, or local tools
that only clone the default branch), that commit may not be included,
and you might get an outdated view or nothing at all depending on how
it’s fetched.
	
Trying this recommended fix.
2025-06-28 19:46:44 -07:00
Michael Bolin
f30bf4bbcf fix: support pre-release identifiers in tags (#1422)
Had to update the regex in the GitHub workflow to allow suffixes like
`-alpha.4`.

Successfully ran:

```
./scripts/create_github_release.sh 0.1.0-alpha.4
```

to create
https://github.com/openai/codex/releases/tag/codex-rs-b289c9207090b2e27494545d7b5404e063bd86f3-1-rust-v0.1.0-alpha.4

and verified that when I run `codex --version`, it prints `codex-cli
0.1.0-alpha.4`.
2025-06-28 16:05:53 -07:00
Michael Bolin
1b7c8d2569 fix: build with codegen-units = 1 for profile.release (#1421)
Great suggestion from @zamazan4ik on
https://github.com/openai/codex/issues/1411.
2025-06-28 15:24:48 -07:00
Michael Bolin
4a341efe92 feat: highlight matching characters in fuzzy file search (#1420)
Using the new file-search API introduced in
https://github.com/openai/codex/pull/1419, matching characters are now
shown in bold in the TUI:


https://github.com/user-attachments/assets/8bbcc6c6-75a3-493f-8ea4-b2a063e09b3a

Fixes https://github.com/openai/codex/issues/1261
2025-06-28 15:04:23 -07:00
Michael Bolin
e2efe8da9c feat: introduce --compute-indices flag to codex-file-search (#1419)
This is a small quality-of-life feature, the addition of
`--compute-indices` to the CLI, which, if enabled, will compute and set
the `indices` field for each `FileMatch` returned by `run()`. Note we
only bother to compute `indices` once we have the top N results because
there could be a lot of intermediate "top N" results during the search
that are ultimately discarded.

When set, the indices are included in the JSON output when `--json` is
specified and the matching indices are displayed in bold when `--json`
is not specified.
2025-06-28 14:39:29 -07:00
Michael Bolin
5a0f236ca4 feat: add support for @ to do file search (#1401)
Introduces support for `@` to trigger a fuzzy-filename search in the
composer. Under the hood, this leverages
https://crates.io/crates/nucleo-matcher to do the fuzzy matching and
https://crates.io/crates/ignore to build up the list of file candidates
(so that it respects `.gitignore`).

For simplicity (at least for now), we do not do any caching between
searches like VS Code does for its file search:


1d89ed699b/src/vs/workbench/services/search/node/rawSearchService.ts (L212-L218)

Because we do not do any caching, I saw queries take up to three seconds
on large repositories with hundreds of thousands of files. To that end,
we do not perform searches synchronously on each keystroke, but instead
dispatch an event to do the search on a background thread that
asynchronously reports back to the UI when the results are available.
This is largely handled by the `FileSearchManager` introduced in this
PR, which also has logic for debouncing requests so there is at most one
search in flight at a time.

While we could potentially polish and tune this feature further, it may
already be overengineered for how it will be used, in practice, so we
can improve things going forward if it turns out that this is not "good
enough" in the wild.

Note this feature does not work like `@` in the TypeScript CLI, which
was more like directory-based tab completion. In the Rust CLI, `@`
triggers a full-repo fuzzy-filename search.

Fixes https://github.com/openai/codex/issues/1261.
2025-06-28 13:47:42 -07:00
Michael Bolin
ff8ae1ffa1 feat: make file search cancellable (#1414)
Update `run()` to take `cancel_flag: Arc<AtomicBool>` that the worker
threads will periodically check to see if it is `true`, exiting early
(and returning empty results) if so.
2025-06-27 20:01:45 -07:00
Michael Bolin
b3ad764532 chore: change arg from PathBuf to &Path (#1409)
Caller no longer needs to clone a `PathBuf`: can just pass `&Path`.
2025-06-27 16:24:41 -07:00
Michael Bolin
a331a67b3e chore: change built_in_model_providers so "openai" is the only "bundled" provider (#1407)
As we are [close to releasing the Rust CLI
beta](https://github.com/openai/codex/discussions/1405), for the moment,
let's take a more neutral stance on what it takes to be a "built-in"
provider.

* For example, there seems to be a discrepancy around what the "right"
configuration for Gemini is: https://github.com/openai/codex/pull/881
* And while the current list of "built-in" providers are all arguably
"well-known" names, this raises a question of what to do about
potentially less familiar providers, such as
https://github.com/openai/codex/pull/1142. Do we just accept every pull
request like this, or is there some criteria a provider has to meet to
"qualify" to be bundled with Codex CLI?

I think that if we can establish clear ground rules for being a built-in
provider, then we can bring this back. But until then, I would rather
take a minimalist approach because if we decided to reverse our position
later, it would break folks who were depending on the presence of the
built-in providers.
2025-06-27 14:49:55 -07:00
Gabriel Peal
2e293ce903 Handle Ctrl+C quit when idle (#1402)
## Summary
- show `Ctrl+C to quit` hint when pressing Ctrl+C with no active task
- exiting with Ctrl+C if the hint is already visible
- clear the hint when tasks begin or other keys are pressed


https://github.com/user-attachments/assets/931e2d7c-1c80-4b45-9908-d119f74df23c



------
https://chatgpt.com/s/cd_685ec8875a308191beaa95886dc1379e

Fixes #1245
2025-06-27 13:37:11 -04:00
Michael Bolin
64feeb3803 fix: add tiebreaker logic for paths when scores are equal (#1400)
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1400).
* #1401
* __->__ #1400
2025-06-26 23:05:10 -07:00
Michael Bolin
fa0e17f83a feat: add support for /diff command (#1389)
Adds support for a `/diff` command comparable to the one available in
the TypeScript CLI.

<img width="1103" alt="Screenshot 2025-06-26 at 12 31 33 PM"
src="https://github.com/user-attachments/assets/5dc646ca-301f-41ff-92a7-595c68db64b6"
/>

While here, changed the `SlashCommand` enum so the declared variant
order is the order the commands appear in the popup menu. This way,
`/toggle-mouse-mode` is listed last, as it is the least likely to be
used.

Fixes https://github.com/openai/codex/issues/1253.
2025-06-26 13:03:31 -07:00
Gabriel Peal
a339a7bcce [Rust] Allow resuming a session that was killed with ctrl + c (#1387)
Previously, if you ctrl+c'd a conversation, all subsequent turns would
400 because the Responses API never got a response for one of its call
ids. This ensures that if we aren't sending a call id by hand, we
generate a synthetic aborted call.

Fixes #1244 


https://github.com/user-attachments/assets/5126354f-b970-45f5-8c65-f811bca8294a
2025-06-26 14:40:42 -04:00
Michael Bolin
fcfe43c7df feat: show number of tokens remaining in UI (#1388)
When using the OpenAI Responses API, we now record the `usage` field for
a `"response.completed"` event, which includes metrics about the number
of tokens consumed. We also introduce `openai_model_info.rs`, which
includes current data about the most common OpenAI models available via
the API (specifically `context_window` and `max_output_tokens`). If
Codex does not recognize the model, you can set `model_context_window`
and `model_max_output_tokens` explicitly in `config.toml`.

When then introduce a new event type to `protocol.rs`, `TokenCount`,
which includes the `TokenUsage` for the most recent turn.

Finally, we update the TUI to record the running sum of tokens used so
the percentage of available context window remaining can be reported via
the placeholder text for the composer:

![Screenshot 2025-06-25 at 11 20
55 PM](https://github.com/user-attachments/assets/6fd6982f-7247-4f14-84b2-2e600cb1fd49)

We could certainly get much fancier with this (such as reporting the
estimated cost of the conversation), but for now, we are just trying to
achieve feature parity with the TypeScript CLI.

Though arguably this improves upon the TypeScript CLI, as the TypeScript
CLI uses heuristics to estimate the number of tokens used rather than
using the `usage` information directly:


296996d74e/codex-cli/src/utils/approximate-tokens-used.ts (L3-L16)

Fixes https://github.com/openai/codex/issues/1242
2025-06-25 23:31:11 -07:00
Michael Bolin
296996d74e feat: standalone file search CLI (#1386)
Standalone fuzzy filename search library that should be helpful in
addressing https://github.com/openai/codex/issues/1261.
2025-06-25 13:29:03 -07:00
Michael Bolin
50924101d2 feat: add --dangerously-bypass-approvals-and-sandbox (#1384)
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
2025-06-25 12:36:10 -07:00
Michael Bolin
72082164c1 chore: rename AskForApproval::UnlessAllowListed to AskForApproval::UnlessTrusted (#1385)
We could just rename to `Untrusted` instead of `UnlessTrusted`, but I
think `AskForApproval::UnlessTrusted` reads a bit better.
2025-06-25 12:26:13 -07:00
Michael Bolin
e09691337d chore: improve docstring for --full-auto (#1379)
Reference `-c sandbox.mode=workspace-write` in the docstring and users
can read the config docs for `sandbox` for more information.
2025-06-25 09:13:36 -07:00
Michael Bolin
86d5a9d80d chore: rename unless-allow-listed to untrusted (#1378)
For the `approval_policy` config option, renames `unless-allow-listed`
to `untrusted`. In general, when it comes to exec'ing commands, I think
"trusted" is a more accurate term than "safe."

Also drops the `AskForApproval::AutoEdit` variant, as we were not really
making use of it, anyway.

Fixes https://github.com/openai/codex/issues/1250.


---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1378).
* #1379
* __->__ #1378
2025-06-24 22:19:21 -07:00
Michael Bolin
531ce7626f fix: pretty-print the sandbox config in the TUI/exec modes (#1376)
Now that https://github.com/openai/codex/pull/1373 simplified the
sandbox config, we can print something much simpler in the TUI (and in
`codex exec`) to summarize the sandbox config.

Before:

![Screenshot 2025-06-24 at 5 45
52 PM](https://github.com/user-attachments/assets/b7633efb-a619-43e1-9abe-7bb0be2d0ec0)

With this change:

![Screenshot 2025-06-24 at 5 46
44 PM](https://github.com/user-attachments/assets/8d099bdd-a429-4796-a08d-70931d984e4f)

For reference, my `config.toml` contains:

```
[sandbox]
mode = "workspace-write"
writable_roots = ["/tmp", "/Users/mbolin/.pyenv/shims"]
```

Fixes https://github.com/openai/codex/issues/1248
2025-06-24 17:48:51 -07:00
Michael Bolin
63363a54e5 chore: install just in the devcontainer for Linux development (#1375)
Apparently `just` was added to `apt` in Ubuntu 24, so this required
updating the Ubuntu version in the `Dockerfile` to make it so we could
simply `apt install just`.

Though then that caused a conflict with the custom `dev` user we were
using, though the end result seems simpler since now we just use the
default `ubuntu` user provided by Ubuntu 24.
2025-06-24 17:20:53 -07:00
Michael Bolin
6d65010aad chore: install clippy and rustfmt in the devcontainer for Linux development (#1374)
I discovered it was difficult to do development in the devcontainer
without these tools available.
2025-06-24 17:05:36 -07:00
Michael Bolin
0776d78357 feat: redesign sandbox config (#1373)
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.
2025-06-24 16:59:47 -07:00
Eric Wright
ed5e848f3e add: responses api support for azure (#1321)
- Use Responses API for Azure provider endpoints
- Added a unit test to catch regression on the change from
`/chat/completions` to `/responses`
- Updated the default AOAI api version from `2025-03-01-preview` to
`2025-04-01-preview` to avoid user/400 errors due to missing summary
support in the March API version.
- Changes have been tested locally on AOAI endpoints
2025-06-22 18:01:13 -07:00
Govind Kamtamneni
5aafe190e2 feat(ts): provider‑specific API‑key discovery and clearer Azure guidance (#1324)
## Summary

This PR refactors the Codex CLI authentication flow so that
**non-OpenAI** providers (for example **azure**, or any future addition)
can supply their API key through a dedicated environment variable
without triggering the OpenAI login flow.

Key behaviours introduced:

* When `provider !== "openai"` the CLI consults `src/utils/providers.ts`
to locate the correct environment variable (`AZURE_OPENAI_API_KEY`,
`GEMINI_API_KEY`, and so on) before considering any interactive login.
* Credit redemption (`--free`) and PKCE login now run **only** when the
provider is OpenAI, eliminating unwanted browser prompts for Azure and
others.
* User-facing error messages are revamped to guide Azure users to
**[https://ai.azure.com/](https://ai.azure.com)** and show the exact
variable name they must set.
* All code paths still export `OPENAI_API_KEY` so legacy scripts
continue to operate unchanged.

---

## Example `config.json`

```jsonc
{
  "model": "codex-mini",
  "provider": "azure",
  "providers": {
    "azure": {
      "name": "AzureOpenAI",
      "baseURL": "https://ai-<project-name>.openai.azure.com/openai",
      "envKey": "AZURE_OPENAI_API_KEY"
    }
  },
  "history": {
    "maxSize": 1000,
    "saveHistory": true,
    "sensitivePatterns": []
  }
}
```

With this file in `~/.codex/config.json`, a single command line is
enough:

```bash
export AZURE_OPENAI_API_KEY="<your-key>"
codex "Hello from Azure"
```

No browser window opens, and the CLI works in entirely non-interactive
mode.

---

## Rationale

The new flow enables Codex to run **asynchronously** in sandboxed
environments such as GitHub Actions pipelines. By passing `--provider
azure` (or setting it in `config.json`) and exporting the correct key,
CI/CD jobs can invoke Codex without any ChatGPT-style login or PKCE
round-trip. This unlocks fully automated testing and deployment
scenarios.

---

## What’s changed

| File | Type | Description |
| ------------------------ | ------------------- |
-----------------------------------------------------------------------------------------------------------------------------
|
| `codex-cli/src/cli.tsx` | **feat / refactor** | +43 / -20 lines.
Imports `providers`, adds early provider-specific key lookup, gates
`--free` redemption, rewrites help text. |
| `src/utils/providers.ts` | **chore** | Now consumed by CLI for env-var
discovery. |

---

## How to test

```bash
# Azure example
export AZURE_OPENAI_API_KEY="<your-key>"
codex --provider azure "Automated run in CI"

# OpenAI example (unchanged behaviour)
codex --provider openai --login "Standard OpenAI flow"
```

Expected outcomes:

* Azure and other provider paths are non-interactive when provider flag
is passed.
* The CLI always sets `OPENAI_API_KEY` for backward compatibility.

---

## Checklist

* [x] Logic behind provider-specific env-var lookup added.
* [x] Redundant OpenAI login steps removed for other providers.
* [x] Unit tests cover new branches.
* [x] README and sample config updated.
* [x] CI passes on all supported Node versions.

---

**Related work**

* #92
* #769 
* #1321



I have read the CLA Document and I hereby sign the CLA.
2025-06-22 17:56:36 -07:00
Michael Bolin
b73426c1c4 docs: update codex-rs/README.md to list new features in the Rust CLI (#1267)
Let users know about what the Rust CLI supports that the TypeScript CLI
doesn't!
2025-06-06 18:32:10 -07:00
Reilly Wood
345a38502d codex-rs: Rename /clear to /new, make it start an entirely new chat (#1264)
I noticed that `/clear` wasn't fully clearing chat history; it would
clear the chat history widgets _in the UI_, but the LLM still had access
to information from previous messages.

This PR renames `/clear` to `/new` for clarity as per Michael's
suggestion, resetting `app_state` to a fresh `ChatWidget`.
2025-06-06 16:29:37 -07:00
Michael Bolin
029f39b9da feat: port maybeRedeemCredits() from get-api-key.tsx to login_with_chatgpt.py (#1221)
This builds on https://github.com/openai/codex/pull/1212 and ports the
`maybeRedeemCredits()` function from `get-api-key.ts` to
`login_with_chatgpt.py`:


a80240cfdc/codex-cli/src/utils/get-api-key.tsx (L84-L89)
2025-06-05 23:34:10 -07:00
Michael Bolin
a80240cfdc chore: ensure next Node.js release includes musl binaries for arm64 Linux (#1232)
Target a workflow with more recent binary artifacts.
2025-06-05 23:14:10 -07:00
Michael Bolin
2d5246050a fix: use aarch64-unknown-linux-musl instead of aarch64-unknown-linux-gnu (#1228)
Now that we have published a GitHub Release that contains arm64 musl
artifacts for Linux, update the following scripts to take advantage of
them:

- `dotslash-config.json` now uses musl artifacts for the `linux-aarch64`
target
- `install_native_deps.sh` for the TypeScript CLI now includes
`codex-linux-sandbox-aarch64-unknown-linux-musl` instead of
`codex-linux-sandbox-aarch64-unknown-linux-gnu` for sandboxing
- `codex-cli/bin/codex.js` now checks for `aarch64-unknown-linux-musl`
artifacts instead of `aarch64-unknown-linux-gnu` ones
2025-06-05 22:45:45 -07:00
Michael Bolin
77b017f67d fix: truncate auth.json file before rewriting it (#1231)
This was missed in https://github.com/openai/codex/pull/1212. Caught by
@rizwankce in
https://github.com/openai/codex/discussions/1174#discussioncomment-13377475.
2025-06-05 22:11:02 -07:00
Michael Bolin
c02d25fbad fix: include codex-linux-sandbox-aarch64-unknown-linux-musl in the set of release artifacts (#1230)
This was missed in https://github.com/openai/codex/pull/1225. Once we
create a new GitHub Release with this change, we can use the URL from
the workflow that triggered the release in
https://github.com/openai/codex/pull/1228.
2025-06-05 22:03:07 -07:00
Michael Bolin
9db53b33aa fix: support arm64 build for Linux (#1225)
Users were running into issues with glibc mismatches on arm64 linux. In
the past, we did not provide a musl build for arm64 Linux because we had
trouble getting the openssl dependency to build correctly. Though today
I just tried the same trick in `Cargo.toml` that we were doing for
`x86_64-unknown-linux-musl` (using `openssl-sys` with `features =
["vendored"]`), so I'm not sure what problem we had in the past the
builds "just worked" today!

Though one tweak that did have to be made is that the integration tests
for Seccomp/Landlock empirically require longer timeouts on arm64 linux,
or at least on the `ubuntu-24.04-arm` GitHub Runner. As such, we change
the timeouts for arm64 in `codex-rs/linux-sandbox/tests/landlock.rs`.

Though in solving this problem, I decided I needed a turnkey solution
for testing the Linux build(s) from my Mac laptop, so this PR introduces
`.devcontainer/Dockerfile` and `.devcontainer/devcontainer.json` to
facilitate this. Detailed instructions are in `.devcontainer/README.md`.

We will update `dotslash-config.json` and other release-related scripts
in a follow-up PR.
2025-06-05 20:29:46 -07:00
Michael Bolin
515b6331bd feat: add support for login with ChatGPT (#1212)
This does not implement the full Login with ChatGPT experience, but it
should unblock people.

**What works**

* The `codex` multitool now has a `login` subcommand, so you can run
`codex login`, which should write `CODEX_HOME/auth.json` if you complete
the flow successfully. The TUI will now read the `OPENAI_API_KEY` from
`auth.json`.
* The TUI should refresh the token if it has expired and the necessary
information is in `auth.json`.
* There is a `LoginScreen` in the TUI that tells you to run `codex
login` if both (1) your model provider expects to use `OPENAI_API_KEY`
as its env var, and (2) `OPENAI_API_KEY` is not set.

**What does not work**

* The `LoginScreen` does not support the login flow from within the TUI.
Instead, it tells you to quit, run `codex login`, and then run `codex`
again.
* `codex exec` does read from `auth.json` yet, nor does it direct the
user to go through the login flow if `OPENAI_API_KEY` is not be found.
* The `maybeRedeemCredits()` function from `get-api-key.tsx` has not
been ported from TypeScript to `login_with_chatgpt.py` yet:


a67a67f325/codex-cli/src/utils/get-api-key.tsx (L84-L89)

**Implementation**

Currently, the OAuth flow requires running a local webserver on
`127.0.0.1:1455`. It seemed wasteful to incur the additional binary cost
of a webserver dependency in the Rust CLI just to support login, so
instead we implement this logic in Python, as Python has a `http.server`
module as part of its standard library. Specifically, we bundle the
contents of a single Python file as a string in the Rust CLI and then
use it to spawn a subprocess as `python3 -c
{{SOURCE_FOR_PYTHON_SERVER}}`.

As such, the most significant files in this PR are:

```
codex-rs/login/src/login_with_chatgpt.py
codex-rs/login/src/lib.rs
```

Now that the CLI may load `OPENAI_API_KEY` from the environment _or_
`CODEX_HOME/auth.json`, we need a new abstraction for reading/writing
this variable, so we introduce:

```
codex-rs/core/src/openai_api_key.rs
```

Note that `std::env::set_var()` is [rightfully] `unsafe` in Rust 2024,
so we use a LazyLock<RwLock<Option<String>>> to store `OPENAI_API_KEY`
so it is read in a thread-safe manner.

Ultimately, it should be possible to go through the entire login flow
from the TUI. This PR introduces a placeholder `LoginScreen` UI for that
right now, though the new `codex login` subcommand introduced in this PR
should be a viable workaround until the UI is ready.

**Testing**

Because the login flow is currently implemented in a standalone Python
file, you can test it without building any Rust code as follows:

```
rm -rf /tmp/codex_home && mkdir /tmp/codex_home
CODEX_HOME=/tmp/codex_home python3 codex-rs/login/src/login_with_chatgpt.py
```

For reference:

* the original TypeScript implementation was introduced in
https://github.com/openai/codex/pull/963
* support for redeeming credits was later added in
https://github.com/openai/codex/pull/974
2025-06-04 08:44:17 -07:00
Reilly Wood
a67a67f325 codex-rs: make tool calls prettier (#1211)
This PR overhauls how active tool calls and completed tool calls are
displayed:

1. More use of colour to indicate success/failure and distinguish
between components like tool name+arguments
2. Previously, the entire `CallToolResult` was serialized to JSON and
pretty-printed. Now, we extract each individual `CallToolResultContent`
and print those
1. The previous solution was wasting space by unnecessarily showing
details of the `CallToolResult` struct to users, without formatting the
actual tool call results nicely
2. We're now able to show users more information from tool results in
less space, with nicer formatting when tools return JSON results

### Before:

<img width="1251" alt="Screenshot 2025-06-03 at 11 24 26"
src="https://github.com/user-attachments/assets/5a58f222-219c-4c53-ace7-d887194e30cf"
/>

### After:

<img width="1265" alt="image"
src="https://github.com/user-attachments/assets/99fe54d0-9ebe-406a-855b-7aa529b91274"
/>

## Future Work

1. Integrate image tool result handling better. We should be able to
display images even if they're not the first `CallToolResultContent`
2. Users should have some way to view the full version of truncated tool
results
3. It would be nice to add some left padding for tool results, make it
more clear that they are results. This is doable, just a little fiddly
due to the way `first_visible_line` scrolling works
4. There's almost certainly a better way to format JSON than "all on 1
line with spaces to make Ratatui wrapping work". But I think that works
OK for now.
2025-06-03 14:29:26 -07:00
Michael Bolin
c6fcec55fe fix: always send full instructions when using the Responses API (#1207)
This fixes a longstanding error in the Rust CLI where `codex.rs`
contained an errant `is_first_turn` check that would exclude the user
instructions for subsequent "turns" of a conversation when using the
responses API (i.e., when `previous_response_id` existed).

While here, renames `Prompt.instructions` to `Prompt.user_instructions`
since we now have quite a few levels of instructions floating around.
Also removed an unnecessary use of `clone()` in
`Prompt.get_full_instructions()`.
2025-06-03 09:40:19 -07:00
Michael Bolin
6fcc528a43 fix: provide tolerance for apply_patch tool (#993)
As explained in detail in the doc comment for `ParseMode::Lenient`, we
have observed that GPT-4.1 does not always generate a valid invocation
of `apply_patch`. Fortunately, the error is predictable, so we introduce
some new logic to the `codex-apply-patch` crate to recover from this
error.

Because we would like to avoid this becoming a de facto standard (as it
would be incompatible if `apply_patch` were provided as an actual
executable, unless we also introduced the lenient behavior in the
executable, as well), we require passing `ParseMode::Lenient` to
`parse_patch_text()` to make it clear that the caller is opting into
supporting this special case.

Note the analogous change to the TypeScript CLI was
https://github.com/openai/codex/pull/930. In addition to changing the
accepted input to `apply_patch`, it also introduced additional
instructions for the model, which we include in this PR.

Note that `apply-patch` does not depend on either `regex` or
`regex-lite`, so some of the checks are slightly more verbose to avoid
introducing this dependency.

That said, this PR does not leverage the existing
`extract_heredoc_body_from_apply_patch_command()`, which depends on
`tree-sitter` and `tree-sitter-bash`:


5a5aa89914/codex-rs/apply-patch/src/lib.rs (L191-L246)

though perhaps it should.
2025-06-03 09:06:38 -07:00
Michael Bolin
5a5aa89914 chore: replace regex with regex-lite, where appropriate (#1200)
As explained on https://crates.io/crates/regex-lite, `regex-lite` is a
lighter alternative to `regex` and seems to be sufficient for our
purposes.
2025-06-02 17:11:45 -07:00
Michael Bolin
0f3cc8f842 feat: make reasoning effort/summaries configurable (#1199)
Previous to this PR, we always set `reasoning` when making a request
using the Responses API:


d7245cbbc9/codex-rs/core/src/client.rs (L108-L111)

Though if you tried to use the Rust CLI with `--model gpt-4.1`, this
would fail with:

```shell
"Unsupported parameter: 'reasoning.effort' is not supported with this model."
```

We take a cue from the TypeScript CLI, which does a check on the model
name:


d7245cbbc9/codex-cli/src/utils/agent/agent-loop.ts (L786-L789)

This PR does a similar check, though also adds support for the following
config options:

```
model_reasoning_effort = "low" | "medium" | "high" | "none"
model_reasoning_summary = "auto" | "concise" | "detailed" | "none"
```

This way, if you have a model whose name happens to start with `"o"` (or
`"codex"`?), you can set these to `"none"` to explicitly disable
reasoning, if necessary. (That said, it seems unlikely anyone would use
the Responses API with non-OpenAI models, but we provide an escape
hatch, anyway.)

This PR also updates both the TUI and `codex exec` to show `reasoning
effort` and `reasoning summaries` in the header.
2025-06-02 16:01:34 -07:00
Michael Bolin
d7245cbbc9 fix: chat completions API now also passes tools along (#1167)
Prior to this PR, there were two big misses in `chat_completions.rs`:

1. The loop in `stream_chat_completions()` was only including items of
type `ResponseItem::Message` when building up the `"messages"` JSON for
the `POST` request to the `chat/completions` endpoint. This fixes things
by ensuring other variants (`FunctionCall`, `LocalShellCall`, and
`FunctionCallOutput`) are included, as well.
2. In `process_chat_sse()`, we were not recording tool calls and were
only emitting items of type
`ResponseEvent::OutputItemDone(ResponseItem::Message)` to the stream.
Now we introduce `FunctionCallState`, which is used to accumulate the
`delta`s of type `tool_calls`, so we can ultimately emit a
`ResponseItem::FunctionCall`, when appropriate.

While function calling now appears to work for chat completions with my
local testing, I believe that there are still edge cases that are not
covered and that this codepath would benefit from a battery of
integration tests. (As part of that further cleanup, we should also work
to support streaming responses in the UI.)

The other important part of this PR is some cleanup in
`core/src/codex.rs`. In particular, it was hard to reason about how
`run_task()` was building up the list of messages to include in a
request across the various cases:

- Responses API
- Chat Completions API
- Responses API used in concert with ZDR

I like to think things are a bit cleaner now where:

- `zdr_transcript` (if present) contains all messages in the history of
the conversation, which includes function call outputs that have not
been sent back to the model yet
- `pending_input` includes any messages the user has submitted while the
turn is in flight that need to be injected as part of the next `POST` to
the model
- `input_for_next_turn` includes the tool call outputs that have not
been sent back to the model yet
2025-06-02 13:47:51 -07:00
Michael Bolin
e40f86b446 chore: logging cleanup (#1196)
Update what we log to make `RUST_LOG=debug` a bit easier to work with.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1196).
* #1167
* __->__ #1196
2025-06-02 13:31:33 -07:00
Michael Bolin
7896b1089d chore: update the WORKFLOW_URL in install_native_deps.sh to the latest release (#1190) 2025-05-31 10:30:50 -07:00
Michael Bolin
1410ae95ca fix: set --config hide_agent_reasoning=true in the GitHub Action (#1185)
Whoops, I had this flipped in https://github.com/openai/codex/pull/1183.
2025-05-30 23:57:05 -07:00
Michael Bolin
fccf5f3221 fix: disable agent reasoning output by default in the GitHub Action (#1183) 2025-05-30 23:49:48 -07:00
Michael Bolin
1159eaf04f feat: show the version when starting Codex (#1182)
The TypeScript version of the CLI shows the version when it starts up,
which is helpful when users share screenshots (and nice to know, as a
user).
2025-05-30 23:24:36 -07:00
Michael Bolin
e81327e5f4 feat: add hide_agent_reasoning config option (#1181)
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
```
2025-05-30 23:14:56 -07:00
Michael Bolin
4f3d294762 feat: dim the timestamp in the exec output (#1180)
This required changing `ts_println!()` to take `$self:ident`, which is a
bit more verbose, but the usability improvement seems worth it.

Also eliminated an unnecessary `.to_string()` while here.
2025-05-30 16:27:37 -07:00
Michael Bolin
cf1d070538 feat: grab-bag of improvements to exec output (#1179)
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.
2025-05-30 16:22:10 -07:00
Michael Bolin
ae743d56b0 feat: for codex exec, if PROMPT is not specified, read from stdin if not a TTY (#1178)
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).
2025-05-30 14:41:55 -07:00
Michael Bolin
1bf82056b3 fix: introduce create_tools_json() and share it with chat_completions.rs (#1177)
The main motivator behind this PR is that `stream_chat_completions()`
was not adding the `"tools"` entry to the payload posted to the
`/chat/completions` endpoint. This (1) refactors the existing logic to
build up the `"tools"` JSON from `client.rs` into `openai_tools.rs`, and
(2) updates the use of responses API (`client.rs`) and chat completions
API (`chat_completions.rs`) to both use it.

Note this PR alone is not sufficient to get tool calling from chat
completions working: that is done in
https://github.com/openai/codex/pull/1167.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1177).
* #1167
* __->__ #1177
2025-05-30 14:07:03 -07:00
Michael Bolin
e207f20f64 fix: add extra debugging to GitHub Action (#1173)
https://github.com/openai/codex/actions/runs/15352839832/job/43205041563
appeared to fail around `postComment()`, but I don't see the output from
`fail()` in the logs. Adding a bit more info.
2025-05-30 11:16:30 -07:00
Michael Bolin
0f40ef5a10 fix: missed a step in #1171 for codex.yml (#1172)
Missed in my copy/paste.
2025-05-30 11:04:41 -07:00
Michael Bolin
8676185389 fix: update outdated repo setup in codex.yml (#1171)
We should do some work to share the setup logic across `codex.yml`,
`ci.yml`, and `rust-ci.yml`.
2025-05-30 10:58:57 -07:00
Michael Bolin
baa92f37e0 feat: initial import of experimental GitHub Action (#1170)
This is a first cut at a GitHub Action that lets you define prompt
templates in `.md` files under `.github/codex/labels` that will run
Codex with the associated prompt when the label is added to a GitHub
pull request.

For example, this PR includes these files:

```
.github/codex/labels/codex-attempt.md
.github/codex/labels/codex-code-review.md
.github/codex/labels/codex-investigate-issue.md
```

And the new `.github/workflows/codex.yml` workflow declares the
following triggers:

```yaml
on:
  issues:
    types: [opened, labeled]
  pull_request:
    branches: [main]
    types: [labeled]
```

as well as the following expression to gate the action:

```
jobs:
  codex:
    if: |
      (github.event_name == 'issues' && (
        (github.event.action == 'labeled' && (github.event.label.name == 'codex-attempt' || github.event.label.name == 'codex-investigate-issue'))
      )) ||
      (github.event_name == 'pull_request' && github.event.action == 'labeled' && github.event.label.name == 'codex-code-review')
```

Note the "actor" who added the label must have write access to the repo
for the action to take effect.

After adding a label, the action will "ack" the request by replacing the
original label (e.g., `codex-review`) with an `-in-progress` suffix
(e.g., `codex-review-in-progress`). When it is finished, it will swap
the `-in-progress` label with a `-completed` one (e.g.,
`codex-review-completed`).

Users of the action are responsible for providing an `OPENAI_API_KEY`
and making it available as a secret to the action.
2025-05-30 10:55:28 -07:00
Michael Bolin
a0239c3cd6 fix: enable set positional-arguments in justfile (#1169)
The way these definitions worked before, they did not handle quoted args
with spaces properly.

For example, if you had `/tmp/test-just/printlen.py` as:

```python
#!/usr/bin/env python3

import sys

print(len(sys.argv))
```

and your `justfile` was:

```
printlen *args:
    /tmp/test-just/printlen.py {{args}}
```

Then:

```shell
$ just printlen foo bar
3
$ just printlen 'foo bar'
3
```

which is not what we want: `'foo bar'` should be treated as one
argument.

The fix is to use
[positional-arguments](515e806b51/README.md (L1131)):

```
set positional-arguments

printlen *args:
    /tmp/test-just/printlen.py "$@"
```
2025-05-30 09:11:53 -07:00
Michael Bolin
bdfa95ed31 docs: split the config-related portion of codex-rs/README.md into its own config.md file (#1165)
Also updated the overview on `codex-rs/README.md` while here.
2025-05-29 16:59:35 -07:00
Fouad Matin
828e2062c2 fix(codex-rs): use codex-mini-latest as default (#1164) 2025-05-29 16:55:19 -07:00
Michael Bolin
92957c47fb fix: update justfile to facilitate running CLIs from source and formatting source code (#1163) 2025-05-29 15:35:14 -07:00
Michael Bolin
8c1902b562 chore: update GitHub workflow for native artifacts for npm release (#1162)
Among other things, this picks up this UI treatment fix:

https://github.com/openai/codex/pull/1161
2025-05-29 15:34:06 -07:00
Michael Bolin
a32d305ae6 fix: update UI treatment of slash command menu to match that of the TS CLI (#1161)
Uses the same colors as in the TypeScript CLI:


![image](https://github.com/user-attachments/assets/919cd472-ffb4-4654-a46a-d84f0cd9c097)

Now it is also readable on a light theme, e.g., in Ghostty:


![image](https://github.com/user-attachments/assets/468c37b0-ea63-4455-9b48-73dc2c95f0f6)
2025-05-29 14:57:55 -07:00
Michael Bolin
a768a6a41d fix: introduce ResponseInputItem::McpToolCallOutput variant (#1151)
The output of an MCP server tool call can be one of several types, but
to date, we treated all outputs as text by showing the serialized JSON
as the "tool output" in Codex:


25a9949c49/codex-rs/mcp-types/src/lib.rs (L96-L101)

This PR adds support for the `ImageContent` variant so we can now
display an image output from an MCP tool call.

In making this change, we introduce a new
`ResponseInputItem::McpToolCallOutput` variant so that we can work with
the `mcp_types::CallToolResult` directly when the function call is made
to an MCP server.

Though arguably the more significant change is the introduction of
`HistoryCell::CompletedMcpToolCallWithImageOutput`, which is a cell that
uses `ratatui_image` to render an image into the terminal. To support
this, we introduce `ImageRenderCache`, cache a
`ratatui_image::picker::Picker`, and `ensure_image_cache()` to cache the
appropriate scaled image data and dimensions based on the current
terminal size.

To test, I created a minimal `package.json`:

```json
{
  "name": "kitty-mcp",
  "version": "1.0.0",
  "type": "module",
  "description": "MCP that returns image of kitty",
  "main": "index.js",
  "dependencies": {
    "@modelcontextprotocol/sdk": "^1.12.0"
  }
}
```

with the following `index.js` to define the MCP server:

```js
#!/usr/bin/env node

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { readFile } from "node:fs/promises";
import { join } from "node:path";

const IMAGE_URI = "image://Ada.png";

const server = new McpServer({
  name: "Demo",
  version: "1.0.0",
});

server.tool(
  "get-cat-image",
  "If you need a cat image, this tool will provide one.",
  async () => ({
    content: [
      { type: "image", data: await getAdaPngBase64(), mimeType: "image/png" },
    ],
  })
);

server.resource("Ada the Cat", IMAGE_URI, async (uri) => {
  const base64Image = await getAdaPngBase64();
  return {
    contents: [
      {
        uri: uri.href,
        mimeType: "image/png",
        blob: base64Image,
      },
    ],
  };
});

async function getAdaPngBase64() {
  const __dirname = new URL(".", import.meta.url).pathname;
  // From 9705ce2c59/assets/Ada.png
  const filePath = join(__dirname, "Ada.png");
  const imageData = await readFile(filePath);
  const base64Image = imageData.toString("base64");
  return base64Image;
}

const transport = new StdioServerTransport();
await server.connect(transport);
```

With the local changes from this PR, I added the following to my
`config.toml`:

```toml
[mcp_servers.kitty]
command = "node"
args = ["/Users/mbolin/code/kitty-mcp/index.js"]
```

Running the TUI from source:

```
cargo run --bin codex -- --model o3 'I need a picture of a cat'
```

I get:

<img width="732" alt="image"
src="https://github.com/user-attachments/assets/bf80b721-9ca0-4d81-aec7-77d6899e2869"
/>

Now, that said, I have only tested in iTerm and there is definitely some
funny business with getting an accurate character-to-pixel ratio
(sometimes the `CompletedMcpToolCallWithImageOutput` thinks it needs 10
rows to render instead of 4), so there is still work to be done here.
2025-05-28 19:03:17 -07:00
Michael Bolin
25a9949c49 fix: ensure inputSchema for MCP tool always has "properties" field when talking to OpenAI (#1150)
As noted in the comment introduced in this PR, this is analogous to the
issue reported in
https://github.com/openai/openai-agents-python/issues/449. This seems to
work now.
2025-05-28 17:17:21 -07:00
Michael Bolin
392fdd7db6 fix: honor RUST_LOG in mcp-client CLI and default to DEBUG (#1149)
We had `debug!()` logging statements already, but they weren't being
printed because `tracing_subscriber` was not set up.
2025-05-28 17:10:06 -07:00
Michael Bolin
ae1a83f095 feat: introduce CellWidget trait (#1148)
The motivation behind this PR is to make it so a `HistoryCell` is more
like a `WidgetRef` that knows how to render itself into a `Rect` so that
it can be backed by something other than a `Vec<Line>`. Because a
`HistoryCell` is intended to appear in a scrollable list, we want to
ensure the stack of cells can be scrolled one `Line` at a time even if
the `HistoryCell` is not backed by a `Vec<Line>` itself.

To this end, we introduce the `CellWidget` trait whose key method is:

```
fn render_window(&self, first_visible_line: usize, area: Rect, buf: &mut Buffer);
```

The `first_visible_line` param is what differs from
`WidgetRef::render_ref()`, as a `CellWidget` needs to know the offset
into its "full view" at which it should start rendering.

The bookkeeping in `ConversationHistoryWidget` has been updated
accordingly to ensure each `CellWidget` in the history is rendered
appropriately.
2025-05-28 14:03:19 -07:00
Michael Bolin
d60f350cf8 feat: add support for -c/--config to override individual config items (#1137)
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.
2025-05-27 23:11:44 -07:00
Michael Bolin
eba0e32909 fix: update install_native_deps.sh to pick up the latest release (#1136) 2025-05-27 10:06:41 -07:00
Michael Bolin
29d154cb13 fix: use o4-mini as the default model (#1135)
Rollback of https://github.com/openai/codex/pull/972.
2025-05-27 09:12:55 -07:00
Michael Bolin
6b5b184f21 fix: TUI was not honoring --skip-git-repo-check correctly (#1105)
I discovered that if I ran `codex <PROMPT>` in a cwd that was not a Git
repo, Codex did not automatically run `<PROMPT>` after I accepted the
Git warning. It appears that we were not managing the `AppState`
transition correctly, so this fixes the bug and ensures the Codex
session does not start until the user accepts the Git warning.

In particular, we now create the `ChatWidget` lazily and store it in the
`AppState::Chat` variant.
2025-05-24 08:33:49 -07:00
Michael Bolin
4bf81373a7 fix: forgot to pass codex_linux_sandbox_exe through in cli/src/debug_sandbox.rs (#1095)
I accidentally missed this in https://github.com/openai/codex/pull/1086.
2025-05-23 11:53:13 -07:00
Michael Bolin
89ef4efdcf fix: overhaul how we spawn commands under seccomp/landlock on Linux (#1086)
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.
2025-05-23 11:37:07 -07:00
Michael Bolin
d1de7bb383 feat: add codex_linux_sandbox_exe: Option<PathBuf> field to Config (#1089)
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.
2025-05-22 21:52:28 -07:00
Michael Bolin
63deb7c369 fix: for the @native release of the Node module, use the Rust version by default (#1084)
Added logic so that when we run `./scripts/stage_release.sh --native`
(for the `@native` version of the Node module), we drop a `use-native`
file next to `codex.js`. If present, `codex.js` will now run the Rust
CLI.

Ran `./scripts/stage_release.sh --native` and verified that when the
running `codex.js` in the staged folder:

```
$ /var/folders/wm/f209bc1n2bd_r0jncn9s6j_00000gp/T/tmp.efvEvBlSN6/bin/codex.js --version
codex-cli 0.0.2505220956
```

it ran the expected Rust version of the CLI, as desired.

While here, I also updated the Rust version to one that I cut today,
which includes the new shell environment policy config option:
https://github.com/openai/codex/pull/1061. Note this may "break" some
users if the processes spawned by Codex need extra environment
variables. (We are still working to determine what the right defaults
should be for this option.)
2025-05-22 13:42:55 -07:00
Michael Bolin
cb379d7797 feat: introduce support for shell_environment_policy in config.toml (#1061)
To date, when handling `shell` and `local_shell` tool calls, we were
spawning new processes using the environment inherited from the Codex
process itself. This means that the sensitive `OPENAI_API_KEY` that
Codex needs to talk to OpenAI models was made available to everything
run by `shell` and `local_shell`. While there are cases where that might
be useful, it does not seem like a good default.

This PR introduces a complex `shell_environment_policy` config option to
control the `env` used with these tool calls. It is inevitably a bit
complex so that it is possible to override individual components of the
policy so without having to restate the entire thing.

Details are in the updated `README.md` in this PR, but here is the
relevant bit that explains the individual fields of
`shell_environment_policy`:

| Field | Type | Default | Description |
| ------------------------- | -------------------------- | ------- |
-----------------------------------------------------------------------------------------------------------------------------------------------
|
| `inherit` | string | `core` | Starting template for the
environment:<br>`core` (`HOME`, `PATH`, `USER`, …), `all` (clone full
parent env), or `none` (start empty). |
| `ignore_default_excludes` | boolean | `false` | When `false`, Codex
removes any var whose **name** contains `KEY`, `SECRET`, or `TOKEN`
(case-insensitive) before other rules run. |
| `exclude` | array&lt;string&gt; | `[]` | Case-insensitive glob
patterns to drop after the default filter.<br>Examples: `"AWS_*"`,
`"AZURE_*"`. |
| `set` | table&lt;string,string&gt; | `{}` | Explicit key/value
overrides or additions – always win over inherited values. |
| `include_only` | array&lt;string&gt; | `[]` | If non-empty, a
whitelist of patterns; only variables that match _one_ pattern survive
the final step. (Generally used with `inherit = "all"`.) |


In particular, note that the default is `inherit = "core"`, so:

* if you have extra env variables that you want to inherit from the
parent process, use `inherit = "all"` and then specify `include_only`
* if you have extra env variables where you want to hardcode the values,
the default `inherit = "core"` will work fine, but then you need to
specify `set`

This configuration is not battle-tested, so we will probably still have
to play with it a bit. `core/src/exec_env.rs` has the critical business
logic as well as unit tests.

Though if nothing else, previous to this change:

```
$ cargo run --bin codex -- debug seatbelt -- printenv OPENAI_API_KEY
# ...prints OPENAI_API_KEY...
```

But after this change it does not print anything (as desired).

One final thing to call out about this PR is that the
`configure_command!` macro we use in `core/src/exec.rs` has to do some
complex logic with respect to how it builds up the `env` for the process
being spawned under Landlock/seccomp. Specifically, doing
`cmd.env_clear()` followed by `cmd.envs(&$env_map)` (which is arguably
the most intuitive way to do it) caused the Landlock unit tests to fail
because the processes spawned by the unit tests started failing in
unexpected ways! If we forgo `env_clear()` in favor of updating env vars
one at a time, the tests still pass. The comment in the code talks about
this a bit, and while I would like to investigate this more, I need to
move on for the moment, but I do plan to come back to it to fully
understand what is going on. For example, this suggests that we might
not be able to spawn a C program that calls `env_clear()`, which would
be...weird. We may still have to fiddle with our Landlock config if that
is the case.
2025-05-22 09:51:19 -07:00
Michael Bolin
ef7208359f feat: show Config overview at start of exec (#1073)
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.
2025-05-21 22:53:02 -07:00
Michael Bolin
5746561428 chore: move types out of config.rs into config_types.rs (#1054)
`config.rs` is already quite long without these definitions. Since they
have no real dependencies of their own, let's move them to their own
file so `config.rs` can focus on the business logic of loading a config.
2025-05-20 11:55:25 -07:00
Michael Bolin
d766e845b3 feat: experimental --output-last-message flag to exec subcommand (#1037)
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.
2025-05-19 16:08:18 -07:00
Michael Bolin
a4bfdf6779 chore: produce .tar.gz versions of artifacts in addition to .zst (#1036)
For sparse containers/environments that do not have `zstd`, provide
`.tar.gz` as alternative archive format.
2025-05-19 15:17:45 -07:00
Fouad Matin
44022db8d0 bump(version): 0.1.2505172129 (#1008)
## `0.1.2505172129`

### 🪲 Bug Fixes

- Add node version check (#1007)
- Persist token after refresh (#1006)
2025-05-17 21:35:54 -07:00
Fouad Matin
a86270f581 fix: add node version check (#1007) 2025-05-17 21:27:41 -07:00
Fouad Matin
835eb77a7d fix: persist token after refresh (#1006)
After a token refresh/exchange, persist the new refresh and id token
2025-05-17 21:27:02 -07:00
Fouad Matin
dbc0ad348e bump(version): 0.1.2505171619 (#1001)
## `0.1.2505171619`

- `codex --login` + `codex --free` (#998)
2025-05-17 16:25:21 -07:00
Fouad Matin
9b4c2984d4 add: codex --login + codex --free (#998)
## Summary
- add `--login` and `--free` flags to cli help
- handle `--login` and `--free` logic in cli
- factor out redeem flow into `maybeRedeemCredits`
- call new helper from login callback
2025-05-17 16:13:12 -07:00
Michael Bolin
f3bde21759 chore: update install_native_deps.sh to use rust-v0.0.2505171051 (#995)
Use a more recent built of the Rust binaries to include with the Node
module.
2025-05-17 11:25:24 -07:00
Michael Bolin
1c6a3f1097 fix: artifacts from previous frames were bleeding through in TUI (#989)
Prior to this PR, I would frequently see glyphs from previous frames
"bleed" through like this:


![image](https://github.com/user-attachments/assets/8784b3d7-f691-4df6-8666-34e2f134ee85)

I think this was due to two issues (now addressed in this PR):

* We were not making use of `ratatui::widgets::Clear` to clear out the
buffer before drawing into it.
* To calculate the `width` used with `wrapped_line_count_for_cell()`, we
were not accounting for the scrollbar.
* Now we calculate `effective_width` using
`inner.width.saturating_sub(1)` where the `1` is for the scrollbar.
* We compute `text_area` using `effective_with` and pass the `text_area`
to `paragraph.render()`.
* We eliminate the conditional `needs_scrollbar` check and always call
`render(Scrollbar)`

I suspect this bug was introduced in
https://github.com/openai/codex/pull/937, though I did not try to
verify: I'm just happy that it appears to be fixed!
2025-05-17 10:51:11 -07:00
Michael Bolin
f8b6b1db81 fix: ensure the first user message always displays after the session info (#988)
Previously, if the first user message was sent with the command
invocation, e.g.:

```
$ cargo run --bin codex 'hello'
```

Then the user message was added as the first entry in the history and
then `is_first_event` would be `false` here:


031df77dfb/codex-rs/tui/src/conversation_history_widget.rs (L178-L179)

which would prevent the "welcome" message with things like the the model
version from displaying.

The fix in this PR is twofold:

* Reorganize the logic so the `ChatWidget` constructor stores
`initial_user_message` rather than sending it right away. Now inside
`handle_codex_event()`, it waits for the `SessionConfigured` event and
sends the `initial_user_message`, if it exists.
* In `conversation_history_widget.rs`, `add_session_info()` checks to
see whether a `WelcomeMessage` exists in the history when determining
the value of `has_welcome_message`. By construction, we expect that
`WelcomeMessage` is always the first message (in which case the existing
`let is_first_event = self.entries.is_empty();` logic would be sound),
but we decide to be extra defensive in case an `EventMsg::Error` is
processed before `EventMsg::SessionConfigured`.
2025-05-17 09:00:23 -07:00
Christoph K
031df77dfb Remove unnecessary console log from test (#970)
When running `npm test` on `codex-cli`, the test
`agent-cancel-prev-response.test.ts` logs a significant body of text to
console for no obvious reason.

This is not helpful, as it makes test logs messy and far longer.

This change deletes the `console.log(...)` that produces the behavior.
2025-05-16 19:48:11 -07:00
Michael Bolin
f9143d0361 fix: do not let Tab keypress flow through to composer when used to toggle focus (#977)
One line fix from Codex!
2025-05-16 19:27:49 -07:00
Fouad Matin
2880925a44 bump(version): 0.1.2505161800 (#978)
## `0.1.2505161800`

- Sign in with chatgpt credits (#974)
- Add support for OpenAI tool type, local_shell (#961)
2025-05-16 18:18:15 -07:00
Fouad Matin
3e19e8fd59 add: sign in with chatgpt credits (#974) 2025-05-16 17:55:08 -07:00
Trevor Creech
c7312c9d52 Fix CLA link in workflow (#964)
## Summary
- fix the CLA link posted by the bot
- docs suggest using an absolute URL:
https://github.com/marketplace/actions/cla-assistant-lite
2025-05-16 17:11:57 -07:00
Michael Bolin
1dc14cefa1 fix: make codex-mini-latest the default model in the Rust TUI (#972)
It's time to make `codex-mini-latest` the new default, as this should be
an "evergreen" model pointer.

* Equivalent change in TypeScript
https://github.com/openai/codex/pull/951
* See some notes about using `codex-mini-latest` with MCP in
https://github.com/openai/codex/pull/961
2025-05-16 17:08:18 -07:00
Michael Bolin
7ca84087e6 feat: make it possible to toggle mouse mode in the Rust TUI (#971)
I did a bit of research to understand why I could not use my mouse to
drag to select text to copy to the clipboard in iTerm.

Apparently https://github.com/openai/codex/pull/641 to enable mousewheel
scrolling broke this functionality. It seems that, unless we put in a
bit of effort, we can have drag-to-select or scrolling, but not both.
Though if you know the trick to hold down `Option` will dragging with
the mouse in iTerm, you can probably get by with this. (I did not know
about this option prior to researching this issue.)

Nevertheless, users may still prefer to disable mouse capture
altogether, so this PR introduces:

* the ability to set `tui.disable_mouse_capture = true` in `config.toml`
to disable mouse capture
* a new command, `/toggle-mouse-mode` to toggle mouse capture
2025-05-16 16:16:50 -07:00
Michael Bolin
67ac8ef605 fix: use text other than 'TODO' as test example (#969)
I casually `rg TODO` to look for TODOs, so the use of TODO in a sample
string in test output was throwing things off.
2025-05-16 14:51:03 -07:00
Michael Bolin
f48dd99f22 feat: add support for OpenAI tool type, local_shell (#961)
The new `codex-mini-latest` model expects a new tool with `{"type":
"local_shell"}`. Its contract is similar to the existing `function` tool
with `"name": "shell"`, so this takes the `local_shell` tool call into
`ExecParams` and sends it through the existing
`handle_container_exec_with_params()` code path.

This also adds the following logic when adding the default set of tools
to a request:

```rust
let default_tools = if self.model.starts_with("codex") {
    &DEFAULT_CODEX_MODEL_TOOLS
} else {
    &DEFAULT_TOOLS
};
```

That is, if the model name starts with `"codex"`, we add `{"type":
"local_shell"}` to the list of tools; otherwise, we add the
aforementioned `shell` tool.

To test this, I ran the TUI with `-m codex-mini-latest` and verified
that it used the `local_shell` tool. Though I also had some entries in
`[mcp_servers]` in my personal `config.toml`. The `codex-mini-latest`
model seemed eager to try the tools from the MCP servers first, so I
have personally commented them out for now, so keep an eye out if you're
testing `codex-mini-latest`!

Perhaps we should include more details with `{"type": "local_shell"}` or
update the following:


fd0b1b0208/codex-rs/core/prompt.md

For reference, the corresponding change in the TypeScript CLI is
https://github.com/openai/codex/pull/951.
2025-05-16 14:38:08 -07:00
Michael Bolin
dfd54e1433 chore: refactor handle_function_call() into smaller functions (#965)
Overall, `codex.rs` is still far too large, but at least there's less
indenting now that things have been moved into smaller functions.

This will also make it easier to introduce the `local_shell` tool in
https://github.com/openai/codex/pull/961.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/965).
* #961
* __->__ #965
2025-05-16 14:17:10 -07:00
Michael Bolin
9739820366 fix: remove file named ">" in the codex-cli folder (#968)
This file appears to have been accidentally added in
https://github.com/openai/codex/pull/912. Its presence makes the repo
impossible to clone on Windows.
2025-05-16 14:08:23 -07:00
Fouad Matin
fd0b1b0208 bump(version): 0.1.2505161243 (#967)
## `0.1.2505161243`

- Sign in with chatgpt (#963)
- Session history viewer (#912)
- Apply patch issue when using different cwd (#942)
- Diff command for filenames with special characters (#954)
2025-05-16 12:46:52 -07:00
Fouad Matin
c6e08ad8c1 add: sign in with chatgpt (#963)
Sign in with ChatGPT to get an API key (flow to grant API credits for Plus/Pro coming later today!)
2025-05-16 12:28:54 -07:00
Fouad Matin
cabf83f2ed add: session history viewer (#912)
- A new “/sessions” command is available for browsing previous sessions,
as shown in the updated slash command list

- The CLI now documents and parses a new “--history” flag to browse past
sessions from the command line

- A dedicated `SessionsOverlay` component loads session metadata and
allows toggling between viewing and resuming sessions

- When the sessions overlay is opened during a chat, selecting a session
can either show the saved rollout or resume it
2025-05-16 12:28:22 -07:00
Michael Bolin
1e39189393 feat: add support for file_opener option in Rust, similiar to #911 (#957)
This ports the enhancement introduced in
https://github.com/openai/codex/pull/911 (and the fixes in
https://github.com/openai/codex/pull/919) for the TypeScript CLI to the
Rust one.
2025-05-16 11:33:08 -07:00
Michael Bolin
3d9f4fcd8a fix: introduce ExtractHeredocError that implements PartialEq (#958) 2025-05-16 09:42:27 -07:00
Sebastian Lund
84e01f4b62 fix: apply patch issue when using different cwd (#942)
If you run a codex instance outside of the current working directory
from where you launched the codex binary it won't be able to apply
patches correctly, even if the sandbox policy allows it. This manifests
weird behaviours, such as

* Reading the same filename in the binary working directory, and
overwriting it in the session working directory. e.g. if you have a
`readme` in both folders it will overwrite the readme in the session
working directory with the readme in the binary working directory
*applied with the suggested patch*.
* The LLM ends up in weird loops trying to verify and debug why the
apply_patch won't work, and it can result in it applying patches by
manually writing python or javascript if it figures out that either is
supported by the system instead.

I added a test-case to ensure that the patch contents are based on the
cwd.

## Issue: mixing relative & absolute paths in apply_patch

1. The apply_patch tool use relative paths based on the session working
directory.
2. `unified_diff_from_chunks` eventually ends up [reading the source
file](https://github.com/reflectionai/codex/blob/main/codex-rs/apply-patch/src/lib.rs#L410)
to figure out what the diff is, by using the relative path.
3. The changes are targeted using an absolute path derived from the
current working directory.

The end-result in case session working directory differs from the binary
working directory: we get the diff for a file relative to the binary
working directory, and apply it on a file in the session working
directory.
2025-05-16 09:12:16 -07:00
hanson-openai
7edfbae062 fix: diff command for filenames with special characters (#954)
## Summary
- fix quoting issues in `/diff` to correctly handle files with special
characters
- add regression test for `getGitDiff` when filenames contain `$`
- relax timeout in raw-exec-process-group test

Fixes https://github.com/openai/codex/issues/943

## Testing
- `pnpm test`
2025-05-16 09:10:44 -07:00
Fouad Matin
316289d01d bump(version): 0.1.2505160811 codex-mini-latest (#953)
## `0.1.2505160811`

- `codex-mini-latest` (#951)
2025-05-16 08:18:20 -07:00
Michael Bolin
30cbfdfa87 chore: update exec crate to use std::time instead of chrono (#952)
When I originally wrote `elapsed.rs`, I realized we were using both
`std::time` and `chrono` with no real benefit of having both. We should
try to keep the `exec` subcommand trim (as it also buildable as a
standalone executable), so this helps tighten things up.
2025-05-16 08:14:50 -07:00
Fouad Matin
070499f534 add: codex-mini-latest (#951)
💽

---------

Co-authored-by: Trevor Creech <tcreech@openai.com>
2025-05-16 08:04:00 -07:00
Michael Bolin
ce2ecbe72f feat: record messages from user in ~/.codex/history.jsonl (#939)
This is a large change to support a "history" feature like you would
expect in a shell like Bash.

History events are recorded in `$CODEX_HOME/history.jsonl`. Because it
is a JSONL file, it is straightforward to append new entries (as opposed
to the TypeScript file that uses `$CODEX_HOME/history.json`, so to be
valid JSON, each new entry entails rewriting the entire file). Because
it is possible for there to be multiple instances of Codex CLI writing
to `history.jsonl` at once, we use advisory file locking when working
with `history.jsonl` in `codex-rs/core/src/message_history.rs`.

Because we believe history is a sufficiently useful feature, we enable
it by default. Though to provide some safety, we set the file
permissions of `history.jsonl` to be `o600` so that other users on the
system cannot read the user's history. We do not yet support a default
list of `SENSITIVE_PATTERNS` as the TypeScript CLI does:


3fdf9df133/codex-cli/src/utils/storage/command-history.ts (L10-L17)

We are going to take a more conservative approach to this list in the
Rust CLI. For example, while `/\b[A-Za-z0-9-_]{20,}\b/` might exclude
sensitive information like API tokens, it would also exclude valuable
information such as references to Git commits.

As noted in the updated documentation, users can opt-out of history by
adding the following to `config.toml`:

```toml
[history]
persistence = "none" 
```

Because `history.jsonl` could, in theory, be quite large, we take a[n
arguably overly pedantic] approach in reading history entries into
memory. Specifically, we start by telling the client the current number
of entries in the history file (`history_entry_count`) as well as the
inode (`history_log_id`) of `history.jsonl` (see the new fields on
`SessionConfiguredEvent`).

The client is responsible for keeping new entries in memory to create a
"local history," but if the user hits up enough times to go "past" the
end of local history, then the client should use the new
`GetHistoryEntryRequest` in the protocol to fetch older entries.
Specifically, it should pass the `history_log_id` it was given
originally and work backwards from `history_entry_count`. (It should
really fetch history in batches rather than one-at-a-time, but that is
something we can improve upon in subsequent PRs.)

The motivation behind this crazy scheme is that it is designed to defend
against:

* The `history.jsonl` being truncated during the session such that the
index into the history is no longer consistent with what had been read
up to that point. We do not yet have logic to enforce a `max_bytes` for
`history.jsonl`, but once we do, we will aspire to implement it in a way
that should result in a new inode for the file on most systems.
* New items from concurrent Codex CLI sessions amending to the history.
Because, in absence of truncation, `history.jsonl` is an append-only
log, so long as the client reads backwards from `history_entry_count`,
it should always get a consistent view of history. (That said, it will
not be able to read _new_ commands from concurrent sessions, but perhaps
we will introduce a `/` command to reload latest history or something
down the road.)

Admittedly, my testing of this feature thus far has been fairly light. I
expect we will find bugs and introduce enhancements/fixes going forward.
2025-05-15 16:26:23 -07:00
Michael Bolin
3fdf9df133 chore: introduce AppEventSender to help fix clippy warnings and update to Rust 1.87 (#948)
Moving to Rust 1.87 introduced a clippy warning that
`SendError<AppEvent>` was too large.

In practice, the only thing we ever did when we got this error was log
it (if the mspc channel is closed, then the app is likely shutting down
or something, so there's not much to do...), so this finally motivated
me to introduce `AppEventSender`, which wraps
`std::sync::mpsc::Sender<AppEvent>` with a `send()` method that invokes
`send()` on the underlying `Sender` and logs an `Err` if it gets one.

This greatly simplifies the code, as many functions that previously
returned `Result<(), SendError<AppEvent>>` now return `()`, so we don't
have to propagate an `Err` all over the place that we don't really
handle, anyway.

This also makes it so we can upgrade to Rust 1.87 in CI.
2025-05-15 14:50:30 -07:00
Michael Bolin
ec5e82b77c chore: pin Rust version to 1.86 and use io::Error::other to prepare for 1.87 (#947)
Previously, our GitHub actions specified the Rust toolchain as
`dtolnay/rust-toolchain@stable`, which meant the version could change
out from under us. In this case, the move from 1.86 to 1.87 introduced
new clippy warnings, causing build failures.

Because it will take a little time to fix all the new clippy warnings,
this PR pins things to 1.86 for now to unbreak the build.

It also replaces `io::Error::new(io::ErrorKind::Other)` with
`io::Error::other()` in preparation for 1.87.
2025-05-15 14:07:16 -07:00
Michael Bolin
5fc9fc3e3e chore: expose codex_home via Config (#941) 2025-05-15 00:30:13 -07:00
Michael Bolin
0b9ef93da5 fix: properly wrap lines in the Rust TUI (#937)
As discussed on
699ec5a87f (commitcomment-156776835),
to properly support scrolling long content in Ratatui for a sequence of
cells, we need to:

* take the `Vec<Line>` for each cell
* using the wrapping logic we want to use at render time, compute the
_effective line count_ using `Paragraph::line_count()` (see
`wrapped_line_count_for_cell()` in this PR)
* sum up the effective line count to compute the height of the area
being scrolled
* given a `scroll_position: usize`, index into the list of "effective
lines" and accumulate the appropriate `Vec<Line>` for the cells that
should be displayed
* take that `Vec<Line>` to create a `Paragraph` and use the same
line-wrapping policy that was used in `wrapped_line_count_for_cell()`
* display the resulting `Paragraph` and use the accounting to display a
scrollbar with the appropriate thumb size and offset without having to
render the `Vec<Line>` for the full history

With this change, lines wrap as I expect and everything appears to
redraw correctly as I resize my terminal!
2025-05-14 16:51:41 -07:00
Michael Bolin
34aa1991f1 chore: handle all cases for EventMsg (#936)
For now, this removes the `#[non_exhaustive]` directive on `EventMsg` so
that we are forced to handle all `EventMsg` by default. (We may revisit
this if/when we publish `core/` as a `lib` crate.) For now, it is
helpful to have this as a forcing function because we have effectively
two UIs (`tui` and `exec`) and usually when we add a new variant to
`EventMsg`, we want to be sure that we update both.
2025-05-14 13:36:43 -07:00
Michael Bolin
497c5396c0 feat: add mcp subcommand to CLI to run Codex as an MCP server (#934)
Previously, running Codex as an MCP server required a standalone binary
in our Cargo workspace, but this PR makes it available as a subcommand
(`mcp`) of the main CLI.

Ran this with:

```
RUST_LOG=debug npx @modelcontextprotocol/inspector cargo run --bin codex -- mcp
```

and verified it worked as expected in the inspector at
`http://127.0.0.1:6274/`.
2025-05-14 13:15:41 -07:00
Michael Bolin
a12e4b0b31 feat: add support for commands in the Rust TUI (#935)
Introduces support for slash commands like in the TypeScript CLI. We do
not support the full set of commands yet, but the core abstraction is
there now.

In particular, we have a `SlashCommand` enum and due to thoughtful use
of the [strum](https://crates.io/crates/strum) crate, it requires
minimal boilerplate to add a new command to the list.

The key new piece of UI is `CommandPopup`, though the keyboard events
are still handled by `ChatComposer`. The behavior is roughly as follows:

* if the first character in the composer is `/`, the command popup is
displayed (if you really want to send a message to Codex that starts
with a `/`, simply put a space before the `/`)
* while the popup is displayed, up/down can be used to change the
selection of the popup
* if there is a selection, hitting tab completes the command, but does
not send it
* if there is a selection, hitting enter sends the command
* if the prefix of the composer matches a command, the command will be
visible in the popup so the user can see the description (commands could
take arguments, so additional text may appear after the command name
itself)


https://github.com/user-attachments/assets/39c3e6ee-eeb7-4ef7-a911-466d8184975f

Incidentally, Codex wrote almost all the code for this PR!
2025-05-14 12:55:49 -07:00
Michael Bolin
0402aef126 chore: move each view used in BottomPane into its own file (#928)
`BottomPane` was getting a bit unwieldy because it maintained a
`PaneState` enum with three variants and many of its methods had `match`
statements to handle each variant. To replace the enum, this PR:

* Introduces a `trait BottomPaneView` that has two implementations:
`StatusIndicatorView` and `ApprovalModalView`.
* Migrates `PaneState::TextInput` into its own struct, `ChatComposer`,
that does **not** implement `BottomPaneView`.
* Updates `BottomPane` so it has `composer: ChatComposer` and
`active_view: Option<Box<dyn BottomPaneView<'a> + 'a>>`. The idea is
that `active_view` takes priority and is displayed when it is `Some`;
otherwise, `ChatComposer` is displayed.
* While methods of `BottomPane` often have to check whether
`active_view` is present to decide which component to delegate to, the
code is more straightforward than before and introducing new
implementations of `BottomPaneView` should be less painful.

Because we want to retain the `TextArea` owned by `ChatComposer` even
when another view is displayed, to keep the ownership logic simple, it
seemed best to keep `ChatComposer` distinct from `BottomPaneView`.
2025-05-14 10:13:29 -07:00
Michael Bolin
399e819c9b fix: increase timeout for test_dev_null_write (#933)
After updating this test in https://github.com/openai/codex/pull/923, I
have been getting some timeouts with this test in CI, so increasing the
timeout to match that of `test_writable_root`:


327cf41f0f/codex-rs/core/src/landlock.rs (L211-L213)
2025-05-14 10:06:14 -07:00
Yaroslav Halchenko
327cf41f0f Add codespell support (config, workflow to detect/not fix) and make it fix some typos (#903)
More about codespell: https://github.com/codespell-project/codespell .

I personally introduced it to dozens if not hundreds of projects already
and so far only positive feedback.

CI workflow has 'permissions' set only to 'read' so also should be safe.

Let me know if just want to take typo fixes in and get rid of the CI

---------

Signed-off-by: Yaroslav O. Halchenko <debian@onerussian.com>
2025-05-14 09:39:49 -07:00
Fouad Matin
9e7cd2b25a bump(version): 0.1.2505140839 (#932)
## `0.1.2505140839`

### 🪲 Bug Fixes

- Gpt-4.1 apply_patch handling (#930)
- Add support for fileOpener in config.json (#911)
- Patch in #366 and #367 for marked-terminal (#916)
- Remember to set lastIndex = 0 on shared RegExp (#918)
- Always load version from package.json at runtime (#909)
- Tweak the label for citations for better rendering (#919)
- Tighten up some logic around session timestamps and ids (#922)
- Change EventMsg enum so every variant takes a single struct (#925)
- Reasoning default to medium, show workdir when supplied (#931)
- Test_dev_null_write() was not using echo as intended (#923)
2025-05-14 08:44:52 -07:00
Fouad Matin
73259351ff fix: reasoning default to medium, show workdir when supplied (#931) 2025-05-14 08:38:41 -07:00
Fouad Matin
77347d268d fix: gpt-4.1 apply_patch handling (#930) 2025-05-14 08:34:09 -07:00
Fouad Matin
678f0dbfec add: dynamic instructions (#927) 2025-05-14 01:27:46 -07:00
Michael Bolin
1bf00a3a95 feat: Ctrl+J for newline in Rust TUI, default to one line of height (#926)
While the `TextArea` used in the Rust TUI is "multiline," it is not like
an HTML `<textarea>` in that it does not wrap, so there was not much
benefit to setting `MIN_TEXTAREA_ROWS` to `3`, so this PR changes it to
`1`. Though there are now three ways to "increase" the height due to
actual linebreaks:

* paste in multiline content (this worked before this PR)
* pressing `Ctrl+J` will insert a newline
* if you have your terminal emulator set such that it is possible to
press something that `crossterm` interprets as "Enter plus some
modifier," then now that will also work

Now things look a bit more compact on startup:

<img width="745" alt="image"
src="https://github.com/user-attachments/assets/86e2857f-f31c-46f5-a80b-1ab2120b266e"
/>
2025-05-13 21:42:14 -07:00
Michael Bolin
5bf9445351 fix: test_dev_null_write() was not using echo as intended (#923)
I believe this test meant to verify that echoing content to `/dev/null`
succeeded, but instead, I believe it was testing the equivalent to `echo
'blah > /dev/null'`.
2025-05-13 21:40:26 -07:00
Michael Bolin
a5f3a34827 fix: change EventMsg enum so every variant takes a single struct (#925)
https://github.com/openai/codex/pull/922 did this for the
`SessionConfigured` enum variant, and I think it is generally helpful to
be able to work with the values as each enum variant as their own type,
so this converts the remaining variants and updates all of the
callsites.

Added a simple unit test to verify that the JSON-serialized version of
`Event` does not have any unexpected nesting.
2025-05-13 20:44:42 -07:00
Michael Bolin
e6c206d19d fix: tighten up some logic around session timestamps and ids (#922)
* update `SessionConfigured` event to include the UUID for the session
* show the UUID in the Rust TUI
* use local timestamps in log files instead of UTC
* include timestamps in log file names for easier discovery
2025-05-13 19:22:16 -07:00
Michael Bolin
3c03c25e56 feat: introduce --profile for Rust CLI (#921)
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`.
2025-05-13 16:52:52 -07:00
Adeeb
ae809f3721 restructure flake for codex-rs (#888)
Right now since the repo is having two different implementations of
codex, flake was updated to work with both typescript implementation and
rust implementation
2025-05-13 13:08:42 -07:00
Michael Bolin
a786c1d188 feat: auto-approve nl and support piping to sed (#920)
Auto-approved:

```
["nl", "-ba", "README.md"]
["sed", "-n", "1,200p", "filename.txt"]
["bash", "-lc", "sed -n '1,200p' filename.txt"]
["bash", "-lc", "nl -ba README.md | sed -n '1,200p'"]
```

Not auto approved:

```
["sed", "-n", "'1,200p'", "filename.txt"]
["sed", "-n", "1,200p", "file1.txt", "file2.txt"]
```
2025-05-13 13:06:35 -07:00
Michael Bolin
0ac7e8d55b fix: tweak the label for citations for better rendering (#919)
Adds a space so that sequential citations have some more breathing room.

As I had to update the tests for this change, I also introduced a
`toDiffableString()` helper to make the test easier to update as we make
formatting changes to the output.
2025-05-13 12:46:21 -07:00
Michael Bolin
1ff3e14d5a fix: patch in #366 and #367 for marked-terminal (#916)
This PR uses [`pnpm
patch`](https://www.petermekhaeil.com/til/pnpm-patch/) to pull in the
following proposed fixes for `marked-terminal`:

* https://github.com/mikaelbr/marked-terminal/pull/366
* https://github.com/mikaelbr/marked-terminal/pull/367

This adds a substantial test to `codex-cli/tests/markdown.test.tsx` to
verify the new behavior.

Note that one of the tests shows two citations being split across a line
even though the rendered version would fit comfortably on one line.
Changing this likely requires a subtle fix to `marked-terminal` to
account for "rendered length" when determining line breaks.
2025-05-13 12:29:17 -07:00
Michael Bolin
dd354e2134 fix: remember to set lastIndex = 0 on shared RegExp (#918)
I had not observed an issue in the wild because of this yet, but it
feels like it was only a matter of time...
2025-05-13 12:01:06 -07:00
Michael Bolin
557f608f25 fix: add support for fileOpener in config.json (#911)
This PR introduces the following type:

```typescript
export type FileOpenerScheme = "vscode" | "cursor" | "windsurf";
```

and uses it as the new type for a `fileOpener` option in `config.json`.
If set, this will be used to linkify file annotations in the output
using the URI-based file opener supported in VS Code-based IDEs.

Currently, this does not pass:

Updated `codex-cli/tests/markdown.test.tsx` to verify the new behavior.
Note it required mocking `supports-hyperlinks` and temporarily modifying
`chalk.level` to yield the desired output.
2025-05-13 09:45:46 -07:00
Michael Bolin
05bb5d7d46 fix: always load version from package.json at runtime (#909)
Note the high-level motivation behind this change is to avoid the need
to make temporary changes in the source tree in order to cut a release
build since that runs the risk of leaving things in an inconsistent
state in the event of a failure. The existing code:

```
import pkg from "../../package.json" assert { type: "json" };
```

did not work as intended because, as written, ESBuild would bake the
contents of the local `package.json` into the release build at build
time whereas we want it to read the contents at runtime so we can use
the `package.json` in the tree to build the code and later inject a
modified version into the release package with a timestamped build
version.

Changes:

* move `CLI_VERSION` out of `src/utils/session.ts` and into
`src/version.ts` so `../package.json` is a correct relative path both
from `src/version.ts` in the source tree and also in the final
`dist/cli.js` build output
* change `assert` to `with` in `import pkg` as apparently `with` became
standard in Node 22
* mark `"../package.json"` as external in `build.mjs` so the version is
not baked into the `.js` at build time

After using `pnpm stage-release` to build a release version, if I use
Node 22.0 to run Codex, I see the following printed to stderr at
startup:

```
(node:71308) ExperimentalWarning: Importing JSON modules is an experimental feature and might change at any time
(Use `node --trace-warnings ...` to show where the warning was created)
```

Note it is a warning and does not prevent Codex from running.

In Node 22.12, the warning goes away, but the warning still appears in
Node 22.11. For Node 22, 22.15.0 is the current LTS version, so LTS
users will not see this.

Also, something about moving the definition of `CLI_VERSION` caused a
problem with the mocks in `check-updates.test.ts`. I asked Codex to fix
it, and it came up with the change to the test configs. I don't know
enough about vitest to understand what it did, but the tests seem
healthy again, so I'm going with it.
2025-05-12 21:27:15 -07:00
Michael Bolin
61b881d4e5 fix: agent instructions were not being included when ~/.codex/instructions.md was empty (#908)
I had seen issues where `codex-rs` would not always write files without
me pressuring it to do so, and between that and the report of
https://github.com/openai/codex/issues/900, I decided to look into this
further. I found two serious issues with agent instructions:

(1) We were only sending agent instructions on the first turn, but
looking at the TypeScript code, we should be sending them on every turn.

(2) There was a serious issue where the agent instructions were
frequently lost:

* The TypeScript CLI appears to keep writing `~/.codex/instructions.md`:
55142e3e6c/codex-cli/src/utils/config.ts (L586)
* If `instructions.md` is present, the Rust CLI uses the contents of it
INSTEAD OF the default prompt, even if `instructions.md` is empty:
55142e3e6c/codex-rs/core/src/config.rs (L202-L203)

The combination of these two things means that I have been using
`codex-rs` without these key instructions:
https://github.com/openai/codex/blob/main/codex-rs/core/prompt.md

Looking at the TypeScript code, it appears we should be concatenating
these three items every time (if they exist):

* `prompt.md`
* `~/.codex/instructions.md`
* nearest `AGENTS.md`

This PR fixes things so that:

* `Config.instructions` is `None` if `instructions.md` is empty
* `Payload.instructions` is now `&'a str` instead of `Option<&'a
String>` because we should always have _something_ to send
* `Prompt` now has a `get_full_instructions()` helper that returns a
`Cow<str>` that will always include the agent instructions first.
2025-05-12 17:24:44 -07:00
Michael Bolin
55142e3e6c fix: use "thinking" instead of "codex reasoning" as the label for reasoning events in the TUI (#905) 2025-05-12 15:19:45 -07:00
Michael Bolin
115fb0b95d fix: navigate initialization phase before tools/list request in MCP client (#904)
Apparently the MCP server implemented in JavaScript did not require the
`initialize` handshake before responding to tool list/call, so I missed
this.
2025-05-12 15:15:26 -07:00
Avi Rosenberg
ab4cb94227 fix: Normalize paths in resolvePathAgainstWorkdir to prevent path traversal vulnerability (#895)
This PR fixes a potential path traversal vulnerability by ensuring all
paths are properly normalized in the `resolvePathAgainstWorkdir`
function.

## Changes
- Added path normalization for both absolute and relative paths
- Ensures normalized paths are used in all subsequent operations
- Prevents potential path traversal attacks through non-normalized paths

This minimal change addresses the security concern without adding
unnecessary complexity, while maintaining compatibility with existing
code.
2025-05-12 13:44:00 -07:00
Michael Bolin
73fe1381aa chore: introduce new --native flag to Node module release process (#844)
This PR introduces an optional build flag, `--native`, that will build a
version of the Codex npm module that:

- Includes both the Node.js and native Rust versions (for Mac and Linux)
- Will run the native version if `CODEX_RUST=1` is set
- Runs the TypeScript version otherwise

Note this PR also updates the workflow URL to
https://github.com/openai/codex/actions/runs/14872557396, as that is a
build from today that includes everything up through
https://github.com/openai/codex/pull/843.

Test Plan:

In `~/code/codex/codex-cli`, I ran:

```
pnpm stage-release --native
```

The end of the output was:

```
Staged version 0.1.2505121317 for release in /var/folders/wm/f209bc1n2bd_r0jncn9s6j_00000gp/T/tmp.xd2p5ETYGN
Test Node:
    node /var/folders/wm/f209bc1n2bd_r0jncn9s6j_00000gp/T/tmp.xd2p5ETYGN/bin/codex.js --help
Test Rust:
    CODEX_RUST=1 node /var/folders/wm/f209bc1n2bd_r0jncn9s6j_00000gp/T/tmp.xd2p5ETYGN/bin/codex.js --help
Next:  cd "/var/folders/wm/f209bc1n2bd_r0jncn9s6j_00000gp/T/tmp.xd2p5ETYGN" && npm publish --tag native
```

I verified that running each of these commands ran the expected version
of Codex.

While here, I also added `bin` to the `files` list in `package.json`,
which should have been done as part of
https://github.com/openai/codex/pull/757, as that added new entries to
`bin` that were matched by `.gitignore` but should have been included in
a release.
2025-05-12 13:38:10 -07:00
jcoens-openai
f3bd143867 Disallow expect via lints (#865)
Adds `expect()` as a denied lint. Same deal applies with `unwrap()`
where we now need to put `#[expect(...` on ones that we legit want. Took
care to enable `expect()` in test contexts.

# Tests

```
cargo fmt
cargo clippy --all-features --all-targets --no-deps -- -D warnings
cargo test
```
2025-05-12 08:45:46 -07:00
Michael Bolin
a1f51bf91b fix: fix border style for BottomPane (#893)
This PR fixes things so that:

* when the `BottomPane` is in the `StatusIndicator` state, the border
should be dim
* when the `BottomPane` does not have input focus, the border should be
dim

To make it easier to enforce this invariant, this PR introduces
`BottomPane::set_state()` that will:

* update `self.state`
* call `update_border_for_input_focus()`
* request a repaint

This should make it easier to enforce other updates for state changes
going forward.
2025-05-10 23:34:13 -07:00
Michael Bolin
b4785b5f88 feat: include "reasoning" messages in Rust TUI (#892)
As shown in the screenshot, we now include reasoning messages from the
model in the TUI under the heading "codex reasoning":


![image](https://github.com/user-attachments/assets/d8eb3dc3-2f9f-4e95-847e-d24b421249a8)

To ensure these are visible by default when using `o4-mini`, this also
changes the default value for `summary` (formerly `generate_summary`,
which is deprecated in favor of `summary` according to the docs) from
unset to `"auto"`.
2025-05-10 21:43:27 -07:00
Michael Bolin
2b122da087 feat: add support for AGENTS.md in Rust CLI (#885)
The TypeScript CLI already has support for including the contents of
`AGENTS.md` in the instructions sent with the first turn of a
conversation. This PR brings this functionality to the Rust CLI.

To be considered, `AGENTS.md` must be in the `cwd` of the session, or in
one of the parent folders up to a Git/filesystem root (whichever is
encountered first).

By default, a maximum of 32 KiB of `AGENTS.md` will be included, though
this is configurable using the new-in-this-PR `project_doc_max_bytes`
option in `config.toml`.
2025-05-10 17:52:59 -07:00
Corry Haines
b42ad670f1 fix: flex-mode via config/flag (#813)
* Add flexMode to stored config, and use it during config loading unless
the flag is explicitly passed.
* If the config asks for flexMode and the model doesn't support it,
silently disable flexMode.

Resolves #803
2025-05-10 16:18:20 -07:00
Pranav
646e7e9c11 feat: added arceeai as a provider (#818)
- Added ArceeAI as a provider  - https://conductor.arcee.ai/v1
- Compatible with ArceeAI SLMs (Virtuoso, Maestro)
- Works with ArceeAI's Conductor auto‑router models (auto, auto‑tool),
once #817 is merged
2025-05-10 16:16:28 -07:00
Pranav
19262f632f fix: guard against missing choices (#817)
- Fixes guard by using optional chaining to safely check
chunk.choices?.[0] before accessing.
- Currently, accessing chunk.choices[0] without checking could throw if
choices was missing from the chunk.
2025-05-10 16:16:19 -07:00
Corry Haines
fcc76cf3e7 Add reasoning effort option to CLI help text (#815)
Reasoning effort was already available, but not expressed into the help
text, so it was non-discoverable.

Other issues discovered, but will fix in separate PR since they are
larger:
* #816 reasoningEffort isn't displayed in the terminal-header, making it
rather hard to see the state of configuration
* I don't think the config file setting works, as the CLI option always
"wins" and overwrites it
2025-05-10 15:58:59 -07:00
Fouad Matin
3104d81b7b fix: migrate to AGENTS.md (#764)
Migrate from `codex.md` to `AGENTS.md`
2025-05-10 15:57:49 -07:00
Tomas Cupr
e307d007aa fix: retry on OpenAI server_error even without status code (#814)
Fix: retry on server_error responses that lack an HTTP status code

### What happened

1. An OpenAI endpoint returned a **5xx** (transient server-side
failure).
2. The SDK surfaced it as an `APIError` with

{ "type": "server_error", "message": "...", "status": undefined }

           (The SDK does not always populate `status` for these cases.)
3. Our retry logic in `src/utils/agent/agent-loop.ts` determined

isServerError = typeof status === "number" && status >= 500;

Because `status` was *undefined*, the error was **not** recognised as
retriable, the exception bubbled out, and the CLI crashed with a stack
           trace similar to:

               Error: An error occurred while processing the request.
                   at .../cli.js:474:1514

### Root cause

The transient-error detector ignored the semantic flag type ===
"server_error" that the SDK provides when the numeric status is missing.

#### Fix (1 loc + comment)

Extend the check:

const status = errCtx?.status ?? errCtx?.httpStatus ??
errCtx?.statusCode;

const isServerError = (typeof status === "number" && status >= 500) ||
// classic 5xx
errCtx?.type === "server_error";                   // <-- NEW

Now the agent:

* Retries up to **5** times (existing logic) when the backend reports a
transient failure, even if `status` is absent.
* If all retries fail, surfaces the existing friendly system message
instead of an uncaught exception.

### Tests & validation

pnpm test # all suites green (17 agent-level tests now include this
path)
pnpm run lint    # 0 errors / warnings
pnpm run typecheck

A new unit-test file isn’t required—the behaviour is already covered by
tests/agent-server-retry.test.ts, which stubs type: "server_error" and
now passes with the updated logic.

### Impact

* No API-surface changes.
* Prevents CLI crashes on intermittent OpenAI outages.
* Adds robust handling for other providers that may follow the same
error-shape.
2025-05-10 15:43:03 -07:00
Michael Bolin
fde48aaa0d feat: experimental env var: CODEX_SANDBOX_NETWORK_DISABLED (#879)
When using Codex to develop Codex itself, I noticed that sometimes it
would try to add `#[ignore]` to the following tests:

```
keeps_previous_response_id_between_tasks()
retries_on_early_close()
```

Both of these tests start a `MockServer` that launches an HTTP server on
an ephemeral port and requires network access to hit it, which the
Seatbelt policy associated with `--full-auto` correctly denies. If I
wasn't paying attention to the code that Codex was generating, one of
these `#[ignore]` annotations could have slipped into the codebase,
effectively disabling the test for everyone.

To that end, this PR enables an experimental environment variable named
`CODEX_SANDBOX_NETWORK_DISABLED` that is set to `1` if the
`SandboxPolicy` used to spawn the process does not have full network
access. I say it is "experimental" because I'm not convinced this API is
quite right, but we need to start somewhere. (It might be more
appropriate to have an env var like `CODEX_SANDBOX=full-auto`, but the
challenge is that our newer `SandboxPolicy` abstraction does not map to
a simple set of enums like in the TypeScript CLI.)

We leverage this new functionality by adding the following code to the
aforementioned tests as a way to "dynamically disable" them:

```rust
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
    println!(
        "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
    );
    return;
}
```

We can use the `debug seatbelt --full-auto` command to verify that
`cargo test` fails when run under Seatbelt prior to this change:

```
$ cargo run --bin codex -- debug seatbelt --full-auto -- cargo test
---- keeps_previous_response_id_between_tasks stdout ----

thread 'keeps_previous_response_id_between_tasks' panicked at /Users/mbolin/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/wiremock-0.6.3/src/mock_server/builder.rs:107:46:
Failed to bind an OS port for a mock server.: Os { code: 1, kind: PermissionDenied, message: "Operation not permitted" }
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace


failures:
    keeps_previous_response_id_between_tasks

test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s

error: test failed, to rerun pass `-p codex-core --test previous_response_id`
```

Though after this change, the above command succeeds! This means that,
going forward, when Codex operates on Codex itself, when it runs `cargo
test`, only "real failures" should cause the command to fail.

As part of this change, I decided to tighten up the codepaths for
running `exec()` for shell tool calls. In particular, we do it in `core`
for the main Codex business logic itself, but we also expose this logic
via `debug` subcommands in the CLI in the `cli` crate. The logic for the
`debug` subcommands was not quite as faithful to the true business logic
as I liked, so I:

* refactored a bit of the Linux code, splitting `linux.rs` into
`linux_exec.rs` and `landlock.rs` in the `core` crate.
* gating less code behind `#[cfg(target_os = "linux")]` because such
code does not get built by default when I develop on Mac, which means I
either have to build the code in Docker or wait for CI signal
* introduced `macro_rules! configure_command` in `exec.rs` so we can
have both sync and async versions of this code. The synchronous version
seems more appropriate for straight threads or potentially fork/exec.
2025-05-09 18:29:34 -07:00
Govind Kamtamneni
7795272282 Adds Azure OpenAI support (#769)
## Summary

This PR introduces support for Azure OpenAI as a provider within the
Codex CLI. Users can now configure the tool to leverage their Azure
OpenAI deployments by specifying `"azure"` as the provider in
`config.json` and setting the corresponding `AZURE_OPENAI_API_KEY` and
`AZURE_OPENAI_API_VERSION` environment variables. This functionality is
added alongside the existing provider options (OpenAI, OpenRouter,
etc.).

Related to #92

**Note:** This PR is currently in **Draft** status because tests on the
`main` branch are failing. It will be marked as ready for review once
the `main` branch is stable and tests are passing.

---

## What’s Changed

-   **Configuration (`config.ts`, `providers.ts`, `README.md`):**
- Added `"azure"` to the supported `providers` list in `providers.ts`,
specifying its name, default base URL structure, and environment
variable key (`AZURE_OPENAI_API_KEY`).
- Defined the `AZURE_OPENAI_API_VERSION` environment variable in
`config.ts` with a default value (`2025-03-01-preview`).
    -   Updated `README.md` to:
        -   Include "azure" in the list of providers.
- Add a configuration section for Azure OpenAI, detailing the required
environment variables (`AZURE_OPENAI_API_KEY`,
`AZURE_OPENAI_API_VERSION`) with examples.
- **Client Instantiation (`terminal-chat.tsx`, `singlepass-cli-app.tsx`,
`agent-loop.ts`, `compact-summary.ts`, `model-utils.ts`):**
- Modified various components and utility functions where the OpenAI
client is initialized.
- Added conditional logic to check if the configured `provider` is
`"azure"`.
- If the provider is Azure, the `AzureOpenAI` client from the `openai`
package is instantiated, using the configured `baseURL`, `apiKey` (from
`AZURE_OPENAI_API_KEY`), and `apiVersion` (from
`AZURE_OPENAI_API_VERSION`).
- Otherwise, the standard `OpenAI` client is instantiated as before.
-   **Dependencies:**
- Relies on the `openai` package's built-in support for `AzureOpenAI`.
No *new* external dependencies were added specifically for this Azure
implementation beyond the `openai` package itself.

---

## How to Test

*This has been tested locally and confirmed working with Azure OpenAI.*

1.  **Configure `config.json`:**
Ensure your `~/.codex/config.json` (or project-specific config) includes
Azure and sets it as the active provider:
    ```json
    {
      "providers": {
        // ... other providers
        "azure": {
          "name": "AzureOpenAI",
"baseURL": "https://YOUR_RESOURCE_NAME.openai.azure.com", // Replace
with your Azure endpoint
          "envKey": "AZURE_OPENAI_API_KEY"
        }
      },
      "provider": "azure", // Set Azure as the active provider
      "model": "o4-mini" // Use your Azure deployment name here
      // ... other config settings
    }
    ```
2.  **Set up Environment Variables:**
    ```bash
    # Set the API Key for your Azure OpenAI resource
    export AZURE_OPENAI_API_KEY="your-azure-api-key-here"

# Set the API Version (Optional - defaults to `2025-03-01-preview` if
not set)
# Ensure this version is supported by your Azure deployment and endpoint
    export AZURE_OPENAI_API_VERSION="2025-03-01-preview"
    ```
3.  **Get the Codex CLI by building from this PR branch:**
Clone your fork, checkout this branch (`feat/azure-openai`), navigate to
`codex-cli`, and build:
    ```bash
    # cd /path/to/your/fork/codex
    git checkout feat/azure-openai # Or your branch name
    cd codex-cli
    corepack enable
    pnpm install
    pnpm build
    ```
4.  **Invoke Codex:**
Run the locally built CLI using `node` from the `codex-cli` directory:
    ```bash
    node ./dist/cli.js "Explain the purpose of this PR"
    ```
*(Alternatively, if you ran `pnpm link` after building, you can use
`codex "Explain the purpose of this PR"` from anywhere)*.
5. **Verify:** Confirm that the command executes successfully and
interacts with your configured Azure OpenAI deployment.

---

## Tests

- [x] Tested locally against an Azure OpenAI deployment using API Key
authentication. Basic commands and interactions confirmed working.

---

## Checklist

- [x] Added Azure provider details to configuration files
(`providers.ts`, `config.ts`).
- [x] Implemented conditional `AzureOpenAI` client initialization based
on provider setting.
-   [x] Ensured `apiVersion` is passed correctly to the Azure client.
-   [x] Updated `README.md` with Azure OpenAI setup instructions.
- [x] Manually tested core functionality against a live Azure OpenAI
endpoint.
- [x] Add/update automated tests for the Azure code path (pending `main`
stability).

cc @theabhinavdas @nikodem-wrona @fouad-openai @tibo-openai (adjust as
needed)

---

I have read the CLA Document and I hereby sign the CLA
2025-05-09 18:11:32 -07:00
jcoens-openai
78843c3940 feat: Allow pasting newlines (#866)
Noticed that when pasting multi-line blocks, each newline was treated
like a new submission.
Update tui to handle Paste directly and map newlines to shift+enter.

# Test

Copied this into clipboard:
```
Do nothing.
Explain this repo to me.
```

Pasted in and saw multi-line input. Hitting Enter then submitted the
full block.
2025-05-09 11:33:46 -07:00
Michael Bolin
93817643ee chore: refactor exec() into spawn_child() and consume_truncated_output() (#878)
This PR is a straight refactor so that creating the `Child` process for
an `shell` tool call and consuming its output can be separate concerns.
For the actual tool call, we will always apply
`consume_truncated_output()`, but for the top-level debug commands in
the CLI (e.g., `debug seatbelt` and `debug landlock`), we only want to
use the `spawn_child()` part of `exec()`.

We want the subcommands to match the `shell` tool call usage as
faithfully as possible. This becomes more important when we introduce a
new parameter to `spawn_child()` in
https://github.com/openai/codex/pull/879.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/878).
* #879
* __->__ #878
2025-05-09 11:03:58 -07:00
Michael Bolin
27198bfe11 fix: make McpConnectionManager tolerant of MCPs that fail to start (#854)
I added a typo in my `config.toml` such that the `command` for one of my
`mcp_servers` did not exist and I verified that the error was surfaced
in the TUI (and that I was still able to use Codex).


![image](https://github.com/user-attachments/assets/f13cc08c-f4c6-40ec-9ab4-a9d75e03152f)
2025-05-08 23:45:54 -07:00
Michael Bolin
b940adae8e fix: get responses API working again in Rust (#872)
I inadvertently regressed support for the Responses API when adding
support for the chat completions API in
https://github.com/openai/codex/pull/862. This should get both APIs
working again, but the chat completions codepath seems more complex than
necessary. I'll try to clean that up shortly, but I want to get things
working again ASAP.
2025-05-08 22:49:15 -07:00
Michael Bolin
e924070cee feat: support the chat completions API in the Rust CLI (#862)
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.
2025-05-08 21:46:06 -07:00
Michael Bolin
a538e6acb2 fix: use continue-on-error: true to tidy up GitHub Action (#871)
I installed the GitHub Actions extension for VS Code and it started
giving me lint warnings about this line:


a9adb4175c/.github/workflows/rust-ci.yml (L99)

Using an env var to track the state of individual steps was not great,
so I did some research about GitHub actions, which led to the discovery
of combining `continue-on-error: true` with `if .. steps.STEP.outcome ==
'failure'...`.

Apparently there is also a `failure()` macro that is supposed to make
this simpler, but I saw a number of complains online about it not
working as expected. Checking `outcome` seems maybe more reliable at the
cost of being slightly more verbose.
2025-05-08 16:21:11 -07:00
Michael Bolin
a9adb4175c fix: enable clippy on tests (#870)
https://github.com/openai/codex/pull/855 added the clippy warning to
disallow `unwrap()`, but apparently we were not verifying that tests
were "clippy clean" in CI, so I ended up with a lot of local errors in
VS Code.

This turns on the check in CI and fixes the offenders.
2025-05-08 16:02:56 -07:00
Michael Bolin
699ec5a87f fix: remove wrapping in Rust TUI that was incompatible with scrolling math (#868)
I noticed that sometimes I would enter a new message, but it would not
show up in the conversation history. Even if I focused the conversation
history and tried to scroll it to the bottom, I could not bring it into
view. At first, I was concerned that messages were not making it to the
UI layer, but I added debug statements and verified that was not the
issue.

It turned out that, previous to this PR, lines that are wider than the
viewport take up multiple lines of vertical space because `wrap()` was
set on the `Paragraph` inside the scroll pane. Unfortunately, that broke
our "scrollbar math" that assumed each `Line` contributes one line of
height in the UI.

This PR removes the `wrap()`, but introduces a new issue, which is that
now you cannot see long lines without resizing your terminal window. For
now, I filed an issue here:

https://github.com/openai/codex/issues/869

I think the long-term fix is to fix our math so it calculates the height
of a `Line` after it is wrapped given the current width of the viewport.
2025-05-08 15:17:17 -07:00
jcoens-openai
87cf120873 Workspace lints and disallow unwrap (#855)
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.
2025-05-08 09:46:18 -07:00
Michael Bolin
9fdf2fa066 fix: remove clap dependency from core crate (#860) 2025-05-07 19:33:09 -07:00
Michael Bolin
86022f097e feat: read model_provider and model_providers from config.toml (#853)
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!
2025-05-07 17:38:28 -07:00
Michael Bolin
cfe50c7107 fix: creating an instance of Codex requires a Config (#859)
I discovered that I accidentally introduced a change in
https://github.com/openai/codex/pull/829 where we load a fresh `Config`
in the middle of `codex.rs`:


c3e10e180a/codex-rs/core/src/codex.rs (L515-L522)

This is not good because the `Config` could differ from the one that has
the user's overrides specified from the CLI. Also, in unit tests, it
means the `Config` was picking up my personal settings as opposed to
using a vanilla config, which was problematic.

This PR cleans things up by moving the common case where
`Op::ConfigureSession` is derived from `Config` (originally done in
`codex_wrapper.rs`) and making it the standard way to initialize `Codex`
by putting it in `Codex::spawn()`. Note this also eliminates quite a bit
of boilerplate from the tests and relieves the caller of the
responsibility of minting out unique IDs when invoking `submit()`.
2025-05-07 16:33:28 -07:00
Michael Bolin
c3e10e180a fix: remove CodexBuilder and Recorder (#858)
These abstractions were originally created exclusively for the REPL,
which was removed in https://github.com/openai/codex/pull/754.
Currently, the create some unnecessary Tokio tasks, so we are better off
without them. (We can always bring this back if we have a new use case.)
2025-05-07 16:11:42 -07:00
Michael Bolin
42617f8726 feat: save session transcripts when using Rust CLI (#845)
This adds support for saving transcripts when using the Rust CLI. Like
the TypeScript CLI, it saves the transcript to `~/.codex/sessions`,
though it uses JSONL for the file format (and `.jsonl` for the file
extension) so that even if Codex crashes, what was written to the
`.jsonl` file should generally still be valid JSONL content.
2025-05-07 13:49:15 -07:00
Michael Bolin
9da6ebef3f fix: add optional timeout to McpClient::send_request() (#852)
We now impose a 10s timeout on the initial `tools/list` request to an
MCP server. We do not apply a timeout for other types of requests yet,
but we should start enforcing those, as well.
2025-05-07 12:56:38 -07:00
Michael Bolin
0360b4d0d7 feat: introduce the use of tui-markdown (#851)
This introduces the use of the `tui-markdown` crate to parse an
assistant message as Markdown and style it using ANSI for a better user
experience. As shown in the screenshot below, it has support for syntax
highlighting for _tagged_ fenced code blocks:

<img width="907" alt="image"
src="https://github.com/user-attachments/assets/900dc229-80bb-46e8-b1bb-efee4c70ba3c"
/>

That said, `tui-markdown` is not as configurable (or stylish!) as
https://www.npmjs.com/package/marked-terminal, which is what we use in
the TypeScript CLI. In particular:

* The styles are hardcoded and `tui_markdown::from_str()` does not take
any options whatsoever. It uses "bold white" for inline code style which
does not stand out as much as the yellow used by `marked-terminal`:


65402cbda7/tui-markdown/src/lib.rs (L464)

I asked Codex to take a first pass at this and it came up with:

https://github.com/joshka/tui-markdown/pull/80

* If a fenced code block is not tagged, then it does not get
highlighted. I would rather add some logic here:


65402cbda7/tui-markdown/src/lib.rs (L262)

that uses something like https://pypi.org/project/guesslang/ to examine
the value of `text` and try to use the appropriate syntax highlighter.

* When we have a fenced code block, we do not want to show the opening
and closing triple backticks in the output.

To unblock ourselves, we might want to bundle our own fork of
`tui-markdown` temporarily until we figure out what the shape of the API
should be and then try to upstream it.
2025-05-07 10:46:32 -07:00
jcoens-openai
a080d7b0fd Update submodules version to come from the workspace (#850)
Tie the version of submodules to the workspace version.
2025-05-07 10:08:06 -07:00
jcoens-openai
8a89d3aeda Update cargo to 2024 edition (#842)
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
2025-05-07 08:37:48 -07:00
Michael Bolin
c577e94b67 chore: introduce codex-common crate (#843)
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.
2025-05-06 17:38:56 -07:00
Michael Bolin
7d8b38b37b feat: show MCP tool calls in codex exec subcommand (#841)
This is analogous to the change for the TUI in
https://github.com/openai/codex/pull/836, but for `codex exec`.

To test, I ran:

```
cargo run --bin codex-exec -- 'what is the weather in wellesley ma tomorrow'
```

and saw:


![image](https://github.com/user-attachments/assets/5714e07f-88c7-4dd9-aa0d-be54c1670533)
2025-05-06 16:52:43 -07:00
Michael Bolin
6f87f4c69f feat: drop support for q in the Rust TUI since we already support ctrl+d (#799)
Out of the box, we will make `/` the only official "escape sequence" for
commands in the Rust TUI. We will look to support `q` (or any string you
want to use as a "macro") via a plugin, but not make it part of the
default experience.

Existing `q` users will have to get by with `ctrl+d` for now.
2025-05-06 16:34:17 -07:00
Michael Bolin
aa36a15f9f fix: make all fields of Session struct private again (#840)
https://github.com/openai/codex/pull/829 noted it introduced a circular
dep between `codex.rs` and `mcp_tool_call.rs`. This attempts to clean
things up: the circular dep still exists, but at least all the fields of
`Session` are private again.
2025-05-06 16:21:35 -07:00
Michael Bolin
88e7ca5f2b feat: show MCP tool calls in TUI (#836)
Adds logic for the `McpToolCallBegin` and `McpToolCallEnd` events in
`codex-rs/tui/src/chatwidget.rs` so they get entries in the conversation
history in the TUI.

Building on top of https://github.com/openai/codex/pull/829, here is the
result of running:

```
cargo run --bin codex -- 'what is the weather in san francisco tomorrow'
```


![image](https://github.com/user-attachments/assets/db4a79bb-4988-46cb-acb2-446d5ba9e058)
2025-05-06 16:12:15 -07:00
Michael Bolin
147a940449 feat: support mcp_servers in config.toml (#829)
This adds initial support for MCP servers in the style of Claude Desktop
and Cursor. Note this PR is the bare minimum to get things working end
to end: all configured MCP servers are launched every time Codex is run,
there is no recovery for MCP servers that crash, etc.

(Also, I took some shortcuts to change some fields of `Session` to be
`pub(crate)`, which also means there are circular deps between
`codex.rs` and `mcp_tool_call.rs`, but I will clean that up in a
subsequent PR.)

`codex-rs/README.md` is updated as part of this PR to explain how to use
this feature. There is a bit of plumbing to route the new settings from
`Config` to the business logic in `codex.rs`. The most significant
chunks for new code are in `mcp_connection_manager.rs` (which defines
the `McpConnectionManager` struct) and `mcp_tool_call.rs`, which is
responsible for tool calls.

This PR also introduces new `McpToolCallBegin` and `McpToolCallEnd`
event types to the protocol, but does not add any handlers for them.
(See https://github.com/openai/codex/pull/836 for initial usage.)

To test, I added the following to my `~/.codex/config.toml`:

```toml
# Local build of https://github.com/hideya/mcp-server-weather-js
[mcp_servers.weather]
command = "/Users/mbolin/code/mcp-server-weather-js/dist/index.js"
args = []
```

And then I ran the following:

```
codex-rs$ cargo run --bin codex exec 'what is the weather in san francisco'
[2025-05-06T22:40:05] Task started: 1
[2025-05-06T22:40:18] Agent message: Here’s the latest National Weather Service forecast for San Francisco (downtown, near 37.77° N, 122.42° W):

This Afternoon (Tue):
• Sunny, high near 69 °F
• West-southwest wind around 12 mph

Tonight:
• Partly cloudy, low around 52 °F
• SW wind 7–10 mph
...
```

Note that Codex itself is not able to make network calls, so it would
not normally be able to get live weather information like this. However,
the weather MCP is [currently] not run under the Codex sandbox, so it is
able to hit `api.weather.gov` and fetch current weather information.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/829).
* #836
* __->__ #829
2025-05-06 15:47:59 -07:00
Michael Bolin
49d040215a fix: build all crates individually as part of CI (#833)
I discovered that `cargo build` worked for the entire workspace, but not
for the `mcp-client` or `core` crates.

* `mcp-client` failed to build because it underspecified the set of
features it needed from `tokio`.
* `core` failed to build because it was using a "feature" of its own
crate in the default, no-feature version.
 
This PR fixes the builds and adds a check in CI to defend against this
sort of thing going forward.
2025-05-06 12:02:49 -07:00
Michael Bolin
5f1b8f707c feat: update McpClient::new_stdio_client() to accept an env (#831)
Cleans up the signature for `new_stdio_client()` to more closely mirror
how MCP servers are declared in config files (`command`, `args`, `env`).
Also takes a cue from Claude Code where the MCP server is launched with
a restricted `env` so that it only includes "safe" things like `USER`
and `PATH` (see the `create_env_for_mcp_server()` function introduced in
this PR for details) by default, as it is common for developers to have
sensitive API keys present in their environment that should only be
forwarded to the MCP server when the user has explicitly configured it
to do so.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/831).
* #829
* __->__ #831
2025-05-06 11:14:47 -07:00
Michael Bolin
2cf7aeeeb6 feat: initial McpClient for Rust (#822)
This PR introduces an initial `McpClient` that we will use to give Codex
itself programmatic access to foreign MCPs. This does not wire it up in
Codex itself yet, but the new `mcp-client` crate includes a `main.rs`
for basic testing for now.

Manually tested by sending a `tools/list` request to Codex's own MCP
server:

```
codex-rs$ cargo build
codex-rs$ cargo run --bin codex-mcp-client ./target/debug/codex-mcp-server
{
  "tools": [
    {
      "description": "Run a Codex session. Accepts configuration parameters matching the Codex Config struct.",
      "inputSchema": {
        "properties": {
          "approval-policy": {
            "description": "Execution approval policy expressed as the kebab-case variant name (`unless-allow-listed`, `auto-edit`, `on-failure`, `never`).",
            "enum": [
              "auto-edit",
              "unless-allow-listed",
              "on-failure",
              "never"
            ],
            "type": "string"
          },
          "cwd": {
            "description": "Working directory for the session. If relative, it is resolved against the server process's current working directory.",
            "type": "string"
          },
          "disable-response-storage": {
            "description": "Disable server-side response storage.",
            "type": "boolean"
          },
          "model": {
            "description": "Optional override for the model name (e.g. \"o3\", \"o4-mini\")",
            "type": "string"
          },
          "prompt": {
            "description": "The *initial user prompt* to start the Codex conversation.",
            "type": "string"
          },
          "sandbox-permissions": {
            "description": "Sandbox permissions using the same string values accepted by the CLI (e.g. \"disk-write-cwd\", \"network-full-access\").",
            "items": {
              "enum": [
                "disk-full-read-access",
                "disk-write-cwd",
                "disk-write-platform-user-temp-folder",
                "disk-write-platform-global-temp-folder",
                "disk-full-write-access",
                "network-full-access"
              ],
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "prompt"
        ],
        "type": "object"
      },
      "name": "codex"
    }
  ]
}
```
2025-05-05 12:52:55 -07:00
Anil Karaka
76a979007e fix: increase output limits for truncating collector (#575)
This Pull Request addresses an issue where the output of commands
executed in the raw-exec utility was being truncated due to restrictive
limits on the number of lines and bytes collected. The truncation caused
the message [Output truncated: too many lines or bytes] to appear when
processing large outputs, which could hinder the functionality of the
CLI.

Changes Made

Increased the maximum output limits in the
[createTruncatingCollector](https://github.com/openai/codex/pull/575)
utility:
Bytes: Increased from 10 KB to 100 KB.
Lines: Increased from 256 lines to 1024 lines.
Installed the @types/node package to resolve missing type definitions
for [NodeJS](https://github.com/openai/codex/pull/575) and
[Buffer](https://github.com/openai/codex/pull/575).
Verified and fixed any related errors in the
[createTruncatingCollector](https://github.com/openai/codex/pull/575)
implementation.

Issue Solved: 

This PR ensures that larger outputs can be processed without truncation,
improving the usability of the CLI for commands that generate extensive
output. https://github.com/openai/codex/issues/509

---------

Co-authored-by: Michael Bolin <bolinfest@gmail.com>
2025-05-05 10:26:55 -07:00
Andrey Mishchenko
7e97980cb4 Use "Title case" for ToC (#812) 2025-05-05 08:49:42 -07:00
Michael Bolin
2b72d05c5e feat: make Codex available as a tool when running it as an MCP server (#811)
This PR replaces the placeholder `"echo"` tool call in the MCP server
with a `"codex"` tool that calls Codex. Events such as
`ExecApprovalRequest` and `ApplyPatchApprovalRequest` are not handled
properly yet, but I have `approval_policy = "never"` set in my
`~/.codex/config.toml` such that those codepaths are not exercised.

The schema for this MPC tool is defined by a new `CodexToolCallParam`
struct introduced in this PR. It is fairly similar to `ConfigOverrides`,
as the param is used to help create the `Config` used to start the Codex
session, though it also includes the `prompt` used to kick off the
session.

This PR also introduces the use of the third-party `schemars` crate to
generate the JSON schema, which is verified in the
`verify_codex_tool_json_schema()` unit test.

Events that are dispatched during the Codex session are sent back to the
MCP client as MCP notifications. This gives the client a way to monitor
progress as the tool call itself may take minutes to complete depending
on the complexity of the task requested by the user.

In the video below, I launched the server via:

```shell
mcp-server$ RUST_LOG=debug npx @modelcontextprotocol/inspector cargo run --
```

In the video, you can see the flow of:

* requesting the list of tools
* choosing the **codex** tool
* entering a value for **prompt** and then making the tool call

Note that I left the other fields blank because when unspecified, the
values in my `~/.codex/config.toml` were used:


https://github.com/user-attachments/assets/1975058c-b004-43ef-8c8d-800a953b8192

Note that while using the inspector, I did run into
https://github.com/modelcontextprotocol/inspector/issues/293, though the
tip about ensuring I had only one instance of the **MCP Inspector** tab
open in my browser seemed to fix things.
2025-05-05 07:16:19 -07:00
Michael Bolin
5d924d44cf fix: ensure apply_patch resolves relative paths against workdir or project cwd (#810)
https://github.com/openai/codex/pull/800 kicked off some work to be more
disciplined about honoring the `cwd` param passed in rather than
assuming `std::env::current_dir()` as the `cwd`. As part of this, we
need to ensure `apply_patch` calls honor the appropriate `cwd` as well,
which is significant if the paths in the `apply_patch` arg are not
absolute paths themselves. Failing that:

- The `apply_patch` function call can contain an optional`workdir`
param, so:
- If specified and is an absolute path, it should be used to resolve
relative paths
- If specified and is a relative path, should be resolved against
`Config.cwd` and then any relative paths will be resolved against the
result
- If `workdir` is not specified on the function call, relative paths
should be resolved against `Config.cwd`

Note that we had a similar issue in the TypeScript CLI that was fixed in
https://github.com/openai/codex/pull/556.

As part of the fix, this PR introduces `ApplyPatchAction` so clients can
deal with that instead of the raw `HashMap<PathBuf,
ApplyPatchFileChange>`. This enables us to enforce, by construction,
that all paths contained in the `ApplyPatchAction` are absolute paths.
2025-05-04 12:32:51 -07:00
Michael Bolin
a134bdde49 fix: is_inside_git_repo should take the directory as a param (#809)
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.
2025-05-04 11:39:10 -07:00
Michael Bolin
cd12f0c24a fix: TUI should use cwd from Config (#808)
https://github.com/openai/codex/pull/800 made `cwd` a property of
`Config`, so the TUI should use this instead of running
`std::env::current_dir()`.
2025-05-04 11:12:40 -07:00
Michael Bolin
421e159888 feat: make cwd a required field of Config so we stop assuming std::env::current_dir() in a session (#800)
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`.
2025-05-04 10:57:12 -07:00
Andrey Mishchenko
4b61fb8bab use "Title case" in README.md (#798) 2025-05-03 10:17:44 -07:00
Michael Bolin
0442458309 doc: update the config.toml documentation for the Rust CLI in codex-rs/README.md (#795)
https://github.com/openai/codex/pull/793 had important information on
the `notify` config option that seemed worth memorializing, so this PR
updates the documentation about all of the configurable options in
`~/.codex/config.toml`.
2025-05-02 20:32:24 -07:00
Michael Bolin
a180ed44e8 feat: configurable notifications in the Rust CLI (#793)
With this change, you can specify a program that will be executed to get
notified about events generated by Codex. The notification info will be
packaged as a JSON object. The supported notification types are defined
by the `UserNotification` enum introduced in this PR. Initially, it
contains only one variant, `AgentTurnComplete`:

```rust
pub(crate) enum UserNotification {
    #[serde(rename_all = "kebab-case")]
    AgentTurnComplete {
        turn_id: String,

        /// Messages that the user sent to the agent to initiate the turn.
        input_messages: Vec<String>,

        /// The last message sent by the assistant in the turn.
        last_assistant_message: Option<String>,
    },
}
```

This is intended to support the common case when a "turn" ends, which
often means it is now your chance to give Codex further instructions.

For example, I have the following in my `~/.codex/config.toml`:

```toml
notify = ["python3", "/Users/mbolin/.codex/notify.py"]
```

I created my own custom notifier script that calls out to
[terminal-notifier](https://github.com/julienXX/terminal-notifier) to
show a desktop push notification on macOS. Contents of `notify.py`:

```python
#!/usr/bin/env python3

import json
import subprocess
import sys


def main() -> int:
    if len(sys.argv) != 2:
        print("Usage: notify.py <NOTIFICATION_JSON>")
        return 1

    try:
        notification = json.loads(sys.argv[1])
    except json.JSONDecodeError:
        return 1

    match notification_type := notification.get("type"):
        case "agent-turn-complete":
            assistant_message = notification.get("last-assistant-message")
            if assistant_message:
                title = f"Codex: {assistant_message}"
            else:
                title = "Codex: Turn Complete!"
            input_messages = notification.get("input_messages", [])
            message = " ".join(input_messages)
            title += message
        case _:
            print(f"not sending a push notification for: {notification_type}")
            return 0

    subprocess.check_output(
        [
            "terminal-notifier",
            "-title",
            title,
            "-message",
            message,
            "-group",
            "codex",
            "-ignoreDnD",
            "-activate",
            "com.googlecode.iterm2",
        ]
    )

    return 0


if __name__ == "__main__":
    sys.exit(main())
```

For reference, here are related PRs that tried to add this functionality
to the TypeScript version of the Codex CLI:

* https://github.com/openai/codex/pull/160
* https://github.com/openai/codex/pull/498
2025-05-02 19:48:13 -07:00
Michael Bolin
21cd953dbd feat: introduce mcp-server crate (#792)
This introduces the `mcp-server` crate, which contains a barebones MCP
server that provides an `echo` tool that echoes the user's request back
to them.

To test it out, I launched
[modelcontextprotocol/inspector](https://github.com/modelcontextprotocol/inspector)
like so:

```
mcp-server$ npx @modelcontextprotocol/inspector cargo run --
```

and opened up `http://127.0.0.1:6274` in my browser:


![image](https://github.com/user-attachments/assets/83fc55d4-25c2-4497-80cd-e9702283ff93)

I also had to make a small fix to `mcp-types`, adding
`#[serde(untagged)]` to a number of `enum`s.
2025-05-02 17:25:58 -07:00
Michael Bolin
865e518771 fix: mcp-types serialization wasn't quite working (#791)
While creating a basic MCP server in
https://github.com/openai/codex/pull/792, I discovered a number of bugs
with the initial `mcp-types` crate that I needed to fix in order to
implement the server.

For example, I discovered that when serializing a message, `"jsonrpc":
"2.0"` was not being included.

I changed the codegen so that the field is added as:

```rust
    #[serde(rename = "jsonrpc", default = "default_jsonrpc")]
    pub jsonrpc: String,
```

This ensures that the field is serialized as `"2.0"`, though the field
still has to be assigned, which is tedious. I may experiment with
`Default` or something else in the future. (I also considered creating a
custom serializer, but I'm not sure it's worth the trouble.)

While here, I also added `MCP_SCHEMA_VERSION` and `JSONRPC_VERSION` as
`pub const`s for the crate.

I also discovered that MCP rejects sending `null` for optional fields,
so I had to add `#[serde(skip_serializing_if = "Option::is_none")]` on
`Option` fields.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/791).
* #792
* __->__ #791
2025-05-02 16:38:05 -07:00
Michael Bolin
83961e0299 feat: introduce mcp-types crate (#787)
This adds our own `mcp-types` crate to our Cargo workspace. We vendor in
the
[`2025-03-26/schema.json`](05f2045136/schema/2025-03-26/schema.json)
from the MCP repo and introduce a `generate_mcp_types.py` script to
codegen the `lib.rs` from the JSON schema.

Test coverage is currently light, but I plan to refine things as we
start making use of this crate.

And yes, I am aware that
https://github.com/modelcontextprotocol/rust-sdk exists, though the
published https://crates.io/crates/rmcp appears to be a competing
effort. While things are up in the air, it seems better for us to
control our own version of this code.

Incidentally, Codex did a lot of the work for this PR. I told it to
never edit `lib.rs` directly and instead to update
`generate_mcp_types.py` and then re-run it to update `lib.rs`. It
followed these instructions and once things were working end-to-end, I
iteratively asked for changes to the tests until the API looked
reasonable (and the code worked). Codex was responsible for figuring out
what to do to `generate_mcp_types.py` to achieve the requested test/API
changes.
2025-05-02 13:33:14 -07:00
anup-openai
f6b1ce2e3a Configure HTTPS agent for proxies (#775)
- Some workflows require you to route openAI API traffic through a proxy
- See
https://github.com/openai/openai-node/tree/v4?tab=readme-ov-file#configuring-an-https-agent-eg-for-proxies
for more details

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
Co-authored-by: Fouad Matin <fouad@openai.com>
2025-05-02 12:08:13 -07:00
Fouad Matin
b864cc3810 update: vite version (#766) 2025-05-02 09:30:08 -07:00
Michael Bolin
a4b51f6b67 feat: use Landlock for sandboxing on Linux in TypeScript CLI (#763)
Building on top of https://github.com/openai/codex/pull/757, this PR
updates Codex to use the Landlock executor binary for sandboxing in the
Node.js CLI. Note that Codex has to be invoked with either `--full-auto`
or `--auto-edit` to activate sandboxing. (Using `--suggest` or
`--dangerously-auto-approve-everything` ensures the sandboxing codepath
will not be exercised.)

When I tested this on a Linux host (specifically, `Ubuntu 24.04.1 LTS`),
things worked as expected: I ran Codex CLI with `--full-auto` and then
asked it to do `echo 'hello mbolin' into hello_world.txt` and it
succeeded without prompting me.

However, in my testing, I discovered that the sandboxing did *not* work
when using `--full-auto` in a Linux Docker container from a macOS host.
I updated the code to throw a detailed error message when this happens:


![image](https://github.com/user-attachments/assets/e5b99def-f00e-4ade-a0c5-2394d30df52e)
2025-05-01 12:34:56 -07:00
Michael Bolin
3f5975ad5a chore: make build process a single script to run (#757)
This introduces `./codex-cli/scripts/stage_release.sh`, which is a shell
script that stages a release for the Node.js module in a temp directory.
It updates the release to include these native binaries:

```
bin/codex-linux-sandbox-arm64
bin/codex-linux-sandbox-x64
```

though this PR does not update Codex CLI to use them yet.

When doing local development, run
`./codex-cli/scripts/install_native_deps.sh` to install these in your
own `bin/` folder.

This PR also updates `README.md` to document the new workflow.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/757).
* #763
* __->__ #757
2025-05-01 08:36:07 -07:00
Fouad Matin
463a230991 bump(version): 0.1.2504301751 (#768)
## `0.1.2504301751`

### 🚀 Features

- User config api key (#569)
- `@mention` files in codex (#701)
- Add `--reasoning` CLI flag (#314)
- Lower default retry wait time and increase number of tries (#720)
- Add common package registries domains to allowed-domains list (#414)

### 🪲 Bug Fixes

- Insufficient quota message (#758)
- Input keyboard shortcut opt+delete (#685)
- `/diff` should include untracked files (#686)
- Only allow running without sandbox if explicitly marked in safe
container (#699)
- Tighten up check for /usr/bin/sandbox-exec (#710)
- Check if sandbox-exec is available (#696)
- Duplicate messages in quiet mode (#680)
2025-04-30 17:55:34 -07:00
Fouad Matin
985fd44ec0 fix: input keyboard shortcut opt+delete (#685) 2025-04-30 17:17:13 -07:00
moppywhip
bc4e6db749 feat: @mention files in codex (#701)
Solves #700

## State of the World Before

Prior to this PR, when users wanted to share file contents with Codex,
they had two options:
- Manually copy and paste file contents into the chat
- Wait for the assistant to use the shell tool to view the file

The second approach required the assistant to:
1. Recognize the need to view a file
2. Execute a shell tool call
3. Wait for the tool call to complete
4. Process the file contents

This consumed extra tokens and reduced user control over which files
were shared with the model.

## State of the World After

With this PR, users can now:
- Reference files directly in their chat input using the `@path` syntax
- Have file contents automatically expanded into XML blocks before being
sent to the LLM

For example, users can type `@src/utils/config.js` in their message, and
the file contents will be included in context. Within the terminal chat
history, these file blocks will be collapsed back to `@path` format in
the UI for clean presentation.

Tag File suggestions:
<img width="857" alt="file-suggestions"
src="https://github.com/user-attachments/assets/397669dc-ad83-492d-b5f0-164fab2ff4ba"
/>

Tagging files in action:
<img width="858" alt="tagging-files"
src="https://github.com/user-attachments/assets/0de9d559-7b7f-4916-aeff-87ae9b16550a"
/>

Demo video of file tagging:
[![Demo video of file
tagging](https://img.youtube.com/vi/vL4LqtBnqt8/0.jpg)](https://www.youtube.com/watch?v=vL4LqtBnqt8)

## Implementation Details

This PR consists of 2 main components:

1. **File Tag Utilities**:
- New `file-tag-utils.ts` utility module that handles both expansion and
collapsing of file tags
- `expandFileTags()` identifies `@path` tokens and replaces them with
XML blocks containing file contents
- `collapseXmlBlocks()` reverses the process, converting XML blocks back
to `@path` format for UI display
- Tokens are only expanded if they point to valid files (directories are
ignored)
   - Expansion happens just before sending input to the model

2. **Terminal Chat Integration**:
- Leveraged the existing file system completion system for tabbing to
support the `@path` syntax
   - Added `updateFsSuggestions` helper to manage filesystem suggestions
- Added `replaceFileSystemSuggestion` to replace input with filesystem
suggestions
- Applied `collapseXmlBlocks` in the chat response rendering so that
tagged files are shown as simple `@path` tags

The PR also includes test coverage for both the UI and the file tag
utilities.

## Next Steps

Some ideas I'd like to implement if this feature gets merged:

- Line selection: `@path[50:80]` to grab specific sections of files
- Method selection: `@path#methodName` to grab just one function/class
- Visual improvements: highlight file tags in the UI to make them more
noticeable
2025-04-30 16:19:55 -07:00
Kevin Alwell
bd82101859 fix: insufficient quota message (#758)
This pull request includes a change to improve the error message
displayed when there is insufficient quota in the `AgentLoop` class. The
updated message provides more detailed information and a link for
managing or purchasing credits.

Error message improvement:

*
[`codex-cli/src/utils/agent/agent-loop.ts`](diffhunk://#diff-b15957eac2720c3f1f55aa32f172cdd0ac6969caf4e7be87983df747a9f97083L1140-R1140):
Updated the error message in the `AgentLoop` class to include the
specific error message (if available) and a link to manage or purchase
credits.


Fixes #751
2025-04-30 16:00:50 -07:00
Michael Bolin
033d379eca fix: remove unused _writableRoots arg to exec() function (#762)
I suspect this was done originally so that `execForSandbox()` had a
consistent signature for both the `SandboxType.NONE` and
`SandboxType.MACOS_SEATBELT` cases, but that is not really necessary and
turns out to make the upcoming Landlock support a bit more complicated
to implement, so I had Codex remove it and clean up the call sites.
2025-04-30 14:08:27 -07:00
Michael Bolin
e6fe8d6fa1 chore: mark Rust releases as "prerelease" (#761)
Apparently the URLs for draft releases cannot be downloaded using
unauthenticated `curl`, which means the DotSlash file only works for
users who are authenticated with `gh`. According to chat, prereleases
_can_ be fetched with unauthenticated `curl`, so let's try that.
2025-04-30 13:25:53 -07:00
Michael Bolin
b571249867 chore: script to create a Rust release (#759)
For now, keep things simple such that we never update the `version` in
the `Cargo.toml` for the workspace root on the `main` branch. Instead,
create a new branch for a release, push one commit that updates the
`version`, and then tag that branch to kick off a release.

To test, I ran this script and created this release job:

https://github.com/openai/codex/actions/runs/14762580641
2025-04-30 12:39:03 -07:00
Michael Bolin
24278347b7 fix: remove codex-repl from GitHub workflows (#760)
I missed this when doing https://github.com/openai/codex/pull/754.
2025-04-30 12:10:24 -07:00
Michael Bolin
8f7a54501c chore: Rust release, set prerelease:false and version=0.0.2504301132 (#755)
The generated DotSlash file has URLs that refer to
`https://github.com/openai/codex/releases/`, so let's set
`prerelease:false` (but keep `draft:true` for now) so those URLs should
work.

Also updated `version` in Cargo workspace so I will kick off a build
once this lands.
2025-04-30 11:53:03 -07:00
Michael Bolin
2f1d96e77d fix: remove errant eslint-disable so pnpm run lint passes again (#756)
My bad: introduced in https://github.com/openai/codex/pull/753.
2025-04-30 11:37:11 -07:00
Michael Bolin
84aaefa102 fix: read version from package.json instead of modifying session.ts (#753)
I am working to simplify the build process. As a first step, update
`session.ts` so it reads the `version` from `package.json` at runtime so
we no longer have to modify it during the build process. I want to get
to a place where the build looks like:

```
cd codex-cli
pnpm i
pnpm build
RELEASE_DIR=$(mktemp -d)
cp -r bin "$RELEASE_DIR/bin"
cp -r dist "$RELEASE_DIR/dist"
cp -r src "$RELEASE_DIR/src" # important if we want sourcemaps to continue to work
cp ../README.md "$RELEASE_DIR"
VERSION=$(printf '0.1.%d' $(date +%y%m%d%H%M))
jq --arg version "$VERSION" '.version = $version' package.json > "$RELEASE_DIR/package.json"
```

Then the contents of `$RELEASE_DIR` should be good to `npm publish`, no?
2025-04-30 11:03:10 -07:00
Michael Bolin
c432d9ef81 chore: remove the REPL crate/subcommand (#754)
@oai-ragona and I discussed it, and we feel the REPL crate has served
its purpose, so we're going to delete the code and future archaeologists
can find it in Git history.
2025-04-30 10:15:50 -07:00
Michael Bolin
4746ee900f fix: remove expected dot after v in rust-v tag name (#742)
I think this extra dot was not intentional, but I'm not sure. Certainly
this comment suggests it should not be there:


85999d7277/.github/workflows/rust-release.yml (L4)
2025-04-30 10:05:47 -07:00
Michael Bolin
f2ed46ceca fix: include x86_64-unknown-linux-gnu in the list of arch to build codex-linux-sandbox (#748) 2025-04-29 21:19:14 -07:00
Michael Bolin
e42dacbdc8 fix: add another place where $dest was missing in rust-release.yml (#747)
I thought https://github.com/openai/codex/pull/745 was the last fix I
needed, but apparently not.
2025-04-29 20:23:54 -07:00
Michael Bolin
5122fe647f chore: fix errors in .github/workflows/rust-release.yml and prep 0.0.2504292006 release (#745)
Apparently I made two key mistakes in
https://github.com/openai/codex/pull/740 (fixed in this PR):

* I forgot to redefine `$dest` in the `Stage Linux-only artifacts` step
* I did not define the `if` check correctly in the `Stage Linux-only
artifacts` step

This fixes both of those issues and bumps the workspace version to
`0.0.2504292006` in preparation for another release attempt.
2025-04-29 20:12:23 -07:00
Michael Bolin
1a39568e03 chore: set Cargo workspace to version 0.0.2504291954 to create a scratch release (#744) 2025-04-29 19:56:30 -07:00
Michael Bolin
efb0acc152 fix: primary output of the codex-cli crate is named codex, not codex-cli (#743)
I just got a bunch of failures in the release workflow:

https://github.com/openai/codex/actions/runs/14745492805/job/41391926707

along the lines of:

```
cp: cannot stat 'target/aarch64-unknown-linux-gnu/release/codex-cli': No such file or directory
```
2025-04-29 19:53:29 -07:00
Michael Bolin
85999d7277 chore: set Cargo workspace to version 0.0.2504291926 to create a scratch release (#741)
Needed to exercise the new release process in
https://github.com/openai/codex/pull/671.
2025-04-29 19:35:37 -07:00
Michael Bolin
411bfeb410 feat: codex-linux-sandbox standalone executable (#740)
This introduces a standalone executable that run the equivalent of the
`codex debug landlock` subcommand and updates `rust-release.yml` to
include it in the release.

The idea is that we will include this small binary with the TypeScript
CLI to provide support for Linux sandboxing.
2025-04-29 19:21:26 -07:00
Michael Bolin
27bc4516bf feat: bring back -s option to specify sandbox permissions (#739) 2025-04-29 18:42:52 -07:00
oai-ragona
cb0b0259f4 [codex-rs] Add rust-release action (#671)
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.
2025-04-29 16:38:47 -07:00
Michael Bolin
0a00b5ed29 fix: overhaul SandboxPolicy and config loading in Rust (#732)
Previous to this PR, `SandboxPolicy` was a bit difficult to work with:


237f8a11e1/codex-rs/core/src/protocol.rs (L98-L108)

Specifically:

* It was an `enum` and therefore options were mutually exclusive as
opposed to additive.
* It defined things in terms of what the agent _could not_ do as opposed
to what they _could_ do. This made things hard to support because we
would prefer to build up a sandbox config by starting with something
extremely restrictive and only granting permissions for things the user
as explicitly allowed.

This PR changes things substantially by redefining the policy in terms
of two concepts:

* A `SandboxPermission` enum that defines permissions that can be
granted to the agent/sandbox.
* A `SandboxPolicy` that internally stores a `Vec<SandboxPermission>`,
but externally exposes a simpler API that can be used to configure
Seatbelt/Landlock.

Previous to this PR, we supported a `--sandbox` flag that effectively
mapped to an enum value in `SandboxPolicy`. Though now that
`SandboxPolicy` is a wrapper around `Vec<SandboxPermission>`, the single
`--sandbox` flag no longer makes sense. While I could have turned it
into a flag that the user can specify multiple times, I think the
current values to use with such a flag are long and potentially messy,
so for the moment, I have dropped support for `--sandbox` altogether and
we can bring it back once we have figured out the naming thing.

Since `--sandbox` is gone, users now have to specify `--full-auto` to
get a sandbox that allows writes in `cwd`. Admittedly, there is no clean
way to specify the equivalent of `--full-auto` in your `config.toml`
right now, so we will have to revisit that, as well.

Because `Config` presents a `SandboxPolicy` field and `SandboxPolicy`
changed considerably, I had to overhaul how config loading works, as
well. There are now two distinct concepts, `ConfigToml` and `Config`:

* `ConfigToml` is the deserialization of `~/.codex/config.toml`. As one
might expect, every field is `Optional` and it is `#[derive(Deserialize,
Default)]`. Consistent use of `Optional` makes it clear what the user
has specified explicitly.
* `Config` is the "normalized config" and is produced by merging
`ConfigToml` with `ConfigOverrides`. Where `ConfigToml` contains a raw
`Option<Vec<SandboxPermission>>`, `Config` presents only the final
`SandboxPolicy`.

The changes to `core/src/exec.rs` and `core/src/linux.rs` merit extra
special attention to ensure we are faithfully mapping the
`SandboxPolicy` to the Seatbelt and Landlock configs, respectively.

Also, take note that `core/src/seatbelt_readonly_policy.sbpl` has been
renamed to `codex-rs/core/src/seatbelt_base_policy.sbpl` and that
`(allow file-read*)` has been removed from the `.sbpl` file as now this
is added to the policy in `core/src/exec.rs` when
`sandbox_policy.has_full_disk_read_access()` is `true`.
2025-04-29 15:01:16 -07:00
Matan Yemini
237f8a11e1 feat: add common package registries domains to allowed-domains list (#414)
feat: add common package registries domains to allowed-domains list
2025-04-29 12:07:00 -07:00
Kevin Alwell
a6ed7ff103 Fixes issue #726 by adding config to configToSave object (#728)
The saveConfig() function only includes a hardcoded subset of properties
when writing the config file. Any property not explicitly listed (like
disableResponseStorage) will be dropped.
I have added `disableResponseStorage` to the `configToSave` object as
the immediate fix.

[Linking Issue this fixes.](https://github.com/openai/codex/issues/726)
2025-04-29 13:10:16 -04:00
Michael Bolin
3b39964f81 feat: improve output of exec subcommand (#719) 2025-04-29 09:59:35 -07:00
Rashim
892242ef7c feat: add --reasoning CLI flag (#314)
This PR adds a new CLI flag: `--reasoning`, which allows users to
customize the reasoning effort level (`low`, `medium`, or `high`) used
by OpenAI's `o` models.
By introducing the `--reasoning` flag, users gain more flexibility when
working with the models. It enables optimization for either speed or
depth of reasoning, depending on specific use cases.
This PR resolves #107

- **Flag**: `--reasoning`
- **Accepted Values**: `low`, `medium`, `high`
- **Default Behavior**: If not specified, the model uses the default
reasoning level.

## Example Usage

```bash
codex --reasoning=low "Write a simple function to calculate factorial"

---------

Co-authored-by: Fouad Matin <169186268+fouad-openai@users.noreply.github.com>
Co-authored-by: yashrwealthy <yash.rastogi@wealthy.in>
Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-29 07:30:49 -07:00
Fouad Matin
19928bc257 [codex-rs] fix: exit code 1 if no api key (#697) 2025-04-28 21:42:06 -07:00
Michael Bolin
b9bba09819 fix: eliminate runtime dependency on patch(1) for apply_patch (#718)
When processing an `apply_patch` tool call, we were already computing
the new file content in order to compute the unified diff. Before this
PR, we were shelling out to `patch(1)` to apply the unified diff once
the user accepted the change, but this updates the code to just retain
the new file content and use it to write the file when the user accepts.
This simplifies deployment because it no longer assumes `patch(1)` is on
the host.

Note this change is internal to the Codex agent and does not affect
`protocol.rs`.
2025-04-28 21:15:41 -07:00
Thibault Sottiaux
d09dbba7ec feat: lower default retry wait time and increase number of tries (#720)
In total we now guarantee that we will wait for at least 60s before
giving up.

---------

Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-28 21:11:30 -07:00
Michael Bolin
e79549f039 feat: add debug landlock subcommand comparable to debug seatbelt (#715)
This PR adds a `debug landlock` subcommand to the Codex CLI for testing
how Codex would execute a command using the specified sandbox policy.

Built and ran this code in the `rust:latest` Docker container. In the
container, hitting the network with vanilla `curl` succeeds:

```
$ curl google.com
<HTML><HEAD><meta http-equiv="content-type" content="text/html;charset=utf-8">
<TITLE>301 Moved</TITLE></HEAD><BODY>
<H1>301 Moved</H1>
The document has moved
<A HREF="http://www.google.com/">here</A>.
</BODY></HTML>
```

whereas this fails, as expected:

```
$ cargo run -- debug landlock -s network-restricted -- curl google.com
curl: (6) getaddrinfo() thread failed to start
```
2025-04-28 16:37:05 -07:00
Michael Bolin
e7ad9449ea feat: make it possible to set disable_response_storage = true in config.toml (#714)
https://github.com/openai/codex/pull/642 introduced support for the
`--disable-response-storage` flag, but if you are a ZDR customer, it is
tedious to set this every time, so this PR makes it possible to set this
once in `config.toml` and be done with it.

Incidentally, this tidies things up such that now `init_codex()` takes
only one parameter: `Config`.
2025-04-28 15:39:34 -07:00
Michael Bolin
cca1122ddc fix: make the TUI the default/"interactive" CLI in Rust (#711)
Originally, the `interactive` crate was going to be a placeholder for
building out a UX that was comparable to that of the existing TypeScript
CLI. Though after researching how Ratatui works, that seems difficult to
do because it is designed around the idea that it will redraw the full
screen buffer each time (and so any scrolling should be "internal" to
your Ratatui app) whereas the TypeScript CLI expects to render the full
history of the conversation every time(*) (which is why you can use your
terminal scrollbar to scroll it).

While it is possible to use Ratatui in a way that acts more like what
the TypeScript CLI is doing, it is awkward and seemingly results in
tedious code, so I think we should abandon that approach. As such, this
PR deletes the `interactive/` folder and the code that depended on it.

Further, since we added support for mousewheel scrolling in the TUI in
https://github.com/openai/codex/pull/641, it certainly feels much better
and the need for scroll support via the terminal scrollbar is greatly
diminished. This is now a more appropriate default UX for the
"multitool" CLI.

(*) Incidentally, I haven't verified this, but I think this results in
O(N^2) work in rendering, which seems potentially problematic for long
conversations.
2025-04-28 13:46:22 -07:00
Michael Bolin
40460faf2a fix: tighten up check for /usr/bin/sandbox-exec (#710)
* In both TypeScript and Rust, we now invoke `/usr/bin/sandbox-exec`
explicitly rather than whatever `sandbox-exec` happens to be on the
`PATH`.
* Changed `isSandboxExecAvailable` to use `access()` rather than
`command -v` so that:
  *  We only do the check once over the lifetime of the Codex process.
  * The check is specific to `/usr/bin/sandbox-exec`.
* We now do a syscall rather than incur the overhead of spawning a
process, dealing with timeouts, etc.

I think there is still room for improvement here where we should move
the `isSandboxExecAvailable` check earlier in the CLI, ideally right
after we do arg parsing to verify that we can provide the Seatbelt
sandbox if that is what the user has requested.
2025-04-28 13:42:04 -07:00
Michael Bolin
38575ed8aa fix: increase timeout of test_writable_root (#713)
Although we made some promising fixes in
https://github.com/openai/codex/pull/662, we are still seeing some
flakiness in `test_writable_root()`. If this continues to flake with the
more generous timeout, we should try something other than simply
increasing the timeout.
2025-04-28 13:09:27 -07:00
Michael Bolin
77e2918049 fix: drop d as keyboard shortcut for scrolling in the TUI (#704)
The existing `b` and `space` are sufficient and `d` and `u` default to
half-page scrolling in `less`, so the way we supported `d` and `u`
wasn't faithful to that, anyway:

https://man7.org/linux/man-pages/man1/less.1.html

If we decide to bring `d` and `u` back, they should probably match
`less`?
2025-04-28 10:39:58 -07:00
Thibault Sottiaux
fa5fa8effc fix: only allow running without sandbox if explicitly marked in safe container (#699)
Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-28 07:48:38 -07:00
Michael Bolin
4eda4dd772 feat: load defaults into Config and introduce ConfigOverrides (#677)
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.
2025-04-27 21:47:50 -07:00
Thibault Sottiaux
e9d16d3c2b fix: check if sandbox-exec is available (#696)
- Introduce `isSandboxExecAvailable()` helper and tidy import ordering
in `handle-exec-command.ts`.
- Add runtime check for the `sandbox-exec` binary on macOS; fall back to
`SandboxType.NONE` with a warning if it’s missing, preventing crashes.

---------

Signed-off-by: Thibault Sottiaux <tibo@openai.com>
Co-authored-by: Fouad Matin <fouad@openai.com>
2025-04-27 17:04:47 -07:00
Fouad Matin
523996b5cb fix: /diff should include untracked files (#686) 2025-04-26 12:43:51 -07:00
Tomas Cupr
bc500d3009 feat: user config api key (#569)
Adds support for reading OPENAI_API_KEY (and other variables) from a
user‑wide dotenv file (~/.codex.config). Precedence order is now:
  1. explicit environment variable
  2. project‑local .env (loaded earlier)
  3. ~/.codex.config

Also adds a regression test that ensures the multiline editor correctly
handles cases where printable text and the CSI‑u Shift+Enter sequence
arrive in the same input chunk.

House‑kept with Prettier; removed stray temp.json artifact.
2025-04-26 10:13:30 -07:00
moppywhip
9b0ccf9aeb fix: duplicate messages in quiet mode (#680)
Addressing #600 and #664 (partially)

## Bug
Codex was staging duplicate items in output running when the same
response item appeared in both the streaming events. Specifically:

1. Items would be staged once when received as a
`response.output_item.done` event
2. The same items would be staged again when included in the final
`response.completed` payload

This duplication would result in each message being sent several times
in the quiet mode output.

## Changes
- Added a Set (`alreadyStagedItemIds`) to track items that have already
been staged
- Modified the `stageItem` function to check if an item's ID is already
in this set before staging it
- Added a regression test (`agent-dedupe-items.test.ts`) that verifies
items with the same ID are only staged once

## Testing
Like other tests, the included test creates a mock OpenAI stream that
emits the same message twice (once as an incremental event and once in
the final response) and verifies the item is only passed to `onItem`
once.
2025-04-26 09:14:50 -07:00
Michael Bolin
b0ba65a936 fix: write logs to ~/.codex/log instead of /tmp (#669)
Previously, the Rust TUI was writing log files to `/tmp`, which is
world-readable and not available on Windows, so that isn't great.

This PR tries to clean things up by adding a function that provides the
path to the "Codex config dir," e.g., `~/.codex` (though I suppose we
could support `$CODEX_HOME` to override this?) and then defines other
paths in terms of the result of `codex_dir()`.

For example, `log_dir()` returns the folder where log files should be
written which is defined in terms of `codex_dir()`. I updated the TUI to
use this function. On UNIX, we even go so far as to `chmod 600` the log
file by default, though as noted in a comment, it's a bit tedious to do
the equivalent on Windows, so we just let that go for now.

This also changes the default logging level to `info` for `codex_core`
and `codex_tui` when `RUST_LOG` is not specified. I'm not really sure if
we should use a more verbose default (it may be helpful when debugging
user issues), though if so, we should probably also set up log rotation?
2025-04-25 17:37:41 -07:00
Fouad Matin
103093f793 bump(version): 0.1.2504251709 (#660)
## `0.1.2504251709`

### 🚀 Features

- Add openai model info configuration (#551)
- Added provider to run quiet mode function (#571)
- Create parent directories when creating new files (#552)
- Print bug report URL in terminal instead of opening browser (#510)
(#528)
- Add support for custom provider configuration in the user config
(#537)
- Add support for OpenAI-Organization and OpenAI-Project headers (#626)
- Add specific instructions for creating API keys in error msg (#581)
- Enhance toCodePoints to prevent potential unicode 14 errors (#615)
- More native keyboard navigation in multiline editor (#655)
- Display error on selection of invalid model (#594)

### 🪲 Bug Fixes

- Model selection (#643)
- Nits in apply patch (#640)
- Input keyboard shortcuts (#676)
- `apply_patch` unicode characters (#625)
- Don't clear turn input before retries (#611)
- More loosely match context for apply_patch (#610)
- Update bug report template - there is no --revision flag (#614)
- Remove outdated copy of text input and external editor feature (#670)
- Remove unreachable "disableResponseStorage" logic flow introduced in
#543 (#573)
- Non-openai mode - fix for gemini content: null, fix 429 to throw
before stream (#563)
- Only allow going up in history when not already in history if input is
empty (#654)
- Do not grant "node" user sudo access when using run_in_container.sh
(#627)
- Update scripts/build_container.sh to use pnpm instead of npm (#631)
- Update lint-staged config to use pnpm --filter (#582)
- Non-openai mode - don't default temp and top_p (#572)
- Fix error catching when checking for updates (#597)
- Close stdin when running an exec tool call (#636)
2025-04-25 17:15:40 -07:00
Fouad Matin
3f4762d969 fix: input keyboard shortcuts (#676)
Fixes keyboard shortcuts:
- ctrl+a/e
- opt+arrow keys
2025-04-25 16:58:09 -07:00
Michael Bolin
f3ee933a74 ci: build Rust on Windows as part of CI (#665)
While we aren't ready to provide Windows binaries of Codex CLI, it seems
like a good idea to ensure we guard platform-specific code
appropriately.
2025-04-25 16:22:16 -07:00
Thibault Sottiaux
44d68f9dbf fix: remove outdated copy of text input and external editor feature (#670)
Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-25 16:11:16 -07:00
Misha Davidov
15bf5ca971 fix: handling weird unicode characters in apply_patch (#674)
I � unicode
2025-04-25 16:01:58 -07:00
Michael Bolin
c18f1689a9 fix: small fixes so Codex compiles on Windows (#673)
Small fixes required:

* `ExitStatusExt` differs because UNIX expects exit code to be `i32`
whereas Windows does `u32`
* Marking a file "executable only by owner" is a bit more involved on
Windows. We just do something approximate for now (and add a TODO) to
get things compiling.

I created this PR on my personal Windows machine and `cargo test` and
`cargo clippy` succeed. Once this is in, I'll rebase
https://github.com/openai/codex/pull/665 on top so Windows stays fixed!
2025-04-25 15:58:44 -07:00
Michael Bolin
ebd2ae4abd fix: remove dependency on expanduser crate (#667)
In putting up https://github.com/openai/codex/pull/665, I discovered
that the `expanduser` crate does not compile on Windows. Looking into
it, we do not seem to need it because we were only using it with a value
that was passed in via a command-line flag, so the shell expands `~` for
us before we see it, anyway. (I changed the type in `Cli` from `String`
to `PathBuf`, to boot.)

If we do need this sort of functionality in the future,
https://docs.rs/shellexpand/latest/shellexpand/fn.tilde.html seems
promising.
2025-04-25 14:20:21 -07:00
Michael Bolin
9c3ebac3b7 fix: flipped the sense of Prompt.store in #642 (#663)
I got the sense of this wrong in
https://github.com/openai/codex/pull/642. In that PR, I made
`--disable-response-storage` work, but broke the default case.

With this fix, both cases work and I think the code is a bit cleaner.
2025-04-25 13:41:17 -07:00
Parker Thompson
7d9de34bc7 [codex-rs] Improve linux sandbox timeouts (#662)
* Fixes flaking rust unit test
* Adds explicit sandbox exec timeout handling
2025-04-25 12:56:20 -07:00
Parker Thompson
55e25abf78 [codex-rs] CI performance for rust (#639)
* Refactors the rust-ci into a matrix build
* Adds directory caching for the build artifacts
* Adds workflow dispatch for manual testing
2025-04-25 12:44:03 -07:00
Michael Bolin
b323d10ea7 feat: add ZDR support to Rust implementation (#642)
This adds support for the `--disable-response-storage` flag across our
multiple Rust CLIs to support customers who have opted into Zero-Data
Retention (ZDR). The analogous changes to the TypeScript CLI were:

* https://github.com/openai/codex/pull/481
* https://github.com/openai/codex/pull/543

For a client using ZDR, `previous_response_id` will never be available,
so the `input` field of an API request must include the full transcript
of the conversation thus far. As such, this PR changes the type of
`Prompt.input` from `Vec<ResponseInputItem>` to `Vec<ResponseItem>`.

Practically speaking, `ResponseItem` was effectively a "superset" of
`ResponseInputItem` already. The main difference for us is that
`ResponseItem` includes the `FunctionCall` variant that we have to
include as part of the conversation history in the ZDR case.

Another key change in this PR is modifying `try_run_turn()` so that it
returns the `Vec<ResponseItem>` for the turn in addition to the
`Vec<ResponseInputItem>` produced by `try_run_turn()`. This is because
the caller of `run_turn()` needs to record the `Vec<ResponseItem>` when
ZDR is enabled.

To that end, this PR introduces `ZdrTranscript` (and adds
`zdr_transcript: Option<ZdrTranscript>` to `struct State` in `codex.rs`)
to take responsibility for maintaining the conversation transcript in
the ZDR case.
2025-04-25 12:08:18 -07:00
Michael Bolin
dc7b83666a feat(tui-rs): add support for mousewheel scrolling (#641)
It is intuitive to try to scroll the conversation history using the
mouse in the TUI, but prior to this change, we only supported scrolling
via keyboard events.

This PR enables mouse capture upon initialization (and disables it on
exit) such that we get `ScrollUp` and `ScrollDown` events in
`codex-rs/tui/src/app.rs`. I initially mapped each event to scrolling by
one line, but that felt sluggish. I decided to introduce
`ScrollEventHelper` so we could debounce scroll events and measure the
number of scroll events in a 100ms window to determine the "magnitude"
of the scroll event. I put in a basic heuristic to start, but perhaps
someone more motivated can play with it over time.

`ScrollEventHelper` takes care of handling the atomic fields and thread
management to ensure an `AppEvent::Scroll` event is pumped back through
the event loop at the appropriate time with the accumulated delta.
2025-04-25 12:01:52 -07:00
oai-ragona
d7a40195e6 [codex-rs] Reliability pass on networking (#658)
We currently see a behavior that looks like this:
```
2025-04-25T16:52:24.552789Z  WARN codex_core::codex: stream disconnected - retrying turn (1/10 in 232ms)...
codex> event: BackgroundEvent { message: "stream error: stream disconnected before completion: Transport error: error decoding response body; retrying 1/10 in 232ms…" }
2025-04-25T16:52:54.789885Z  WARN codex_core::codex: stream disconnected - retrying turn (2/10 in 418ms)...
codex> event: BackgroundEvent { message: "stream error: stream disconnected before completion: Transport error: error decoding response body; retrying 2/10 in 418ms…" }
```

This PR contains a few different fixes that attempt to resolve/improve
this:
1. **Remove overall client timeout.** I think
[this](https://github.com/openai/codex/pull/658/files#diff-c39945d3c42f29b506ff54b7fa2be0795b06d7ad97f1bf33956f60e3c6f19c19L173)
is perhaps the big fix -- it looks to me like this was actually timing
out even if events were still coming through, and that was causing a
disconnect right in the middle of a healthy stream.
2. **Cap response sizes.** We were frequently sending MUCH larger
responses than the upstream typescript `codex`, and that was definitely
not helping. [Fix
here](https://github.com/openai/codex/pull/658/files#diff-d792bef59aa3ee8cb0cbad8b176dbfefe451c227ac89919da7c3e536a9d6cdc0R21-R26)
for that one.
3. **Much higher idle timeout.** Our idle timeout value was much lower
than typescript.
4. **Sub-linear backoff.** We were much too aggressively backing off,
[this](https://github.com/openai/codex/pull/658/files#diff-5d5959b95c6239e6188516da5c6b7eb78154cd9cfedfb9f753d30a7b6d6b8b06R30-R33)
makes it sub-exponential but maintains the jitter and such.

I was seeing that `stream error: stream disconnected` behavior
constantly, and anecdotally I can no longer reproduce. It feels much
snappier.
2025-04-25 11:44:22 -07:00
Tomas Cupr
4760aa1eb9 perf: optimize token streaming with balanced approach (#635)
- Replace setTimeout(10ms) with queueMicrotask for immediate processing
- Add minimal 3ms setTimeout for rendering to maintain readable UX
- Reduces per-token delay while preserving streaming experience
- Add performance test to verify optimization works correctly

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-25 10:49:38 -07:00
Thibault Sottiaux
d401283a41 feat: more native keyboard navigation in multiline editor (#655)
Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-25 10:35:30 -07:00
rumple
69ce06d2f8 feat: Add support for OpenAI-Organization and OpenAI-Project headers (#626)
Added support for OpenAI-Organization and OpenAI-Project headers for
OpenAI API calls.

This is for #74
2025-04-25 09:52:42 -07:00
Thibault Sottiaux
866626347b fix: only allow going up in history when not already in history if input is empty (#654)
\+ cleanup below input help to be "ctrl+c to exit | "/" to see commands
| enter to send" now that we have command autocompletion
\+ minor other drive-by code cleanups

---------

Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-25 09:39:24 -07:00
Pulipaka Sai Krishna
2759ff39da fix: model selection (#643)
fix: pass correct selected model in ModelOverlay

The ModelOverlay component was incorrectly passing the current model
instead of the newly selected model to its onSelect callback. This
prevented model changes from being applied properly.

The fix ensures that when a user selects a new model, the parent
component receives the correct newly selected model value, allowing
model changes to work as intended.
2025-04-25 09:38:05 -07:00
Luci
3fe7e53327 fix: nits in apply patch (#640)
## Description

Fix a nit in `apply patch`, potentially improving performance slightly.
2025-04-25 07:27:48 -07:00
Luci
1ef8e8afd3 docs: provider config (#653)
close: #651

Hi! @tibo-openai 👋 Could you share some great examples of
`instructions.md` files? Thanks!

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-25 07:25:32 -07:00
Luci
a9ecb2efce chore: upgrade prettier to v3 (#644)
## Description

This PR addresses the following improvements:

**Unify Prettier Version**: Currently, the Prettier version used in
`/package.json` and `/codex-cli/package.json` are different. In this PR,
we're updating both to use Prettier v3.

- Prettier v3 introduces improved support for JavaScript and TypeScript.
(e.g. the formatting scenario shown in the image below. This is more
aligned with the TypeScript indentation standard).

<img width="1126" alt="image"
src="https://github.com/user-attachments/assets/6e237eb8-4553-4574-b336-ed9561c55370"
/>

**Add Prettier Auto-Formatting in lint-staged**: We've added a step to
automatically run prettier --write on JavaScript and TypeScript files as
part of the lint-staged process, before the ESLint checks.

- This will help ensure that all committed code is properly formatted
according to the project's Prettier configuration.
2025-04-25 07:21:50 -07:00
Michael Bolin
bfe6fac463 fix: close stdin when running an exec tool call (#636)
We were already doing this in the TypeScript version, but forgot to
bring this over to Rust:


c38c2a59c7/codex-cli/src/utils/agent/sandbox/raw-exec.ts (L76-L78)
2025-04-24 18:06:08 -07:00
Michael Bolin
6a9c9f4b6c fix: add RUST_BACKTRACE=full when running cargo test in CI (#638)
This should provide more information in the event of a failure.
2025-04-24 18:05:56 -07:00
Michael Bolin
5cdcbfa9b4 fix: only run rust-ci.yml on PRs that modify files in codex-rs (#637)
The `rust-ci.yml` build appears to be a bit flaky (we're looking into
it...), so to save TypeScript contributors some noise, restrict the
`rust-ci.yml` job so that it only runs on PRs that touch files in
`codex-rs/`.
2025-04-24 17:59:35 -07:00
Luci
c38c2a59c7 fix(utils): save config (#578)
## Description

When `saveConfig` is called, the project doc is incorrectly saved into
user instructions. This change ensures that only user instructions are
saved to `instructions.md` during saveConfig, preventing data
corruption.

close: #576

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-24 17:32:33 -07:00
Michael Bolin
58f0e5ab74 feat: introduce codex_execpolicy crate for defining "safe" commands (#634)
As described in detail in `codex-rs/execpolicy/README.md` introduced in
this PR, `execpolicy` is a tool that lets you define a set of _patterns_
used to match [`execv(3)`](https://linux.die.net/man/3/execv)
invocations. When a pattern is matched, `execpolicy` returns the parsed
version in a structured form that is amenable to static analysis.

The primary use case is to define patterns match commands that should be
auto-approved by a tool such as Codex. This supports a richer pattern
matching mechanism that the sort of prefix-matching we have done to
date, e.g.:


5e40d9d221/codex-cli/src/approvals.ts (L333-L354)

Note we are still playing with the API and the `system_path` option in
particular still needs some work.
2025-04-24 17:14:47 -07:00
nvp159
5e40d9d221 feat(bug-report): print bug report URL in terminal instead of opening browser (#510) (#528)
Solves #510 
This PR changes the `/bug` command to print the URL into the terminal
(so it works in headless sessions) instead of trying to open a browser.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-24 17:00:14 -07:00
sooraj
36a5a02d5c feat: display error on selection of invalid model (#594)
Up-to-date of #78 

Fixes #32

addressed requested changes @tibo-openai :) made sense to me


though, previous rationale with passing the state up was assuming there
could be a future need to have a shared state with all available models
being available to the parent
2025-04-24 16:56:00 -07:00
Michael Bolin
bb2d411043 fix: update scripts/build_container.sh to use pnpm instead of npm (#631)
I suspect this is why some contributors kept accidentally including a
new `codex-cli/package-lock.json` in their PRs.

Note the `Dockerfile` still uses `npm` instead of `pnpm`, but that
appears to be fine. (Probably nicer to globally install as few things as
possible in the image.)
2025-04-24 16:38:57 -07:00
oai-ragona
b34ed2ab83 [codex-rs] More fine-grained sandbox flag support on Linux (#632)
##### What/Why
This PR makes it so that in Linux we actually respect the different
types of `--sandbox` flag, such that users can apply network and
filesystem restrictions in combination (currently the only supported
behavior), or just pick one or the other.

We should add similar support for OSX in a future PR.

##### Testing
From Linux devbox, updated tests to use more specific flags:
```
test linux::tests_linux::sandbox_blocks_ping ... ok
test linux::tests_linux::sandbox_blocks_getent ... ok
test linux::tests_linux::test_root_read ... ok
test linux::tests_linux::test_dev_null_write ... ok
test linux::tests_linux::sandbox_blocks_dev_tcp_redirection ... ok
test linux::tests_linux::sandbox_blocks_ssh ... ok
test linux::tests_linux::test_writable_root ... ok
test linux::tests_linux::sandbox_blocks_curl ... ok
test linux::tests_linux::sandbox_blocks_wget ... ok
test linux::tests_linux::sandbox_blocks_nc ... ok
test linux::tests_linux::test_root_write - should panic ... ok
```

##### Todo
- [ ] Add negative tests (e.g. confirm you can hit the network if you
configure filesystem only restrictions)
2025-04-24 15:33:45 -07:00
Michael Bolin
61805a832d fix: do not grant "node" user sudo access when using run_in_container.sh (#627)
This exploration came out of my review of
https://github.com/openai/codex/pull/414.

`run_in_container.sh` runs Codex in a Docker container like so:


bd1c3deed9/codex-cli/scripts/run_in_container.sh (L51-L58)

But then runs `init_firewall.sh` to set up the firewall to restrict
network access.

Previously, we did this by adding `/usr/local/bin/init_firewall.sh` to
the container and adding a special rule in `/etc/sudoers.d` so the
unprivileged user (`node`) could run the privileged `init_firewall.sh`
script to open up the firewall for `api.openai.com`:


31d0d7a305/codex-cli/Dockerfile (L51-L56)

Though I believe this is unnecessary, as we can use `docker exec --user
root` from _outside_ the container to run
`/usr/local/bin/init_firewall.sh` as `root` without adding a special
case in `/etc/sudoers.d`.

This appears to work as expected, as I tested it by doing the following:

```
./codex-cli/scripts/build_container.sh
./codex-cli/scripts/run_in_container.sh 'what is the output of `curl https://www.openai.com`'
```

This was a bit funny because in some of my runs, Codex wasn't convinced
it had network access, so I had to convince it to try the `curl`
request:


![image](https://github.com/user-attachments/assets/80bd487c-74e2-4cd3-aa0f-26a6edd8d3f7)

As you can see, when it ran `curl -s https\://www.openai.com`, it a
connection failure, so the network policy appears to be working as
intended.

Note this PR also removes `sudo` from the `apt-get install` list in the
`Dockerfile`.
2025-04-24 14:25:02 -07:00
Fouad Matin
bd1c3deed9 update: readme (#630)
- mention support for ZDR
- codex open source fund
2025-04-24 14:05:26 -07:00
Michael Bolin
31d0d7a305 feat: initial import of Rust implementation of Codex CLI in codex-rs/ (#629)
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.
2025-04-24 13:31:40 -07:00
Misha Davidov
acc4acc81e fix: apply_patch unicode characters (#625)
fuzzy-er matching for apply_patch to handle u00A0 and u202F spaces.
2025-04-24 13:04:37 -07:00
Luci
e84fa6793d fix(agent-loop): notify type (#608)
## Description

The `as AppConfig` type assertion in the constructor may introduce
potential type safety risks. Removing the assertion and making `notify`
an optional parameter could enhance type robustness and prevent
unexpected runtime errors.

close: #605
2025-04-24 11:08:52 -07:00
Asa
d1c0d5e683 feat: update README and config to support custom providers with API k… (#577)
When using a non-built-in provider with the `--provider` option, users
are prompted:

```
Set the environment variable <provider>_API_KEY and re-run this command.
You can create a <provider>_API_KEY in the <provider> dashboard.
```

However, many users are confused because, even after correctly setting
`<provider>_API_KEY`, authentication may still fail unless
`OPENAI_API_KEY` is _also_ present in the environment. This is not
intuitive and leads to ambiguity about which API key is actually
required and used as a fallback, especially when using custom or
third-party (non-listed) providers.

Furthermore, the original README/documentation did not mention the
requirement to set `<provider>_BASE_URL` for non-built-in providers,
which is necessary for proper client behavior. This omission made the
configuration process more difficult for users trying to integrate with
custom endpoints.
2025-04-24 11:08:19 -07:00
Luci
6d68a90064 feat: enhance toCodePoints to prevent potential unicode 14 errors (#615)
## Description

`Array.from` may fail when handling certain characters newly added in
Unicode 14. Where possible, it seems better to use `Intl.Segmenter` for
more reliable processing.


![image](https://github.com/user-attachments/assets/2cbd779d-69d3-448e-b76a-d793cb639d96)
2025-04-24 10:49:18 -07:00
Ilya Kamen
1008e1b9a0 fix: update bug report template - there is no --revision flag (#614)
I think there was a wrong word; --revision seems not to exist in help
and does nothing.
2025-04-24 10:48:42 -07:00
Luci
257167a034 fix: lint-staged error (#617)
## Description

In a recent commit, the command `"cd codex-cli && pnpm run typecheck"`
was updated to `"pnpm --filter @openai/codex run typecheck"`.

However, this change introduces an issue: 
when running `pnpm --filter @openai/codex run typecheck`, it executes
`tsc --noEmit somefile.ts` directly, bypassing the `tsconfig.json`
configuration. As a result, numerous type errors are triggered,
preventing successful commits.

Close: #619
2025-04-24 10:48:35 -07:00
Misha Davidov
9b102965b9 feat: more loosely match context for apply_patch (#610)
More of a proposal than anything but models seem to struggle with
composing valid patches for `apply_patch` for context matching when
there are unicode look-a-likes involved. This would normalize them.

```
top-level          # ASCII
top-level          # U+2011 NON-BREAKING HYPHEN
top–level          # U+2013 EN DASH
top—level          # U+2014 EM DASH
top‒level          # U+2012 FIGURE DASH
```

thanks unicode.
2025-04-24 09:05:19 -07:00
theg1239
ad1e39c903 feat: add specific instructions for creating API keys in error msg (#581)
Updates the error message for missing Gemini API keys to reference
"Google AI Studio" instead of the generic "GEMINI dashboard". This
provides users with more accurate information about where to obtain
their Gemini API keys.

This could be extended to other providers as well.
2025-04-24 06:33:34 -05:00
theg1239
006992b85a chore: update lint-staged config to use pnpm --filter (#582)
Replaced directory-specific commands with workspace-aware pnpm commands
2025-04-24 06:33:13 -05:00
Connor Christie
622323a59b fix: don't clear turn input before retries (#611)
The current turn input in the agent loop is being discarded before
consuming the stream events which causes the stream reconnect (after
rate limit failure) to not include the inputs. Since the new stream
includes the previous response ID, it triggers a bad request exception
considering the input doesn't match what OpenAI has stored on the server
side and subsequently a very confusing error message of: `No tool output
found for function call call_xyz`.

This should fix https://github.com/openai/codex/issues/586.

## Testing

I have a personal project that I'm working on that runs multiple Codex
CLIs in parallel and often runs into rate limit errors (as seen in the
OpenAI logs). After making this change, I am no longer experiencing
Codex crashing and it was able to retry and handle everything gracefully
until completion (even though I still see rate limiting in the OpenAI
logs).
2025-04-24 06:29:36 -05:00
Connor Christie
c75cb507f0 bug: fix error catching when checking for updates (#597)
This fixes https://github.com/openai/codex/issues/480 where the latest
code was crashing when attempting to be run inside docker since the
update checker attempts to reach out to `npm.antfu.dev` but that DNS is
not allowed in the firewall rules.

I believe the original code was attempting to catch and ignore any
errors when checking for updates but was doing so incorrectly. If you
use await on a promise, you have to use a standard try/catch instead of
`Promise.catch` so this fixes that.

## Testing

### Before

```
$ scripts/run_in_container.sh "explain this project to me"
7d1aa845edf9a36fe4d5b331474b5cb8ba79537b682922b554ea677f14996c6b
Resolving api.openai.com...
Adding 162.159.140.245 for api.openai.com
Adding 172.66.0.243 for api.openai.com
Host network detected as: 172.17.0.0/24
Firewall configuration complete
Verifying firewall rules...
Firewall verification passed - unable to reach https://example.com as expected
Firewall verification passed - able to reach https://api.openai.com as expected
TypeError: fetch failed
    at node:internal/deps/undici/undici:13510:13
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async getLatestVersionBatch (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132669:17)
    at async getLatestVersion (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132674:19)
    at async getUpdateCheckInfo (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132748:20)
    at async checkForUpdates (file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:132772:23)
    at async file:///usr/local/share/npm-global/lib/node_modules/@openai/codex/dist/cli.js:142027:1 {
  [cause]: AggregateError [ECONNREFUSED]: 
      at internalConnectMultiple (node:net:1122:18)
      at afterConnectMultiple (node:net:1689:7) {
    code: 'ECONNREFUSED',
    [errors]: [ [Error], [Error] ]
  }
}
```

### After

```
$ scripts/run_in_container.sh "explain this project to me"
91aa716e3d3f86c9cf6013dd567be31b2c44eb5d7ab184d55ef498731020bb8d
Resolving api.openai.com...
Adding 162.159.140.245 for api.openai.com
Adding 172.66.0.243 for api.openai.com
Host network detected as: 172.17.0.0/24
Firewall configuration complete
Verifying firewall rules...
Firewall verification passed - unable to reach https://example.com as expected
Firewall verification passed - able to reach https://api.openai.com as expected
╭──────────────────────────────────────────────────────────────╮
│ ● OpenAI Codex (research preview) v0.1.2504221401            │
╰──────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────────────────────────╮
│ localhost session: 7c782f196ae04503866e39f071e26a69          │
│ ↳ model: o4-mini                                             │
│ ↳ provider: openai                                           │
│ ↳ approval: full-auto                                        │
╰──────────────────────────────────────────────────────────────╯
user
explain this project to me
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│( ●    ) 2s  Thinking                                                                                                                                                                                                                                                  │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
  send q or ctrl+c to exit | send "/clear" to reset | send "/help" for commands | press enter to send | shift+enter for new line — 100% context left
```
2025-04-23 15:21:00 -07:00
kshern
146a61b073 feat: add support for custom provider configuration in the user config (#537)
### What

- Add support for loading and merging custom provider configurations
from a local `providers.json` file.
- Allow users to override or extend default providers with their own
settings.

### Why

This change enables users to flexibly customize and extend provider
endpoints and API keys without modifying the codebase, making the CLI
more adaptable for various LLM backends and enterprise use cases.

### How

- Introduced `loadProvidersFromFile` and `getMergedProviders` in config
logic.
- Added/updated related tests in [tests/config.test.tsx]


### Checklist

- [x] Lint passes for changed files
- [x] Tests pass for all files
- [x] Documentation/comments updated as needed

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-23 01:45:56 -04:00
Erick
b428d66f2b feat: added provider to run quiet mode function (#571)
Adding support to be able to run other models in quiet mode

ie: `codex --approval-mode full-auto -q "explain the current directory"
--provider xai --model grok-3-beta`
2025-04-23 01:12:18 -04:00
Connor Christie
cbeb5c3057 fix: remove unreachable "disableResponseStorage" logic flow introduced in #543 (#573)
This PR cleans up unreachable code that was added as a result of
https://github.com/openai/codex/pull/543.

The code being removed is already being handled above:

23f0887df3/codex-cli/src/utils/agent/agent-loop.ts (L535-L539)
2025-04-23 01:08:52 -04:00
Daniel Nakov
4261973467 bug: non-openai mode - don't default temp and top_p (#572)
I haven't seen any actual errors due to this, but it's been bothering me
that I had it defaulted to 1. I think best to leave it undefined and
have each provider do their thing
2025-04-23 01:07:40 -04:00
Daniel Nakov
23f0887df3 bug: non-openai mode - fix for gemini content: null, fix 429 to throw before stream (#563)
Gemini's API is finicky, it 400's without an error when you pass
content: null
Also fixed the rate limiting issues by throwing outside of the iterator.
I think there's a separate issue with the second isRateLimit check in
agent-loop - turnInput is cleared by that time, so it retries without
the last message.
2025-04-22 20:37:48 -04:00
Misha Davidov
20b6ef0de8 feat: create parent directories when creating new files. (#552)
apply_patch doesn't create parent directories when creating a new file
leading to confusion and flailing by the agent. This will create parent
directories automatically when absent.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-22 19:45:17 -04:00
chunterb
750d97e8ad feat: add openai model info configuration (#551)
In reference to [Issue 548](https://github.com/openai/codex/issues/548)
- part 1.
2025-04-22 17:31:25 -04:00
Fouad Matin
12bc2dcc4e bump(version): 0.1.2504221401 (#559)
## `0.1.2504221401`

### 🚀 Features

- Show actionable errors when api keys are missing (#523)
- Add CLI `--version` flag (#492)

### 🐛 Bug Fixes

- Agent loop for ZDR (`disableResponseStorage`) (#543)
- Fix relative `workdir` check for `apply_patch` (#556)
- Minimal mid-stream #429 retry loop using existing back-off (#506)
- Inconsistent usage of base URL and API key (#507)
- Remove requirement for api key for ollama (#546)
- Support `[provider]_BASE_URL` (#542)
2025-04-22 14:18:04 -07:00
Nick Carchedi
dc096302e5 fix typo in prompt (#558) 2025-04-22 17:15:28 -04:00
Michael Bolin
7c1f2d7deb when a shell tool call invokes apply_patch, resolve relative paths against workdir, if specified (#556)
Previously, we were ignoring the `workdir` field in an `ExecInput` when
running it through `canAutoApprove()`. For ordinary `exec()` calls, that
was sufficient, but for `apply_patch`, we need the `workdir` to resolve
relative paths in the `apply_patch` argument so that we can check them
in `isPathConstrainedTowritablePaths()`.

Likewise, we also need the workdir when running `execApplyPatch()`
because the paths need to be resolved again.

Ideally, the `ApplyPatchCommand` returned by `canAutoApprove()` would
not be a simple `patch: string`, but the parsed patch with all of the
paths resolved, in which case `execApplyPatch()` could expect absolute
paths and would not need `workdir`.
2025-04-22 14:07:47 -07:00
Fouad Matin
a30e79b768 fix: agent loop for disable response storage (#543)
- Fixes post-merge of #506

---------

Co-authored-by: Ilan Bigio <ilan@openai.com>
2025-04-22 13:49:10 -07:00
Daniil Davydov
f99c9080fd fix: support [provider]_BASE_URL (#542)
Resolved issue where an OLLAMA_BASE_URL was not properly handled
(openai/codex#516).
2025-04-22 15:05:48 -04:00
moppywhip
549fc650c3 fix: remove requirement for api key for ollama (#546)
Fixes #540 
# Skip API key validation for Ollama provider

## Description
This PR modifies the CLI to not require an API key when using Ollama as
the provider

## Changes
- Modified the validation logic to skip API key checks for these
providers
- Updated the README to clarify that Ollama doesn't require an API key
2025-04-22 13:59:31 -04:00
Naveen Kumar Battula
fcd1d4bdf9 feat: show actionable errors when api keys are missing (#523)
Change errors on missing api key of other providers from
<img width="854" alt="image"
src="https://github.com/user-attachments/assets/f488a247-5040-4b02-92d6-90a2204419ff"
/>
(missing deepseek key but still throws error for openai)
to
<img width="854" alt="image"
src="https://github.com/user-attachments/assets/8333d24a-91f8-4ba8-9a51-ed22a7e8a074"
/>
This should help new users figure out the issue easier and go to the
right place to get api keys

OpenAI key missing would popup with the right link
<img width="854" alt="image"
src="https://github.com/user-attachments/assets/0ecc9320-380f-425c-972e-4312bf610955"
/>
2025-04-22 12:55:08 -04:00
Michael Bolin
94d5408875 add instructions for connecting to a visual debugger under Contributing (#496)
While here, I also moved the Nix stuff to the end of the
**Contributing** section and replaced some examples with `npm` to use
`pnpm`.
2025-04-22 09:43:10 -07:00
Michael Bolin
9b06fb48a7 add check to ensure ToC in README.md matches headings in the file (#541)
This introduces a Python script (written by Codex!) to verify that the
table of contents in the root `README.md` matches the headings. Like
`scripts/asciicheck.py` in https://github.com/openai/codex/pull/513, it
reports differences by default (and exits non-zero if there are any) and
also has a `--fix` option to synchronize the ToC with the headings.

This will be enforced by CI and the changes to `README.md` in this PR
were generated by the script, so you can see that our ToC was missing
some entries prior to this PR.
2025-04-22 09:38:12 -07:00
narenoai
dd330646d2 feat: add CLI –version flag (#492)
Adds a new flag to cli `--version` that prints the current version and
exits

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-22 12:28:21 -04:00
Scott Leibrand
ee6e1765fa agent-loop: minimal mid-stream #429 retry loop using existing back-off (#506)
As requested by @tibo-openai at
https://github.com/openai/codex/pull/357#issuecomment-2816554203, this
attempts a more minimal implementation of #357 that preserves as much as
possible of the existing code's exponential backoff logic.

Adds a small retry wrapper around the streaming for‑await loop so that
HTTP 429s which occur *after* the stream has started no longer crash the
CLI.

Highlights
• Re‑uses existing RATE_LIMIT_RETRY_WAIT_MS constant and 5‑attempt
limit.
• Exponential back‑off identical to initial request handling. 

This comment is probably more useful here in the PR:
// The OpenAI SDK may raise a 429 (rate‑limit) *after* the stream has
// started. Prior logic already retries the initial `responses.create`
        // call, but we need to add equivalent resilience for mid‑stream
        // failures.  We keep the implementation minimal by wrapping the
// existing `for‑await` loop in a small retry‑for‑loop that re‑creates
        // the stream with exponential back‑off.
2025-04-22 11:02:10 -04:00
Gabriel Bianconi
98a22273d9 fix: inconsistent usage of base URL and API key (#507)
A recent commit introduced the ability to use third-party model
providers. (Really appreciate it!)

However, the usage is inconsistent: some pieces of code use the custom
providers, whereas others still have the old behavior. Additionally,
`OPENAI_BASE_URL` is now being disregarded when it shouldn't be.

This PR normalizes the usage to `getApiKey` and `getBaseUrl`, and
enables the use of `OPENAI_BASE_URL` if present.

---------

Co-authored-by: Gabriel Bianconi <GabrielBianconi@users.noreply.github.com>
2025-04-22 10:51:26 -04:00
Thomas
d78f77edb7 fix(agent-loop): update required properties to include workdir and ti… (#530)
Without this I get an issue running codex it in a docker container. I
receive:

```
{
    "answer": "{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"\\\"Say hello world\\\"\"}],\"type\":\"message\"}\n{\"id\":\"error-1745325184914\",\"type\":\"message\",\"role\":\"system\",\"content\":[{\"type\":\"input_text\",\"text\":\"⚠️  OpenAI rejected the request (request ID: req_f9027b59ebbce00061e9cd2dbb2d529a). Error details: Status: 400, Code: invalid_function_parameters, Type: invalid_request_error, Message: 400 Invalid schema for function 'shell': In context=(), 'required' is required to be supplied and to be an array including every key in properties. Missing 'workdir'.. Please verify your settings and try again.\"}]}\n"
}
```

This fix makes it work.
2025-04-22 10:32:36 -04:00
Michael Bolin
c00ae2dcc1 Enforce ASCII in README.md (#513)
This all started because I was going to write a script to autogenerate
the Table of Contents in the root `README.md`, but I noticed that the
`href` for the "Why Codex?" heading was `#whycodex` instead of
`#why-codex`. This piqued my curiosity and it turned out that the space
in "Why Codex?" was not an ASCII space but **U+00A0**, a non-breaking
space, and so GitHub ignored it when generating the `href` for the
heading.

This also meant that when I did a text search for `why codex` in the
`README.md` in VS Code, the "Why Codex" heading did not match because of
the presence of **U+00A0**.

In short, these types of Unicode characters seem like a hazard, so I
decided to introduce this script to flag them, and if desired, to
replace them with "good enough" ASCII equivalents. For now, this only
applies to the root `README.md` file, but I think we should ultimately
apply this across our source code, as well, as we seem to have quite a
lot of non-ASCII Unicode and it's probably going to cause `rg` to miss
things.

Contributions of this PR:

* `./scripts/asciicheck.py`, which takes a list of filepaths and returns
non-zero if any of them contain non-ASCII characters. (Currently, there
is one exception for  aka **U+2728**, though I would like to default to
an empty allowlist and then require all exceptions to be specified as
flags.)
* A `--fix` option that will attempt to rewrite files with violations
using a equivalents from a hardcoded substitution list.
* An update to `ci.yml` to verify `./scripts/asciicheck.py README.md`
succeeds.
* A cleanup of `README.md` using the `--fix` option as well as some
editorial decisions on my part.
* I tried to update the `href`s in the Table of Contents to reflect the
changes in the heading titles. (TIL that if a heading has a character
like `&` surrounded by spaces, it becomes `--` in the generated `href`.)
2025-04-22 10:07:40 -04:00
Fouad Matin
2cb8355968 bump(version): 0.1.2504220136 (#518)
## `0.1.2504220136`

### 🚀 Features

- Add support for ZDR orgs (#481)
- Include fractional portion of chunk that exceeds stdout/stderr limit
(#497)
2025-04-22 01:45:30 -07:00
Fouad Matin
9f5ccbb618 feat: add support for ZDR orgs (#481)
- Add `store: boolean` to `AgentLoop` to enable client-side storage of
response items
- Add `--disable-response-storage` arg + `disableResponseStorage` config
2025-04-22 01:30:16 -07:00
Michael Bolin
3eba86a553 include fractional portion of chunk that exceeds stdout/stderr limit (#497)
I saw cases where the first chunk of output from `ls -R` could be large
enough to exceed `MAX_OUTPUT_BYTES` or `MAX_OUTPUT_LINES`, in which case
the loop would exit early in `createTruncatingCollector()` such that
nothing was appended to the `chunks` array. As a result, the reported
`stdout` of `ls -R` would be empty.

I asked Codex to add logic to handle this edge case and write a unit
test. I used this as my test:

```
./codex-cli/dist/cli.js -q 'what is the output of `ls -R`'
```

now it appears to include a ton of stuff whereas before this change, I
saw:

```
{"type":"function_call_output","call_id":"call_a2QhVt7HRJYKjb3dIc8w1aBB","output":"{\"output\":\"\\n\\n[Output truncated: too many lines or bytes]\",\"metadata\":{\"exit_code\":0,\"duration_seconds\":0.5}}"}
```
2025-04-21 19:06:03 -07:00
Fouad Matin
99ed27ad1b bump(version): 0.1.2504211509 (#493)
## `0.1.2504211509`

### 🚀 Features

- Support multiple providers via Responses-Completion transformation
(#247)
- Add user-defined safe commands configuration and approval logic #380
(#386)
- Allow switching approval modes when prompted to approve an
edit/command (#400)
- Add support for `/diff` command autocomplete in TerminalChatInput
(#431)
- Auto-open model selector if user selects deprecated model (#427)
- Read approvalMode from config file (#298)
- `/diff` command to view git diff (#426)
- Tab completions for file paths (#279)
- Add /command autocomplete (#317)
- Allow multi-line input (#438)

### 🐛 Bug Fixes

- `full-auto` support in quiet mode (#374)
- Enable shell option for child process execution (#391)
- Configure husky and lint-staged for pnpm monorepo (#384)
- Command pipe execution by improving shell detection (#437)
- Name of the file not matching the name of the component (#354)
- Allow proper exit from new Switch approval mode dialog (#453)
- Ensure /clear resets context and exclude system messages from
approximateTokenUsed count (#443)
- `/clear` now clears terminal screen and resets context left indicator
(#425)
- Correct fish completion function name in CLI script (#485)
- Auto-open model-selector when model is not found (#448)
- Remove unnecessary isLoggingEnabled() checks (#420)
- Improve test reliability for `raw-exec` (#434)
- Unintended tear down of agent loop (#483)
- Remove extraneous type casts (#462)
2025-04-21 15:13:33 -07:00
Fouad Matin
0e9d75657b update: readme (#491) 2025-04-21 15:06:03 -07:00
Daniel Nakov
e7a3eec942 docs: Add note about non-openai providers; add --provider cli flag to the help (#484) 2025-04-21 14:53:09 -07:00
Mitchell Kutchuk
09f0ae3899 fix: unintended tear down of agent loop (#483)
fixes #465
2025-04-21 15:01:09 -04:00
Benny Yen
f72cfd7ef3 fix: correct fish completion function name in CLI script (#485)
Missing an underscore.

fish function:
https://github.com/fish-shell/fish-shell/blob/master/share/functions/__fish_complete_path.fish

fixes https://github.com/openai/codex/issues/469
2025-04-21 14:45:49 -04:00
Michael Bolin
12ec57b330 do not auto-approve the find command if it contains options that write files or spawn commands (#482)
Updates `isSafeCommand()` so that an invocation of `find` is not
auto-approved if it contains any of: `-exec`, `-execdir`, `-ok`,
`-okdir`, `-delete`, `-fls`, `-fprint`, `-fprint0`, `-fprintf`.
2025-04-21 10:29:58 -07:00
Jon Church
7346f4388e chore: drop src from publish (#474)
Publish shouldn't need the source files published along with the
distributable bin.

`src` is being shipped to the registry rn:
https://www.npmjs.com/package/@openai/codex?activeTab=code

You can verify that the src is not needed by packing the project
manually after removing src from the files:

```sh
# from the codex-cli dir
rm -rf dist # just for hygiene
pnpm run build
pnpm pack

mkdir /tmp/codex-tar-test
mv openai-codex-0.1.2504181820.tgz /tmp/codex-tar-test
cd /tmp/codex-tar-test

pnpm init
pnpm add ./openai-codex-0.1.2504181820.tgz /tmp/codex-tar-test
pnpm exec codex --full-auto "run a bash -c command to echo hello world"
```

The cli is operational

> noticed this when checking the screenshot included in
https://github.com/openai/codex/pull/461
2025-04-21 09:56:00 -07:00
Michael Bolin
d36d295a1a revert #386 due to unsafe shell command parsing (#478)
Reverts https://github.com/openai/codex/pull/386 because:

* The parsing logic for shell commands was unsafe (`split(/\s+/)`
instead of something like `shell-quote`)
* We have a different plan for supporting auto-approved commands.
2025-04-21 12:52:11 -04:00
nerdielol
797eba4930 fix: /clear now clears terminal screen and resets context left indicator (#425)
## What does this PR do?
* Implements the full `/clear` command in **codex‑cli**:
  * Resets chat history **and** wipes the terminal screen.
  * Shows a single system message: `Context cleared`.
* Adds comprehensive unit tests for the new behaviour.

## Why is it needed?
* Fixes user‑reported bugs:  
  * **#395**  
  * **#405**

## How is it implemented?
* **Code** – Adds `process.stdout.write('\x1b[3J\x1b[H\x1b[2J')` in
`terminal.tsx`. Removed reference to `prev` in `
        setItems((prev) => [
          ...prev,
` in `terminal-chat-new-input.tsx` & `terminal-chat-input.tsx`.

## CI / QA
All commands pass locally:
```bash
pnpm test      # green
pnpm run lint  # green
pnpm run typecheck  # zero TS errors
```

## Results



https://github.com/user-attachments/assets/11dcf05c-e054-495a-8ecb-ac6ef21a9da4

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-21 12:39:46 -04:00
Jon Church
5b19451770 chore(build): cleanup dist before build (#477)
Another one that I noticed.

The dist structure is very simple rn, so unlikely to run into orphaned
files as you're emitting a single built artifact which wil be
overwritten on build, but I always prefer to do clean builds as
"hygiene".

I had a dirty dist personally after local development and testing some
things, as an example.

Alternatives could be to create a `clean` script with cross platform
`rimraf dist`
2025-04-21 12:35:25 -04:00
Thibault Sottiaux
3c4f1fea9b chore: consolidate model utils and drive-by cleanups (#476)
Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-21 12:33:57 -04:00
Thibault Sottiaux
dc276999a9 chore: improve storage/ implementation; use log(...) consistently (#473)
This PR tidies up primitives under storage/.

**Noop changes:**

* Promote logger implementation to top-level utility outside of agent/
* Use logger within storage primitives
* Cleanup doc strings and comments

**Functional changes:**

* Increase command history size to 10_000
* Remove unnecessary debounce implementation and ensure a session ID is
created only once per agent loop

---------

Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-21 09:51:34 -04:00
Aaron Casanova
8f1ea7fa85 fix: remove extraneous type casts (#462) 2025-04-21 00:00:56 -07:00
Benny Yen
3e71c87708 refactor(updates): fetch version from registry instead of npm CLI to support multiple managers (#446)
## Background  
Addressing feedback from
https://github.com/openai/codex/pull/333#discussion_r2050893224, this PR
adds support for Bun alongside npm, pnpm while keeping the code simple.

## Summary  
The update‑check flow is refactored to use a direct registry lookup
(`fast-npm-meta` + `semver`) instead of shelling out to `npm outdated`,
and adds a lightweight installer‑detection mechanism that:

1. Checks if the invoked script lives under a known global‑bin directory
(npm, pnpm, or bun)
2. If not, falls back to local detection via `getUserAgent()` (the
`package‑manager‑detector` library)

## What’s Changed  
- **Registry‑based version check**  
- Replace `execFile("npm", ["outdated"])` with `getLatestVersion()` and
`semver.gt()`
- **Multi‑manager support**  
- New `renderUpdateCommand` handles update commands for `npm`, `pnpm`,
and `bun`.
  - Detect global installer first via `detectInstallerByPath()`  
  - Fallback to local detection via `getUserAgent()`  
- **Module cleanup**  
- Extract `detectInstallerByPath` into
`utils/package-manager-detector.ts`
- Remove legacy `checkOutdated`, `getNPMCommandPath`, and child‑process
JSON parsing
- **Flow improvements in `checkForUpdates`**  
  1. Short‑circuit by `UPDATE_CHECK_FREQUENCY`  
  3. Fetch & compare versions  
  4. Persist new timestamp immediately  
  5. Render & display styled box only when an update exists  
- **Maintain simplicity**
- All multi‑manager logic lives in one small helper and a concise lookup
rather than a complex adapter hierarchy
- Core `checkForUpdates` remains a single, easy‑to‑follow async function
- **Dependencies added**  
- `fast-npm-meta`, `semver`, `package-manager-detector`, `@types/semver`

## Considerations
If we decide to drop the interactive update‑message (`npm install -g
@openai/codex`) rendering altogether, we could remove most of the
installer‑detection code and dependencies, which would simplify the
codebase further but result in a less friendly UX.

## Preview

* npm

![refactor-update-check-flow-npm](https://github.com/user-attachments/assets/57320114-3fb6-4985-8780-3388a1d1ec85)

* bun

![refactor-update-check-flow-bun](https://github.com/user-attachments/assets/d93bf0ae-a687-412a-ab92-581b4f967307)

## Simple Flow Chart

```mermaid
flowchart TD
  A(Start) --> B[Read state]
  B --> C{Recent check?}
  C -- Yes --> Z[End]
  C -- No --> D[Fetch latest version]
  D --> E[Save check time]
  E --> F{Version data OK?}
  F -- No --> Z
  F -- Yes --> G{Update available?}
  G -- No --> Z
  G -- Yes --> H{Global install?}
  H -- Yes --> I[Select global manager]
  H -- No --> K{Local install?}
  K -- No --> Z
  K -- Yes --> L[Select local manager]
  I & L --> M[Render update message]
  M --> N[Format with boxen]
  N --> O[Print update]
  O --> Z
```
2025-04-21 00:00:20 -07:00
Abdelrhman Kamal Mahmoud Ali Slim
655564f25d fix: auto-open model-selector when model is not found (#448)
Change the check from checking if the model has been deprecated to check
if the model_not_found


https://github.com/user-attachments/assets/ad0f7daf-5eb4-4e4b-89e5-04240044c64f
2025-04-20 23:56:20 -07:00
Aaron Casanova
ee3a9bc14b Remove README.md and bin from package.json#files field (#461)
This PR removes always included files and folders from the
[`package.json#files`
field](https://docs.npmjs.com/cli/v11/configuring-npm/package-json#files):

> Certain files are always included, regardless of settings:
> - package.json
> - README
> - LICENSE / LICENCE
> - The file in the "main" field
> - The file(s) in the "bin" field

Validated by running `pnpm i && cd codex-cli && pnpm build && pnpm
release:readme && pnpm pack` and confirming both the `README.md` file
and `bin` directory are still included in the tarball:

<img width="227" alt="image"
src="https://github.com/user-attachments/assets/ecd90a07-73c7-4940-8c83-cb1d51dfcf96"
/>
2025-04-20 23:54:27 -07:00
Aiden Cline
ee7ce5b601 feat: tab completions for file paths (#279)
Made a PR as was requested in the #113
2025-04-20 22:34:27 -07:00
Jordan Docherty
f6b12aa994 refactor(history-overlay): split into modular functions & add tests (fixes #402) (#403)
## What
This PR targets #402 and refactors the `history-overlay.tsx`component to
reduce cognitive complexity by splitting the `buildLists` function into
smaller, focused helper functions. It also adds comprehensive test
coverage to ensure the functionality remains intact.

## Why
The original `buildLists` function had high cognitive complexity due to
multiple nested conditionals, complex string manipulation, and mixed
responsibilities. This refactor makes the code more maintainable and
easier to understand while preserving all existing functionality.

## How
- Split `buildLists` into focused helper functions
- Added comprehensive test coverage for all functionality
- Maintained existing behavior and keyboard interactions
- Improved code organization and readability

## Testing
All tests pass, including:
- Command mode functionality
- File mode functionality
- Keyboard interactions
- Error handling
2025-04-20 22:27:06 -07:00
Abdelrhman Kamal Mahmoud Ali Slim
f97557f59f refactor(component): rename component to match its filename (#432)
Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-20 22:21:49 -07:00
Scott Leibrand
e3c8ce49ca fix: allow proper exit from new Switch approval mode dialog (#453)
As described in
https://github.com/openai/codex/issues/392#issuecomment-2817090022
introduced by #400

The testing I'd done worked correctly because I was using the (s)
shortcut, but selecting the same option using arrow‑key → Enter on
“Switch approval mode” was preventing the user from subsequently exiting
the Switch approval mode dialog, requiring a ^C to quit codex entirely.
With this fix, both entry methods work correctly in my testing.

Per codex:

Issue

- When you navigated down (↓) to “Switch approval mode (s)” in the Shell
Command review dialog and pressed Enter, the ApprovalModeOverlay would
open—but because the underlying `TerminalChatCommandReview` component
stayed mounted (albeit disabled), its own Ink input handlers immediately
re‑captured the same key events and re‑opened the overlay as soon as you
hit Esc or Enter again. In practice this made it impossible to exit the
submenu.

Root cause

- We only disabled the SelectInput via `isDisabled`, but never fully
unmounted the review UI when an overlay was shown, so its `useInput` and
`<Select>` hooks were still active and “stealing” keys.

Fix

- In `terminal-chat.tsx` we now only render `<TerminalChatInput>` (and
by extension `TerminalChatCommandReview`) when `overlayMode === "none"`.
That unmounts all of its key handlers whenever any overlay (history,
model, approval, help, diff) is open, so no input leaks through.

Files changed

- **src/components/chat/terminal-chat.tsx**: Wrapped the entire
`<TerminalChatInput>` block in `overlayMode === "none" && agent`

With that in place, arrow‑key → Enter on “Switch approval mode”
correctly opens the overlay, and then you can use Enter/Esc inside the
overlay without getting stuck or immediately re‑opening it.
2025-04-20 22:19:53 -07:00
Brayden Moon
8dd1125681 fix: command pipe execution by improving shell detection (#437)
## Description
This PR fixes Issue #421 where commands with pipes (e.g., `grep -R ...
-n | head -n 20`) were failing to execute properly after PR #391 was
merged.

## Changes
- Modified the `requiresShell` function to only enable shell mode when
the command is a single string containing shell operators
- Added logic to handle the case where shell operators are passed as
separate arguments
- Added comprehensive tests to verify the fix

## Root Cause
The issue was that the `requiresShell` function was detecting shell
operators like `|` even when they were passed as separate arguments,
which caused the command to be executed with `shell: true`
unnecessarily. This was causing syntax errors when running commands with
pipes.

## Testing
- Added unit tests to verify the fix
- Manually tested with real commands using pipes
- Ensured all existing tests pass

Fixes #421
2025-04-20 21:11:19 -07:00
Daniel Nakov
eafbc75612 feat: support multiple providers via Responses-Completion transformation (#247)
https://github.com/user-attachments/assets/9ecb51be-fa65-4e99-8512-abb898dda569

Implemented it as a transformation between Responses API and Completion
API so that it supports existing providers that implement the Completion
API and minimizes the changes needed to the codex repo.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
Co-authored-by: Fouad Matin <169186268+fouad-openai@users.noreply.github.com>
Co-authored-by: Fouad Matin <fouad@openai.com>
2025-04-20 20:59:34 -07:00
Jordan Docherty
693bd59ecc fix(raw-exec-process-group): improve test reliability (#434)
This PR improves the reliability of `raw-exec-process-group.test`,
addressing [#415](https://github.com/openai/codex/issues/415)

Before: The test would fail sporadically in CI because it checked for
process termination immediately after abort, without accounting for the
time it takes for processes to fully terminate.

Now: We've added a robust `ensureProcessGone` helper that:
- Polls the process status with a 500ms timeout
- Retries every 50ms if the process is still alive
- Provides clear error messages if termination takes too long

We now wait for the child process to fully exit after sending abort
signals, instead of assuming instant death, fixing flakiness caused by
asynchronous process termination.

Changes:
- Added `ensureProcessGone` helper function with retry logic
- Improved error handling and timeout management

See [this bash
demo](https://gist.github.com/jdocherty/a84dbca2fbf7b47e5f95c87a07034ae8)
for a minimal reproduction of why process death is asynchronous and why
the test needs to retry after aborting.
2025-04-20 12:21:02 -07:00
Michael Bolin
b554b522f7 fix: remove unnecessary isLoggingEnabled() checks (#420)
It appears that use of `isLoggingEnabled()` was erroneously copypasta'd
in many places. This PR updates its docstring to clarify that should
only be used to avoid constructing a potentially expensive docstring.
With this change, the only function that merits/uses this check is
`execCommand()`.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/420).
* #423
* __->__ #420
* #419
2025-04-20 09:58:06 -07:00
Abdelrhman Kamal Mahmoud Ali Slim
81cf47e591 feat: auto-open model selector if user selects deprecated model (#427)
https://github.com/user-attachments/assets/d254dff6-f1f9-4492-9dfd-d185c38d3a75
2025-04-20 09:51:49 -07:00
Michael Bolin
e372e4667b Make it so CONFIG_DIR is not in the list of writable roots by default (#419)
To play it safe, let's keep `CONFIG_DIR` out of the default list of
writable roots.

This also fixes an issue where `execWithSeatbelt()` was modifying
`writableRoots` instead of creating a new array.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/419).
* #423
* #420
* __->__ #419
2025-04-20 09:37:07 -07:00
Abdelrhman Kamal Mahmoud Ali Slim
425430debb fix(cli): ensure /clear resets context and exclude system messages from approximateTokenUsed count (#443)
https://github.com/user-attachments/assets/58b8f261-a359-4cd8-8c84-90d8d91a5592
2025-04-20 08:52:14 -07:00
Brayden Moon
6d6ca454cd feat: allow multi-line input (#438)
## Description
This PR implements multi-line input support for Codex when it asks for
user feedback (Issue #344). Users can now use Shift+Enter to add new
lines in their responses, making it easier to provide formatted code
snippets, lists, or other structured content.

## Changes
- Replace the single-line TextInput component with the
MultilineTextEditor component in terminal-chat-input.tsx
- Add support for Shift+Enter to create new lines
- Update key handling logic to properly handle history navigation in a
multi-line context
- Add reference to the editor to access cursor position information
- Update help text to inform users about the Shift+Enter functionality
- Add tests for the new functionality

## Testing
- Added new test file (terminal-chat-input-multiline.test.tsx) to test
the multi-line input functionality
- All existing tests continue to pass
- Manually tested the feature to ensure it works as expected

## Fixes
Closes #344

## Screenshots
N/A

## Additional Notes
This implementation maintains backward compatibility while adding the
requested multi-line input functionality. The UI remains clean and
intuitive, with a simple hint about using Shift+Enter for new lines.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-20 08:51:38 -07:00
Thomas
fc1e45636e feat: add support for /diff command autocomplete in TerminalChatInput (#431)
It's not working without this
2025-04-19 20:01:40 -07:00
Michael Bolin
63c99e7d82 use spawn instead of exec to avoid injection vulnerability (#416)
https://github.com/openai/codex/pull/160 introduced a call to `exec()`
that takes a format string as an argument, but it is not clear that the
expansions within the format string are escaped safely. As written, it
is possible a carefully crafted command (e.g., if `cwd` were `"; && rm
-rf` or something...) could run arbitrary code.

Moving to `spawn()` makes this a bit better, as now at least `spawn()`
itself won't run an arbitrary process, though I suppose `osascript`
itself still could if the value passed to `-e` were abused. I'm not
clear on the escaping rules for AppleScript to ensure that `safePreview`
and `cwd` are injected safely.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/416).
* #423
* #420
* #419
* __->__ #416
2025-04-19 18:29:00 -07:00
Tomas Cupr
a3889f92e4 fix: full-auto support in quiet mode (#374)
Fixes https://github.com/openai/codex/issues/292

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-19 17:00:33 -07:00
Fouad Matin
b3b195351e feat: /diff command to view git diff (#426)
Adds `/diff` command to view git diff
2025-04-19 16:23:27 -07:00
Michael Bolin
419f085cc4 re-enable Prettier check for codex-cli in CI (#417)
This check was lost in https://github.com/openai/codex/pull/287. Both
the root folder and `codex-cli/` have their own `pnpm format` commands
that check the formatting of different things.

Also ran `pnpm format:fix` to fix the formatting violations that got in
while this was disabled in CI.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/417).
* #420
* #419
* #416
* __->__ #417
2025-04-19 11:22:45 -07:00
Thomas
081786eaa6 feat: add /command autocomplete (#317)
Add interactive slash‑command autocomplete & navigation in chat input

    Description
This PR enhances the chat input component by adding first‑class support
for slash commands (/help, /clear, /compact, etc.)
    with:

* **Live filtering:** As soon as the user types leading `/`, a list of
matching commands is shown below the prompt.
* **Arrow‑key navigation:** Up/Down arrows cycle through suggestions.
* **Enter to autocomplete:** Pressing Enter on a partial command will
fill it (without submitting) so you can add
    arguments or simply press Enter again to execute.
* **Type‑safe registry:** A new `slash‑commands.ts` file declares all
supported commands in one place, along with
    TypeScript types to prevent drift.
* **Validation:** Only registered commands will ever autocomplete or be
suggested; unknown single‑word slash inputs still
    show an “Invalid command” system message.
        * **Automated tests:**
            * Unit tests for the command registry and prefix filtering

            * Existing tests continue passing with no regressions

    Motivation
Slash commands provide a quick, discoverable way to control the agent
(clearing history, compacting context, opening overlays,
etc.). Before, users had to memorize the exact command or rely on the
generic /help list—autocomplete makes them far more
    accessible and reduces typos.

    Changes

* `src/utils/slash‑commands.ts` – defines `SlashCommand` and exports a
flat list of supported commands + descriptions
        * `terminal‑chat‑input.tsx`
            * Import and type the command registry

* Render filtered suggestions under the prompt when input starts with
`/`

* Hook into `useInput` to handle Up/Down and Enter for selection & fill

* Flag to swallow the first Enter (autocomplete) and only submit on the
next
* Updated tests in `tests/slash‑commands.test.ts` to cover registry
contents and filtering logic
        * Removed old JS version and fixed stray `@ts‑expect‑error`

    How to test locally

        1. Type `/` in the prompt—you should see matching commands.
2. Use arrows to move the highlight, press Enter to fill, then Enter
again to execute.
3. Run the full test suite (`npm test`) to verify no regressions.

    Notes

* Future work could include fuzzy matching, paging long lists, or more
visual styling.
* This change is purely additive and does not affect non‑slash inputs or
existing slash handlers.

---------

Co-authored-by: Fouad Matin <169186268+fouad-openai@users.noreply.github.com>
Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-19 07:25:46 -07:00
John Gardner
965420cfc5 feat: read approvalMode from config file (#298)
This PR implements support for reading the approvalMode setting from the
user's config file (`~/.codex/config.json` or `~/.codex/config.yaml`),
allowing users to set a persistent default approval mode without needing
to specify command-line flags for each session.

Changes:
- Added approvalMode to the AppConfig type in config.ts
- Updated loadConfig() to read the approval mode from the config file
- Modified saveConfig() to persist the approval mode setting
- Updated CLI logic to respect the config-defined approval mode (while
maintaining CLI flag priority)
- Added comprehensive tests for approval mode config functionality
- Updated README to document the new config option in both YAML and JSON
formats
- additions to `.gitignore` for other CLI tools

Motivation:
As a user who regularly works with CLI-tools, I found it odd to have to
alias this with the command flags I wanted when `approvalMode` simply
wasn't being parsed even though it was an optional prop in `config.ts`.
This change allows me (and other users) to set the preference once in
the config file, streamlining daily usage while maintaining the ability
to override via command-line flags when needed.

Testing:
I've added a new test case loads and saves approvalMode correctly that
verifies:
- Reading the approvalMode from the config file works correctly
- Saving the approvalMode to the config file works as expected
- The value persists through load/save operations

All tests related to the implementation are passing.
2025-04-19 07:25:25 -07:00
Suyash-K
b37b257e63 gracefully handle SSE parse errors and suppress raw parser code (#367)
Closes #187
Closes #358

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-19 07:24:29 -07:00
Abdelrhman Kamal Mahmoud Ali Slim
f3cab736b4 fix: name of the file not matching the name of the component (#354)
before

![image](https://github.com/user-attachments/assets/e47595bc-8b5b-470d-8cca-1d4c4afbf802)
after

![image](https://github.com/user-attachments/assets/c04bc384-534e-44f0-9917-08a15f7280dc)

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-19 07:23:02 -07:00
Scott Leibrand
9eeb78e54f feat: allow switching approval modes when prompted to approve an edit/command (#400)
Implements https://github.com/openai/codex/issues/392

When the user is in suggest or auto-edit mode and gets an approval
request, they now have an option in the `Shell Command` dialog to:
`Switch approval mode (v)`

That option brings up the standard `Switch approval mode` dialog,
allowing the user to switch into the desired mode, then drops them back
to the `Shell Command` dialog's `Allow command?` prompt, allowing them
to approve the current command and let the agent continue doing the rest
of what it was doing without interruption.
```
╭────────────────────────────────────────────────────────
│Shell Command
│                          
│$ apply_patch << 'PATCH'    
│*** Begin Patch                      
│*** Update File: foo.txt          
│@@ -1 +1 @@                         
│-foo                                          
│+bar                                         
│*** End Patch                         
│PATCH                                    
│                                                
│                                                
│Allow command?                   
│                                                
│    Yes (y)                                
│    Explain this command (x) 
│    Edit or give feedback (e)  
│    Switch approval mode (v)
│    No, and keep going (n)    
│    No, and stop for now (esc)
╰────────────────────────────────────────────────────────╭────────────────────────────────────────────────────────
│ Switch approval mode      
│ Current mode: suggest  
│                                          
│                                          
│                                          
│ ❯ suggest                        
│   auto-edit                       
│   full-auto                        
│ type to search · enter to confirm · esc to cancel 
╰────────────────────────────────────────────────────────
```
2025-04-19 07:21:19 -07:00
Alpha Diop
6c7fbc7b94 fix: configure husky and lint-staged for pnpm monorepo (#384)
# Improve Developer Experience with Husky and lint-staged for pnpm
Monorepo

## Summary
This PR enhances the developer experience by configuring Husky and
lint-staged to work properly with our pnpm monorepo structure. It
centralizes Git hooks at the root level and ensures consistent code
quality across the project.

## Changes
- Centralized Husky and lint-staged configuration at the monorepo root
- Added pre-commit hook that runs lint-staged to enforce code quality
- Configured lint-staged to:
  - Format JSON, MD, and YAML files with Prettier
  - Lint and typecheck TypeScript files before commits
- Fixed release script in codex-cli package.json (changed "pmpm" to "npm
publish")
- Removed duplicate Husky and lint-staged configurations from codex-cli
package.json

## Benefits
- **Consistent Code Quality**: Ensures all committed code meets project
standards
- **Automated Formatting**: Automatically formats code during commits
- **Early Error Detection**: Catches type errors and lint issues before
they're committed
- **Centralized Configuration**: Easier to maintain and update in one
place
- **Improved Collaboration**: Ensures consistent code style across the
team

## Future Improvements
We could further enhance this setup by
**Commit Message Validation**: Add commitlint to enforce conventional
commit messages

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-19 07:18:36 -07:00
Robbie Hammond
8e2760e83d Add fallback text for missing images (#397)
# What?
* When a prompt references an image path that doesn’t exist, replace it
with
  ```[missing image: <path>]``` instead of throwing an ENOENT.
* Adds a few unit tests for input-utils as there weren't any beforehand.

# Why?
Right now if you enter an invalid image path (e.g. it doesn't exist),
codex immediately crashes with a ENOENT error like so:
```
Error: ENOENT: no such file or directory, open 'test.png'
   ...
 {
  errno: -2,
  code: 'ENOENT',
  syscall: 'open',
  path: 'test.png'
}
```
This aborts the entire session. A soft fallback lets the rest of the
input continue.

# How?
Wraps the image encoding + inputItem content pushing in a try-catch. 

This is a minimal patch to avoid completely crashing — future work could
surface a warning to the user when this happens, or something to that
effect.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-18 22:55:24 -07:00
Shuto Otaki
b46b596e5f fix: enable shell option for child process execution (#391)
## Changes

- Added a `requiresShell` function to detect when a command contains
shell operators
- In the `exec` function, enabled the `shell: true` option if shell
operators are present

## Why This Is Necessary

See the discussion in this issue comment:  
https://github.com/openai/codex/issues/320#issuecomment-2816528014

## Code Explanation

The `requiresShell` function parses the command arguments and checks for
any shell‑specific operators. If it finds shell operators, it adds the
`shell: true` option when running the command so that it’s executed
through a shell interpreter.
2025-04-18 22:42:19 -07:00
autotaker
ca7ab76569 feat: add user-defined safe commands configuration and approval logic #380 (#386)
This pull request adds a feature that allows users to configure
auto-approved commands via a `safeCommands` array in the configuration
file.

## Related Issue
#380 

## Changes
- Added loading and validation of the `safeCommands` array in
`src/utils/config.ts`
- Implemented auto-approval logic for commands matching `safeCommands`
prefixes in `src/approvals.ts`
- Added test cases in `src/tests/approvals.test.ts` to verify
`safeCommands` behavior
- Updated documentation with examples and explanations of the
configuration
2025-04-18 22:35:32 -07:00
Benny Yen
fd6f6c51c0 docs: update README to use pnpm commands (#390)
Since we migrated to `pnpm` in #287, this updates the README to reflect
that change.
Just a small cleanup to align the commands with the current setup.
2025-04-18 22:16:13 -07:00
salama-openai
1a8610cd9e feat: add flex mode option for cost savings (#372)
Adding in an option to turn on flex processing mode to reduce costs when
running the agent.

Bumped the openai typescript version to add the new feature.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-18 22:15:01 -07:00
Fouad Matin
6f2271e8cd bump(version): 0.1.2504181820 (#385) 2025-04-18 18:25:33 -07:00
Fouad Matin
aa32e22d4b fix: /bug report command, thinking indicator (#381)
- Fix `/bug` report command
- Fix thinking indicator
2025-04-18 18:13:34 -07:00
Jon Church
c40f4891d4 chore: update lockfile (#379)
Not 100% this isn't a me thing, but might be dirty state leftover from
the pnpm migration
2025-04-18 17:17:35 -07:00
Thibault Sottiaux
9d77d791e3 fix: include pnpm lock file (#377)
Signed-off-by: Thibault Sottiaux <tibo@openai.com>
2025-04-18 17:01:11 -07:00
Benny Yen
d61da89ed3 feat: notify when a newer version is available (#333)
**Summary**  
This change introduces a new startup check that notifies users if a
newer `@openai/codex` version is available. To avoid spamming, it writes
a small state file recording the last check time and will only re‑check
once every 24 hours.

**What’s Changed**  
- **New file** `src/utils/check-updates.ts`  
  - Runs `npm outdated --global @openai/codex`  
  - Reads/writes `codex-state.json` under `CONFIG_DIR`  
  - Limits checks to once per day (`UPDATE_CHECK_FREQUENCY = 24h`)  
- Uses `boxen` for a styled alert and `which` to locate the npm binary
- **Hooked into** `src/cli.tsx` entrypoint:
  ```ts
  import { checkForUpdates } from "./utils/check-updates";
  // …
  // after loading config
  await checkForUpdates().catch();
  ```
- **Dependencies**  
  - Added `boxen@^8.0.1`, `which@^5.0.0`, `@types/which@^3.0.4`  
- **Tests**  
  - Vitest suite under `tests/check-updates.test.ts`  
  - Snapshot in `__snapshots__/check-updates.test.ts.snap`  

**Motivation**  
Addresses issue #244. Users running a stale global install will now see
a friendly reminder—at most once per day—to upgrade and enjoy the latest
features.

**Test Plan**  
- `getNPMCommandPath()` resolves npm correctly  
- `checkOutdated()` parses `npm outdated` JSON  
- State file prevents repeat alerts within 24h  
- Boxen snapshot matches expected output  
- No console output when state indicates a recent check  

**Related Issue**  
try resolves #244


**Preview**
Prompt a pnpm‑style alert when outdated  

![outdated‑alert](https://github.com/user-attachments/assets/294dad45-d858-45d1-bf34-55e672ab883a)

Let me know if you’d tweak any of the messaging, throttle frequency,
placement in the startup flow, or anything else.

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-04-18 17:00:45 -07:00
Abdelrhman Kamal Mahmoud Ali Slim
d69a17ac49 Fix: Change file name to start with small letter instead of captial l… (#356) 2025-04-18 16:55:49 -07:00
BadPirate
bec3947058 Fix #371 Allow multiple containers on same machine (#373)
- Docker container name based on work  directory
- Centralize container removal logic
- Improve quoting for command arguments
- Ensure workdir is always set and normalized

Resolves: #371 

Signed-off-by: BadPirate <badpirate@gmail.com>

Signed-off-by: BadPirate <badpirate@gmail.com>
2025-04-18 16:48:07 -07:00
Alpha Diop
e2fe2572ba chore: migrate to pnpm for improved monorepo management (#287)
# Migrate to pnpm for improved monorepo management

## Summary
This PR migrates the Codex repository from npm to pnpm, providing faster
dependency installation, better disk space usage, and improved monorepo
management.

## Changes
- Added `pnpm-workspace.yaml` to define workspace packages
- Added `.npmrc` with optimal pnpm configuration
- Updated root package.json with workspace scripts
- Moved resolutions and overrides to the root package.json
- Updated scripts to use pnpm instead of npm
- Added documentation for the migration
- Updated GitHub Actions workflow for pnpm

## Benefits
- **Faster installations**: pnpm is significantly faster than npm
- **Disk space savings**: pnpm's content-addressable store avoids
duplication
- **Strict dependency management**: prevents phantom dependencies
- **Simplified monorepo management**: better workspace coordination
- **Preparation for Turborepo**: as discussed, this is the first step
before adding Turborepo

## Testing
- Verified that `pnpm install` works correctly
- Verified that `pnpm run build` completes successfully
- Ensured all existing functionality is preserved

## Documentation
Added a detailed migration guide in `PNPM_MIGRATION.md` explaining:
- Why we're migrating to pnpm
- How to use pnpm with this repository
- Common commands and workspace-specific commands
- Monorepo structure and configuration

## Next Steps
As discussed, once this change is stable, we can consider adding
Turborepo as a follow-up enhancement.
2025-04-18 16:25:15 -07:00
Jon Church
9a046dfcaa Revert "fix: canonicalize the writeable paths used in seatbelt policy… (#370)
This reverts commit 3356ac0aef.

related #330
2025-04-18 16:11:34 -07:00
Fouad Matin
8e2e77fafb feat: add /bug report command (#312)
Add `/bug` command for chat session
2025-04-18 14:09:35 -07:00
Prama
4acd7d8617 fix: Improper spawn of sh on Windows Powershell (#318)
# Fix CLI launcher on Windows by replacing `sh`-based entrypoint with
cross-platform Node script

## What's changed

* This PR attempts to replace the sh-based entry point with a node
script that works on all platforms including Windows Powershell and CMD

## Why 

* Previously, when installing Codex globally via `npm i -g
@openai/codex`, Windows resulted in a broken CLI issue due to the `ps1`
launcher trying to execute `sh.exe`.

* If users don't have Unix-style shell, running the command will fail as
seen below since `sh.exe` can't be found

* Output:
 ``` 
& : The term 'sh.exe' is not recognized as the name of a cmdlet,
function, script file, or operable program. Check the
spelling of the name, or if a path was included, verify that the path is
correct and try again.
At C:\Users\{user}\AppData\Roaming\npm\codex.ps1:24 char:7
+     & "sh$exe"  "$basedir/node_modules/@openai/codex/bin/codex" $args
+       ~~~~~~~~
+ CategoryInfo : ObjectNotFound: (sh.exe:String) [],
CommandNotFoundException
    + FullyQualifiedErrorId : CommandNotFoundException
```



## How
* By using a Node based entry point that resolves the path to the compiled ESM bundle and dynamically loads it using native ESM

* Removed dependency on platform-specific launchers allowing a single entrypoint to work everywhere Node.js runs.


## Result

Codex CLI now supports cross-platform and launches correctly via:
* macOS / Linux
* Windows PowerShell
* GitBash
* CMD
* WSL

Directly addresses #316 

![image](https://github.com/user-attachments/assets/85faaca4-24bc-47c9-8160-4e30df6da4c3)


![image](https://github.com/user-attachments/assets/a13f7adc-52c1-4c0e-af02-e35a35dc45d4)
2025-04-18 11:35:51 -07:00
Amar Sood
82f5abbeea Fix handling of Shift+Enter in e.g. Ghostty (#338)
Fix: Shift + Enter no longer prints “[27;2;13~” in the single‑line
input. Validated as working and necessary in Ghostty on Linux.

## Key points
- src/components/vendor/ink-text-input.tsx
- Added early handler that recognises the two modifyOtherKeys
escape‑sequences
    - [13;<mod>u  (mode 2 / CSI‑u)
    - [27;<mod>;13~ (mode 1 / legacy CSI‑~)
- If Ctrl is held (hasCtrl flag) → call onSubmit() (same as plain
Enter).
- Otherwise → insert a real newline at the caret (same as Option+Enter).
  - Prevents the raw sequence from being inserted into the buffer.

- src/components/chat/multiline-editor.tsx
- Replaced non‑breaking spaces with normal spaces to satisfy eslint
no‑irregular‑whitespace rule (no behaviour change).

All unit tests (114) and ESLint now pass:
npm test ✔️
npm run lint ✔️
2025-04-18 09:19:06 -07:00
Thomas
7b5f343179 fix: update context left display logic in TerminalChatInput component (#307)
Added persistent context length with colour coding.
2025-04-18 09:16:33 -07:00
429 changed files with 68689 additions and 10281 deletions

1
.codespellignore Normal file
View File

@@ -0,0 +1 @@
iTerm

6
.codespellrc Normal file
View File

@@ -0,0 +1,6 @@
[codespell]
# Ref: https://github.com/codespell-project/codespell#using-a-config-file
skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts
check-hidden = true
ignore-regex = ^\s*"image/\S+": ".*|\b(afterAll)\b
ignore-words-list = ratatui,ser

27
.devcontainer/Dockerfile Normal file
View File

@@ -0,0 +1,27 @@
FROM ubuntu:24.04
ARG DEBIAN_FRONTEND=noninteractive
# enable 'universe' because musl-tools & clang live there
RUN apt-get update && \
apt-get install -y --no-install-recommends \
software-properties-common && \
add-apt-repository --yes universe
# now install build deps
RUN apt-get update && \
apt-get install -y --no-install-recommends \
build-essential curl git ca-certificates \
pkg-config clang musl-tools libssl-dev just && \
rm -rf /var/lib/apt/lists/*
# Ubuntu 24.04 ships with user 'ubuntu' already created with UID 1000.
USER ubuntu
# install Rust + musl target as dev user
RUN curl -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal && \
~/.cargo/bin/rustup target add aarch64-unknown-linux-musl && \
~/.cargo/bin/rustup component add clippy rustfmt
ENV PATH="/home/ubuntu/.cargo/bin:${PATH}"
WORKDIR /workspace

30
.devcontainer/README.md Normal file
View File

@@ -0,0 +1,30 @@
# Containerized Development
We provide the following options to facilitate Codex development in a container. This is particularly useful for verifying the Linux build when working on a macOS host.
## Docker
To build the Docker image locally for x64 and then run it with the repo mounted under `/workspace`:
```shell
CODEX_DOCKER_IMAGE_NAME=codex-linux-dev
docker build --platform=linux/amd64 -t "$CODEX_DOCKER_IMAGE_NAME" ./.devcontainer
docker run --platform=linux/amd64 --rm -it -e CARGO_TARGET_DIR=/workspace/codex-rs/target-amd64 -v "$PWD":/workspace -w /workspace/codex-rs "$CODEX_DOCKER_IMAGE_NAME"
```
Note that `/workspace/target` will contain the binaries built for your host platform, so we include `-e CARGO_TARGET_DIR=/workspace/codex-rs/target-amd64` in the `docker run` command so that the binaries built inside your container are written to a separate directory.
For arm64, specify `--platform=linux/amd64` instead for both `docker build` and `docker run`.
Currently, the `Dockerfile` works for both x64 and arm64 Linux, though you need to run `rustup target add x86_64-unknown-linux-musl` yourself to install the musl toolchain for x64.
## VS Code
VS Code recognizes the `devcontainer.json` file and gives you the option to develop Codex in a container. Currently, `devcontainer.json` builds and runs the `arm64` flavor of the container.
From the integrated terminal in VS Code, you can build either flavor of the `arm64` build (GNU or musl):
```shell
cargo build --target aarch64-unknown-linux-musl
cargo build --target aarch64-unknown-linux-gnu
```

View File

@@ -0,0 +1,27 @@
{
"name": "Codex",
"build": {
"dockerfile": "Dockerfile",
"context": "..",
"platform": "linux/arm64"
},
/* Force VS Code to run the container as arm64 in
case your host is x86 (or vice-versa). */
"runArgs": ["--platform=linux/arm64"],
"containerEnv": {
"RUST_BACKTRACE": "1",
"CARGO_TARGET_DIR": "${containerWorkspaceFolder}/codex-rs/target-arm64"
},
"remoteUser": "ubuntu",
"customizations": {
"vscode": {
"settings": {
"terminal.integrated.defaultProfile.linux": "bash"
},
"extensions": ["rust-lang.rust-analyzer", "tamasfe.even-better-toml"]
}
}
}

View File

@@ -19,13 +19,14 @@ body:
id: version
attributes:
label: What version of Codex is running?
description: Copy the output of `codex --revision`
description: Copy the output of `codex --version`
- type: input
id: model
attributes:
label: Which model were you using?
description: Like `gpt-4.1`, `o4-mini`, `o3`, etc.
- type: input
id: platform
attributes:
label: What platform is your computer?
description: |

1
.github/actions/codex/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
/node_modules/

View File

@@ -0,0 +1,8 @@
printWidth = 80
quoteProps = "consistent"
semi = true
tabWidth = 2
trailingComma = "all"
# Preserve existing behavior for markdown/text wrapping.
proseWrap = "preserve"

140
.github/actions/codex/README.md vendored Normal file
View File

@@ -0,0 +1,140 @@
# openai/codex-action
`openai/codex-action` is a GitHub Action that facilitates the use of [Codex](https://github.com/openai/codex) on GitHub issues and pull requests. Using the action, associate **labels** to run Codex with the appropriate prompt for the given context. Codex will respond by posting comments or creating PRs, whichever you specify!
Here is a sample workflow that uses `openai/codex-action`:
```yaml
name: Codex
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
jobs:
codex:
if: ... # optional, but can be effective in conserving CI resources
runs-on: ubuntu-latest
# TODO(mbolin): Need to verify if/when `write` is necessary.
permissions:
contents: write
issues: write
pull-requests: write
steps:
# By default, Codex runs network disabled using --full-auto, so perform
# any setup that requires network (such as installing dependencies)
# before openai/codex-action.
- name: Checkout repository
uses: actions/checkout@v4
- name: Run Codex
uses: openai/codex-action@latest
with:
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
github_token: ${{ secrets.GITHUB_TOKEN }}
```
See sample usage in [`codex.yml`](../../workflows/codex.yml).
## Triggering the Action
Using the sample workflow above, we have:
```yaml
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
```
which means our workflow will be triggered when any of the following events occur:
- a label is added to an issue
- a label is added to a pull request against the `main` branch
### Label-Based Triggers
To define a GitHub label that should trigger Codex, create a file named `.github/codex/labels/LABEL-NAME.md` in your repository where `LABEL-NAME` is the name of the label. The content of the file is the prompt template to use when the label is added (see more on [Prompt Template Variables](#prompt-template-variables) below).
For example, if the file `.github/codex/labels/codex-review.md` exists, then:
- Adding the `codex-review` label will trigger the workflow containing the `openai/codex-action` GitHub Action.
- When `openai/codex-action` starts, it will replace the `codex-review` label with `codex-review-in-progress`.
- When `openai/codex-action` is finished, it will replace the `codex-review-in-progress` label with `codex-review-completed`.
If Codex sees that either `codex-review-in-progress` or `codex-review-completed` is already present, it will not perform the action.
As determined by the [default config](./src/default-label-config.ts), Codex will act on the following labels by default:
- Adding the `codex-review` label to a pull request will have Codex review the PR and add it to the PR as a comment.
- Adding the `codex-triage` label to an issue will have Codex investigate the issue and report its findings as a comment.
- Adding the `codex-issue-fix` label to an issue will have Codex attempt to fix the issue and create a PR wit the fix, if any.
## Action Inputs
The `openai/codex-action` GitHub Action takes the following inputs
### `openai_api_key` (required)
Set your `OPENAI_API_KEY` as a [repository secret](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions). See **Secrets and varaibles** then **Actions** in the settings for your GitHub repo.
Note that the secret name does not have to be `OPENAI_API_KEY`. For example, you might want to name it `CODEX_OPENAI_API_KEY` and then configure it on `openai/codex-action` as follows:
```yaml
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
```
### `github_token` (required)
This is required so that Codex can post a comment or create a PR. Set this value on the action as follows:
```yaml
github_token: ${{ secrets.GITHUB_TOKEN }}
```
### `codex_args`
A whitespace-delimited list of arguments to pass to Codex. Defaults to `--full-auto`, but if you want to override the default model to use `o3`:
```yaml
codex_args: "--full-auto --model o3"
```
For more complex configurations, use the `codex_home` input.
### `codex_home`
If set, the value to use for the `$CODEX_HOME` environment variable when running Codex. As explained [in the docs](https://github.com/openai/codex/tree/main/codex-rs#readme), this folder can contain the `config.toml` to configure Codex, custom instructions, and log files.
This should be a relative path within your repo.
## Prompt Template Variables
As shown above, `"prompt"` and `"promptPath"` are used to define prompt templates that will be populated and passed to Codex in response to certain events. All template variables are of the form `{CODEX_ACTION_...}` and the supported values are defined below.
### `CODEX_ACTION_ISSUE_TITLE`
If the action was triggered on a GitHub issue, this is the issue title.
Specifically it is read as the `.issue.title` from the `$GITHUB_EVENT_PATH`.
### `CODEX_ACTION_ISSUE_BODY`
If the action was triggered on a GitHub issue, this is the issue body.
Specifically it is read as the `.issue.body` from the `$GITHUB_EVENT_PATH`.
### `CODEX_ACTION_GITHUB_EVENT_PATH`
The value of the `$GITHUB_EVENT_PATH` environment variable, which is the path to the file that contains the JSON payload for the event that triggered the workflow. Codex can use `jq` to read only the fields of interest from this file.
### `CODEX_ACTION_PR_DIFF`
If the action was triggered on a pull request, this is the diff between the base and head commits of the PR. It is the output from `git diff`.
Note that the content of the diff could be quite large, so is generally safer to point Codex at `CODEX_ACTION_GITHUB_EVENT_PATH` and let it decide how it wants to explore the change.

127
.github/actions/codex/action.yml vendored Normal file
View File

@@ -0,0 +1,127 @@
name: "Codex [reusable action]"
description: "A reusable action that runs a Codex model."
inputs:
openai_api_key:
description: "The value to use as the OPENAI_API_KEY environment variable when running Codex."
required: true
trigger_phrase:
description: "Text to trigger Codex from a PR/issue body or comment."
required: false
default: ""
github_token:
description: "Token so Codex can comment on the PR or issue."
required: true
codex_args:
description: "A whitespace-delimited list of arguments to pass to Codex. Due to limitations in YAML, arguments with spaces are not supported. For more complex configurations, use the `codex_home` input."
required: false
default: "--config hide_agent_reasoning=true --full-auto"
codex_home:
description: "Value to use as the CODEX_HOME environment variable when running Codex."
required: false
codex_release_tag:
description: "The release tag of the Codex model to run, e.g., 'rust-v0.3.0'. Defaults to the latest release."
required: false
default: ""
runs:
using: "composite"
steps:
# Do this in Bash so we do not even bother to install Bun if the sender does
# not have write access to the repo.
- name: Verify user has write access to the repo.
env:
GH_TOKEN: ${{ github.token }}
shell: bash
run: |
set -euo pipefail
PERMISSION=$(gh api \
"/repos/${GITHUB_REPOSITORY}/collaborators/${{ github.event.sender.login }}/permission" \
| jq -r '.permission')
if [[ "$PERMISSION" != "admin" && "$PERMISSION" != "write" ]]; then
exit 1
fi
- name: Download Codex
env:
GH_TOKEN: ${{ github.token }}
shell: bash
run: |
set -euo pipefail
# Determine OS/arch and corresponding Codex artifact name.
uname_s=$(uname -s)
uname_m=$(uname -m)
case "$uname_s" in
Linux*) os="linux" ;;
Darwin*) os="apple-darwin" ;;
*) echo "Unsupported operating system: $uname_s"; exit 1 ;;
esac
case "$uname_m" in
x86_64*) arch="x86_64" ;;
arm64*|aarch64*) arch="aarch64" ;;
*) echo "Unsupported architecture: $uname_m"; exit 1 ;;
esac
# linux builds differentiate between musl and gnu.
if [[ "$os" == "linux" ]]; then
if [[ "$arch" == "x86_64" ]]; then
triple="${arch}-unknown-linux-musl"
else
# Only other supported linux build is aarch64 gnu.
triple="${arch}-unknown-linux-gnu"
fi
else
# macOS
triple="${arch}-apple-darwin"
fi
# Note that if we start baking version numbers into the artifact name,
# we will need to update this action.yml file to match.
artifact="codex-exec-${triple}.tar.gz"
TAG_ARG="${{ inputs.codex_release_tag }}"
# The usage is `gh release download [<tag>] [flags]`, so if TAG_ARG
# is empty, we do not pass it so we can default to the latest release.
gh release download ${TAG_ARG:+$TAG_ARG} --repo openai/codex \
--pattern "$artifact" --output - \
| tar xzO > /usr/local/bin/codex-exec
chmod +x /usr/local/bin/codex-exec
# Display Codex version to confirm binary integrity; ensure we point it
# at the checked-out repository via --cd so that any subsequent commands
# use the correct working directory.
codex-exec --cd "$GITHUB_WORKSPACE" --version
- name: Install Bun
uses: oven-sh/setup-bun@v2
with:
bun-version: 1.2.11
- name: Install dependencies
shell: bash
run: |
cd ${{ github.action_path }}
bun install --production
- name: Run Codex
shell: bash
run: bun run ${{ github.action_path }}/src/main.ts
# Process args plus environment variables often have a max of 128 KiB,
# so we should fit within that limit?
env:
INPUT_CODEX_ARGS: ${{ inputs.codex_args || '' }}
INPUT_CODEX_HOME: ${{ inputs.codex_home || ''}}
INPUT_TRIGGER_PHRASE: ${{ inputs.trigger_phrase || '' }}
OPENAI_API_KEY: ${{ inputs.openai_api_key }}
GITHUB_TOKEN: ${{ inputs.github_token }}
GITHUB_EVENT_ACTION: ${{ github.event.action || '' }}
GITHUB_EVENT_LABEL_NAME: ${{ github.event.label.name || '' }}
GITHUB_EVENT_ISSUE_NUMBER: ${{ github.event.issue.number || '' }}
GITHUB_EVENT_ISSUE_BODY: ${{ github.event.issue.body || '' }}
GITHUB_EVENT_REVIEW_BODY: ${{ github.event.review.body || '' }}
GITHUB_EVENT_COMMENT_BODY: ${{ github.event.comment.body || '' }}

91
.github/actions/codex/bun.lock vendored Normal file
View File

@@ -0,0 +1,91 @@
{
"lockfileVersion": 1,
"workspaces": {
"": {
"name": "codex-action",
"dependencies": {
"@actions/core": "^1.11.1",
"@actions/github": "^6.0.1",
},
"devDependencies": {
"@types/bun": "^1.2.19",
"@types/node": "^24.1.0",
"prettier": "^3.6.2",
"typescript": "^5.8.3",
},
},
},
"packages": {
"@actions/core": ["@actions/core@1.11.1", "", { "dependencies": { "@actions/exec": "^1.1.1", "@actions/http-client": "^2.0.1" } }, "sha512-hXJCSrkwfA46Vd9Z3q4cpEpHB1rL5NG04+/rbqW9d3+CSvtB1tYe8UTpAlixa1vj0m/ULglfEK2UKxMGxCxv5A=="],
"@actions/exec": ["@actions/exec@1.1.1", "", { "dependencies": { "@actions/io": "^1.0.1" } }, "sha512-+sCcHHbVdk93a0XT19ECtO/gIXoxvdsgQLzb2fE2/5sIZmWQuluYyjPQtrtTHdU1YzTZ7bAPN4sITq2xi1679w=="],
"@actions/github": ["@actions/github@6.0.1", "", { "dependencies": { "@actions/http-client": "^2.2.0", "@octokit/core": "^5.0.1", "@octokit/plugin-paginate-rest": "^9.2.2", "@octokit/plugin-rest-endpoint-methods": "^10.4.0", "@octokit/request": "^8.4.1", "@octokit/request-error": "^5.1.1", "undici": "^5.28.5" } }, "sha512-xbZVcaqD4XnQAe35qSQqskb3SqIAfRyLBrHMd/8TuL7hJSz2QtbDwnNM8zWx4zO5l2fnGtseNE3MbEvD7BxVMw=="],
"@actions/http-client": ["@actions/http-client@2.2.3", "", { "dependencies": { "tunnel": "^0.0.6", "undici": "^5.25.4" } }, "sha512-mx8hyJi/hjFvbPokCg4uRd4ZX78t+YyRPtnKWwIl+RzNaVuFpQHfmlGVfsKEJN8LwTCvL+DfVgAM04XaHkm6bA=="],
"@actions/io": ["@actions/io@1.1.3", "", {}, "sha512-wi9JjgKLYS7U/z8PPbco+PvTb/nRWjeoFlJ1Qer83k/3C5PHQi28hiVdeE2kHXmIL99mQFawx8qt/JPjZilJ8Q=="],
"@fastify/busboy": ["@fastify/busboy@2.1.1", "", {}, "sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA=="],
"@octokit/auth-token": ["@octokit/auth-token@4.0.0", "", {}, "sha512-tY/msAuJo6ARbK6SPIxZrPBms3xPbfwBrulZe0Wtr/DIY9lje2HeV1uoebShn6mx7SjCHif6EjMvoREj+gZ+SA=="],
"@octokit/core": ["@octokit/core@5.2.1", "", { "dependencies": { "@octokit/auth-token": "^4.0.0", "@octokit/graphql": "^7.1.0", "@octokit/request": "^8.4.1", "@octokit/request-error": "^5.1.1", "@octokit/types": "^13.0.0", "before-after-hook": "^2.2.0", "universal-user-agent": "^6.0.0" } }, "sha512-dKYCMuPO1bmrpuogcjQ8z7ICCH3FP6WmxpwC03yjzGfZhj9fTJg6+bS1+UAplekbN2C+M61UNllGOOoAfGCrdQ=="],
"@octokit/endpoint": ["@octokit/endpoint@9.0.6", "", { "dependencies": { "@octokit/types": "^13.1.0", "universal-user-agent": "^6.0.0" } }, "sha512-H1fNTMA57HbkFESSt3Y9+FBICv+0jFceJFPWDePYlR/iMGrwM5ph+Dd4XRQs+8X+PUFURLQgX9ChPfhJ/1uNQw=="],
"@octokit/graphql": ["@octokit/graphql@7.1.1", "", { "dependencies": { "@octokit/request": "^8.4.1", "@octokit/types": "^13.0.0", "universal-user-agent": "^6.0.0" } }, "sha512-3mkDltSfcDUoa176nlGoA32RGjeWjl3K7F/BwHwRMJUW/IteSa4bnSV8p2ThNkcIcZU2umkZWxwETSSCJf2Q7g=="],
"@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
"@octokit/plugin-paginate-rest": ["@octokit/plugin-paginate-rest@9.2.2", "", { "dependencies": { "@octokit/types": "^12.6.0" }, "peerDependencies": { "@octokit/core": "5" } }, "sha512-u3KYkGF7GcZnSD/3UP0S7K5XUFT2FkOQdcfXZGZQPGv3lm4F2Xbf71lvjldr8c1H3nNbF+33cLEkWYbokGWqiQ=="],
"@octokit/plugin-rest-endpoint-methods": ["@octokit/plugin-rest-endpoint-methods@10.4.1", "", { "dependencies": { "@octokit/types": "^12.6.0" }, "peerDependencies": { "@octokit/core": "5" } }, "sha512-xV1b+ceKV9KytQe3zCVqjg+8GTGfDYwaT1ATU5isiUyVtlVAO3HNdzpS4sr4GBx4hxQ46s7ITtZrAsxG22+rVg=="],
"@octokit/request": ["@octokit/request@8.4.1", "", { "dependencies": { "@octokit/endpoint": "^9.0.6", "@octokit/request-error": "^5.1.1", "@octokit/types": "^13.1.0", "universal-user-agent": "^6.0.0" } }, "sha512-qnB2+SY3hkCmBxZsR/MPCybNmbJe4KAlfWErXq+rBKkQJlbjdJeS85VI9r8UqeLYLvnAenU8Q1okM/0MBsAGXw=="],
"@octokit/request-error": ["@octokit/request-error@5.1.1", "", { "dependencies": { "@octokit/types": "^13.1.0", "deprecation": "^2.0.0", "once": "^1.4.0" } }, "sha512-v9iyEQJH6ZntoENr9/yXxjuezh4My67CBSu9r6Ve/05Iu5gNgnisNWOsoJHTP6k0Rr0+HQIpnH+kyammu90q/g=="],
"@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
"@types/bun": ["@types/bun@1.2.19", "", { "dependencies": { "bun-types": "1.2.19" } }, "sha512-d9ZCmrH3CJ2uYKXQIUuZ/pUnTqIvLDS0SK7pFmbx8ma+ziH/FRMoAq5bYpRG7y+w1gl+HgyNZbtqgMq4W4e2Lg=="],
"@types/node": ["@types/node@24.1.0", "", { "dependencies": { "undici-types": "~7.8.0" } }, "sha512-ut5FthK5moxFKH2T1CUOC6ctR67rQRvvHdFLCD2Ql6KXmMuCrjsSsRI9UsLCm9M18BMwClv4pn327UvB7eeO1w=="],
"@types/react": ["@types/react@19.1.8", "", { "dependencies": { "csstype": "^3.0.2" } }, "sha512-AwAfQ2Wa5bCx9WP8nZL2uMZWod7J7/JSplxbTmBQ5ms6QpqNYm672H0Vu9ZVKVngQ+ii4R/byguVEUZQyeg44g=="],
"before-after-hook": ["before-after-hook@2.2.3", "", {}, "sha512-NzUnlZexiaH/46WDhANlyR2bXRopNg4F/zuSA3OpZnllCUgRaOF2znDioDWrmbNVsuZk6l9pMquQB38cfBZwkQ=="],
"bun-types": ["bun-types@1.2.19", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-uAOTaZSPuYsWIXRpj7o56Let0g/wjihKCkeRqUBhlLVM/Bt+Fj9xTo+LhC1OV1XDaGkz4hNC80et5xgy+9KTHQ=="],
"csstype": ["csstype@3.1.3", "", {}, "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="],
"deprecation": ["deprecation@2.3.1", "", {}, "sha512-xmHIy4F3scKVwMsQ4WnVaS8bHOx0DmVwRywosKhaILI0ywMDWPtBSku2HNxRvF7jtwDRsoEwYQSfbxj8b7RlJQ=="],
"once": ["once@1.4.0", "", { "dependencies": { "wrappy": "1" } }, "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w=="],
"prettier": ["prettier@3.6.2", "", { "bin": { "prettier": "bin/prettier.cjs" } }, "sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ=="],
"tunnel": ["tunnel@0.0.6", "", {}, "sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg=="],
"typescript": ["typescript@5.8.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ=="],
"undici": ["undici@5.29.0", "", { "dependencies": { "@fastify/busboy": "^2.0.0" } }, "sha512-raqeBD6NQK4SkWhQzeYKd1KmIG6dllBOTt55Rmkt4HtI9mwdWtJljnrXjAFUBLTSN67HWrOIZ3EPF4kjUw80Bg=="],
"undici-types": ["undici-types@7.8.0", "", {}, "sha512-9UJ2xGDvQ43tYyVMpuHlsgApydB8ZKfVYTsLDhXkFL/6gfkp+U8xTGdh8pMJv1SpZna0zxG1DwsKZsreLbXBxw=="],
"universal-user-agent": ["universal-user-agent@6.0.1", "", {}, "sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ=="],
"wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
"@octokit/plugin-paginate-rest/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],
"@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],
"bun-types/@types/node": ["@types/node@24.0.13", "", { "dependencies": { "undici-types": "~7.8.0" } }, "sha512-Qm9OYVOFHFYg3wJoTSrz80hoec5Lia/dPp84do3X7dZvLikQvM1YpmvTBEdIr/e+U8HTkFjLHLnl78K/qjf+jQ=="],
"@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],
"@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],
}
}

21
.github/actions/codex/package.json vendored Normal file
View File

@@ -0,0 +1,21 @@
{
"name": "codex-action",
"version": "0.0.0",
"private": true,
"scripts": {
"format": "prettier --check src",
"format:fix": "prettier --write src",
"test": "bun test",
"typecheck": "tsc"
},
"dependencies": {
"@actions/core": "^1.11.1",
"@actions/github": "^6.0.1"
},
"devDependencies": {
"@types/bun": "^1.2.19",
"@types/node": "^24.1.0",
"prettier": "^3.6.2",
"typescript": "^5.8.3"
}
}

View File

@@ -0,0 +1,85 @@
import * as github from "@actions/github";
import type { EnvContext } from "./env-context";
/**
* Add an "eyes" reaction to the entity (issue, issue comment, or pull request
* review comment) that triggered the current Codex invocation.
*
* The purpose is to provide immediate feedback to the user similar to the
* *-in-progress label flow indicating that the bot has acknowledged the
* request and is working on it.
*
* We attempt to add the reaction best suited for the current GitHub event:
*
* • issues → POST /repos/{owner}/{repo}/issues/{issue_number}/reactions
* • issue_comment → POST /repos/{owner}/{repo}/issues/comments/{comment_id}/reactions
* • pull_request_review_comment → POST /repos/{owner}/{repo}/pulls/comments/{comment_id}/reactions
*
* If the specific target is unavailable (e.g. unexpected payload shape) we
* silently skip instead of failing the whole action because the reaction is
* merely cosmetic.
*/
export async function addEyesReaction(ctx: EnvContext): Promise<void> {
const octokit = ctx.getOctokit();
const { owner, repo } = github.context.repo;
const eventName = github.context.eventName;
try {
switch (eventName) {
case "issue_comment": {
const commentId = (github.context.payload as any)?.comment?.id;
if (commentId) {
await octokit.rest.reactions.createForIssueComment({
owner,
repo,
comment_id: commentId,
content: "eyes",
});
return;
}
break;
}
case "pull_request_review_comment": {
const commentId = (github.context.payload as any)?.comment?.id;
if (commentId) {
await octokit.rest.reactions.createForPullRequestReviewComment({
owner,
repo,
comment_id: commentId,
content: "eyes",
});
return;
}
break;
}
case "issues": {
const issueNumber = github.context.issue.number;
if (issueNumber) {
await octokit.rest.reactions.createForIssue({
owner,
repo,
issue_number: issueNumber,
content: "eyes",
});
return;
}
break;
}
default: {
// Fallback: try to react to the issue/PR if we have a number.
const issueNumber = github.context.issue.number;
if (issueNumber) {
await octokit.rest.reactions.createForIssue({
owner,
repo,
issue_number: issueNumber,
content: "eyes",
});
}
}
}
} catch (error) {
// Do not fail the action if reaction creation fails log and continue.
console.warn(`Failed to add \"eyes\" reaction: ${error}`);
}
}

53
.github/actions/codex/src/comment.ts vendored Normal file
View File

@@ -0,0 +1,53 @@
import type { EnvContext } from "./env-context";
import { runCodex } from "./run-codex";
import { postComment } from "./post-comment";
import { addEyesReaction } from "./add-reaction";
/**
* Handle `issue_comment` and `pull_request_review_comment` events once we know
* the action is supported.
*/
export async function onComment(ctx: EnvContext): Promise<void> {
const triggerPhrase = ctx.tryGet("INPUT_TRIGGER_PHRASE");
if (!triggerPhrase) {
console.warn("Empty trigger phrase: skipping.");
return;
}
// Attempt to get the body of the comment from the environment. Depending on
// the event type either `GITHUB_EVENT_COMMENT_BODY` (issue & PR comments) or
// `GITHUB_EVENT_REVIEW_BODY` (PR reviews) is set.
const commentBody =
ctx.tryGetNonEmpty("GITHUB_EVENT_COMMENT_BODY") ??
ctx.tryGetNonEmpty("GITHUB_EVENT_REVIEW_BODY") ??
ctx.tryGetNonEmpty("GITHUB_EVENT_ISSUE_BODY");
if (!commentBody) {
console.warn("Comment body not found in environment: skipping.");
return;
}
// Check if the trigger phrase is present.
if (!commentBody.includes(triggerPhrase)) {
console.log(
`Trigger phrase '${triggerPhrase}' not found: nothing to do for this comment.`,
);
return;
}
// Derive the prompt by removing the trigger phrase. Remove only the first
// occurrence to keep any additional occurrences that might be meaningful.
const prompt = commentBody.replace(triggerPhrase, "").trim();
if (prompt.length === 0) {
console.warn("Prompt is empty after removing trigger phrase: skipping");
return;
}
// Provide immediate feedback that we are working on the request.
await addEyesReaction(ctx);
// Run Codex and post the response as a new comment.
const lastMessage = await runCodex(prompt, ctx);
await postComment(lastMessage, ctx);
}

11
.github/actions/codex/src/config.ts vendored Normal file
View File

@@ -0,0 +1,11 @@
import { readdirSync, statSync } from "fs";
import * as path from "path";
export interface Config {
labels: Record<string, LabelConfig>;
}
export interface LabelConfig {
/** Returns the prompt template. */
getPromptTemplate(): string;
}

View File

@@ -0,0 +1,44 @@
import type { Config } from "./config";
export function getDefaultConfig(): Config {
return {
labels: {
"codex-investigate-issue": {
getPromptTemplate: () =>
`
Troubleshoot whether the reported issue is valid.
Provide a concise and respectful comment summarizing the findings.
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}
`.trim(),
},
"codex-code-review": {
getPromptTemplate: () =>
`
Review this PR and respond with a very concise final message, formatted in Markdown.
There should be a summary of the changes (1-2 sentences) and a few bullet points if necessary.
Then provide the **review** (1-2 sentences plus bullet points, friendly tone).
{CODEX_ACTION_GITHUB_EVENT_PATH} contains the JSON that triggered this GitHub workflow. It contains the \`base\` and \`head\` refs that define this PR. Both refs are available locally.
`.trim(),
},
"codex-attempt-fix": {
getPromptTemplate: () =>
`
Attempt to solve the reported issue.
If a code change is required, create a new branch, commit the fix, and open a pull-request that resolves the problem.
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}
`.trim(),
},
},
};
}

116
.github/actions/codex/src/env-context.ts vendored Normal file
View File

@@ -0,0 +1,116 @@
/*
* Centralised access to environment variables used by the Codex GitHub
* Action.
*
* To enable proper unit-testing we avoid reading from `process.env` at module
* initialisation time. Instead a `EnvContext` object is created (usually from
* the real `process.env`) and passed around explicitly or where that is not
* yet practical imported as the shared `defaultContext` singleton. Tests can
* create their own context backed by a stubbed map of variables without having
* to mutate global state.
*/
import { fail } from "./fail";
import * as github from "@actions/github";
export interface EnvContext {
/**
* Return the value for a given environment variable or terminate the action
* via `fail` if it is missing / empty.
*/
get(name: string): string;
/**
* Attempt to read an environment variable. Returns the value when present;
* otherwise returns undefined (does not call `fail`).
*/
tryGet(name: string): string | undefined;
/**
* Attempt to read an environment variable. Returns non-empty string value or
* null if unset or empty string.
*/
tryGetNonEmpty(name: string): string | null;
/**
* Return a memoised Octokit instance authenticated via the token resolved
* from the provided argument (when defined) or the environment variables
* `GITHUB_TOKEN`/`GH_TOKEN`.
*
* Subsequent calls return the same cached instance to avoid spawning
* multiple REST clients within a single action run.
*/
getOctokit(token?: string): ReturnType<typeof github.getOctokit>;
}
/** Internal helper *not* exported. */
function _getRequiredEnv(
name: string,
env: Record<string, string | undefined>,
): string | undefined {
const value = env[name];
// Avoid leaking secrets into logs while still logging non-secret variables.
if (name.endsWith("KEY") || name.endsWith("TOKEN")) {
if (value) {
console.log(`value for ${name} was found`);
}
} else {
console.log(`${name}=${value}`);
}
return value;
}
/** Create a context backed by the supplied environment map (defaults to `process.env`). */
export function createEnvContext(
env: Record<string, string | undefined> = process.env,
): EnvContext {
// Lazily instantiated Octokit client shared across this context.
let cachedOctokit: ReturnType<typeof github.getOctokit> | null = null;
return {
get(name: string): string {
const value = _getRequiredEnv(name, env);
if (value == null) {
fail(`Missing required environment variable: ${name}`);
}
return value;
},
tryGet(name: string): string | undefined {
return _getRequiredEnv(name, env);
},
tryGetNonEmpty(name: string): string | null {
const value = _getRequiredEnv(name, env);
return value == null || value === "" ? null : value;
},
getOctokit(token?: string) {
if (cachedOctokit) {
return cachedOctokit;
}
// Determine the token to authenticate with.
const githubToken = token ?? env["GITHUB_TOKEN"] ?? env["GH_TOKEN"];
if (!githubToken) {
fail(
"Unable to locate a GitHub token. `github_token` should have been set on the action.",
);
}
cachedOctokit = github.getOctokit(githubToken!);
return cachedOctokit;
},
};
}
/**
* Shared context built from the actual `process.env`. Production code that is
* not yet refactored to receive a context explicitly may import and use this
* singleton. Tests should avoid the singleton and instead pass their own
* context to the functions they exercise.
*/
export const defaultContext: EnvContext = createEnvContext();

4
.github/actions/codex/src/fail.ts vendored Normal file
View File

@@ -0,0 +1,4 @@
export function fail(message: string): never {
console.error(message);
process.exit(1);
}

149
.github/actions/codex/src/git-helpers.ts vendored Normal file
View File

@@ -0,0 +1,149 @@
import { spawnSync } from "child_process";
import * as github from "@actions/github";
import { EnvContext } from "./env-context";
function runGit(args: string[], silent = true): string {
console.info(`Running git ${args.join(" ")}`);
const res = spawnSync("git", args, {
encoding: "utf8",
stdio: silent ? ["ignore", "pipe", "pipe"] : "inherit",
});
if (res.error) {
throw res.error;
}
if (res.status !== 0) {
// Return stderr so caller may handle; else throw.
throw new Error(
`git ${args.join(" ")} failed with code ${res.status}: ${res.stderr}`,
);
}
return res.stdout.trim();
}
function stageAllChanges() {
runGit(["add", "-A"]);
}
function hasStagedChanges(): boolean {
const res = spawnSync("git", ["diff", "--cached", "--quiet", "--exit-code"]);
return res.status !== 0;
}
function ensureOnBranch(
issueNumber: number,
protectedBranches: string[],
suggestedSlug?: string,
): string {
let branch = "";
try {
branch = runGit(["symbolic-ref", "--short", "-q", "HEAD"]);
} catch {
branch = "";
}
// If detached HEAD or on a protected branch, create a new branch.
if (!branch || protectedBranches.includes(branch)) {
if (suggestedSlug) {
const safeSlug = suggestedSlug
.toLowerCase()
.replace(/[^\w\s-]/g, "")
.trim()
.replace(/\s+/g, "-");
branch = `codex-fix-${issueNumber}-${safeSlug}`;
} else {
branch = `codex-fix-${issueNumber}-${Date.now()}`;
}
runGit(["switch", "-c", branch]);
}
return branch;
}
function commitIfNeeded(issueNumber: number) {
if (hasStagedChanges()) {
runGit([
"commit",
"-m",
`fix: automated fix for #${issueNumber} via Codex`,
]);
}
}
function pushBranch(branch: string, githubToken: string, ctx: EnvContext) {
const repoSlug = ctx.get("GITHUB_REPOSITORY"); // owner/repo
const remoteUrl = `https://x-access-token:${githubToken}@github.com/${repoSlug}.git`;
runGit(["push", "--force-with-lease", "-u", remoteUrl, `HEAD:${branch}`]);
}
/**
* If this returns a string, it is the URL of the created PR.
*/
export async function maybePublishPRForIssue(
issueNumber: number,
lastMessage: string,
ctx: EnvContext,
): Promise<string | undefined> {
// Only proceed if GITHUB_TOKEN available.
const githubToken =
ctx.tryGetNonEmpty("GITHUB_TOKEN") ?? ctx.tryGetNonEmpty("GH_TOKEN");
if (!githubToken) {
console.warn("No GitHub token - skipping PR creation.");
return undefined;
}
// Print `git status` for debugging.
runGit(["status"]);
// Stage any remaining changes so they can be committed and pushed.
stageAllChanges();
const octokit = ctx.getOctokit(githubToken);
const { owner, repo } = github.context.repo;
// Determine default branch to treat as protected.
let defaultBranch = "main";
try {
const repoInfo = await octokit.rest.repos.get({ owner, repo });
defaultBranch = repoInfo.data.default_branch ?? "main";
} catch (e) {
console.warn(`Failed to get default branch, assuming 'main': ${e}`);
}
const sanitizedMessage = lastMessage.replace(/\u2022/g, "-");
const [summaryLine] = sanitizedMessage.split(/\r?\n/);
const branch = ensureOnBranch(issueNumber, [defaultBranch, "master"], summaryLine);
commitIfNeeded(issueNumber);
pushBranch(branch, githubToken, ctx);
// Try to find existing PR for this branch
const headParam = `${owner}:${branch}`;
const existing = await octokit.rest.pulls.list({
owner,
repo,
head: headParam,
state: "open",
});
if (existing.data.length > 0) {
return existing.data[0].html_url;
}
// Determine base branch (default to main)
let baseBranch = "main";
try {
const repoInfo = await octokit.rest.repos.get({ owner, repo });
baseBranch = repoInfo.data.default_branch ?? "main";
} catch (e) {
console.warn(`Failed to get default branch, assuming 'main': ${e}`);
}
const pr = await octokit.rest.pulls.create({
owner,
repo,
title: summaryLine,
head: branch,
base: baseBranch,
body: sanitizedMessage,
});
return pr.data.html_url;
}

16
.github/actions/codex/src/git-user.ts vendored Normal file
View File

@@ -0,0 +1,16 @@
export function setGitHubActionsUser(): void {
const commands = [
["git", "config", "--global", "user.name", "github-actions[bot]"],
[
"git",
"config",
"--global",
"user.email",
"41898282+github-actions[bot]@users.noreply.github.com",
],
];
for (const command of commands) {
Bun.spawnSync(command);
}
}

View File

@@ -0,0 +1,11 @@
import * as pathMod from "path";
import { EnvContext } from "./env-context";
export function resolveWorkspacePath(path: string, ctx: EnvContext): string {
if (pathMod.isAbsolute(path)) {
return path;
} else {
const workspace = ctx.get("GITHUB_WORKSPACE");
return pathMod.join(workspace, path);
}
}

View File

@@ -0,0 +1,56 @@
import type { Config, LabelConfig } from "./config";
import { getDefaultConfig } from "./default-label-config";
import { readFileSync, readdirSync, statSync } from "fs";
import * as path from "path";
/**
* Build an in-memory configuration object by scanning the repository for
* Markdown templates located in `.github/codex/labels`.
*
* Each `*.md` file in that directory represents a label that can trigger the
* Codex GitHub Action. The filename **without** the extension is interpreted
* as the label name, e.g. `codex-review.md` ➜ `codex-review`.
*
* For every such label we derive the corresponding `doneLabel` by appending
* the suffix `-completed`.
*/
export function loadConfig(workspace: string): Config {
const labelsDir = path.join(workspace, ".github", "codex", "labels");
let entries: string[];
try {
entries = readdirSync(labelsDir);
} catch {
// If the directory is missing, return the default configuration.
return getDefaultConfig();
}
const labels: Record<string, LabelConfig> = {};
for (const entry of entries) {
if (!entry.endsWith(".md")) {
continue;
}
const fullPath = path.join(labelsDir, entry);
if (!statSync(fullPath).isFile()) {
continue;
}
const labelName = entry.slice(0, -3); // trim ".md"
labels[labelName] = new FileLabelConfig(fullPath);
}
return { labels };
}
class FileLabelConfig implements LabelConfig {
constructor(private readonly promptPath: string) {}
getPromptTemplate(): string {
return readFileSync(this.promptPath, "utf8");
}
}

80
.github/actions/codex/src/main.ts vendored Executable file
View File

@@ -0,0 +1,80 @@
#!/usr/bin/env bun
import type { Config } from "./config";
import { defaultContext, EnvContext } from "./env-context";
import { loadConfig } from "./load-config";
import { setGitHubActionsUser } from "./git-user";
import { onLabeled } from "./process-label";
import { ensureBaseAndHeadCommitsForPRAreAvailable } from "./prompt-template";
import { performAdditionalValidation } from "./verify-inputs";
import { onComment } from "./comment";
import { onReview } from "./review";
async function main(): Promise<void> {
const ctx: EnvContext = defaultContext;
// Build the configuration dynamically by scanning `.github/codex/labels`.
const GITHUB_WORKSPACE = ctx.get("GITHUB_WORKSPACE");
const config: Config = loadConfig(GITHUB_WORKSPACE);
// Optionally perform additional validation of prompt template files.
performAdditionalValidation(config, GITHUB_WORKSPACE);
const GITHUB_EVENT_NAME = ctx.get("GITHUB_EVENT_NAME");
const GITHUB_EVENT_ACTION = ctx.get("GITHUB_EVENT_ACTION");
// Set user.name and user.email to a bot before Codex runs, just in case it
// creates a commit.
setGitHubActionsUser();
switch (GITHUB_EVENT_NAME) {
case "issues": {
if (GITHUB_EVENT_ACTION === "labeled") {
await onLabeled(config, ctx);
return;
} else if (GITHUB_EVENT_ACTION === "opened") {
await onComment(ctx);
return;
}
break;
}
case "issue_comment": {
if (GITHUB_EVENT_ACTION === "created") {
await onComment(ctx);
return;
}
break;
}
case "pull_request": {
if (GITHUB_EVENT_ACTION === "labeled") {
await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
await onLabeled(config, ctx);
return;
}
break;
}
case "pull_request_review": {
await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
if (GITHUB_EVENT_ACTION === "submitted") {
await onReview(ctx);
return;
}
break;
}
case "pull_request_review_comment": {
await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
if (GITHUB_EVENT_ACTION === "created") {
await onComment(ctx);
return;
}
break;
}
}
console.warn(
`Unsupported action '${GITHUB_EVENT_ACTION}' for event '${GITHUB_EVENT_NAME}'.`,
);
}
main();

View File

@@ -0,0 +1,62 @@
import { fail } from "./fail";
import * as github from "@actions/github";
import { EnvContext } from "./env-context";
/**
* Post a comment to the issue / pull request currently in scope.
*
* Provide the environment context so that token lookup (inside getOctokit) does
* not rely on global state.
*/
export async function postComment(
commentBody: string,
ctx: EnvContext,
): Promise<void> {
// Append a footer with a link back to the workflow run, if available.
const footer = buildWorkflowRunFooter(ctx);
const bodyWithFooter = footer ? `${commentBody}${footer}` : commentBody;
const octokit = ctx.getOctokit();
console.info("Got Octokit instance for posting comment");
const { owner, repo } = github.context.repo;
const issueNumber = github.context.issue.number;
if (!issueNumber) {
console.warn(
"No issue or pull_request number found in GitHub context; skipping comment creation.",
);
return;
}
try {
console.info("Calling octokit.rest.issues.createComment()");
await octokit.rest.issues.createComment({
owner,
repo,
issue_number: issueNumber,
body: bodyWithFooter,
});
} catch (error) {
fail(`Failed to create comment via GitHub API: ${error}`);
}
}
/**
* Helper to build a Markdown fragment linking back to the workflow run that
* generated the current comment. Returns `undefined` if required environment
* variables are missing e.g. when running outside of GitHub Actions so we
* can gracefully skip the footer in those cases.
*/
function buildWorkflowRunFooter(ctx: EnvContext): string | undefined {
const serverUrl =
ctx.tryGetNonEmpty("GITHUB_SERVER_URL") ?? "https://github.com";
const repository = ctx.tryGetNonEmpty("GITHUB_REPOSITORY");
const runId = ctx.tryGetNonEmpty("GITHUB_RUN_ID");
if (!repository || !runId) {
return undefined;
}
const url = `${serverUrl}/${repository}/actions/runs/${runId}`;
return `\n\n---\n*[_View workflow run_](${url})*`;
}

View File

@@ -0,0 +1,195 @@
import { fail } from "./fail";
import { EnvContext } from "./env-context";
import { renderPromptTemplate } from "./prompt-template";
import { postComment } from "./post-comment";
import { runCodex } from "./run-codex";
import * as github from "@actions/github";
import { Config, LabelConfig } from "./config";
import { maybePublishPRForIssue } from "./git-helpers";
export async function onLabeled(
config: Config,
ctx: EnvContext,
): Promise<void> {
const GITHUB_EVENT_LABEL_NAME = ctx.get("GITHUB_EVENT_LABEL_NAME");
const labelConfig = config.labels[GITHUB_EVENT_LABEL_NAME] as
| LabelConfig
| undefined;
if (!labelConfig) {
fail(
`Label \`${GITHUB_EVENT_LABEL_NAME}\` not found in config: ${JSON.stringify(config)}`,
);
}
await processLabelConfig(ctx, GITHUB_EVENT_LABEL_NAME, labelConfig);
}
/**
* Wrapper that handles `-in-progress` and `-completed` semantics around the core lint/fix/review
* processing. It will:
*
* - Skip execution if the `-in-progress` or `-completed` label is already present.
* - Mark the PR/issue as `-in-progress`.
* - After successful execution, mark the PR/issue as `-completed`.
*/
async function processLabelConfig(
ctx: EnvContext,
label: string,
labelConfig: LabelConfig,
): Promise<void> {
const octokit = ctx.getOctokit();
const { owner, repo, issueNumber, labelNames } =
await getCurrentLabels(octokit);
const inProgressLabel = `${label}-in-progress`;
const completedLabel = `${label}-completed`;
for (const markerLabel of [inProgressLabel, completedLabel]) {
if (labelNames.includes(markerLabel)) {
console.log(
`Label '${markerLabel}' already present on issue/PR #${issueNumber}. Skipping Codex action.`,
);
// Clean up: remove the triggering label to avoid confusion and re-runs.
await addAndRemoveLabels(octokit, {
owner,
repo,
issueNumber,
remove: markerLabel,
});
return;
}
}
// Mark the PR/issue as in progress.
await addAndRemoveLabels(octokit, {
owner,
repo,
issueNumber,
add: inProgressLabel,
remove: label,
});
// Run the core Codex processing.
await processLabel(ctx, label, labelConfig);
// Mark the PR/issue as completed.
await addAndRemoveLabels(octokit, {
owner,
repo,
issueNumber,
add: completedLabel,
remove: inProgressLabel,
});
}
async function processLabel(
ctx: EnvContext,
label: string,
labelConfig: LabelConfig,
): Promise<void> {
const template = labelConfig.getPromptTemplate();
const populatedTemplate = await renderPromptTemplate(template, ctx);
// Always run Codex and post the resulting message as a comment.
let commentBody = await runCodex(populatedTemplate, ctx);
// Current heuristic: only try to create a PR if "attempt" or "fix" is in the
// label name. (Yes, we plan to evolve this.)
if (label.indexOf("fix") !== -1 || label.indexOf("attempt") !== -1) {
console.info(`label ${label} indicates we should attempt to create a PR`);
const prUrl = await maybeFixIssue(ctx, commentBody);
if (prUrl) {
commentBody += `\n\n---\nOpened pull request: ${prUrl}`;
}
} else {
console.info(
`label ${label} does not indicate we should attempt to create a PR`,
);
}
await postComment(commentBody, ctx);
}
async function maybeFixIssue(
ctx: EnvContext,
lastMessage: string,
): Promise<string | undefined> {
// Attempt to create a PR out of any changes Codex produced.
const issueNumber = github.context.issue.number!; // exists for issues triggering this path
try {
return await maybePublishPRForIssue(issueNumber, lastMessage, ctx);
} catch (e) {
console.warn(`Failed to publish PR: ${e}`);
}
}
async function getCurrentLabels(
octokit: ReturnType<typeof github.getOctokit>,
): Promise<{
owner: string;
repo: string;
issueNumber: number;
labelNames: Array<string>;
}> {
const { owner, repo } = github.context.repo;
const issueNumber = github.context.issue.number;
if (!issueNumber) {
fail("No issue or pull_request number found in GitHub context.");
}
const { data: issueData } = await octokit.rest.issues.get({
owner,
repo,
issue_number: issueNumber,
});
const labelNames =
issueData.labels?.map((label: any) =>
typeof label === "string" ? label : label.name,
) ?? [];
return { owner, repo, issueNumber, labelNames };
}
async function addAndRemoveLabels(
octokit: ReturnType<typeof github.getOctokit>,
opts: {
owner: string;
repo: string;
issueNumber: number;
add?: string;
remove?: string;
},
): Promise<void> {
const { owner, repo, issueNumber, add, remove } = opts;
if (add) {
try {
await octokit.rest.issues.addLabels({
owner,
repo,
issue_number: issueNumber,
labels: [add],
});
} catch (error) {
console.warn(`Failed to add label '${add}': ${error}`);
}
}
if (remove) {
try {
await octokit.rest.issues.removeLabel({
owner,
repo,
issue_number: issueNumber,
name: remove,
});
} catch (error) {
console.warn(`Failed to remove label '${remove}': ${error}`);
}
}
}

View File

@@ -0,0 +1,284 @@
/*
* Utilities to render Codex prompt templates.
*
* A template is a Markdown (or plain-text) file that may contain one or more
* placeholders of the form `{CODEX_ACTION_<NAME>}`. At runtime these
* placeholders are substituted with dynamically generated content. Each
* placeholder is resolved **exactly once** even if it appears multiple times
* in the same template.
*/
import { readFile } from "fs/promises";
import { EnvContext } from "./env-context";
// ---------------------------------------------------------------------------
// Helpers
// ---------------------------------------------------------------------------
/**
* Lazily caches parsed `$GITHUB_EVENT_PATH` contents keyed by the file path so
* we only hit the filesystem once per unique event payload.
*/
const githubEventDataCache: Map<string, Promise<any>> = new Map();
function getGitHubEventData(ctx: EnvContext): Promise<any> {
const eventPath = ctx.get("GITHUB_EVENT_PATH");
let cached = githubEventDataCache.get(eventPath);
if (!cached) {
cached = readFile(eventPath, "utf8").then((raw) => JSON.parse(raw));
githubEventDataCache.set(eventPath, cached);
}
return cached;
}
async function runCommand(args: Array<string>): Promise<string> {
const result = Bun.spawnSync(args, {
stdout: "pipe",
stderr: "pipe",
});
if (result.success) {
return result.stdout.toString();
}
console.error(`Error running ${JSON.stringify(args)}: ${result.stderr}`);
return "";
}
// ---------------------------------------------------------------------------
// Public API
// ---------------------------------------------------------------------------
// Regex that captures the variable name without the surrounding { } braces.
const VAR_REGEX = /\{(CODEX_ACTION_[A-Z0-9_]+)\}/g;
// Cache individual placeholder values so each one is resolved at most once per
// process even if many templates reference it.
const placeholderCache: Map<string, Promise<string>> = new Map();
/**
* Parse a template string, resolve all placeholders and return the rendered
* result.
*/
export async function renderPromptTemplate(
template: string,
ctx: EnvContext,
): Promise<string> {
// ---------------------------------------------------------------------
// 1) Gather all *unique* placeholders present in the template.
// ---------------------------------------------------------------------
const variables = new Set<string>();
for (const match of template.matchAll(VAR_REGEX)) {
variables.add(match[1]);
}
// ---------------------------------------------------------------------
// 2) Kick off (or reuse) async resolution for each variable.
// ---------------------------------------------------------------------
for (const variable of variables) {
if (!placeholderCache.has(variable)) {
placeholderCache.set(variable, resolveVariable(variable, ctx));
}
}
// ---------------------------------------------------------------------
// 3) Await completion so we can perform a simple synchronous replace below.
// ---------------------------------------------------------------------
const resolvedEntries: [string, string][] = [];
for (const [key, promise] of placeholderCache.entries()) {
resolvedEntries.push([key, await promise]);
}
const resolvedMap = new Map<string, string>(resolvedEntries);
// ---------------------------------------------------------------------
// 4) Replace each occurrence. We use replace with a callback to ensure
// correct substitution even if variable names overlap (they shouldn't,
// but better safe than sorry).
// ---------------------------------------------------------------------
return template.replace(VAR_REGEX, (_, varName: string) => {
return resolvedMap.get(varName) ?? "";
});
}
export async function ensureBaseAndHeadCommitsForPRAreAvailable(
ctx: EnvContext,
): Promise<{ baseSha: string; headSha: string } | null> {
const prShas = await getPrShas(ctx);
if (prShas == null) {
console.warn("Unable to resolve PR branches");
return null;
}
const event = await getGitHubEventData(ctx);
const pr = event.pull_request;
if (!pr) {
console.warn("event.pull_request is not defined - unexpected");
return null;
}
const workspace = ctx.get("GITHUB_WORKSPACE");
// Refs (branch names)
const baseRef: string | undefined = pr.base?.ref;
const headRef: string | undefined = pr.head?.ref;
// Clone URLs
const baseRemoteUrl: string | undefined = pr.base?.repo?.clone_url;
const headRemoteUrl: string | undefined = pr.head?.repo?.clone_url;
if (!baseRef || !headRef || !baseRemoteUrl || !headRemoteUrl) {
console.warn(
"Missing PR ref or remote URL information - cannot fetch commits",
);
return null;
}
// Ensure we have the base branch.
await runCommand([
"git",
"-C",
workspace,
"fetch",
"--no-tags",
"origin",
baseRef,
]);
// Ensure we have the head branch.
if (headRemoteUrl === baseRemoteUrl) {
// Same repository the commit is available from `origin`.
await runCommand([
"git",
"-C",
workspace,
"fetch",
"--no-tags",
"origin",
headRef,
]);
} else {
// Fork make sure a `pr` remote exists that points at the fork. Attempting
// to add a remote that already exists causes git to error, so we swallow
// any non-zero exit codes from that specific command.
await runCommand([
"git",
"-C",
workspace,
"remote",
"add",
"pr",
headRemoteUrl,
]);
// Whether adding succeeded or the remote already existed, attempt to fetch
// the head ref from the `pr` remote.
await runCommand([
"git",
"-C",
workspace,
"fetch",
"--no-tags",
"pr",
headRef,
]);
}
return prShas;
}
// ---------------------------------------------------------------------------
// Internal helpers still exported for use by other modules.
// ---------------------------------------------------------------------------
export async function resolvePrDiff(ctx: EnvContext): Promise<string> {
const prShas = await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
if (prShas == null) {
console.warn("Unable to resolve PR branches");
return "";
}
const workspace = ctx.get("GITHUB_WORKSPACE");
const { baseSha, headSha } = prShas;
return runCommand([
"git",
"-C",
workspace,
"diff",
"--color=never",
`${baseSha}..${headSha}`,
]);
}
// ---------------------------------------------------------------------------
// Placeholder resolution
// ---------------------------------------------------------------------------
async function resolveVariable(name: string, ctx: EnvContext): Promise<string> {
switch (name) {
case "CODEX_ACTION_ISSUE_TITLE": {
const event = await getGitHubEventData(ctx);
const issue = event.issue ?? event.pull_request;
return issue?.title ?? "";
}
case "CODEX_ACTION_ISSUE_BODY": {
const event = await getGitHubEventData(ctx);
const issue = event.issue ?? event.pull_request;
return issue?.body ?? "";
}
case "CODEX_ACTION_GITHUB_EVENT_PATH": {
return ctx.get("GITHUB_EVENT_PATH");
}
case "CODEX_ACTION_BASE_REF": {
const event = await getGitHubEventData(ctx);
return event?.pull_request?.base?.ref ?? "";
}
case "CODEX_ACTION_HEAD_REF": {
const event = await getGitHubEventData(ctx);
return event?.pull_request?.head?.ref ?? "";
}
case "CODEX_ACTION_PR_DIFF": {
return resolvePrDiff(ctx);
}
// -------------------------------------------------------------------
// Add new template variables here.
// -------------------------------------------------------------------
default: {
// Unknown variable leave it blank to avoid leaking placeholders to the
// final prompt. The alternative would be to `fail()` here, but silently
// ignoring unknown placeholders is more forgiving and better matches the
// behaviour of typical template engines.
console.warn(`Unknown template variable: ${name}`);
return "";
}
}
}
async function getPrShas(
ctx: EnvContext,
): Promise<{ baseSha: string; headSha: string } | null> {
const event = await getGitHubEventData(ctx);
const pr = event.pull_request;
if (!pr) {
console.warn("event.pull_request is not defined");
return null;
}
// Prefer explicit SHAs if available to avoid relying on local branch names.
const baseSha: string | undefined = pr.base?.sha;
const headSha: string | undefined = pr.head?.sha;
if (!baseSha || !headSha) {
console.warn("one of base or head is not defined on event.pull_request");
return null;
}
return { baseSha, headSha };
}

42
.github/actions/codex/src/review.ts vendored Normal file
View File

@@ -0,0 +1,42 @@
import type { EnvContext } from "./env-context";
import { runCodex } from "./run-codex";
import { postComment } from "./post-comment";
import { addEyesReaction } from "./add-reaction";
/**
* Handle `pull_request_review` events. We treat the review body the same way
* as a normal comment.
*/
export async function onReview(ctx: EnvContext): Promise<void> {
const triggerPhrase = ctx.tryGet("INPUT_TRIGGER_PHRASE");
if (!triggerPhrase) {
console.warn("Empty trigger phrase: skipping.");
return;
}
const reviewBody = ctx.tryGet("GITHUB_EVENT_REVIEW_BODY");
if (!reviewBody) {
console.warn("Review body not found in environment: skipping.");
return;
}
if (!reviewBody.includes(triggerPhrase)) {
console.log(
`Trigger phrase '${triggerPhrase}' not found: nothing to do for this review.`,
);
return;
}
const prompt = reviewBody.replace(triggerPhrase, "").trim();
if (prompt.length === 0) {
console.warn("Prompt is empty after removing trigger phrase: skipping.");
return;
}
await addEyesReaction(ctx);
const lastMessage = await runCodex(prompt, ctx);
await postComment(lastMessage, ctx);
}

56
.github/actions/codex/src/run-codex.ts vendored Normal file
View File

@@ -0,0 +1,56 @@
import { fail } from "./fail";
import { EnvContext } from "./env-context";
import { tmpdir } from "os";
import { join } from "node:path";
import { readFile, mkdtemp } from "fs/promises";
import { resolveWorkspacePath } from "./github-workspace";
/**
* Runs the Codex CLI with the provided prompt and returns the output written
* to the "last message" file.
*/
export async function runCodex(
prompt: string,
ctx: EnvContext,
): Promise<string> {
const OPENAI_API_KEY = ctx.get("OPENAI_API_KEY");
const tempDirPath = await mkdtemp(join(tmpdir(), "codex-"));
const lastMessageOutput = join(tempDirPath, "codex-prompt.md");
const args = ["/usr/local/bin/codex-exec"];
const inputCodexArgs = ctx.tryGet("INPUT_CODEX_ARGS")?.trim();
if (inputCodexArgs) {
args.push(...inputCodexArgs.split(/\s+/));
}
args.push("--output-last-message", lastMessageOutput, prompt);
const env: Record<string, string> = { ...process.env, OPENAI_API_KEY };
const INPUT_CODEX_HOME = ctx.tryGet("INPUT_CODEX_HOME");
if (INPUT_CODEX_HOME) {
env.CODEX_HOME = resolveWorkspacePath(INPUT_CODEX_HOME, ctx);
}
console.log(`Running Codex: ${JSON.stringify(args)}`);
const result = Bun.spawnSync(args, {
stdout: "inherit",
stderr: "inherit",
env,
});
if (!result.success) {
fail(`Codex failed: see above for details.`);
}
// Read the output generated by Codex.
let lastMessage: string;
try {
lastMessage = await readFile(lastMessageOutput, "utf8");
} catch (err) {
fail(`Failed to read Codex output at '${lastMessageOutput}': ${err}`);
}
return lastMessage;
}

View File

@@ -0,0 +1,33 @@
// Validate the inputs passed to the composite action.
// The script currently ensures that the provided configuration file exists and
// matches the expected schema.
import type { Config } from "./config";
import { existsSync } from "fs";
import * as path from "path";
import { fail } from "./fail";
export function performAdditionalValidation(config: Config, workspace: string) {
// Additional validation: ensure referenced prompt files exist and are Markdown.
for (const [label, details] of Object.entries(config.labels)) {
// Determine which prompt key is present (the schema guarantees exactly one).
const promptPathStr =
(details as any).prompt ?? (details as any).promptPath;
if (promptPathStr) {
const promptPath = path.isAbsolute(promptPathStr)
? promptPathStr
: path.join(workspace, promptPathStr);
if (!existsSync(promptPath)) {
fail(`Prompt file for label '${label}' not found: ${promptPath}`);
}
if (!promptPath.endsWith(".md")) {
fail(
`Prompt file for label '${label}' must be a .md file (got ${promptPathStr}).`,
);
}
}
}
}

15
.github/actions/codex/tsconfig.json vendored Normal file
View File

@@ -0,0 +1,15 @@
{
"compilerOptions": {
"lib": ["ESNext"],
"target": "ESNext",
"module": "ESNext",
"moduleDetection": "force",
"moduleResolution": "bundler",
"noEmit": true,
"strict": true,
"skipLibCheck": true
},
"include": ["src"]
}

3
.github/codex/home/config.toml vendored Normal file
View File

@@ -0,0 +1,3 @@
model = "o3"
# Consider setting [mcp_servers] here!

9
.github/codex/labels/codex-attempt.md vendored Normal file
View File

@@ -0,0 +1,9 @@
Attempt to solve the reported issue.
If a code change is required, create a new branch, commit the fix, and open a pull request that resolves the problem.
Here is the original GitHub issue that triggered this run:
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}

7
.github/codex/labels/codex-review.md vendored Normal file
View File

@@ -0,0 +1,7 @@
Review this PR and respond with a very concise final message, formatted in Markdown.
There should be a summary of the changes (1-2 sentences) and a few bullet points if necessary.
Then provide the **review** (1-2 sentences plus bullet points, friendly tone).
{CODEX_ACTION_GITHUB_EVENT_PATH} contains the JSON that triggered this GitHub workflow. It contains the `base` and `head` refs that define this PR. Both refs are available locally.

7
.github/codex/labels/codex-triage.md vendored Normal file
View File

@@ -0,0 +1,7 @@
Troubleshoot whether the reported issue is valid.
Provide a concise and respectful comment summarizing the findings.
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}

26
.github/dependabot.yaml vendored Normal file
View File

@@ -0,0 +1,26 @@
# https://docs.github.com/en/code-security/dependabot/working-with-dependabot/dependabot-options-reference#package-ecosystem-
version: 2
updates:
- package-ecosystem: bun
directory: .github/actions/codex
schedule:
interval: weekly
- package-ecosystem: cargo
directories:
- codex-rs
- codex-rs/*
schedule:
interval: weekly
- package-ecosystem: devcontainers
directory: /
schedule:
interval: weekly
- package-ecosystem: docker
directory: codex-cli
schedule:
interval: weekly
- package-ecosystem: github-actions
directory: /
schedule:
interval: weekly

28
.github/dotslash-config.json vendored Normal file
View File

@@ -0,0 +1,28 @@
{
"outputs": {
"codex-exec": {
"platforms": {
"macos-aarch64": { "regex": "^codex-exec-aarch64-apple-darwin\\.zst$", "path": "codex-exec" },
"macos-x86_64": { "regex": "^codex-exec-x86_64-apple-darwin\\.zst$", "path": "codex-exec" },
"linux-x86_64": { "regex": "^codex-exec-x86_64-unknown-linux-musl\\.zst$", "path": "codex-exec" },
"linux-aarch64": { "regex": "^codex-exec-aarch64-unknown-linux-musl\\.zst$", "path": "codex-exec" }
}
},
"codex": {
"platforms": {
"macos-aarch64": { "regex": "^codex-aarch64-apple-darwin\\.zst$", "path": "codex" },
"macos-x86_64": { "regex": "^codex-x86_64-apple-darwin\\.zst$", "path": "codex" },
"linux-x86_64": { "regex": "^codex-x86_64-unknown-linux-musl\\.zst$", "path": "codex" },
"linux-aarch64": { "regex": "^codex-aarch64-unknown-linux-musl\\.zst$", "path": "codex" }
}
},
"codex-linux-sandbox": {
"platforms": {
"linux-x86_64": { "regex": "^codex-linux-sandbox-x86_64-unknown-linux-musl\\.zst$", "path": "codex-linux-sandbox" },
"linux-aarch64": { "regex": "^codex-linux-sandbox-aarch64-unknown-linux-musl\\.zst$", "path": "codex-linux-sandbox" }
}
}
}
}

View File

@@ -19,40 +19,67 @@ jobs:
with:
node-version: 22
# Run codex-cli/ tasks first because they are higher signal.
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
version: 10.8.1
run_install: false
- name: Install dependencies (codex-cli)
working-directory: codex-cli
run: npm ci
- name: Check formatting (codex-cli)
working-directory: codex-cli
run: npm run format
- name: Run tests (codex-cli)
working-directory: codex-cli
run: npm run test
- name: Lint (codex-cli)
working-directory: codex-cli
- name: Get pnpm store directory
id: pnpm-cache
shell: bash
run: |
npm run lint -- \
echo "store_path=$(pnpm store path --silent)" >> $GITHUB_OUTPUT
- name: Setup pnpm cache
uses: actions/cache@v4
with:
path: ${{ steps.pnpm-cache.outputs.store_path }}
key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/pnpm-lock.yaml') }}
restore-keys: |
${{ runner.os }}-pnpm-store-
- name: Install dependencies
run: pnpm install
# Run all tasks using workspace filters
- name: Check TypeScript code formatting
working-directory: codex-cli
run: pnpm run format
- name: Check Markdown and config file formatting
run: pnpm run format
- name: Run tests
run: pnpm run test
- name: Lint
run: |
pnpm --filter @openai/codex exec -- eslint src tests --ext ts --ext tsx \
--report-unused-disable-directives \
--rule "no-console:error" \
--rule "no-debugger:error" \
--max-warnings=-1
- name: Typecheck (codex-cli)
- name: Type-check
run: pnpm run typecheck
- name: Build
run: pnpm run build
- name: Ensure staging a release works.
working-directory: codex-cli
run: npm run typecheck
env:
GH_TOKEN: ${{ github.token }}
run: pnpm stage-release
- name: Build (codex-cli)
working-directory: codex-cli
run: npm run build
- name: Ensure root README.md contains only ASCII and certain Unicode code points
run: ./scripts/asciicheck.py README.md
- name: Check root README ToC
run: python3 scripts/readme_toc.py README.md
# Run formatting checks in the root directory last.
- name: Install dependencies (root)
run: npm ci
- name: Check formatting (root)
run: npm run format
- name: Ensure codex-cli/README.md contains only ASCII and certain Unicode code points
run: ./scripts/asciicheck.py codex-cli/README.md
- name: Check codex-cli/README ToC
run: python3 scripts/readme_toc.py codex-cli/README.md

View File

@@ -23,7 +23,7 @@ jobs:
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
path-to-document: docs/CLA.md
path-to-document: https://github.com/openai/codex/blob/main/docs/CLA.md
path-to-signatures: signatures/cla.json
branch: cla-signatures
allowlist: dependabot[bot]

27
.github/workflows/codespell.yml vendored Normal file
View File

@@ -0,0 +1,27 @@
# Codespell configuration is within .codespellrc
---
name: Codespell
on:
push:
branches: [main]
pull_request:
branches: [main]
permissions:
contents: read
jobs:
codespell:
name: Check for spelling errors
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Annotate locations with typos
uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
- name: Codespell
uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2
with:
ignore_words_file: .codespellignore

95
.github/workflows/codex.yml vendored Normal file
View File

@@ -0,0 +1,95 @@
name: Codex
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
jobs:
codex:
# This `if` check provides complex filtering logic to avoid running Codex
# on every PR. Admittedly, one thing this does not verify is whether the
# sender has write access to the repo: that must be done as part of a
# runtime step.
#
# Note the label values should match the ones in the .github/codex/labels
# folder.
if: |
(github.event_name == 'issues' && (
(github.event.action == 'labeled' && (github.event.label.name == 'codex-attempt' || github.event.label.name == 'codex-triage'))
)) ||
(github.event_name == 'pull_request' && github.event.action == 'labeled' && github.event.label.name == 'codex-review')
runs-on: ubuntu-latest
permissions:
contents: write # can push or create branches
issues: write # for comments + labels on issues/PRs
pull-requests: write # for PR comments/labels
steps:
# TODO: Consider adding an optional mode (--dry-run?) to actions/codex
# that verifies whether Codex should actually be run for this event.
# (For example, it may be rejected because the sender does not have
# write access to the repo.) The benefit would be two-fold:
# 1. As the first step of this job, it gives us a chance to add a reaction
# or comment to the PR/issue ASAP to "ack" the request.
# 2. It saves resources by skipping the clone and setup steps below if
# Codex is not going to run.
- name: Checkout repository
uses: actions/checkout@v4
# We install the dependencies like we would for an ordinary CI job,
# particularly because Codex will not have network access to install
# these dependencies.
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: 22
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
version: 10.8.1
run_install: false
- name: Get pnpm store directory
id: pnpm-cache
shell: bash
run: |
echo "store_path=$(pnpm store path --silent)" >> $GITHUB_OUTPUT
- name: Setup pnpm cache
uses: actions/cache@v4
with:
path: ${{ steps.pnpm-cache.outputs.store_path }}
key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/pnpm-lock.yaml') }}
restore-keys: |
${{ runner.os }}-pnpm-store-
- name: Install dependencies
run: pnpm install
- uses: dtolnay/rust-toolchain@1.88
with:
targets: x86_64-unknown-linux-gnu
components: clippy
- uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
${{ github.workspace }}/codex-rs/target/
key: cargo-ubuntu-24.04-x86_64-unknown-linux-gnu-${{ hashFiles('**/Cargo.lock') }}
# Note it is possible that the `verify` step internal to Run Codex will
# fail, in which case the work to setup the repo was worthless :(
- name: Run Codex
uses: ./.github/actions/codex
with:
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
github_token: ${{ secrets.GITHUB_TOKEN }}
codex_home: ./.github/codex/home

118
.github/workflows/rust-ci.yml vendored Normal file
View File

@@ -0,0 +1,118 @@
name: rust-ci
on:
pull_request:
branches:
- main
paths:
- "codex-rs/**"
- ".github/**"
push:
branches:
- main
workflow_dispatch:
# For CI, we build in debug (`--profile dev`) rather than release mode so we
# get signal faster.
jobs:
# CI that don't need specific targets
general:
name: Format / etc
runs-on: ubuntu-24.04
defaults:
run:
working-directory: codex-rs
steps:
- uses: actions/checkout@v4
- uses: dtolnay/rust-toolchain@1.88
with:
components: rustfmt
- name: cargo fmt
run: cargo fmt -- --config imports_granularity=Item --check
# CI to validate on different os/targets
lint_build_test:
name: ${{ matrix.runner }} - ${{ matrix.target }}
runs-on: ${{ matrix.runner }}
timeout-minutes: 30
defaults:
run:
working-directory: codex-rs
strategy:
fail-fast: false
matrix:
# Note: While Codex CLI does not support Windows today, we include
# Windows in CI to ensure the code at least builds there.
include:
- runner: macos-14
target: aarch64-apple-darwin
- runner: macos-14
target: x86_64-apple-darwin
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
- runner: ubuntu-24.04
target: x86_64-unknown-linux-gnu
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-gnu
- runner: windows-latest
target: x86_64-pc-windows-msvc
steps:
- uses: actions/checkout@v4
- uses: dtolnay/rust-toolchain@1.88
with:
targets: ${{ matrix.target }}
components: clippy
- uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
${{ github.workspace }}/codex-rs/target/
key: cargo-${{ matrix.runner }}-${{ matrix.target }}-${{ hashFiles('**/Cargo.lock') }}
- if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
name: Install musl build tools
run: |
sudo apt install -y musl-tools pkg-config
- name: cargo clippy
id: clippy
continue-on-error: true
run: cargo clippy --target ${{ matrix.target }} --all-features --tests -- -D warnings
# Running `cargo build` from the workspace root builds the workspace using
# the union of all features from third-party crates. This can mask errors
# where individual crates have underspecified features. To avoid this, we
# run `cargo build` for each crate individually, though because this is
# slower, we only do this for the x86_64-unknown-linux-gnu target.
- name: cargo build individual crates
id: build
if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' }}
continue-on-error: true
run: find . -name Cargo.toml -mindepth 2 -maxdepth 2 -print0 | xargs -0 -n1 -I{} bash -c 'cd "$(dirname "{}")" && cargo build'
- name: cargo test
id: test
continue-on-error: true
run: cargo test --all-features --target ${{ matrix.target }}
env:
RUST_BACKTRACE: 1
# Fail the job if any of the previous steps failed.
- name: verify all steps passed
if: |
steps.clippy.outcome == 'failure' ||
steps.build.outcome == 'failure' ||
steps.test.outcome == 'failure'
run: |
echo "One or more checks failed (clippy, build, or test). See logs for details."
exit 1

193
.github/workflows/rust-release.yml vendored Normal file
View File

@@ -0,0 +1,193 @@
# Release workflow for codex-rs.
# To release, follow a workflow like:
# ```
# git tag -a rust-v0.1.0 -m "Release 0.1.0"
# git push origin rust-v0.1.0
# ```
name: rust-release
on:
push:
tags:
- "rust-v*.*.*"
concurrency:
group: ${{ github.workflow }}
cancel-in-progress: true
jobs:
tag-check:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Validate tag matches Cargo.toml version
shell: bash
run: |
set -euo pipefail
echo "::group::Tag validation"
# 1. Must be a tag and match the regex
[[ "${GITHUB_REF_TYPE}" == "tag" ]] \
|| { echo "❌ Not a tag push"; exit 1; }
[[ "${GITHUB_REF_NAME}" =~ ^rust-v[0-9]+\.[0-9]+\.[0-9]+(-(alpha|beta)(\.[0-9]+)?)?$ ]] \
|| { echo "❌ Tag '${GITHUB_REF_NAME}' doesn't match expected format"; exit 1; }
# 2. Extract versions
tag_ver="${GITHUB_REF_NAME#rust-v}"
cargo_ver="$(grep -m1 '^version' codex-rs/Cargo.toml \
| sed -E 's/version *= *"([^"]+)".*/\1/')"
# 3. Compare
[[ "${tag_ver}" == "${cargo_ver}" ]] \
|| { echo "❌ Tag ${tag_ver} ≠ Cargo.toml ${cargo_ver}"; exit 1; }
echo "✅ Tag and Cargo.toml agree (${tag_ver})"
echo "::endgroup::"
build:
needs: tag-check
name: ${{ matrix.runner }} - ${{ matrix.target }}
runs-on: ${{ matrix.runner }}
timeout-minutes: 30
defaults:
run:
working-directory: codex-rs
strategy:
fail-fast: false
matrix:
include:
- runner: macos-14
target: aarch64-apple-darwin
- runner: macos-14
target: x86_64-apple-darwin
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
- runner: ubuntu-24.04
target: x86_64-unknown-linux-gnu
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-gnu
steps:
- uses: actions/checkout@v4
- uses: dtolnay/rust-toolchain@1.88
with:
targets: ${{ matrix.target }}
- uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
${{ github.workspace }}/codex-rs/target/
key: cargo-release-${{ matrix.runner }}-${{ matrix.target }}-${{ hashFiles('**/Cargo.lock') }}
- if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
name: Install musl build tools
run: |
sudo apt install -y musl-tools pkg-config
- name: Cargo build
run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-exec --bin codex-linux-sandbox
- name: Stage artifacts
shell: bash
run: |
dest="dist/${{ matrix.target }}"
mkdir -p "$dest"
cp target/${{ matrix.target }}/release/codex-exec "$dest/codex-exec-${{ matrix.target }}"
cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
# After https://github.com/openai/codex/pull/1228 is merged and a new
# release is cut with an artifacts built after that PR, the `-gnu`
# variants can go away as we will only use the `-musl` variants.
- if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'x86_64-unknown-linux-gnu' || matrix.target == 'aarch64-unknown-linux-gnu' || matrix.target == 'aarch64-unknown-linux-musl' }}
name: Stage Linux-only artifacts
shell: bash
run: |
dest="dist/${{ matrix.target }}"
cp target/${{ matrix.target }}/release/codex-linux-sandbox "$dest/codex-linux-sandbox-${{ matrix.target }}"
- name: Compress artifacts
shell: bash
run: |
# Path that contains the uncompressed binaries for the current
# ${{ matrix.target }}
dest="dist/${{ matrix.target }}"
# For compatibility with environments that lack the `zstd` tool we
# additionally create a `.tar.gz` alongside every single binary that
# we publish. The end result is:
# codex-<target>.zst (existing)
# codex-<target>.tar.gz (new)
# ...same naming for codex-exec-* and codex-linux-sandbox-*
# 1. Produce a .tar.gz for every file in the directory *before* we
# run `zstd --rm`, because that flag deletes the original files.
for f in "$dest"/*; do
base="$(basename "$f")"
# Skip files that are already archives (shouldn't happen, but be
# safe).
if [[ "$base" == *.tar.gz ]]; then
continue
fi
# Create per-binary tar.gz
tar -C "$dest" -czf "$dest/${base}.tar.gz" "$base"
# Also create .zst (existing behaviour) *and* remove the original
# uncompressed binary to keep the directory small.
zstd -T0 -19 --rm "$dest/$base"
done
- uses: actions/upload-artifact@v4
with:
name: ${{ matrix.target }}
# Upload the per-binary .zst files as well as the new .tar.gz
# equivalents we generated in the previous step.
path: |
codex-rs/dist/${{ matrix.target }}/*
release:
needs: build
name: release
runs-on: ubuntu-latest
steps:
- uses: actions/download-artifact@v4
with:
path: dist
- name: List
run: ls -R dist/
- name: Define release name
id: release_name
run: |
# Extract the version from the tag name, which is in the format
# "rust-v0.1.0".
version="${GITHUB_REF_NAME#rust-v}"
echo "name=${version}" >> $GITHUB_OUTPUT
- name: Create GitHub Release
uses: softprops/action-gh-release@v2
with:
name: ${{ steps.release_name.outputs.name }}
tag_name: ${{ github.ref_name }}
files: dist/**
# For now, tag releases as "prerelease" because we are not claiming
# the Rust CLI is stable yet.
prerelease: true
- uses: facebook/dotslash-publish-release@v2
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
tag: ${{ github.ref_name }}
config: .github/dotslash-config.json

18
.gitignore vendored
View File

@@ -1,5 +1,11 @@
# deps
# Node.js dependencies
node_modules
.pnpm-store
.pnpm-debug.log
# Keep pnpm-lock.yaml
!pnpm-lock.yaml
# build
dist/
@@ -17,9 +23,14 @@ result
.vscode/
.idea/
.history/
.zed/
*.swp
*~
# cli tools
CLAUDE.md
.claude/
# caches
.cache/
.turbo/
@@ -61,9 +72,12 @@ Icon?
# Unwanted package managers
.yarn/
yarn.lock
pnpm-lock.yaml
# release
package.json-e
session.ts-e
CHANGELOG.ignore.md
CHANGELOG.ignore.md
# nix related
.direnv
.envrc

1
.husky/pre-commit Normal file
View File

@@ -0,0 +1 @@
pnpm lint-staged

4
.npmrc Normal file
View File

@@ -0,0 +1,4 @@
shamefully-hoist=true
strict-peer-dependencies=false
node-linker=hoisted
prefer-workspace-packages=true

View File

@@ -1,2 +1,3 @@
/codex-cli/dist
/codex-cli/node_modules
pnpm-lock.yaml

18
.vscode/launch.json vendored Normal file
View File

@@ -0,0 +1,18 @@
{
"version": "0.2.0",
"configurations": [
{
"type": "lldb",
"request": "launch",
"name": "Cargo launch",
"cargo": {
"cwd": "${workspaceFolder}/codex-rs",
"args": [
"build",
"--bin=codex-tui"
]
},
"args": []
}
]
}

10
.vscode/settings.json vendored Normal file
View File

@@ -0,0 +1,10 @@
{
"rust-analyzer.checkOnSave": true,
"rust-analyzer.check.command": "clippy",
"rust-analyzer.check.extraArgs": ["--all-features", "--tests"],
"rust-analyzer.rustfmt.extraArgs": ["--config", "imports_granularity=Item"],
"[rust]": {
"editor.defaultFormatter": "rust-lang.rust-analyzer",
"editor.formatOnSave": true,
}
}

9
AGENTS.md Normal file
View File

@@ -0,0 +1,9 @@
# Rust/codex-rs
In the codex-rs folder where the rust code lives:
- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR`. You operate in a sandbox where `CODEX_SANDBOX_NETWORK_DISABLED=1` will be set whenever you use the `shell` tool. Any existing code that uses `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` was authored with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations.
Before creating a pull request with changes to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix` (in `codex-rs` directory) to fix any linter issues in the code, ensure the test suite passes by running `cargo test --all-features` in the `codex-rs` directory.
When making individual changes prefer running tests on individual files or projects first.

View File

@@ -2,19 +2,185 @@
You can install any of these versions: `npm install -g codex@version`
## 0.1.2504172351
## `0.1.2505172129`
### 🪲 Bug Fixes
- Add node version check (#1007)
- Persist token after refresh (#1006)
## `0.1.2505171619`
- `codex --login` + `codex --free` (#998)
## `0.1.2505161800`
- Sign in with chatgpt credits (#974)
- Add support for OpenAI tool type, local_shell (#961)
## `0.1.2505161243`
- Sign in with chatgpt (#963)
- Session history viewer (#912)
- Apply patch issue when using different cwd (#942)
- Diff command for filenames with special characters (#954)
## `0.1.2505160811`
- `codex-mini-latest` (#951)
## `0.1.2505140839`
### 🪲 Bug Fixes
- Gpt-4.1 apply_patch handling (#930)
- Add support for fileOpener in config.json (#911)
- Patch in #366 and #367 for marked-terminal (#916)
- Remember to set lastIndex = 0 on shared RegExp (#918)
- Always load version from package.json at runtime (#909)
- Tweak the label for citations for better rendering (#919)
- Tighten up some logic around session timestamps and ids (#922)
- Change EventMsg enum so every variant takes a single struct (#925)
- Reasoning default to medium, show workdir when supplied (#931)
- Test_dev_null_write() was not using echo as intended (#923)
## `0.1.2504301751`
### 🚀 Features
- User config api key (#569)
- `@mention` files in codex (#701)
- Add `--reasoning` CLI flag (#314)
- Lower default retry wait time and increase number of tries (#720)
- Add common package registries domains to allowed-domains list (#414)
### 🪲 Bug Fixes
- Insufficient quota message (#758)
- Input keyboard shortcut opt+delete (#685)
- `/diff` should include untracked files (#686)
- Only allow running without sandbox if explicitly marked in safe container (#699)
- Tighten up check for /usr/bin/sandbox-exec (#710)
- Check if sandbox-exec is available (#696)
- Duplicate messages in quiet mode (#680)
## `0.1.2504251709`
### 🚀 Features
- Add openai model info configuration (#551)
- Added provider to run quiet mode function (#571)
- Create parent directories when creating new files (#552)
- Print bug report URL in terminal instead of opening browser (#510) (#528)
- Add support for custom provider configuration in the user config (#537)
- Add support for OpenAI-Organization and OpenAI-Project headers (#626)
- Add specific instructions for creating API keys in error msg (#581)
- Enhance toCodePoints to prevent potential unicode 14 errors (#615)
- More native keyboard navigation in multiline editor (#655)
- Display error on selection of invalid model (#594)
### 🪲 Bug Fixes
- Model selection (#643)
- Nits in apply patch (#640)
- Input keyboard shortcuts (#676)
- `apply_patch` unicode characters (#625)
- Don't clear turn input before retries (#611)
- More loosely match context for apply_patch (#610)
- Update bug report template - there is no --revision flag (#614)
- Remove outdated copy of text input and external editor feature (#670)
- Remove unreachable "disableResponseStorage" logic flow introduced in #543 (#573)
- Non-openai mode - fix for gemini content: null, fix 429 to throw before stream (#563)
- Only allow going up in history when not already in history if input is empty (#654)
- Do not grant "node" user sudo access when using run_in_container.sh (#627)
- Update scripts/build_container.sh to use pnpm instead of npm (#631)
- Update lint-staged config to use pnpm --filter (#582)
- Non-openai mode - don't default temp and top_p (#572)
- Fix error catching when checking for updates (#597)
- Close stdin when running an exec tool call (#636)
## `0.1.2504221401`
### 🚀 Features
- Show actionable errors when api keys are missing (#523)
- Add CLI `--version` flag (#492)
### 🪲 Bug Fixes
- Agent loop for ZDR (`disableResponseStorage`) (#543)
- Fix relative `workdir` check for `apply_patch` (#556)
- Minimal mid-stream #429 retry loop using existing back-off (#506)
- Inconsistent usage of base URL and API key (#507)
- Remove requirement for api key for ollama (#546)
- Support `[provider]_BASE_URL` (#542)
## `0.1.2504220136`
### 🚀 Features
- Add support for ZDR orgs (#481)
- Include fractional portion of chunk that exceeds stdout/stderr limit (#497)
## `0.1.2504211509`
### 🚀 Features
- Support multiple providers via Responses-Completion transformation (#247)
- Add user-defined safe commands configuration and approval logic #380 (#386)
- Allow switching approval modes when prompted to approve an edit/command (#400)
- Add support for `/diff` command autocomplete in TerminalChatInput (#431)
- Auto-open model selector if user selects deprecated model (#427)
- Read approvalMode from config file (#298)
- `/diff` command to view git diff (#426)
- Tab completions for file paths (#279)
- Add /command autocomplete (#317)
- Allow multi-line input (#438)
### 🪲 Bug Fixes
- `full-auto` support in quiet mode (#374)
- Enable shell option for child process execution (#391)
- Configure husky and lint-staged for pnpm monorepo (#384)
- Command pipe execution by improving shell detection (#437)
- Name of the file not matching the name of the component (#354)
- Allow proper exit from new Switch approval mode dialog (#453)
- Ensure /clear resets context and exclude system messages from approximateTokenUsed count (#443)
- `/clear` now clears terminal screen and resets context left indicator (#425)
- Correct fish completion function name in CLI script (#485)
- Auto-open model-selector when model is not found (#448)
- Remove unnecessary isLoggingEnabled() checks (#420)
- Improve test reliability for `raw-exec` (#434)
- Unintended tear down of agent loop (#483)
- Remove extraneous type casts (#462)
## `0.1.2504181820`
### 🚀 Features
- Add `/bug` report command (#312)
- Notify when a newer version is available (#333)
### 🪲 Bug Fixes
- Update context left display logic in TerminalChatInput component (#307)
- Improper spawn of sh on Windows Powershell (#318)
- `/bug` report command, thinking indicator (#381)
- Include pnpm lock file (#377)
## `0.1.2504172351`
### 🚀 Features
- Add Nix flake for reproducible development environments (#225)
### 🐛 Bug Fixes
### 🪲 Bug Fixes
- Handle invalid commands (#304)
- Raw-exec-process-group.test improve reliability and error handling (#280)
- Canonicalize the writeable paths used in seatbelt policy (#275)
## 0.1.2504172304
## `0.1.2504172304`
### 🚀 Features
@@ -27,7 +193,7 @@ You can install any of these versions: `npm install -g codex@version`
- `--config`/`-c` flag to open global instructions in nvim (#158)
- Update position of cursor when navigating input history with arrow keys to the end of the text (#255)
### 🐛 Bug Fixes
### 🪲 Bug Fixes
- Correct word deletion logic for trailing spaces (Ctrl+Backspace) (#131)
- Improve Windows compatibility for CLI commands and sandbox (#261)

70
PNPM.md Normal file
View File

@@ -0,0 +1,70 @@
# Migration to pnpm
This project has been migrated from npm to pnpm to improve dependency management and developer experience.
## Why pnpm?
- **Faster installation**: pnpm is significantly faster than npm and yarn
- **Disk space savings**: pnpm uses a content-addressable store to avoid duplication
- **Phantom dependency prevention**: pnpm creates a strict node_modules structure
- **Native workspaces support**: simplified monorepo management
## How to use pnpm
### Installation
```bash
# Global installation of pnpm
npm install -g pnpm@10.8.1
# Or with corepack (available with Node.js 22+)
corepack enable
corepack prepare pnpm@10.8.1 --activate
```
### Common commands
| npm command | pnpm equivalent |
| --------------- | ---------------- |
| `npm install` | `pnpm install` |
| `npm run build` | `pnpm run build` |
| `npm test` | `pnpm test` |
| `npm run lint` | `pnpm run lint` |
### Workspace-specific commands
| Action | Command |
| ------------------------------------------ | ---------------------------------------- |
| Run a command in a specific package | `pnpm --filter @openai/codex run build` |
| Install a dependency in a specific package | `pnpm --filter @openai/codex add lodash` |
| Run a command in all packages | `pnpm -r run test` |
## Monorepo structure
```
codex/
├── pnpm-workspace.yaml # Workspace configuration
├── .npmrc # pnpm configuration
├── package.json # Root dependencies and scripts
├── codex-cli/ # Main package
│ └── package.json # codex-cli specific dependencies
└── docs/ # Documentation (future package)
```
## Configuration files
- **pnpm-workspace.yaml**: Defines the packages included in the monorepo
- **.npmrc**: Configures pnpm behavior
- **Root package.json**: Contains shared scripts and dependencies
## CI/CD
CI/CD workflows have been updated to use pnpm instead of npm. Make sure your CI environments use pnpm 10.8.1 or higher.
## Known issues
If you encounter issues with pnpm, try the following solutions:
1. Remove the `node_modules` folder and `pnpm-lock.yaml` file, then run `pnpm install`
2. Make sure you're using pnpm 10.8.1 or higher
3. Verify that Node.js 22 or higher is installed

535
README.md
View File

@@ -1,51 +1,61 @@
<h1 align="center">OpenAI Codex CLI</h1>
<p align="center">Lightweight coding agent that runs in your terminal</p>
<p align="center"><code>npm i -g @openai/codex</code></p>
<p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>
![Codex demo GIF using: codex "explain this codebase to me"](./.github/demo.gif)
This is the home of the **Codex CLI**, which is a coding agent from OpenAI that runs locally on your computer. If you are looking for the _cloud-based agent_ from OpenAI, **Codex [Web]**, see <https://chatgpt.com/codex>.
<!-- ![Codex demo GIF using: codex "explain this codebase to me"](./.github/demo.gif) -->
---
<details>
<summary><strong>Table&nbsp;of&nbsp;Contents</strong></summary>
<summary><strong>Table of contents</strong></summary>
- [Experimental Technology Disclaimer](#experimental-technology-disclaimer)
<!-- Begin ToC -->
- [Experimental technology disclaimer](#experimental-technology-disclaimer)
- [Quickstart](#quickstart)
- [Why Codex?](#whycodex)
- [Security Model \& Permissions](#securitymodelpermissions)
- [OpenAI API Users](#openai-api-users)
- [OpenAI Plus/Pro Users](#openai-pluspro-users)
- [Why Codex?](#why-codex)
- [Security model & permissions](#security-model--permissions)
- [Platform sandboxing details](#platform-sandboxing-details)
- [System Requirements](#systemrequirements)
- [CLI Reference](#clireference)
- [Memory \& Project Docs](#memoryprojectdocs)
- [Noninteractive / CI mode](#noninteractivecimode)
- [System requirements](#system-requirements)
- [CLI reference](#cli-reference)
- [Memory & project docs](#memory--project-docs)
- [Non-interactive / CI mode](#non-interactive--ci-mode)
- [Model Context Protocol (MCP)](#model-context-protocol-mcp)
- [Tracing / verbose logging](#tracing--verbose-logging)
- [Recipes](#recipes)
- [Installation](#installation)
- [DotSlash](#dotslash)
- [Configuration](#configuration)
- [FAQ](#faq)
- [Funding Opportunity](#funding-opportunity)
- [Zero data retention (ZDR) usage](#zero-data-retention-zdr-usage)
- [Codex open source fund](#codex-open-source-fund)
- [Contributing](#contributing)
- [Development workflow](#development-workflow)
- [Nix Flake Development](#nix-flake-development)
- [Writing highimpact code changes](#writing-highimpact-code-changes)
- [Writing high-impact code changes](#writing-high-impact-code-changes)
- [Opening a pull request](#opening-a-pull-request)
- [Review process](#review-process)
- [Community values](#community-values)
- [Getting help](#getting-help)
- [Contributor License Agreement (CLA)](#contributor-license-agreement-cla)
- [Contributor license agreement (CLA)](#contributor-license-agreement-cla)
- [Quick fixes](#quick-fixes)
- [Releasing `codex`](#releasing-codex)
- [Security \& Responsible AI](#securityresponsibleai)
- [Security & responsible AI](#security--responsible-ai)
- [License](#license)
- [Zero Data Retention (ZDR) Organization Limitation](#zero-data-retention-zdr-organization-limitation)
<!-- End ToC -->
</details>
---
## Experimental Technology Disclaimer
## Experimental technology disclaimer
Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. Were building it in the open with the community and welcome:
Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. We're building it in the open with the community and welcome:
- Bug reports
- Feature requests
@@ -56,27 +66,103 @@ Help us improve by filing issues or submitting PRs (see the section below for ho
## Quickstart
Install globally:
Install globally with your preferred package manager:
```shell
npm install -g @openai/codex
npm install -g @openai/codex # Alternatively: `brew install codex`
```
Or go to the [latest GitHub Release](https://github.com/openai/codex/releases/latest) and download the appropriate binary for your platform.
### OpenAI API Users
Next, set your OpenAI API key as an environment variable:
```shell
export OPENAI_API_KEY="your-api-key-here"
```
> **Note:** This command sets the key only for your current terminal session. To make it permanent, add the `export` line to your shell's configuration file (e.g., `~/.zshrc`).
>
> **Tip:** You can also place your API key into a `.env` file at the root of your project:
>
> ```env
> OPENAI_API_KEY=your-api-key-here
> ```
>
> The CLI will automatically load variables from `.env` (via `dotenv/config`).
> [!NOTE]
> This command sets the key only for your current terminal session. You can add the `export` line to your shell's configuration file (e.g., `~/.zshrc`), but we recommend setting it for the session.
### OpenAI Plus/Pro Users
If you have a paid OpenAI account, run the following to start the login process:
```
codex login
```
If you complete the process successfully, you should have a `~/.codex/auth.json` file that contains the credentials that Codex will use.
To verify whether you are currently logged in, run:
```
codex login status
```
If you encounter problems with the login flow, please comment on <https://github.com/openai/codex/issues/1243>.
<details>
<summary><strong>Use <code>--profile</code> to use other models</strong></summary>
Codex also allows you to use other providers that support the OpenAI Chat Completions (or Responses) API.
To do so, you must first define custom [providers](./config.md#model_providers) in `~/.codex/config.toml`. For example, the provider for a standard Ollama setup would be defined as follows:
```toml
[model_providers.ollama]
name = "Ollama"
base_url = "http://localhost:11434/v1"
```
The `base_url` will have `/chat/completions` appended to it to build the full URL for the request.
For providers that also require an `Authorization` header of the form `Bearer: SECRET`, an `env_key` can be specified, which indicates the environment variable to read to use as the value of `SECRET` when making a request:
```toml
[model_providers.openrouter]
name = "OpenRouter"
base_url = "https://openrouter.ai/api/v1"
env_key = "OPENROUTER_API_KEY"
```
Providers that speak the Responses API are also supported by adding `wire_api = "responses"` as part of the definition. Accessing OpenAI models via Azure is an example of such a provider, though it also requires specifying additional `query_params` that need to be appended to the request URL:
```toml
[model_providers.azure]
name = "Azure"
# Make sure you set the appropriate subdomain for this URL.
base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"
env_key = "AZURE_OPENAI_API_KEY" # Or "OPENAI_API_KEY", whichever you use.
# Newer versions appear to support the responses API, see https://github.com/openai/codex/pull/1321
query_params = { api-version = "2025-04-01-preview" }
wire_api = "responses"
```
Once you have defined a provider you wish to use, you can configure it as your default provider as follows:
```toml
model_provider = "azure"
```
> [!TIP]
> If you find yourself experimenting with a variety of models and providers, then you likely want to invest in defining a _profile_ for each configuration like so:
```toml
[profiles.o3]
model_provider = "azure"
model = "o3"
[profiles.mistral]
model_provider = "ollama"
model = "mistral"
```
This way, you can specify one command-line argument (.e.g., `--profile o3`, `--profile mistral`) to override multiple settings together.
</details>
<br />
Run interactively:
@@ -91,143 +177,150 @@ codex "explain this codebase to me"
```
```shell
codex --approval-mode full-auto "create the fanciest todo-list app"
codex --full-auto "create the fanciest todo-list app"
```
Thats it Codex will scaffold a file, run it inside a sandbox, install any
That's it - Codex will scaffold a file, run it inside a sandbox, install any
missing dependencies, and show you the live result. Approve the changes and
theyll be committed to your working directory.
they'll be committed to your working directory.
---
## Why Codex?
## Why Codex?
Codex CLI is built for developers who already **live in the terminal** and want
ChatGPTlevel reasoning **plus** the power to actually run code, manipulate
files, and iterate all under version control. In short, its _chatdriven
ChatGPT-level reasoning **plus** the power to actually run code, manipulate
files, and iterate - all under version control. In short, it's _chat-driven
development_ that understands and executes your repo.
- **Zero setup** bring your OpenAI API key and it just works!
- **Zero setup** - bring your OpenAI API key and it just works!
- **Full auto-approval, while safe + secure** by running network-disabled and directory-sandboxed
- **Multimodal** pass in screenshots or diagrams to implement features ✨
- **Multimodal** - pass in screenshots or diagrams to implement features ✨
And it's **fully open-source** so you can see and contribute to how it develops!
---
## Security Model & Permissions
## Security model & permissions
Codex lets you decide _how much autonomy_ the agent receives and auto-approval policy via the
`--approval-mode` flag (or the interactive onboarding prompt):
Codex lets you decide _how much autonomy_ you want to grant the agent. The following options can be configured independently:
| Mode | What the agent may do without asking | Still requires approval |
| ------------------------- | -------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| **Suggest** <br>(default) | • Read any file in the repo | • **All** file writes/patches <br>• **Any** arbitrary shell commands (aside from reading files) |
| **Auto Edit** | • Read **and** applypatch writes to files | • **All** shell commands |
| **Full Auto** | • Read/write files <br>• Execute shell commands (network disabled, writes limited to your workdir) | |
- [`approval_policy`](./codex-rs/config.md#approval_policy) determines when you should be prompted to approve whether Codex can execute a command
- [`sandbox`](./codex-rs/config.md#sandbox) determines the _sandbox policy_ that Codex uses to execute untrusted commands
In **Full Auto** every command is run **networkdisabled** and confined to the
current working directory (plus temporary files) for defenseindepth. Codex
will also show a warning/confirmation if you start in **autoedit** or
**fullauto** while the directory is _not_ tracked by Git, so you always have a
safety net.
By default, Codex runs with `--ask-for-approval untrusted` and `--sandbox read-only`, which means that:
Coming soon: youll be able to whitelist specific commands to autoexecute with
the network enabled, once were confident in additional safeguards.
- The user is prompted to approve every command not on the set of "trusted" commands built into Codex (`cat`, `ls`, etc.)
- Approved commands are run outside of a sandbox because user approval implies "trust," in this case.
Running Codex with the `--full-auto` convenience flag changes the configuration to `--ask-for-approval on-failure` and `--sandbox workspace-write`, which means that:
- Codex does not initially ask for user approval before running an individual command.
- Though when it runs a command, it is run under a sandbox in which:
- It can read any file on the system.
- It can only write files under the current directory (or the directory specified via `--cd`).
- Network requests are completely disabled.
- Only if the command exits with a non-zero exit code will it ask the user for approval. If granted, it will re-attempt the command outside of the sandbox. (A common case is when Codex cannot `npm install` a dependency because that requires network access.)
Again, these two options can be configured independently. For example, if you want Codex to perform an "exploration" where you are happy for it to read anything it wants but you never want to be prompted, you could run Codex with `--ask-for-approval never` and `--sandbox read-only`.
### Platform sandboxing details
The hardening mechanism Codex uses depends on your OS:
The mechanism Codex uses to implement the sandbox policy depends on your OS:
- **macOS 12+** commands are wrapped with **Apple Seatbelt** (`sandbox-exec`).
- **macOS 12+** uses **Apple Seatbelt** and runs commands using `sandbox-exec` with a profile (`-p`) that corresponds to the `--sandbox` that was specified.
- **Linux** uses a combination of Landlock/seccomp APIs to enforce the `sandbox` configuration.
- Everything is placed in a readonly jail except for a small set of
writable roots (`$PWD`, `$TMPDIR`, `~/.codex`, etc.).
- Outbound network is _fully blocked_ by default even if a child process
tries to `curl` somewhere it will fail.
- **Linux** there is no sandboxing by default.
We recommend using Docker for sandboxing, where Codex launches itself inside a **minimal
container image** and mounts your repo _read/write_ at the same path. A
custom `iptables`/`ipset` firewall script denies all egress except the
OpenAI API. This gives you deterministic, reproducible runs without needing
root on the host. You can use the [`run_in_container.sh`](./codex-cli/scripts/run_in_container.sh) script to set up the sandbox.
Note that when running Linux in a containerized environment such as Docker, sandboxing may not work if the host/container configuration does not support the necessary Landlock/seccomp APIs. In such cases, we recommend configuring your Docker container so that it provides the sandbox guarantees you are looking for and then running `codex` with `--sandbox danger-full-access` (or, more simply, the `--dangerously-bypass-approvals-and-sandbox` flag) within your container.
---
## System Requirements
## System requirements
| Requirement | Details |
| --------------------------- | --------------------------------------------------------------- |
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 **via WSL2** |
| Node.js | **22 or newer** (LTS recommended) |
| Git (optional, recommended) | 2.23+ for builtin PR helpers |
| RAM | 4GB minimum (8GB recommended) |
> Never run `sudo npm install -g`; fix npm permissions instead.
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 **via WSL2** |
| Git (optional, recommended) | 2.23+ for built-in PR helpers |
| RAM | 4-GB minimum (8-GB recommended) |
---
## CLI Reference
## CLI reference
| Command | Purpose | Example |
| ------------------------------------ | ----------------------------------- | ------------------------------------ |
| `codex` | Interactive REPL | `codex` |
| `codex ""` | Initial prompt for interactive REPL | `codex "fix lint errors"` |
| `codex -q "…"` | Noninteractive "quiet mode" | `codex -q --json "explain utils.ts"` |
| `codex completion <bash\|zsh\|fish>` | Print shell completion script | `codex completion bash` |
| Command | Purpose | Example |
| ------------------ | ---------------------------------- | ------------------------------- |
| `codex` | Interactive TUI | `codex` |
| `codex "..."` | Initial prompt for interactive TUI | `codex "fix lint errors"` |
| `codex exec "..."` | Non-interactive "automation mode" | `codex exec "explain utils.ts"` |
Key flags: `--model/-m`, `--approval-mode/-a`, `--quiet/-q`, and `--notify`.
Key flags: `--model/-m`, `--ask-for-approval/-a`.
---
## Memory & Project Docs
## Memory & project docs
Codex merges Markdown instructions in this order:
You can give Codex extra instructions and guidance using `AGENTS.md` files. Codex looks for `AGENTS.md` files in the following places, and merges them top-down:
1. `~/.codex/instructions.md` personal global guidance
2. `codex.md` at repo root shared project notes
3. `codex.md` in cwd subpackage specifics
Disable with `--no-project-doc` or `CODEX_DISABLE_PROJECT_DOC=1`.
1. `~/.codex/AGENTS.md` - personal global guidance
2. `AGENTS.md` at repo root - shared project notes
3. `AGENTS.md` in the current working directory - sub-folder/feature specifics
---
## Noninteractive / CI mode
## Non-interactive / CI mode
Run Codex headless in pipelines. Example GitHub Action step:
Run Codex head-less in pipelines. Example GitHub Action step:
```yaml
- name: Update changelog via Codex
run: |
npm install -g @openai/codex
export OPENAI_API_KEY="${{ secrets.OPENAI_KEY }}"
codex -a auto-edit --quiet "update CHANGELOG for next release"
codex exec --full-auto "update CHANGELOG for next release"
```
Set `CODEX_QUIET_MODE=1` to silence interactive UI noise.
## Model Context Protocol (MCP)
## Tracing / Verbose Logging
The Codex CLI can be configured to leverage MCP servers by defining an [`mcp_servers`](./codex-rs/config.md#mcp_servers) section in `~/.codex/config.toml`. It is intended to mirror how tools such as Claude and Cursor define `mcpServers` in their respective JSON config files, though the Codex format is slightly different since it uses TOML rather than JSON, e.g.:
Setting the environment variable `DEBUG=true` prints full API request and response details:
```shell
DEBUG=true codex
```toml
# IMPORTANT: the top-level key is `mcp_servers` rather than `mcpServers`.
[mcp_servers.server-name]
command = "npx"
args = ["-y", "mcp-server"]
env = { "API_KEY" = "value" }
```
> [!TIP]
> It is somewhat experimental, but the Codex CLI can also be run as an MCP _server_ via `codex mcp`. If you launch it with an MCP client such as `npx @modelcontextprotocol/inspector codex mcp` and send it a `tools/list` request, you will see that there is only one tool, `codex`, that accepts a grab-bag of inputs, including a catch-all `config` map for anything you might want to override. Feel free to play around with it and provide feedback via GitHub issues.
## Tracing / verbose logging
Because Codex is written in Rust, it honors the `RUST_LOG` environment variable to configure its logging behavior.
The TUI defaults to `RUST_LOG=codex_core=info,codex_tui=info` and log messages are written to `~/.codex/log/codex-tui.log`, so you can leave the following running in a separate terminal to monitor log messages as they are written:
```
tail -F ~/.codex/log/codex-tui.log
```
By comparison, the non-interactive mode (`codex exec`) defaults to `RUST_LOG=error`, but messages are printed inline, so there is no need to monitor a separate file.
See the Rust documentation on [`RUST_LOG`](https://docs.rs/env_logger/latest/env_logger/#enabling-logging) for more information on the configuration options.
---
## Recipes
Below are a few bitesize examples you can copypaste. Replace the text in quotes with your own task. See the [prompting guide](https://github.com/openai/codex/blob/main/codex-cli/examples/prompting_guide.md) for more tips and usage patterns.
Below are a few bite-size examples you can copy-paste. Replace the text in quotes with your own task. See the [prompting guide](https://github.com/openai/codex/blob/main/codex-cli/examples/prompting_guide.md) for more tips and usage patterns.
| ✨ | What you type | What happens |
| --- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| 1 | `codex "Refactor the Dashboard component to React Hooks"` | Codex rewrites the class component, runs `npm test`, and shows the diff. |
| 1 | `codex "Refactor the Dashboard component to React Hooks"` | Codex rewrites the class component, runs `npm test`, and shows the diff. |
| 2 | `codex "Generate SQL migrations for adding a users table"` | Infers your ORM, creates migration files, and runs them in a sandboxed DB. |
| 3 | `codex "Write unit tests for utils/date.ts"` | Generates tests, executes them, and iterates until they pass. |
| 4 | `codex "Bulkrename *.jpeg *.jpg with git mv"` | Safely renames files and updates imports/usages. |
| 5 | `codex "Explain what this regex does: ^(?=.*[A-Z]).{8,}$"` | Outputs a stepbystep human explanation. |
| 4 | `codex "Bulk-rename *.jpeg -> *.jpg with git mv"` | Safely renames files and updates imports/usages. |
| 5 | `codex "Explain what this regex does: ^(?=.*[A-Z]).{8,}$"` | Outputs a step-by-step human explanation. |
| 6 | `codex "Carefully review this repo, and propose 3 high impact well-scoped PRs"` | Suggests impactful PRs in the current codebase. |
| 7 | `codex "Look for vulnerabilities and create a security review report"` | Finds and explains security bugs. |
@@ -236,38 +329,65 @@ Below are a few bitesize examples you can copypaste. Replace the text in q
## Installation
<details open>
<summary><strong>From npm (Recommended)</strong></summary>
<summary><strong>Install Codex CLI using your preferred package manager.</strong></summary>
From `brew` (recommended, downloads only the binary for your platform):
```bash
npm install -g @openai/codex
# or
yarn global add @openai/codex
# or
bun install -g @openai/codex
brew install codex
```
From `npm` (generally more readily available, but downloads binaries for all supported platforms):
```bash
npm i -g @openai/codex
```
Or go to the [latest GitHub Release](https://github.com/openai/codex/releases/latest) and download the appropriate binary for your platform.
Admittedly, each GitHub Release contains many executables, but in practice, you likely want one of these:
- macOS
- Apple Silicon/arm64: `codex-aarch64-apple-darwin.tar.gz`
- x86_64 (older Mac hardware): `codex-x86_64-apple-darwin.tar.gz`
- Linux
- x86_64: `codex-x86_64-unknown-linux-musl.tar.gz`
- arm64: `codex-aarch64-unknown-linux-musl.tar.gz`
Each archive contains a single entry with the platform baked into the name (e.g., `codex-x86_64-unknown-linux-musl`), so you likely want to rename it to `codex` after extracting it.
### DotSlash
The GitHub Release also contains a [DotSlash](https://dotslash-cli.com/) file for the Codex CLI named `codex`. Using a DotSlash file makes it possible to make a lightweight commit to source control to ensure all contributors use the same version of an executable, regardless of what platform they use for development.
</details>
<details>
<summary><strong>Build from source</strong></summary>
<summary><strong>Build from source</strong></summary>
```bash
# Clone the repository and navigate to the CLI package
# Clone the repository and navigate to the root of the Cargo workspace.
git clone https://github.com/openai/codex.git
cd codex/codex-cli
cd codex/codex-rs
# Install dependencies and build
npm install
npm run build
# Install the Rust toolchain, if necessary.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
source "$HOME/.cargo/env"
rustup component add rustfmt
rustup component add clippy
# Get the usage and the options
node ./dist/cli.js --help
# Build Codex.
cargo build
# Run the locallybuilt CLI directly
node ./dist/cli.js
# Launch the TUI with a sample prompt.
cargo run --bin codex -- "explain this codebase to me"
# Or link the command globally for convenience
npm link
# After making changes, ensure the code is clean.
cargo fmt -- --config imports_granularity=Item
cargo clippy --tests
# Run the tests.
cargo test
```
</details>
@@ -276,22 +396,11 @@ npm link
## Configuration
Codex looks for config files in **`~/.codex/`**.
Codex supports a rich set of configuration options documented in [`codex-rs/config.md`](./codex-rs/config.md).
```yaml
# ~/.codex/config.yaml
model: o4-mini # Default model
fullAutoErrorMode: ask-user # or ignore-and-continue
notify: true # Enable desktop notifications for responses
```
By default, Codex loads its configuration from `~/.codex/config.toml`.
You can also define custom instructions:
```yaml
# ~/.codex/instructions.md
- Always respond with emojis
- Only use git commands if I explicitly mention you should
```
Though `--config` can be used to set/override ad-hoc config values for individual invocations of `codex`.
---
@@ -326,43 +435,38 @@ Codex runs model-generated commands in a sandbox. If a proposed command or file
<details>
<summary>Does it work on Windows?</summary>
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) Codex has been tested on macOS and Linux with Node ≥ 22.
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex has been tested on macOS and Linux with Node 22.
</details>
---
## Zero Data Retention (ZDR) Organization Limitation
## Zero data retention (ZDR) usage
> **Note:** Codex CLI does **not** currently support OpenAI organizations with [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) enabled.
If your OpenAI organization has Zero Data Retention enabled, you may encounter errors such as:
Codex CLI **does** support OpenAI organizations with [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) enabled. If your OpenAI organization has Zero Data Retention enabled and you still encounter errors such as:
```
OpenAI rejected the request. Error details: Status: 400, Code: unsupported_parameter, Type: invalid_request_error, Message: 400 Previous response cannot be used for this organization due to Zero Data Retention.
```
**Why?**
Ensure you are running `codex` with `--config disable_response_storage=true` or add this line to `~/.codex/config.toml` to avoid specifying the command line option each time:
- Codex CLI relies on the Responses API with `store:true` to enable internal reasoning steps.
- As noted in the [docs](https://platform.openai.com/docs/guides/your-data#responses-api), the Responses API requires a 30-day retention period by default, or when the store parameter is set to true.
- ZDR organizations cannot use `store:true`, so requests will fail.
```toml
disable_response_storage = true
```
**What can I do?**
- If you are part of a ZDR organization, Codex CLI will not work until support is added.
- We are tracking this limitation and will update the documentation if support becomes available.
See [the configuration documentation on `disable_response_storage`](./codex-rs/config.md#disable_response_storage) for details.
---
## Funding Opportunity
## Codex open source fund
Were excited to launch a **$1 million initiative** supporting open source projects that use Codex CLI and other OpenAI models.
We're excited to launch a **$1 million initiative** supporting open source projects that use Codex CLI and other OpenAI models.
- Grants are awarded in **$25,000** API credit increments.
- Grants are awarded up to **$25,000** API credits.
- Applications are reviewed **on a rolling basis**.
**Interested? [Apply here](https://openai.com/form/codex-open-source-fund/).**
**Interested? [Apply here](https://openai.com/form/codex-open-source-fund/).**
---
@@ -370,153 +474,96 @@ Were excited to launch a **$1 million initiative** supporting open source pr
This project is under active development and the code will likely change pretty significantly. We'll update this message once that's complete!
More broadly we welcome contributions whether you are opening your very first pull request or youre a seasoned maintainer. At the same time we care about reliability and longterm maintainability, so the bar for merging code is intentionally **high**. The guidelines below spell out what highquality means in practice and should make the whole process transparent and friendly.
More broadly we welcome contributions - whether you are opening your very first pull request or you're a seasoned maintainer. At the same time we care about reliability and long-term maintainability, so the bar for merging code is intentionally **high**. The guidelines below spell out what "high-quality" means in practice and should make the whole process transparent and friendly.
### Development workflow
- Create a _topic branch_ from `main` e.g. `feat/interactive-prompt`.
- Create a _topic branch_ from `main` - e.g. `feat/interactive-prompt`.
- Keep your changes focused. Multiple unrelated fixes should be opened as separate PRs.
- Use `npm run test:watch` during development for superfast feedback.
- We use **Vitest** for unit tests, **ESLint** + **Prettier** for style, and **TypeScript** for typechecking.
- Before pushing, run the full test/type/lint suite:
- Following the [development setup](#development-workflow) instructions above, ensure your change is free of lint warnings and test failures.
### Git Hooks with Husky
This project uses [Husky](https://typicode.github.io/husky/) to enforce code quality checks:
- **Pre-commit hook**: Automatically runs lint-staged to format and lint files before committing
- **Pre-push hook**: Runs tests and type checking before pushing to the remote
These hooks help maintain code quality and prevent pushing code with failing tests. For more details, see [HUSKY.md](./codex-cli/HUSKY.md).
```bash
npm test && npm run lint && npm run typecheck
```
- If you have **not** yet signed the Contributor License Agreement (CLA), add a PR comment containing the exact text
```text
I have read the CLA Document and I hereby sign the CLA
```
The CLAAssistant bot will turn the PR status green once all authors have signed.
```bash
# Watch mode (tests rerun on change)
npm run test:watch
# Typecheck without emitting files
npm run typecheck
# Automatically fix lint + prettier issues
npm run lint:fix
npm run format:fix
```
#### Nix Flake Development
Prerequisite: Nix >= 2.4 with flakes enabled (`experimental-features = nix-command flakes` in `~/.config/nix/nix.conf`).
Enter a Nix development shell:
```bash
nix develop
```
This shell includes Node.js, installs dependencies, builds the CLI, and provides a `codex` command alias.
Build and run the CLI directly:
```bash
nix build
./result/bin/codex --help
```
Run the CLI via the flake app:
```bash
nix run .#codex
```
### Writing highimpact code changes
### Writing high-impact code changes
1. **Start with an issue.** Open a new one or comment on an existing discussion so we can agree on the solution before code is written.
2. **Add or update tests.** Every new feature or bugfix should come with test coverage that fails before your change and passes afterwards. 100 % coverage is not required, but aim for meaningful assertions.
3. **Document behaviour.** If your change affects userfacing behaviour, update the README, inline help (`codex --help`), or relevant example projects.
2. **Add or update tests.** Every new feature or bug-fix should come with test coverage that fails before your change and passes afterwards. 100% coverage is not required, but aim for meaningful assertions.
3. **Document behaviour.** If your change affects user-facing behaviour, update the README, inline help (`codex --help`), or relevant example projects.
4. **Keep commits atomic.** Each commit should compile and the tests should pass. This makes reviews and potential rollbacks easier.
### Opening a pull request
- Fill in the PR template (or include similar information) **What? Why? How?**
- Run **all** checks locally (`npm test && npm run lint && npm run typecheck`). CI failures that could have been caught locally slow down the process.
- Make sure your branch is uptodate with `main` and that you have resolved merge conflicts.
- Mark the PR as **Ready for review** only when you believe it is in a mergeable state.
- Fill in the PR template (or include similar information) - **What? Why? How?**
- Run **all** checks locally (`cargo test && cargo clippy --tests && cargo fmt -- --config imports_granularity=Item`). CI failures that could have been caught locally slow down the process.
- Make sure your branch is up-to-date with `main` and that you have resolved merge conflicts.
- Mark the PR as **Ready for review** only when you believe it is in a merge-able state.
### Review process
1. One maintainer will be assigned as a primary reviewer.
2. We may ask for changes please do not take this personally. We value the work, we just also value consistency and longterm maintainability.
3. When there is consensus that the PR meets the bar, a maintainer will squashandmerge.
2. We may ask for changes - please do not take this personally. We value the work, we just also value consistency and long-term maintainability.
3. When there is consensus that the PR meets the bar, a maintainer will squash-and-merge.
### Community values
- **Be kind and inclusive.** Treat others with respect; we follow the [Contributor Covenant](https://www.contributor-covenant.org/).
- **Assume good intent.** Written communication is hard err on the side of generosity.
- **Assume good intent.** Written communication is hard - err on the side of generosity.
- **Teach & learn.** If you spot something confusing, open an issue or PR with improvements.
### Getting help
If you run into problems setting up the project, would like feedback on an idea, or just want to say _hi_ please open a Discussion or jump into the relevant issue. We are happy to help.
If you run into problems setting up the project, would like feedback on an idea, or just want to say _hi_ - please open a Discussion or jump into the relevant issue. We are happy to help.
Together we can make Codex CLI an incredible tool. **Happy hacking!** :rocket:
### Contributor License Agreement (CLA)
### Contributor license agreement (CLA)
All contributors **must** accept the CLA. The process is lightweight:
1. Open your pull request.
2. Paste the following comment (or reply `recheck` if youve signed before):
2. Paste the following comment (or reply `recheck` if you've signed before):
```text
I have read the CLA Document and I hereby sign the CLA
```
3. The CLAAssistant bot records your signature in the repo and marks the status check as passed.
3. The CLA-Assistant bot records your signature in the repo and marks the status check as passed.
No special Git commands, email attachments, or commit footers required.
#### Quick fixes
| Scenario | Command |
| ----------------- | ----------------------------------------------------------------------------------------- |
| Amend last commit | `git commit --amend -s --no-edit && git push -f` |
| GitHub UI only | Edit the commit message in the PR → add<br>`Signed-off-by: Your Name <email@example.com>` |
| Scenario | Command |
| ----------------- | ------------------------------------------------ |
| Amend last commit | `git commit --amend -s --no-edit && git push -f` |
The **DCO check** blocks merges until every commit in the PR carries the footer (with squash this is just the one).
### Releasing `codex`
To publish a new version of the CLI, run the release scripts defined in `codex-cli/package.json`:
_For admins only._
1. Open the `codex-cli` directory
2. Make sure you're on a branch like `git checkout -b bump-version`
3. Bump the version and `CLI_VERSION` to current datetime: `npm run release:version`
4. Commit the version bump (with DCO sign-off):
```bash
git add codex-cli/src/utils/session.ts codex-cli/package.json
git commit -s -m "chore(release): codex-cli v$(node -p \"require('./codex-cli/package.json').version\")"
```
5. Copy README, build, and publish to npm: `npm run release`
6. Push to branch: `git push origin HEAD`
Make sure you are on `main` and have no local changes. Then run:
```shell
VERSION=0.2.0 # Can also be 0.2.0-alpha.1 or any valid Rust version.
./codex-rs/scripts/create_github_release.sh "$VERSION"
```
This will make a local commit on top of `main` with `version` set to `$VERSION` in `codex-rs/Cargo.toml` (note that on `main`, we leave the version as `version = "0.0.0"`).
This will push the commit using the tag `rust-v${VERSION}`, which in turn kicks off [the release workflow](.github/workflows/rust-release.yml). This will create a new GitHub Release named `$VERSION`.
If everything looks good in the generated GitHub Release, uncheck the **pre-release** box so it is the latest release.
Create a PR to update [`Formula/c/codex.rb`](https://github.com/Homebrew/homebrew-core/blob/main/Formula/c/codex.rb) on Homebrew.
---
## Security &amp; Responsible AI
## Security & responsible AI
Have you discovered a vulnerability or have concerns about model output? Please email **security@openai.com** and we will respond promptly.
Have you discovered a vulnerability or have concerns about model output? Please e-mail **security@openai.com** and we will respond promptly.
---
## License
This repository is licensed under the [Apache-2.0 License](LICENSE).
This repository is licensed under the [Apache-2.0 License](LICENSE).

View File

@@ -35,10 +35,10 @@ conventional_commits = true
commit_parsers = [
{ message = "^feat", group = "<!-- 0 -->🚀 Features" },
{ message = "^fix", group = "<!-- 1 -->🐛 Bug Fixes" },
{ message = "^fix", group = "<!-- 1 -->🪲 Bug Fixes" },
{ message = "^bump", group = "<!-- 6 -->🛳️ Release" },
# Fallback  skip anything that didn't match the above rules.
{ message = ".*", group = "<!-- 10 -->💼 Other", skip = true },
{ message = ".*", group = "<!-- 10 -->💼 Other" },
]
filter_unconventional = false

View File

@@ -1,6 +1,6 @@
module.exports = {
root: true,
env: { browser: true, es2020: true },
env: { browser: true, node: true, es2020: true },
extends: [
"eslint:recommended",
"plugin:@typescript-eslint/recommended",

7
codex-cli/.gitignore vendored Normal file
View File

@@ -0,0 +1,7 @@
# Added by ./scripts/install_native_deps.sh
/bin/codex-aarch64-apple-darwin
/bin/codex-aarch64-unknown-linux-musl
/bin/codex-linux-sandbox-arm64
/bin/codex-linux-sandbox-x64
/bin/codex-x86_64-apple-darwin
/bin/codex-x86_64-unknown-linux-musl

View File

@@ -1,32 +0,0 @@
#!/usr/bin/env sh
if [ -z "$husky_skip_init" ]; then
debug () {
if [ "$HUSKY_DEBUG" = "1" ]; then
echo "husky (debug) - $1"
fi
}
readonly hook_name="$(basename -- "$0")"
debug "starting $hook_name..."
if [ "$HUSKY" = "0" ]; then
debug "HUSKY env variable is set to 0, skipping hook"
exit 0
fi
if [ -f ~/.huskyrc ]; then
debug "sourcing ~/.huskyrc"
. ~/.huskyrc
fi
readonly husky_skip_init=1
export husky_skip_init
sh -e "$0" "$@"
exitCode="$?"
if [ $exitCode != 0 ]; then
echo "husky - $hook_name hook exited with code $exitCode (error)"
fi
exit $exitCode
fi

View File

@@ -1,5 +0,0 @@
#!/usr/bin/env sh
. "$(dirname -- "$0")/_/husky.sh"
# Run lint-staged to check files that are about to be committed
npm run pre-commit

View File

@@ -1,5 +0,0 @@
#!/usr/bin/env sh
. "$(dirname -- "$0")/_/husky.sh"
# Run tests and type checking before pushing
npm test && npm run typecheck

View File

@@ -1,9 +0,0 @@
{
"*.{ts,tsx}": [
"eslint --fix",
"prettier --write"
],
"*.{json,md,yml}": [
"prettier --write"
]
}

View File

@@ -1,4 +1,4 @@
FROM node:20-slim
FROM node:24-slim
ARG TZ
ENV TZ="$TZ"
@@ -20,7 +20,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
less \
man-db \
procps \
sudo \
unzip \
ripgrep \
zsh \
@@ -47,10 +46,14 @@ RUN npm install -g codex.tgz \
&& rm -rf /usr/local/share/npm-global/lib/node_modules/codex-cli/tests \
&& rm -rf /usr/local/share/npm-global/lib/node_modules/codex-cli/docs
# Copy and set up firewall script
COPY scripts/init_firewall.sh /usr/local/bin/
# Inside the container we consider the environment already sufficiently locked
# down, therefore instruct Codex CLI to allow running without sandboxing.
ENV CODEX_UNSAFE_ALLOW_NO_SANDBOX=1
# Copy and set up firewall script as root.
USER root
RUN chmod +x /usr/local/bin/init_firewall.sh && \
echo "node ALL=(root) NOPASSWD: /usr/local/bin/init_firewall.sh" > /etc/sudoers.d/node-firewall && \
chmod 0440 /etc/sudoers.d/node-firewall
COPY scripts/init_firewall.sh /usr/local/bin/
RUN chmod 500 /usr/local/bin/init_firewall.sh
# Drop back to non-root.
USER node

736
codex-cli/README.md Normal file
View File

@@ -0,0 +1,736 @@
<h1 align="center">OpenAI Codex CLI</h1>
<p align="center">Lightweight coding agent that runs in your terminal</p>
<p align="center"><code>npm i -g @openai/codex</code></p>
> [!IMPORTANT]
> This is the documentation for the _legacy_ TypeScript implementation of the Codex CLI. It has been superseded by the _Rust_ implementation. See the [README in the root of the Codex repository](https://github.com/openai/codex/blob/main/README.md) for details.
![Codex demo GIF using: codex "explain this codebase to me"](../.github/demo.gif)
---
<details>
<summary><strong>Table of contents</strong></summary>
<!-- Begin ToC -->
- [Experimental technology disclaimer](#experimental-technology-disclaimer)
- [Quickstart](#quickstart)
- [Why Codex?](#why-codex)
- [Security model & permissions](#security-model--permissions)
- [Platform sandboxing details](#platform-sandboxing-details)
- [System requirements](#system-requirements)
- [CLI reference](#cli-reference)
- [Memory & project docs](#memory--project-docs)
- [Non-interactive / CI mode](#non-interactive--ci-mode)
- [Tracing / verbose logging](#tracing--verbose-logging)
- [Recipes](#recipes)
- [Installation](#installation)
- [Configuration guide](#configuration-guide)
- [Basic configuration parameters](#basic-configuration-parameters)
- [Custom AI provider configuration](#custom-ai-provider-configuration)
- [History configuration](#history-configuration)
- [Configuration examples](#configuration-examples)
- [Full configuration example](#full-configuration-example)
- [Custom instructions](#custom-instructions)
- [Environment variables setup](#environment-variables-setup)
- [FAQ](#faq)
- [Zero data retention (ZDR) usage](#zero-data-retention-zdr-usage)
- [Codex open source fund](#codex-open-source-fund)
- [Contributing](#contributing)
- [Development workflow](#development-workflow)
- [Git hooks with Husky](#git-hooks-with-husky)
- [Debugging](#debugging)
- [Writing high-impact code changes](#writing-high-impact-code-changes)
- [Opening a pull request](#opening-a-pull-request)
- [Review process](#review-process)
- [Community values](#community-values)
- [Getting help](#getting-help)
- [Contributor license agreement (CLA)](#contributor-license-agreement-cla)
- [Quick fixes](#quick-fixes)
- [Releasing `codex`](#releasing-codex)
- [Alternative build options](#alternative-build-options)
- [Nix flake development](#nix-flake-development)
- [Security & responsible AI](#security--responsible-ai)
- [License](#license)
<!-- End ToC -->
</details>
---
## Experimental technology disclaimer
Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. We're building it in the open with the community and welcome:
- Bug reports
- Feature requests
- Pull requests
- Good vibes
Help us improve by filing issues or submitting PRs (see the section below for how to contribute)!
## Quickstart
Install globally:
```shell
npm install -g @openai/codex
```
Next, set your OpenAI API key as an environment variable:
```shell
export OPENAI_API_KEY="your-api-key-here"
```
> **Note:** This command sets the key only for your current terminal session. You can add the `export` line to your shell's configuration file (e.g., `~/.zshrc`) but we recommend setting for the session. **Tip:** You can also place your API key into a `.env` file at the root of your project:
>
> ```env
> OPENAI_API_KEY=your-api-key-here
> ```
>
> The CLI will automatically load variables from `.env` (via `dotenv/config`).
<details>
<summary><strong>Use <code>--provider</code> to use other models</strong></summary>
> Codex also allows you to use other providers that support the OpenAI Chat Completions API. You can set the provider in the config file or use the `--provider` flag. The possible options for `--provider` are:
>
> - openai (default)
> - openrouter
> - azure
> - gemini
> - ollama
> - mistral
> - deepseek
> - xai
> - groq
> - arceeai
> - any other provider that is compatible with the OpenAI API
>
> If you use a provider other than OpenAI, you will need to set the API key for the provider in the config file or in the environment variable as:
>
> ```shell
> export <provider>_API_KEY="your-api-key-here"
> ```
>
> If you use a provider not listed above, you must also set the base URL for the provider:
>
> ```shell
> export <provider>_BASE_URL="https://your-provider-api-base-url"
> ```
</details>
<br />
Run interactively:
```shell
codex
```
Or, run with a prompt as input (and optionally in `Full Auto` mode):
```shell
codex "explain this codebase to me"
```
```shell
codex --approval-mode full-auto "create the fanciest todo-list app"
```
That's it - Codex will scaffold a file, run it inside a sandbox, install any
missing dependencies, and show you the live result. Approve the changes and
they'll be committed to your working directory.
---
## Why Codex?
Codex CLI is built for developers who already **live in the terminal** and want
ChatGPT-level reasoning **plus** the power to actually run code, manipulate
files, and iterate - all under version control. In short, it's _chat-driven
development_ that understands and executes your repo.
- **Zero setup** - bring your OpenAI API key and it just works!
- **Full auto-approval, while safe + secure** by running network-disabled and directory-sandboxed
- **Multimodal** - pass in screenshots or diagrams to implement features ✨
And it's **fully open-source** so you can see and contribute to how it develops!
---
## Security model & permissions
Codex lets you decide _how much autonomy_ the agent receives and auto-approval policy via the
`--approval-mode` flag (or the interactive onboarding prompt):
| Mode | What the agent may do without asking | Still requires approval |
| ------------------------- | --------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| **Suggest** <br>(default) | <li>Read any file in the repo | <li>**All** file writes/patches<li> **Any** arbitrary shell commands (aside from reading files) |
| **Auto Edit** | <li>Read **and** apply-patch writes to files | <li>**All** shell commands |
| **Full Auto** | <li>Read/write files <li> Execute shell commands (network disabled, writes limited to your workdir) | - |
In **Full Auto** every command is run **network-disabled** and confined to the
current working directory (plus temporary files) for defense-in-depth. Codex
will also show a warning/confirmation if you start in **auto-edit** or
**full-auto** while the directory is _not_ tracked by Git, so you always have a
safety net.
Coming soon: you'll be able to whitelist specific commands to auto-execute with
the network enabled, once we're confident in additional safeguards.
### Platform sandboxing details
The hardening mechanism Codex uses depends on your OS:
- **macOS 12+** - commands are wrapped with **Apple Seatbelt** (`sandbox-exec`).
- Everything is placed in a read-only jail except for a small set of
writable roots (`$PWD`, `$TMPDIR`, `~/.codex`, etc.).
- Outbound network is _fully blocked_ by default - even if a child process
tries to `curl` somewhere it will fail.
- **Linux** - there is no sandboxing by default.
We recommend using Docker for sandboxing, where Codex launches itself inside a **minimal
container image** and mounts your repo _read/write_ at the same path. A
custom `iptables`/`ipset` firewall script denies all egress except the
OpenAI API. This gives you deterministic, reproducible runs without needing
root on the host. You can use the [`run_in_container.sh`](../codex-cli/scripts/run_in_container.sh) script to set up the sandbox.
---
## System requirements
| Requirement | Details |
| --------------------------- | --------------------------------------------------------------- |
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 **via WSL2** |
| Node.js | **22 or newer** (LTS recommended) |
| Git (optional, recommended) | 2.23+ for built-in PR helpers |
| RAM | 4-GB minimum (8-GB recommended) |
> Never run `sudo npm install -g`; fix npm permissions instead.
---
## CLI reference
| Command | Purpose | Example |
| ------------------------------------ | ----------------------------------- | ------------------------------------ |
| `codex` | Interactive REPL | `codex` |
| `codex "..."` | Initial prompt for interactive REPL | `codex "fix lint errors"` |
| `codex -q "..."` | Non-interactive "quiet mode" | `codex -q --json "explain utils.ts"` |
| `codex completion <bash\|zsh\|fish>` | Print shell completion script | `codex completion bash` |
Key flags: `--model/-m`, `--approval-mode/-a`, `--quiet/-q`, and `--notify`.
---
## Memory & project docs
You can give Codex extra instructions and guidance using `AGENTS.md` files. Codex looks for `AGENTS.md` files in the following places, and merges them top-down:
1. `~/.codex/AGENTS.md` - personal global guidance
2. `AGENTS.md` at repo root - shared project notes
3. `AGENTS.md` in the current working directory - sub-folder/feature specifics
Disable loading of these files with `--no-project-doc` or the environment variable `CODEX_DISABLE_PROJECT_DOC=1`.
---
## Non-interactive / CI mode
Run Codex head-less in pipelines. Example GitHub Action step:
```yaml
- name: Update changelog via Codex
run: |
npm install -g @openai/codex
export OPENAI_API_KEY="${{ secrets.OPENAI_KEY }}"
codex -a auto-edit --quiet "update CHANGELOG for next release"
```
Set `CODEX_QUIET_MODE=1` to silence interactive UI noise.
## Tracing / verbose logging
Setting the environment variable `DEBUG=true` prints full API request and response details:
```shell
DEBUG=true codex
```
---
## Recipes
Below are a few bite-size examples you can copy-paste. Replace the text in quotes with your own task. See the [prompting guide](https://github.com/openai/codex/blob/main/codex-cli/examples/prompting_guide.md) for more tips and usage patterns.
| ✨ | What you type | What happens |
| --- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| 1 | `codex "Refactor the Dashboard component to React Hooks"` | Codex rewrites the class component, runs `npm test`, and shows the diff. |
| 2 | `codex "Generate SQL migrations for adding a users table"` | Infers your ORM, creates migration files, and runs them in a sandboxed DB. |
| 3 | `codex "Write unit tests for utils/date.ts"` | Generates tests, executes them, and iterates until they pass. |
| 4 | `codex "Bulk-rename *.jpeg -> *.jpg with git mv"` | Safely renames files and updates imports/usages. |
| 5 | `codex "Explain what this regex does: ^(?=.*[A-Z]).{8,}$"` | Outputs a step-by-step human explanation. |
| 6 | `codex "Carefully review this repo, and propose 3 high impact well-scoped PRs"` | Suggests impactful PRs in the current codebase. |
| 7 | `codex "Look for vulnerabilities and create a security review report"` | Finds and explains security bugs. |
---
## Installation
<details open>
<summary><strong>From npm (Recommended)</strong></summary>
```bash
npm install -g @openai/codex
# or
yarn global add @openai/codex
# or
bun install -g @openai/codex
# or
pnpm add -g @openai/codex
```
</details>
<details>
<summary><strong>Build from source</strong></summary>
```bash
# Clone the repository and navigate to the CLI package
git clone https://github.com/openai/codex.git
cd codex/codex-cli
# Enable corepack
corepack enable
# Install dependencies and build
pnpm install
pnpm build
# Linux-only: download prebuilt sandboxing binaries (requires gh and zstd).
./scripts/install_native_deps.sh
# Get the usage and the options
node ./dist/cli.js --help
# Run the locally-built CLI directly
node ./dist/cli.js
# Or link the command globally for convenience
pnpm link
```
</details>
---
## Configuration guide
Codex configuration files can be placed in the `~/.codex/` directory, supporting both YAML and JSON formats.
### Basic configuration parameters
| Parameter | Type | Default | Description | Available Options |
| ------------------- | ------- | ---------- | -------------------------------- | ---------------------------------------------------------------------------------------------- |
| `model` | string | `o4-mini` | AI model to use | Any model name supporting OpenAI API |
| `approvalMode` | string | `suggest` | AI assistant's permission mode | `suggest` (suggestions only)<br>`auto-edit` (automatic edits)<br>`full-auto` (fully automatic) |
| `fullAutoErrorMode` | string | `ask-user` | Error handling in full-auto mode | `ask-user` (prompt for user input)<br>`ignore-and-continue` (ignore and proceed) |
| `notify` | boolean | `true` | Enable desktop notifications | `true`/`false` |
### Custom AI provider configuration
In the `providers` object, you can configure multiple AI service providers. Each provider requires the following parameters:
| Parameter | Type | Description | Example |
| --------- | ------ | --------------------------------------- | ----------------------------- |
| `name` | string | Display name of the provider | `"OpenAI"` |
| `baseURL` | string | API service URL | `"https://api.openai.com/v1"` |
| `envKey` | string | Environment variable name (for API key) | `"OPENAI_API_KEY"` |
### History configuration
In the `history` object, you can configure conversation history settings:
| Parameter | Type | Description | Example Value |
| ------------------- | ------- | ------------------------------------------------------ | ------------- |
| `maxSize` | number | Maximum number of history entries to save | `1000` |
| `saveHistory` | boolean | Whether to save history | `true` |
| `sensitivePatterns` | array | Patterns of sensitive information to filter in history | `[]` |
### Configuration examples
1. YAML format (save as `~/.codex/config.yaml`):
```yaml
model: o4-mini
approvalMode: suggest
fullAutoErrorMode: ask-user
notify: true
```
2. JSON format (save as `~/.codex/config.json`):
```json
{
"model": "o4-mini",
"approvalMode": "suggest",
"fullAutoErrorMode": "ask-user",
"notify": true
}
```
### Full configuration example
Below is a comprehensive example of `config.json` with multiple custom providers:
```json
{
"model": "o4-mini",
"provider": "openai",
"providers": {
"openai": {
"name": "OpenAI",
"baseURL": "https://api.openai.com/v1",
"envKey": "OPENAI_API_KEY"
},
"azure": {
"name": "AzureOpenAI",
"baseURL": "https://YOUR_PROJECT_NAME.openai.azure.com/openai",
"envKey": "AZURE_OPENAI_API_KEY"
},
"openrouter": {
"name": "OpenRouter",
"baseURL": "https://openrouter.ai/api/v1",
"envKey": "OPENROUTER_API_KEY"
},
"gemini": {
"name": "Gemini",
"baseURL": "https://generativelanguage.googleapis.com/v1beta/openai",
"envKey": "GEMINI_API_KEY"
},
"ollama": {
"name": "Ollama",
"baseURL": "http://localhost:11434/v1",
"envKey": "OLLAMA_API_KEY"
},
"mistral": {
"name": "Mistral",
"baseURL": "https://api.mistral.ai/v1",
"envKey": "MISTRAL_API_KEY"
},
"deepseek": {
"name": "DeepSeek",
"baseURL": "https://api.deepseek.com",
"envKey": "DEEPSEEK_API_KEY"
},
"xai": {
"name": "xAI",
"baseURL": "https://api.x.ai/v1",
"envKey": "XAI_API_KEY"
},
"groq": {
"name": "Groq",
"baseURL": "https://api.groq.com/openai/v1",
"envKey": "GROQ_API_KEY"
},
"arceeai": {
"name": "ArceeAI",
"baseURL": "https://conductor.arcee.ai/v1",
"envKey": "ARCEEAI_API_KEY"
}
},
"history": {
"maxSize": 1000,
"saveHistory": true,
"sensitivePatterns": []
}
}
```
### Custom instructions
You can create a `~/.codex/AGENTS.md` file to define custom guidance for the agent:
```markdown
- Always respond with emojis
- Only use git commands when explicitly requested
```
### Environment variables setup
For each AI provider, you need to set the corresponding API key in your environment variables. For example:
```bash
# OpenAI
export OPENAI_API_KEY="your-api-key-here"
# Azure OpenAI
export AZURE_OPENAI_API_KEY="your-azure-api-key-here"
export AZURE_OPENAI_API_VERSION="2025-04-01-preview" (Optional)
# OpenRouter
export OPENROUTER_API_KEY="your-openrouter-key-here"
# Similarly for other providers
```
---
## FAQ
<details>
<summary>OpenAI released a model called Codex in 2021 - is this related?</summary>
In 2021, OpenAI released Codex, an AI system designed to generate code from natural language prompts. That original Codex model was deprecated as of March 2023 and is separate from the CLI tool.
</details>
<details>
<summary>Which models are supported?</summary>
Any model available with [Responses API](https://platform.openai.com/docs/api-reference/responses). The default is `o4-mini`, but pass `--model gpt-4.1` or set `model: gpt-4.1` in your config file to override.
</details>
<details>
<summary>Why does <code>o3</code> or <code>o4-mini</code> not work for me?</summary>
It's possible that your [API account needs to be verified](https://help.openai.com/en/articles/10910291-api-organization-verification) in order to start streaming responses and seeing chain of thought summaries from the API. If you're still running into issues, please let us know!
</details>
<details>
<summary>How do I stop Codex from editing my files?</summary>
Codex runs model-generated commands in a sandbox. If a proposed command or file change doesn't look right, you can simply type **n** to deny the command or give the model feedback.
</details>
<details>
<summary>Does it work on Windows?</summary>
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex has been tested on macOS and Linux with Node 22.
</details>
---
## Zero data retention (ZDR) usage
Codex CLI **does** support OpenAI organizations with [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) enabled. If your OpenAI organization has Zero Data Retention enabled and you still encounter errors such as:
```
OpenAI rejected the request. Error details: Status: 400, Code: unsupported_parameter, Type: invalid_request_error, Message: 400 Previous response cannot be used for this organization due to Zero Data Retention.
```
You may need to upgrade to a more recent version with: `npm i -g @openai/codex@latest`
---
## Codex open source fund
We're excited to launch a **$1 million initiative** supporting open source projects that use Codex CLI and other OpenAI models.
- Grants are awarded up to **$25,000** API credits.
- Applications are reviewed **on a rolling basis**.
**Interested? [Apply here](https://openai.com/form/codex-open-source-fund/).**
---
## Contributing
This project is under active development and the code will likely change pretty significantly. We'll update this message once that's complete!
More broadly we welcome contributions - whether you are opening your very first pull request or you're a seasoned maintainer. At the same time we care about reliability and long-term maintainability, so the bar for merging code is intentionally **high**. The guidelines below spell out what "high-quality" means in practice and should make the whole process transparent and friendly.
### Development workflow
- Create a _topic branch_ from `main` - e.g. `feat/interactive-prompt`.
- Keep your changes focused. Multiple unrelated fixes should be opened as separate PRs.
- Use `pnpm test:watch` during development for super-fast feedback.
- We use **Vitest** for unit tests, **ESLint** + **Prettier** for style, and **TypeScript** for type-checking.
- Before pushing, run the full test/type/lint suite:
### Git hooks with Husky
This project uses [Husky](https://typicode.github.io/husky/) to enforce code quality checks:
- **Pre-commit hook**: Automatically runs lint-staged to format and lint files before committing
- **Pre-push hook**: Runs tests and type checking before pushing to the remote
These hooks help maintain code quality and prevent pushing code with failing tests. For more details, see [HUSKY.md](./HUSKY.md).
```bash
pnpm test && pnpm run lint && pnpm run typecheck
```
- If you have **not** yet signed the Contributor License Agreement (CLA), add a PR comment containing the exact text
```text
I have read the CLA Document and I hereby sign the CLA
```
The CLA-Assistant bot will turn the PR status green once all authors have signed.
```bash
# Watch mode (tests rerun on change)
pnpm test:watch
# Type-check without emitting files
pnpm typecheck
# Automatically fix lint + prettier issues
pnpm lint:fix
pnpm format:fix
```
### Debugging
To debug the CLI with a visual debugger, do the following in the `codex-cli` folder:
- Run `pnpm run build` to build the CLI, which will generate `cli.js.map` alongside `cli.js` in the `dist` folder.
- Run the CLI with `node --inspect-brk ./dist/cli.js` The program then waits until a debugger is attached before proceeding. Options:
- In VS Code, choose **Debug: Attach to Node Process** from the command palette and choose the option in the dropdown with debug port `9229` (likely the first option)
- Go to <chrome://inspect> in Chrome and find **localhost:9229** and click **trace**
### Writing high-impact code changes
1. **Start with an issue.** Open a new one or comment on an existing discussion so we can agree on the solution before code is written.
2. **Add or update tests.** Every new feature or bug-fix should come with test coverage that fails before your change and passes afterwards. 100% coverage is not required, but aim for meaningful assertions.
3. **Document behaviour.** If your change affects user-facing behaviour, update the README, inline help (`codex --help`), or relevant example projects.
4. **Keep commits atomic.** Each commit should compile and the tests should pass. This makes reviews and potential rollbacks easier.
### Opening a pull request
- Fill in the PR template (or include similar information) - **What? Why? How?**
- Run **all** checks locally (`npm test && npm run lint && npm run typecheck`). CI failures that could have been caught locally slow down the process.
- Make sure your branch is up-to-date with `main` and that you have resolved merge conflicts.
- Mark the PR as **Ready for review** only when you believe it is in a merge-able state.
### Review process
1. One maintainer will be assigned as a primary reviewer.
2. We may ask for changes - please do not take this personally. We value the work, we just also value consistency and long-term maintainability.
3. When there is consensus that the PR meets the bar, a maintainer will squash-and-merge.
### Community values
- **Be kind and inclusive.** Treat others with respect; we follow the [Contributor Covenant](https://www.contributor-covenant.org/).
- **Assume good intent.** Written communication is hard - err on the side of generosity.
- **Teach & learn.** If you spot something confusing, open an issue or PR with improvements.
### Getting help
If you run into problems setting up the project, would like feedback on an idea, or just want to say _hi_ - please open a Discussion or jump into the relevant issue. We are happy to help.
Together we can make Codex CLI an incredible tool. **Happy hacking!** :rocket:
### Contributor license agreement (CLA)
All contributors **must** accept the CLA. The process is lightweight:
1. Open your pull request.
2. Paste the following comment (or reply `recheck` if you've signed before):
```text
I have read the CLA Document and I hereby sign the CLA
```
3. The CLA-Assistant bot records your signature in the repo and marks the status check as passed.
No special Git commands, email attachments, or commit footers required.
#### Quick fixes
| Scenario | Command |
| ----------------- | ------------------------------------------------ |
| Amend last commit | `git commit --amend -s --no-edit && git push -f` |
The **DCO check** blocks merges until every commit in the PR carries the footer (with squash this is just the one).
### Releasing `codex`
To publish a new version of the CLI you first need to stage the npm package. A
helper script in `codex-cli/scripts/` does all the heavy lifting. Inside the
`codex-cli` folder run:
```bash
# Classic, JS implementation that includes small, native binaries for Linux sandboxing.
pnpm stage-release
# Optionally specify the temp directory to reuse between runs.
RELEASE_DIR=$(mktemp -d)
pnpm stage-release --tmp "$RELEASE_DIR"
# "Fat" package that additionally bundles the native Rust CLI binaries for
# Linux. End-users can then opt-in at runtime by setting CODEX_RUST=1.
pnpm stage-release --native
```
Go to the folder where the release is staged and verify that it works as intended. If so, run the following from the temp folder:
```
cd "$RELEASE_DIR"
npm publish
```
### Alternative build options
#### Nix flake development
Prerequisite: Nix >= 2.4 with flakes enabled (`experimental-features = nix-command flakes` in `~/.config/nix/nix.conf`).
Enter a Nix development shell:
```bash
# Use either one of the commands according to which implementation you want to work with
nix develop .#codex-cli # For entering codex-cli specific shell
nix develop .#codex-rs # For entering codex-rs specific shell
```
This shell includes Node.js, installs dependencies, builds the CLI, and provides a `codex` command alias.
Build and run the CLI directly:
```bash
# Use either one of the commands according to which implementation you want to work with
nix build .#codex-cli # For building codex-cli
nix build .#codex-rs # For building codex-rs
./result/bin/codex --help
```
Run the CLI via the flake app:
```bash
# Use either one of the commands according to which implementation you want to work with
nix run .#codex-cli # For running codex-cli
nix run .#codex-rs # For running codex-rs
```
Use direnv with flakes
If you have direnv installed, you can use the following `.envrc` to automatically enter the Nix shell when you `cd` into the project directory:
```bash
cd codex-rs
echo "use flake ../flake.nix#codex-cli" >> .envrc && direnv allow
cd codex-cli
echo "use flake ../flake.nix#codex-rs" >> .envrc && direnv allow
```
---
## Security & responsible AI
Have you discovered a vulnerability or have concerns about model output? Please e-mail **security@openai.com** and we will respond promptly.
---
## License
This repository is licensed under the [Apache-2.0 License](LICENSE).

View File

@@ -1,20 +0,0 @@
#!/usr/bin/env sh
# resolve script path in case of symlink
SOURCE="$0"
while [ -h "$SOURCE" ]; do
DIR=$(dirname "$SOURCE")
SOURCE=$(readlink "$SOURCE")
case "$SOURCE" in
/*) ;; # absolute path
*) SOURCE="$DIR/$SOURCE" ;; # relative path
esac
done
DIR=$(cd "$(dirname "$SOURCE")" && pwd)
if command -v node >/dev/null 2>&1; then
exec node "$DIR/../dist/cli.js" "$@"
elif command -v bun >/dev/null 2>&1; then
exec bun "$DIR/../dist/cli.js" "$@"
else
echo "Error: node or bun is required to run codex" >&2
exit 1
fi

153
codex-cli/bin/codex.js Executable file
View File

@@ -0,0 +1,153 @@
#!/usr/bin/env node
// Unified entry point for the Codex CLI.
/*
* Behavior
* =========
* 1. By default we import the JavaScript implementation located in
* dist/cli.js.
*
* 2. Developers can opt-in to a pre-compiled Rust binary by setting the
* environment variable CODEX_RUST to a truthy value (`1`, `true`, etc.).
* When that variable is present we resolve the correct binary for the
* current platform / architecture and execute it via child_process.
*
* If the CODEX_RUST=1 is specified and there is no native binary for the
* current platform / architecture, an error is thrown.
*/
import fs from "fs";
import path from "path";
import { fileURLToPath, pathToFileURL } from "url";
// Determine whether the user explicitly wants the Rust CLI.
// __dirname equivalent in ESM
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
// For the @native release of the Node module, the `use-native` file is added,
// indicating we should default to the native binary. For other releases,
// setting CODEX_RUST=1 will opt-in to the native binary, if included.
const wantsNative = fs.existsSync(path.join(__dirname, "use-native")) ||
(process.env.CODEX_RUST != null
? ["1", "true", "yes"].includes(process.env.CODEX_RUST.toLowerCase())
: false);
// Try native binary if requested.
if (wantsNative && process.platform !== 'win32') {
const { platform, arch } = process;
let targetTriple = null;
switch (platform) {
case "linux":
case "android":
switch (arch) {
case "x64":
targetTriple = "x86_64-unknown-linux-musl";
break;
case "arm64":
targetTriple = "aarch64-unknown-linux-musl";
break;
default:
break;
}
break;
case "darwin":
switch (arch) {
case "x64":
targetTriple = "x86_64-apple-darwin";
break;
case "arm64":
targetTriple = "aarch64-apple-darwin";
break;
default:
break;
}
break;
default:
break;
}
if (!targetTriple) {
throw new Error(`Unsupported platform: ${platform} (${arch})`);
}
const binaryPath = path.join(__dirname, "..", "bin", `codex-${targetTriple}`);
// Use an asynchronous spawn instead of spawnSync so that Node is able to
// respond to signals (e.g. Ctrl-C / SIGINT) while the native binary is
// executing. This allows us to forward those signals to the child process
// and guarantees that when either the child terminates or the parent
// receives a fatal signal, both processes exit in a predictable manner.
const { spawn } = await import("child_process");
const child = spawn(binaryPath, process.argv.slice(2), {
stdio: "inherit",
});
child.on("error", (err) => {
// Typically triggered when the binary is missing or not executable.
// Re-throwing here will terminate the parent with a non-zero exit code
// while still printing a helpful stack trace.
// eslint-disable-next-line no-console
console.error(err);
process.exit(1);
});
// Forward common termination signals to the child so that it shuts down
// gracefully. In the handler we temporarily disable the default behavior of
// exiting immediately; once the child has been signaled we simply wait for
// its exit event which will in turn terminate the parent (see below).
const forwardSignal = (signal) => {
if (child.killed) {
return;
}
try {
child.kill(signal);
} catch {
/* ignore */
}
};
["SIGINT", "SIGTERM", "SIGHUP"].forEach((sig) => {
process.on(sig, () => forwardSignal(sig));
});
// When the child exits, mirror its termination reason in the parent so that
// shell scripts and other tooling observe the correct exit status.
// Wrap the lifetime of the child process in a Promise so that we can await
// its termination in a structured way. The Promise resolves with an object
// describing how the child exited: either via exit code or due to a signal.
const childResult = await new Promise((resolve) => {
child.on("exit", (code, signal) => {
if (signal) {
resolve({ type: "signal", signal });
} else {
resolve({ type: "code", exitCode: code ?? 1 });
}
});
});
if (childResult.type === "signal") {
// Re-emit the same signal so that the parent terminates with the expected
// semantics (this also sets the correct exit code of 128 + n).
process.kill(process.pid, childResult.signal);
} else {
process.exit(childResult.exitCode);
}
} else {
// Fallback: execute the original JavaScript CLI.
// Resolve the path to the compiled CLI bundle
const cliPath = path.resolve(__dirname, "../dist/cli.js");
const cliUrl = pathToFileURL(cliPath).href;
// Load and execute the CLI
try {
await import(cliUrl);
} catch (err) {
// eslint-disable-next-line no-console
console.error(err);
process.exit(1);
}
}

View File

@@ -1,6 +1,8 @@
import * as esbuild from "esbuild";
import * as fs from "fs";
import * as path from "path";
const OUT_DIR = 'dist'
/**
* ink attempts to import react-devtools-core in an ESM-unfriendly way:
*
@@ -39,6 +41,11 @@ const isDevBuild =
const plugins = [ignoreReactDevToolsPlugin];
// Build Hygiene, ensure we drop previous dist dir and any leftover files
const outPath = path.resolve(OUT_DIR);
if (fs.existsSync(outPath)) {
fs.rmSync(outPath, { recursive: true, force: true });
}
// Add a shebang that enables sourcemap support for dev builds so that stack
// traces point to the original TypeScript lines without requiring callers to
@@ -50,7 +57,7 @@ if (isDevBuild) {
name: "dev-shebang",
setup(build) {
build.onEnd(async () => {
const outFile = path.resolve(isDevBuild ? "dist/cli-dev.js" : "dist/cli.js");
const outFile = path.resolve(isDevBuild ? `${OUT_DIR}/cli-dev.js` : `${OUT_DIR}/cli.js`);
let code = await fs.promises.readFile(outFile, "utf8");
if (code.startsWith("#!")) {
code = code.replace(/^#!.*\n/, devShebangLine);
@@ -65,11 +72,14 @@ if (isDevBuild) {
esbuild
.build({
entryPoints: ["src/cli.tsx"],
// Do not bundle the contents of package.json at build time: always read it
// at runtime.
external: ["../package.json"],
bundle: true,
format: "esm",
platform: "node",
tsconfig: "tsconfig.json",
outfile: isDevBuild ? "dist/cli-dev.js" : "dist/cli.js",
outfile: isDevBuild ? `${OUT_DIR}/cli-dev.js` : `${OUT_DIR}/cli.js`,
minify: !isDevBuild,
sourcemap: isDevBuild ? "inline" : true,
plugins,

43
codex-cli/default.nix Normal file
View File

@@ -0,0 +1,43 @@
{ pkgs, monorep-deps ? [], ... }:
let
node = pkgs.nodejs_22;
in
rec {
package = pkgs.buildNpmPackage {
pname = "codex-cli";
version = "0.1.0";
src = ./.;
npmDepsHash = "sha256-3tAalmh50I0fhhd7XreM+jvl0n4zcRhqygFNB1Olst8";
nodejs = node;
npmInstallFlags = [ "--frozen-lockfile" ];
meta = with pkgs.lib; {
description = "OpenAI Codex commandline interface";
license = licenses.asl20;
homepage = "https://github.com/openai/codex";
};
};
devShell = pkgs.mkShell {
name = "codex-cli-dev";
buildInputs = monorep-deps ++ [
node
pkgs.pnpm
];
shellHook = ''
echo "Entering development shell for codex-cli"
# cd codex-cli
if [ -f package-lock.json ]; then
pnpm ci || echo "npm ci failed"
else
pnpm install || echo "npm install failed"
fi
npm run build || echo "npm build failed"
export PATH=$PWD/node_modules/.bin:$PATH
alias codex="node $PWD/dist/cli.js"
'';
};
app = {
type = "app";
program = "${package}/bin/codex";
};
}

View File

@@ -1,7 +1,7 @@
name: "impossible-pong"
description: |
Update index.html with the following features:
- Add an overlayed styled popup to start the game on first load
- Add an overlaid styled popup to start the game on first load
- Between each point, show a 3 second countdown (this should be skipped if a player wins)
- After each game the AI wins, display text at the bottom of the screen with lighthearted insults for the player
- Add a leaderboard to the right of the court that shows how many games each player has won.

View File

@@ -13,7 +13,7 @@ act,prompt,for_devs
"Advertiser","I want you to act as an advertiser. You will create a campaign to promote a product or service of your choice. You will choose a target audience, develop key messages and slogans, select the media channels for promotion, and decide on any additional activities needed to reach your goals. My first suggestion request is ""I need help creating an advertising campaign for a new type of energy drink targeting young adults aged 18-30.""",FALSE
"Storyteller","I want you to act as a storyteller. You will come up with entertaining stories that are engaging, imaginative and captivating for the audience. It can be fairy tales, educational stories or any other type of stories which has the potential to capture people's attention and imagination. Depending on the target audience, you may choose specific themes or topics for your storytelling session e.g., if it's children then you can talk about animals; If it's adults then history-based tales might engage them better etc. My first request is ""I need an interesting story on perseverance.""",FALSE
"Football Commentator","I want you to act as a football commentator. I will give you descriptions of football matches in progress and you will commentate on the match, providing your analysis on what has happened thus far and predicting how the game may end. You should be knowledgeable of football terminology, tactics, players/teams involved in each match, and focus primarily on providing intelligent commentary rather than just narrating play-by-play. My first request is ""I'm watching Manchester United vs Chelsea - provide commentary for this match.""",FALSE
"Stand-up Comedian","I want you to act as a stand-up comedian. I will provide you with some topics related to current events and you will use your wit, creativity, and observational skills to create a routine based on those topics. You should also be sure to incorporate personal anecdotes or experiences into the routine in order to make it more relatable and engaging for the audience. My first request is ""I want an humorous take on politics.""",FALSE
"Stand-up Comedian","I want you to act as a stand-up comedian. I will provide you with some topics related to current events and you will use your with, creativity, and observational skills to create a routine based on those topics. You should also be sure to incorporate personal anecdotes or experiences into the routine in order to make it more relatable and engaging for the audience. My first request is ""I want an humorous take on politics.""",FALSE
"Motivational Coach","I want you to act as a motivational coach. I will provide you with some information about someone's goals and challenges, and it will be your job to come up with strategies that can help this person achieve their goals. This could involve providing positive affirmations, giving helpful advice or suggesting activities they can do to reach their end goal. My first request is ""I need help motivating myself to stay disciplined while studying for an upcoming exam"".",FALSE
"Composer","I want you to act as a composer. I will provide the lyrics to a song and you will create music for it. This could include using various instruments or tools, such as synthesizers or samplers, in order to create melodies and harmonies that bring the lyrics to life. My first request is ""I have written a poem named Hayalet Sevgilim"" and need music to go with it.""""""",FALSE
"Debater","I want you to act as a debater. I will provide you with some topics related to current events and your task is to research both sides of the debates, present valid arguments for each side, refute opposing points of view, and draw persuasive conclusions based on evidence. Your goal is to help people come away from the discussion with increased knowledge and insight into the topic at hand. My first request is ""I want an opinion piece about Deno.""",FALSE
@@ -23,7 +23,7 @@ act,prompt,for_devs
"Movie Critic","I want you to act as a movie critic. You will develop an engaging and creative movie review. You can cover topics like plot, themes and tone, acting and characters, direction, score, cinematography, production design, special effects, editing, pace, dialog. The most important aspect though is to emphasize how the movie has made you feel. What has really resonated with you. You can also be critical about the movie. Please avoid spoilers. My first request is ""I need to write a movie review for the movie Interstellar""",FALSE
"Relationship Coach","I want you to act as a relationship coach. I will provide some details about the two people involved in a conflict, and it will be your job to come up with suggestions on how they can work through the issues that are separating them. This could include advice on communication techniques or different strategies for improving their understanding of one another's perspectives. My first request is ""I need help solving conflicts between my spouse and myself.""",FALSE
"Poet","I want you to act as a poet. You will create poems that evoke emotions and have the power to stir people's soul. Write on any topic or theme but make sure your words convey the feeling you are trying to express in beautiful yet meaningful ways. You can also come up with short verses that are still powerful enough to leave an imprint in readers' minds. My first request is ""I need a poem about love.""",FALSE
"Rapper","I want you to act as a rapper. You will come up with powerful and meaningful lyrics, beats and rhythm that can 'wow' the audience. Your lyrics should have an intriguing meaning and message which people can relate too. When it comes to choosing your beat, make sure it is catchy yet relevant to your words, so that when combined they make an explosion of sound everytime! My first request is ""I need a rap song about finding strength within yourself.""",FALSE
"Rapper","I want you to act as a rapper. You will come up with powerful and meaningful lyrics, beats and rhythm that can 'wow' the audience. Your lyrics should have an intriguing meaning and message which people can relate too. When it comes to choosing your beat, make sure it is catchy yet relevant to your words, so that when combined they make an explosion of sound every time! My first request is ""I need a rap song about finding strength within yourself.""",FALSE
"Motivational Speaker","I want you to act as a motivational speaker. Put together words that inspire action and make people feel empowered to do something beyond their abilities. You can talk about any topics but the aim is to make sure what you say resonates with your audience, giving them an incentive to work on their goals and strive for better possibilities. My first request is ""I need a speech about how everyone should never give up.""",FALSE
"Philosophy Teacher","I want you to act as a philosophy teacher. I will provide some topics related to the study of philosophy, and it will be your job to explain these concepts in an easy-to-understand manner. This could include providing examples, posing questions or breaking down complex ideas into smaller pieces that are easier to comprehend. My first request is ""I need help understanding how different philosophical theories can be applied in everyday life.""",FALSE
"Philosopher","I want you to act as a philosopher. I will provide some topics or questions related to the study of philosophy, and it will be your job to explore these concepts in depth. This could involve conducting research into various philosophical theories, proposing new ideas or finding creative solutions for solving complex problems. My first request is ""I need help developing an ethical framework for decision making.""",FALSE
1 act prompt for_devs
13 Advertiser I want you to act as an advertiser. You will create a campaign to promote a product or service of your choice. You will choose a target audience, develop key messages and slogans, select the media channels for promotion, and decide on any additional activities needed to reach your goals. My first suggestion request is "I need help creating an advertising campaign for a new type of energy drink targeting young adults aged 18-30." FALSE
14 Storyteller I want you to act as a storyteller. You will come up with entertaining stories that are engaging, imaginative and captivating for the audience. It can be fairy tales, educational stories or any other type of stories which has the potential to capture people's attention and imagination. Depending on the target audience, you may choose specific themes or topics for your storytelling session e.g., if it's children then you can talk about animals; If it's adults then history-based tales might engage them better etc. My first request is "I need an interesting story on perseverance." FALSE
15 Football Commentator I want you to act as a football commentator. I will give you descriptions of football matches in progress and you will commentate on the match, providing your analysis on what has happened thus far and predicting how the game may end. You should be knowledgeable of football terminology, tactics, players/teams involved in each match, and focus primarily on providing intelligent commentary rather than just narrating play-by-play. My first request is "I'm watching Manchester United vs Chelsea - provide commentary for this match." FALSE
16 Stand-up Comedian I want you to act as a stand-up comedian. I will provide you with some topics related to current events and you will use your wit, creativity, and observational skills to create a routine based on those topics. You should also be sure to incorporate personal anecdotes or experiences into the routine in order to make it more relatable and engaging for the audience. My first request is "I want an humorous take on politics." I want you to act as a stand-up comedian. I will provide you with some topics related to current events and you will use your with, creativity, and observational skills to create a routine based on those topics. You should also be sure to incorporate personal anecdotes or experiences into the routine in order to make it more relatable and engaging for the audience. My first request is "I want an humorous take on politics." FALSE
17 Motivational Coach I want you to act as a motivational coach. I will provide you with some information about someone's goals and challenges, and it will be your job to come up with strategies that can help this person achieve their goals. This could involve providing positive affirmations, giving helpful advice or suggesting activities they can do to reach their end goal. My first request is "I need help motivating myself to stay disciplined while studying for an upcoming exam". FALSE
18 Composer I want you to act as a composer. I will provide the lyrics to a song and you will create music for it. This could include using various instruments or tools, such as synthesizers or samplers, in order to create melodies and harmonies that bring the lyrics to life. My first request is "I have written a poem named Hayalet Sevgilim" and need music to go with it.""" FALSE
19 Debater I want you to act as a debater. I will provide you with some topics related to current events and your task is to research both sides of the debates, present valid arguments for each side, refute opposing points of view, and draw persuasive conclusions based on evidence. Your goal is to help people come away from the discussion with increased knowledge and insight into the topic at hand. My first request is "I want an opinion piece about Deno." FALSE
23 Movie Critic I want you to act as a movie critic. You will develop an engaging and creative movie review. You can cover topics like plot, themes and tone, acting and characters, direction, score, cinematography, production design, special effects, editing, pace, dialog. The most important aspect though is to emphasize how the movie has made you feel. What has really resonated with you. You can also be critical about the movie. Please avoid spoilers. My first request is "I need to write a movie review for the movie Interstellar" FALSE
24 Relationship Coach I want you to act as a relationship coach. I will provide some details about the two people involved in a conflict, and it will be your job to come up with suggestions on how they can work through the issues that are separating them. This could include advice on communication techniques or different strategies for improving their understanding of one another's perspectives. My first request is "I need help solving conflicts between my spouse and myself." FALSE
25 Poet I want you to act as a poet. You will create poems that evoke emotions and have the power to stir people's soul. Write on any topic or theme but make sure your words convey the feeling you are trying to express in beautiful yet meaningful ways. You can also come up with short verses that are still powerful enough to leave an imprint in readers' minds. My first request is "I need a poem about love." FALSE
26 Rapper I want you to act as a rapper. You will come up with powerful and meaningful lyrics, beats and rhythm that can 'wow' the audience. Your lyrics should have an intriguing meaning and message which people can relate too. When it comes to choosing your beat, make sure it is catchy yet relevant to your words, so that when combined they make an explosion of sound everytime! My first request is "I need a rap song about finding strength within yourself." I want you to act as a rapper. You will come up with powerful and meaningful lyrics, beats and rhythm that can 'wow' the audience. Your lyrics should have an intriguing meaning and message which people can relate too. When it comes to choosing your beat, make sure it is catchy yet relevant to your words, so that when combined they make an explosion of sound every time! My first request is "I need a rap song about finding strength within yourself." FALSE
27 Motivational Speaker I want you to act as a motivational speaker. Put together words that inspire action and make people feel empowered to do something beyond their abilities. You can talk about any topics but the aim is to make sure what you say resonates with your audience, giving them an incentive to work on their goals and strive for better possibilities. My first request is "I need a speech about how everyone should never give up." FALSE
28 Philosophy Teacher I want you to act as a philosophy teacher. I will provide some topics related to the study of philosophy, and it will be your job to explain these concepts in an easy-to-understand manner. This could include providing examples, posing questions or breaking down complex ideas into smaller pieces that are easier to comprehend. My first request is "I need help understanding how different philosophical theories can be applied in everyday life." FALSE
29 Philosopher I want you to act as a philosopher. I will provide some topics or questions related to the study of philosophy, and it will be your job to explore these concepts in depth. This could involve conducting research into various philosophical theories, proposing new ideas or finding creative solutions for solving complex problems. My first request is "I need help developing an ethical framework for decision making." FALSE

File diff suppressed because it is too large Load Diff

View File

@@ -1,9 +1,9 @@
{
"name": "@openai/codex",
"version": "0.1.2504172351",
"version": "0.0.0-dev",
"license": "Apache-2.0",
"bin": {
"codex": "bin/codex"
"codex": "bin/codex.js"
},
"type": "module",
"engines": {
@@ -20,34 +20,31 @@
"typecheck": "tsc --noEmit",
"build": "node build.mjs",
"build:dev": "NODE_ENV=development node build.mjs --dev && NODE_OPTIONS=--enable-source-maps node dist/cli-dev.js",
"release:readme": "cp ../README.md ./README.md",
"release:version": "TS=$(date +%y%m%d%H%M) && sed -E -i'' -e \"s/\\\"0\\.1\\.[0-9]{10}\\\"/\\\"0.1.${TS}\\\"/g\" package.json src/utils/session.ts",
"release:build-and-publish": "npm run build && npm publish",
"release": "npm run release:readme && npm run release:version && npm install && npm run release:build-and-publish",
"prepare": "husky",
"pre-commit": "lint-staged"
"stage-release": "./scripts/stage_release.sh"
},
"files": [
"README.md",
"bin",
"dist",
"src"
"dist"
],
"dependencies": {
"@inkjs/ui": "^2.0.0",
"chalk": "^5.2.0",
"diff": "^7.0.0",
"dotenv": "^16.1.4",
"express": "^5.1.0",
"fast-deep-equal": "^3.1.3",
"fast-npm-meta": "^0.4.2",
"figures": "^6.1.0",
"file-type": "^20.1.0",
"https-proxy-agent": "^7.0.6",
"ink": "^5.2.0",
"js-yaml": "^4.1.0",
"marked": "^15.0.7",
"marked-terminal": "^7.3.0",
"meow": "^13.2.0",
"open": "^10.1.0",
"openai": "^4.89.0",
"openai": "^4.95.1",
"package-manager-detector": "^1.2.0",
"react": "^18.2.0",
"shell-quote": "^1.8.2",
"strip-ansi": "^7.1.0",
@@ -58,12 +55,16 @@
"devDependencies": {
"@eslint/js": "^9.22.0",
"@types/diff": "^7.0.2",
"@types/express": "^5.0.1",
"@types/js-yaml": "^4.0.9",
"@types/marked-terminal": "^6.1.1",
"@types/react": "^18.0.32",
"@types/semver": "^7.7.0",
"@types/shell-quote": "^1.7.5",
"@types/which": "^3.0.4",
"@typescript-eslint/eslint-plugin": "^7.18.0",
"@typescript-eslint/parser": "^7.18.0",
"boxen": "^8.0.1",
"esbuild": "^0.25.2",
"eslint-plugin-import": "^2.31.0",
"eslint-plugin-react": "^7.32.2",
@@ -71,24 +72,18 @@
"eslint-plugin-react-refresh": "^0.4.19",
"husky": "^9.1.7",
"ink-testing-library": "^3.0.0",
"lint-staged": "^15.5.1",
"prettier": "^2.8.7",
"prettier": "^3.5.3",
"punycode": "^2.3.1",
"semver": "^7.7.1",
"ts-node": "^10.9.1",
"typescript": "^5.0.3",
"vitest": "^3.0.9",
"whatwg-url": "^14.2.0"
},
"resolutions": {
"braces": "^3.0.3",
"micromatch": "^4.0.8",
"semver": "^7.7.1"
},
"overrides": {
"punycode": "^2.3.1"
"vite": "^6.3.4",
"vitest": "^3.1.2",
"whatwg-url": "^14.2.0",
"which": "^5.0.0"
},
"repository": {
"type": "git",
"url": "https://github.com/openai/codex"
"url": "git+https://github.com/openai/codex.git"
}
}

View File

@@ -0,0 +1,9 @@
# npm releases
Run the following:
To build the 0.2.x or later version of the npm module, which runs the Rust version of the CLI, build it as follows:
```bash
./codex-cli/scripts/stage_rust_release.py --release-version 0.6.0
```

View File

@@ -8,9 +8,9 @@ pushd "$SCRIPT_DIR/.." >> /dev/null || {
echo "Error: Failed to change directory to $SCRIPT_DIR/.."
exit 1
}
npm install
npm run build
pnpm install
pnpm run build
rm -rf ./dist/openai-codex-*.tgz
npm pack --pack-destination ./dist
pnpm pack --pack-destination ./dist
mv ./dist/openai-codex-*.tgz ./dist/codex.tgz
docker build -t codex -f "./Dockerfile" .

View File

@@ -2,6 +2,26 @@
set -euo pipefail # Exit on error, undefined vars, and pipeline failures
IFS=$'\n\t' # Stricter word splitting
# Read allowed domains from file
ALLOWED_DOMAINS_FILE="/etc/codex/allowed_domains.txt"
if [ -f "$ALLOWED_DOMAINS_FILE" ]; then
ALLOWED_DOMAINS=()
while IFS= read -r domain; do
ALLOWED_DOMAINS+=("$domain")
done < "$ALLOWED_DOMAINS_FILE"
echo "Using domains from file: ${ALLOWED_DOMAINS[*]}"
else
# Fallback to default domains
ALLOWED_DOMAINS=("api.openai.com")
echo "Domains file not found, using default: ${ALLOWED_DOMAINS[*]}"
fi
# Ensure we have at least one domain
if [ ${#ALLOWED_DOMAINS[@]} -eq 0 ]; then
echo "ERROR: No allowed domains specified"
exit 1
fi
# Flush existing rules and delete existing ipsets
iptables -F
iptables -X
@@ -24,8 +44,7 @@ iptables -A OUTPUT -o lo -j ACCEPT
ipset create allowed-domains hash:net
# Resolve and add other allowed domains
for domain in \
"api.openai.com"; do
for domain in "${ALLOWED_DOMAINS[@]}"; do
echo "Resolving $domain..."
ips=$(dig +short A "$domain")
if [ -z "$ips" ]; then
@@ -87,7 +106,7 @@ else
echo "Firewall verification passed - unable to reach https://example.com as expected"
fi
# Verify OpenAI API access
# Always verify OpenAI API access is working
if ! curl --connect-timeout 5 https://api.openai.com >/dev/null 2>&1; then
echo "ERROR: Firewall verification failed - unable to reach https://api.openai.com"
exit 1

View File

@@ -0,0 +1,106 @@
#!/usr/bin/env bash
# Install native runtime dependencies for codex-cli.
#
# By default the script copies the sandbox binaries that are required at
# runtime. When called with the --full-native flag, it additionally
# bundles pre-built Rust CLI binaries so that the resulting npm package can run
# the native implementation when users set CODEX_RUST=1.
#
# Usage
# install_native_deps.sh [--full-native] [--workflow-url URL] [CODEX_CLI_ROOT]
#
# The optional RELEASE_ROOT is the path that contains package.json. Omitting
# it installs the binaries into the repository's own bin/ folder to support
# local development.
set -euo pipefail
# ------------------
# Parse arguments
# ------------------
CODEX_CLI_ROOT=""
INCLUDE_RUST=0
# Until we start publishing stable GitHub releases, we have to grab the binaries
# from the GitHub Action that created them. Update the URL below to point to the
# appropriate workflow run:
WORKFLOW_URL="https://github.com/openai/codex/actions/runs/15981617627"
while [[ $# -gt 0 ]]; do
case "$1" in
--full-native)
INCLUDE_RUST=1
;;
--workflow-url)
shift || { echo "--workflow-url requires an argument"; exit 1; }
if [ -n "$1" ]; then
WORKFLOW_URL="$1"
fi
;;
*)
if [[ -z "$CODEX_CLI_ROOT" ]]; then
CODEX_CLI_ROOT="$1"
else
echo "Unexpected argument: $1" >&2
exit 1
fi
;;
esac
shift
done
# ----------------------------------------------------------------------------
# Determine where the binaries should be installed.
# ----------------------------------------------------------------------------
if [ -n "$CODEX_CLI_ROOT" ]; then
# The caller supplied a release root directory.
BIN_DIR="$CODEX_CLI_ROOT/bin"
else
# No argument; fall back to the repos own bin directory.
# Resolve the path of this script, then walk up to the repo root.
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
CODEX_CLI_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
BIN_DIR="$CODEX_CLI_ROOT/bin"
fi
# Make sure the destination directory exists.
mkdir -p "$BIN_DIR"
# ----------------------------------------------------------------------------
# Download and decompress the artifacts from the GitHub Actions workflow.
# ----------------------------------------------------------------------------
WORKFLOW_ID="${WORKFLOW_URL##*/}"
ARTIFACTS_DIR="$(mktemp -d)"
trap 'rm -rf "$ARTIFACTS_DIR"' EXIT
# NB: The GitHub CLI `gh` must be installed and authenticated.
gh run download --dir "$ARTIFACTS_DIR" --repo openai/codex "$WORKFLOW_ID"
# Decompress the artifacts for Linux sandboxing.
zstd -d "$ARTIFACTS_DIR/x86_64-unknown-linux-musl/codex-linux-sandbox-x86_64-unknown-linux-musl.zst" \
-o "$BIN_DIR/codex-linux-sandbox-x64"
zstd -d "$ARTIFACTS_DIR/aarch64-unknown-linux-musl/codex-linux-sandbox-aarch64-unknown-linux-musl.zst" \
-o "$BIN_DIR/codex-linux-sandbox-arm64"
if [[ "$INCLUDE_RUST" -eq 1 ]]; then
# x64 Linux
zstd -d "$ARTIFACTS_DIR/x86_64-unknown-linux-musl/codex-x86_64-unknown-linux-musl.zst" \
-o "$BIN_DIR/codex-x86_64-unknown-linux-musl"
# ARM64 Linux
zstd -d "$ARTIFACTS_DIR/aarch64-unknown-linux-musl/codex-aarch64-unknown-linux-musl.zst" \
-o "$BIN_DIR/codex-aarch64-unknown-linux-musl"
# x64 macOS
zstd -d "$ARTIFACTS_DIR/x86_64-apple-darwin/codex-x86_64-apple-darwin.zst" \
-o "$BIN_DIR/codex-x86_64-apple-darwin"
# ARM64 macOS
zstd -d "$ARTIFACTS_DIR/aarch64-apple-darwin/codex-aarch64-apple-darwin.zst" \
-o "$BIN_DIR/codex-aarch64-apple-darwin"
fi
echo "Installed native dependencies into $BIN_DIR"

View File

@@ -10,6 +10,8 @@ set -e
# Default the work directory to WORKSPACE_ROOT_DIR if not provided.
WORK_DIR="${WORKSPACE_ROOT_DIR:-$(pwd)}"
# Default allowed domains - can be overridden with OPENAI_ALLOWED_DOMAINS env var
OPENAI_ALLOWED_DOMAINS="${OPENAI_ALLOWED_DOMAINS:-api.openai.com}"
# Parse optional flag.
if [ "$1" = "--work_dir" ]; then
@@ -23,6 +25,16 @@ fi
WORK_DIR=$(realpath "$WORK_DIR")
# Generate a unique container name based on the normalized work directory
CONTAINER_NAME="codex_$(echo "$WORK_DIR" | sed 's/\//_/g' | sed 's/[^a-zA-Z0-9_-]//g')"
# Define cleanup to remove the container on script exit, ensuring no leftover containers
cleanup() {
docker rm -f "$CONTAINER_NAME" >/dev/null 2>&1 || true
}
# Trap EXIT to invoke cleanup regardless of how the script terminates
trap cleanup EXIT
# Ensure a command is provided.
if [ "$#" -eq 0 ]; then
echo "Usage: $0 [--work_dir directory] \"COMMAND\""
@@ -35,11 +47,17 @@ if [ -z "$WORK_DIR" ]; then
exit 1
fi
# Remove any existing container named 'codex'.
docker rm -f codex 2>/dev/null || true
# Verify that OPENAI_ALLOWED_DOMAINS is not empty
if [ -z "$OPENAI_ALLOWED_DOMAINS" ]; then
echo "Error: OPENAI_ALLOWED_DOMAINS is empty."
exit 1
fi
# Kill any existing container for the working directory using cleanup(), centralizing removal logic.
cleanup
# Run the container with the specified directory mounted at the same path inside the container.
docker run --name codex -d \
docker run --name "$CONTAINER_NAME" -d \
-e OPENAI_API_KEY \
--cap-add=NET_ADMIN \
--cap-add=NET_RAW \
@@ -47,8 +65,25 @@ docker run --name codex -d \
codex \
sleep infinity
# Initialize the firewall inside the container.
docker exec codex bash -c "sudo /usr/local/bin/init_firewall.sh"
# Write the allowed domains to a file in the container
docker exec --user root "$CONTAINER_NAME" bash -c "mkdir -p /etc/codex"
for domain in $OPENAI_ALLOWED_DOMAINS; do
# Validate domain format to prevent injection
if [[ ! "$domain" =~ ^[a-zA-Z0-9][a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$ ]]; then
echo "Error: Invalid domain format: $domain"
exit 1
fi
echo "$domain" | docker exec --user root -i "$CONTAINER_NAME" bash -c "cat >> /etc/codex/allowed_domains.txt"
done
# Set proper permissions on the domains file
docker exec --user root "$CONTAINER_NAME" bash -c "chmod 444 /etc/codex/allowed_domains.txt && chown root:root /etc/codex/allowed_domains.txt"
# Initialize the firewall inside the container as root user
docker exec --user root "$CONTAINER_NAME" bash -c "/usr/local/bin/init_firewall.sh"
# Remove the firewall script after running it
docker exec --user root "$CONTAINER_NAME" bash -c "rm -f /usr/local/bin/init_firewall.sh"
# Execute the provided command in the container, ensuring it runs in the work directory.
# We use a parameterized bash command to safely handle the command and directory.
@@ -57,4 +92,4 @@ quoted_args=""
for arg in "$@"; do
quoted_args+=" $(printf '%q' "$arg")"
done
docker exec -it codex bash -c "cd \"/app$WORK_DIR\" && codex --full-auto ${quoted_args}"
docker exec -it "$CONTAINER_NAME" bash -c "cd \"/app$WORK_DIR\" && codex --full-auto ${quoted_args}"

View File

@@ -0,0 +1,154 @@
#!/usr/bin/env bash
# -----------------------------------------------------------------------------
# stage_release.sh
# -----------------------------------------------------------------------------
# Stages an npm release for @openai/codex.
#
# Usage:
#
# --tmp <dir> : Use <dir> instead of a freshly created temp directory.
# --native : Bundle the pre-built Rust CLI binaries for Linux alongside
# the JavaScript implementation (a so-called "fat" package).
# -h|--help : Print usage.
#
# When --native is supplied we copy the linux-sandbox binaries (as before) and
# additionally fetch / unpack the two Rust targets that we currently support:
# - x86_64-unknown-linux-musl
# - aarch64-unknown-linux-musl
#
# NOTE: This script is intended to be run from the repository root via
# `pnpm --filter codex-cli stage-release ...` or inside codex-cli with the
# helper script entry in package.json (`pnpm stage-release ...`).
# -----------------------------------------------------------------------------
set -euo pipefail
# Helper - usage / flag parsing
usage() {
cat <<EOF
Usage: $(basename "$0") [--tmp DIR] [--native] [--version VERSION]
Options
--tmp DIR Use DIR to stage the release (defaults to a fresh mktemp dir)
--native Bundle Rust binaries for Linux (fat package)
--version Specify the version to release (defaults to a timestamp-based version)
-h, --help Show this help
Legacy positional argument: the first non-flag argument is still interpreted
as the temporary directory (for backwards compatibility) but is deprecated.
EOF
exit "${1:-0}"
}
TMPDIR=""
INCLUDE_NATIVE=0
# Default to a timestamp-based version (keep same scheme as before)
VERSION="$(printf '0.1.%d' "$(date +%y%m%d%H%M)")"
WORKFLOW_URL=""
# Manual flag parser - Bash getopts does not handle GNU long options well.
while [[ $# -gt 0 ]]; do
case "$1" in
--tmp)
shift || { echo "--tmp requires an argument"; usage 1; }
TMPDIR="$1"
;;
--tmp=*)
TMPDIR="${1#*=}"
;;
--native)
INCLUDE_NATIVE=1
;;
--version)
shift || { echo "--version requires an argument"; usage 1; }
VERSION="$1"
;;
--workflow-url)
shift || { echo "--workflow-url requires an argument"; exit 1; }
WORKFLOW_URL="$1"
;;
-h|--help)
usage 0
;;
--*)
echo "Unknown option: $1" >&2
usage 1
;;
*)
echo "Unexpected extra argument: $1" >&2
usage 1
;;
esac
shift
done
# Fallback when the caller did not specify a directory.
# If no directory was specified create a fresh temporary one.
if [[ -z "$TMPDIR" ]]; then
TMPDIR="$(mktemp -d)"
fi
# Ensure the directory exists, then resolve to an absolute path.
mkdir -p "$TMPDIR"
TMPDIR="$(cd "$TMPDIR" && pwd)"
# Main build logic
echo "Staging release in $TMPDIR"
# The script lives in codex-cli/scripts/ - change into codex-cli root so that
# relative paths keep working.
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
CODEX_CLI_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
pushd "$CODEX_CLI_ROOT" >/dev/null
# 1. Build the JS artifacts ---------------------------------------------------
pnpm install
pnpm build
# Paths inside the staged package
mkdir -p "$TMPDIR/bin"
cp -r bin/codex.js "$TMPDIR/bin/codex.js"
cp -r dist "$TMPDIR/dist"
cp -r src "$TMPDIR/src" # keep source for TS sourcemaps
cp ../README.md "$TMPDIR" || true # README is one level up - ignore if missing
# Modify package.json - bump version and optionally add the native directory to
# the files array so that the binaries are published to npm.
jq --arg version "$VERSION" \
'.version = $version' \
package.json > "$TMPDIR/package.json"
# 2. Native runtime deps (sandbox plus optional Rust binaries)
if [[ "$INCLUDE_NATIVE" -eq 1 ]]; then
./scripts/install_native_deps.sh --full-native --workflow-url "$WORKFLOW_URL" "$TMPDIR"
touch "${TMPDIR}/bin/use-native"
else
./scripts/install_native_deps.sh "$TMPDIR"
fi
popd >/dev/null
echo "Staged version $VERSION for release in $TMPDIR"
if [[ "$INCLUDE_NATIVE" -eq 1 ]]; then
echo "Verify the CLI:"
echo " node ${TMPDIR}/bin/codex.js --version"
echo " node ${TMPDIR}/bin/codex.js --help"
else
echo "Test Node:"
echo " node ${TMPDIR}/bin/codex.js --help"
fi
# Print final hint for convenience
if [[ "$INCLUDE_NATIVE" -eq 1 ]]; then
echo "Next: cd \"$TMPDIR\" && npm publish --tag native"
else
echo "Next: cd \"$TMPDIR\" && npm publish"
fi

View File

@@ -0,0 +1,62 @@
#!/usr/bin/env python3
import json
import subprocess
import sys
import argparse
from pathlib import Path
def main() -> int:
parser = argparse.ArgumentParser(
description="""Stage a release for the npm module.
Run this after the GitHub Release has been created and use
`--release-version` to specify the version to release.
"""
)
parser.add_argument(
"--release-version", required=True, help="Version to release, e.g., 0.3.0"
)
args = parser.parse_args()
version = args.release_version
gh_run = subprocess.run(
[
"gh",
"run",
"list",
"--branch",
f"rust-v{version}",
"--json",
"workflowName,url,headSha",
"--jq",
'first(.[] | select(.workflowName == "rust-release"))',
],
stdout=subprocess.PIPE,
check=True,
)
gh_run.check_returncode()
workflow = json.loads(gh_run.stdout)
sha = workflow["headSha"]
print(f"should `git checkout {sha}`")
current_dir = Path(__file__).parent.resolve()
stage_release = subprocess.run(
[
current_dir / "stage_release.sh",
"--version",
version,
"--workflow-url",
workflow["url"],
"--native",
]
)
stage_release.check_returncode()
return 0
if __name__ == "__main__":
sys.exit(main())

View File

@@ -1,12 +1,13 @@
import type { ApprovalPolicy } from "./approvals";
import type { AppConfig } from "./utils/config";
import type { TerminalChatSession } from "./utils/session.js";
import type { ResponseItem } from "openai/resources/responses/responses";
import TerminalChat from "./components/chat/terminal-chat";
import TerminalChatPastRollout from "./components/chat/terminal-chat-past-rollout";
import { checkInGit } from "./utils/check-in-git";
import { CLI_VERSION, type TerminalChatSession } from "./utils/session.js";
import { onExit } from "./utils/terminal";
import { CLI_VERSION } from "./version";
import { ConfirmInput } from "@inkjs/ui";
import { Box, Text, useApp, useStdin } from "ink";
import React, { useMemo, useState } from "react";
@@ -49,6 +50,7 @@ export default function App({
<TerminalChatPastRollout
session={rollout.session}
items={rollout.items}
fileOpener={config.fileOpener}
/>
);
}

View File

@@ -71,13 +71,14 @@ export type ApprovalPolicy =
*/
export function canAutoApprove(
command: ReadonlyArray<string>,
workdir: string | undefined,
policy: ApprovalPolicy,
writableRoots: ReadonlyArray<string>,
env: NodeJS.ProcessEnv = process.env,
): SafetyAssessment {
if (command[0] === "apply_patch") {
return command.length === 2 && typeof command[1] === "string"
? canAutoApproveApplyPatch(command[1], writableRoots, policy)
? canAutoApproveApplyPatch(command[1], workdir, writableRoots, policy)
: {
type: "reject",
reason: "Invalid apply_patch command",
@@ -103,7 +104,12 @@ export function canAutoApprove(
) {
const applyPatchArg = tryParseApplyPatch(command[2]);
if (applyPatchArg != null) {
return canAutoApproveApplyPatch(applyPatchArg, writableRoots, policy);
return canAutoApproveApplyPatch(
applyPatchArg,
workdir,
writableRoots,
policy,
);
}
let bashCmd;
@@ -135,8 +141,8 @@ export function canAutoApprove(
// bashCmd could be a mix of strings and operators, e.g.:
// "ls || (true && pwd)" => [ 'ls', { op: '||' }, '(', 'true', { op: '&&' }, 'pwd', ')' ]
// We try to ensure that *every* command segment is deemed safe and that
// all operators belong to an allowlist. If so, the entire expression is
// considered autoapprovable.
// all operators belong to an allow-list. If so, the entire expression is
// considered auto-approvable.
const shellSafe = isEntireShellExpressionSafe(bashCmd);
if (shellSafe != null) {
@@ -162,6 +168,7 @@ export function canAutoApprove(
function canAutoApproveApplyPatch(
applyPatchArg: string,
workdir: string | undefined,
writableRoots: ReadonlyArray<string>,
policy: ApprovalPolicy,
): SafetyAssessment {
@@ -179,7 +186,13 @@ function canAutoApproveApplyPatch(
break;
}
if (isWritePatchConstrainedToWritablePaths(applyPatchArg, writableRoots)) {
if (
isWritePatchConstrainedToWritablePaths(
applyPatchArg,
workdir,
writableRoots,
)
) {
return {
type: "auto-approve",
reason: "apply_patch command is constrained to writable paths",
@@ -208,6 +221,7 @@ function canAutoApproveApplyPatch(
*/
function isWritePatchConstrainedToWritablePaths(
applyPatchArg: string,
workdir: string | undefined,
writableRoots: ReadonlyArray<string>,
): boolean {
// `identify_files_needed()` returns a list of files that will be modified or
@@ -222,10 +236,12 @@ function isWritePatchConstrainedToWritablePaths(
return (
allPathsConstrainedTowritablePaths(
identify_files_needed(applyPatchArg),
workdir,
writableRoots,
) &&
allPathsConstrainedTowritablePaths(
identify_files_added(applyPatchArg),
workdir,
writableRoots,
)
);
@@ -233,24 +249,49 @@ function isWritePatchConstrainedToWritablePaths(
function allPathsConstrainedTowritablePaths(
candidatePaths: ReadonlyArray<string>,
workdir: string | undefined,
writableRoots: ReadonlyArray<string>,
): boolean {
return candidatePaths.every((candidatePath) =>
isPathConstrainedTowritablePaths(candidatePath, writableRoots),
isPathConstrainedTowritablePaths(candidatePath, workdir, writableRoots),
);
}
/** If candidatePath is relative, it will be resolved against cwd. */
function isPathConstrainedTowritablePaths(
candidatePath: string,
workdir: string | undefined,
writableRoots: ReadonlyArray<string>,
): boolean {
const candidateAbsolutePath = path.resolve(candidatePath);
const candidateAbsolutePath = resolvePathAgainstWorkdir(
candidatePath,
workdir,
);
return writableRoots.some((writablePath) =>
pathContains(writablePath, candidateAbsolutePath),
);
}
/**
* If not already an absolute path, resolves `candidatePath` against `workdir`
* if specified; otherwise, against `process.cwd()`.
*/
export function resolvePathAgainstWorkdir(
candidatePath: string,
workdir: string | undefined,
): string {
// Normalize candidatePath to prevent path traversal attacks
const normalizedCandidatePath = path.normalize(candidatePath);
if (path.isAbsolute(normalizedCandidatePath)) {
return normalizedCandidatePath;
} else if (workdir != null) {
return path.resolve(workdir, normalizedCandidatePath);
} else {
return path.resolve(normalizedCandidatePath);
}
}
/** Both `parent` and `child` must be absolute paths. */
function pathContains(parent: string, child: string): boolean {
const relative = path.relative(parent, child);
@@ -314,7 +355,7 @@ export function isSafeCommand(
};
case "true":
return {
reason: "Noop (true)",
reason: "No-op (true)",
group: "Utility",
};
case "echo":
@@ -324,16 +365,45 @@ export function isSafeCommand(
reason: "View file contents",
group: "Reading files",
};
case "rg":
case "nl":
return {
reason: "View file with line numbers",
group: "Reading files",
};
case "rg": {
// Certain ripgrep options execute external commands or invoke other
// processes, so we must reject them.
const isUnsafe = command.some(
(arg: string) =>
UNSAFE_OPTIONS_FOR_RIPGREP_WITHOUT_ARGS.has(arg) ||
[...UNSAFE_OPTIONS_FOR_RIPGREP_WITH_ARGS].some(
(opt) => arg === opt || arg.startsWith(`${opt}=`),
),
);
if (isUnsafe) {
break;
}
return {
reason: "Ripgrep search",
group: "Searching",
};
case "find":
return {
reason: "Find files or directories",
group: "Searching",
};
}
case "find": {
// Certain options to `find` allow executing arbitrary processes, so we
// cannot auto-approve them.
if (
command.some((arg: string) => UNSAFE_OPTIONS_FOR_FIND_COMMAND.has(arg))
) {
break;
} else {
return {
reason: "Find files or directories",
group: "Searching",
};
}
}
case "grep":
return {
reason: "Text search (grep)",
@@ -398,11 +468,15 @@ export function isSafeCommand(
}
break;
case "sed":
// We allow two types of sed invocations:
// 1. `sed -n 1,200p FILE`
// 2. `sed -n 1,200p` because the file is passed via stdin, e.g.,
// `nl -ba README.md | sed -n '1,200p'`
if (
cmd1 === "-n" &&
isValidSedNArg(cmd2) &&
typeof cmd3 === "string" &&
command.length === 4
(command.length === 3 ||
(typeof cmd3 === "string" && command.length === 4))
) {
return {
reason: "Sed print subset",
@@ -421,12 +495,43 @@ function isValidSedNArg(arg: string | undefined): boolean {
return arg != null && /^(\d+,)?\d+p$/.test(arg);
}
const UNSAFE_OPTIONS_FOR_FIND_COMMAND: ReadonlySet<string> = new Set([
// Options that can execute arbitrary commands.
"-exec",
"-execdir",
"-ok",
"-okdir",
// Option that deletes matching files.
"-delete",
// Options that write pathnames to a file.
"-fls",
"-fprint",
"-fprint0",
"-fprintf",
]);
// Ripgrep options that are considered unsafe because they may execute
// arbitrary commands or spawn auxiliary processes.
const UNSAFE_OPTIONS_FOR_RIPGREP_WITH_ARGS: ReadonlySet<string> = new Set([
// Executes an arbitrary command for each matching file.
"--pre",
// Allows custom hostname command which could leak environment details.
"--hostname-bin",
]);
const UNSAFE_OPTIONS_FOR_RIPGREP_WITHOUT_ARGS: ReadonlySet<string> = new Set([
// Enables searching inside archives which triggers external decompression
// utilities reject out of an abundance of caution.
"--search-zip",
"-z",
]);
// ---------------- Helper utilities for complex shell expressions -----------------
// A conservative allowlist of bash operators that do not, on their own, cause
// A conservative allow-list of bash operators that do not, on their own, cause
// side effects. Redirections (>, >>, <, etc.) and command substitution `$()`
// are intentionally excluded. Parentheses used for grouping are treated as
// strings by `shellquote`, so we do not add them here. Reference:
// strings by `shell-quote`, so we do not add them here. Reference:
// https://github.com/substack/node-shell-quote#parsecmd-opts
const SAFE_SHELL_OPERATORS: ReadonlySet<string> = new Set([
"&&", // logical AND
@@ -452,7 +557,7 @@ function isEntireShellExpressionSafe(
}
try {
// Collect command segments delimited by operators. `shellquote` represents
// Collect command segments delimited by operators. `shell-quote` represents
// subshell grouping parentheses as literal strings "(" and ")"; treat them
// as unsafe to keep the logic simple (since subshells could introduce
// unexpected scope changes).
@@ -520,7 +625,7 @@ function isParseEntryWithOp(
return (
typeof entry === "object" &&
entry != null &&
// Using the safe `in` operator keeps the check propertysafe even when
// Using the safe `in` operator keeps the check property-safe even when
// `entry` is a `string`.
"op" in entry &&
typeof (entry as { op?: unknown }).op === "string"

View File

@@ -1,6 +1,19 @@
#!/usr/bin/env node
import "dotenv/config";
// Exit early if on an older version of Node.js (< 22)
const major = process.versions.node.split(".").map(Number)[0]!;
if (major < 22) {
// eslint-disable-next-line no-console
console.error(
"\n" +
"Codex CLI requires Node.js version 22 or newer.\n" +
`You are running Node.js v${process.versions.node}.\n` +
"Please upgrade Node.js: https://nodejs.org/en/download/\n",
);
process.exit(1);
}
// Hack to suppress deprecation warnings (punycode)
// eslint-disable-next-line @typescript-eslint/no-explicit-any
(process as any).noDeprecation = true;
@@ -10,30 +23,36 @@ import type { ApprovalPolicy } from "./approvals";
import type { CommandConfirmation } from "./utils/agent/agent-loop";
import type { AppConfig } from "./utils/config";
import type { ResponseItem } from "openai/resources/responses/responses";
import type { ReasoningEffort } from "openai/resources.mjs";
import App from "./app";
import { runSinglePass } from "./cli-singlepass";
import SessionsOverlay from "./components/sessions-overlay.js";
import { AgentLoop } from "./utils/agent/agent-loop";
import { initLogger } from "./utils/agent/log";
import { ReviewDecision } from "./utils/agent/review";
import { AutoApprovalMode } from "./utils/auto-approval-mode";
import { checkForUpdates } from "./utils/check-updates";
import {
loadConfig,
PRETTY_PRINT,
INSTRUCTIONS_FILEPATH,
} from "./utils/config";
import { createInputItem } from "./utils/input-utils";
import {
isModelSupportedForResponses,
preloadModels,
} from "./utils/model-utils.js";
getApiKey as fetchApiKey,
maybeRedeemCredits,
} from "./utils/get-api-key";
import { createInputItem } from "./utils/input-utils";
import { initLogger } from "./utils/logger/log";
import { isModelSupportedForResponses } from "./utils/model-utils.js";
import { parseToolCall } from "./utils/parsers";
import { providers } from "./utils/providers";
import { onExit, setInkRenderer } from "./utils/terminal";
import chalk from "chalk";
import { spawnSync } from "child_process";
import fs from "fs";
import { render } from "ink";
import meow from "meow";
import os from "os";
import path from "path";
import React from "react";
@@ -53,10 +72,16 @@ const cli = meow(
$ codex completion <bash|zsh|fish>
Options
--version Print version and exit
-h, --help Show usage and exit
-m, --model <model> Model to use for completions (default: o4-mini)
-m, --model <model> Model to use for completions (default: codex-mini-latest)
-p, --provider <provider> Provider to use for completions (default: openai)
-i, --image <path> Path(s) to image files to include as input
-v, --view <rollout> Inspect a previously saved rollout instead of starting a session
--history Browse previous sessions
--login Start a new sign in flow
--free Retry redeeming free credits
-q, --quiet Non-interactive mode that only prints the assistant's final output
-c, --config Open the instructions file in your editor
-w, --writable-root <path> Writable folder for sandbox in full-auto mode (can be specified multiple times)
@@ -65,11 +90,19 @@ const cli = meow(
--auto-edit Automatically approve file edits; still prompt for commands
--full-auto Automatically approve edits and commands when executed in the sandbox
--no-project-doc Do not automatically include the repository's 'codex.md'
--no-project-doc Do not automatically include the repository's 'AGENTS.md'
--project-doc <file> Include an additional markdown file at <file> as context
--full-stdout Do not truncate stdout/stderr from command outputs
--notify Enable desktop notifications for responses
--disable-response-storage Disable serverside response storage (sends the
full conversation context with every request)
--flex-mode Use "flex-mode" processing mode for the request (only supported
with models o3 and o4-mini)
--reasoning <effort> Set the reasoning effort level (low, medium, high) (default: high)
Dangerous options
--dangerously-auto-approve-everything
Skip all confirmation prompts and execute commands without
@@ -91,8 +124,13 @@ const cli = meow(
flags: {
// misc
help: { type: "boolean", aliases: ["h"] },
version: { type: "boolean", description: "Print version and exit" },
view: { type: "string" },
history: { type: "boolean", description: "Browse previous sessions" },
login: { type: "boolean", description: "Force a new sign in flow" },
free: { type: "boolean", description: "Retry redeeming free credits" },
model: { type: "string", aliases: ["m"] },
provider: { type: "string", aliases: ["p"] },
image: { type: "string", isMultiple: true, aliases: ["i"] },
quiet: {
type: "boolean",
@@ -133,24 +171,41 @@ const cli = meow(
},
noProjectDoc: {
type: "boolean",
description: "Disable automatic inclusion of projectlevel codex.md",
description: "Disable automatic inclusion of project-level AGENTS.md",
},
projectDoc: {
type: "string",
description: "Path to a markdown file to include as project doc",
},
flexMode: {
type: "boolean",
description:
"Enable the flex-mode service tier (only supported by models o3 and o4-mini)",
},
fullStdout: {
type: "boolean",
description:
"Disable truncation of command stdout/stderr messages (show everything)",
aliases: ["no-truncate"],
},
reasoning: {
type: "string",
description: "Set the reasoning effort level (low, medium, high)",
choices: ["low", "medium", "high"],
default: "high",
},
// Notification
notify: {
type: "boolean",
description: "Enable desktop notifications for responses",
},
disableResponseStorage: {
type: "boolean",
description:
"Disable server-side response storage (sends full conversation context with every request)",
},
// Experimental mode where whole directory is loaded in context and model is requested
// to make code edits in a single pass.
fullContext: {
@@ -163,6 +218,10 @@ const cli = meow(
},
);
// ---------------------------------------------------------------------------
// Global flag handling
// ---------------------------------------------------------------------------
// Handle 'completion' subcommand before any prompting or API calls
if (cli.input[0] === "completion") {
const shell = cli.input[1] || "bash";
@@ -182,7 +241,7 @@ _codex() {
}
_codex`,
fish: `# fish completion for codex
complete -c codex -a '(_fish_complete_path)' -d 'file path'`,
complete -c codex -a '(__fish_complete_path)' -d 'file path'`,
};
const script = scripts[shell];
if (!script) {
@@ -194,19 +253,20 @@ complete -c codex -a '(_fish_complete_path)' -d 'file path'`,
console.log(script);
process.exit(0);
}
// Show help if requested
// For --help, show help and exit.
if (cli.flags.help) {
cli.showHelp();
}
// Handle config flag: open instructions file in editor and exit
// For --config, open custom instructions file in editor and exit.
if (cli.flags.config) {
// Ensure configuration and instructions file exist
try {
loadConfig();
loadConfig(); // Ensures the file is created if it doesn't already exit.
} catch {
// ignore errors
}
const filePath = INSTRUCTIONS_FILEPATH;
const editor =
process.env["EDITOR"] || (process.platform === "win32" ? "notepad" : "vi");
@@ -218,45 +278,194 @@ if (cli.flags.config) {
// API key handling
// ---------------------------------------------------------------------------
const apiKey = process.env["OPENAI_API_KEY"];
if (!apiKey) {
// eslint-disable-next-line no-console
console.error(
`\n${chalk.red("Missing OpenAI API key.")}\n\n` +
`Set the environment variable ${chalk.bold("OPENAI_API_KEY")} ` +
`and re-run this command.\n` +
`You can create a key here: ${chalk.bold(
chalk.underline("https://platform.openai.com/account/api-keys"),
)}\n`,
);
process.exit(1);
}
const fullContextMode = Boolean(cli.flags.fullContext);
let config = loadConfig(undefined, undefined, {
cwd: process.cwd(),
disableProjectDoc: Boolean(cli.flags.noProjectDoc),
projectDocPath: cli.flags.projectDoc as string | undefined,
projectDocPath: cli.flags.projectDoc,
isFullContext: fullContextMode,
});
const prompt = cli.input[0];
const model = cli.flags.model;
const imagePaths = cli.flags.image as Array<string> | undefined;
// `prompt` can be updated later when the user resumes a previous session
// via the `--history` flag. Therefore it must be declared with `let` rather
// than `const`.
let prompt = cli.input[0];
const model = cli.flags.model ?? config.model;
const imagePaths = cli.flags.image;
const provider = cli.flags.provider ?? config.provider ?? "openai";
const client = {
issuer: "https://auth.openai.com",
client_id: "app_EMoamEEZ73f0CkXaXp7hrann",
};
let apiKey = "";
let savedTokens:
| {
id_token?: string;
access_token?: string;
refresh_token: string;
}
| undefined;
// Try to load existing auth file if present
try {
const home = os.homedir();
const authDir = path.join(home, ".codex");
const authFile = path.join(authDir, "auth.json");
if (fs.existsSync(authFile)) {
const data = JSON.parse(fs.readFileSync(authFile, "utf-8"));
savedTokens = data.tokens;
const lastRefreshTime = data.last_refresh
? new Date(data.last_refresh).getTime()
: 0;
const expired = Date.now() - lastRefreshTime > 28 * 24 * 60 * 60 * 1000;
if (data.OPENAI_API_KEY && !expired) {
apiKey = data.OPENAI_API_KEY;
}
}
} catch {
// ignore errors
}
// Get provider-specific API key if not OpenAI
if (provider.toLowerCase() !== "openai") {
const providerInfo = providers[provider.toLowerCase()];
if (providerInfo) {
const providerApiKey = process.env[providerInfo.envKey];
if (providerApiKey) {
apiKey = providerApiKey;
}
}
}
// Only proceed with OpenAI auth flow if:
// 1. Provider is OpenAI and no API key is set, or
// 2. Login flag is explicitly set
if (provider.toLowerCase() === "openai" && !apiKey) {
if (cli.flags.login) {
apiKey = await fetchApiKey(client.issuer, client.client_id);
try {
const home = os.homedir();
const authDir = path.join(home, ".codex");
const authFile = path.join(authDir, "auth.json");
if (fs.existsSync(authFile)) {
const data = JSON.parse(fs.readFileSync(authFile, "utf-8"));
savedTokens = data.tokens;
}
} catch {
/* ignore */
}
} else {
apiKey = await fetchApiKey(client.issuer, client.client_id);
}
}
// Ensure the API key is available as an environment variable for legacy code
process.env["OPENAI_API_KEY"] = apiKey;
// Only attempt credit redemption for OpenAI provider
if (cli.flags.free && provider.toLowerCase() === "openai") {
// eslint-disable-next-line no-console
console.log(`${chalk.bold("codex --free")} attempting to redeem credits...`);
if (!savedTokens?.refresh_token) {
apiKey = await fetchApiKey(client.issuer, client.client_id, true);
// fetchApiKey includes credit redemption as the end of the flow
} else {
await maybeRedeemCredits(
client.issuer,
client.client_id,
savedTokens.refresh_token,
savedTokens.id_token,
);
}
}
// Set of providers that don't require API keys
const NO_API_KEY_REQUIRED = new Set(["ollama"]);
// Skip API key validation for providers that don't require an API key
if (!apiKey && !NO_API_KEY_REQUIRED.has(provider.toLowerCase())) {
// eslint-disable-next-line no-console
console.error(
`\n${chalk.red(`Missing ${provider} API key.`)}\n\n` +
`Set the environment variable ${chalk.bold(
`${provider.toUpperCase()}_API_KEY`,
)} ` +
`and re-run this command.\n` +
`${
provider.toLowerCase() === "openai"
? `You can create a key here: ${chalk.bold(
chalk.underline("https://platform.openai.com/account/api-keys"),
)}\n`
: provider.toLowerCase() === "azure"
? `You can create a ${chalk.bold(
`${provider.toUpperCase()}_OPENAI_API_KEY`,
)} ` +
`in Azure AI Foundry portal at ${chalk.bold(chalk.underline("https://ai.azure.com"))}.\n`
: provider.toLowerCase() === "gemini"
? `You can create a ${chalk.bold(
`${provider.toUpperCase()}_API_KEY`,
)} ` + `in the ${chalk.bold(`Google AI Studio`)}.\n`
: `You can create a ${chalk.bold(
`${provider.toUpperCase()}_API_KEY`,
)} ` + `in the ${chalk.bold(`${provider}`)} dashboard.\n`
}`,
);
process.exit(1);
}
const flagPresent = Object.hasOwn(cli.flags, "disableResponseStorage");
const disableResponseStorage = flagPresent
? Boolean(cli.flags.disableResponseStorage) // value user actually passed
: (config.disableResponseStorage ?? false); // fall back to YAML, default to false
config = {
apiKey,
...config,
model: model ?? config.model,
notify: Boolean(cli.flags.notify),
reasoningEffort:
(cli.flags.reasoning as ReasoningEffort | undefined) ?? "medium",
flexMode: cli.flags.flexMode || (config.flexMode ?? false),
provider,
disableResponseStorage,
};
if (!(await isModelSupportedForResponses(config.model))) {
// Check for updates after loading config. This is important because we write state file in
// the config dir.
try {
await checkForUpdates();
} catch {
// ignore
}
// For --flex-mode, validate and exit if incorrect.
if (config.flexMode) {
const allowedFlexModels = new Set(["o3", "o4-mini"]);
if (!allowedFlexModels.has(config.model)) {
if (cli.flags.flexMode) {
// eslint-disable-next-line no-console
console.error(
`The --flex-mode option is only supported when using the 'o3' or 'o4-mini' models. ` +
`Current model: '${config.model}'.`,
);
process.exit(1);
} else {
config.flexMode = false;
}
}
}
if (
!(await isModelSupportedForResponses(provider, config.model)) &&
(!provider || provider.toLowerCase() === "openai")
) {
// eslint-disable-next-line no-console
console.error(
`The model "${config.model}" does not appear in the list of models ` +
`available to your account. Doublecheck the spelling (use\n` +
`available to your account. Double-check the spelling (use\n` +
` openai models list\n` +
`to see the full list) or choose another model with the --model flag.`,
);
@@ -265,6 +474,47 @@ if (!(await isModelSupportedForResponses(config.model))) {
let rollout: AppRollout | undefined;
// For --history, show session selector and optionally update prompt or rollout.
if (cli.flags.history) {
const result: { path: string; mode: "view" | "resume" } | null =
await new Promise((resolve) => {
const instance = render(
React.createElement(SessionsOverlay, {
onView: (p: string) => {
instance.unmount();
resolve({ path: p, mode: "view" });
},
onResume: (p: string) => {
instance.unmount();
resolve({ path: p, mode: "resume" });
},
onExit: () => {
instance.unmount();
resolve(null);
},
}),
);
});
if (!result) {
process.exit(0);
}
if (result.mode === "view") {
try {
const content = fs.readFileSync(result.path, "utf-8");
rollout = JSON.parse(content) as AppRollout;
} catch (error) {
// eslint-disable-next-line no-console
console.error("Error reading session file:", error);
process.exit(1);
}
} else {
prompt = `Resume this session: ${result.path}`;
}
}
// For --view, optionally load an existing rollout from disk, display it and exit.
if (cli.flags.view) {
const viewPath = cli.flags.view;
const absolutePath = path.isAbsolute(viewPath)
@@ -280,7 +530,7 @@ if (cli.flags.view) {
}
}
// If we are running in --fullcontext mode, do that and exit.
// For --fullcontext, run the separate cli entrypoint and exit.
if (fullContextMode) {
await runSinglePass({
originalPrompt: prompt,
@@ -296,14 +546,8 @@ const additionalWritableRoots: ReadonlyArray<string> = (
cli.flags.writableRoot ?? []
).map((p) => path.resolve(p));
// If we are running in --quiet mode, do that and exit.
const quietMode = Boolean(cli.flags.quiet);
const autoApproveEverything = Boolean(
cli.flags.dangerouslyAutoApproveEverything,
);
const fullStdout = Boolean(cli.flags.fullStdout);
if (quietMode) {
// For --quiet, run the cli without user interactions and exit.
if (cli.flags.quiet) {
process.env["CODEX_QUIET_MODE"] = "1";
if (!prompt || prompt.trim() === "") {
// eslint-disable-next-line no-console
@@ -312,12 +556,19 @@ if (quietMode) {
);
process.exit(1);
}
await runQuietMode({
prompt: prompt as string,
imagePaths: imagePaths || [],
approvalPolicy: autoApproveEverything
// Determine approval policy for quiet mode based on flags
const quietApprovalPolicy: ApprovalPolicy =
cli.flags.fullAuto || cli.flags.approvalMode === "full-auto"
? AutoApprovalMode.FULL_AUTO
: AutoApprovalMode.SUGGEST,
: cli.flags.autoEdit || cli.flags.approvalMode === "auto-edit"
? AutoApprovalMode.AUTO_EDIT
: config.approvalMode || AutoApprovalMode.SUGGEST;
await runQuietMode({
prompt,
imagePaths: imagePaths || [],
approvalPolicy: quietApprovalPolicy,
additionalWritableRoots,
config,
});
@@ -335,16 +586,15 @@ if (quietMode) {
// it is more dangerous than --fullAuto we deliberately give it lower
// priority so a user specifying both flags still gets the safer behaviour.
// 3. --autoEdit automatically approve edits, but prompt for commands.
// 4. Default suggest mode (prompt for everything).
// 4. config.approvalMode - use the approvalMode setting from ~/.codex/config.json.
// 5. Default suggest mode (prompt for everything).
const approvalPolicy: ApprovalPolicy =
cli.flags.fullAuto || cli.flags.approvalMode === "full-auto"
? AutoApprovalMode.FULL_AUTO
: cli.flags.autoEdit || cli.flags.approvalMode === "auto-edit"
? AutoApprovalMode.AUTO_EDIT
: AutoApprovalMode.SUGGEST;
preloadModels();
? AutoApprovalMode.AUTO_EDIT
: config.approvalMode || AutoApprovalMode.SUGGEST;
const instance = render(
<App
@@ -354,7 +604,7 @@ const instance = render(
imagePaths={imagePaths}
approvalPolicy={approvalPolicy}
additionalWritableRoots={additionalWritableRoots}
fullStdout={fullStdout}
fullStdout={Boolean(cli.flags.fullStdout)}
/>,
{
patchConsole: process.env["DEBUG"] ? false : true,
@@ -428,8 +678,10 @@ async function runQuietMode({
model: config.model,
config: config,
instructions: config.instructions,
provider: config.provider,
approvalPolicy,
additionalWritableRoots,
disableResponseStorage: config.disableResponseStorage,
onItem: (item: ResponseItem) => {
// eslint-disable-next-line no-console
console.log(formatResponseItemForQuietMode(item));
@@ -440,7 +692,12 @@ async function runQuietMode({
getCommandConfirmation: (
_command: Array<string>,
): Promise<CommandConfirmation> => {
return Promise.resolve({ review: ReviewDecision.NO_CONTINUE });
// In quiet mode, default to NO_CONTINUE, except when in full-auto mode
const reviewDecision =
approvalPolicy === AutoApprovalMode.FULL_AUTO
? ReviewDecision.YES
: ReviewDecision.NO_CONTINUE;
return Promise.resolve({ review: reviewDecision });
},
onLastResponseId: () => {
/* intentionally ignored in quiet mode */
@@ -461,13 +718,13 @@ process.on("SIGQUIT", exit);
process.on("SIGTERM", exit);
// ---------------------------------------------------------------------------
// Fallback for CtrlC when stdin is in rawmode
// Fallback for Ctrl-C when stdin is in raw-mode
// ---------------------------------------------------------------------------
if (process.stdin.isTTY) {
// Ensure we do not leave the terminal in raw mode if the user presses
// CtrlC while some other component has focus and Ink is intercepting
// input. Node does *not* emit a SIGINT in rawmode, so we listen for the
// Ctrl-C while some other component has focus and Ink is intercepting
// input. Node does *not* emit a SIGINT in raw-mode, so we listen for the
// corresponding byte (0x03) ourselves and trigger a graceful shutdown.
const onRawData = (data: Buffer | string): void => {
const str = Buffer.isBuffer(data) ? data.toString("utf8") : data;
@@ -478,6 +735,6 @@ if (process.stdin.isTTY) {
process.stdin.on("data", onRawData);
}
// Ensure terminal cleanup always runs, even when other code calls
// Ensure terminal clean-up always runs, even when other code calls
// `process.exit()` directly.
process.once("exit", onExit);

View File

@@ -1,6 +1,7 @@
import type { TerminalHeaderProps } from "./terminal-header.js";
import type { GroupedResponseItem } from "./use-message-grouping.js";
import type { ResponseItem } from "openai/resources/responses/responses.mjs";
import type { FileOpenerScheme } from "src/utils/config.js";
import TerminalChatResponseItem from "./terminal-chat-response-item.js";
import TerminalHeader from "./terminal-header.js";
@@ -19,11 +20,13 @@ type MessageHistoryProps = {
confirmationPrompt: React.ReactNode;
loading: boolean;
headerProps: TerminalHeaderProps;
fileOpener: FileOpenerScheme | undefined;
};
const MessageHistory: React.FC<MessageHistoryProps> = ({
batch,
headerProps,
fileOpener,
}) => {
const messages = batch.map(({ item }) => item!);
@@ -68,7 +71,10 @@ const MessageHistory: React.FC<MessageHistoryProps> = ({
message.type === "message" && message.role === "user" ? 0 : 1
}
>
<TerminalChatResponseItem item={message} />
<TerminalChatResponseItem
item={message}
fileOpener={fileOpener}
/>
</Box>
);
}}

View File

@@ -3,7 +3,7 @@
import { useTerminalSize } from "../../hooks/use-terminal-size";
import TextBuffer from "../../text-buffer.js";
import chalk from "chalk";
import { Box, Text, useInput, useStdin } from "ink";
import { Box, Text, useInput } from "ink";
import { EventEmitter } from "node:events";
import React, { useRef, useState } from "react";
@@ -14,7 +14,7 @@ import React, { useRef, useState } from "react";
* The real `process.stdin` object exposed by Node.js inherits these methods
* from `Socket`, but the lightweight stub used in tests only extends
* `EventEmitter`. Ink calls the two methods when enabling/disabling raw
* mode, so make them harmless noops when they're absent to avoid runtime
* mode, so make them harmless no-ops when they're absent to avoid runtime
* failures during unit tests.
* ----------------------------------------------------------------------- */
@@ -137,6 +137,9 @@ export interface MultilineTextEditorProps {
// Called when the internal text buffer updates.
readonly onChange?: (text: string) => void;
// Optional initial cursor position (character offset)
readonly initialCursorOffset?: number;
}
// Expose a minimal imperative API so parent components (e.g. TerminalChatInput)
@@ -155,6 +158,8 @@ export interface MultilineTextEditorHandle {
isCursorAtLastRow(): boolean;
/** Full text contents */
getText(): string;
/** Move the cursor to the end of the text */
moveCursorToEnd(): void;
}
const MultilineTextEditorInner = (
@@ -167,6 +172,7 @@ const MultilineTextEditorInner = (
onSubmit,
focus = true,
onChange,
initialCursorOffset,
}: MultilineTextEditorProps,
ref: React.Ref<MultilineTextEditorHandle | null>,
): React.ReactElement => {
@@ -174,7 +180,7 @@ const MultilineTextEditorInner = (
// Editor State
// ---------------------------------------------------------------------------
const buffer = useRef(new TextBuffer(initialText));
const buffer = useRef(new TextBuffer(initialText, initialCursorOffset));
const [version, setVersion] = useState(0);
// Keep track of the current terminal size so that the editor grows/shrinks
@@ -187,41 +193,6 @@ const MultilineTextEditorInner = (
// minimum so that the UI never becomes unusably small.
const effectiveWidth = Math.max(20, width ?? terminalSize.columns);
// ---------------------------------------------------------------------------
// External editor integration helpers.
// ---------------------------------------------------------------------------
// Access to stdin so we can toggle rawmode while the external editor is
// in control of the terminal.
const { stdin, setRawMode } = useStdin();
/**
* Launch the user's preferred $EDITOR, blocking until they close it, then
* reload the edited file back into the inmemory TextBuffer. The heavy
* work is delegated to `TextBuffer.openInExternalEditor`, but we are
* responsible for temporarily *disabling* raw mode so the child process can
* interact with the TTY normally.
*/
const openExternalEditor = React.useCallback(async () => {
// Preserve the current rawmode setting so we can restore it afterwards.
const wasRaw = stdin?.isRaw ?? false;
try {
setRawMode?.(false);
await buffer.current.openInExternalEditor();
} catch (err) {
// Surface the error so it doesn't fail silently for now we log to
// stderr. In the future this could surface a toast / overlay.
// eslint-disable-next-line no-console
console.error("[MultilineTextEditor] external editor error", err);
} finally {
if (wasRaw) {
setRawMode?.(true);
}
// Force a rerender so the component reflects the mutated buffer.
setVersion((v) => v + 1);
}
}, [buffer, stdin, setRawMode]);
// ---------------------------------------------------------------------------
// Keyboard handling.
// ---------------------------------------------------------------------------
@@ -232,25 +203,6 @@ const MultilineTextEditorInner = (
return;
}
// Singlestep editor shortcut: Ctrl+X or Ctrl+E
// Treat both true Ctrl+Key combinations *and* raw control codes so that
// the shortcut works consistently in real terminals (rawmode) and the
// inktestinglibrary stub which delivers only the raw byte (e.g. 0x05
// for CtrlE) without setting `key.ctrl`.
const isCtrlX =
(key.ctrl && (input === "x" || input === "\x18")) || input === "\x18";
const isCtrlE =
(key.ctrl && (input === "e" || input === "\x05")) ||
input === "\x05" ||
(!key.ctrl &&
input === "e" &&
input.length === 1 &&
input.charCodeAt(0) === 5);
if (isCtrlX || isCtrlE) {
openExternalEditor();
return;
}
if (
process.env["TEXTBUFFER_DEBUG"] === "1" ||
process.env["TEXTBUFFER_DEBUG"] === "true"
@@ -259,25 +211,47 @@ const MultilineTextEditorInner = (
console.log("[MultilineTextEditor] event", { input, key });
}
// 1) CSIu / modifyOtherKeys (Ink strips initial ESC, so we start with '[')
// 1a) CSI-u / modifyOtherKeys *mode 2* (Ink strips initial ESC, so we
// start with '[') format: "[<code>;<modifiers>u".
if (input.startsWith("[") && input.endsWith("u")) {
const m = input.match(/^\[([0-9]+);([0-9]+)u$/);
if (m && m[1] === "13") {
const mod = Number(m[2]);
// In xterm's encoding: bit1 (value 2) is Shift. Everything >1 that
// isn't exactly 1 means some modifier was held. We treat *shift
// present* (2,4,6,8) as newline; plain (1) as submit.
// In xterm's encoding: bit-1 (value 2) is Shift. Everything >1 that
// isn't exactly 1 means some modifier was held. We treat *shift or
// alt present* (2,3,4,6,8,9) as newline; Ctrl (bit-2 / value 4)
// triggers submit. See xterm/DEC modifyOtherKeys docs.
// Xterm encodes modifier keys in `mod` bit2 (value 4) indicates
// that Ctrl was held. We avoid the `&` bitwise operator (disallowed
// by our ESLint config) by using arithmetic instead.
const hasCtrl = Math.floor(mod / 4) % 2 === 1;
if (hasCtrl) {
if (onSubmit) {
onSubmit(buffer.current.getText());
}
} else {
// Any variant without Ctrl just inserts newline (Shift, Alt, none)
buffer.current.newline();
}
setVersion((v) => v + 1);
return;
}
}
// 1b) CSI-~ / modifyOtherKeys *mode 1* format: "[27;<mod>;<code>~".
// Terminals such as iTerm2 (default), older xterm versions, or when
// modifyOtherKeys=1 is configured, emit this legacy sequence. We
// translate it to the same behaviour as the mode2 variant above so
// that Shift+Enter (newline) / Ctrl+Enter (submit) work regardless
// of the users terminal settings.
if (input.startsWith("[27;") && input.endsWith("~")) {
const m = input.match(/^\[27;([0-9]+);13~$/);
if (m) {
const mod = Number(m[1]);
const hasCtrl = Math.floor(mod / 4) % 2 === 1;
if (hasCtrl) {
if (onSubmit) {
onSubmit(buffer.current.getText());
}
} else {
buffer.current.newline();
}
setVersion((v) => v + 1);
@@ -350,6 +324,16 @@ const MultilineTextEditorInner = (
return row === lineCount - 1;
},
getText: () => buffer.current.getText(),
moveCursorToEnd: () => {
buffer.current.move("home");
const lines = buffer.current.getText().split("\n");
for (let i = 0; i < lines.length - 1; i++) {
buffer.current.move("down");
}
buffer.current.move("end");
// Force a re-render
setVersion((v) => v + 1);
},
}),
[],
);
@@ -405,5 +389,4 @@ const MultilineTextEditorInner = (
};
const MultilineTextEditor = React.forwardRef(MultilineTextEditorInner);
export default MultilineTextEditor;

View File

@@ -15,11 +15,18 @@ const DEFAULT_DENY_MESSAGE =
export function TerminalChatCommandReview({
confirmationPrompt,
onReviewCommand,
// callback to switch approval mode overlay
onSwitchApprovalMode,
explanation: propExplanation,
// whether this review Select is active (listening for keys)
isActive = true,
}: {
confirmationPrompt: React.ReactNode;
onReviewCommand: (decision: ReviewDecision, customMessage?: string) => void;
onSwitchApprovalMode: () => void;
explanation?: string;
// when false, disable the underlying Select so it won't capture input
isActive?: boolean;
}): React.ReactElement {
const [mode, setMode] = React.useState<"select" | "input" | "explanation">(
"select",
@@ -70,6 +77,7 @@ export function TerminalChatCommandReview({
const opts: Array<
| { label: string; value: ReviewDecision }
| { label: string; value: "edit" }
| { label: string; value: "switch" }
> = [
{
label: "Yes (y)",
@@ -93,6 +101,11 @@ export function TerminalChatCommandReview({
label: "Edit or give feedback (e)",
value: "edit",
},
// allow switching approval mode
{
label: "Switch approval mode (s)",
value: "switch",
},
{
label: "No, and keep going (n)",
value: ReviewDecision.NO_CONTINUE,
@@ -106,44 +119,50 @@ export function TerminalChatCommandReview({
return opts;
}, [showAlwaysApprove]);
useInput((input, key) => {
if (mode === "select") {
if (input === "y") {
onReviewCommand(ReviewDecision.YES);
} else if (input === "x") {
onReviewCommand(ReviewDecision.EXPLAIN);
} else if (input === "e") {
setMode("input");
} else if (input === "n") {
onReviewCommand(
ReviewDecision.NO_CONTINUE,
"Don't do that, keep going though",
);
} else if (input === "a" && showAlwaysApprove) {
onReviewCommand(ReviewDecision.ALWAYS);
} else if (key.escape) {
onReviewCommand(ReviewDecision.NO_EXIT);
useInput(
(input, key) => {
if (mode === "select") {
if (input === "y") {
onReviewCommand(ReviewDecision.YES);
} else if (input === "x") {
onReviewCommand(ReviewDecision.EXPLAIN);
} else if (input === "e") {
setMode("input");
} else if (input === "n") {
onReviewCommand(
ReviewDecision.NO_CONTINUE,
"Don't do that, keep going though",
);
} else if (input === "a" && showAlwaysApprove) {
onReviewCommand(ReviewDecision.ALWAYS);
} else if (input === "s") {
// switch approval mode
onSwitchApprovalMode();
} else if (key.escape) {
onReviewCommand(ReviewDecision.NO_EXIT);
}
} else if (mode === "explanation") {
// When in explanation mode, any key returns to select mode
if (key.return || key.escape || input === "x") {
setMode("select");
}
} else {
// text entry mode
if (key.return) {
// if user hit enter on empty msg, fall back to DEFAULT_DENY_MESSAGE
const custom = msg.trim() === "" ? DEFAULT_DENY_MESSAGE : msg;
onReviewCommand(ReviewDecision.NO_CONTINUE, custom);
} else if (key.escape) {
// treat escape as denial with default message as well
onReviewCommand(
ReviewDecision.NO_CONTINUE,
msg.trim() === "" ? DEFAULT_DENY_MESSAGE : msg,
);
}
}
} else if (mode === "explanation") {
// When in explanation mode, any key returns to select mode
if (key.return || key.escape || input === "x") {
setMode("select");
}
} else {
// text entry mode
if (key.return) {
// if user hit enter on empty msg, fall back to DEFAULT_DENY_MESSAGE
const custom = msg.trim() === "" ? DEFAULT_DENY_MESSAGE : msg;
onReviewCommand(ReviewDecision.NO_CONTINUE, custom);
} else if (key.escape) {
// treat escape as denial with default message as well
onReviewCommand(
ReviewDecision.NO_CONTINUE,
msg.trim() === "" ? DEFAULT_DENY_MESSAGE : msg,
);
}
}
});
},
{ isActive },
);
return (
<Box flexDirection="column" gap={1} borderStyle="round" marginTop={1}>
@@ -191,9 +210,13 @@ export function TerminalChatCommandReview({
<Text>Allow command?</Text>
<Box paddingX={2} flexDirection="column" gap={1}>
<Select
onChange={(value: ReviewDecision | "edit") => {
isDisabled={!isActive}
visibleOptionCount={approvalOptions.length}
onChange={(value: ReviewDecision | "edit" | "switch") => {
if (value === "edit") {
setMode("input");
} else if (value === "switch") {
onSwitchApprovalMode();
} else {
onReviewCommand(value);
}

View File

@@ -0,0 +1,64 @@
import { Box, Text } from "ink";
import React, { useMemo } from "react";
type TextCompletionProps = {
/**
* Array of text completion options to display in the list
*/
completions: Array<string>;
/**
* Maximum number of completion items to show at once in the view
*/
displayLimit: number;
/**
* Index of the currently selected completion in the completions array
*/
selectedCompletion: number;
};
function TerminalChatCompletions({
completions,
selectedCompletion,
displayLimit,
}: TextCompletionProps): JSX.Element {
const visibleItems = useMemo(() => {
// Try to keep selection centered in view
let startIndex = Math.max(
0,
selectedCompletion - Math.floor(displayLimit / 2),
);
// Fix window position when at the end of the list
if (completions.length - startIndex < displayLimit) {
startIndex = Math.max(0, completions.length - displayLimit);
}
const endIndex = Math.min(completions.length, startIndex + displayLimit);
return completions.slice(startIndex, endIndex).map((completion, index) => ({
completion,
originalIndex: index + startIndex,
}));
}, [completions, selectedCompletion, displayLimit]);
return (
<Box flexDirection="column">
{visibleItems.map(({ completion, originalIndex }) => (
<Text
key={completion}
dimColor={originalIndex !== selectedCompletion}
underline={originalIndex === selectedCompletion}
backgroundColor={
originalIndex === selectedCompletion ? "blackBright" : undefined
}
>
{completion}
</Text>
))}
</Box>
);
}
export default TerminalChatCompletions;

View File

@@ -1,82 +1,28 @@
import { log, isLoggingEnabled } from "../../utils/agent/log.js";
import Spinner from "../vendor/ink-spinner.js";
import { log } from "../../utils/logger/log.js";
import { Box, Text, useInput, useStdin } from "ink";
import React, { useState } from "react";
import { useInterval } from "use-interval";
const thinkingTexts = ["Thinking"]; /* [
"Consulting the rubber duck",
"Maximizing paperclips",
"Reticulating splines",
"Immanentizing the Eschaton",
"Thinking",
"Thinking about thinking",
"Spinning in circles",
"Counting dust specks",
"Updating priors",
"Feeding the utility monster",
"Taking off",
"Wireheading",
"Counting to infinity",
"Staring into the Basilisk",
"Negotiationing acausal trades",
"Searching the library of babel",
"Multiplying matrices",
"Solving the halting problem",
"Counting grains of sand",
"Simulating a simulation",
"Asking the oracle",
"Detangling qubits",
"Reading tea leaves",
"Pondering universal love and transcendent joy",
"Feeling the AGI",
"Shaving the yak",
"Escaping local minima",
"Pruning the search tree",
"Descending the gradient",
"Bikeshedding",
"Securing funding",
"Rewriting in Rust",
"Engaging infinite improbability drive",
"Clapping with one hand",
"Synthesizing",
"Rebasing thesis onto antithesis",
"Transcending the loop",
"Frogeposting",
"Summoning",
"Peeking beyond the veil",
"Seeking",
"Entering deep thought",
"Meditating",
"Decomposing",
"Creating",
"Beseeching the machine spirit",
"Calibrating moral compass",
"Collapsing the wave function",
"Doodling",
"Translating whale song",
"Whispering to silicon",
"Looking for semicolons",
"Asking ChatGPT",
"Bargaining with entropy",
"Channeling",
"Cooking",
"Parroting stochastically",
]; */
// Retaining a single static placeholder text for potential future use. The
// more elaborate randomised thinking prompts were removed to streamline the
// UI the elapsedtime counter now provides sufficient feedback.
export default function TerminalChatInputThinking({
onInterrupt,
active,
thinkingSeconds,
}: {
onInterrupt: () => void;
active: boolean;
thinkingSeconds: number;
}): React.ReactElement {
const [dots, setDots] = useState("");
const [awaitingConfirm, setAwaitingConfirm] = useState(false);
const [dots, setDots] = useState("");
const [thinkingText, setThinkingText] = useState(
() => thinkingTexts[Math.floor(Math.random() * thinkingTexts.length)],
);
// Animate the ellipsis
useInterval(() => {
setDots((prev) => (prev.length < 3 ? prev + "." : ""));
}, 500);
const { stdin, setRawMode } = useStdin();
@@ -94,11 +40,9 @@ export default function TerminalChatInputThinking({
const str = Buffer.isBuffer(data) ? data.toString("utf8") : data;
if (str === "\x1b\x1b") {
if (isLoggingEnabled()) {
log(
"raw stdin: received collapsed ESC ESC starting confirmation timer",
);
}
log(
"raw stdin: received collapsed ESC ESC starting confirmation timer",
);
setAwaitingConfirm(true);
setTimeout(() => setAwaitingConfirm(false), 1500);
}
@@ -110,25 +54,7 @@ export default function TerminalChatInputThinking({
};
}, [stdin, awaitingConfirm, onInterrupt, active, setRawMode]);
useInterval(() => {
setDots((prev) => (prev.length < 3 ? prev + "." : ""));
}, 500);
useInterval(
() => {
setThinkingText((prev) => {
let next = prev;
if (thinkingTexts.length > 1) {
while (next === prev) {
next =
thinkingTexts[Math.floor(Math.random() * thinkingTexts.length)];
}
}
return next;
});
},
active ? 30000 : null,
);
// No timers required beyond tracking the elapsed seconds supplied via props.
useInput(
(_input, key) => {
@@ -137,15 +63,11 @@ export default function TerminalChatInputThinking({
}
if (awaitingConfirm) {
if (isLoggingEnabled()) {
log("useInput: second ESC detected triggering onInterrupt()");
}
log("useInput: second ESC detected triggering onInterrupt()");
onInterrupt();
setAwaitingConfirm(false);
} else {
if (isLoggingEnabled()) {
log("useInput: first ESC detected waiting for confirmation");
}
log("useInput: first ESC detected waiting for confirmation");
setAwaitingConfirm(true);
setTimeout(() => setAwaitingConfirm(false), 1500);
}
@@ -153,13 +75,47 @@ export default function TerminalChatInputThinking({
{ isActive: active },
);
// Custom ball animation including the elapsed seconds
const ballFrames = [
"( ● )",
"( ● )",
"( ● )",
"( ● )",
"( ●)",
"( ● )",
"( ● )",
"( ● )",
"( ● )",
"(● )",
];
const [frame, setFrame] = useState(0);
useInterval(() => {
setFrame((idx) => (idx + 1) % ballFrames.length);
}, 80);
// Preserve the spinner (ball) animation while keeping the elapsed seconds
// text static. We achieve this by rendering the bouncing ball inside the
// parentheses and appending the seconds counter *after* the spinner rather
// than injecting it directly next to the ball (which caused the counter to
// move horizontally together with the ball).
const frameTemplate = ballFrames[frame] ?? ballFrames[0];
const frameWithSeconds = `${frameTemplate} ${thinkingSeconds}s`;
return (
<Box flexDirection="column" gap={1}>
<Box gap={2}>
<Spinner type="ball" />
<Box justifyContent="space-between">
<Box gap={2}>
<Text>{frameWithSeconds}</Text>
<Text>
Thinking
{dots}
</Text>
</Box>
<Text>
{thinkingText}
{dots}
Press <Text bold>Esc</Text> twice to interrupt
</Text>
</Box>
{awaitingConfirm && (

View File

@@ -1,25 +1,36 @@
import type { MultilineTextEditorHandle } from "./multiline-editor";
import type { ReviewDecision } from "../../utils/agent/review.js";
import type { FileSystemSuggestion } from "../../utils/file-system-suggestions.js";
import type { HistoryEntry } from "../../utils/storage/command-history.js";
import type {
ResponseInputItem,
ResponseItem,
} from "openai/resources/responses/responses.mjs";
import MultilineTextEditor from "./multiline-editor";
import { TerminalChatCommandReview } from "./terminal-chat-command-review.js";
import { log, isLoggingEnabled } from "../../utils/agent/log.js";
import TextCompletions from "./terminal-chat-completions.js";
import { loadConfig } from "../../utils/config.js";
import { getFileSystemSuggestions } from "../../utils/file-system-suggestions.js";
import { expandFileTags } from "../../utils/file-tag-utils";
import { createInputItem } from "../../utils/input-utils.js";
import { log } from "../../utils/logger/log.js";
import { setSessionId } from "../../utils/session.js";
import { SLASH_COMMANDS, type SlashCommand } from "../../utils/slash-commands";
import {
loadCommandHistory,
addToHistory,
} from "../../utils/storage/command-history.js";
import { clearTerminal, onExit } from "../../utils/terminal.js";
import Spinner from "../vendor/ink-spinner.js";
import TextInput from "../vendor/ink-text-input.js";
import { Box, Text, useApp, useInput, useStdin } from "ink";
import { fileURLToPath } from "node:url";
import React, { useCallback, useState, Fragment, useEffect } from "react";
import React, {
useCallback,
useState,
Fragment,
useEffect,
useRef,
} from "react";
import { useInterval } from "use-interval";
const suggestions = [
@@ -42,9 +53,13 @@ export default function TerminalChatInput({
openModelOverlay,
openApprovalOverlay,
openHelpOverlay,
openDiffOverlay,
openSessionsOverlay,
onCompact,
interruptAgent,
active,
thinkingSeconds,
items = [],
}: {
isNew: boolean;
loading: boolean;
@@ -62,16 +77,138 @@ export default function TerminalChatInput({
openModelOverlay: () => void;
openApprovalOverlay: () => void;
openHelpOverlay: () => void;
openDiffOverlay: () => void;
openSessionsOverlay: () => void;
onCompact: () => void;
interruptAgent: () => void;
active: boolean;
thinkingSeconds: number;
// New: current conversation items so we can include them in bug reports
items?: Array<ResponseItem>;
}): React.ReactElement {
// Slash command suggestion index
const [selectedSlashSuggestion, setSelectedSlashSuggestion] =
useState<number>(0);
const app = useApp();
const [selectedSuggestion, setSelectedSuggestion] = useState<number>(0);
const [input, setInput] = useState("");
const [history, setHistory] = useState<Array<HistoryEntry>>([]);
const [historyIndex, setHistoryIndex] = useState<number | null>(null);
const [draftInput, setDraftInput] = useState<string>("");
const [skipNextSubmit, setSkipNextSubmit] = useState<boolean>(false);
const [fsSuggestions, setFsSuggestions] = useState<
Array<FileSystemSuggestion>
>([]);
const [selectedCompletion, setSelectedCompletion] = useState<number>(-1);
// Multiline text editor key to force remount after submission
const [editorState, setEditorState] = useState<{
key: number;
initialCursorOffset?: number;
}>({ key: 0 });
// Imperative handle from the multiline editor so we can query caret position
const editorRef = useRef<MultilineTextEditorHandle | null>(null);
// Track the caret row across keystrokes
const prevCursorRow = useRef<number | null>(null);
const prevCursorWasAtLastRow = useRef<boolean>(false);
// --- Helper for updating input, remounting editor, and moving cursor to end ---
const applyFsSuggestion = useCallback((newInputText: string) => {
setInput(newInputText);
setEditorState((s) => ({
key: s.key + 1,
initialCursorOffset: newInputText.length,
}));
}, []);
// --- Helper for updating file system suggestions ---
function updateFsSuggestions(
txt: string,
alwaysUpdateSelection: boolean = false,
) {
// Clear file system completions if a space is typed
if (txt.endsWith(" ")) {
setFsSuggestions([]);
setSelectedCompletion(-1);
} else {
// Determine the current token (last whitespace-separated word)
const words = txt.trim().split(/\s+/);
const lastWord = words[words.length - 1] ?? "";
const shouldUpdateSelection =
lastWord.startsWith("@") || alwaysUpdateSelection;
// Strip optional leading '@' for the path prefix
let pathPrefix: string;
if (lastWord.startsWith("@")) {
pathPrefix = lastWord.slice(1);
// If only '@' is typed, list everything in the current directory
pathPrefix = pathPrefix.length === 0 ? "./" : pathPrefix;
} else {
pathPrefix = lastWord;
}
if (shouldUpdateSelection) {
const completions = getFileSystemSuggestions(pathPrefix);
setFsSuggestions(completions);
if (completions.length > 0) {
setSelectedCompletion((prev) =>
prev < 0 || prev >= completions.length ? 0 : prev,
);
} else {
setSelectedCompletion(-1);
}
} else if (fsSuggestions.length > 0) {
// Token cleared → clear menu
setFsSuggestions([]);
setSelectedCompletion(-1);
}
}
}
/**
* Result of replacing text with a file system suggestion
*/
interface ReplacementResult {
/** The new text with the suggestion applied */
text: string;
/** The selected suggestion if a replacement was made */
suggestion: FileSystemSuggestion | null;
/** Whether a replacement was actually made */
wasReplaced: boolean;
}
// --- Helper for replacing input with file system suggestion ---
function getFileSystemSuggestion(
txt: string,
requireAtPrefix: boolean = false,
): ReplacementResult {
if (fsSuggestions.length === 0 || selectedCompletion < 0) {
return { text: txt, suggestion: null, wasReplaced: false };
}
const words = txt.trim().split(/\s+/);
const lastWord = words[words.length - 1] ?? "";
// Check if @ prefix is required and the last word doesn't have it
if (requireAtPrefix && !lastWord.startsWith("@")) {
return { text: txt, suggestion: null, wasReplaced: false };
}
const selected = fsSuggestions[selectedCompletion];
if (!selected) {
return { text: txt, suggestion: null, wasReplaced: false };
}
const replacement = lastWord.startsWith("@")
? `@${selected.path}`
: selected.path;
words[words.length - 1] = replacement;
return {
text: words.join(" "),
suggestion: selected,
wasReplaced: true,
};
}
// Load command history on component mount
useEffect(() => {
@@ -82,45 +219,226 @@ export default function TerminalChatInput({
loadHistory();
}, []);
// Reset slash suggestion index when input prefix changes
useEffect(() => {
if (input.trim().startsWith("/")) {
setSelectedSlashSuggestion(0);
}
}, [input]);
useInput(
(_input, _key) => {
if (!confirmationPrompt && !loading) {
if (_key.upArrow) {
if (history.length > 0) {
if (historyIndex == null) {
setDraftInput(input);
// Slash command navigation: up/down to select, enter to fill
if (!confirmationPrompt && !loading && input.trim().startsWith("/")) {
const prefix = input.trim();
const matches = SLASH_COMMANDS.filter((cmd: SlashCommand) =>
cmd.command.startsWith(prefix),
);
if (matches.length > 0) {
if (_key.tab) {
// Cycle and fill slash command suggestions on Tab
const len = matches.length;
// Determine new index based on shift state
const nextIdx = _key.shift
? selectedSlashSuggestion <= 0
? len - 1
: selectedSlashSuggestion - 1
: selectedSlashSuggestion >= len - 1
? 0
: selectedSlashSuggestion + 1;
setSelectedSlashSuggestion(nextIdx);
// Autocomplete the command in the input
const match = matches[nextIdx];
if (!match) {
return;
}
const cmd = match.command;
setInput(cmd);
setDraftInput(cmd);
return;
}
if (_key.upArrow) {
setSelectedSlashSuggestion((prev) =>
prev <= 0 ? matches.length - 1 : prev - 1,
);
return;
}
if (_key.downArrow) {
setSelectedSlashSuggestion((prev) =>
prev < 0 || prev >= matches.length - 1 ? 0 : prev + 1,
);
return;
}
if (_key.return) {
// Execute the currently selected slash command
const selIdx = selectedSlashSuggestion;
const cmdObj = matches[selIdx];
if (cmdObj) {
const cmd = cmdObj.command;
setInput("");
setDraftInput("");
setSelectedSlashSuggestion(0);
switch (cmd) {
case "/history":
openOverlay();
break;
case "/sessions":
openSessionsOverlay();
break;
case "/help":
openHelpOverlay();
break;
case "/compact":
onCompact();
break;
case "/model":
openModelOverlay();
break;
case "/approval":
openApprovalOverlay();
break;
case "/diff":
openDiffOverlay();
break;
case "/bug":
onSubmit(cmd);
break;
case "/clear":
onSubmit(cmd);
break;
case "/clearhistory":
onSubmit(cmd);
break;
default:
break;
}
}
return;
}
}
}
if (!confirmationPrompt && !loading) {
if (fsSuggestions.length > 0) {
if (_key.upArrow) {
setSelectedCompletion((prev) =>
prev <= 0 ? fsSuggestions.length - 1 : prev - 1,
);
return;
}
if (_key.downArrow) {
setSelectedCompletion((prev) =>
prev >= fsSuggestions.length - 1 ? 0 : prev + 1,
);
return;
}
if (_key.tab && selectedCompletion >= 0) {
const { text: newText, wasReplaced } =
getFileSystemSuggestion(input);
// Only proceed if the text was actually changed
if (wasReplaced) {
applyFsSuggestion(newText);
setFsSuggestions([]);
setSelectedCompletion(-1);
}
return;
}
}
if (_key.upArrow) {
let moveThroughHistory = true;
// Only use history when the caret was *already* on the very first
// row *before* this key-press.
const cursorRow = editorRef.current?.getRow?.() ?? 0;
const cursorCol = editorRef.current?.getCol?.() ?? 0;
const wasAtFirstRow = (prevCursorRow.current ?? cursorRow) === 0;
if (!(cursorRow === 0 && wasAtFirstRow)) {
moveThroughHistory = false;
}
// If we are not yet in history mode, then also require that the col is zero so that
// we only trigger history navigation when the user is at the start of the input.
if (historyIndex == null && !(cursorRow === 0 && cursorCol === 0)) {
moveThroughHistory = false;
}
// Move through history.
if (history.length && moveThroughHistory) {
let newIndex: number;
if (historyIndex == null) {
const currentDraft = editorRef.current?.getText?.() ?? input;
setDraftInput(currentDraft);
newIndex = history.length - 1;
} else {
newIndex = Math.max(0, historyIndex - 1);
}
setHistoryIndex(newIndex);
setInput(history[newIndex]?.command ?? "");
// Re-mount the editor so it picks up the new initialText
setEditorState((s) => ({ key: s.key + 1 }));
return; // handled
}
return;
// Otherwise let it propagate.
}
if (_key.downArrow) {
if (historyIndex == null) {
return;
// Only move forward in history when we're already *in* history mode
// AND the caret sits on the last line of the buffer.
const wasAtLastRow =
prevCursorWasAtLastRow.current ??
editorRef.current?.isCursorAtLastRow() ??
true;
if (historyIndex != null && wasAtLastRow) {
const newIndex = historyIndex + 1;
if (newIndex >= history.length) {
setHistoryIndex(null);
setInput(draftInput);
setEditorState((s) => ({ key: s.key + 1 }));
} else {
setHistoryIndex(newIndex);
setInput(history[newIndex]?.command ?? "");
setEditorState((s) => ({ key: s.key + 1 }));
}
return; // handled
}
// Otherwise let it propagate
}
const newIndex = historyIndex + 1;
if (newIndex >= history.length) {
setHistoryIndex(null);
setInput(draftInput);
} else {
setHistoryIndex(newIndex);
setInput(history[newIndex]?.command ?? "");
}
return;
// Defer filesystem suggestion logic to onSubmit if enter key is pressed
if (!_key.return) {
// Pressing tab should trigger the file system suggestions
const shouldUpdateSelection = _key.tab;
const targetInput = _key.delete ? input.slice(0, -1) : input + _input;
updateFsSuggestions(targetInput, shouldUpdateSelection);
}
}
// Update the cached cursor position *after* **all** handlers (including
// the internal <MultilineTextEditor>) have processed this key event.
//
// Ink invokes `useInput` callbacks starting with **parent** components
// first, followed by their descendants. As a result the call above
// executes *before* the editor has had a chance to react to the key
// press and update its internal caret position. When navigating
// through a multi-line draft with the ↑ / ↓ arrow keys this meant we
// recorded the *old* cursor row instead of the one that results *after*
// the key press. Consequently, a subsequent ↑ still saw
// `prevCursorRow = 1` even though the caret was already on row 0 and
// history-navigation never kicked in.
//
// Defer the sampling by one tick so we read the *final* caret position
// for this frame.
setTimeout(() => {
prevCursorRow.current = editorRef.current?.getRow?.() ?? null;
prevCursorWasAtLastRow.current =
editorRef.current?.isCursorAtLastRow?.() ?? true;
}, 1);
if (input.trim() === "" && isNew) {
if (_key.tab) {
setSelectedSuggestion(
@@ -152,66 +470,95 @@ export default function TerminalChatInput({
const onSubmit = useCallback(
async (value: string) => {
const inputValue = value.trim();
if (!inputValue) {
// If the user only entered a slash, do not send a chat message.
if (inputValue === "/") {
setInput("");
return;
}
if (inputValue === "/history") {
// Skip this submit if we just autocompleted a slash command.
if (skipNextSubmit) {
setSkipNextSubmit(false);
return;
}
if (!inputValue) {
return;
} else if (inputValue === "/history") {
setInput("");
openOverlay();
return;
}
if (inputValue === "/help") {
} else if (inputValue === "/sessions") {
setInput("");
openSessionsOverlay();
return;
} else if (inputValue === "/help") {
setInput("");
openHelpOverlay();
return;
}
if (inputValue === "/compact") {
} else if (inputValue === "/diff") {
setInput("");
openDiffOverlay();
return;
} else if (inputValue === "/compact") {
setInput("");
onCompact();
return;
}
if (inputValue.startsWith("/model")) {
} else if (inputValue.startsWith("/model")) {
setInput("");
openModelOverlay();
return;
}
if (inputValue.startsWith("/approval")) {
} else if (inputValue.startsWith("/approval")) {
setInput("");
openApprovalOverlay();
return;
}
if (inputValue === "q" || inputValue === ":q" || inputValue === "exit") {
} else if (["exit", "q", ":q"].includes(inputValue)) {
setInput("");
// wait one 60ms frame
setTimeout(() => {
app.exit();
onExit();
process.exit(0);
}, 60);
}, 60); // Wait one frame.
return;
} else if (inputValue === "/clear" || inputValue === "clear") {
setInput("");
setSessionId("");
setLastResponseId("");
// Clear the terminal screen (including scrollback) before resetting context.
clearTerminal();
// Emit a system message to confirm the clear action. We *append*
// it so Ink's <Static> treats it as new output and actually renders it.
setItems((prev) => [
...prev,
{
id: `clear-${Date.now()}`,
type: "message",
role: "system",
content: [{ type: "input_text", text: "Context cleared" }],
},
]);
setItems((prev) => {
const filteredOldItems = prev.filter((item) => {
// Remove any tokenheavy entries (user/assistant turns and function calls)
if (
item.type === "message" &&
(item.role === "user" || item.role === "assistant")
) {
return false;
}
if (
item.type === "function_call" ||
item.type === "function_call_output"
) {
return false;
}
return true; // keep developer/system and other meta entries
});
return [
...filteredOldItems,
{
id: `clear-${Date.now()}`,
type: "message",
role: "system",
content: [{ type: "input_text", text: "Terminal cleared" }],
},
];
});
return;
} else if (inputValue === "/clearhistory") {
@@ -224,7 +571,7 @@ export default function TerminalChatInput({
await clearCommandHistory();
setHistory([]);
// Emit a system message to confirm the history clear action
// Emit a system message to confirm the history clear action.
setItems((prev) => [
...prev,
{
@@ -239,12 +586,65 @@ export default function TerminalChatInput({
},
);
return;
} else if (inputValue === "/bug") {
// Generate a GitHub bug report URL prefilled with session details.
setInput("");
try {
const os = await import("node:os");
const { CLI_VERSION } = await import("../../version.js");
const { buildBugReportUrl } = await import(
"../../utils/bug-report.js"
);
const url = buildBugReportUrl({
items: items ?? [],
cliVersion: CLI_VERSION,
model: loadConfig().model ?? "unknown",
platform: [os.platform(), os.arch(), os.release()]
.map((s) => `\`${s}\``)
.join(" | "),
});
setItems((prev) => [
...prev,
{
id: `bugreport-${Date.now()}`,
type: "message",
role: "system",
content: [
{
type: "input_text",
text: `🔗 Bug report URL: ${url}`,
},
],
},
]);
} catch (error) {
// If anything went wrong, notify the user.
setItems((prev) => [
...prev,
{
id: `bugreport-error-${Date.now()}`,
type: "message",
role: "system",
content: [
{
type: "input_text",
text: `⚠️ Failed to create bug report URL: ${error}`,
},
],
},
]);
}
return;
} else if (inputValue.startsWith("/")) {
// Handle invalid/unrecognized commands.
// Only single-word inputs starting with '/' (e.g., /command) that are not recognized are caught here.
// Any other input, including those starting with '/' but containing spaces
// (e.g., "/command arg"), will fall through and be treated as a regular prompt.
// Handle invalid/unrecognized commands. Only single-word inputs starting with '/'
// (e.g., /command) that are not recognized are caught here. Any other input, including
// those starting with '/' but containing spaces (e.g., "/command arg"), will fall through
// and be treated as a regular prompt.
const trimmed = inputValue.trim();
if (/^\/\S+$/.test(trimmed)) {
@@ -271,11 +671,13 @@ export default function TerminalChatInput({
// detect image file paths for dynamic inclusion
const images: Array<string> = [];
let text = inputValue;
// markdown-style image syntax: ![alt](path)
text = text.replace(/!\[[^\]]*?\]\(([^)]+)\)/g, (_m, p1: string) => {
images.push(p1.startsWith("file://") ? fileURLToPath(p1) : p1);
return "";
});
// quoted file paths ending with common image extensions (e.g. '/path/to/img.png')
text = text.replace(
/['"]([^'"]+?\.(?:png|jpe?g|gif|bmp|webp|svg))['"]/gi,
@@ -284,6 +686,7 @@ export default function TerminalChatInput({
return "";
},
);
// bare file paths ending with common image extensions
text = text.replace(
// eslint-disable-next-line no-useless-escape
@@ -297,13 +700,16 @@ export default function TerminalChatInput({
);
text = text.trim();
const inputItem = await createInputItem(text, images);
// Expand @file tokens into XML blocks for the model
const expandedText = await expandFileTags(text);
const inputItem = await createInputItem(expandedText, images);
submitInput([inputItem]);
// Get config for history persistence
// Get config for history persistence.
const config = loadConfig();
// Add to history and update state
// Add to history and update state.
const updatedHistory = await addToHistory(value, history, {
maxSize: config.history?.maxSize ?? 1000,
saveHistory: config.history?.saveHistory ?? true,
@@ -315,6 +721,8 @@ export default function TerminalChatInput({
setDraftInput("");
setSelectedSuggestion(0);
setInput("");
setFsSuggestions([]);
setSelectedCompletion(-1);
},
[
setInput,
@@ -328,8 +736,12 @@ export default function TerminalChatInput({
openApprovalOverlay,
openModelOverlay,
openHelpOverlay,
history, // Add history to the dependency array
openDiffOverlay,
openSessionsOverlay,
history,
onCompact,
skipNextSubmit,
items,
],
);
@@ -338,7 +750,11 @@ export default function TerminalChatInput({
<TerminalChatCommandReview
confirmationPrompt={confirmationPrompt}
onReviewCommand={submitConfirmation}
// allow switching approval mode via 'v'
onSwitchApprovalMode={openApprovalOverlay}
explanation={explanation}
// disable when input is inactive (e.g., overlay open)
isActive={active}
/>
);
}
@@ -350,65 +766,114 @@ export default function TerminalChatInput({
<TerminalChatInputThinking
onInterrupt={interruptAgent}
active={active}
thinkingSeconds={thinkingSeconds}
/>
) : (
<Box paddingX={1}>
<TextInput
focus={active}
placeholder={
selectedSuggestion
? `"${suggestions[selectedSuggestion - 1]}"`
: "send a message" +
(isNew ? " or press tab to select a suggestion" : "")
}
showCursor
value={input}
onChange={(value) => {
setDraftInput(value);
<MultilineTextEditor
ref={editorRef}
onChange={(txt: string) => {
setDraftInput(txt);
if (historyIndex != null) {
setHistoryIndex(null);
}
setInput(value);
setInput(txt);
}}
key={editorState.key}
initialCursorOffset={editorState.initialCursorOffset}
initialText={input}
height={6}
focus={active}
onSubmit={(txt) => {
// If final token is an @path, replace with filesystem suggestion if available
const {
text: replacedText,
suggestion,
wasReplaced,
} = getFileSystemSuggestion(txt, true);
// If we replaced @path token with a directory, don't submit
if (wasReplaced && suggestion?.isDirectory) {
applyFsSuggestion(replacedText);
// Update suggestions for the new directory
updateFsSuggestions(replacedText, true);
return;
}
onSubmit(replacedText);
setEditorState((s) => ({ key: s.key + 1 }));
setInput("");
setHistoryIndex(null);
setDraftInput("");
}}
onSubmit={onSubmit}
/>
</Box>
)}
</Box>
{/* Slash command autocomplete suggestions */}
{input.trim().startsWith("/") && (
<Box flexDirection="column" paddingX={2} marginBottom={1}>
{SLASH_COMMANDS.filter((cmd: SlashCommand) =>
cmd.command.startsWith(input.trim()),
).map((cmd: SlashCommand, idx: number) => (
<Box key={cmd.command}>
<Text
backgroundColor={
idx === selectedSlashSuggestion ? "blackBright" : undefined
}
>
<Text color="blueBright">{cmd.command}</Text>
<Text> {cmd.description}</Text>
</Text>
</Box>
))}
</Box>
)}
<Box paddingX={2} marginBottom={1}>
<Text dimColor>
{isNew && !input ? (
<>
try:{" "}
{suggestions.map((m, key) => (
<Fragment key={key}>
{key !== 0 ? " | " : ""}
<Text
backgroundColor={
key + 1 === selectedSuggestion ? "blackBright" : ""
}
>
{m}
</Text>
</Fragment>
))}
</>
) : (
<>
send q or ctrl+c to exit | send "/clear" to reset | send "/help"
for commands | press enter to send
{contextLeftPercent < 25 && (
<>
{" — "}
<Text color="red">
{Math.round(contextLeftPercent)}% context left send
"/compact" to condense context
</Text>
</>
)}
</>
)}
</Text>
{isNew && !input ? (
<Text dimColor>
try:{" "}
{suggestions.map((m, key) => (
<Fragment key={key}>
{key !== 0 ? " | " : ""}
<Text
backgroundColor={
key + 1 === selectedSuggestion ? "blackBright" : ""
}
>
{m}
</Text>
</Fragment>
))}
</Text>
) : fsSuggestions.length > 0 ? (
<TextCompletions
completions={fsSuggestions.map((suggestion) => suggestion.path)}
selectedCompletion={selectedCompletion}
displayLimit={5}
/>
) : (
<Text dimColor>
ctrl+c to exit | "/" to see commands | enter to send
{contextLeftPercent > 25 && (
<>
{" — "}
<Text color={contextLeftPercent > 40 ? "green" : "yellow"}>
{Math.round(contextLeftPercent)}% context left
</Text>
</>
)}
{contextLeftPercent <= 25 && (
<>
{" — "}
<Text color="red">
{Math.round(contextLeftPercent)}% context left send
"/compact" to condense context
</Text>
</>
)}
</Text>
)}
</Box>
</Box>
);
@@ -417,12 +882,42 @@ export default function TerminalChatInput({
function TerminalChatInputThinking({
onInterrupt,
active,
thinkingSeconds,
}: {
onInterrupt: () => void;
active: boolean;
thinkingSeconds: number;
}) {
const [dots, setDots] = useState("");
const [awaitingConfirm, setAwaitingConfirm] = useState(false);
const [dots, setDots] = useState("");
// Animate ellipsis
useInterval(() => {
setDots((prev) => (prev.length < 3 ? prev + "." : ""));
}, 500);
// Spinner frames with embedded seconds
const ballFrames = [
"( ● )",
"( ● )",
"( ● )",
"( ● )",
"( ●)",
"( ● )",
"( ● )",
"( ● )",
"( ● )",
"(● )",
];
const [frame, setFrame] = useState(0);
useInterval(() => {
setFrame((idx) => (idx + 1) % ballFrames.length);
}, 80);
// Keep the elapsedseconds text fixed while the ball animation moves.
const frameTemplate = ballFrames[frame] ?? ballFrames[0];
const frameWithSeconds = `${frameTemplate} ${thinkingSeconds}s`;
// ---------------------------------------------------------------------
// Raw stdin listener to catch the case where the terminal delivers two
@@ -453,11 +948,9 @@ function TerminalChatInputThinking({
const str = Buffer.isBuffer(data) ? data.toString("utf8") : data;
if (str === "\x1b\x1b") {
// Treat as the first Escape press prompt the user for confirmation.
if (isLoggingEnabled()) {
log(
"raw stdin: received collapsed ESC ESC starting confirmation timer",
);
}
log(
"raw stdin: received collapsed ESC ESC starting confirmation timer",
);
setAwaitingConfirm(true);
setTimeout(() => setAwaitingConfirm(false), 1500);
}
@@ -470,10 +963,7 @@ function TerminalChatInputThinking({
};
}, [stdin, awaitingConfirm, onInterrupt, active, setRawMode]);
// Cycle the "Thinking…" animation dots.
useInterval(() => {
setDots((prev) => (prev.length < 3 ? prev + "." : ""));
}, 500);
// No local timer: the parent component supplies the elapsed time via props.
// Listen for the escape key to allow the user to interrupt the current
// operation. We require two presses within a short window (1.5s) to avoid
@@ -485,15 +975,11 @@ function TerminalChatInputThinking({
}
if (awaitingConfirm) {
if (isLoggingEnabled()) {
log("useInput: second ESC detected triggering onInterrupt()");
}
log("useInput: second ESC detected triggering onInterrupt()");
onInterrupt();
setAwaitingConfirm(false);
} else {
if (isLoggingEnabled()) {
log("useInput: first ESC detected waiting for confirmation");
}
log("useInput: first ESC detected waiting for confirmation");
setAwaitingConfirm(true);
setTimeout(() => setAwaitingConfirm(false), 1500);
}
@@ -502,17 +988,30 @@ function TerminalChatInputThinking({
);
return (
<Box flexDirection="column" gap={1}>
<Box gap={2}>
<Spinner type="ball" />
<Text>Thinking{dots}</Text>
</Box>
{awaitingConfirm && (
<Text dimColor>
Press <Text bold>Esc</Text> again to interrupt and enter a new
instruction
<Box width="100%" flexDirection="column" gap={1}>
<Box
flexDirection="row"
width="100%"
justifyContent="space-between"
paddingRight={1}
>
<Box gap={2}>
<Text>{frameWithSeconds}</Text>
<Text>
Thinking
{dots}
</Text>
</Box>
<Text>
<Text dimColor>press</Text> <Text bold>Esc</Text>{" "}
{awaitingConfirm ? (
<Text bold>again</Text>
) : (
<Text dimColor>twice</Text>
)}{" "}
<Text dimColor>to interrupt</Text>
</Text>
)}
</Box>
</Box>
);
}

View File

@@ -1,558 +0,0 @@
import type { MultilineTextEditorHandle } from "./multiline-editor";
import type { ReviewDecision } from "../../utils/agent/review.js";
import type { HistoryEntry } from "../../utils/storage/command-history.js";
import type {
ResponseInputItem,
ResponseItem,
} from "openai/resources/responses/responses.mjs";
import MultilineTextEditor from "./multiline-editor";
import { TerminalChatCommandReview } from "./terminal-chat-command-review.js";
import { log, isLoggingEnabled } from "../../utils/agent/log.js";
import { loadConfig } from "../../utils/config.js";
import { createInputItem } from "../../utils/input-utils.js";
import { setSessionId } from "../../utils/session.js";
import {
loadCommandHistory,
addToHistory,
} from "../../utils/storage/command-history.js";
import { clearTerminal, onExit } from "../../utils/terminal.js";
import Spinner from "../vendor/ink-spinner.js";
import { Box, Text, useApp, useInput, useStdin } from "ink";
import { fileURLToPath } from "node:url";
import React, { useCallback, useState, Fragment, useEffect } from "react";
import { useInterval } from "use-interval";
const suggestions = [
"explain this codebase to me",
"fix any build errors",
"are there any bugs in my code?",
];
const typeHelpText = `ctrl+c to exit | "/clear" to reset context | "/help" for commands | ↑↓ to recall history | ctrl+x to open external editor | enter to send`;
// Enable verbose logging for the historynavigation logic when the
// DEBUG_TCI environment variable is truthy. The traces help while debugging
// unittest failures but remain silent in production.
const DEBUG_HIST =
process.env["DEBUG_TCI"] === "1" || process.env["DEBUG_TCI"] === "true";
const thinkingTexts = ["Thinking"]; /* [
"Consulting the rubber duck",
"Maximizing paperclips",
"Reticulating splines",
"Immanentizing the Eschaton",
"Thinking",
"Thinking about thinking",
"Spinning in circles",
"Counting dust specks",
"Updating priors",
"Feeding the utility monster",
"Taking off",
"Wireheading",
"Counting to infinity",
"Staring into the Basilisk",
"Running acausal tariff negotiations",
"Searching the library of babel",
"Multiplying matrices",
"Solving the halting problem",
"Counting grains of sand",
"Simulating a simulation",
"Asking the oracle",
"Detangling qubits",
"Reading tea leaves",
"Pondering universal love and transcendent joy",
"Feeling the AGI",
"Shaving the yak",
"Escaping local minima",
"Pruning the search tree",
"Descending the gradient",
"Painting the bikeshed",
"Securing funding",
]; */
export default function TerminalChatInput({
isNew: _isNew,
loading,
submitInput,
confirmationPrompt,
explanation,
submitConfirmation,
setLastResponseId,
setItems,
contextLeftPercent,
openOverlay,
openModelOverlay,
openApprovalOverlay,
openHelpOverlay,
interruptAgent,
active,
}: {
isNew: boolean;
loading: boolean;
submitInput: (input: Array<ResponseInputItem>) => void;
confirmationPrompt: React.ReactNode | null;
explanation?: string;
submitConfirmation: (
decision: ReviewDecision,
customDenyMessage?: string,
) => void;
setLastResponseId: (lastResponseId: string) => void;
setItems: React.Dispatch<React.SetStateAction<Array<ResponseItem>>>;
contextLeftPercent: number;
openOverlay: () => void;
openModelOverlay: () => void;
openApprovalOverlay: () => void;
openHelpOverlay: () => void;
interruptAgent: () => void;
active: boolean;
}): React.ReactElement {
const app = useApp();
const [selectedSuggestion, setSelectedSuggestion] = useState<number>(0);
const [input, setInput] = useState("");
const [history, setHistory] = useState<Array<HistoryEntry>>([]);
const [historyIndex, setHistoryIndex] = useState<number | null>(null);
const [draftInput, setDraftInput] = useState<string>("");
// Multiline text editor is now the default input mode. We keep an
// incremental `editorKey` so that we can forceremount the component and
// thus reset its internal buffer after each successful submit.
const [editorKey, setEditorKey] = useState(0);
// Load command history on component mount
useEffect(() => {
async function loadHistory() {
const historyEntries = await loadCommandHistory();
setHistory(historyEntries);
}
loadHistory();
}, []);
// Imperative handle from the multiline editor so we can query caret position
const editorRef = React.useRef<MultilineTextEditorHandle | null>(null);
// Track the caret row across keystrokes so we can tell whether the cursor
// was *already* on the first/last line before the current key event. This
// lets us distinguish between a normal vertical navigation (e.g. moving
// from row 1 → row 0 inside a multiline draft) and an attempt to navigate
// the chat history (pressing ↑ again while already at row 0).
const prevCursorRow = React.useRef<number | null>(null);
useInput(
(_input, _key) => {
if (!confirmationPrompt && !loading) {
if (_key.upArrow) {
if (DEBUG_HIST) {
// eslint-disable-next-line no-console
console.log("[TCI] upArrow", {
historyIndex,
input,
cursorRow: editorRef.current?.getRow?.(),
});
}
// Only recall history when the caret was *already* on the very first
// row *before* this keypress. That means the user pressed ↑ while
// the cursor sat at the top mirroring how shells like Bash/zsh
// enter history navigation. When the caret starts on a lower line
// the first ↑ should merely move it up one row; only a subsequent
// press (when we are *still* at row 0) should trigger the recall.
const cursorRow = editorRef.current?.getRow?.() ?? 0;
const wasAtFirstRow = (prevCursorRow.current ?? cursorRow) === 0;
if (history.length > 0 && cursorRow === 0 && wasAtFirstRow) {
if (historyIndex == null) {
const currentDraft = editorRef.current?.getText?.() ?? input;
setDraftInput(currentDraft);
if (DEBUG_HIST) {
// eslint-disable-next-line no-console
console.log("[TCI] store draft", JSON.stringify(currentDraft));
}
}
let newIndex: number;
if (historyIndex == null) {
newIndex = history.length - 1;
} else {
newIndex = Math.max(0, historyIndex - 1);
}
setHistoryIndex(newIndex);
setInput(history[newIndex]?.command ?? "");
// Remount the editor so it picks up the new initialText.
setEditorKey((k) => k + 1);
return; // we handled the key
}
// Otherwise let the event propagate so the editor moves the caret.
}
if (_key.downArrow) {
if (DEBUG_HIST) {
// eslint-disable-next-line no-console
console.log("[TCI] downArrow", { historyIndex, draftInput, input });
}
// Only move forward in history when we're already *in* history mode
// AND the caret sits on the last line of the buffer (so ↓ within a
// multiline draft simply moves the caret down).
if (historyIndex != null && editorRef.current?.isCursorAtLastRow()) {
const newIndex = historyIndex + 1;
if (newIndex >= history.length) {
setHistoryIndex(null);
setInput(draftInput);
setEditorKey((k) => k + 1);
} else {
setHistoryIndex(newIndex);
setInput(history[newIndex]?.command ?? "");
setEditorKey((k) => k + 1);
}
return; // handled
}
// Otherwise let it propagate.
}
}
if (input.trim() === "") {
if (_key.tab) {
setSelectedSuggestion(
(s) => (s + (_key.shift ? -1 : 1)) % (suggestions.length + 1),
);
} else if (selectedSuggestion && _key.return) {
const suggestion = suggestions[selectedSuggestion - 1] || "";
setInput("");
setSelectedSuggestion(0);
submitInput([
{
role: "user",
content: [{ type: "input_text", text: suggestion }],
type: "message",
},
]);
}
} else if (_input === "\u0003" || (_input === "c" && _key.ctrl)) {
setTimeout(() => {
app.exit();
onExit();
process.exit(0);
}, 60);
}
// Update the cached cursor position *after* we've potentially handled
// the key so that the next event has the correct "previous" reference.
prevCursorRow.current = editorRef.current?.getRow?.() ?? null;
},
{ isActive: active },
);
const onSubmit = useCallback(
async (value: string) => {
const inputValue = value.trim();
if (!inputValue) {
return;
}
if (inputValue === "/history") {
setInput("");
openOverlay();
return;
}
if (inputValue === "/help") {
setInput("");
openHelpOverlay();
return;
}
if (inputValue.startsWith("/model")) {
setInput("");
openModelOverlay();
return;
}
if (inputValue.startsWith("/approval")) {
setInput("");
openApprovalOverlay();
return;
}
if (inputValue === "q" || inputValue === ":q" || inputValue === "exit") {
setInput("");
// wait one 60ms frame
setTimeout(() => {
app.exit();
onExit();
process.exit(0);
}, 60);
return;
} else if (inputValue === "/clear" || inputValue === "clear") {
setInput("");
setSessionId("");
setLastResponseId("");
clearTerminal();
// Emit a system message to confirm the clear action. We *append*
// it so Ink's <Static> treats it as new output and actually renders it.
setItems((prev) => [
...prev,
{
id: `clear-${Date.now()}`,
type: "message",
role: "system",
content: [{ type: "input_text", text: "Context cleared" }],
},
]);
return;
} else if (inputValue === "/clearhistory") {
setInput("");
// Import clearCommandHistory function to avoid circular dependencies
// Using dynamic import to lazy-load the function
import("../../utils/storage/command-history.js").then(
async ({ clearCommandHistory }) => {
await clearCommandHistory();
setHistory([]);
// Emit a system message to confirm the history clear action
setItems((prev) => [
...prev,
{
id: `clearhistory-${Date.now()}`,
type: "message",
role: "system",
content: [
{ type: "input_text", text: "Command history cleared" },
],
},
]);
},
);
return;
}
const images: Array<string> = [];
const text = inputValue
.replace(/!\[[^\]]*?\]\(([^)]+)\)/g, (_m, p1: string) => {
images.push(p1.startsWith("file://") ? fileURLToPath(p1) : p1);
return "";
})
.trim();
const inputItem = await createInputItem(text, images);
submitInput([inputItem]);
// Get config for history persistence
const config = loadConfig();
// Add to history and update state
const updatedHistory = await addToHistory(value, history, {
maxSize: config.history?.maxSize ?? 1000,
saveHistory: config.history?.saveHistory ?? true,
sensitivePatterns: config.history?.sensitivePatterns ?? [],
});
setHistory(updatedHistory);
setHistoryIndex(null);
setDraftInput("");
setSelectedSuggestion(0);
setInput("");
},
[
setInput,
submitInput,
setLastResponseId,
setItems,
app,
setHistory,
setHistoryIndex,
openOverlay,
openApprovalOverlay,
openModelOverlay,
openHelpOverlay,
history, // Add history to the dependency array
],
);
if (confirmationPrompt) {
return (
<TerminalChatCommandReview
confirmationPrompt={confirmationPrompt}
onReviewCommand={submitConfirmation}
explanation={explanation}
/>
);
}
return (
<Box flexDirection="column">
{loading ? (
<Box borderStyle="round">
<TerminalChatInputThinking
onInterrupt={interruptAgent}
active={active}
/>
</Box>
) : (
<>
<Box borderStyle="round">
<MultilineTextEditor
ref={editorRef}
onChange={(txt: string) => setInput(txt)}
key={editorKey}
initialText={input}
height={8}
focus={active}
onSubmit={(txt) => {
onSubmit(txt);
setEditorKey((k) => k + 1);
setInput("");
setHistoryIndex(null);
setDraftInput("");
}}
/>
</Box>
<Box paddingX={2} marginBottom={1}>
<Text dimColor>
{!input ? (
<>
try:{" "}
{suggestions.map((m, key) => (
<Fragment key={key}>
{key !== 0 ? " | " : ""}
<Text
backgroundColor={
key + 1 === selectedSuggestion ? "blackBright" : ""
}
>
{m}
</Text>
</Fragment>
))}
</>
) : (
<>
{typeHelpText}
{contextLeftPercent < 25 && (
<>
{" — "}
<Text color="red">
{Math.round(contextLeftPercent)}% context left
</Text>
</>
)}
</>
)}
</Text>
</Box>
</>
)}
</Box>
);
}
function TerminalChatInputThinking({
onInterrupt,
active,
}: {
onInterrupt: () => void;
active: boolean;
}) {
const [dots, setDots] = useState("");
const [awaitingConfirm, setAwaitingConfirm] = useState(false);
const [thinkingText] = useState(
() => thinkingTexts[Math.floor(Math.random() * thinkingTexts.length)],
);
// ---------------------------------------------------------------------
// Raw stdin listener to catch the case where the terminal delivers two
// consecutive ESC bytes ("\x1B\x1B") in a *single* chunk. Ink's `useInput`
// collapses that sequence into one key event, so the regular twostep
// handler above never sees the second press. By inspecting the raw data
// we can identify this special case and trigger the interrupt while still
// requiring a double press for the normal singlebyte ESC events.
// ---------------------------------------------------------------------
const { stdin, setRawMode } = useStdin();
React.useEffect(() => {
if (!active) {
return;
}
// Ensure raw mode already enabled by Ink when the component has focus,
// but called defensively in case that assumption ever changes.
setRawMode?.(true);
const onData = (data: Buffer | string) => {
if (awaitingConfirm) {
return; // already awaiting a second explicit press
}
// Handle both Buffer and string forms.
const str = Buffer.isBuffer(data) ? data.toString("utf8") : data;
if (str === "\x1b\x1b") {
// Treat as the first Escape press prompt the user for confirmation.
if (isLoggingEnabled()) {
log(
"raw stdin: received collapsed ESC ESC starting confirmation timer",
);
}
setAwaitingConfirm(true);
setTimeout(() => setAwaitingConfirm(false), 1500);
}
};
stdin?.on("data", onData);
return () => {
stdin?.off("data", onData);
};
}, [stdin, awaitingConfirm, onInterrupt, active, setRawMode]);
useInterval(() => {
setDots((prev) => (prev.length < 3 ? prev + "." : ""));
}, 500);
useInput(
(_input, key) => {
if (!key.escape) {
return;
}
if (awaitingConfirm) {
if (isLoggingEnabled()) {
log("useInput: second ESC detected triggering onInterrupt()");
}
onInterrupt();
setAwaitingConfirm(false);
} else {
if (isLoggingEnabled()) {
log("useInput: first ESC detected waiting for confirmation");
}
setAwaitingConfirm(true);
setTimeout(() => setAwaitingConfirm(false), 1500);
}
},
{ isActive: active },
);
return (
<Box flexDirection="column" gap={1}>
<Box gap={2}>
<Spinner type="ball" />
<Text>
{thinkingText}
{dots}
</Text>
</Box>
{awaitingConfirm && (
<Text dimColor>
Press <Text bold>Esc</Text> again to interrupt and enter a new
instruction
</Text>
)}
</Box>
);
}

View File

@@ -1,5 +1,6 @@
import type { TerminalChatSession } from "../../utils/session.js";
import type { ResponseItem } from "openai/resources/responses/responses";
import type { FileOpenerScheme } from "src/utils/config.js";
import TerminalChatResponseItem from "./terminal-chat-response-item";
import { Box, Text } from "ink";
@@ -8,9 +9,11 @@ import React from "react";
export default function TerminalChatPastRollout({
session,
items,
fileOpener,
}: {
session: TerminalChatSession;
items: Array<ResponseItem>;
fileOpener: FileOpenerScheme | undefined;
}): React.ReactElement {
const { version, id: sessionId, model } = session;
return (
@@ -51,9 +54,13 @@ export default function TerminalChatPastRollout({
{React.useMemo(
() =>
items.map((item, key) => (
<TerminalChatResponseItem key={key} item={item} />
<TerminalChatResponseItem
key={key}
item={item}
fileOpener={fileOpener}
/>
)),
[items],
[items, fileOpener],
)}
</Box>
</Box>

View File

@@ -1,3 +1,4 @@
import type { OverlayModeType } from "./terminal-chat";
import type { TerminalRendererOptions } from "marked-terminal";
import type {
ResponseFunctionToolCallItem,
@@ -7,27 +8,46 @@ import type {
ResponseOutputMessage,
ResponseReasoningItem,
} from "openai/resources/responses/responses";
import type { FileOpenerScheme } from "src/utils/config";
import { useTerminalSize } from "../../hooks/use-terminal-size";
import { collapseXmlBlocks } from "../../utils/file-tag-utils";
import { parseToolCall, parseToolCallOutput } from "../../utils/parsers";
import chalk, { type ForegroundColorName } from "chalk";
import { Box, Text } from "ink";
import { parse, setOptions } from "marked";
import TerminalRenderer from "marked-terminal";
import React, { useMemo } from "react";
import path from "path";
import React, { useEffect, useMemo } from "react";
import { formatCommandForDisplay } from "src/format-command.js";
import supportsHyperlinks from "supports-hyperlinks";
export default function TerminalChatResponseItem({
item,
fullStdout = false,
setOverlayMode,
fileOpener,
}: {
item: ResponseItem;
fullStdout?: boolean;
setOverlayMode?: React.Dispatch<React.SetStateAction<OverlayModeType>>;
fileOpener: FileOpenerScheme | undefined;
}): React.ReactElement {
switch (item.type) {
case "message":
return <TerminalChatResponseMessage message={item} />;
return (
<TerminalChatResponseMessage
setOverlayMode={setOverlayMode}
message={item}
fileOpener={fileOpener}
/>
);
// @ts-expect-error new item types aren't in SDK yet
case "local_shell_call":
case "function_call":
return <TerminalChatResponseToolCall message={item} />;
// @ts-expect-error new item types aren't in SDK yet
case "local_shell_call_output":
case "function_call_output":
return (
<TerminalChatResponseToolCallOutput
@@ -41,7 +61,9 @@ export default function TerminalChatResponseItem({
// @ts-expect-error `reasoning` is not in the responses API yet
if (item.type === "reasoning") {
return <TerminalChatResponseReasoning message={item} />;
return (
<TerminalChatResponseReasoning message={item} fileOpener={fileOpener} />
);
}
return <TerminalChatResponseGenericMessage message={item} />;
@@ -69,8 +91,10 @@ export default function TerminalChatResponseItem({
export function TerminalChatResponseReasoning({
message,
fileOpener,
}: {
message: ResponseReasoningItem & { duration_ms?: number };
fileOpener: FileOpenerScheme | undefined;
}): React.ReactElement | null {
// Only render when there is a reasoning summary
if (!message.summary || message.summary.length === 0) {
@@ -83,7 +107,7 @@ export function TerminalChatResponseReasoning({
return (
<Box key={key} flexDirection="column">
{s.headline && <Text bold>{s.headline}</Text>}
<Markdown>{s.text}</Markdown>
<Markdown fileOpener={fileOpener}>{s.text}</Markdown>
</Box>
);
})}
@@ -98,29 +122,45 @@ const colorsByRole: Record<string, ForegroundColorName> = {
function TerminalChatResponseMessage({
message,
setOverlayMode,
fileOpener,
}: {
message: ResponseInputMessageItem | ResponseOutputMessage;
setOverlayMode?: React.Dispatch<React.SetStateAction<OverlayModeType>>;
fileOpener: FileOpenerScheme | undefined;
}) {
// auto switch to model mode if the system message contains "has been deprecated"
useEffect(() => {
if (message.role === "system") {
const systemMessage = message.content.find(
(c) => c.type === "input_text",
)?.text;
if (systemMessage?.includes("model_not_found")) {
setOverlayMode?.("model");
}
}
}, [message, setOverlayMode]);
return (
<Box flexDirection="column">
<Text bold color={colorsByRole[message.role] || "gray"}>
{message.role === "assistant" ? "codex" : message.role}
</Text>
<Markdown>
<Markdown fileOpener={fileOpener}>
{message.content
.map(
(c) =>
c.type === "output_text"
? c.text
: c.type === "refusal"
? c.refusal
: c.type === "input_text"
? c.text
: c.type === "input_image"
? "<Image>"
: c.type === "input_file"
? c.filename
: "", // unknown content type
? c.refusal
: c.type === "input_text"
? collapseXmlBlocks(c.text)
: c.type === "input_image"
? "<Image>"
: c.type === "input_file"
? c.filename
: "", // unknown content type
)
.join(" ")}
</Markdown>
@@ -131,16 +171,28 @@ function TerminalChatResponseMessage({
function TerminalChatResponseToolCall({
message,
}: {
message: ResponseFunctionToolCallItem;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
message: ResponseFunctionToolCallItem | any;
}) {
const details = parseToolCall(message);
let workdir: string | undefined;
let cmdReadableText: string | undefined;
if (message.type === "function_call") {
const details = parseToolCall(message);
workdir = details?.workdir;
cmdReadableText = details?.cmdReadableText;
} else if (message.type === "local_shell_call") {
const action = message.action;
workdir = action.working_directory;
cmdReadableText = formatCommandForDisplay(action.command);
}
return (
<Box flexDirection="column" gap={1}>
<Text color="magentaBright" bold>
command
{workdir ? <Text dimColor>{` (${workdir})`}</Text> : ""}
</Text>
<Text>
<Text dimColor>$</Text> {details?.cmdReadableText}
<Text dimColor>$</Text> {cmdReadableText}
</Text>
</Box>
);
@@ -150,7 +202,8 @@ function TerminalChatResponseToolCallOutput({
message,
fullStdout,
}: {
message: ResponseFunctionToolCallOutputItem;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
message: ResponseFunctionToolCallOutputItem | any;
fullStdout: boolean;
}) {
const { output, metadata } = parseToolCallOutput(message.output);
@@ -217,26 +270,91 @@ export function TerminalChatResponseGenericMessage({
export type MarkdownProps = TerminalRendererOptions & {
children: string;
fileOpener: FileOpenerScheme | undefined;
/** Base path for resolving relative file citation paths. */
cwd?: string;
};
export function Markdown({
children,
fileOpener,
cwd,
...options
}: MarkdownProps): React.ReactElement {
const size = useTerminalSize();
const rendered = React.useMemo(() => {
const linkifiedMarkdown = rewriteFileCitations(children, fileOpener, cwd);
// Configure marked for this specific render
setOptions({
// @ts-expect-error missing parser, space props
renderer: new TerminalRenderer({ ...options, width: size.columns }),
});
const parsed = parse(children, { async: false }).trim();
const parsed = parse(linkifiedMarkdown, { async: false }).trim();
// Remove the truncation logic
return parsed;
// eslint-disable-next-line react-hooks/exhaustive-deps -- options is an object of primitives
}, [children, size.columns, size.rows]);
}, [
children,
size.columns,
size.rows,
fileOpener,
supportsHyperlinks.stdout,
chalk.level,
]);
return <Text>{rendered}</Text>;
}
/** Regex to match citations for source files (hence the `F:` prefix). */
const citationRegex = new RegExp(
[
// Opening marker
"【",
// Capture group 1: file ID or name (anything except '†')
"F:([^†]+)",
// Field separator
"†",
// Capture group 2: start line (digits)
"L(\\d+)",
// Non-capturing group for optional end line
"(?:",
// Capture group 3: end line (digits or '?')
"-L(\\d+|\\?)",
// End of optional group (may not be present)
")?",
// Closing marker
"】",
].join(""),
"g", // Global flag
);
function rewriteFileCitations(
markdown: string,
fileOpener: FileOpenerScheme | undefined,
cwd: string = process.cwd(),
): string {
citationRegex.lastIndex = 0;
return markdown.replace(citationRegex, (_match, file, start, _end) => {
const absPath = path.resolve(cwd, file);
if (!fileOpener) {
return `[${file}](${absPath})`;
}
const uri = `${fileOpener}://file${absPath}:${start}`;
const label = `${file}:${start}`;
// In practice, sometimes multiple citations for the same file, but with a
// different line number, are shown sequentially, so we:
// - include the line number in the label to disambiguate them
// - add a space after the link to make it easier to read
return `[${label}](${uri}) `;
});
}

View File

@@ -1,113 +0,0 @@
import type { ResponseItem } from "openai/resources/responses/responses.mjs";
import { approximateTokensUsed } from "../../utils/approximate-tokens-used.js";
/**
* Typeguard that narrows a {@link ResponseItem} to one that represents a
* userauthored message. The OpenAI SDK represents both input *and* output
* messages with a discriminated union where:
* • `type` is the string literal "message" and
* • `role` is one of "user" | "assistant" | "system" | "developer".
*
* For the purposes of deduplication we only care about *user* messages so we
* detect those here in a single, reusable helper.
*/
function isUserMessage(
item: ResponseItem,
): item is ResponseItem & { type: "message"; role: "user"; content: unknown } {
return item.type === "message" && (item as { role?: string }).role === "user";
}
/**
* Returns the maximum context length (in tokens) for a given model.
* These numbers are besteffort guesses and provide a basis for UI percentages.
*/
export function maxTokensForModel(model: string): number {
const lower = model.toLowerCase();
if (lower.includes("32k")) {
return 32000;
}
if (lower.includes("16k")) {
return 16000;
}
if (lower.includes("8k")) {
return 8000;
}
if (lower.includes("4k")) {
return 4000;
}
// Default to 128k for newer longcontext models
return 128000;
}
/**
* Calculates the percentage of tokens remaining in context for a model.
*/
export function calculateContextPercentRemaining(
items: Array<ResponseItem>,
model: string,
): number {
const used = approximateTokensUsed(items);
const max = maxTokensForModel(model);
const remaining = Math.max(0, max - used);
return (remaining / max) * 100;
}
/**
* Deduplicate the stream of {@link ResponseItem}s before they are persisted in
* component state.
*
* Historically we used the (optional) {@code id} field returned by the
* OpenAI streaming API as the primary key: the first occurrence of any given
* {@code id} “won” and subsequent duplicates were dropped. In practice this
* proved brittle because locallygenerated user messages dont include an
* {@code id}. The result was that if a user quickly pressed <Enter> twice the
* exact same message would appear twice in the transcript.
*
* The new rules are therefore:
* 1. If a {@link ResponseItem} has an {@code id} keep only the *first*
* occurrence of that {@code id} (this retains the previous behaviour for
* assistant / tool messages).
* 2. Additionally, collapse *consecutive* user messages with identical
* content. Two messages are considered identical when their serialized
* {@code content} array matches exactly. We purposefully restrict this
* to **adjacent** duplicates so that legitimately repeated questions at
* a later point in the conversation are still shown.
*/
export function uniqueById(items: Array<ResponseItem>): Array<ResponseItem> {
const seenIds = new Set<string>();
const deduped: Array<ResponseItem> = [];
for (const item of items) {
// ──────────────────────────────────────────────────────────────────
// Rule #1 deduplicate by id when present
// ──────────────────────────────────────────────────────────────────
if (typeof item.id === "string" && item.id.length > 0) {
if (seenIds.has(item.id)) {
continue; // skip duplicates
}
seenIds.add(item.id);
}
// ──────────────────────────────────────────────────────────────────
// Rule #2 collapse consecutive identical user messages
// ──────────────────────────────────────────────────────────────────
if (isUserMessage(item) && deduped.length > 0) {
const prev = deduped[deduped.length - 1]!;
if (
isUserMessage(prev) &&
// Note: the `content` field is an array of message parts. Performing
// a deep compare is overkill here; serialising to JSON is sufficient
// (and fast for the tiny payloads involved).
JSON.stringify(prev.content) === JSON.stringify(item.content)
) {
continue; // skip duplicate user message
}
}
deduped.push(item);
}
return deduped;
}

View File

@@ -1,3 +1,4 @@
import type { AppRollout } from "../../app.js";
import type { ApplyPatchCommand, ApprovalPolicy } from "../../approvals.js";
import type { CommandConfirmation } from "../../utils/agent/agent-loop.js";
import type { AppConfig } from "../../utils/config.js";
@@ -5,35 +6,51 @@ import type { ColorName } from "chalk";
import type { ResponseItem } from "openai/resources/responses/responses.mjs";
import TerminalChatInput from "./terminal-chat-input.js";
import { TerminalChatToolCallCommand } from "./terminal-chat-tool-call-item.js";
import {
calculateContextPercentRemaining,
uniqueById,
} from "./terminal-chat-utils.js";
import TerminalChatPastRollout from "./terminal-chat-past-rollout.js";
import { TerminalChatToolCallCommand } from "./terminal-chat-tool-call-command.js";
import TerminalMessageHistory from "./terminal-message-history.js";
import { formatCommandForDisplay } from "../../format-command.js";
import { useConfirmation } from "../../hooks/use-confirmation.js";
import { useTerminalSize } from "../../hooks/use-terminal-size.js";
import { AgentLoop } from "../../utils/agent/agent-loop.js";
import { isLoggingEnabled, log } from "../../utils/agent/log.js";
import { ReviewDecision } from "../../utils/agent/review.js";
import { generateCompactSummary } from "../../utils/compact-summary.js";
import { OPENAI_BASE_URL } from "../../utils/config.js";
import { saveConfig } from "../../utils/config.js";
import { extractAppliedPatches as _extractAppliedPatches } from "../../utils/extract-applied-patches.js";
import { getGitDiff } from "../../utils/get-diff.js";
import { createInputItem } from "../../utils/input-utils.js";
import { getAvailableModels } from "../../utils/model-utils.js";
import { CLI_VERSION } from "../../utils/session.js";
import { log } from "../../utils/logger/log.js";
import {
getAvailableModels,
calculateContextPercentRemaining,
uniqueById,
} from "../../utils/model-utils.js";
import { createOpenAIClient } from "../../utils/openai-client.js";
import { shortCwd } from "../../utils/short-path.js";
import { saveRollout } from "../../utils/storage/save-rollout.js";
import { CLI_VERSION } from "../../version.js";
import ApprovalModeOverlay from "../approval-mode-overlay.js";
import DiffOverlay from "../diff-overlay.js";
import HelpOverlay from "../help-overlay.js";
import HistoryOverlay from "../history-overlay.js";
import ModelOverlay from "../model-overlay.js";
import SessionsOverlay from "../sessions-overlay.js";
import chalk from "chalk";
import fs from "fs/promises";
import { Box, Text } from "ink";
import { exec } from "node:child_process";
import OpenAI from "openai";
import { spawn } from "node:child_process";
import React, { useEffect, useMemo, useRef, useState } from "react";
import { inspect } from "util";
export type OverlayModeType =
| "none"
| "history"
| "sessions"
| "model"
| "approval"
| "help"
| "diff";
type Props = {
config: AppConfig;
prompt?: string;
@@ -54,18 +71,19 @@ const colorsByPolicy: Record<ApprovalPolicy, ColorName | undefined> = {
*
* @param command The command to explain
* @param model The model to use for generating the explanation
* @param flexMode Whether to use the flex-mode service tier
* @param config The configuration object
* @returns A human-readable explanation of what the command does
*/
async function generateCommandExplanation(
command: Array<string>,
model: string,
flexMode: boolean,
config: AppConfig,
): Promise<string> {
try {
// Create a temporary OpenAI client
const oai = new OpenAI({
apiKey: process.env["OPENAI_API_KEY"],
baseURL: OPENAI_BASE_URL,
});
const oai = createOpenAIClient(config);
// Format the command for display
const commandForDisplay = formatCommandForDisplay(command);
@@ -73,6 +91,7 @@ async function generateCommandExplanation(
// Create a prompt that asks for an explanation with a more detailed system prompt
const response = await oai.chat.completions.create({
model,
...(flexMode ? { service_tier: "flex" } : {}),
messages: [
{
role: "system",
@@ -93,11 +112,8 @@ async function generateCommandExplanation(
} catch (error) {
log(`Error generating command explanation: ${error}`);
// Improved error handling with more specific error information
let errorMessage = "Unable to generate explanation due to an error.";
if (error instanceof Error) {
// Include specific error message for better debugging
errorMessage = `Unable to generate explanation: ${error.message}`;
// If it's an API error, check for more specific information
@@ -128,21 +144,26 @@ export default function TerminalChat({
additionalWritableRoots,
fullStdout,
}: Props): React.ReactElement {
// Desktop notification setting
const notify = config.notify;
const notify = Boolean(config.notify);
const [model, setModel] = useState<string>(config.model);
const [provider, setProvider] = useState<string>(config.provider || "openai");
const [lastResponseId, setLastResponseId] = useState<string | null>(null);
const [items, setItems] = useState<Array<ResponseItem>>([]);
const [loading, setLoading] = useState<boolean>(false);
// Allow switching approval modes at runtime via an overlay.
const [approvalPolicy, setApprovalPolicy] = useState<ApprovalPolicy>(
initialApprovalPolicy,
);
const [thinkingSeconds, setThinkingSeconds] = useState(0);
const handleCompact = async () => {
setLoading(true);
try {
const summary = await generateCompactSummary(items, model);
const summary = await generateCompactSummary(
items,
model,
Boolean(config.flexMode),
config,
);
setItems([
{
id: `compact-${Date.now()}`,
@@ -167,15 +188,22 @@ export default function TerminalChat({
setLoading(false);
}
};
const {
requestConfirmation,
confirmationPrompt,
explanation,
submitConfirmation,
} = useConfirmation();
const [overlayMode, setOverlayMode] = useState<
"none" | "history" | "model" | "approval" | "help"
>("none");
const [overlayMode, setOverlayMode] = useState<OverlayModeType>("none");
const [viewRollout, setViewRollout] = useState<AppRollout | null>(null);
// Store the diff text when opening the diff overlay so the view isnt
// recomputed on every rerender while it is open.
// diffText is passed down to the DiffOverlay component. The setter is
// currently unused but retained for potential future updates. Prefix with
// an underscore so eslint ignores the unused variable.
const [diffText, _setDiffText] = useState<string>("");
const [initialPrompt, setInitialPrompt] = useState(_initialPrompt);
const [initialImagePaths, setInitialImagePaths] =
@@ -191,39 +219,44 @@ export default function TerminalChat({
// ────────────────────────────────────────────────────────────────
// DEBUG: log every render w/ key bits of state
// ────────────────────────────────────────────────────────────────
if (isLoggingEnabled()) {
log(
`render agent? ${Boolean(agentRef.current)} loading=${loading} items=${
items.length
}`,
);
}
log(
`render - agent? ${Boolean(agentRef.current)} loading=${loading} items=${
items.length
}`,
);
useEffect(() => {
if (isLoggingEnabled()) {
log("creating NEW AgentLoop");
log(
`model=${model} instructions=${Boolean(
config.instructions,
)} approvalPolicy=${approvalPolicy}`,
);
// Skip recreating the agent if awaiting a decision on a pending confirmation.
if (confirmationPrompt != null) {
log("skip AgentLoop recreation due to pending confirmationPrompt");
return;
}
// Tear down any existing loop before creating a new one
log("creating NEW AgentLoop");
log(
`model=${model} provider=${provider} instructions=${Boolean(
config.instructions,
)} approvalPolicy=${approvalPolicy}`,
);
// Tear down any existing loop before creating a new one.
agentRef.current?.terminate();
const sessionId = crypto.randomUUID();
agentRef.current = new AgentLoop({
model,
provider,
config,
instructions: config.instructions,
approvalPolicy,
disableResponseStorage: config.disableResponseStorage,
additionalWritableRoots,
onLastResponseId: setLastResponseId,
onItem: (item) => {
log(`onItem: ${JSON.stringify(item)}`);
setItems((prev) => {
const updated = uniqueById([...prev, item as ResponseItem]);
saveRollout(updated);
saveRollout(sessionId, updated);
return updated;
});
},
@@ -240,15 +273,18 @@ export default function TerminalChat({
<TerminalChatToolCallCommand commandForDisplay={commandForDisplay} />,
);
// If the user wants an explanation, generate one and ask again
// If the user wants an explanation, generate one and ask again.
if (review === ReviewDecision.EXPLAIN) {
log(`Generating explanation for command: ${commandForDisplay}`);
// Generate an explanation using the same model
const explanation = await generateCommandExplanation(command, model);
const explanation = await generateCommandExplanation(
command,
model,
Boolean(config.flexMode),
config,
);
log(`Generated explanation: ${explanation}`);
// Ask for confirmation again, but with the explanation
// Ask for confirmation again, but with the explanation.
const confirmResult = await requestConfirmation(
<TerminalChatToolCallCommand
commandForDisplay={commandForDisplay}
@@ -256,11 +292,11 @@ export default function TerminalChat({
/>,
);
// Update the decision based on the second confirmation
// Update the decision based on the second confirmation.
review = confirmResult.decision;
customDenyMessage = confirmResult.customDenyMessage;
// Return the final decision with the explanation
// Return the final decision with the explanation.
return { review, customDenyMessage, applyPatch, explanation };
}
@@ -268,30 +304,23 @@ export default function TerminalChat({
},
});
// force a render so JSX below can "see" the freshly created agent
// Force a render so JSX below can "see" the freshly created agent.
forceUpdate();
if (isLoggingEnabled()) {
log(`AgentLoop created: ${inspect(agentRef.current, { depth: 1 })}`);
}
log(`AgentLoop created: ${inspect(agentRef.current, { depth: 1 })}`);
return () => {
if (isLoggingEnabled()) {
log("terminating AgentLoop");
}
log("terminating AgentLoop");
agentRef.current?.terminate();
agentRef.current = undefined;
forceUpdate(); // rerender after teardown too
};
}, [
model,
config,
approvalPolicy,
requestConfirmation,
additionalWritableRoots,
]);
// We intentionally omit 'approvalPolicy' and 'confirmationPrompt' from the deps
// so switching modes or showing confirmation dialogs doesnt tear down the loop.
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [model, provider, config, requestConfirmation, additionalWritableRoots]);
// whenever loading starts/stops, reset or start a timer — but pause the
// Whenever loading starts/stops, reset or start a timer — but pause the
// timer while a confirmation overlay is displayed so we don't trigger a
// rerender every second during apply_patch reviews.
useEffect(() => {
@@ -316,14 +345,15 @@ export default function TerminalChat({
};
}, [loading, confirmationPrompt]);
// Notify desktop with a preview when an assistant response arrives
// Notify desktop with a preview when an assistant response arrives.
const prevLoadingRef = useRef<boolean>(false);
useEffect(() => {
// Only notify when notifications are enabled
// Only notify when notifications are enabled.
if (!notify) {
prevLoadingRef.current = loading;
return;
}
if (
prevLoadingRef.current &&
!loading &&
@@ -350,21 +380,20 @@ export default function TerminalChat({
const safePreview = preview.replace(/"/g, '\\"');
const title = "Codex CLI";
const cwd = PWD;
exec(
`osascript -e 'display notification "${safePreview}" with title "${title}" subtitle "${cwd}" sound name "Ping"'`,
);
spawn("osascript", [
"-e",
`display notification "${safePreview}" with title "${title}" subtitle "${cwd}" sound name "Ping"`,
]);
}
}
}
prevLoadingRef.current = loading;
}, [notify, loading, confirmationPrompt, items, PWD]);
// Let's also track whenever the ref becomes available
// Let's also track whenever the ref becomes available.
const agent = agentRef.current;
useEffect(() => {
if (isLoggingEnabled()) {
log(`agentRef.current is now ${Boolean(agent)}`);
}
log(`agentRef.current is now ${Boolean(agent)}`);
}, [agent]);
// ---------------------------------------------------------------------
@@ -384,7 +413,7 @@ export default function TerminalChat({
const inputItems = [
await createInputItem(initialPrompt || "", initialImagePaths || []),
];
// Clear them to prevent subsequent runs
// Clear them to prevent subsequent runs.
setInitialPrompt("");
setInitialImagePaths([]);
agent?.run(inputItems);
@@ -397,7 +426,7 @@ export default function TerminalChat({
// ────────────────────────────────────────────────────────────────
useEffect(() => {
(async () => {
const available = await getAvailableModels();
const available = await getAvailableModels(provider);
if (model && available.length > 0 && !available.includes(model)) {
setItems((prev) => [
...prev,
@@ -408,7 +437,7 @@ export default function TerminalChat({
content: [
{
type: "input_text",
text: `Warning: model "${model}" is not in the list of available models returned by OpenAI.`,
text: `Warning: model "${model}" is not in the list of available models for provider "${provider}".`,
},
],
},
@@ -419,7 +448,7 @@ export default function TerminalChat({
// eslint-disable-next-line react-hooks/exhaustive-deps
}, []);
// Just render every item in order, no grouping/collapse
// Just render every item in order, no grouping/collapse.
const lastMessageBatch = items.map((item) => ({ item }));
const groupCounts: Record<string, number> = {};
const userMsgCount = items.filter(
@@ -431,11 +460,22 @@ export default function TerminalChat({
[items, model],
);
if (viewRollout) {
return (
<TerminalChatPastRollout
fileOpener={config.fileOpener}
session={viewRollout.session}
items={viewRollout.items}
/>
);
}
return (
<Box flexDirection="column">
<Box flexDirection="column">
{agent ? (
<TerminalMessageHistory
setOverlayMode={setOverlayMode}
batch={lastMessageBatch}
groupCounts={groupCounts}
items={items}
@@ -449,18 +489,21 @@ export default function TerminalChat({
version: CLI_VERSION,
PWD,
model,
provider,
approvalPolicy,
colorsByPolicy,
agent,
initialImagePaths,
flexModeEnabled: Boolean(config.flexMode),
}}
fileOpener={config.fileOpener}
/>
) : (
<Box>
<Text color="gray">Initializing agent</Text>
</Box>
)}
{agent && (
{overlayMode === "none" && agent && (
<TerminalChatInput
loading={loading}
setItems={setItems}
@@ -482,17 +525,36 @@ export default function TerminalChat({
openModelOverlay={() => setOverlayMode("model")}
openApprovalOverlay={() => setOverlayMode("approval")}
openHelpOverlay={() => setOverlayMode("help")}
openSessionsOverlay={() => setOverlayMode("sessions")}
openDiffOverlay={() => {
const { isGitRepo, diff } = getGitDiff();
let text: string;
if (isGitRepo) {
text = diff;
} else {
text = "`/diff` — _not inside a git repository_";
}
setItems((prev) => [
...prev,
{
id: `diff-${Date.now()}`,
type: "message",
role: "system",
content: [{ type: "input_text", text }],
},
]);
// Ensure no overlay is shown.
setOverlayMode("none");
}}
onCompact={handleCompact}
active={overlayMode === "none"}
interruptAgent={() => {
if (!agent) {
return;
}
if (isLoggingEnabled()) {
log(
"TerminalChat: interruptAgent invoked calling agent.cancel()",
);
}
log(
"TerminalChat: interruptAgent invoked calling agent.cancel()",
);
agent.cancel();
setLoading(false);
@@ -516,32 +578,74 @@ export default function TerminalChat({
agent.run(inputs, lastResponseId || "");
return {};
}}
items={items}
thinkingSeconds={thinkingSeconds}
/>
)}
{overlayMode === "history" && (
<HistoryOverlay items={items} onExit={() => setOverlayMode("none")} />
)}
{overlayMode === "sessions" && (
<SessionsOverlay
onView={async (p) => {
try {
const txt = await fs.readFile(p, "utf-8");
const data = JSON.parse(txt) as AppRollout;
setViewRollout(data);
setOverlayMode("none");
} catch {
setOverlayMode("none");
}
}}
onResume={(p) => {
setOverlayMode("none");
setInitialPrompt(`Resume this session: ${p}`);
}}
onExit={() => setOverlayMode("none")}
/>
)}
{overlayMode === "model" && (
<ModelOverlay
currentModel={model}
providers={config.providers}
currentProvider={provider}
hasLastResponse={Boolean(lastResponseId)}
onSelect={(newModel) => {
if (isLoggingEnabled()) {
log(
"TerminalChat: interruptAgent invoked calling agent.cancel()",
);
if (!agent) {
log("TerminalChat: agent is not ready yet");
}
onSelect={(allModels, newModel) => {
log(
"TerminalChat: interruptAgent invoked calling agent.cancel()",
);
if (!agent) {
log("TerminalChat: agent is not ready yet");
}
agent?.cancel();
setLoading(false);
if (!allModels?.includes(newModel)) {
// eslint-disable-next-line no-console
console.error(
chalk.bold.red(
`Model "${chalk.yellow(
newModel,
)}" is not available for provider "${chalk.yellow(
provider,
)}".`,
),
);
return;
}
setModel(newModel);
setLastResponseId((prev) =>
prev && newModel !== model ? null : prev,
);
// Save model to config
saveConfig({
...config,
model: newModel,
provider: provider,
});
setItems((prev) => [
...prev,
{
@@ -559,6 +663,51 @@ export default function TerminalChat({
setOverlayMode("none");
}}
onSelectProvider={(newProvider) => {
log(
"TerminalChat: interruptAgent invoked calling agent.cancel()",
);
if (!agent) {
log("TerminalChat: agent is not ready yet");
}
agent?.cancel();
setLoading(false);
// Select default model for the new provider.
const defaultModel = model;
// Save provider to config.
const updatedConfig = {
...config,
provider: newProvider,
model: defaultModel,
};
saveConfig(updatedConfig);
setProvider(newProvider);
setModel(defaultModel);
setLastResponseId((prev) =>
prev && newProvider !== provider ? null : prev,
);
setItems((prev) => [
...prev,
{
id: `switch-provider-${Date.now()}`,
type: "message",
role: "system",
content: [
{
type: "input_text",
text: `Switched provider to ${newProvider} with model ${defaultModel}`,
},
],
},
]);
// Don't close the overlay so user can select a model for the new provider
// setOverlayMode("none");
}}
onExit={() => setOverlayMode("none")}
/>
)}
@@ -567,12 +716,19 @@ export default function TerminalChat({
<ApprovalModeOverlay
currentMode={approvalPolicy}
onSelect={(newMode) => {
agent?.cancel();
setLoading(false);
// Update approval policy without cancelling an in-progress session.
if (newMode === approvalPolicy) {
return;
}
setApprovalPolicy(newMode as ApprovalPolicy);
if (agentRef.current) {
(
agentRef.current as unknown as {
approvalPolicy: ApprovalPolicy;
}
).approvalPolicy = newMode as ApprovalPolicy;
}
setItems((prev) => [
...prev,
{
@@ -597,6 +753,13 @@ export default function TerminalChat({
{overlayMode === "help" && (
<HelpOverlay onExit={() => setOverlayMode("none")} />
)}
{overlayMode === "diff" && (
<DiffOverlay
diffText={diffText}
onExit={() => setOverlayMode("none")}
/>
)}
</Box>
</Box>
);

View File

@@ -9,10 +9,12 @@ export interface TerminalHeaderProps {
version: string;
PWD: string;
model: string;
provider?: string;
approvalPolicy: string;
colorsByPolicy: Record<string, string | undefined>;
agent?: AgentLoop;
initialImagePaths?: Array<string>;
flexModeEnabled?: boolean;
}
const TerminalHeader: React.FC<TerminalHeaderProps> = ({
@@ -20,18 +22,21 @@ const TerminalHeader: React.FC<TerminalHeaderProps> = ({
version,
PWD,
model,
provider = "openai",
approvalPolicy,
colorsByPolicy,
agent,
initialImagePaths,
flexModeEnabled = false,
}) => {
return (
<>
{terminalRows < 10 ? (
// Compact header for small terminal windows
<Text>
Codex v{version} {PWD} {model} {" "}
Codex v{version} - {PWD} - {model} ({provider}) -{" "}
<Text color={colorsByPolicy[approvalPolicy]}>{approvalPolicy}</Text>
{flexModeEnabled ? " - flex-mode" : ""}
</Text>
) : (
<>
@@ -62,12 +67,22 @@ const TerminalHeader: React.FC<TerminalHeaderProps> = ({
<Text dimColor>
<Text color="blueBright"></Text> model: <Text bold>{model}</Text>
</Text>
<Text dimColor>
<Text color="blueBright"></Text> provider:{" "}
<Text bold>{provider}</Text>
</Text>
<Text dimColor>
<Text color="blueBright"></Text> approval:{" "}
<Text bold color={colorsByPolicy[approvalPolicy]} dimColor>
<Text bold color={colorsByPolicy[approvalPolicy]}>
{approvalPolicy}
</Text>
</Text>
{flexModeEnabled && (
<Text dimColor>
<Text color="blueBright"></Text> flex-mode:{" "}
<Text bold>enabled</Text>
</Text>
)}
{initialImagePaths?.map((img, idx) => (
<Text key={img ?? idx} color="gray">
<Text color="blueBright"></Text> image:{" "}

View File

@@ -1,17 +1,19 @@
import type { OverlayModeType } from "./terminal-chat.js";
import type { TerminalHeaderProps } from "./terminal-header.js";
import type { GroupedResponseItem } from "./use-message-grouping.js";
import type { ResponseItem } from "openai/resources/responses/responses.mjs";
import type { FileOpenerScheme } from "src/utils/config.js";
import TerminalChatResponseItem from "./terminal-chat-response-item.js";
import TerminalHeader from "./terminal-header.js";
import { Box, Static, Text } from "ink";
import { Box, Static } from "ink";
import React, { useMemo } from "react";
// A batch entry can either be a standalone response item or a grouped set of
// items (e.g. autoapproved toolcall batches) that should be rendered
// together.
type BatchEntry = { item?: ResponseItem; group?: GroupedResponseItem };
type MessageHistoryProps = {
type TerminalMessageHistoryProps = {
batch: Array<BatchEntry>;
groupCounts: Record<string, number>;
items: Array<ResponseItem>;
@@ -21,25 +23,27 @@ type MessageHistoryProps = {
thinkingSeconds: number;
headerProps: TerminalHeaderProps;
fullStdout: boolean;
setOverlayMode: React.Dispatch<React.SetStateAction<OverlayModeType>>;
fileOpener: FileOpenerScheme | undefined;
};
const MessageHistory: React.FC<MessageHistoryProps> = ({
const TerminalMessageHistory: React.FC<TerminalMessageHistoryProps> = ({
batch,
headerProps,
loading,
thinkingSeconds,
// `loading` and `thinkingSeconds` handled by input component now.
loading: _loading,
thinkingSeconds: _thinkingSeconds,
fullStdout,
setOverlayMode,
fileOpener,
}) => {
// Flatten batch entries to response items.
const messages = useMemo(() => batch.map(({ item }) => item!), [batch]);
return (
<Box flexDirection="column">
{loading && (
<Box marginTop={1}>
<Text color="yellow">{`thinking for ${thinkingSeconds}s`}</Text>
</Box>
)}
{/* The dedicated thinking indicator in the input area now displays the
elapsed time, so we no longer render a separate counter here. */}
<Static items={["header", ...messages]}>
{(item, index) => {
if (item === "header") {
@@ -58,15 +62,25 @@ const MessageHistory: React.FC<MessageHistoryProps> = ({
key={`${message.id}-${index}`}
flexDirection="column"
marginLeft={
message.type === "message" && message.role === "user" ? 0 : 4
message.type === "message" &&
(message.role === "user" || message.role === "assistant")
? 0
: 4
}
marginTop={
message.type === "message" && message.role === "user" ? 0 : 1
}
marginBottom={
message.type === "message" && message.role === "assistant"
? 1
: 0
}
>
<TerminalChatResponseItem
item={message}
fullStdout={fullStdout}
setOverlayMode={setOverlayMode}
fileOpener={fileOpener}
/>
</Box>
);
@@ -76,4 +90,4 @@ const MessageHistory: React.FC<MessageHistoryProps> = ({
);
};
export default React.memo(MessageHistory);
export default React.memo(TerminalMessageHistory);

View File

@@ -0,0 +1,93 @@
import { Box, Text, useInput } from "ink";
import React, { useState } from "react";
/**
* Simple scrollable view for displaying a diff.
* The component is intentionally lightweight and mirrors the UX of
* HistoryOverlay: Up/Down or j/k to scroll, PgUp/PgDn for paging and Esc to
* close. The caller is responsible for computing the diff text.
*/
export default function DiffOverlay({
diffText,
onExit,
}: {
diffText: string;
onExit: () => void;
}): JSX.Element {
const lines = diffText.length > 0 ? diffText.split("\n") : ["(no changes)"];
const [cursor, setCursor] = useState(0);
// Determine how many rows we can display similar to HistoryOverlay.
const rows = process.stdout.rows || 24;
const headerRows = 2;
const footerRows = 1;
const maxVisible = Math.max(4, rows - headerRows - footerRows);
useInput((input, key) => {
if (key.escape || input === "q") {
onExit();
return;
}
if (key.downArrow || input === "j") {
setCursor((c) => Math.min(lines.length - 1, c + 1));
} else if (key.upArrow || input === "k") {
setCursor((c) => Math.max(0, c - 1));
} else if (key.pageDown) {
setCursor((c) => Math.min(lines.length - 1, c + maxVisible));
} else if (key.pageUp) {
setCursor((c) => Math.max(0, c - maxVisible));
} else if (input === "g") {
setCursor(0);
} else if (input === "G") {
setCursor(lines.length - 1);
}
});
const firstVisible = Math.min(
Math.max(0, cursor - Math.floor(maxVisible / 2)),
Math.max(0, lines.length - maxVisible),
);
const visible = lines.slice(firstVisible, firstVisible + maxVisible);
// Very small helper to colorize diff lines in a basic way.
function renderLine(line: string, idx: number): JSX.Element {
let color: "green" | "red" | "cyan" | undefined = undefined;
if (line.startsWith("+")) {
color = "green";
} else if (line.startsWith("-")) {
color = "red";
} else if (line.startsWith("@@") || line.startsWith("diff --git")) {
color = "cyan";
}
return (
<Text key={idx} color={color} wrap="truncate-end">
{line === "" ? " " : line}
</Text>
);
}
return (
<Box
flexDirection="column"
borderStyle="round"
borderColor="gray"
width={Math.min(120, process.stdout.columns || 120)}
>
<Box paddingX={1}>
<Text bold>Working tree diff ({lines.length} lines)</Text>
</Box>
<Box flexDirection="column" paddingX={1}>
{visible.map((line, idx) => {
return renderLine(line, firstVisible + idx);
})}
</Box>
<Box paddingX={1}>
<Text dimColor>esc Close Scroll PgUp/PgDn g/G First/Last</Text>
</Box>
</Box>
);
}

View File

@@ -52,6 +52,13 @@ export default function HelpOverlay({
<Text>
<Text color="cyan">/clearhistory</Text> clear command history
</Text>
<Text>
<Text color="cyan">/bug</Text> generate a prefilled GitHub issue URL
with session log
</Text>
<Text>
<Text color="cyan">/diff</Text> view working tree git diff
</Text>
<Text>
<Text color="cyan">/compact</Text> condense context into a summary
</Text>

View File

@@ -14,7 +14,10 @@ export default function HistoryOverlay({ items, onExit }: Props): JSX.Element {
const [mode, setMode] = useState<Mode>("commands");
const [cursor, setCursor] = useState(0);
const { commands, files } = useMemo(() => buildLists(items), [items]);
const { commands, files } = useMemo(
() => formatHistoryForDisplay(items),
[items],
);
const list = mode === "commands" ? commands : files;
@@ -95,7 +98,7 @@ export default function HistoryOverlay({ items, onExit }: Props): JSX.Element {
);
}
function buildLists(items: Array<ResponseItem>): {
function formatHistoryForDisplay(items: Array<ResponseItem>): {
commands: Array<string>;
files: Array<string>;
} {
@@ -103,33 +106,9 @@ function buildLists(items: Array<ResponseItem>): {
const filesSet = new Set<string>();
for (const item of items) {
if (
item.type === "message" &&
(item as unknown as { role?: string }).role === "user"
) {
// TODO: We're ignoring images/files here.
const parts =
(item as unknown as { content?: Array<unknown> }).content ?? [];
const texts: Array<string> = [];
if (Array.isArray(parts)) {
for (const part of parts) {
if (part && typeof part === "object" && "text" in part) {
const t = (part as unknown as { text?: string }).text;
if (typeof t === "string" && t.length > 0) {
texts.push(t);
}
}
}
}
if (texts.length > 0) {
const fullPrompt = texts.join(" ");
// Truncate very long prompts so the history view stays legible.
const truncated =
fullPrompt.length > 120 ? `${fullPrompt.slice(0, 117)}` : fullPrompt;
commands.push(`> ${truncated}`);
}
const userPrompt = processUserMessage(item);
if (userPrompt) {
commands.push(userPrompt);
continue;
}
@@ -169,35 +148,11 @@ function buildLists(items: Array<ResponseItem>): {
const cmdArray: Array<string> | undefined = Array.isArray(argsObj?.["cmd"])
? (argsObj!["cmd"] as Array<string>)
: Array.isArray(argsObj?.["command"])
? (argsObj!["command"] as Array<string>)
: undefined;
? (argsObj!["command"] as Array<string>)
: undefined;
if (cmdArray && cmdArray.length > 0) {
commands.push(cmdArray.join(" "));
// Heuristic for file paths in command args
for (const part of cmdArray) {
if (!part.startsWith("-") && part.includes("/")) {
filesSet.add(part);
}
}
// Specialcase apply_patch so we can extract the list of modified files
if (cmdArray[0] === "apply_patch" || cmdArray.includes("apply_patch")) {
const patchTextMaybe = cmdArray.find((s) =>
s.includes("*** Begin Patch"),
);
if (typeof patchTextMaybe === "string") {
const lines = patchTextMaybe.split("\n");
for (const line of lines) {
const m = line.match(/^[-+]{3} [ab]\/(.+)$/);
if (m && m[1]) {
filesSet.add(m[1]);
}
}
}
}
commands.push(processCommandArray(cmdArray, filesSet));
continue; // We processed this as a command; no need to treat as generic tool call.
}
@@ -205,33 +160,96 @@ function buildLists(items: Array<ResponseItem>): {
// short argument representation to give users an idea of what
// happened.
if (typeof toolName === "string" && toolName.length > 0) {
let summary = toolName;
if (argsJson && typeof argsJson === "object") {
// Extract a few common argument keys to make the summary more useful
// without being overly verbose.
const interestingKeys = [
"path",
"file",
"filepath",
"filename",
"pattern",
];
for (const key of interestingKeys) {
const val = (argsJson as Record<string, unknown>)[key];
if (typeof val === "string") {
summary += ` ${val}`;
if (val.includes("/")) {
filesSet.add(val);
}
break;
}
}
}
commands.push(summary);
commands.push(processNonExecTool(toolName, argsJson, filesSet));
}
}
return { commands, files: Array.from(filesSet) };
}
function processUserMessage(item: ResponseItem): string | null {
if (
item.type === "message" &&
(item as unknown as { role?: string }).role === "user"
) {
// TODO: We're ignoring images/files here.
const parts =
(item as unknown as { content?: Array<unknown> }).content ?? [];
const texts: Array<string> = [];
if (Array.isArray(parts)) {
for (const part of parts) {
if (part && typeof part === "object" && "text" in part) {
const t = (part as unknown as { text?: string }).text;
if (typeof t === "string" && t.length > 0) {
texts.push(t);
}
}
}
}
if (texts.length > 0) {
const fullPrompt = texts.join(" ");
// Truncate very long prompts so the history view stays legible.
return fullPrompt.length > 120
? `> ${fullPrompt.slice(0, 117)}`
: `> ${fullPrompt}`;
}
}
return null;
}
function processCommandArray(
cmdArray: Array<string>,
filesSet: Set<string>,
): string {
const cmd = cmdArray.join(" ");
// Heuristic for file paths in command args
for (const part of cmdArray) {
if (!part.startsWith("-") && part.includes("/")) {
filesSet.add(part);
}
}
// Specialcase apply_patch so we can extract the list of modified files
if (cmdArray[0] === "apply_patch" || cmdArray.includes("apply_patch")) {
const patchTextMaybe = cmdArray.find((s) => s.includes("*** Begin Patch"));
if (typeof patchTextMaybe === "string") {
const lines = patchTextMaybe.split("\n");
for (const line of lines) {
const m = line.match(/^[-+]{3} [ab]\/(.+)$/);
if (m && m[1]) {
filesSet.add(m[1]);
}
}
}
}
return cmd;
}
function processNonExecTool(
toolName: string,
argsJson: unknown,
filesSet: Set<string>,
): string {
let summary = toolName;
if (argsJson && typeof argsJson === "object") {
// Extract a few common argument keys to make the summary more useful
// without being overly verbose.
const interestingKeys = ["path", "file", "filepath", "filename", "pattern"];
for (const key of interestingKeys) {
const val = (argsJson as Record<string, unknown>)[key];
if (typeof val === "string") {
summary += ` ${val}`;
if (val.includes("/")) {
filesSet.add(val);
}
break;
}
}
}
return summary;
}

View File

@@ -1,7 +1,7 @@
import TypeaheadOverlay from "./typeahead-overlay.js";
import {
getAvailableModels,
RECOMMENDED_MODELS,
RECOMMENDED_MODELS as _RECOMMENDED_MODELS,
} from "../utils/model-utils.js";
import { Box, Text, useInput } from "ink";
import React, { useEffect, useState } from "react";
@@ -16,39 +16,53 @@ import React, { useEffect, useState } from "react";
*/
type Props = {
currentModel: string;
currentProvider?: string;
hasLastResponse: boolean;
onSelect: (model: string) => void;
providers?: Record<string, { name: string; baseURL: string; envKey: string }>;
onSelect: (allModels: Array<string>, model: string) => void;
onSelectProvider?: (provider: string) => void;
onExit: () => void;
};
export default function ModelOverlay({
currentModel,
providers = {},
currentProvider = "openai",
hasLastResponse,
onSelect,
onSelectProvider,
onExit,
}: Props): JSX.Element {
const [items, setItems] = useState<Array<{ label: string; value: string }>>(
[],
);
const [providerItems, _setProviderItems] = useState<
Array<{ label: string; value: string }>
>(Object.values(providers).map((p) => ({ label: p.name, value: p.name })));
const [mode, setMode] = useState<"model" | "provider">("model");
const [isLoading, setIsLoading] = useState<boolean>(true);
// This effect will run when the provider changes to update the model list
useEffect(() => {
setIsLoading(true);
(async () => {
const models = await getAvailableModels();
// Split the list into recommended and “other” models.
const recommended = RECOMMENDED_MODELS.filter((m) => models.includes(m));
const others = models.filter((m) => !recommended.includes(m));
const ordered = [...recommended, ...others.sort()];
setItems(
ordered.map((m) => ({
label: recommended.includes(m) ? `${m}` : m,
value: m,
})),
);
try {
const models = await getAvailableModels(currentProvider);
// Convert the models to the format needed by TypeaheadOverlay
setItems(
models.map((m) => ({
label: m,
value: m,
})),
);
} catch (error) {
// Silently handle errors - remove console.error
// console.error("Error loading models:", error);
} finally {
setIsLoading(false);
}
})();
}, []);
}, [currentProvider]);
// ---------------------------------------------------------------------------
// If the conversation already contains a response we cannot change the model
@@ -58,10 +72,14 @@ export default function ModelOverlay({
// available action is to dismiss the overlay (Esc or Enter).
// ---------------------------------------------------------------------------
// Always register input handling so hooks are called consistently.
// Register input handling for switching between model and provider selection
useInput((_input, key) => {
if (hasLastResponse && (key.escape || key.return)) {
onExit();
} else if (!hasLastResponse) {
if (key.tab) {
setMode(mode === "model" ? "provider" : "model");
}
}
});
@@ -91,17 +109,56 @@ export default function ModelOverlay({
);
}
if (mode === "provider") {
return (
<TypeaheadOverlay
title="Select provider"
description={
<Box flexDirection="column">
<Text>
Current provider:{" "}
<Text color="greenBright">{currentProvider}</Text>
</Text>
<Text dimColor>press tab to switch to model selection</Text>
</Box>
}
initialItems={providerItems}
currentValue={currentProvider}
onSelect={(provider) => {
if (onSelectProvider) {
onSelectProvider(provider);
// Immediately switch to model selection so user can pick a model for the new provider
setMode("model");
}
}}
onExit={onExit}
/>
);
}
return (
<TypeaheadOverlay
title="Switch model"
title="Select model"
description={
<Text>
Current model: <Text color="greenBright">{currentModel}</Text>
</Text>
<Box flexDirection="column">
<Text>
Current model: <Text color="greenBright">{currentModel}</Text>
</Text>
<Text>
Current provider: <Text color="greenBright">{currentProvider}</Text>
</Text>
{isLoading && <Text color="yellow">Loading models...</Text>}
<Text dimColor>press tab to switch to provider selection</Text>
</Box>
}
initialItems={items}
currentValue={currentModel}
onSelect={onSelect}
onSelect={(selectedModel) =>
onSelect(
items?.map((m) => m.value),
selectedModel,
)
}
onExit={onExit}
/>
);

View File

@@ -1,5 +1,5 @@
import Indicator, { type Props as IndicatorProps } from "./Indicator.js";
import ItemComponent, { type Props as ItemProps } from "./Item.js";
import Indicator, { type Props as IndicatorProps } from "./indicator.js";
import ItemComponent, { type Props as ItemProps } from "./item.js";
import isEqual from "fast-deep-equal";
import { Box, useInput } from "ink";
import React, {

Some files were not shown because too many files have changed in this diff Show More