Compare commits

...

324 Commits

Author SHA1 Message Date
Ahmed Ibrahim
9f63b77fb2 tests 2025-10-01 17:52:13 -07:00
Ahmed Ibrahim
7750d859ef tests 2025-10-01 17:49:56 -07:00
Ahmed Ibrahim
cd70f68240 tests 2025-10-01 17:49:34 -07:00
Ahmed Ibrahim
0c3e584af6 plan is on by default 2025-10-01 17:30:49 -07:00
pakrym-oai
e899ae7d8a Include request ID in the error message (#4572)
To help with issue debugging
<img width="1414" height="253" alt="image"
src="https://github.com/user-attachments/assets/254732df-44ac-4252-997a-6c5e0927355b"
/>
2025-10-01 15:36:04 -07:00
iceweasel-oai
6f97ec4990 canonicalize display of Agents.md paths on Windows. (#4577)
Canonicalize path on Windows to 
- remove unattractive path prefixes such as `\\?\`
- simplify it (`../AGENTS.md` vs
`C:\Users\iceweasel\code\coded\Agents.md`)
before: <img width="1110" height="45" alt="Screenshot 2025-10-01 123520"
src="https://github.com/user-attachments/assets/48920ae6-d89c-41b8-b4ea-df5c18fb5fad"
/>

after: 
<img width="585" height="46" alt="Screenshot 2025-10-01 123612"
src="https://github.com/user-attachments/assets/70a1761a-9d97-4836-b14c-670b6f13e608"
/>
2025-10-01 14:33:19 -07:00
Jeremy Rose
07c1db351a rework patch/exec approval UI (#4573)
| Scenario | Screenshot |
| ---------------------- |
----------------------------------------------------------------------------------------------------------------------------------------------------
|
| short patch | <img width="1096" height="533" alt="short patch"
src="https://github.com/user-attachments/assets/8a883429-0965-4c0b-9002-217b3759b557"
/> |
| short command | <img width="1096" height="533" alt="short command"
src="https://github.com/user-attachments/assets/901abde8-2494-4e86-b98a-7cabaf87ca9c"
/> |
| long patch | <img width="1129" height="892" alt="long patch"
src="https://github.com/user-attachments/assets/fa799a29-a0d6-48e6-b2ef-10302a7916d3"
/> |
| long command | <img width="1096" height="892" alt="long command"
src="https://github.com/user-attachments/assets/11ddf79b-98cb-4b60-ac22-49dfa7779343"
/> |
| viewing complete patch | <img width="1129" height="892" alt="viewing
complete patch"
src="https://github.com/user-attachments/assets/81666958-af94-420e-aa66-b60d0a42b9db"
/> |
2025-10-01 14:29:05 -07:00
pakrym-oai
31102af54b Add initial set of doc comments to the SDK (#4513)
Also perform minor code cleanup.
2025-10-01 13:12:59 -07:00
Thibault Sottiaux
5d78c1edd3 Revert "chore: prompt update to enforce good usage of apply_patch" (#4576)
Reverts openai/codex#3846
2025-10-01 20:11:36 +00:00
pakrym-oai
170c685882 Explicit node imports (#4567)
To help with compatibility
2025-10-01 12:39:04 -07:00
Eric Traut
609f75acec Fix hang on second oauth login attempt (#4568)
This PR fixes a bug that results in a hang in the oauth login flow if a
user logs in, then logs out, then logs in again without first closing
the browser window.

Root cause of problem: We use a local web server for the oauth flow, and
it's implemented using the `tiny_http` rust crate. During the first
login, a socket is created between the browser and the server. The
`tiny_http` library creates worker threads that persist for as long as
this socket remains open. Currently, there's no way to close the
connection on the server side — the library provides no API to do this.
The library also filters all "Connect: close" headers, which makes it
difficult to tell the client browser to close the connection. On the
second login attempt, the browser uses the existing connection rather
than creating a new one. Since that connection is associated with a
server instance that no longer exists, it is effectively ignored.

I considered switching from `tiny_http` to a different web server
library, but that would have been a big change with significant
regression risk. This PR includes a more surgical fix that works around
the limitation of `tiny_http` and sends a "Connect: close" header on the
last "success" page of the oauth flow.
2025-10-01 12:26:28 -07:00
Michael Bolin
eabe18714f fix: use number instead of bigint for the generated TS for RequestId (#4575)
Before this PR:

```typescript
export type RequestId = string | bigint;
```

After:

```typescript
export type RequestId = string | number;
```

`bigint` introduces headaches in TypeScript without providing any real
value.
2025-10-01 12:10:20 -07:00
easong-openai
ceaba36c7f fix ctr-n hint (#4566)
don't show or enable ctr-n to choose best of n while not in the composer
2025-10-01 18:42:04 +00:00
Michael Bolin
d94e8bad8b feat: add --emergency-version-override option to create_github_release script (#4556)
I just had to use this like so:

```
./codex-rs/scripts/create_github_release --publish-alpha --emergency-version-override 0.43.0-alpha.10
```

because the build for `0.43.0-alpha.9` failed:

https://github.com/openai/codex/actions/runs/18167317356
2025-10-01 11:40:04 -07:00
pakrym-oai
8a367ef6bf SDK: support working directory and skipGitRepoCheck options (#4563)
Make options not required, add support for working directory and
skipGitRepoCheck options on the turn
2025-10-01 11:26:49 -07:00
easong-openai
400a5a90bf Fall back to configured instruction files if AGENTS.md isn't available (#4544)
Allow users to configure an agents.md alternative to consume, but warn
the user it may degrade model performance.

Fixes #4376
2025-10-01 18:19:59 +00:00
Ahmed Ibrahim
2f370e946d Show context window usage while tasks run (#4536)
## Summary
- show the remaining context window percentage in `/status` alongside
existing token usage details
- replace the composer shortcut prompt with the context window
percentage (or an unavailable message) while a task is running
- update TUI snapshots to reflect the new context window line

## Testing
- cargo test -p codex-tui

------
https://chatgpt.com/codex/tasks/task_i_68dc6e7397ac8321909d7daff25a396c
2025-10-01 18:03:05 +00:00
Ahmed Ibrahim
751b3b50ac Show placeholder for commands with no output (#4509)
## Summary
- show a dim “(no output)” placeholder when an executed command produces
no stdout or stderr so empty runs are visible
- update TUI snapshots to include the new placeholder in history
renderings

## Testing
- cargo test -p codex-tui


------
https://chatgpt.com/codex/tasks/task_i_68dc056c1d5883218fe8d9929e9b1657
2025-10-01 10:42:30 -07:00
Ahmed Ibrahim
d78d0764aa Add Updated at time in resume picker (#4468)
<img width="639" height="281" alt="image"
src="https://github.com/user-attachments/assets/92b2ad2b-9e18-4485-9b8d-d7056eb98651"
/>
2025-10-01 10:40:43 -07:00
rakesh-oai
699c121606 Handle trailing backslash properly (#4559)
**Summary**

This PR fixes an issue in the device code login flow where trailing
slashes in the issuer URL could cause malformed URLs during codex token
exchange step


**Test**


Before the changes

`Error logging in with device code: device code exchange failed: error
decoding response body`

After the changes

`Successfully logged in`
2025-10-01 10:32:09 -07:00
iceweasel-oai
dde615f482 implement command safety for PowerShell commands (#4269)
Implement command safety for PowerShell commands on Windows

This change adds a new Windows-specific command-safety module under
`codex-rs/core/src/command_safety/windows_safe_commands.rs` to strictly
sanitise PowerShell invocations. Key points:

- Introduce `is_safe_command_windows()` to only allow explicitly
read-only PowerShell calls.
- Parse and split PowerShell invocations (including inline `-Command`
scripts and pipelines).
- Block unsafe switches (`-File`, `-EncodedCommand`, `-ExecutionPolicy`,
unknown flags, call operators, redirections, separators).
- Whitelist only read-only cmdlets (`Get-ChildItem`, `Get-Content`,
`Select-Object`, etc.), safe Git subcommands (`status`, `log`, `show`,
`diff`, `cat-file`), and ripgrep without unsafe options.
- Add comprehensive unit tests covering allowed and rejected command
patterns (nested calls, side effects, chaining, redirections).

This ensures Codex on Windows can safely execute discover-only
PowerShell workflows without risking destructive operations.
2025-10-01 09:56:48 -07:00
Michael Bolin
325fad1d92 fix: pnpm/action-setup@v4 should run before actions/setup-node@v5 (#4555)
`rust-release.yml` just failed:

https://github.com/openai/codex/actions/runs/18167317356/job/51714366768

The error is:

> Error: Unable to locate executable file: pnpm. Please verify either
the file path exists or the file can be found within a directory
specified by the PATH environment variable. Also check the file mode to
verify the file is executable.

We need to install `pnpm` first like we do in `ci.yml`:


f815157dd9/.github/workflows/ci.yml (L17-L25)
2025-10-01 09:04:14 -07:00
Michael Bolin
f815157dd9 chore: introduce publishing logic for @openai/codex-sdk (#4543)
There was a bit of copypasta I put up with when were publishing two
packages to npm, but now that it's three, I created some more scripts to
consolidate things.

With this change, I ran:

```shell
./scripts/stage_npm_packages.py --release-version 0.43.0-alpha.8 --package codex --package codex-responses-api-proxy --package codex-sdk
```

Indeed when it finished, I ended up with:

```shell
$ tree dist
dist
└── npm
    ├── codex-npm-0.43.0-alpha.8.tgz
    ├── codex-responses-api-proxy-npm-0.43.0-alpha.8.tgz
    └── codex-sdk-npm-0.43.0-alpha.8.tgz
$ tar tzvf dist/npm/codex-sdk-npm-0.43.0-alpha.8.tgz
-rwxr-xr-x  0 0      0    25476720 Oct 26  1985 package/vendor/aarch64-apple-darwin/codex/codex
-rwxr-xr-x  0 0      0    29871400 Oct 26  1985 package/vendor/aarch64-unknown-linux-musl/codex/codex
-rwxr-xr-x  0 0      0    28368096 Oct 26  1985 package/vendor/x86_64-apple-darwin/codex/codex
-rwxr-xr-x  0 0      0    36029472 Oct 26  1985 package/vendor/x86_64-unknown-linux-musl/codex/codex
-rw-r--r--  0 0      0       10926 Oct 26  1985 package/LICENSE
-rw-r--r--  0 0      0    30187520 Oct 26  1985 package/vendor/aarch64-pc-windows-msvc/codex/codex.exe
-rw-r--r--  0 0      0    35277824 Oct 26  1985 package/vendor/x86_64-pc-windows-msvc/codex/codex.exe
-rw-r--r--  0 0      0        4842 Oct 26  1985 package/dist/index.js
-rw-r--r--  0 0      0        1347 Oct 26  1985 package/package.json
-rw-r--r--  0 0      0        9867 Oct 26  1985 package/dist/index.js.map
-rw-r--r--  0 0      0          12 Oct 26  1985 package/README.md
-rw-r--r--  0 0      0        4287 Oct 26  1985 package/dist/index.d.ts
```
2025-10-01 08:29:59 -07:00
jif-oai
b8195a17e5 chore: sanbox extraction (#4286)
# Extract and Centralize Sandboxing
- Goal: Improve safety and clarity by centralizing sandbox planning and
execution.
  - Approach:
- Add planner (ExecPlan) and backend registry (Direct/Seatbelt/Linux)
with run_with_plan.
- Refactor codex.rs to plan-then-execute; handle failures/escalation via
the plan.
- Delegate apply_patch to the codex binary and run it with an empty env
for determinism.
2025-10-01 12:05:12 +01:00
rakesh-oai
349ef7edc6 Fix Callback URL for staging and prod environments (#4533)
# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
2025-10-01 02:57:37 +00:00
Michael Bolin
5881c0d6d4 fix: remove mcp-types from app server protocol (#4537)
We continue the separation between `codex app-server` and `codex
mcp-server`.

In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.

Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.

We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.

Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.
2025-10-01 02:16:26 +00:00
pakrym-oai
8dd771d217 Add executable detection and export Codex from the SDK (#4532)
Executable detection uses the same rules as the codex wrapper.
2025-09-30 18:06:16 -07:00
Michael Bolin
32853ecbc5 fix: use macros to ensure request/response symmetry (#4529)
Manually curating `protocol-ts/src/lib.rs` was error-prone, as expected.
I finally asked Codex to write some Rust macros so we can ensure that:

- For every variant of `ClientRequest` and `ServerRequest`, there is an
associated `params` and `response` type.
- All response types are included automatically in the output of `codex
generate-ts`.
2025-09-30 18:06:05 -07:00
pakrym-oai
7fc3edf8a7 Remove legacy codex exec --json format (#4525)
`codex exec --json` now maps to the behavior of `codex exec
--experimental-json` with new event and item shapes.

Thread events:
- thread.started
- turn.started
- turn.completed
- turn.failed
- item.started
- item.updated
- item.completed

Item types: 
- assistant_message
- reasoning
- command_execution
- file_change
- mcp_tool_call
- web_search
- todo_list
- error

Sample output:

<details>
`codex exec "list my assigned github issues"  --json | jq`

```
{
  "type": "thread.started",
  "thread_id": "01999ce5-f229-7661-8570-53312bd47ea3"
}
{
  "type": "turn.started"
}
{
  "type": "item.completed",
  "item": {
    "id": "item_0",
    "item_type": "reasoning",
    "text": "**Planning to list assigned GitHub issues**"
  }
}
{
  "type": "item.started",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "in_progress"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_2",
    "item_type": "reasoning",
    "text": "**Organizing final message structure**"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_3",
    "item_type": "assistant_message",
    "text": "**Assigned Issues**\n- openai/codex#3267 – “stream error: stream disconnected before completion…” (bug) – last update 2025-09-08\n- openai/codex#3257 – “You've hit your usage limit. Try again in 4 days 20 hours 9 minutes.” – last update 2025-09-23\n- openai/codex#3054 – “reqwest SSL panic (library has no ciphers)” (bug) – last update 2025-09-03\n- openai/codex#3051 – “thread 'main' panicked at linux-sandbox/src/linux_run_main.rs:53:5:” (bug) – last update 2025-09-10\n- openai/codex#3004 – “Auto-compact when approaching context limit” (enhancement) – last update 2025-09-26\n- openai/codex#2916 – “Feature request: Add OpenAI service tier support for cost optimization” – last update 2025-09-12\n- openai/codex#1581 – “stream error: stream disconnected before completion: stream closed before response.complete; retrying...” (bug) – last update 2025-09-17"
  }
}
{
  "type": "turn.completed",
  "usage": {
    "input_tokens": 34785,
    "cached_input_tokens": 12544,
    "output_tokens": 560
  }
}
```

</details>
2025-09-30 17:21:37 -07:00
Jeremy Rose
01e6503672 wrap markdown at render time (#4506)
This results in correctly indenting list items with long lines.

<img width="1006" height="251" alt="Screenshot 2025-09-30 at 10 00
48 AM"
src="https://github.com/user-attachments/assets/0a076cf6-ca3c-4efb-b3af-dc07617cdb6f"
/>
2025-09-30 23:13:55 +00:00
pakrym-oai
9c259737d3 Delete codex proto (#4520) 2025-09-30 22:33:28 +00:00
Michael Bolin
b8e1fe60c5 fix: enable process hardening in Codex CLI for release builds (#4521)
I don't believe there is any upside in making process hardening opt-in
for Codex CLI releases. If you want to tinker with Codex CLI, then build
from source (or run as `root`)?
2025-09-30 14:34:35 -07:00
Michael Bolin
ddfb7eb548 fix: clean up TypeScript exports (#4518)
Fixes:

- Removed overdeclaration of types that were unnecessary because they
were already included by induction.
- Reordered list of response types to match the enum order, making it
easier to identify what was missing.
- Added `ExecArbitraryCommandResponse` because it was missing.
- Leveraged `use codex_protocol::mcp_protocol::*;` to make the file more
readable.
- Removed crate dependency on `mcp-types` now that we have separate the
app server from the MCP server:
https://github.com/openai/codex/pull/4471

My next move is to come up with some scheme that ensures request types
always have a response type and that the response type is automatically
included with the output of `codex generate-ts`.
2025-09-30 14:08:43 -07:00
Michael Bolin
6910be3224 fix: ensure every variant of ClientRequest has a params field (#4512)
This ensures changes the generated TypeScript type for `ClientRequest`
so that instead of this:

```typescript
/**
 * Request from the client to the server.
 */
export type ClientRequest =
  | { method: "initialize"; id: RequestId; params: InitializeParams }
  | { method: "newConversation"; id: RequestId; params: NewConversationParams }
  // ...
  | { method: "getUserAgent"; id: RequestId }
  | { method: "userInfo"; id: RequestId }
  // ...
```

we have this:

```typescript
/**
 * Request from the client to the server.
 */
export type ClientRequest =
  | { method: "initialize"; id: RequestId; params: InitializeParams }
  | { method: "newConversation"; id: RequestId; params: NewConversationParams }
  // ...
  | { method: "getUserAgent"; id: RequestId; params: undefined }
  | { method: "userInfo"; id: RequestId; params: undefined }
  // ...
```

which makes TypeScript happier when it comes to destructuring instances
of `ClientRequest` because it does not complain about `params` not being
guaranteed to exist anymore.
2025-09-30 12:03:32 -07:00
pakrym-oai
a534356fe1 Wire up web search item (#4511)
Add handling for web search events.
2025-09-30 12:01:17 -07:00
pakrym-oai
c89b0e1235 [SDK] Test that a tread can be continued with extra params (#4508) 2025-09-30 17:22:14 +00:00
jif-oai
f6a152848a chore: prompt update to enforce good usage of apply_patch (#3846)
Update prompt to prevent codex to use Python script or fancy commands to
edit files.

## Testing:
3 scenarios have been considered:
1. Rename codex to meca_code. Proceed to the whole refactor file by
file. Don't ask for approval at each step
2. Add a description to every single function you can find in the repo
3. Rewrite codex.rs in a more idiomatic way. Make sure to touch ONLY
this file and that clippy does not complain at the end

Before this update, 22% (estimation as it's sometimes hard to find all
the creative way the model find to edit files) of the file editions
where made using something else than a raw `apply_patch`

After this update, not a single edition without `apply_patch` was found

[EDIT]
I managed to have a few `["bash", "-lc", "apply_path"]` when reaching <
10% context left
2025-09-30 10:18:59 -07:00
dedrisian-oai
3592ecb23c Named args for custom prompts (#4474)
Here's the logic:

1. If text is empty and selector is open:
- Enter on a prompt without args should autosubmit the prompt
- Enter on a prompt with numeric args should add `/prompts:name ` to the
text input
- Enter on a prompt with named args should add `/prompts:name ARG1=""
ARG2=""` to the text input
2. If text is not empty but no args are passed:
- For prompts with numeric args -> we allow it to submit (params are
optional)
- For prompts with named args -> we throw an error (all params should
have values)

<img width="454" height="246" alt="Screenshot 2025-09-23 at 2 23 21 PM"
src="https://github.com/user-attachments/assets/fd180a1b-7d17-42ec-b231-8da48828b811"
/>
2025-09-30 10:06:41 -07:00
pakrym-oai
516acc030b Support model and sandbox mode in the sdk (#4503) 2025-09-30 09:00:39 -07:00
easong-openai
5b038135de Add cloud tasks (#3197)
Adds a TUI for managing, applying, and creating cloud tasks
2025-09-30 10:10:33 +00:00
Michael Bolin
d9dbf48828 fix: separate codex mcp into codex mcp-server and codex app-server (#4471)
This is a very large PR with some non-backwards-compatible changes.

Historically, `codex mcp` (or `codex mcp serve`) started a JSON-RPC-ish
server that had two overlapping responsibilities:

- Running an MCP server, providing some basic tool calls.
- Running the app server used to power experiences such as the VS Code
extension.

This PR aims to separate these into distinct concepts:

- `codex mcp-server` for the MCP server
- `codex app-server` for the "application server"

Note `codex mcp` still exists because it already has its own subcommands
for MCP management (`list`, `add`, etc.)

The MCP logic continues to live in `codex-rs/mcp-server` whereas the
refactored app server logic is in the new `codex-rs/app-server` folder.
Note that most of the existing integration tests in
`codex-rs/mcp-server/tests/suite` were actually for the app server, so
all the tests have been moved with the exception of
`codex-rs/mcp-server/tests/suite/mod.rs`.

Because this is already a large diff, I tried not to change more than I
had to, so `codex-rs/app-server/tests/common/mcp_process.rs` still uses
the name `McpProcess` for now, but I will do some mechanical renamings
to things like `AppServer` in subsequent PRs.

While `mcp-server` and `app-server` share some overlapping functionality
(like reading streams of JSONL and dispatching based on message types)
and some differences (completely different message types), I ended up
doing a bit of copypasta between the two crates, as both have somewhat
similar `message_processor.rs` and `outgoing_message.rs` files for now,
though I expect them to diverge more in the near future.

One material change is that of the initialize handshake for `codex
app-server`, as we no longer use the MCP types for that handshake.
Instead, we update `codex-rs/protocol/src/mcp_protocol.rs` to add an
`Initialize` variant to `ClientRequest`, which takes the `ClientInfo`
object we need to update the `USER_AGENT_SUFFIX` in
`codex-rs/app-server/src/message_processor.rs`.

One other material change is in
`codex-rs/app-server/src/codex_message_processor.rs` where I eliminated
a use of the `send_event_as_notification()` method I am generally trying
to deprecate (because it blindly maps an `EventMsg` into a
`JSONNotification`) in favor of `send_server_notification()`, which
takes a `ServerNotification`, as that is intended to be a custom enum of
all notification types supported by the app server. So to make this
update, I had to introduce a new variant of `ServerNotification`,
`SessionConfigured`, which is a non-backwards compatible change with the
old `codex mcp`, and clients will have to be updated after the next
release that contains this PR. Note that
`codex-rs/app-server/tests/suite/list_resume.rs` also had to be update
to reflect this change.

I introduced `codex-rs/utils/json-to-toml/src/lib.rs` as a small utility
crate to avoid some of the copying between `mcp-server` and
`app-server`.
2025-09-30 07:06:18 +00:00
Gabriel Peal
2e95e5602d Update MCP docs to reference experimental RMCP client (#4422) 2025-09-30 02:44:16 -04:00
dedrisian-oai
87a654cf6b Move PR-style review to top (#4486)
<img width="469" height="330" alt="Screenshot 2025-09-29 at 10 31 22 PM"
src="https://github.com/user-attachments/assets/b5e20a08-85b4-4095-8a7f-0f58d1195b7e"
/>
2025-09-30 06:03:37 +00:00
pakrym-oai
27c6c5d7a7 SDK CI (#4483)
Build debug codex in SDK configuration
2025-09-29 21:15:02 -07:00
pakrym-oai
c09e131653 Set originator for codex exec (#4485)
Distinct from the main CLI.
2025-09-29 20:59:19 -07:00
pakrym-oai
ea82f86662 Rename conversation to thread in codex exec (#4482) 2025-09-29 20:18:30 -07:00
pakrym-oai
a8edc57740 Add MCP tool call item to codex exec (#4481)
No arguments/results for now.
```
{
  "type": "item.started",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "in_progress"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "completed"
  }
}
```
2025-09-29 19:45:11 -07:00
pakrym-oai
52e591ce60 Add some types and a basic test to the SDK (#4472) 2025-09-29 19:40:08 -07:00
rakesh-oai
079303091f Rakesh/support device auth (#3531)
# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

# test

```
codex-rs % export CODEX_DEVICE_AUTH_BASE_URL=http://localhost:3007
codex-rs % cargo run --bin codex login --experimental_use-device-code
   Compiling codex-login v0.0.0 (/Users/rakesh/code/codex/codex-rs/login)
   Compiling codex-mcp-server v0.0.0 (/Users/rakesh/code/codex/codex-rs/mcp-server)
   Compiling codex-tui v0.0.0 (/Users/rakesh/code/codex/codex-rs/tui)
   Compiling codex-cli v0.0.0 (/Users/rakesh/code/codex/codex-rs/cli)
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 2.90s
     Running `target/debug/codex login --experimental_use-device-code`
To authenticate, enter this code when prompted: 6Q27-KBVRF with interval 5
^C

```

The error in the last line is since the poll endpoint is not yet
implemented
2025-09-30 02:34:57 +00:00
pakrym-oai
4a80059b1b Add turn.failed and rename session created to thread started (#4478)
Don't produce completed when turn failed.
2025-09-29 18:38:04 -07:00
dedrisian-oai
bf76258cdc Custom prompts begin with /prompts: (#4476)
<img width="608" height="354" alt="Screenshot 2025-09-29 at 4 41 08 PM"
src="https://github.com/user-attachments/assets/162508eb-c1ac-4bc0-95f2-5e23cb4ae428"
/>
2025-09-29 17:58:16 -07:00
Ahmed Ibrahim
c64da4ff71 Fixes (#4458)
Fixing the "? for shortcuts"

- Only show the hint when composer is empty
- Don't reset footer on new task updates
- Reorder the elements
- Align the "?" and "/" with overlay on and off

Based on #4364
2025-09-30 00:10:04 +00:00
Ahmed Ibrahim
98efd352ae reintroduce "? for shortcuts" (#4364)
Reverts openai/codex#4362
2025-09-29 23:35:47 +00:00
dedrisian-oai
80ccec6530 Custom prompt args (numeric) (#4470)
[Cherry picked from /pull/3565]

Adds $1, $2, $3, $ARGUMENTS param parsing for custom prompts.
2025-09-29 16:14:37 -07:00
Jeremy Rose
c81baaabda no background for /command or @file popup (#4469)
before:

<img width="855" height="270" alt="Screenshot 2025-09-29 at 3 42 53 PM"
src="https://github.com/user-attachments/assets/eb247e1f-0947-4830-93c4-d4ecb2992b32"
/>


after:

<img width="855" height="270" alt="Screenshot 2025-09-29 at 3 43 04 PM"
src="https://github.com/user-attachments/assets/46717844-6066-47a4-a34a-1a75508ea2c3"
/>
2025-09-29 22:58:15 +00:00
Jeremy Rose
55b74c95e2 render • as dim (#4467)
<img width="988" height="686" alt="Screenshot 2025-09-29 at 3 28 30 PM"
src="https://github.com/user-attachments/assets/634a6e6f-cdc0-49af-97c1-096e871414bb"
/>
2025-09-29 15:46:47 -07:00
Ahmed Ibrahim
16057e76b0 [Core]: add tail in the rollout data (#4461)
This will help us show the conversation tail and last updated timestamp.
2025-09-29 14:32:26 -07:00
pakrym-oai
adbc38a978 TypeScript SDK scaffold (#4455) 2025-09-29 13:27:13 -07:00
dedrisian-oai
83a4d4d8ed Parse out frontmatter for custom prompts (#4456)
[Cherry picked from https://github.com/openai/codex/pull/3565]

Removes the frontmatter description/args from custom prompt files and
only includes body.
2025-09-29 13:06:08 -07:00
Dylan
197f45a3be [mcp-server] Expose fuzzy file search in MCP (#2677)
## Summary
Expose a simple fuzzy file search implementation for mcp clients to work
with

## Testing
- [x] Tested locally
2025-09-29 12:19:09 -07:00
vishnu-oai
04c1782e52 OpenTelemetry events (#2103)
### Title

## otel

Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.

```toml
[otel]
environment = "staging"   # defaults to "dev"
exporter = "none"          # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false    # defaults to false; redact prompt text unless explicitly enabled
```

Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.

### Event catalog

Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.

With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):

- `codex.api_request`
  - `cf_ray` (optional)
  - `attempt`
  - `duration_ms`
  - `http.response.status_code` (optional)
  - `error.message` (failures)
- `codex.sse_event`
  - `event.kind`
  - `duration_ms`
  - `error.message` (failures)
  - `input_token_count` (completion only)
  - `output_token_count` (completion only)
  - `cached_token_count` (completion only, optional)
  - `reasoning_token_count` (completion only, optional)
  - `tool_token_count` (completion only)
- `codex.user_prompt`
  - `prompt_length`
  - `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
  - `tool_name`
  - `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
  - `source` (`config` or `user`)
- `codex.tool_result`
  - `tool_name`
  - `call_id`
  - `arguments`
  - `duration_ms` (execution time for the tool)
  - `success` (`"true"` or `"false"`)
  - `output`

### Choosing an exporter

Set `otel.exporter` to control where events go:

- `none` – leaves instrumentation active but skips exporting. This is
the
  default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
  endpoint, protocol, and headers your collector expects:

  ```toml
  [otel]
  exporter = { otlp-http = {
    endpoint = "https://otel.example.com/v1/logs",
    protocol = "binary",
    headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
  }}
  ```

- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
  metadata headers:

  ```toml
  [otel]
  exporter = { otlp-grpc = {
    endpoint = "https://otel.example.com:4317",
    headers = { "x-otlp-meta" = "abc123" }
  }}
  ```

If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.

If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.

---------

Co-authored-by: Anton Panasenko <apanasenko@openai.com>
2025-09-29 11:30:55 -07:00
Jeremy Rose
d15253415a fix clear-to-end being emitted at the end of a row (#4447)
This was causing glitchy behavior when a line in the input was the exact
width of the terminal.
2025-09-29 16:52:35 +00:00
Ed Bayes
c4120a265b [CODEX-3595] Remove period when copying highlighted text in iTerm (#4419) 2025-09-28 20:50:04 -07:00
Michael Bolin
618a42adf5 feat: introduce npm module for codex-responses-api-proxy (#4417)
This PR expands `.github/workflows/rust-release.yml` so that it also
builds and publishes the `npm` module for
`@openai/codex-responses-api-proxy` in addition to `@openai/codex`. Note
both `npm` modules are similar, in that they each contain a single `.js`
file that is a thin launcher around the appropriate native executable.
(Since we have a minimal dependency on Node.js, I also lowered the
minimum version from 20 to 16 and verified that works on my machine.)

As part of this change, we tighten up some of the docs around
`codex-responses-api-proxy` and ensure the details regarding protecting
the `OPENAI_API_KEY` in memory match the implementation.

To test the `npm` build process, I ran:

```
./codex-cli/scripts/build_npm_package.py --package codex-responses-api-proxy --version 0.43.0-alpha.3
```

which stages the `npm` module for `@openai/codex-responses-api-proxy` in
a temp directory, using the binary artifacts from
https://github.com/openai/codex/releases/tag/rust-v0.43.0-alpha.3.
2025-09-28 19:34:06 -07:00
dedrisian-oai
a9d54b9e92 Add /review to main commands (#4416)
<img width="517" height="249" alt="Screenshot 2025-09-28 at 4 33 26 PM"
src="https://github.com/user-attachments/assets/6d34734e-fe3c-4b88-8239-a6436bcb9fa5"
/>
2025-09-28 16:59:39 -07:00
Michael Bolin
79e51dd607 fix: clean up some minor issues with .github/workflows/ci.yml (#4408) 2025-09-28 15:31:17 -07:00
Michael Bolin
ff6dbff0b6 feat: build codex-responses-api-proxy for all platforms as part of the GitHub Release (#4406)
This should make the `codex-responses-api-proxy` binaries available for
all platforms in a GitHub Release as well as a corresponding DotSlash
file.

Making `codex-responses-api-proxy` available as an `npm` module will be
done in a follow-up PR.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/4404).
* __->__ #4406
* #4404
* #4403
2025-09-28 15:25:15 -07:00
Michael Bolin
99841332e2 chore: remove responses-api-proxy from the multitool (#4404)
This removes the `codex responses-api-proxy` subcommand in favor of
running it as a standalone CLI.

As part of this change, we:

- remove the dependency on `tokio`/`async/await` as well as `codex_arg0`
- introduce the use of `pre_main_hardening()` so `CODEX_SECURE_MODE=1`
is not required

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/4404).
* #4406
* __->__ #4404
* #4403
2025-09-28 15:22:27 -07:00
Michael Bolin
7407469791 chore: lower logging level from error to info for MCP startup (#4412) 2025-09-28 15:13:44 -07:00
Michael Bolin
43615becf0 chore: move pre_main_hardening() utility into its own crate (#4403) 2025-09-28 14:35:14 -07:00
dedrisian-oai
9ee6e6f342 Improve update nudge (#4405)
Makes the update nudge larger and adds a link to see latest release:

<img width="542" height="337" alt="Screenshot 2025-09-28 at 11 19 05 AM"
src="https://github.com/user-attachments/assets/1facce96-72f0-4a97-910a-df8b5b8b07af"
/>
2025-09-28 11:46:15 -07:00
Thibault Sottiaux
d7286e9829 chore: remove model upgrade popup (#4332) 2025-09-27 13:25:09 -07:00
Fouad Matin
bcf2bc0aa5 fix(tui): make ? work again (#4362)
Revert #4330 #4316
2025-09-27 12:18:33 -07:00
Michael Bolin
68765214b3 fix: remove default timeout of 30s in the proxy (#4336)
This is likely the reason that I saw some conversations "freeze up" when
using the proxy.

Note the client in `core` does not specify a timeout when making
requests to the Responses API, so the proxy should not, either.
2025-09-27 07:54:32 -07:00
Ahmed Ibrahim
5c67dc3af1 Edit the spacing in shortcuts (#4330)
<img width="739" height="132" alt="image"
src="https://github.com/user-attachments/assets/e8d40abb-ac41-49a2-abc4-ddc6decef989"
/>
2025-09-26 22:54:38 -07:00
Jeremy Rose
c0960c0f49 tui: separator above final agent message (#4324)
Adds a separator line before the final agent message

<img width="1011" height="884" alt="Screenshot 2025-09-26 at 4 55 01 PM"
src="https://github.com/user-attachments/assets/7c91adbf-6035-4578-8b88-a6921f11bcbc"
/>
2025-09-26 22:49:59 -07:00
Thibault Sottiaux
90c3a5650c fix: set gpt-5-codex medium preset reasoning (#4335)
Otherwise it shows up as none, see
https://github.com/openai/codex/issues/4321
2025-09-26 22:31:39 -07:00
Thibault Sottiaux
a3254696c8 docs: refresh README under codex-rs (#4333) 2025-09-26 21:45:46 -07:00
Ahmed Ibrahim
2719fdd12a Add "? for shortcuts" (#4316)
https://github.com/user-attachments/assets/9e61b197-024b-4cbc-b40d-c446b448e759
2025-09-26 18:24:26 -07:00
Gabriel Peal
3a1be084f9 [MCP] Add experimental support for streamable HTTP MCP servers (#4317)
This PR adds support for streamable HTTP MCP servers when the
`experimental_use_rmcp_client` is enabled.

To set one up, simply add a new mcp server config with the url:
```
[mcp_servers.figma]
url = "http://127.0.0.1:3845/mcp"
```

It also supports an optional `bearer_token` which will be provided in an
authorization header. The full oauth flow is not supported yet.

The config parsing will throw if it detects that the user mixed and
matched config fields (like command + bearer token or url + env).

The best way to review it is to review `core/src` and then
`rmcp-client/src/rmcp_client.rs` first. The rest is tests and
propagating the `Transport` struct around the codebase.

Example with the Figma MCP:
<img width="5084" height="1614" alt="CleanShot 2025-09-26 at 13 35 40"
src="https://github.com/user-attachments/assets/eaf2771e-df3e-4300-816b-184d7dec5a28"
/>
2025-09-26 21:24:01 -04:00
Jeremy Rose
43b63ccae8 update composer + user message styling (#4240)
Changes:

- the composer and user messages now have a colored background that
stretches the entire width of the terminal.
- the prompt character was changed from a cyan `▌` to a bold `›`.
- the "working" shimmer now follows the "dark gray" color of the
terminal, better matching the terminal's color scheme

| Terminal + Background        | Screenshot |
|------------------------------|------------|
| iTerm with dark bg | <img width="810" height="641" alt="Screenshot
2025-09-25 at 11 44 52 AM"
src="https://github.com/user-attachments/assets/1317e579-64a9-4785-93e6-98b0258f5d92"
/> |
| iTerm with light bg | <img width="845" height="540" alt="Screenshot
2025-09-25 at 11 46 29 AM"
src="https://github.com/user-attachments/assets/e671d490-c747-4460-af0b-3f8d7f7a6b8e"
/> |
| iTerm with color bg | <img width="825" height="564" alt="Screenshot
2025-09-25 at 11 47 12 AM"
src="https://github.com/user-attachments/assets/141cda1b-1164-41d5-87da-3be11e6a3063"
/> |
| Terminal.app with dark bg | <img width="577" height="367"
alt="Screenshot 2025-09-25 at 11 45 22 AM"
src="https://github.com/user-attachments/assets/93fc4781-99f7-4ee7-9c8e-3db3cd854fe5"
/> |
| Terminal.app with light bg | <img width="577" height="367"
alt="Screenshot 2025-09-25 at 11 46 04 AM"
src="https://github.com/user-attachments/assets/19bf6a3c-91e0-447b-9667-b8033f512219"
/> |
| Terminal.app with color bg | <img width="577" height="367"
alt="Screenshot 2025-09-25 at 11 45 50 AM"
src="https://github.com/user-attachments/assets/dd7c4b5b-342e-4028-8140-f4e65752bd0b"
/> |
2025-09-26 16:35:56 -07:00
pakrym-oai
cc1b21e47f Add turn started/completed events and correct exit code on error (#4309)
Adds new event for session completed that includes usage. Also ensures
we return 1 on failures.
```
{
  "type": "session.created",
  "session_id": "019987a7-93e7-7b20-9e05-e90060e411ea"
}
{
  "type": "turn.started"
}
...
{
  "type": "turn.completed",
  "usage": {
    "input_tokens": 78913,
    "cached_input_tokens": 65280,
    "output_tokens": 1099
  }
}
```
2025-09-26 16:21:50 -07:00
iceweasel-oai
55801700de reject dangerous commands for AskForApproval::Never (#4307)
If we detect a dangerous command but approval_policy is Never, simply
reject the command.
2025-09-26 14:08:28 -07:00
Ahmed Ibrahim
1fba99ed85 /status followup (#4304)
- Render `send a message to load usage data` in the beginning of the
session
- Render `data not available yet` if received no rate limits 
- nit case
- Deleted stall snapshots that were moved to
`codex-rs/tui/src/status/snapshots`
2025-09-26 18:16:54 +00:00
Thibault Sottiaux
d3f6f6629b chore: dead code removal; remove frame count and stateful render helpers (#4310) 2025-09-26 17:52:02 +00:00
Gabriel Peal
e555a36c6a [MCP] Introduce an experimental official rust sdk based mcp client (#4252)
The [official Rust
SDK](57fc428c57)
has come a long way since we first started our mcp client implementation
5 months ago and, today, it is much more complete than our own
stdio-only implementation.

This PR introduces a new config flag `experimental_use_rmcp_client`
which will use a new mcp client powered by the sdk instead of our own.

To keep this PR simple, I've only implemented the same stdio MCP
functionality that we had but will expand on it with future PRs.

---------

Co-authored-by: pakrym-oai <pakrym@openai.com>
2025-09-26 13:13:37 -04:00
pakrym-oai
ea095e30c1 Add todo-list tool support (#4255)
Adds a 1-per-turn todo-list item and item.updated event

```jsonl
{"type":"item.started","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan  now","completed":false},{"text":"Update progress to next step","completed":false}]}}
{"type":"item.updated","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan  now","completed":true},{"text":"Update progress to next step","completed":false}]}}
{"type":"item.completed","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan  now","completed":true},{"text":"Update progress to next step","completed":false}]}}
```
2025-09-26 09:35:47 -07:00
Michael Bolin
c549481513 feat: introduce responses-api-proxy (#4246)
Details are in `responses-api-proxy/README.md`, but the key contribution
of this PR is a new subcommand, `codex responses-api-proxy`, which reads
the auth token for use with the OpenAI Responses API from `stdin` at
startup and then proxies `POST` requests to `/v1/responses` over to
`https://api.openai.com/v1/responses`, injecting the auth token as part
of the `Authorization` header.

The expectation is that `codex responses-api-proxy` is launched by a
privileged user who has access to the auth token so that it can be used
by unprivileged users of the Codex CLI on the same host.

If the client only has one user account with `sudo`, one option is to:

- run `sudo codex responses-api-proxy --http-shutdown --server-info
/tmp/server-info.json` to start the server
- record the port written to `/tmp/server-info.json`
- relinquish their `sudo` privileges (which is irreversible!) like so:

```
sudo deluser $USER sudo || sudo gpasswd -d $USER sudo || true
```

- use `codex` with the proxy (see `README.md`)
- when done, make a `GET` request to the server using the `PORT` from
`server-info.json` to shut it down:

```shell
curl --fail --silent --show-error "http://127.0.0.1:$PORT/shutdown"
```

To protect the auth token, we:

- allocate a 1024 byte buffer on the stack and write `"Bearer "` into it
to start
- we then read from `stdin`, copying to the contents into the buffer
after the prefix
- after verifying the input looks good, we create a `String` from that
buffer (so the data is now on the heap)
- we zero out the stack-allocated buffer using
https://crates.io/crates/zeroize so it is not optimized away by the
compiler
- we invoke `.leak()` on the `String` so we can treat its contents as a
`&'static str`, as it will live for the rest of the processs
- on UNIX, we `mlock(2)` the memory backing the `&'static str`
- when using the `&'static str` when building an HTTP request, we use
`HeaderValue::from_static()` to avoid copying the `&str`
- we also invoke `.set_sensitive(true)` on the `HeaderValue`, which in
theory indicates to other parts of the HTTP stack that the header should
be treated with "special care" to avoid leakage:


439d1c50d7/src/header/value.rs (L346-L376)
2025-09-26 08:19:00 -07:00
jif-oai
8797145678 fix: token usage for compaction (#4281)
Emit token usage update when draining compaction
2025-09-26 16:24:27 +02:00
Ahmed Ibrahim
a53720e278 Show exec output on success with trimmed display (#4113)
- Refactor Exec Cell into its own module
- update exec command rendering to inline the first command line
- limit continuation lines
- always show trimmed output
2025-09-26 07:13:44 -07:00
Ahmed Ibrahim
41f5d61f24 Move approvals to use ListSelectionView (#4275)
Unify selection menus:
- Move approvals to the vertical menu `ListSelectionView`
- Add header section to `ListSelectionView`

<img width="502" height="214" alt="image"
src="https://github.com/user-attachments/assets/f4b43ddf-3549-403c-ad9e-a523688714e4"
/>

<img width="748" height="214" alt="image"
src="https://github.com/user-attachments/assets/f94ac7b5-dc94-4dc0-a1df-7a8e3ba2453b"
/>

---------

Co-authored-by: pakrym-oai <pakrym@openai.com>
2025-09-26 07:13:29 -07:00
Ahmed Ibrahim
02609184be Refactor the footer logic to a new file (#4259)
This will help us have more control over the footer

---------

Co-authored-by: pakrym-oai <pakrym@openai.com>
2025-09-26 07:13:13 -07:00
jif-oai
1fc3413a46 ref: state - 2 (#4229)
Extracting tasks in a module and start abstraction behind a Trait (more
to come on this but each task will be tackled in a dedicated PR)
The goal was to drop the ActiveTask and to have a (potentially) set of
tasks during each turn
2025-09-26 13:49:08 +00:00
iceweasel-oai
eb2b739d6a core: add potentially dangerous command check (#4211)
Certain shell commands are potentially dangerous, and we want to check
for them.
Unless the user has explicitly approved a command, we will *always* ask
them for approval
when one of these commands is encountered, regardless of whether they
are in a sandbox, or what their approval policy is.

The first (of probably many) such examples is `git reset --hard`. We
will be conservative and check for any `git reset`
2025-09-25 19:46:20 -07:00
pakrym-oai
a10403d697 Actually mount sse once (#4264)
Mock server was responding with the same result many times.
2025-09-26 01:17:51 +00:00
pakrym-oai
8e3a048fec Add codex exec testing helpers (#4254)
Add a shortcut to create working directories and run codex exec with
fake server.
2025-09-25 17:12:45 -07:00
Eric Traut
9f2ab97fbc Fixed login failure with API key in IDE extension when a .codex directory doesn't exist (#4258)
This addresses bug #4092

Testing:
* Confirmed error occurs prior to fix if logging in using API key and no
`~/.codex` directory exists
* Confirmed after fix that `~/.codex` directory is properly created and
error doesn't occur
2025-09-25 16:53:28 -07:00
iceweasel-oai
38c9d7dca1 fix typo in sandbox doc (#4256)
just fixes a simple typo I noticed.
2025-09-25 16:03:44 -07:00
pakrym-oai
67aab04c66 [codex exec] Add item.started and support it for command execution (#4250)
Adds a new `item.started` event to `codex exec` and implements it for
command_execution item type.

```jsonl
{"type":"session.created","session_id":"019982d1-75f0-7920-b051-e0d3731a5ed8"}
{"type":"item.completed","item":{"id":"item_0","item_type":"reasoning","text":"**Executing commands securely**\n\nI'm thinking about how the default harness typically uses \"bash -lc,\" while historically \"bash\" is what we've been using. The command should be executed as a string in our CLI, so using \"bash -lc 'echo hello'\" is optimal but calling \"echo hello\" directly feels safer. The sandbox makes sure environment variables like CODEX_SANDBOX_NETWORK_DISABLED=1 are set, so I won't ask for approval. I just need to run \"echo hello\" and correctly present the output."}}
{"type":"item.completed","item":{"id":"item_1","item_type":"reasoning","text":"**Preparing for tool calls**\n\nI realize that I need to include a preamble before making any tool calls. So, I'll first state the preamble in the commentary channel, then proceed with the tool call. After that, I need to present the final message along with the output. It's possible that the CLI will show the output inline, but I must ensure that I present the result clearly regardless. Let's move forward and get this organized!"}}
{"type":"item.completed","item":{"id":"item_2","item_type":"assistant_message","text":"Running `echo` to confirm shell access and print output."}}
{"type":"item.started","item":{"id":"item_3","item_type":"command_execution","command":"bash -lc echo hello","aggregated_output":"","exit_code":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_3","item_type":"command_execution","command":"bash -lc echo hello","aggregated_output":"hello\n","exit_code":0,"status":"completed"}}
{"type":"item.completed","item":{"id":"item_4","item_type":"assistant_message","text":"hello"}}
```
2025-09-25 22:25:02 +00:00
Ahmed Ibrahim
7355ca48c5 fix (#4251)
# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
2025-09-25 15:12:25 -07:00
Jeremy Rose
affb5fc1d0 fix bug when resizing to a smaller width (#4248)
The composer and key hint lines were using line styles, causing ratatui
to print spaces all the way to the right side of the terminal. this
meant that resizing the terminal to be narrower would result in
rewrapping those lines, causing the bottom area to rerender and push all
content up.

Before


https://github.com/user-attachments/assets/8b14555a-1fc5-4f78-8df7-1410ee25e07a

After


https://github.com/user-attachments/assets/707645ab-89c7-4c7f-b556-02f53cef8a2f
2025-09-25 14:17:13 -07:00
Jeremy Rose
4a5f05c136 make tests pass cleanly in sandbox (#4067)
This changes the reqwest client used in tests to be sandbox-friendly,
and skips a bunch of other tests that don't work inside the
sandbox/without network.
2025-09-25 13:11:14 -07:00
pakrym-oai
acc2b63dfb Fix error message (#4204)
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
2025-09-25 11:10:40 -07:00
pakrym-oai
344d4a1d68 Add explicit codex exec events (#4177)
This pull request add a new experimental format of JSON output.

You can try it using `codex exec --experimental-json`.

Design takes a lot of inspiration from Responses API items and stream
format.

# Session and items
Each invocation of `codex exec` starts or resumes a session. 

Session contains multiple high-level item types:
1. Assistant message 
2. Assistant thinking 
3. Command execution 
4. File changes
5. To-do lists
6. etc.

# Events 
Session and items are going through their life cycles which is
represented by events.

Session is `session.created` or `session.resumed`
Items are `item.added`, `item.updated`, `item.completed`,
`item.require_approval` (or other item types like `item.output_delta`
when we need streaming).

So a typical session can look like:

<details>

```
{
  "type": "session.created",
  "session_id": "01997dac-9581-7de3-b6a0-1df8256f2752"
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_0",
    "item_type": "assistant_message",
    "text": "I’ll locate the top-level README and remove its first line. Then I’ll show a quick summary of what changed."
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_1",
    "item_type": "command_execution",
    "command": "bash -lc ls -la | sed -n '1,200p'",
    "aggregated_output": "pyenv: cannot rehash: /Users/pakrym/.pyenv/shims isn't writable\ntotal 192\ndrwxr-xr-x@  33 pakrym  staff   1056 Sep 24 14:36 .\ndrwxr-xr-x   41 pakrym  staff   1312 Sep 24 09:17 ..\n-rw-r--r--@   1 pakrym  staff      6 Jul  9 16:16 .codespellignore\n-rw-r--r--@   1 pakrym  staff    258 Aug 13 09:40 .codespellrc\ndrwxr-xr-x@   5 pakrym  staff    160 Jul 23 08:26 .devcontainer\n-rw-r--r--@   1 pakrym  staff   6148 Jul 22 10:03 .DS_Store\ndrwxr-xr-x@  15 pakrym  staff    480 Sep 24 14:38 .git\ndrwxr-xr-x@  12 pakrym  staff    384 Sep  2 16:00 .github\n-rw-r--r--@   1 pakrym  staff    778 Jul  9 16:16 .gitignore\ndrwxr-xr-x@   3 pakrym  staff     96 Aug 11 09:37 .husky\n-rw-r--r--@   1 pakrym  staff    104 Jul  9 16:16 .npmrc\n-rw-r--r--@   1 pakrym  staff     96 Sep  2 08:52 .prettierignore\n-rw-r--r--@   1 pakrym  staff    170 Jul  9 16:16 .prettierrc.toml\ndrwxr-xr-x@   5 pakrym  staff    160 Sep 14 17:43 .vscode\ndrwxr-xr-x@   2 pakrym  staff     64 Sep 11 11:37 2025-09-11\n-rw-r--r--@   1 pakrym  staff   5505 Sep 18 09:28 AGENTS.md\n-rw-r--r--@   1 pakrym  staff     92 Sep  2 08:52 CHANGELOG.md\n-rw-r--r--@   1 pakrym  staff   1145 Jul  9 16:16 cliff.toml\ndrwxr-xr-x@  11 pakrym  staff    352 Sep 24 13:03 codex-cli\ndrwxr-xr-x@  38 pakrym  staff   1216 Sep 24 14:38 codex-rs\ndrwxr-xr-x@  18 pakrym  staff    576 Sep 23 11:01 docs\n-rw-r--r--@   1 pakrym  staff   2038 Jul  9 16:16 flake.lock\n-rw-r--r--@   1 pakrym  staff   1434 Jul  9 16:16 flake.nix\n-rw-r--r--@   1 pakrym  staff  10926 Jul  9 16:16 LICENSE\ndrwxr-xr-x@ 465 pakrym  staff  14880 Jul 15 07:36 node_modules\n-rw-r--r--@   1 pakrym  staff    242 Aug  5 08:25 NOTICE\n-rw-r--r--@   1 pakrym  staff    578 Aug 14 12:31 package.json\n-rw-r--r--@   1 pakrym  staff    498 Aug 11 09:37 pnpm-lock.yaml\n-rw-r--r--@   1 pakrym  staff     58 Aug 11 09:37 pnpm-workspace.yaml\n-rw-r--r--@   1 pakrym  staff   2402 Jul  9 16:16 PNPM.md\n-rw-r--r--@   1 pakrym  staff   4393 Sep 12 14:36 README.md\ndrwxr-xr-x@   4 pakrym  staff    128 Sep 18 09:28 scripts\ndrwxr-xr-x@   2 pakrym  staff     64 Sep 11 11:34 tmp\n",
    "exit_code": 0,
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_2",
    "item_type": "reasoning",
    "text": "**Reviewing README.md file**\n\nI've located the README.md file at the root, and it’s 4393 bytes. Now, I need to remove the first line, but first, I should check its content to make sure I’m patching it correctly. I’ll use sed to display the first 20 lines. By reviewing those lines, I can determine exactly what needs to be removed before I proceed with the editing. Let's do this carefully!"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_3",
    "item_type": "command_execution",
    "command": "bash -lc sed -n '1,40p' README.md",
    "aggregated_output": "<h1 align=\"center\">OpenAI Codex CLI</h1>\n\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n  <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n  </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n```shell\nnpm install -g @openai/codex\n```\n\nAlternatively, if you use Homebrew:\n\n```shell\nbrew install codex\n```\n\nThen simply run `codex` to get started:\n\n```shell\ncodex\n```\n\n<details>\n<summary>You can also go to the <a href=\"https://github.com/openai/codex/releases/latest\">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>\n\n",
    "exit_code": 0,
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_4",
    "item_type": "reasoning",
    "text": "**Updating README file**\n\nThe user wants to update the README by removing the first line, which is an HTML h1 tag. I'll proceed to delete that line while keeping the rest intact. To do this, I need to use the apply_patch tool and create a patch in the diff format. I’ll take care to include context lines around the change. After removing the header, I’m considering whether to delete the following blank line as well to keep it tidy."
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_5",
    "item_type": "reasoning",
    "text": "**Crafting the patch**\n\nThe user has asked to remove just the first line, without mentioning the blank lines. Technically, leaving a blank line at the start is acceptable, but it's not ideal. Ideally, I'd prefer to remove the first line while maintaining the subsequent blank line. However, if I can also remove that blank line, it could tidy things up even more. Still, since the user's request is strictly to remove only the first line, I'll stick to that and craft the patch accordingly."
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_6",
    "item_type": "assistant_message",
    "text": "Applying the change by removing the first line from `README.md`."
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_7",
    "item_type": "file_change",
    "changes": [
      {
        "path": "/Users/pakrym/code/codex/README.md",
        "kind": "update"
      }
    ],
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_8",
    "item_type": "reasoning",
    "text": "**Validating README Update**\n\nI updated the README.md and now I need to validate that the first line has been successfully removed. To do this, I'll check the first 10 lines of the document to ensure everything looks correct. It’s always good to double-check these kinds of changes, so I’m going to take that extra step to make sure the update was executed properly. Let's see what those initial lines say!"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_9",
    "item_type": "command_execution",
    "command": "bash -lc sed -n '1,20p' README.md",
    "aggregated_output": "\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n  <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n  </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n",
    "exit_code": 0,
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "itm_10",
    "item_type": "assistant_message",
    "text": "- Updated `README.md:1` by removing the opening H1 line.\n- The README now starts with the install instructions paragraph.\n\nWant me to also remove the leading blank line at the top?"
  }
}
```

</details>

The idea is to give users fully formatted items they can use directly in
their rendering/application logic and avoid having them building up
items manually based on events (unless they want to for streaming).

This PR implements only the `item.completed` payload for some event
types, more event types and item types to come.

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-09-25 17:47:09 +00:00
Michael Bolin
a0c37f5d07 chore: refactor attempt_stream_responses() out of stream_responses() (#4194)
I would like to be able to swap in a different way to resolve model
sampling requests, so this refactoring consolidates things behind
`attempt_stream_responses()` to make that easier. Ideally, we would
support an in-memory backend that we can use in our integration tests,
for example.
2025-09-25 10:34:07 -07:00
Jeremy Rose
103adcdf2d fix: esc w/ queued messages overwrites draft in composer (#4237)
Instead of overwriting the contents of the composer when pressing
<kbd>Esc</kbd> when there's a queued message, prepend the queued
message(s) to the composer draft.
2025-09-25 10:07:27 -07:00
Michael Bolin
d61dea6fe6 feat: add support for CODEX_SECURE_MODE=1 to restrict process observability (#4220)
Because the `codex` process could contain sensitive information in
memory, such as API keys, we add logic so that when
`CODEX_SECURE_MODE=1` is specified, we avail ourselves of whatever the
operating system provides to restrict observability/tampering, which
includes:

- disabling `ptrace(2)`, so it is not possible to attach to the process
with a debugger, such as `gdb`
- disabling core dumps

Admittedly, a user with root privileges can defeat these safeguards.

For now, we only add support for this in the `codex` multitool, but we
may ultimately want to support this in some of the smaller CLIs that are
buildable out of our Cargo workspace.
2025-09-25 10:02:28 -07:00
Ahmed Ibrahim
e363dac249 revamp /status (#4196)
<img width="543" height="520" alt="image"
src="https://github.com/user-attachments/assets/bbc0eec0-e40b-45e7-bcd0-a997f8eeffa2"
/>
2025-09-25 15:38:50 +00:00
jif-oai
250b244ab4 ref: full state refactor (#4174)
## Current State Observations
- `Session` currently holds many unrelated responsibilities (history,
approval queues, task handles, rollout recorder, shell discovery, token
tracking, etc.), making it hard to reason about ownership and lifetimes.
- The anonymous `State` struct inside `codex.rs` mixes session-long data
with turn-scoped queues and approval bookkeeping.
- Turn execution (`run_task`) relies on ad-hoc local variables that
should conceptually belong to a per-turn state object.
- External modules (`codex::compact`, tests) frequently poke the raw
`Session.state` mutex, which couples them to implementation details.
- Interrupts, approvals, and rollout persistence all have bespoke
cleanup paths, contributing to subtle bugs when a turn is aborted
mid-flight.

## Desired End State
- Keep a slim `Session` object that acts as the orchestrator and façade.
It should expose a focused API (submit, approvals, interrupts, event
emission) without storing unrelated fields directly.
- Introduce a `state` module that encapsulates all mutable data
structures:
- `SessionState`: session-persistent data (history, approved commands,
token/rate-limit info, maybe user preferences).
- `ActiveTurn`: metadata for the currently running turn (sub-id, task
kind, abort handle) and an `Arc<TurnState>`.
- `TurnState`: all turn-scoped pieces (pending inputs, approval waiters,
diff tracker, review history, auto-compact flags, last agent message,
outstanding tool call bookkeeping).
- Group long-lived helpers/managers into a dedicated `SessionServices`
struct so `Session` does not accumulate "random" fields.
- Provide clear, lock-safe APIs so other modules never touch raw
mutexes.
- Ensure every turn creates/drops a `TurnState` and that
interrupts/finishes delegate cleanup to it.
2025-09-25 12:16:06 +02:00
pakrym-oai
d1ed3a4cef github: update codespell action to v2.1 in workflow (#4205)
Old version fails to find python 3.8 docker image
2025-09-25 04:05:00 +00:00
pakrym-oai
e85742635f Send text parameter for non-gpt-5 models (#4195)
We had a hardcoded check for gpt-5 before.

Fixes: https://github.com/openai/codex/issues/4181
2025-09-24 22:00:06 +00:00
Michael Bolin
87b299aa3f chore: drop unused values from env_flags (#4188)
For the most part, we try to avoid environment variables in favor of
config options so the environment variables do not leak into child
processes. These environment variables are no longer honored, so let's
delete them to be clear.

Ultimately, I would also like to eliminate `CODEX_RS_SSE_FIXTURE` in
favor of something cleaner.
2025-09-24 14:29:51 -07:00
iceweasel-oai
0e58870634 adds a windows-specific method to check if a command is safe (#4119)
refactors command_safety files into its own package, so we can add
platform-specific ones
Also creates a windows-specific of `is_known_safe_command` that just
returns false always, since that is what happens today.
2025-09-24 14:03:43 -07:00
Jeremy Rose
42847baaf7 pageless session list (#3194) 2025-09-24 13:44:48 -07:00
Jeremy Rose
6032d784ee improve MCP tool call styling (#3871)
<img width="760" height="213" alt="Screenshot 2025-09-18 at 12 29 15 PM"
src="https://github.com/user-attachments/assets/48a205b7-b95a-4988-8c76-efceb998dee7"
/>
2025-09-24 13:36:01 -07:00
Jeremy Rose
7bff8df10e hide the status indicator when the answer stream starts (#4101)
This eliminates a "bounce" at the end of streaming where we hide the
status indicator at the end of the turn and the composer moves up two
lines.

Also, simplify streaming further by removing the HistorySink and
inverting control, and collapsing a few single-element structures.
2025-09-24 11:51:48 -07:00
pakrym-oai
addc946d13 Simplify tool implemetations (#4160)
Use Result<String, FunctionCallError> for all tool handling code and
rely on error propagation instead of creating failed items everywhere.
2025-09-24 17:27:35 +00:00
dependabot[bot]
bffdbec2c5 chore(deps): bump chrono from 0.4.41 to 0.4.42 in /codex-rs (#4028)
Bumps [chrono](https://github.com/chronotope/chrono) from 0.4.41 to
0.4.42.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/chronotope/chrono/releases">chrono's
releases</a>.</em></p>
<blockquote>
<h2>0.4.42</h2>
<h2>What's Changed</h2>
<ul>
<li>Add fuzzer for DateTime::parse_from_str by <a
href="https://github.com/tyler92"><code>@​tyler92</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1700">chronotope/chrono#1700</a></li>
<li>Fix wrong amount of micro/milliseconds by <a
href="https://github.com/nmlt"><code>@​nmlt</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1703">chronotope/chrono#1703</a></li>
<li>Add warning about MappedLocalTime and wasm by <a
href="https://github.com/lutzky"><code>@​lutzky</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1702">chronotope/chrono#1702</a></li>
<li>Fix incorrect parsing of fixed-length second fractions by <a
href="https://github.com/chris-leach"><code>@​chris-leach</code></a> in
<a
href="https://redirect.github.com/chronotope/chrono/pull/1705">chronotope/chrono#1705</a></li>
<li>Fix cfgs for <code>wasm32-linux</code> support by <a
href="https://github.com/arjunr2"><code>@​arjunr2</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1707">chronotope/chrono#1707</a></li>
<li>Fix OpenHarmony's <code>tzdata</code> parsing by <a
href="https://github.com/ldm0"><code>@​ldm0</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1679">chronotope/chrono#1679</a></li>
<li>Convert NaiveDate to/from days since unix epoch by <a
href="https://github.com/findepi"><code>@​findepi</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1715">chronotope/chrono#1715</a></li>
<li>Add <code>?Sized</code> bound to related methods of
<code>DelayedFormat::write_to</code> by <a
href="https://github.com/Huliiiiii"><code>@​Huliiiiii</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1721">chronotope/chrono#1721</a></li>
<li>Add <code>from_timestamp_secs</code> method to <code>DateTime</code>
by <a href="https://github.com/jasonaowen"><code>@​jasonaowen</code></a>
in <a
href="https://redirect.github.com/chronotope/chrono/pull/1719">chronotope/chrono#1719</a></li>
<li>Migrate to core::error::Error by <a
href="https://github.com/benbrittain"><code>@​benbrittain</code></a> in
<a
href="https://redirect.github.com/chronotope/chrono/pull/1704">chronotope/chrono#1704</a></li>
<li>Upgrade to windows-bindgen 0.63 by <a
href="https://github.com/djc"><code>@​djc</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1730">chronotope/chrono#1730</a></li>
<li>strftime: simplify error handling by <a
href="https://github.com/djc"><code>@​djc</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1731">chronotope/chrono#1731</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f3fd15f976"><code>f3fd15f</code></a>
Bump version to 0.4.42</li>
<li><a
href="5cf5603500"><code>5cf5603</code></a>
strftime: add regression test case</li>
<li><a
href="a6231701ee"><code>a623170</code></a>
strftime: simplify error handling</li>
<li><a
href="36fbfb1221"><code>36fbfb1</code></a>
strftime: move specifier handling out of match to reduce rightward
drift</li>
<li><a
href="7f413c363b"><code>7f413c3</code></a>
strftime: yield None early</li>
<li><a
href="9d5dfe1640"><code>9d5dfe1</code></a>
strftime: outline constants</li>
<li><a
href="e5f6be7db4"><code>e5f6be7</code></a>
strftime: move error() method below caller</li>
<li><a
href="d516c2764d"><code>d516c27</code></a>
strftime: merge impl blocks</li>
<li><a
href="0ee2172fb9"><code>0ee2172</code></a>
strftime: re-order items to keep impls together</li>
<li><a
href="757a8b0226"><code>757a8b0</code></a>
Upgrade to windows-bindgen 0.63</li>
<li>Additional commits viewable in <a
href="https://github.com/chronotope/chrono/compare/v0.4.41...v0.4.42">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=chrono&package-manager=cargo&previous-version=0.4.41&new-version=0.4.42)](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>
2025-09-24 16:53:26 +00:00
dependabot[bot]
353a5c2046 chore(deps): bump unicode-width from 0.1.14 to 0.2.1 in /codex-rs (#2156)
Bumps [unicode-width](https://github.com/unicode-rs/unicode-width) from
0.1.14 to 0.2.1.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="0085e91db7"><code>0085e91</code></a>
Publish 0.2.1</li>
<li><a
href="6db0c14cbd"><code>6db0c14</code></a>
Remove <code>compiler-builtins</code> from <code>rustc-dep-of-std</code>
dependencies (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/77">#77</a>)</li>
<li><a
href="0bccd3f1b5"><code>0bccd3f</code></a>
update copyright year (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/76">#76</a>)</li>
<li><a
href="7a7fcdc813"><code>7a7fcdc</code></a>
Support Unicode 16 (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/74">#74</a>)</li>
<li><a
href="82d7136b49"><code>82d7136</code></a>
Advertise and enforce MSRV (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/73">#73</a>)</li>
<li><a
href="e77b2929bc"><code>e77b292</code></a>
Make characters with <code>Line_Break=Ambiguous</code> ambiguous (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/61">#61</a>)</li>
<li><a
href="5a7fced663"><code>5a7fced</code></a>
Update version number in Readme (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/70">#70</a>)</li>
<li><a
href="79eab0d9fc"><code>79eab0d</code></a>
Publish 0.2.0 with newlines treated as width 1 (<a
href="https://redirect.github.com/unicode-rs/unicode-width/issues/68">#68</a>)</li>
<li>See full diff in <a
href="https://github.com/unicode-rs/unicode-width/compare/v0.1.14...v0.2.1">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=unicode-width&package-manager=cargo&previous-version=0.1.14&new-version=0.2.1)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

You can trigger a rebase of this PR 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>

> **Note**
> Automatic rebases have been disabled on this pull request as it has
been open for over 30 days.

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-09-24 16:33:46 +00:00
Tien Nguyen
00c7f7a16c chore: remove once_cell dependency from multiple crates (#4154)
This commit removes the `once_cell` dependency from `Cargo.toml` files
in the `codex-rs` and `apply-patch` directories, replacing its usage
with `std::sync::LazyLock` and `std::sync::OnceLock` where applicable.
This change simplifies the dependency tree and utilizes standard library
features for lazy initialization.

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
2025-09-24 09:15:57 -07:00
Michael Bolin
82e65975b2 fix: add tolerance for ambiguous behavior in gh run list (#4162)
I am not sure what is going on, as
https://github.com/openai/codex/pull/3660 introduced this new logic and
I swear that CI was green before I merged that PR, but I am seeing
failures in this CI job this morning. This feels like a
non-backwards-compatible change in `gh`, but that feels unlikely...

Nevertheless, this is what I currently see on my laptop:

```
$ gh --version
gh version 2.76.2 (2025-07-30)
https://github.com/cli/cli/releases/tag/v2.76.2
$ gh run list --workflow .github/workflows/rust-release.yml --branch rust-v0.40.0 --json workflowName,url,headSha --jq 'first(.[])'
{
  "headSha": "5268705a69713752adcbd8416ef9e84a683f7aa3",
  "url": "https://github.com/openai/codex/actions/runs/17952349351",
  "workflowName": ".github/workflows/rust-release.yml"
}
```

Looking at sample output from an old GitHub issue
(https://github.com/cli/cli/issues/6678), it appears that, at least at
one point in time, the `workflowName` was _not_ the path to the
workflow.
2025-09-24 09:15:03 -07:00
Michael Bolin
639a6fd2f3 chore: upgrade to Rust 1.90 (#4124)
Inspired by Dependabot's attempt to do this:
https://github.com/openai/codex/pull/4029

The new version of Clippy found some unused structs that are removed in
this PR.

Though nothing stood out to me in the Release Notes in terms of things
we should start to take advantage of:
https://blog.rust-lang.org/2025/09/18/Rust-1.90.0/.
2025-09-24 08:32:00 -07:00
jif-oai
db4aa6f916 nit: 350k tokens (#4156)
350k tokens for gpt-5-codex auto-compaction and update comments for
better description
2025-09-24 15:31:27 +00:00
Ahmed Ibrahim
cb96f4f596 Add Reset in for rate limits (#4111)
- Parse the headers
- Reorganize the struct because it's getting too long
- show the resets at in the tui

<img width="324" height="79" alt="image"
src="https://github.com/user-attachments/assets/ca15cd48-f112-4556-91ab-1e3a9bc4683d"
/>
2025-09-24 15:31:08 +00:00
jif-oai
5b910f1f05 chore: extract readiness in a dedicated utils crate (#4140)
Create an `utils` directory for the small utils crates
2025-09-24 10:15:54 +00:00
jif-oai
af6304c641 nit: drop instruction override for auto-compact (#4137)
drop instruction override for auto-compact as this is not used and
dangerous as it invalidates the cache
2025-09-24 10:47:12 +01:00
jif-oai
b90eeabd74 nit: update auto compact to 250k (#4135)
update auto compact for gpt-5-codex to 250k
2025-09-24 09:41:33 +00:00
dependabot[bot]
f7d2f3e54d chore(deps): bump tempfile from 3.20.0 to 3.22.0 in /codex-rs (#4030)
Bumps [tempfile](https://github.com/Stebalien/tempfile) from 3.20.0 to
3.22.0.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/Stebalien/tempfile/blob/master/CHANGELOG.md">tempfile's
changelog</a>.</em></p>
<blockquote>
<h2>3.22.0</h2>
<ul>
<li>Updated <code>windows-sys</code> requirement to allow version
0.61.x</li>
<li>Remove <code>unstable-windows-keep-open-tempfile</code>
feature.</li>
</ul>
<h2>3.21.0</h2>
<ul>
<li>Updated <code>windows-sys</code> requirement to allow version
0.60.x</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f720dbe098"><code>f720dbe</code></a>
chore: release 3.22.0</li>
<li><a
href="55d742cb5d"><code>55d742c</code></a>
chore: remove deprecated unstable feature flag</li>
<li><a
href="bc41a0b586"><code>bc41a0b</code></a>
build(deps): update windows-sys requirement from &gt;=0.52, &lt;0.61 to
&gt;=0.52, &lt;0....</li>
<li><a
href="3c55387ede"><code>3c55387</code></a>
test: make sure we don't drop tempdirs early (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/373">#373</a>)</li>
<li><a
href="17bf644406"><code>17bf644</code></a>
doc(builder): clarify permissions (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/372">#372</a>)</li>
<li><a
href="c7423f1761"><code>c7423f1</code></a>
doc(env): document the alternative to setting the tempdir (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/371">#371</a>)</li>
<li><a
href="5af60ca9e3"><code>5af60ca</code></a>
test(wasi): run a few tests that shouldn't have been disabled (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/370">#370</a>)</li>
<li><a
href="6c0c56198a"><code>6c0c561</code></a>
fix(doc): temp_dir doesn't check if writable</li>
<li><a
href="48bff5f54c"><code>48bff5f</code></a>
test(tempdir): configure tempdir on wasi</li>
<li><a
href="704a1d2752"><code>704a1d2</code></a>
test(tempdir): cleanup tempdir tests and run more tests on wasi</li>
<li>Additional commits viewable in <a
href="https://github.com/Stebalien/tempfile/compare/v3.20.0...v3.22.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=tempfile&package-manager=cargo&previous-version=3.20.0&new-version=3.22.0)](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>
2025-09-23 23:41:35 -07:00
dependabot[bot]
3fe3b6328b chore(deps): bump log from 0.4.27 to 0.4.28 in /codex-rs (#4027)
[//]: # (dependabot-start)
⚠️  **Dependabot is rebasing this PR** ⚠️ 

Rebasing might not happen immediately, so don't worry if this takes some
time.

Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.

---

[//]: # (dependabot-end)

Bumps [log](https://github.com/rust-lang/log) from 0.4.27 to 0.4.28.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/rust-lang/log/releases">log's
releases</a>.</em></p>
<blockquote>
<h2>0.4.28</h2>
<h2>What's Changed</h2>
<ul>
<li>ci: drop really old trick and ensure MSRV for all feature combo by
<a href="https://github.com/tisonkun"><code>@​tisonkun</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/676">rust-lang/log#676</a></li>
<li>chore: fix some typos in comment by <a
href="https://github.com/xixishidibei"><code>@​xixishidibei</code></a>
in <a
href="https://redirect.github.com/rust-lang/log/pull/677">rust-lang/log#677</a></li>
<li>Unhide <code>#[derive(Debug)]</code> in example by <a
href="https://github.com/ZylosLumen"><code>@​ZylosLumen</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/688">rust-lang/log#688</a></li>
<li>Chore: delete compare_exchange method for AtomicUsize on platforms
without atomics by <a
href="https://github.com/HaoliangXu"><code>@​HaoliangXu</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/690">rust-lang/log#690</a></li>
<li>Add <code>increment_severity()</code> and
<code>decrement_severity()</code> methods for <code>Level</code> and
<code>LevelFilter</code> by <a
href="https://github.com/nebkor"><code>@​nebkor</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/692">rust-lang/log#692</a></li>
<li>Prepare for 0.4.28 release by <a
href="https://github.com/KodrAus"><code>@​KodrAus</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/695">rust-lang/log#695</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/xixishidibei"><code>@​xixishidibei</code></a>
made their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/677">rust-lang/log#677</a></li>
<li><a
href="https://github.com/ZylosLumen"><code>@​ZylosLumen</code></a> made
their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/688">rust-lang/log#688</a></li>
<li><a
href="https://github.com/HaoliangXu"><code>@​HaoliangXu</code></a> made
their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/690">rust-lang/log#690</a></li>
<li><a href="https://github.com/nebkor"><code>@​nebkor</code></a> made
their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/692">rust-lang/log#692</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/rust-lang/log/compare/0.4.27...0.4.28">https://github.com/rust-lang/log/compare/0.4.27...0.4.28</a></p>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/rust-lang/log/blob/master/CHANGELOG.md">log's
changelog</a>.</em></p>
<blockquote>
<h2>[0.4.28] - 2025-09-02</h2>
<h2>What's Changed</h2>
<ul>
<li>ci: drop really old trick and ensure MSRV for all feature combo by
<a href="https://github.com/tisonkun"><code>@​tisonkun</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/676">rust-lang/log#676</a></li>
<li>Chore: delete compare_exchange method for AtomicUsize on platforms
without atomics by <a
href="https://github.com/HaoliangXu"><code>@​HaoliangXu</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/690">rust-lang/log#690</a></li>
<li>Add <code>increment_severity()</code> and
<code>decrement_severity()</code> methods for <code>Level</code> and
<code>LevelFilter</code> by <a
href="https://github.com/nebkor"><code>@​nebkor</code></a> in <a
href="https://redirect.github.com/rust-lang/log/pull/692">rust-lang/log#692</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/xixishidibei"><code>@​xixishidibei</code></a>
made their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/677">rust-lang/log#677</a></li>
<li><a
href="https://github.com/ZylosLumen"><code>@​ZylosLumen</code></a> made
their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/688">rust-lang/log#688</a></li>
<li><a
href="https://github.com/HaoliangXu"><code>@​HaoliangXu</code></a> made
their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/690">rust-lang/log#690</a></li>
<li><a href="https://github.com/nebkor"><code>@​nebkor</code></a> made
their first contribution in <a
href="https://redirect.github.com/rust-lang/log/pull/692">rust-lang/log#692</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/rust-lang/log/compare/0.4.27...0.4.28">https://github.com/rust-lang/log/compare/0.4.27...0.4.28</a></p>
<h3>Notable Changes</h3>
<ul>
<li>MSRV is bumped to 1.61.0 in <a
href="https://redirect.github.com/rust-lang/log/pull/676">rust-lang/log#676</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="6e1735597b"><code>6e17355</code></a>
Merge pull request <a
href="https://redirect.github.com/rust-lang/log/issues/695">#695</a>
from rust-lang/cargo/0.4.28</li>
<li><a
href="57719dbef5"><code>57719db</code></a>
focus on user-facing source changes in the changelog</li>
<li><a
href="e0630c6485"><code>e0630c6</code></a>
prepare for 0.4.28 release</li>
<li><a
href="60829b11f5"><code>60829b1</code></a>
Merge pull request <a
href="https://redirect.github.com/rust-lang/log/issues/692">#692</a>
from nebkor/up-and-down</li>
<li><a
href="95d44f8af5"><code>95d44f8</code></a>
change names of log-level-changing methods to be more descriptive</li>
<li><a
href="2b63dfada6"><code>2b63dfa</code></a>
Add <code>up()</code> and <code>down()</code> methods for
<code>Level</code> and <code>LevelFilter</code></li>
<li><a
href="3aa1359e92"><code>3aa1359</code></a>
Merge pull request <a
href="https://redirect.github.com/rust-lang/log/issues/690">#690</a>
from HaoliangXu/master</li>
<li><a
href="1091f2cbd2"><code>1091f2c</code></a>
Chore:delete compare_exchange method for AtomicUsize on platforms</li>
<li><a
href="24c5f44efd"><code>24c5f44</code></a>
Merge pull request <a
href="https://redirect.github.com/rust-lang/log/issues/688">#688</a>
from ZylosLumen/patch-1</li>
<li><a
href="4498495467"><code>4498495</code></a>
Unhide <code>#[derive(Debug)]</code> in example</li>
<li>Additional commits viewable in <a
href="https://github.com/rust-lang/log/compare/0.4.27...0.4.28">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=log&package-manager=cargo&previous-version=0.4.27&new-version=0.4.28)](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>
2025-09-23 23:07:54 -07:00
dependabot[bot]
8144ddb3da chore(deps): bump serde from 1.0.224 to 1.0.226 in /codex-rs (#4031)
[//]: # (dependabot-start)
⚠️  **Dependabot is rebasing this PR** ⚠️ 

Rebasing might not happen immediately, so don't worry if this takes some
time.

Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.

---

[//]: # (dependabot-end)

Bumps [serde](https://github.com/serde-rs/serde) from 1.0.224 to
1.0.226.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/serde/releases">serde's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.226</h2>
<ul>
<li>Deduplicate variant matching logic inside generated Deserialize impl
for adjacently tagged enums (<a
href="https://redirect.github.com/serde-rs/serde/issues/2935">#2935</a>,
thanks <a
href="https://github.com/Mingun"><code>@​Mingun</code></a>)</li>
</ul>
<h2>v1.0.225</h2>
<ul>
<li>Avoid triggering a deprecation warning in derived Serialize and
Deserialize impls for a data structure that contains its own
deprecations (<a
href="https://redirect.github.com/serde-rs/serde/issues/2879">#2879</a>,
thanks <a
href="https://github.com/rcrisanti"><code>@​rcrisanti</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="1799547846"><code>1799547</code></a>
Release 1.0.226</li>
<li><a
href="2dbeefb11b"><code>2dbeefb</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2935">#2935</a>
from Mingun/dedupe-adj-enums</li>
<li><a
href="8a3c29ff19"><code>8a3c29f</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2986">#2986</a>
from dtolnay/didnotwork</li>
<li><a
href="defc24d361"><code>defc24d</code></a>
Remove &quot;did not work&quot; comment from test suite</li>
<li><a
href="2316610760"><code>2316610</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2929">#2929</a>
from Mingun/flatten-enum-tests</li>
<li><a
href="c09e2bd690"><code>c09e2bd</code></a>
Add tests for flatten unit variant in adjacently tagged (tag + content)
enums</li>
<li><a
href="fe7dcc4cd8"><code>fe7dcc4</code></a>
Test all possible orders of map entries for enum-flatten-in-struct
representa...</li>
<li><a
href="a20e66e131"><code>a20e66e</code></a>
Check serialization in
flatten::enum_::internally_tagged::unit_enum_with_unkn...</li>
<li><a
href="1c1a5d95cd"><code>1c1a5d9</code></a>
Reorder struct_ and newtype tests of adjacently_tagged enums to match
order i...</li>
<li><a
href="ee3c2372fb"><code>ee3c237</code></a>
Opt in to generate-macro-expansion when building on docs.rs</li>
<li>Additional commits viewable in <a
href="https://github.com/serde-rs/serde/compare/v1.0.224...v1.0.226">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=serde&package-manager=cargo&previous-version=1.0.224&new-version=1.0.226)](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>
2025-09-23 23:06:30 -07:00
Michael Bolin
9336f2b84b fix: npm publish --tag alpha when building an alpha release (#4112)
This updates our release process so that when we build an alpha of the
Codex CLI (as determined by pushing a tag of the format
`rust-v<cli-version>-alpha.<alpha-version>`), we will now publish the
corresponding npm module publicly, but under the `alpha` tag. As you can
see, this PR adds `--tag alpha` to the `npm publish` command, as
appropriate.
2025-09-23 23:03:43 -07:00
Michael Bolin
af37785bca fix: vendor ripgrep in the npm module (#3660)
We try to ensure ripgrep (`rg`) is provided with Codex.

- For `brew`, we declare it as a dependency of our formula:

08d82d8b00/Formula/c/codex.rb (L24)
- For `npm`, we declare `@vscode/ripgrep` as a dependency, which
installs the platform-specific binary as part of a `postinstall` script:

fdb8dadcae/codex-cli/package.json (L22)
- Users who download the CLI directly from GitHub Releases are on their
own.

In practice, I have seen `@vscode/ripgrep` fail on occasion. Here is a
trace from a GitHub workflow:

```
npm error code 1
npm error path /Users/runner/hostedtoolcache/node/20.19.5/arm64/lib/node_modules/@openai/codex/node_modules/@vscode/ripgrep
npm error command failed
npm error command sh -c node ./lib/postinstall.js
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 1 failed, retrying in 2 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 2 failed, retrying in 4 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 3 failed, retrying in 8 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 4 failed, retrying in 16 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Error: Request failed: 403
```

To eliminate this error, this PR changes things so that we vendor the
`rg` binary into https://www.npmjs.com/package/@openai/codex so it is
guaranteed to be included when a user runs `npm i -g @openai/codex`.

The downside of this approach is the increase in package size: we
include the `rg` executable for six architectures (in addition to the
six copies of `codex` we already include). In a follow-up, I plan to add
support for "slices" of our npm module, so that soon users will be able
to do:

```
npm install -g @openai/codex@aarch64-apple-darwin
```

Admittedly, this is a sizable change and I tried to clean some things up
in the process:

- `install_native_deps.sh` has been replaced by `install_native_deps.py`
- `stage_release.sh` and `stage_rust_release.py` has been replaced by
`build_npm_package.py`

We now vendor in a DotSlash file for ripgrep (as a modest attempt to
facilitate local testing) and then build up the extension by:

- creating a temp directory and copying `package.json` over to it with
the target value for `"version"`
- finding the GitHub workflow that corresponds to the
`--release-version` and copying the various `codex` artifacts to
respective `vendor/TARGET_TRIPLE/codex` folder
- downloading the `rg` artifacts specified in the DotSlash file and
copying them over to the respective `vendor/TARGET_TRIPLE/path` folder
- if `--pack-output` is specified, runs `npm pack` on the temp directory

To test, I downloaded the artifact produced by this CI job:


https://github.com/openai/codex/actions/runs/17961595388/job/51085840022?pr=3660

and verified that `node ./bin/codex.js 'which -a rg'` worked as
intended.
2025-09-23 23:00:33 -07:00
Dylan
594248f415 [exec] add include-plan-tool flag and print it nicely (#3461)
### Summary
Sometimes in exec runs, we want to allow the model to use the
`update_plan` tool, but that's not easily configurable. This change adds
a feature flag for this, and formats the output so it's human-readable

## Test Plan
<img width="1280" height="354" alt="Screenshot 2025-09-11 at 12 39
44 AM"
src="https://github.com/user-attachments/assets/72e11070-fb98-47f5-a784-5123ca7333d9"
/>
2025-09-23 16:50:59 -07:00
Ahmed Ibrahim
8227a5ba1b Send limits when getting rate limited (#4102)
Users need visibility on rate limits when they are rate limited.
2025-09-23 22:56:34 +00:00
pakrym-oai
fdb8dadcae Add exec output-schema parameter (#4079)
Adds structured output to `exec` via the `--structured-output`
parameter.
2025-09-23 13:59:16 -07:00
pakrym-oai
0f9a796617 Use anyhow::Result in tests for error propagation (#4105) 2025-09-23 13:31:36 -07:00
Ahmed Ibrahim
c6e8671b2a Refactor codex card layout (#4069)
Refactor it to be used in status
2025-09-23 17:37:14 +00:00
jif-oai
b84a920067 chore: compact do not modify instructions (#4088)
Keep the developer instruction and insert the summarisation message as a
user message instead
2025-09-23 17:59:17 +01:00
jif-oai
6cd5309d91 feat: readiness tool (#4090)
Readiness flag with token-based subscription and async wait function
that waits for all the subscribers to be ready
2025-09-23 17:27:20 +01:00
Ahmed Ibrahim
664ee07540 Rate limits warning (#4075)
Only show the highest warning rate.
Change the warning threshold
2025-09-23 09:15:16 -07:00
ae
51c465bddc fix: usage data tweaks (#4082)
- Only show the usage data section when signed in with ChatGPT. (Tested
with Chat auth and API auth.)
- Friendlier string change.
- Also removed `.dim()` on the string, since it was the only string in
`/status` that was dim.
2025-09-23 09:14:02 -07:00
jif-oai
e0fbc112c7 feat: git tooling for undo (#3914)
## Summary
Introduces a “ghost commit” workflow that snapshots the tree without
touching refs.
1. git commit-tree writes an unreferenced commit object from the current
index, optionally pointing to the current HEAD as its parent.
2. We then stash that commit id and use git restore --source <ghost> to
roll the worktree (and index) back to the recorded snapshot later on.

## Details
- Ghost commits live only as loose objects—we never update branches or
tags—so the repo history stays untouched while still giving us a full
tree snapshot.
- Force-included paths let us stage otherwise ignored files before
capturing the tree.
- Restoration rehydrates both tracked and force-included files while
leaving untracked/ignored files alone.
2025-09-23 16:59:52 +01:00
pakrym-oai
76ecbb3d8e Use TestCodex builder in stream retry tests (#4096)
## Summary
- refactor the stream retry integration tests to construct conversations
through `TestCodex`
- remove bespoke config and tempdir setup now handled by the shared
builder

## Testing
- cargo test -p codex-core --test all
stream_error_allows_next_turn::continue_after_stream_error
- cargo test -p codex-core --test all
stream_no_completed::retries_on_early_close

------
https://chatgpt.com/codex/tasks/task_i_68d2b94d83888320bc75a0bc3bd77b49
2025-09-23 08:57:08 -07:00
jif-oai
2451b19d13 chore: enable auto-compaction for gpt-5-codex (#4093)
enable auto-compaction for `gpt-5-codex` at 220k tokens
2025-09-23 16:12:36 +01:00
pakrym-oai
5c7d9e27b1 Add notifier tests (#4064)
Proposal:
1. Use anyhow for tests and avoid unwrap
2. Extract a helper for starting a test instance of codex
2025-09-23 14:25:46 +00:00
Thibault Sottiaux
c93e77b68b feat: update default (#4076)
Changes:
- Default model and docs now use gpt-5-codex. 
- Disables the GPT-5 Codex NUX by default.
- Keeps presets available for API key users.
2025-09-22 20:10:52 -07:00
dedrisian-oai
c415827ac2 Truncate potentially long user messages in compact message. (#4068)
If a prior user message is massive, any future `/compact` task would
fail because we're verbatim copying the user message into the new chat.
2025-09-22 23:12:26 +00:00
Jeremy Rose
4e0550b995 fix codex resume message at end of session (#3957)
This was only being printed when running the codex-tui executable
directly, not via the codex-cli wrapper.
2025-09-22 22:24:31 +00:00
Jeremy Rose
f54a49157b Fix pager overlay clear between pages (#3952)
should fix characters sometimes hanging around while scrolling the
transcript.
2025-09-22 15:12:29 -07:00
Ahmed Ibrahim
dd56750612 Change headers and struct of rate limits (#4060) 2025-09-22 21:06:20 +00:00
dedrisian-oai
8bc73a2bfd Fix branch mode prompt for /review (#4061)
Updates `/review` branch mode to review against a branch's upstream.
2025-09-22 12:34:08 -07:00
jif-oai
be366a31ab chore: clippy on redundant closure (#4058)
Add redundant closure clippy rules and let Codex fix it by minimising
FQP
2025-09-22 19:30:16 +00:00
Ahmed Ibrahim
c75920a071 Change limits warning copy (#4059) 2025-09-22 18:52:45 +00:00
dedrisian-oai
8daba53808 feat: Add view stack to BottomPane (#4026)
Adds a "View Stack" to the bottom pane to allow for pushing/popping
bottom panels.

`esc` will go back instead of dismissing.

Benefit: We retain the "selection state" of a parent panel (e.g. the
review panel).
2025-09-22 11:29:39 -07:00
Ahmed Ibrahim
d2940bd4c3 Remove /limits after moving to /status (#4055)
Moved to /status #4053
2025-09-22 18:23:05 +00:00
friel-openai
76a9b11678 Tui: fix backtracking (#4020)
Backtracking multiple times could drop earlier turns. We now derive the
active user-turn positions from the transcript on demand (keying off the
latest session header) instead of caching state. This keeps the replayed
context intact during repeated edits and adds a regression test.
2025-09-22 11:16:25 -07:00
Jeremy Rose
fa80bbb587 simplify StreamController (#3928)
no intended functional change, just simplifying the code.
2025-09-22 11:14:04 -07:00
Ahmed Ibrahim
434eb4fd49 Add limits to /status (#4053)
Add limits to status

<img width="579" height="430" alt="image"
src="https://github.com/user-attachments/assets/d3794d92-ffca-47be-8011-b4452223cc89"
/>
2025-09-22 18:13:34 +00:00
Jeremy Rose
19f46439ae timeouts for mcp tool calls (#3959)
defaults to 60sec, overridable with MCP_TOOL_TIMEOUT or on a per-server
basis in the config.
2025-09-22 10:30:59 -07:00
jif-oai
e258ca61b4 chore: more clippy rules 2 (#4057)
The only file to watch is the cargo.toml
All the others come from just fix + a few manual small fix

The set of rules have been taken from the list of clippy rules
arbitrarily while trying to optimise the learning and style of the code
while limiting the loss of productivity
2025-09-22 17:16:02 +00:00
jif-oai
e5fe50d3ce chore: unify cargo versions (#4044)
Unify cargo versions at root
2025-09-22 16:47:01 +00:00
pakrym-oai
14a115d488 Add non_sandbox_test helper (#3880)
Makes tests shorter
2025-09-22 14:50:41 +00:00
dedrisian-oai
5996ee0e5f feat: Add more /review options (#3961)
Adds the following options:

1. Review current changes
2. Review a specific commit
3. Review against a base branch (PR style)
4. Custom instructions

<img width="487" height="330" alt="Screenshot 2025-09-20 at 2 11 36 PM"
src="https://github.com/user-attachments/assets/edb0aaa5-5747-47fa-881f-cc4c4f7fe8bc"
/>

---

\+ Adds the following UI helpers:

1. Makes list selection searchable
2. Adds navigation to the bottom pane, so you could add a stack of
popups
3. Basic custom prompt view
2025-09-21 20:18:35 -07:00
Ahmed Ibrahim
a4ebd069e5 Tui: Rate limits (#3977)
### /limits: show rate limits graph

<img width="442" height="287" alt="image"
src="https://github.com/user-attachments/assets/3e29a241-a4b0-4df8-bf71-43dc4dd805ca"
/>

### Warning on close to rate limits:

<img width="507" height="96" alt="image"
src="https://github.com/user-attachments/assets/732a958b-d240-4a89-8289-caa92de83537"
/>

Based on #3965
2025-09-21 10:20:49 -07:00
Ahmed Ibrahim
04504d8218 Forward Rate limits to the UI (#3965)
We currently get information about rate limits in the response headers.
We want to forward them to the clients to have better transparency.
UI/UX plans have been discussed and this information is needed.
2025-09-20 21:26:16 -07:00
Jeremy Rose
42d335deb8 Cache keyboard enhancement detection before event streams (#3950)
Hopefully fixes incorrectly showing ^J instead of Shift+Enter in the key
hints occasionally.
2025-09-19 21:38:36 +00:00
Jeremy Rose
ad0c2b4db3 don't clear screen on startup (#3925) 2025-09-19 14:22:58 -07:00
Jeremy Rose
ff389dc52f fix alignment in slash command popup (#3937) 2025-09-19 19:08:04 +00:00
pakrym-oai
9b18875a42 Use helpers instead of fixtures (#3888)
Move to using test helper method everywhere.
2025-09-19 06:46:25 -07:00
pakrym-oai
881c7978f1 Move responses mocking helpers to a shared lib (#3878)
These are generally useful
2025-09-18 17:53:14 -07:00
Ahmed Ibrahim
a7fda70053 Use a unified shell tell to not break cache (#3814)
Currently, we change the tool description according to the sandbox
policy and approval policy. This breaks the cache when the user hits
`/approvals`. This PR does the following:
- Always use the shell with escalation parameter:
- removes `create_shell_tool_for_sandbox` and always uses unified tool
via `create_shell_tool`
- Reject the func call when the model uses escalation parameter when it
cannot.
2025-09-19 00:08:28 +00:00
Michael Bolin
de64f5f007 fix: update try_parse_word_only_commands_sequence() to return commands in order (#3881)
Incidentally, we had a test for this in
`accepts_multiple_commands_with_allowed_operators()`, but it was
verifying the bad behavior. Oops!
2025-09-18 16:07:38 -07:00
Michael Bolin
8595237505 fix: ensure cwd for conversation and sandbox are separate concerns (#3874)
Previous to this PR, both of these functions take a single `cwd`:


71038381aa/codex-rs/core/src/seatbelt.rs (L19-L25)


71038381aa/codex-rs/core/src/landlock.rs (L16-L23)

whereas `cwd` and `sandbox_cwd` should be set independently (fixed in
this PR).

Added `sandbox_distinguishes_command_and_policy_cwds()` to
`codex-rs/exec/tests/suite/sandbox.rs` to verify this.
2025-09-18 14:37:06 -07:00
dedrisian-oai
62258df92f feat: /review (#3774)
Adds `/review` action in TUI

<img width="637" height="370" alt="Screenshot 2025-09-17 at 12 41 19 AM"
src="https://github.com/user-attachments/assets/b1979a6e-844a-4b97-ab20-107c185aec1d"
/>
2025-09-18 14:14:16 -07:00
Jeremy Rose
b34e906396 Reland "refactor transcript view to handle HistoryCells" (#3753)
Reland of #3538
2025-09-18 20:55:53 +00:00
Jeremy Rose
71038381aa fix error on missing notifications in [tui] (#3867)
Fixes #3811.
2025-09-18 11:25:09 -07:00
jif-oai
277fc6254e chore: use tokio mutex and async function to prevent blocking a worker (#3850)
### Why Use `tokio::sync::Mutex`

`std::sync::Mutex` are not _async-aware_. As a result, they will block
the entire thread instead of just yielding the task. Furthermore they
can be poisoned which is not the case of `tokio` Mutex.
This allows the Tokio runtime to continue running other tasks while
waiting for the lock, preventing deadlocks and performance bottlenecks.

In general, this is preferred in async environment
2025-09-18 18:21:52 +01:00
jif-oai
992b531180 fix: some nit Rust reference issues (#3849)
Fix some small references issue. No behavioural change. Just making the
code cleaner
2025-09-18 18:18:06 +01:00
Jeremy Rose
84a0ba9bf5 hint for codex resume on tui exit (#3757)
<img width="931" height="438" alt="Screenshot 2025-09-16 at 4 25 19 PM"
src="https://github.com/user-attachments/assets/ccfb8df1-feaf-45b4-8f7f-56100de916d5"
/>
2025-09-18 09:28:32 -07:00
jif-oai
4a5d6f7c71 Make ESC button work when auto-compaction (#3857)
Only emit a task finished when the compaction comes from a `/compact`
2025-09-18 15:34:16 +00:00
jif-oai
1b3c8b8e94 Unify animations (#3729)
Unify the animation in a single code and add the CTRL + . in the
onboarding
2025-09-18 16:27:15 +01:00
pakrym-oai
d4aba772cb Switch to uuid_v7 and tighten ConversationId usage (#3819)
Make sure conversations have a timestamp.
2025-09-18 14:37:03 +00:00
jif-oai
4c97eeb32a bug: Ignore tests for now (#3777)
Ignore flaky / long tests for now
2025-09-18 10:43:45 +01:00
Thibault Sottiaux
c9505488a1 chore: update "Codex CLI harness, sandboxing, and approvals" section (#3822) 2025-09-17 16:48:20 -07:00
Jeremy Rose
530382db05 Use agent reply text in turn notifications (#3756)
Instead of "Agent turn complete", turn-complete notifications now
include the first handful of chars from the agent's final message.
2025-09-17 11:23:46 -07:00
Abhishek Bhardwaj
208089e58e AGENTS.md: Add instruction to install missing commands (#3807)
This change instructs the model to install any missing command. Else
tokens are wasted when it tries to run
commands that aren't available multiple times before installing them.
2025-09-17 11:06:59 -07:00
Michael Bolin
e5fdb5b0fd fix: specify --repo when calling gh (#3806)
Often, `gh` infers `--repo` when it is run from a Git clone, but our
`publish-npm` step is designed to avoid the overhead of cloning the
repo, so add the `--repo` option explicitly to fix things.
2025-09-17 11:05:22 -07:00
Michael Bolin
5332f6e215 fix: make publish-npm its own job with specific permissions (#3767)
The build for `v0.37.0-alpha.3` failed on the `Create GitHub Release`
step:

https://github.com/openai/codex/actions/runs/17786866086/job/50556513221

with:

```
⚠️ GitHub release failed with status: 403
{"message":"Resource not accessible by integration","documentation_url":"https://docs.github.com/rest/releases/releases#create-a-release","status":"403"}
Skip retry — your GitHub token/PAT does not have the required permission to create a release
```

I believe I should have not introduced a top-level `permissions` for the
workflow in https://github.com/openai/codex/pull/3431 because that
affected the `permissions` for each job in the workflow.

This PR introduces `publish-npm` as its own job, which allows us to:

- consolidate all the Node.js-related steps required for publishing
- limit the reach of the `id-token: write` permission
- skip it altogether if is an alpha build

With this PR, each of `release`, `publish-npm`, and `update-branch` has
an explicit `permissions` block.
2025-09-16 22:55:53 -07:00
Michael Bolin
5d87f5d24a fix: ensure pnpm is installed before running npm install (#3763)
Note we do the same thing in `ci.yml`:


791d7b125f/.github/workflows/ci.yml (L17-L25)
2025-09-16 21:36:13 -07:00
Michael Bolin
791d7b125f fix: make GitHub Action publish to npm using trusted publishing (#3431) 2025-09-16 20:33:59 -07:00
dedrisian-oai
72733e34c4 Add dev message upon review out (#3758)
Proposal: We want to record a dev message like so:

```
{
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "<user_action>
  <context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
  <action>review</action>
  <results>
  {findings_str}
  </results>
</user_action>"
        }
      ]
    },
```

Without showing in the chat transcript.

Rough idea, but it fixes issue where the user finishes a review thread,
and asks the parent "fix the rest of the review issues" thinking that
the parent knows about it.

### Question: Why not a tool call?

Because the agent didn't make the call, it was a human. + we haven't
implemented sub-agents yet, and we'll need to think about the way we
represent these human-led tool calls for the agent.
2025-09-16 18:43:32 -07:00
Jeremy Rose
b8d2b1a576 restyle thinking outputs (#3755)
<img width="1205" height="930" alt="Screenshot 2025-09-16 at 2 23 18 PM"
src="https://github.com/user-attachments/assets/bb2494f1-dd59-4bc9-9c4e-740605c999fd"
/>
2025-09-16 16:42:43 -07:00
dedrisian-oai
7fe4021f95 Review mode core updates (#3701)
1. Adds the environment prompt (including cwd) to review thread
2. Prepends the review prompt as a user message (temporary fix so the
instructions are not replaced on backend)
3. Sets reasoning to low
4. Sets default review model to `gpt-5-codex`
2025-09-16 13:36:51 -07:00
Dylan
11285655c4 fix: Record EnvironmentContext in SendUserTurn (#3678)
## Summary
SendUserTurn has not been correctly handling updates to policies. While
the tui protocol handles this in `Op::OverrideTurnContext`, the
SendUserTurn should be appending `EnvironmentContext` messages when the
sandbox settings change. MCP client behavior should match the cli
behavior, so we update `SendUserTurn` message to match.

## Testing
- [x] Added prompt caching tests
2025-09-16 11:32:20 -07:00
Ahmed Ibrahim
244687303b Persist search items (#3745)
Let's record the search items because they are part of the history.
2025-09-16 18:02:15 +00:00
pakrym-oai
5e2c4f7e35 Update azure model provider example (#3680)
Make the section linkable.
2025-09-16 08:43:29 -07:00
Dylan
a8026d3846 fix: read-only escalations (#3673)
## Summary
Splitting out this smaller fix from #2694 - fixes the sandbox
permissions so Chat / read-only mode tool definition matches
expectations

## Testing 
- [x] Tested locally

<img width="1271" height="629" alt="Screenshot 2025-09-15 at 2 51 19 PM"
src="https://github.com/user-attachments/assets/fcb247e4-30b6-4199-80d7-a2876d79ad7d"
/>
2025-09-15 19:01:10 -07:00
easong-openai
45bccd36b0 fix permissions alignment 2025-09-15 17:34:04 -07:00
dependabot[bot]
404c126fc3 chore(deps): bump wildmatch from 2.4.0 to 2.5.0 in /codex-rs (#3619)
Bumps [wildmatch](https://github.com/becheran/wildmatch) from 2.4.0 to
2.5.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/becheran/wildmatch/releases">wildmatch's
releases</a>.</em></p>
<blockquote>
<h2>v2.5.0</h2>
<p><a
href="https://redirect.github.com/becheran/wildmatch/pull/27">becheran/wildmatch#27</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="b39902c120"><code>b39902c</code></a>
chore: Release wildmatch version 2.5.0</li>
<li><a
href="87a8cf4c80"><code>87a8cf4</code></a>
Merge pull request <a
href="https://redirect.github.com/becheran/wildmatch/issues/28">#28</a>
from smichaku/micha/fix-unicode-case-insensitive-matching</li>
<li><a
href="a3ab4903f5"><code>a3ab490</code></a>
fix: Fix unicode matching for non-ASCII characters</li>
<li>See full diff in <a
href="https://github.com/becheran/wildmatch/compare/v2.4.0...v2.5.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=wildmatch&package-manager=cargo&previous-version=2.4.0&new-version=2.5.0)](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>
2025-09-15 12:57:17 -07:00
dependabot[bot]
88027552dd chore(deps): bump serde from 1.0.219 to 1.0.223 in /codex-rs (#3618)
Bumps [serde](https://github.com/serde-rs/serde) from 1.0.219 to
1.0.223.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/serde/releases">serde's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.223</h2>
<ul>
<li>Fix serde_core documentation links (<a
href="https://redirect.github.com/serde-rs/serde/issues/2978">#2978</a>)</li>
</ul>
<h2>v1.0.222</h2>
<ul>
<li>Make <code>serialize_with</code> attribute produce code that works
if respanned to 2024 edition (<a
href="https://redirect.github.com/serde-rs/serde/issues/2950">#2950</a>,
thanks <a href="https://github.com/aytey"><code>@​aytey</code></a>)</li>
</ul>
<h2>v1.0.221</h2>
<ul>
<li>Documentation improvements (<a
href="https://redirect.github.com/serde-rs/serde/issues/2973">#2973</a>)</li>
<li>Deprecate <code>serde_if_integer128!</code> macro (<a
href="https://redirect.github.com/serde-rs/serde/issues/2975">#2975</a>)</li>
</ul>
<h2>v1.0.220</h2>
<ul>
<li>Add a way for data formats to depend on serde traits without waiting
for serde_derive compilation: <a
href="https://docs.rs/serde_core">https://docs.rs/serde_core</a> (<a
href="https://redirect.github.com/serde-rs/serde/issues/2608">#2608</a>,
thanks <a
href="https://github.com/osiewicz"><code>@​osiewicz</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="6c316d7cb5"><code>6c316d7</code></a>
Release 1.0.223</li>
<li><a
href="a4ac0c2bc6"><code>a4ac0c2</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2978">#2978</a>
from dtolnay/htmlrooturl</li>
<li><a
href="ed76364f87"><code>ed76364</code></a>
Change serde_core's html_root_url to docs.rs/serde_core</li>
<li><a
href="57e21a1afa"><code>57e21a1</code></a>
Release 1.0.222</li>
<li><a
href="bb58726133"><code>bb58726</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2950">#2950</a>
from aytey/fix_lifetime_issue_2024</li>
<li><a
href="3f6925125b"><code>3f69251</code></a>
Delete unneeded field of MapDeserializer</li>
<li><a
href="fd4decf2fe"><code>fd4decf</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2976">#2976</a>
from dtolnay/content</li>
<li><a
href="00b1b6b2b5"><code>00b1b6b</code></a>
Move Content's Deserialize impl from serde_core to serde</li>
<li><a
href="cf141aa8c7"><code>cf141aa</code></a>
Move Content's Clone impl from serde_core to serde</li>
<li><a
href="ff3aee490a"><code>ff3aee4</code></a>
Release 1.0.221</li>
<li>Additional commits viewable in <a
href="https://github.com/serde-rs/serde/compare/v1.0.219...v1.0.223">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=serde&package-manager=cargo&previous-version=1.0.219&new-version=1.0.223)](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>
2025-09-15 12:56:20 -07:00
Michael Bolin
ca8bd09d56 chore: simplify dep so serde=1 in Cargo.toml (#3664)
With this change, dependabot should just have to update `Cargo.lock` for
`serde`, e.g.:

- https://github.com/openai/codex/pull/3617
- https://github.com/openai/codex/pull/3618
2025-09-15 19:22:29 +00:00
dependabot[bot]
39ed8a7d26 chore(deps): bump serde_json from 1.0.143 to 1.0.145 in /codex-rs (#3617)
Bumps [serde_json](https://github.com/serde-rs/json) from 1.0.143 to
1.0.145.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/json/releases">serde_json's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.145</h2>
<ul>
<li>Raise serde version requirement to &gt;=1.0.220</li>
</ul>
<h2>v1.0.144</h2>
<ul>
<li>Switch serde dependency to serde_core (<a
href="https://redirect.github.com/serde-rs/json/issues/1285">#1285</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="efa66e3a1d"><code>efa66e3</code></a>
Release 1.0.145</li>
<li><a
href="23679e2b9d"><code>23679e2</code></a>
Add serde version constraint</li>
<li><a
href="fc27bafbf7"><code>fc27baf</code></a>
Release 1.0.144</li>
<li><a
href="caef3c6ea6"><code>caef3c6</code></a>
Ignore uninlined_format_args pedantic clippy lint</li>
<li><a
href="81ba3aaaff"><code>81ba3aa</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1285">#1285</a>
from dtolnay/serdecore</li>
<li><a
href="d21e8ce7a7"><code>d21e8ce</code></a>
Switch serde dependency to serde_core</li>
<li><a
href="6beb6cd596"><code>6beb6cd</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1286">#1286</a>
from dtolnay/up</li>
<li><a
href="1dbc803749"><code>1dbc803</code></a>
Raise required compiler to Rust 1.61</li>
<li><a
href="0bf5d87003"><code>0bf5d87</code></a>
Enforce trybuild &gt;= 1.0.108</li>
<li><a
href="d12e943590"><code>d12e943</code></a>
Update actions/checkout@v4 -&gt; v5</li>
<li>See full diff in <a
href="https://github.com/serde-rs/json/compare/v1.0.143...v1.0.145">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=serde_json&package-manager=cargo&previous-version=1.0.143&new-version=1.0.145)](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>
2025-09-15 11:58:57 -07:00
Michael Bolin
2df7f7efe5 chore: restore prerelease logic in rust-release.yml (#3659)
Revert #3645.
2025-09-15 17:52:49 +00:00
Jeremy Rose
0560079c41 notifications on approvals and turn end (#3329)
uses OSC 9 to notify when a turn ends or approval is required. won't
work in vs code or terminal.app but iterm2/kitty/wezterm supports it :)
2025-09-15 10:22:02 -07:00
Michael Bolin
0de154194d fix: change MIN_ANIMATION_HEIGHT so show_animation is calculated correctly (#3656)
Reported height was `20` instead of `21`, so `area.height >=
MIN_ANIMATION_HEIGHT` was `false` and therefore `show_animation` was
`false`, so the animation never displayed.
2025-09-15 10:02:53 -07:00
ae
5c583fe89b feat: tweak onboarding strings (#3650) 2025-09-15 08:49:37 -07:00
easong-openai
cf63cbf153 fix stray login url characters persisting in login (#3639)
<img width="885" height="177" alt="image"
src="https://github.com/user-attachments/assets/d396e0a5-f303-494f-bab1-f7af57b88a3e"
/>


Fixes this.
2025-09-15 15:44:53 +00:00
pakrym-oai
b1c291e2bb Add file reference guidelines to gpt-5 prompt (#3651) 2025-09-15 08:35:30 -07:00
Thibault Sottiaux
934d728946 feat: skip animations on small terminals (#3647)
Changes:
- skip the welcome animation when the terminal area is below 60x21
- skip the model upgrade animation when the terminal area is below 60x24
to avoid clipping

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-09-15 08:30:32 -07:00
Michael Bolin
f037b2fd56 chore: rename (#3648) 2025-09-15 08:17:13 -07:00
Thibault Sottiaux
d60cbed691 fix: add references (#3633) 2025-09-15 07:48:22 -07:00
Michael Bolin
6aafe37752 chore: set prerelease:true for now (#3645) 2025-09-15 07:17:46 -07:00
jimmyfraiture2
d555b68469 fix: race condition unified exec (#3644)
Fix race condition without storing an rx in the session
2025-09-15 06:52:39 -07:00
ae
9baa5c33da feat: update splash (#3631)
- Update splash styling.
- Add center truncation for long paths.
  (Uses new `center_truncate_path` utility.)
- Update the suggested commands.


## New splash
<img width="560" height="326" alt="image"
src="https://github.com/user-attachments/assets/b80d7075-f376-4019-a464-b96a78b0676d"
/>

## Example with truncation:
<img width="524" height="317" alt="image"
src="https://github.com/user-attachments/assets/b023c5cc-0bf0-4d21-9b98-bfea85546eda"
/>
2025-09-15 06:44:40 -07:00
dependabot[bot]
fdf4a68646 chore(deps): bump tracing-subscriber from 0.3.19 to 0.3.20 in /codex-rs (#3620)
Bumps [tracing-subscriber](https://github.com/tokio-rs/tracing) from
0.3.19 to 0.3.20.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/tracing/releases">tracing-subscriber's
releases</a>.</em></p>
<blockquote>
<h2>tracing-subscriber 0.3.20</h2>
<p><strong>Security Fix</strong>: ANSI Escape Sequence Injection
(CVE-TBD)</p>
<h2>Impact</h2>
<p>Previous versions of tracing-subscriber were vulnerable to ANSI
escape sequence injection attacks. Untrusted user input containing ANSI
escape sequences could be injected into terminal output when logged,
potentially allowing attackers to:</p>
<ul>
<li>Manipulate terminal title bars</li>
<li>Clear screens or modify terminal display</li>
<li>Potentially mislead users through terminal manipulation</li>
</ul>
<p>In isolation, impact is minimal, however security issues have been
found in terminal emulators that enabled an attacker to use ANSI escape
sequences via logs to exploit vulnerabilities in the terminal
emulator.</p>
<h2>Solution</h2>
<p>Version 0.3.20 fixes this vulnerability by escaping ANSI control
characters in when writing events to destinations that may be printed to
the terminal.</p>
<h2>Affected Versions</h2>
<p>All versions of tracing-subscriber prior to 0.3.20 are affected by
this vulnerability.</p>
<h2>Recommendations</h2>
<p>Immediate Action Required: We recommend upgrading to
tracing-subscriber 0.3.20 immediately, especially if your
application:</p>
<ul>
<li>Logs user-provided input (form data, HTTP headers, query parameters,
etc.)</li>
<li>Runs in environments where terminal output is displayed to
users</li>
</ul>
<h2>Migration</h2>
<p>This is a patch release with no breaking API changes. Simply update
your Cargo.toml:</p>
<pre lang="toml"><code>[dependencies]
tracing-subscriber = &quot;0.3.20&quot;
</code></pre>
<h2>Acknowledgments</h2>
<p>We would like to thank <a href="http://github.com/zefr0x">zefr0x</a>
who responsibly reported the issue at
<code>security@tokio.rs</code>.</p>
<p>If you believe you have found a security vulnerability in any
tokio-rs project, please email us at <code>security@tokio.rs</code>.</p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="4c52ca5266"><code>4c52ca5</code></a>
fmt: fix ANSI escape sequence injection vulnerability (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3368">#3368</a>)</li>
<li><a
href="f71cebe41e"><code>f71cebe</code></a>
subscriber: impl Clone for EnvFilter (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3360">#3360</a>)</li>
<li><a
href="3a1f571102"><code>3a1f571</code></a>
Fix CI (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3361">#3361</a>)</li>
<li><a
href="e63ef57f3d"><code>e63ef57</code></a>
chore: prepare tracing-attributes 0.1.30 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3316">#3316</a>)</li>
<li><a
href="6e59a13b1a"><code>6e59a13</code></a>
attributes: fix tracing::instrument regression around shadowing (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3311">#3311</a>)</li>
<li><a
href="e4df761275"><code>e4df761</code></a>
tracing: update core to 0.1.34 and attributes to 0.1.29 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3305">#3305</a>)</li>
<li><a
href="643f392ebb"><code>643f392</code></a>
chore: prepare tracing-attributes 0.1.29 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3304">#3304</a>)</li>
<li><a
href="d08e7a6eea"><code>d08e7a6</code></a>
chore: prepare tracing-core 0.1.34 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3302">#3302</a>)</li>
<li><a
href="6e70c571d3"><code>6e70c57</code></a>
tracing-subscriber: count numbers of enters in <code>Timings</code> (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/2944">#2944</a>)</li>
<li><a
href="c01d4fd9de"><code>c01d4fd</code></a>
fix docs and enable CI on <code>main</code> branch (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3295">#3295</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/tokio-rs/tracing/compare/tracing-subscriber-0.3.19...tracing-subscriber-0.3.20">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=tracing-subscriber&package-manager=cargo&previous-version=0.3.19&new-version=0.3.20)](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>
2025-09-15 00:51:33 -07:00
dependabot[bot]
adc9e1526b chore(deps): bump slab from 0.4.10 to 0.4.11 in /codex-rs (#3635)
Bumps [slab](https://github.com/tokio-rs/slab) from 0.4.10 to 0.4.11.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/slab/releases">slab's
releases</a>.</em></p>
<blockquote>
<h2>v0.4.11</h2>
<ul>
<li>Fix <code>Slab::get_disjoint_mut</code> out of bounds (<a
href="https://redirect.github.com/tokio-rs/slab/issues/152">#152</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/slab/blob/master/CHANGELOG.md">slab's
changelog</a>.</em></p>
<blockquote>
<h1>0.4.11 (August 8, 2025)</h1>
<ul>
<li>Fix <code>Slab::get_disjoint_mut</code> out of bounds (<a
href="https://redirect.github.com/tokio-rs/slab/issues/152">#152</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="2e5779f8eb"><code>2e5779f</code></a>
Release v0.4.11 (<a
href="https://redirect.github.com/tokio-rs/slab/issues/153">#153</a>)</li>
<li><a
href="2d65c514bc"><code>2d65c51</code></a>
Fix get_disjoint_mut error condition (<a
href="https://redirect.github.com/tokio-rs/slab/issues/152">#152</a>)</li>
<li>See full diff in <a
href="https://github.com/tokio-rs/slab/compare/v0.4.10...v0.4.11">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=slab&package-manager=cargo&previous-version=0.4.10&new-version=0.4.11)](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)
You can disable automated security fix PRs for this repo from the
[Security Alerts page](https://github.com/openai/codex/network/alerts).

</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-09-15 00:48:53 -07:00
Ed Bayes
b9af1d2b16 Login flow polish (#3632)
# Description
- Update sign in flow

# Tests
- Passes CI

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-09-15 00:42:53 -07:00
Ahmed Ibrahim
2d52e3b40a Fix codex resume so flags (cd, model, search, etc.) still work (#3625)
Bug: now we can add flags/config values only before resume. 

`codex -m gpt-5 resume` works

However, `codex resume -m gpt-5` should also work.

This PR is following this
[approach](https://stackoverflow.com/questions/76408952/rust-clap-re-use-same-arguments-in-different-subcommand)
in doing so.

I didn't convert those flags to global because we have `codex login`
that shouldn't expect them.
2025-09-15 06:16:17 +00:00
Thibault Sottiaux
6039f8a126 feat: tighten preset filter, tame storage load logs, enable rollout prompt by default (#3628)
Summary
- common: use exact equality for Swiftfox exclusion to avoid hiding
future slugs that merely contain the substring
- core: treat missing internal_storage.json as expected (debug), warn
only on real IO/parse errors
- tui: drop DEBUG_HIGH gate; always consider showing rollout prompt, but
suppress under ApiKey auth mode
2025-09-14 23:05:41 -07:00
Ahmed Ibrahim
50262a44ce Show abort in the resume (#3629)
Show abort error when resuming a session
2025-09-15 05:24:30 +00:00
Ed Bayes
839b2ae7cf Change animation frames (#3627)
## Description
- Changes animation frames to be smaller
- Cleans up file names and popup logic

## tests
- Passes local CI
2025-09-15 04:36:34 +00:00
easong-openai
6a8e743d57 initial mcp add interface (#3543)
Adds `codex mcp add`, `codex mcp list`, `codex mcp remove`. Currently writes to global config.
2025-09-15 04:30:56 +00:00
Thibault Sottiaux
a797051921 chore: update swiftfox_prompt.md (#3624) 2025-09-15 04:10:35 +00:00
Thibault Sottiaux
d7d9d96d6c feat: add reasoning level to header (#3622) 2025-09-15 03:59:22 +00:00
Ahmed Ibrahim
26f1246a89 Revert "refactor transcript view to handle HistoryCells" (#3614)
Reverts openai/codex#3538
It panics on forking first message. It also calculates the index in a
wrong way.
2025-09-15 03:39:36 +00:00
Ahmed Ibrahim
6581da9b57 Show the header when resuming a conversation (#3615) 2025-09-15 03:31:08 +00:00
Eric Traut
900bb01486 When logging in using ChatGPT, make sure to overwrite API key (#3611)
When logging in using ChatGPT using the `codex login` command, a
successful login should write a new `auth.json` file with the ChatGPT
token information. The old code attempted to retain the API key and
merge the token information into the existing `auth.json` file. With the
new simplified login mechanism, `auth.json` should have auth information
for only ChatGPT or API Key, not both.

The `codex login --api-key <key>` code path was already doing the right
thing here, but the `codex login` command was incorrect. This PR fixes
the problem and adds test cases for both commands.
2025-09-14 19:48:18 -07:00
Ahmed Ibrahim
2ad6a37192 Don't show the model for apikey (#3607) 2025-09-15 01:32:18 +00:00
Eric Traut
e5dd7f0934 Fix get_auth_status response when using custom provider (#3581)
This PR addresses an edge-case bug that appears in the VS Code extension
in the following situation:
1. Log in using ChatGPT (using either the CLI or extension). This will
create an `auth.json` file.
2. Manually modify `config.toml` to specify a custom provider.
3. Start a fresh copy of the VS Code extension.

The profile menu in the VS Code extension will indicate that you are
logged in using ChatGPT even though you're not.

This is caused by the `get_auth_status` method returning an
`auth_method: 'chatgpt'` when a custom provider is configured and it
doesn't use OpenAI auth (i.e. `requires_openai_auth` is false). The
method should always return `auth_method: None` if
`requires_openai_auth` is false.

The same bug also causes the NUX (new user experience) screen to be
displayed in the VSCE in this situation.
2025-09-14 18:27:02 -07:00
Dylan
b6673838e8 fix: model family and apply_patch consistency (#3603)
## Summary
Resolves a merge conflict between #3597 and #3560, and adds tests to
double check our apply_patch configuration.

## Testing
- [x] Added unit tests

---------

Co-authored-by: dedrisian-oai <dedrisian@openai.com>
2025-09-14 18:20:37 -07:00
Fouad Matin
1823906215 fix(tui): update full-auto to default preset (#3608)
Update `--full-auto` to use default preset
2025-09-14 18:14:11 -07:00
Fouad Matin
5185d69f13 fix(core): flaky test completed_commands_do_not_persist_sessions (#3596)
Fix flaky test:
```
        FAIL [   2.641s] codex-core unified_exec::tests::completed_commands_do_not_persist_sessions
  stdout ───

    running 1 test
    test unified_exec::tests::completed_commands_do_not_persist_sessions ... FAILED

    failures:

    failures:
        unified_exec::tests::completed_commands_do_not_persist_sessions

    test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 235 filtered out; finished in 2.63s
    
  stderr ───

    thread 'unified_exec::tests::completed_commands_do_not_persist_sessions' panicked at core/src/unified_exec/mod.rs:582:9:
    assertion failed: result.output.contains("codex")
```
2025-09-14 18:04:05 -07:00
pakrym-oai
4dffa496ac Skip frames files in codespell (#3606)
Fixes CI
2025-09-14 18:00:23 -07:00
Ahmed Ibrahim
ce984b2c71 Add session header to chat widget (#3592)
<img width="570" height="332" alt="image"
src="https://github.com/user-attachments/assets/ca6dfcb0-f3a1-4b3e-978d-4f844ba77527"
/>
2025-09-14 17:53:50 -07:00
pakrym-oai
c47febf221 Append full raw reasoning event text (#3605)
We don't emit correct delta events and only get full reasoning back.
Append it to history.
2025-09-14 17:50:06 -07:00
jimmyfraiture2
76c37c5493 feat: UI animation (#3590)
Add NUX animation

---------

Co-authored-by: Thibault Sottiaux <tibo@openai.com>
2025-09-14 17:42:17 -07:00
dedrisian-oai
2aa84b8891 Fix EventMsg Optional (#3604) 2025-09-15 00:34:33 +00:00
pakrym-oai
9177bdae5e Only one branch for swiftfox (#3601)
Make each model family have a single branch.
2025-09-14 16:56:22 -07:00
Ahmed Ibrahim
a30e5e40ee enable-resume (#3537)
Adding the ability to resume conversations.
we have one verb `resume`. 

Behavior:

`tui`:
`codex resume`: opens session picker
`codex resume --last`: continue last message
`codex resume <session id>`: continue conversation with `session id`

`exec`:
`codex resume --last`: continue last conversation
`codex resume <session id>`: continue conversation with `session id`

Implementation:
- I added a function to find the path in `~/.codex/sessions/` with a
`UUID`. This is helpful in resuming with session id.
- Added the above mentioned flags
- Added lots of testing
2025-09-14 19:33:19 -04:00
jimmyfraiture2
99e1d33bd1 feat: update model save (#3589)
Edit model save to save by default as global or on the profile depending
on the session
2025-09-14 16:25:43 -07:00
dedrisian-oai
b2f6fc3b9a Fix flaky windows test (#3564)
There are exactly 4 types of flaky tests in Windows x86 right now:

1. `review_input_isolated_from_parent_history` => Times out waiting for
closing events
2. `review_does_not_emit_agent_message_on_structured_output` => Times
out waiting for closing events
3. `auto_compact_runs_after_token_limit_hit` => Times out waiting for
closing events
4. `auto_compact_runs_after_token_limit_hit` => Also has a problem where
auto compact should add a third request, but receives 4 requests.

1, 2, and 3 seem to be solved with increasing threads on windows runner
from 2 -> 4.

Don't know yet why # 4 is happening, but probably also because of
WireMock issues on windows causing races.
2025-09-14 23:20:25 +00:00
pakrym-oai
51f88fd04a Fix swiftfox model selector (#3598)
The model shouldn't be saved with a suffix. The effort is a separate
field.
2025-09-14 23:12:21 +00:00
pakrym-oai
916fdc2a37 Add per-model-family prompts (#3597)
Allows more flexibility in defining prompts.
2025-09-14 22:45:15 +00:00
pakrym-oai
863d9c237e Include command output when sending timeout to model (#3576)
Being able to see the output helps the model decide how to handle the
timeout.
2025-09-14 14:38:26 -07:00
Ahmed Ibrahim
7e1543f5d8 Align user history message prefix width (#3467)
<img width="798" height="340" alt="image"
src="https://github.com/user-attachments/assets/fdd63f40-9c94-4e3a-bce5-2d2f333a384f"
/>
2025-09-14 20:51:08 +00:00
Ahmed Ibrahim
d701eb32d7 Gate model upgrade prompt behind ChatGPT auth (#3586)
- refresh the login_state after onboarding.
- should be on chatgpt for upgrade
2025-09-14 13:08:24 -07:00
Michael Bolin
9baae77533 chore: update output_lines() to take a struct instead of a sequence of bools (#3591)
I found the boolean literals hard to follow.
2025-09-14 13:07:38 -07:00
Ahmed Ibrahim
e932722292 Add spacing before queued status indicator messages (#3474)
<img width="687" height="174" alt="image"
src="https://github.com/user-attachments/assets/e68f5a29-cb2d-4aa6-9cbd-f492878d8d0a"
/>
2025-09-14 15:37:28 -04:00
Ahmed Ibrahim
bbea6bbf7e Handle resuming/forking after compact (#3533)
We need to construct the history different when compact happens. For
this, we need to just consider the history after compact and convert
compact to a response item.

This needs to change and use `build_compact_history` when this #3446 is
merged.
2025-09-14 13:23:31 +00:00
Jeremy Rose
4891ee29c5 refactor transcript view to handle HistoryCells (#3538)
No (intended) functional change.

This refactors the transcript view to hold a list of HistoryCells
instead of a list of Lines. This simplifies and makes much of the logic
more robust, as well as laying the groundwork for future changes, e.g.
live-updating history cells in the transcript.

Similar to #2879 in goal. Fixes #2755.
2025-09-13 19:23:14 -07:00
Thibault Sottiaux
bac8a427f3 chore: default swiftfox models to experimental reasoning summaries (#3560) 2025-09-13 23:40:54 +00:00
Thibault Sottiaux
14ab1063a7 chore: rename 2025-09-12 23:17:41 -07:00
Thibault Sottiaux
a77364bbaa chore: remove descriptions 2025-09-12 22:55:40 -07:00
Thibault Sottiaux
19b4ed3c96 w 2025-09-12 22:44:05 -07:00
pakrym-oai
3d4acbaea0 Preserve IDs for more item types in azure (#3542)
https://github.com/openai/codex/issues/3509
2025-09-13 01:09:56 +00:00
pakrym-oai
414b8be8b6 Always request encrypted cot (#3539)
Otherwise future requests will fail with 500
2025-09-12 23:51:30 +00:00
dedrisian-oai
90a0fd342f Review Mode (Core) (#3401)
## 📝 Review Mode -- Core

This PR introduces the Core implementation for Review mode:

- New op `Op::Review { prompt: String }:` spawns a child review task
with isolated context, a review‑specific system prompt, and a
`Config.review_model`.
- `EnteredReviewMode`: emitted when the child review session starts.
Every event from this point onwards reflects the review session.
- `ExitedReviewMode(Option<ReviewOutputEvent>)`: emitted when the review
finishes or is interrupted, with optional structured findings:

```json
{
  "findings": [
    {
      "title": "<≤ 80 chars, imperative>",
      "body": "<valid Markdown explaining *why* this is a problem; cite files/lines/functions>",
      "confidence_score": <float 0.0-1.0>,
      "priority": <int 0-3>,
      "code_location": {
        "absolute_file_path": "<file path>",
        "line_range": {"start": <int>, "end": <int>}
      }
    }
  ],
  "overall_correctness": "patch is correct" | "patch is incorrect",
  "overall_explanation": "<1-3 sentence explanation justifying the overall_correctness verdict>",
  "overall_confidence_score": <float 0.0-1.0>
}
```

## Questions

### Why separate out its own message history?

We want the review thread to match the training of our review models as
much as possible -- that means using a custom prompt, removing user
instructions, and starting a clean chat history.

We also want to make sure the review thread doesn't leak into the parent
thread.

### Why do this as a mode, vs. sub-agents?

1. We want review to be a synchronous task, so it's fine for now to do a
bespoke implementation.
2. We're still unclear about the final structure for sub-agents. We'd
prefer to land this quickly and then refactor into sub-agents without
rushing that implementation.
2025-09-12 23:25:10 +00:00
jif-oai
8d56d2f655 fix: NIT None reasoning effort (#3536)
Fix the reasoning effort not being set to None in the UI
2025-09-12 21:17:49 +00:00
jif-oai
8408f3e8ed Fix NUX UI (#3534)
Fix NUX UI
2025-09-12 14:09:31 -07:00
Jeremy Rose
b8ccfe9b65 core: expand default sandbox (#3483)
this adds some more capabilities to the default sandbox which I feel are
safe. Most are in the
[renderer.sb](https://source.chromium.org/chromium/chromium/src/+/main:sandbox/policy/mac/renderer.sb)
sandbox for chrome renderers, which i feel is fair game for codex
commands.

Specific changes:

1. Allow processes in the sandbox to send signals to any other process
in the same sandbox (e.g. child processes or daemonized processes),
instead of just themselves.
2. Allow user-preference-read
3. Allow process-info* to anything in the same sandbox. This is a bit
wider than Chromium allows, but it seems OK to me to allow anything in
the sandbox to get details about other processes in the same sandbox.
Bazel uses these to e.g. wait for another process to exit.
4. Allow all CPU feature detection, this seems harmless to me. It's
wider than Chromium, but Chromium is concerned about fingerprinting, and
tightly controls what CPU features they actually care about, and we
don't have either that restriction or that advantage.
5. Allow new sysctl-reads:
   ```
     (sysctl-name "vm.loadavg")
     (sysctl-name-prefix "kern.proc.pgrp.")
     (sysctl-name-prefix "kern.proc.pid.")
     (sysctl-name-prefix "net.routetable.")
   ```
bazel needs these for waiting on child processes and for communicating
with its local build server, i believe. I wonder if we should just allow
all (sysctl-read), as reading any arbitrary info about the system seems
fine to me.
6. Allow iokit-open on RootDomainUserClient. This has to do with power
management I believe, and Chromium allows renderers to do this, so okay.
Bazel needs it to boot successfully, possibly for sleep/wake callbacks?
7. Mach lookup to `com.apple.system.opendirectoryd.libinfo`, which has
to do with user data, and which Chrome allows.
8. Mach lookup to `com.apple.PowerManagement.control`. Chromium allows
its GPU process to do this, but not its renderers. Bazel needs this to
boot, probably relatedly to sleep/wake stuff.
2025-09-12 14:03:02 -07:00
pakrym-oai
e3c6903199 Add Azure Responses API workaround (#3528)
Azure Responses API doesn't work well with store:false and response
items.

If store = false and id is sent an error is thrown that ID is not found
If store = false and id is not sent an error is thrown that ID is
required

Add detection for Azure urls and add a workaround to preserve reasoning
item IDs and send store:true
2025-09-12 13:52:15 -07:00
Jeremy Rose
5f6e95b592 if a command parses as a patch, do not attempt to run it (#3382)
sometimes the model forgets to actually invoke `apply_patch` and puts a
patch as the script body. trying to execute this as bash sometimes
creates files named `,` or `{` or does other unknown things, so catch
this situation and return an error to the model.
2025-09-12 13:47:41 -07:00
Ahmed Ibrahim
a2e9cc5530 Update interruption error message styling (#3470)
<img width="497" height="76" alt="image"
src="https://github.com/user-attachments/assets/a1ad279d-1d01-41cd-ac14-b3343a392563"
/>

<img width="493" height="74" alt="image"
src="https://github.com/user-attachments/assets/baf487ba-430e-40fe-8944-2071ec052962"
/>
2025-09-12 16:17:02 -04:00
jif-oai
ea225df22e feat: context compaction (#3446)
## Compact feature:
1. Stops the model when the context window become too large
2. Add a user turn, asking for the model to summarize
3. Build a bridge that contains all the previous user message + the
summary. Rendered from a template
4. Start sampling again from a clean conversation with only that bridge
2025-09-12 13:07:10 -07:00
Ahmed Ibrahim
d4848e558b Add spacing before composer footer hints (#3469)
<img width="647" height="82" alt="image"
src="https://github.com/user-attachments/assets/867eb5d9-3076-4018-846e-260a50408185"
/>
2025-09-12 15:31:24 -04:00
Ahmed Ibrahim
1a6a95fb2a Add spacing between dropdown headers and items (#3472)
<img width="927" height="194" alt="image"
src="https://github.com/user-attachments/assets/f4cb999b-16c3-448a-aed4-060bed8b96dd"
/>

<img width="1246" height="205" alt="image"
src="https://github.com/user-attachments/assets/5d9ba5bd-0c02-46da-a809-b583a176528a"
/>
2025-09-12 15:31:15 -04:00
jif-oai
c6fd056aa6 feat: reasoning effort as optional (#3527)
Allow the reasoning effort to be optional
2025-09-12 12:06:33 -07:00
Michael Bolin
abdcb40f4c feat: change the behavior of SetDefaultModel RPC so None clears the value. (#3529)
It turns out that we want slightly different behavior for the
`SetDefaultModel` RPC because some models do not work with reasoning
(like GPT-4.1), so we should be able to explicitly clear this value.

Verified in `codex-rs/mcp-server/tests/suite/set_default_model.rs`.
2025-09-12 11:35:51 -07:00
Dylan
4ae6b9787a standardize shell description (#3514)
## Summary
Standardizes the shell description across sandbox_types, since we cover
this in the prompt, and have moved necessary details (like
network_access and writeable workspace roots) to EnvironmentContext
messages.

## Test Plan
- [x] updated unit tests
2025-09-12 14:24:09 -04:00
jif-oai
bba567cee9 bug: fix model save (#3525)
Fix those 2 behaviors:
1. The model does not get saved if we don't CTRL + S
2. The reasoning effort get saved
2025-09-12 10:38:12 -07:00
Ahmed Ibrahim
ba6af23cb6 Add spacing to timer duration formats (#3471)
<img width="426" height="28" alt="image"
src="https://github.com/user-attachments/assets/b281aca3-3c8d-4b88-a017-5d2f8ea9f3d5"
/>
2025-09-12 12:05:57 -04:00
Charlie Weems
f805d17930 MCP Documentation Changes Requests in Code Review (#3507)
Add in review changes from @bolinfest that were dropped due to
auto-merge (#3345).
2025-09-12 09:04:49 -07:00
Michael Bolin
90965fbc84 chore: add just test, which runs cargo nextest (#3508)
Since I can never seem to remember to add `--no-fail-fast` when running
`cargo nextest run`, let's just create an alias for it.
2025-09-12 08:44:44 -07:00
Michael Bolin
c172e8e997 feat: added SetDefaultModel to JSON-RPC server (#3512)
This adds `SetDefaultModel`, which takes `model` and `reasoning_effort`
as optional fields. If set, the field will overwrite what is in the
user's `config.toml`.

This reuses logic that was added to support the `/model` command in the
TUI: https://github.com/openai/codex/pull/2799.
2025-09-11 23:44:17 -07:00
Michael Bolin
9bbeb75361 feat: include reasoning_effort in NewConversationResponse (#3506)
`ClientRequest::NewConversation` picks up the reasoning level from the user's defaults in `config.toml`, so it should be reported in `NewConversationResponse`.
2025-09-11 21:04:40 -07:00
Fouad Matin
6ccd32c601 add(readme): IDE (#3494)
update copy in readme to add link to IDE
2025-09-11 17:46:20 -07:00
pakrym-oai
3b5a5412bb Log cf-ray header in client traces (#3488)
## Summary
- log the `cf-ray` header when tracing HTTP responses in the Codex
client
- keep existing response status logging unchanged

## Testing
- just fmt
- just fix -p codex-core
- cargo test -p codex-core *(fails:
suite::client::azure_overrides_assign_properties_used_for_responses_url,
suite::client::env_var_overrides_loaded_auth)*

------
https://chatgpt.com/codex/tasks/task_i_68c31640dacc83209be131baf91611cd
2025-09-11 17:42:44 -07:00
jif-oai
44bb53df1e bug: default to image (#3501)
Default the MIME type to image
2025-09-11 23:10:24 +00:00
jif-oai
8453915e02 feat: TUI onboarding (#3398)
Example of how onboarding could look like
2025-09-11 15:04:29 -07:00
Ahmed Ibrahim
44587c2443 Use PlanType enum when formatting usage-limit CTA (#3495)
- Started using Play type struct
- Added CTA for team/business 
- Refactored a bit to unify the logic
2025-09-11 22:01:25 +00:00
Charlie Weems
8f7b22b652 Add more detailed documentation on MCP server usage (#3345)
Adds further information on how to get started with `codex mcp`:
- Tool details and parameter references
- Quickstart with example using MCP inspector.
2025-09-11 14:38:24 -07:00
Dylan
027944c64e fix: improve handle_sandbox_error timeouts (#3435)
## Summary
Handle timeouts the same way, regardless of approval mode. There's more
to do here, but this is simple and should be zero-regret

## Testing
- [x] existing tests pass
- [x] test locally and verify rollout
2025-09-11 12:09:20 -07:00
Michael Bolin
bec51f6c05 chore: enable clippy::redundant_clone (#3489)
Created this PR by:

- adding `redundant_clone` to `[workspace.lints.clippy]` in
`cargo-rs/Cargol.toml`
- running `cargo clippy --tests --fix`
- running `just fmt`

Though I had to clean up one instance of the following that resulted:

```rust
let codex = codex;
```
2025-09-11 11:59:37 -07:00
pakrym-oai
66967500bb Assign the entire gpt-5 model family same characteristics (#3490)
So the context size indicator is displayed.
2025-09-11 18:56:49 +00:00
Ahmed Ibrahim
167b4f0e25 Clear composer on fork (#3445)
Fixes this

<img width="344" height="51" alt="image"
src="https://github.com/user-attachments/assets/f227d338-b044-4f8d-bf07-87499b4230d8"
/>
2025-09-11 11:45:17 -07:00
Michael Bolin
167154178b fix: use -F instead of -f for force=true in gh call (#3486)
Apparently `-F` is the correct thing to use. From the code sample on 


https://docs.github.com/en/rest/git/refs?apiVersion=2022-11-28#update-a-reference

```shell
gh api \
  --method PATCH \
  -H "Accept: application/vnd.github+json" \
  -H "X-GitHub-Api-Version: 2022-11-28" \
  /repos/OWNER/REPO/git/refs/REF \
   -f 'sha=aa218f56b14c9653891f9e74264a383fa43fefbd' -F "force=true"
```

Also, I ran the following locally and verified it worked:

```shell
export GITHUB_REPOSITORY=openai/codex
export GITHUB_SHA=305252b2fb2d57bb40a9e4bad269db9a761f7099
gh api \
  repos/${GITHUB_REPOSITORY}/git/refs/heads/latest-alpha-cli \
  -X PATCH \
  -f sha="${GITHUB_SHA}" \
  -F force=true
```

`$GITHUB_REPOSITORY` and `$GITHUB_SHA` should already be available as
environment variables for the `run` step without having to be redeclared
in the `env` section.
2025-09-11 11:32:47 -07:00
Ahmed Ibrahim
674e3d3c90 Add Compact and Turn Context to the rollout items (#3444)
Adding compact and turn context to the rollout items

based on #3440
2025-09-11 18:08:51 +00:00
jif-oai
114ce9ff4d NIT unified exec (#3479)
Fix the default value of the experimental flag of unified_exec
2025-09-11 16:19:12 +00:00
Eric Traut
e13b35ecb0 Simplify auth flow and reconcile differences between ChatGPT and API Key auth (#3189)
This PR does the following:
* Adds the ability to paste or type an API key.
* Removes the `preferred_auth_method` config option. The last login
method is always persisted in auth.json, so this isn't needed.
* If OPENAI_API_KEY env variable is defined, the value is used to
prepopulate the new UI. The env variable is otherwise ignored by the
CLI.
* Adds a new MCP server entry point "login_api_key" so we can implement
this same API key behavior for the VS Code extension.
<img width="473" height="140" alt="Screenshot 2025-09-04 at 3 51 04 PM"
src="https://github.com/user-attachments/assets/c11bbd5b-8a4d-4d71-90fd-34130460f9d9"
/>
<img width="726" height="254" alt="Screenshot 2025-09-04 at 3 51 32 PM"
src="https://github.com/user-attachments/assets/6cc76b34-309a-4387-acbc-15ee5c756db9"
/>
2025-09-11 09:16:34 -07:00
Jeremy Rose
377af75730 apply-patch: sort replacements and add regression tests (#3425)
- Ensure replacements are applied in index order for determinism.
- Add tests for addition chunk followed by removal and worktree-aware
helper.

This fixes a panic I observed.

Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>
2025-09-11 09:07:03 -07:00
Michael Bolin
86e0f31a7e chore: rust-release.yml should update the latest-alpha-cli branch (#3458)
This updates `rust-release.yml` so that the last step of creating a
release entails updating the `latest-alpha-cli` branch to point to the
tag used to create the latest release. This will facilitate building
automation to identify the most recent alpha release of Codex CLI
(though note this branch could also point to an official release, as it
is implemented today).

This introduces a new job, `update-branch`, which depends on the
`release` job. I made it separate from the `release` job because
`update-branch` needs the `contents: write` permission, so this limits
the amount of work we do with that permission.

Note I also created a branch protection rule for `latest-alpha-cli`
that:

- specifies repository admins as the only members of the bypass list
- only those with bypass permissions can create, update, or delete this
branch
- this branch requires a linear history
- note that force pushes _are_ allowed

This is the first step in fixing
https://github.com/openai/codex/issues/3098.
2025-09-11 08:06:28 -07:00
Michael Bolin
8f837f1093 fix: add check to ensure output of generate_mcp_types.py matches codex-rs/mcp-types/src/lib.rs (#3450)
As a follow-up to https://github.com/openai/codex/pull/3439, this adds a
CI job to ensure the codegen script has to be updated in order to change
`codex-rs/mcp-types/src/lib.rs`.
2025-09-10 23:31:28 -07:00
Ahmed Ibrahim
162e1235a8 Change forking to read the rollout from file (#3440)
This PR changes get history op to get path. Then, forking will use a
path. This will help us have one unified codepath for resuming/forking
conversations. Will also help in having rollout history in order. It
also fixes a bug where you won't see the UI when resuming after forking.
2025-09-10 17:42:54 -07:00
jif-oai
c09ed74a16 Unified execution (#3288)
## Unified PTY-Based Exec Tool

Note: this requires to have this flag in the config:
`use_experimental_unified_exec_tool=true`

- Adds a PTY-backed interactive exec feature (“unified_exec”) with
session reuse via
  session_id, bounded output (128 KiB), and timeout clamping (≤ 60 s).
- Protocol: introduces ResponseItem::UnifiedExec { session_id,
arguments, timeout_ms }.
- Tools: exposes unified_exec as a function tool (Responses API);
excluded from Chat
  Completions payload while still supported in tool lists.
- Path handling: resolves commands via PATH (or explicit paths), with
UTF‑8/newline‑aware
  truncation (truncate_middle).
- Tests: cover command parsing, path resolution, session
persistence/cleanup, multi‑session
  isolation, timeouts, and truncation behavior.
2025-09-10 17:38:11 -07:00
Michael Bolin
65f3528cad feat: add UserInfo request to JSON-RPC server (#3428)
This adds a simple endpoint that provides the email address encoded in
`$CODEX_HOME/auth.json`.

As noted, for now, we do not hit the server to verify this is the user's
true email address.
2025-09-10 17:03:35 -07:00
Michael Bolin
44262d8fd8 fix: ensure output of codex-rs/mcp-types/generate_mcp_types.py matches codex-rs/mcp-types/src/lib.rs (#3439)
https://github.com/openai/codex/pull/3395 updated `mcp-types/src/lib.rs`
by hand, but that file is generated code that is produced by
`mcp-types/generate_mcp_types.py`. Unfortunately, we do not have
anything in CI to verify this right now, but I will address that in a
subsequent PR.

#3395 ended up introducing a change that added a required field when
deserializing `InitializeResult`, breaking Codex when used as an MCP
client, so the quick fix in #3436 was to make the new field `Optional`
with `skip_serializing_if = "Option::is_none"`, but that did not address
the problem that `mcp-types/generate_mcp_types.py` and
`mcp-types/src/lib.rs` are out of sync.

This PR gets things back to where they are in sync. It removes the
custom `mcp_types::McpClientInfo` type that was added to
`mcp-types/src/lib.rs` and forces us to use the generated
`mcp_types::Implementation` type. Though this PR also updates
`generate_mcp_types.py` to generate the additional `user_agent:
Optional<String>` field on `Implementation` so that we can continue to
specify it when Codex operates as an MCP server.

However, this also requires us to specify `user_agent: None` when Codex
operates as an MCP client.

We may want to introduce our own `InitializeResult` type that is
specific to when we run as a server to avoid this in the future, but my
immediate goal is just to get things back in sync.
2025-09-10 16:14:41 -07:00
Jeremy Rose
95a9938d3a fix trampling projects table when accepting trusted dirs (#3434)
Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>
2025-09-10 23:01:31 +00:00
Jeremy Rose
f69f07b028 put workspace roots in the environment context (#3375)
to keep the tool description constant when the writable roots change.
2025-09-10 15:10:52 -07:00
Gabriel Peal
8d766088e6 Make user_agent optional (#3436)
# External (non-OpenAI) Pull Request Requirements

Currently, mcp server fail to start with:
```
🖐  MCP client for `<CLIENT>` failed to start: missing field `user_agent`
````

It isn't clear to me yet why this is happening. My understanding is that
this struct is simply added as a new field to the response but this
should fix it until I figure out the full story here.

<img width="714" height="262" alt="CleanShot 2025-09-10 at 13 58 59"
src="https://github.com/user-attachments/assets/946b1313-5c1c-43d3-8ae8-ecc3de3406fc"
/>
2025-09-10 14:15:02 -07:00
dedrisian-oai
87654ec0b7 Persist model & reasoning changes (#2799)
Persists `/model` changes across both general and profile-specific
sessions.
2025-09-10 20:53:46 +00:00
Michael Bolin
51d9e05de7 Back out "feat: POSIX unification and snapshot sessions (#3179)" (#3430)
This reverts https://github.com/openai/codex/pull/3179.

#3179 appears to introduce a regression where sourcing dotfiles causes a
bunch of activity in the title bar (and potentially slows things down?)


https://github.com/user-attachments/assets/a68f7fb3-0749-4e0e-a321-2aa6993e01da

Verified this no longer happens after backing out #3179.

Original commit changeset: 62bd0e3d9d
2025-09-10 12:40:24 -07:00
Jeremy Rose
8068cc75f8 replace tui_markdown with a custom markdown renderer (#3396)
Also, simplify the streaming behavior.

This fixes a number of display issues with streaming markdown, and paves
the way for better markdown features (e.g. customizable styles, syntax
highlighting, markdown-aware wrapping).

Not currently supported:
- footnotes
- tables
- reference-style links
2025-09-10 12:13:53 -07:00
Eric Traut
acb28bf914 Improved resiliency of two auth-related tests (#3427)
This PR improves two existing auth-related tests. They were failing when
run in an environment where an `OPENAI_API_KEY` env variable was
defined. The change makes them more resilient.
2025-09-10 11:46:02 -07:00
Kazuhiro Sera
97338de578 Remove a broken link to prompting_guide.md in docs/getting-started.md (#2858)
The file no longer exists. We've been receiving this feedback several
times.
- https://github.com/openai/codex/issues/2374
- https://github.com/openai/codex/issues/2810
- https://github.com/openai/codex/issues/2826

My previous PR https://github.com/openai/codex/pull/2413 for this issue
restored the file but now it's compatible with the current file
structure. Thus, let's simply delete the link.
2025-09-10 10:52:50 -07:00
katyhshi
5200b7a95d docs: fix codex exec heading typo (#2703)
# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the "Contributing" section
of the README or your PR may be closed:
https://github.com/openai/codex#contributing

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
2025-09-10 10:39:53 -07:00
Michael Bolin
64e6c4afbb fix: remove empty file: chatwidget_stream_tests.rs (#3356)
Originally added in https://github.com/openai/codex/pull/2029.
2025-09-10 10:35:24 -07:00
Eric Traut
39db113cc9 Added images to UserMessageEvent (#3400)
This PR adds an `images` field to the existing `UserMessageEvent` so we
can encode zero or more images associated with a user message. This
allows images to be restored when conversations are restored.
2025-09-10 10:18:43 -07:00
Ahmed Ibrahim
45bd5ca4b9 Move initial history to protocol (#3422)
To fix an edge case of forking then resuming

#3419
2025-09-10 10:17:24 -07:00
Michael Bolin
c13c3dadbf fix: remove unnecessary #[allow(dead_code)] annotation (#3357) 2025-09-10 08:19:05 -07:00
Gabriel Peal
8636bff46d Set a user agent suffix when used as a mcp server (#3395)
This automatically adds a user agent suffix whenever the CLI is used as
a MCP server
2025-09-10 02:32:57 +00:00
Ahmed Ibrahim
43809a454e Introduce rollout items (#3380)
This PR introduces Rollout items. This enable us to rollout eventmsgs
and session meta.

This is mostly #3214 with rebase on main
2025-09-09 23:52:33 +00:00
dank-openai
5c48600bb3 alt+delete deletes the word to the right of the cursor (delete_forward_word) (#3394)
This mirrors alt+backspace, which deletes to the left of the cursor.
2025-09-09 22:41:23 +00:00
Andrew Tan
de6559f2ab Include apply_patch tool for oss models from gpt-oss providers with different naming convention (e.g. openai/gpt-oss-*) (#2811)
Model providers like Groq, Openrouter, AWS Bedrock, VertexAI and others
typically prefix the name of gpt-oss models with `openai`, e.g.
`openai/gpt-oss-120b`.

This PR is to match the model name slug using `contains` instead of
`starts_with` to ensure that the `apply_patch` tool is included in the
tools for models names like `openai/gpt-oss-120b`

Without this, the gpt-oss models will often try to call the
`apply_patch` tool directly instead of via the `shell` command, leading
to validation errors.

I have run all the local checks.

Note: The gpt-oss models from non-Ollama providers are typically run via
a profile with a different base_url (instead of with the `--oss` flag)

---------

Co-authored-by: Andrew Tan <andrewtan@Andrews-Mac.local>
2025-09-09 15:02:02 -07:00
pakrym-oai
5bcc9d8b77 Do not send reasoning item IDs (#3390)
Response API doesn't require IDs on reasoning items anymore. 

Fixes: https://github.com/openai/codex/issues/3292
2025-09-09 14:47:06 -07:00
Gabriel Peal
5eab4c7ab4 Replace config.responses_originator_header_internal_override with CODEX_INTERNAL_ORIGINATOR_OVERRIDE_ENV_VAR (#3388)
The previous config approach had a few issues:
1. It is part of the config but not designed to be used externally
2. It had to be wired through many places (look at the +/- on this PR
3. It wasn't guaranteed to be set consistently everywhere because we
don't have a super well defined way that configs stack. For example, the
extension would configure during newConversation but anything that
happened outside of that (like login) wouldn't get it.

This env var approach is cleaner and also creates one less thing we have
to deal with when coming up with a better holistic story around configs.

One downside is that I removed the unit test testing for the override
because I don't want to deal with setting the global env or spawning
child processes and figuring out how to introspect their originator
header. The new code is sufficiently simple and I tested it e2e that I
feel as if this is still worth it.
2025-09-09 17:23:23 -04:00
jif-oai
f656e192bf No fail fast (#3387)
Add --no-fail-fast to the new `nextest`
2025-09-09 13:17:14 -07:00
Jeremy Rose
ee5ecae7c0 tweak "failed to find expected lines" message in apply_patch (#3374)
It was hard for me to read the expected lines as a `["one", "two",
"three"]` array, maybe not so hard for the model but probably not having
to un-escape in its head would help it out :)

Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>
2025-09-09 12:27:50 -07:00
Michael Bolin
58bb2048ac fix: LoginChatGptCompleteNotification does not need to be listed explicitly in protocol-ts (#3222)
I verified that the output of `protocol-ts$ cargo run` is unchanged by
removing this line..

Added a comment on `ServerNotification` with justification to make this
clear.
2025-09-09 11:06:59 -07:00
Wang
ac8a3155d6 feat(core): re-export InitialHistory from conversation_manager (#3270)
This commit adds a re-export for InitialHistory from the internal
conversation_manager module in codex-core's lib.rs.

The `RolloutRecorder::get_rollout_history` method (exposed via `pub use
rollout::RolloutRecorder;`, already present in lib.rs) returns an
`InitialHistory` type, which is defined in the private
conversation_manager module. Without this re-export, consumers of the
public RolloutRecorder API would not be able to directly use the return
type, as they cannot access the private module. This would result in an
inconvenient experience where the method's return value cannot be
handled without additional, non-obvious imports.

By adding `pub use conversation_manager::InitialHistory;`, we make
InitialHistory available as `codex_core::InitialHistory`, improving API
ergonomics for users of the rollout functionality while keeping the
conversation_manager module internal.

No functional changes are made; this is a pure re-export for better
usability.

Signed-off-by: M4n5ter <m4n5terrr@gmail.com>
2025-09-09 10:37:08 -07:00
Michael Bolin
ace14e8d36 feat: add ArchiveConversation to ClientRequest (#3353)
Adds support for `ArchiveConversation` in the JSON-RPC server that takes
a `(ConversationId, PathBuf)` pair and:

- verifies the `ConversationId` corresponds to the rollout id at the
`PathBuf`
- if so, invokes
`ConversationManager.remove_conversation(ConversationId)`
- if the `CodexConversation` was in memory, send `Shutdown` and wait for
`ShutdownComplete` with a timeout
- moves the `.jsonl` file to `$CODEX_HOME/archived_sessions`

---------

Co-authored-by: Gabriel Peal <gabriel@openai.com>
2025-09-09 11:39:00 -04:00
Michael Bolin
2a76a08a9e fix: include rollout_path in NewConversationResponse (#3352)
Adding the `rollout_path` to the `NewConversationResponse` makes it so a
client can perform subsequent operations on a `(ConversationId,
PathBuf)` pair. #3353 will introduce support for `ArchiveConversation`.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/3352).
* #3353
* __->__ #3352
2025-09-09 00:11:48 -07:00
Michael Bolin
16309d6b68 chore: try switching to cargo nextest to speed up CI builds (#3323)
I started looking at https://nexte.st/ because I was interested in a
test harness that lets a test dynamically declare itself "skipped,"
which would be a nice alternative to this pattern:


4c46490e53/codex-rs/core/tests/suite/cli_stream.rs (L22-L27)

ChatGPT pointed me at https://nexte.st/, which also claims to be "up to
3x as fast as cargo test." Locally, in `codex-rs`, I see

- `cargo nextest run` finishes in 19s
- `cargo test` finishes in 37s

Though looking at CI, the wins are quite as big, presumably because my
laptop has more cores than our GitHub runners (which is a separate
issue...). Comparing the [CI jobs from this
PR](https://github.com/openai/codex/actions/runs/17561325162/job/49878216246?pr=3323)
with that of a [recent open
PR](https://github.com/openai/codex/actions/runs/17561066581/job/49877342753?pr=3321):

| | `cargo test` | `cargo nextest` |
| ----------------------------------------------- | ------------ |
--------------- |
| `macos-14 - aarch64-apple-darwin` | 2m16s | 1m51s |
| `macos-14 - aarch64-apple-darwin` | 5m04s | 3m44s |
| `ubuntu-24.04 - x86_64-unknown-linux-musl` | 2m02s | 1m56s |
| `ubuntu-24.04-arm - aarch64-unknown-linux-musl` | 2m01s | 1m35s |
| `windows-latest - x86_64-pc-windows-msvc` | 3m07s | 2m53s |
| `windows-11-arm - aarch64-pc-windows-msvc` | 3m10s | 2m45s |

I thought that, to start, we would only make this change in CI before
declaring it the "official" way for the team to run the test suite.

Though unfortunately, I do not believe that `cargo nextest` _actually_
supports a dynamic skip feature, so I guess I'll have to keep looking?
Some related discussions:

- https://internals.rust-lang.org/t/pre-rfc-skippable-tests/14611
- https://internals.rust-lang.org/t/skippable-tests/21260
2025-09-08 21:39:18 -07:00
jif-oai
62bd0e3d9d feat: POSIX unification and snapshot sessions (#3179)
## Session snapshot
For POSIX shell, the goal is to take a snapshot of the interactive shell
environment, store it in a session file located in `.codex/` and only
source this file for every command that is run.
As a result, if a snapshot files exist, `bash -lc <CALL>` get replaced
by `bash -c <CALL>`.

This also fixes the issue that `bash -lc` does not source `.bashrc`,
resulting in missing env variables and aliases in the codex session.
## POSIX unification
Unify `bash` and `zsh` shell into a POSIX shell. The rational is that
the tool will not use any `zsh` specific capabilities.

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>
2025-09-08 18:09:45 -07:00
jif-oai
a9c68ea270 feat: Run cargo shear during CI (#3338)
Run cargo shear as part of the CI to ensure no unused dependencies
2025-09-09 01:05:08 +00:00
881 changed files with 66333 additions and 12285 deletions

View File

@@ -1,6 +1,6 @@
[codespell]
# Ref: https://github.com/codespell-project/codespell#using-a-config-file
skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl
skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl,frame*.txt
check-hidden = true
ignore-regex = ^\s*"image/\S+": ".*|\b(afterAll)\b
ignore-words-list = ratatui,ser

View File

@@ -27,6 +27,34 @@
"path": "codex.exe"
}
}
},
"codex-responses-api-proxy": {
"platforms": {
"macos-aarch64": {
"regex": "^codex-responses-api-proxy-aarch64-apple-darwin\\.zst$",
"path": "codex-responses-api-proxy"
},
"macos-x86_64": {
"regex": "^codex-responses-api-proxy-x86_64-apple-darwin\\.zst$",
"path": "codex-responses-api-proxy"
},
"linux-x86_64": {
"regex": "^codex-responses-api-proxy-x86_64-unknown-linux-musl\\.zst$",
"path": "codex-responses-api-proxy"
},
"linux-aarch64": {
"regex": "^codex-responses-api-proxy-aarch64-unknown-linux-musl\\.zst$",
"path": "codex-responses-api-proxy"
},
"windows-x86_64": {
"regex": "^codex-responses-api-proxy-x86_64-pc-windows-msvc\\.exe\\.zst$",
"path": "codex-responses-api-proxy.exe"
},
"windows-aarch64": {
"regex": "^codex-responses-api-proxy-aarch64-pc-windows-msvc\\.exe\\.zst$",
"path": "codex-responses-api-proxy.exe"
}
}
}
}
}

View File

@@ -1,7 +1,7 @@
name: ci
on:
pull_request: { branches: [main] }
pull_request: {}
push: { branches: [main] }
jobs:
@@ -27,12 +27,29 @@ jobs:
- name: Install dependencies
run: pnpm install --frozen-lockfile
# Run all tasks using workspace filters
# stage_npm_packages.py requires DotSlash when staging releases.
- uses: facebook/install-dotslash@v2
- name: Ensure staging a release works.
- name: Stage npm package
id: stage_npm_package
env:
GH_TOKEN: ${{ github.token }}
run: ./codex-cli/scripts/stage_release.sh
run: |
set -euo pipefail
CODEX_VERSION=0.40.0
OUTPUT_DIR="${RUNNER_TEMP}"
python3 ./scripts/stage_npm_packages.py \
--release-version "$CODEX_VERSION" \
--package codex \
--output-dir "$OUTPUT_DIR"
PACK_OUTPUT="${OUTPUT_DIR}/codex-npm-${CODEX_VERSION}.tgz"
echo "pack_output=$PACK_OUTPUT" >> "$GITHUB_OUTPUT"
- name: Upload staged npm package artifact
uses: actions/upload-artifact@v4
with:
name: codex-npm-staging
path: ${{ steps.stage_npm_package.outputs.pack_output }}
- name: Ensure root README.md contains only ASCII and certain Unicode code points
run: ./scripts/asciicheck.py README.md

View File

@@ -22,6 +22,6 @@ jobs:
- name: Annotate locations with typos
uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
- name: Codespell
uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2
uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2.1
with:
ignore_words_file: .codespellignore

View File

@@ -57,11 +57,31 @@ jobs:
working-directory: codex-rs
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.89
- uses: dtolnay/rust-toolchain@1.90
with:
components: rustfmt
- name: cargo fmt
run: cargo fmt -- --config imports_granularity=Item --check
- name: Verify codegen for mcp-types
run: ./mcp-types/check_lib_rs.py
cargo_shear:
name: cargo shear
runs-on: ubuntu-24.04
needs: changed
if: ${{ needs.changed.outputs.codex == 'true' || needs.changed.outputs.workflows == 'true' || github.event_name == 'push' }}
defaults:
run:
working-directory: codex-rs
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: cargo-shear
version: 1.5.1
- name: cargo shear
run: cargo shear
# --- CI to validate on different os/targets --------------------------------
lint_build_test:
@@ -123,7 +143,7 @@ jobs:
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.89
- uses: dtolnay/rust-toolchain@1.90
with:
targets: ${{ matrix.target }}
components: clippy
@@ -160,12 +180,17 @@ jobs:
find . -name Cargo.toml -mindepth 2 -maxdepth 2 -print0 \
| xargs -0 -n1 -I{} bash -c 'cd "$(dirname "{}")" && cargo check --profile ${{ matrix.profile }}'
- name: cargo test
- uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: nextest
version: 0.9.103
- name: tests
id: test
# `cargo test` takes too long for release builds to run them on every PR
# Tests take too long for release builds to run them on every PR.
if: ${{ matrix.profile != 'release' }}
continue-on-error: true
run: cargo test --all-features --target ${{ matrix.target }} --profile ${{ matrix.profile }}
run: cargo nextest run --all-features --no-fail-fast --target ${{ matrix.target }}
env:
RUST_BACKTRACE: 1
@@ -182,7 +207,7 @@ jobs:
# --- Gatherer job that you mark as the ONLY required status -----------------
results:
name: CI results (required)
needs: [changed, general, lint_build_test]
needs: [changed, general, cargo_shear, lint_build_test]
if: always()
runs-on: ubuntu-24.04
steps:
@@ -190,6 +215,7 @@ jobs:
shell: bash
run: |
echo "general: ${{ needs.general.result }}"
echo "shear : ${{ needs.cargo_shear.result }}"
echo "matrix : ${{ needs.lint_build_test.result }}"
# If nothing relevant changed (PR touching only root README, etc.),
@@ -201,4 +227,5 @@ jobs:
# Otherwise require the jobs to have succeeded
[[ '${{ needs.general.result }}' == 'success' ]] || { echo 'general failed'; exit 1; }
[[ '${{ needs.cargo_shear.result }}' == 'success' ]] || { echo 'cargo_shear failed'; exit 1; }
[[ '${{ needs.lint_build_test.result }}' == 'success' ]] || { echo 'matrix failed'; exit 1; }

View File

@@ -77,7 +77,7 @@ jobs:
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.89
- uses: dtolnay/rust-toolchain@1.90
with:
targets: ${{ matrix.target }}
@@ -97,7 +97,7 @@ jobs:
sudo apt install -y musl-tools pkg-config
- name: Cargo build
run: cargo build --target ${{ matrix.target }} --release --bin codex
run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
- name: Stage artifacts
shell: bash
@@ -107,8 +107,10 @@ jobs:
if [[ "${{ matrix.runner }}" == windows* ]]; then
cp target/${{ matrix.target }}/release/codex.exe "$dest/codex-${{ matrix.target }}.exe"
cp target/${{ matrix.target }}/release/codex-responses-api-proxy.exe "$dest/codex-responses-api-proxy-${{ matrix.target }}.exe"
else
cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
cp target/${{ matrix.target }}/release/codex-responses-api-proxy "$dest/codex-responses-api-proxy-${{ matrix.target }}"
fi
- if: ${{ matrix.runner == 'windows-11-arm' }}
@@ -167,6 +169,14 @@ jobs:
needs: build
name: release
runs-on: ubuntu-latest
permissions:
contents: write
actions: read
outputs:
version: ${{ steps.release_name.outputs.name }}
tag: ${{ github.ref_name }}
should_publish_npm: ${{ steps.npm_publish_settings.outputs.should_publish }}
npm_tag: ${{ steps.npm_publish_settings.outputs.npm_tag }}
steps:
- name: Checkout repository
@@ -187,21 +197,49 @@ jobs:
version="${GITHUB_REF_NAME#rust-v}"
echo "name=${version}" >> $GITHUB_OUTPUT
- name: Stage npm package
- name: Determine npm publish settings
id: npm_publish_settings
env:
VERSION: ${{ steps.release_name.outputs.name }}
run: |
set -euo pipefail
version="${VERSION}"
if [[ "${version}" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
echo "should_publish=true" >> "$GITHUB_OUTPUT"
echo "npm_tag=" >> "$GITHUB_OUTPUT"
elif [[ "${version}" =~ ^[0-9]+\.[0-9]+\.[0-9]+-alpha\.[0-9]+$ ]]; then
echo "should_publish=true" >> "$GITHUB_OUTPUT"
echo "npm_tag=alpha" >> "$GITHUB_OUTPUT"
else
echo "should_publish=false" >> "$GITHUB_OUTPUT"
echo "npm_tag=" >> "$GITHUB_OUTPUT"
fi
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
run_install: false
- name: Setup Node.js for npm packaging
uses: actions/setup-node@v5
with:
node-version: 22
- name: Install dependencies
run: pnpm install --frozen-lockfile
# stage_npm_packages.py requires DotSlash when staging releases.
- uses: facebook/install-dotslash@v2
- name: Stage npm packages
env:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
TMP_DIR="${RUNNER_TEMP}/npm-stage"
python3 codex-cli/scripts/stage_rust_release.py \
./scripts/stage_npm_packages.py \
--release-version "${{ steps.release_name.outputs.name }}" \
--tmp "${TMP_DIR}"
mkdir -p dist/npm
# Produce an npm-ready tarball using `npm pack` and store it in dist/npm.
# We then rename it to a stable name used by our publishing script.
(cd "$TMP_DIR" && npm pack --pack-destination "${GITHUB_WORKSPACE}/dist/npm")
mv "${GITHUB_WORKSPACE}"/dist/npm/*.tgz \
"${GITHUB_WORKSPACE}/dist/npm/codex-npm-${{ steps.release_name.outputs.name }}.tgz"
--package codex \
--package codex-responses-api-proxy \
--package codex-sdk
- name: Create GitHub Release
uses: softprops/action-gh-release@v2
@@ -219,3 +257,90 @@ jobs:
with:
tag: ${{ github.ref_name }}
config: .github/dotslash-config.json
# Publish to npm using OIDC authentication.
# July 31, 2025: https://github.blog/changelog/2025-07-31-npm-trusted-publishing-with-oidc-is-generally-available/
# npm docs: https://docs.npmjs.com/trusted-publishers
publish-npm:
# Publish to npm for stable releases and alpha pre-releases with numeric suffixes.
if: ${{ needs.release.outputs.should_publish_npm == 'true' }}
name: publish-npm
needs: release
runs-on: ubuntu-latest
permissions:
id-token: write # Required for OIDC
contents: read
steps:
- name: Setup Node.js
uses: actions/setup-node@v5
with:
node-version: 22
registry-url: "https://registry.npmjs.org"
scope: "@openai"
# Trusted publishing requires npm CLI version 11.5.1 or later.
- name: Update npm
run: npm install -g npm@latest
- name: Download npm tarballs from release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
set -euo pipefail
version="${{ needs.release.outputs.version }}"
tag="${{ needs.release.outputs.tag }}"
mkdir -p dist/npm
gh release download "$tag" \
--repo "${GITHUB_REPOSITORY}" \
--pattern "codex-npm-${version}.tgz" \
--dir dist/npm
gh release download "$tag" \
--repo "${GITHUB_REPOSITORY}" \
--pattern "codex-responses-api-proxy-npm-${version}.tgz" \
--dir dist/npm
gh release download "$tag" \
--repo "${GITHUB_REPOSITORY}" \
--pattern "codex-sdk-npm-${version}.tgz" \
--dir dist/npm
# No NODE_AUTH_TOKEN needed because we use OIDC.
- name: Publish to npm
env:
VERSION: ${{ needs.release.outputs.version }}
NPM_TAG: ${{ needs.release.outputs.npm_tag }}
run: |
set -euo pipefail
tag_args=()
if [[ -n "${NPM_TAG}" ]]; then
tag_args+=(--tag "${NPM_TAG}")
fi
tarballs=(
"codex-npm-${VERSION}.tgz"
"codex-responses-api-proxy-npm-${VERSION}.tgz"
"codex-sdk-npm-${VERSION}.tgz"
)
for tarball in "${tarballs[@]}"; do
npm publish "${GITHUB_WORKSPACE}/dist/npm/${tarball}" "${tag_args[@]}"
done
update-branch:
name: Update latest-alpha-cli branch
permissions:
contents: write
needs: release
runs-on: ubuntu-latest
steps:
- name: Update latest-alpha-cli branch
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
set -euo pipefail
gh api \
repos/${GITHUB_REPOSITORY}/git/refs/heads/latest-alpha-cli \
-X PATCH \
-f sha="${GITHUB_SHA}" \
-F force=true

43
.github/workflows/sdk.yml vendored Normal file
View File

@@ -0,0 +1,43 @@
name: sdk
on:
push:
branches: [main]
pull_request: {}
jobs:
sdks:
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@v5
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
run_install: false
- name: Setup Node.js
uses: actions/setup-node@v5
with:
node-version: 22
cache: pnpm
- uses: dtolnay/rust-toolchain@1.90
- name: build codex
run: cargo build --bin codex
working-directory: codex-rs
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Build SDK packages
run: pnpm -r --filter ./sdk/typescript run build
- name: Lint SDK packages
run: pnpm -r --filter ./sdk/typescript run lint
- name: Test SDK packages
run: pnpm -r --filter ./sdk/typescript run test

View File

@@ -4,6 +4,7 @@ In the codex-rs folder where the rust code lives:
- Crate names are prefixed with `codex-`. For example, the `core` folder's crate is named `codex-core`
- When using format! and you can inline variables into {}, always do that.
- Install any commands the repo relies on (for example `just`, `rg`, or `cargo-insta`) if they aren't already available before running instructions here.
- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` or `CODEX_SANDBOX_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.
- Similarly, when you spawn a process using Seatbelt (`/usr/bin/sandbox-exec`), `CODEX_SANDBOX=seatbelt` will be set on the child process. Integration tests that want to run Seatbelt themselves cannot be run under Seatbelt, so checks for `CODEX_SANDBOX=seatbelt` are also often used to early exit out of tests, as appropriate.

View File

@@ -1,8 +1,10 @@
<h1 align="center">OpenAI Codex CLI</h1>
<p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>
<p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, see <a href="https://chatgpt.com/codex">chatgpt.com/codex</a>.</p>
<p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.
</br>
</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href="https://developers.openai.com/codex/ide">install in your IDE</a>
</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href="https://chatgpt.com/codex">chatgpt.com/codex</a></p>
<p align="center">
<img src="./.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" />
@@ -99,4 +101,3 @@ Codex CLI supports a rich set of configuration options, with preferences stored
## License
This repository is licensed under the [Apache-2.0 License](LICENSE).

View File

@@ -1,7 +1 @@
# 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
/vendor/

View File

@@ -208,7 +208,7 @@ The hardening mechanism Codex uses depends on your OS:
| Requirement | Details |
| --------------------------- | --------------------------------------------------------------- |
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 **via WSL2** |
| Node.js | **22 or newer** (LTS recommended) |
| Node.js | **16 or newer** (Node 20 LTS recommended) |
| Git (optional, recommended) | 2.23+ for built-in PR helpers |
| RAM | 4-GB minimum (8-GB recommended) |
@@ -513,7 +513,7 @@ 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 is regularly tested on macOS and Linux with Node 20+, and also supports Node 16.
</details>

View File

@@ -1,6 +1,8 @@
#!/usr/bin/env node
// Unified entry point for the Codex CLI.
import { spawn } from "node:child_process";
import { existsSync } from "fs";
import path from "path";
import { fileURLToPath } from "url";
@@ -40,10 +42,10 @@ switch (platform) {
case "win32":
switch (arch) {
case "x64":
targetTriple = "x86_64-pc-windows-msvc.exe";
targetTriple = "x86_64-pc-windows-msvc";
break;
case "arm64":
targetTriple = "aarch64-pc-windows-msvc.exe";
targetTriple = "aarch64-pc-windows-msvc";
break;
default:
break;
@@ -57,31 +59,16 @@ if (!targetTriple) {
throw new Error(`Unsupported platform: ${platform} (${arch})`);
}
const binaryPath = path.join(__dirname, "..", "bin", `codex-${targetTriple}`);
const vendorRoot = path.join(__dirname, "..", "vendor");
const archRoot = path.join(vendorRoot, targetTriple);
const codexBinaryName = process.platform === "win32" ? "codex.exe" : "codex";
const binaryPath = path.join(archRoot, "codex", codexBinaryName);
// 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");
async function tryImport(moduleName) {
try {
// eslint-disable-next-line node/no-unsupported-features/es-syntax
return await import(moduleName);
} catch (err) {
return null;
}
}
async function resolveRgDir() {
const ripgrep = await tryImport("@vscode/ripgrep");
if (!ripgrep?.rgPath) {
return null;
}
return path.dirname(ripgrep.rgPath);
}
function getUpdatedPath(newDirs) {
const pathSep = process.platform === "win32" ? ";" : ":";
@@ -94,9 +81,9 @@ function getUpdatedPath(newDirs) {
}
const additionalDirs = [];
const rgDir = await resolveRgDir();
if (rgDir) {
additionalDirs.push(rgDir);
const pathDir = path.join(archRoot, "path");
if (existsSync(pathDir)) {
additionalDirs.push(pathDir);
}
const updatedPath = getUpdatedPath(additionalDirs);

79
codex-cli/bin/rg Executable file
View File

@@ -0,0 +1,79 @@
#!/usr/bin/env dotslash
{
"name": "rg",
"platforms": {
"macos-aarch64": {
"size": 1787248,
"hash": "blake3",
"digest": "8d9942032585ea8ee805937634238d9aee7b210069f4703c88fbe568e26fb78a",
"format": "tar.gz",
"path": "ripgrep-14.1.1-aarch64-apple-darwin/rg",
"providers": [
{
"url": "https://github.com/BurntSushi/ripgrep/releases/download/14.1.1/ripgrep-14.1.1-aarch64-apple-darwin.tar.gz"
}
]
},
"linux-aarch64": {
"size": 2047405,
"hash": "blake3",
"digest": "0b670b8fa0a3df2762af2fc82cc4932f684ca4c02dbd1260d4f3133fd4b2a515",
"format": "tar.gz",
"path": "ripgrep-14.1.1-aarch64-unknown-linux-gnu/rg",
"providers": [
{
"url": "https://github.com/BurntSushi/ripgrep/releases/download/14.1.1/ripgrep-14.1.1-aarch64-unknown-linux-gnu.tar.gz"
}
]
},
"macos-x86_64": {
"size": 2082672,
"hash": "blake3",
"digest": "e9b862fc8da3127f92791f0ff6a799504154ca9d36c98bf3e60a81c6b1f7289e",
"format": "tar.gz",
"path": "ripgrep-14.1.1-x86_64-apple-darwin/rg",
"providers": [
{
"url": "https://github.com/BurntSushi/ripgrep/releases/download/14.1.1/ripgrep-14.1.1-x86_64-apple-darwin.tar.gz"
}
]
},
"linux-x86_64": {
"size": 2566310,
"hash": "blake3",
"digest": "f73cca4e54d78c31f832c7f6e2c0b4db8b04fa3eaa747915727d570893dbee76",
"format": "tar.gz",
"path": "ripgrep-14.1.1-x86_64-unknown-linux-musl/rg",
"providers": [
{
"url": "https://github.com/BurntSushi/ripgrep/releases/download/14.1.1/ripgrep-14.1.1-x86_64-unknown-linux-musl.tar.gz"
}
]
},
"windows-x86_64": {
"size": 2058893,
"hash": "blake3",
"digest": "a8ce1a6fed4f8093ee997e57f33254e94b2cd18e26358b09db599c89882eadbd",
"format": "zip",
"path": "ripgrep-14.1.1-x86_64-pc-windows-msvc/rg.exe",
"providers": [
{
"url": "https://github.com/BurntSushi/ripgrep/releases/download/14.1.1/ripgrep-14.1.1-x86_64-pc-windows-msvc.zip"
}
]
},
"windows-aarch64": {
"size": 1667740,
"hash": "blake3",
"digest": "47b971a8c4fca1d23a4e7c19bd4d88465ebc395598458133139406d3bf85f3fa",
"format": "zip",
"path": "rg.exe",
"providers": [
{
"url": "https://github.com/microsoft/ripgrep-prebuilt/releases/download/v13.0.0-13/ripgrep-v13.0.0-13-aarch64-pc-windows-msvc.zip"
}
]
}
}
}

View File

@@ -2,117 +2,16 @@
"name": "@openai/codex",
"version": "0.0.0-dev",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@openai/codex",
"version": "0.0.0-dev",
"license": "Apache-2.0",
"dependencies": {
"@vscode/ripgrep": "^1.15.14"
},
"bin": {
"codex": "bin/codex.js"
},
"engines": {
"node": ">=20"
}
},
"node_modules/@vscode/ripgrep": {
"version": "1.15.14",
"resolved": "https://registry.npmjs.org/@vscode/ripgrep/-/ripgrep-1.15.14.tgz",
"integrity": "sha512-/G1UJPYlm+trBWQ6cMO3sv6b8D1+G16WaJH1/DSqw32JOVlzgZbLkDxRyzIpTpv30AcYGMkCf5tUqGlW6HbDWw==",
"hasInstallScript": true,
"license": "MIT",
"dependencies": {
"https-proxy-agent": "^7.0.2",
"proxy-from-env": "^1.1.0",
"yauzl": "^2.9.2"
}
},
"node_modules/agent-base": {
"version": "7.1.4",
"resolved": "https://registry.npmjs.org/agent-base/-/agent-base-7.1.4.tgz",
"integrity": "sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==",
"license": "MIT",
"engines": {
"node": ">= 14"
}
},
"node_modules/buffer-crc32": {
"version": "0.2.13",
"resolved": "https://registry.npmjs.org/buffer-crc32/-/buffer-crc32-0.2.13.tgz",
"integrity": "sha512-VO9Ht/+p3SN7SKWqcrgEzjGbRSJYTx+Q1pTQC0wrWqHx0vpJraQ6GtHx8tvcg1rlK1byhU5gccxgOgj7B0TDkQ==",
"license": "MIT",
"engines": {
"node": "*"
}
},
"node_modules/debug": {
"version": "4.4.1",
"resolved": "https://registry.npmjs.org/debug/-/debug-4.4.1.tgz",
"integrity": "sha512-KcKCqiftBJcZr++7ykoDIEwSa3XWowTfNPo92BYxjXiyYEVrUQh2aLyhxBCwww+heortUFxEJYcRzosstTEBYQ==",
"license": "MIT",
"dependencies": {
"ms": "^2.1.3"
},
"engines": {
"node": ">=6.0"
},
"peerDependenciesMeta": {
"supports-color": {
"optional": true
}
}
},
"node_modules/fd-slicer": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/fd-slicer/-/fd-slicer-1.1.0.tgz",
"integrity": "sha512-cE1qsB/VwyQozZ+q1dGxR8LBYNZeofhEdUNGSMbQD3Gw2lAzX9Zb3uIU6Ebc/Fmyjo9AWWfnn0AUCHqtevs/8g==",
"license": "MIT",
"dependencies": {
"pend": "~1.2.0"
}
},
"node_modules/https-proxy-agent": {
"version": "7.0.6",
"resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-7.0.6.tgz",
"integrity": "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw==",
"license": "MIT",
"dependencies": {
"agent-base": "^7.1.2",
"debug": "4"
},
"engines": {
"node": ">= 14"
}
},
"node_modules/ms": {
"version": "2.1.3",
"resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
"integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==",
"license": "MIT"
},
"node_modules/pend": {
"version": "1.2.0",
"resolved": "https://registry.npmjs.org/pend/-/pend-1.2.0.tgz",
"integrity": "sha512-F3asv42UuXchdzt+xXqfW1OGlVBe+mxa2mqI0pg5yAHZPvFmY3Y6drSf/GQ1A86WgWEN9Kzh/WrgKa6iGcHXLg==",
"license": "MIT"
},
"node_modules/proxy-from-env": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
"integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==",
"license": "MIT"
},
"node_modules/yauzl": {
"version": "2.10.0",
"resolved": "https://registry.npmjs.org/yauzl/-/yauzl-2.10.0.tgz",
"integrity": "sha512-p4a9I6X6nu6IhoGmBqAcbJy1mlC4j27vEPZX9F4L4/vZT3Lyq1VkFHw/V/PUcB9Buo+DG3iHkT0x3Qya58zc3g==",
"license": "MIT",
"dependencies": {
"buffer-crc32": "~0.2.3",
"fd-slicer": "~1.1.0"
"node": ">=16"
}
}
}

View File

@@ -7,20 +7,15 @@
},
"type": "module",
"engines": {
"node": ">=20"
"node": ">=16"
},
"files": [
"bin",
"dist"
"vendor"
],
"repository": {
"type": "git",
"url": "git+https://github.com/openai/codex.git"
},
"dependencies": {
"@vscode/ripgrep": "^1.15.14"
},
"devDependencies": {
"prettier": "^3.3.3"
"url": "git+https://github.com/openai/codex.git",
"directory": "codex-cli"
}
}

View File

@@ -1,9 +1,19 @@
# 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:
Use the staging helper in the repo root to generate npm tarballs for a release. For
example, to stage the CLI, responses proxy, and SDK packages for version `0.6.0`:
```bash
./codex-cli/scripts/stage_rust_release.py --release-version 0.6.0
./scripts/stage_npm_packages.py \
--release-version 0.6.0 \
--package codex \
--package codex-responses-api-proxy \
--package codex-sdk
```
This downloads the native artifacts once, hydrates `vendor/` for each package, and writes
tarballs to `dist/npm/`.
If you need to invoke `build_npm_package.py` directly, run
`codex-cli/scripts/install_native_deps.py` first and pass `--vendor-src` pointing to the
directory that contains the populated `vendor/` tree.

View File

@@ -0,0 +1,308 @@
#!/usr/bin/env python3
"""Stage and optionally package the @openai/codex npm module."""
import argparse
import json
import shutil
import subprocess
import sys
import tempfile
from pathlib import Path
SCRIPT_DIR = Path(__file__).resolve().parent
CODEX_CLI_ROOT = SCRIPT_DIR.parent
REPO_ROOT = CODEX_CLI_ROOT.parent
RESPONSES_API_PROXY_NPM_ROOT = REPO_ROOT / "codex-rs" / "responses-api-proxy" / "npm"
CODEX_SDK_ROOT = REPO_ROOT / "sdk" / "typescript"
PACKAGE_NATIVE_COMPONENTS: dict[str, list[str]] = {
"codex": ["codex", "rg"],
"codex-responses-api-proxy": ["codex-responses-api-proxy"],
"codex-sdk": ["codex"],
}
COMPONENT_DEST_DIR: dict[str, str] = {
"codex": "codex",
"codex-responses-api-proxy": "codex-responses-api-proxy",
"rg": "path",
}
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Build or stage the Codex CLI npm package.")
parser.add_argument(
"--package",
choices=("codex", "codex-responses-api-proxy", "codex-sdk"),
default="codex",
help="Which npm package to stage (default: codex).",
)
parser.add_argument(
"--version",
help="Version number to write to package.json inside the staged package.",
)
parser.add_argument(
"--release-version",
help=(
"Version to stage for npm release."
),
)
parser.add_argument(
"--staging-dir",
type=Path,
help=(
"Directory to stage the package contents. Defaults to a new temporary directory "
"if omitted. The directory must be empty when provided."
),
)
parser.add_argument(
"--tmp",
dest="staging_dir",
type=Path,
help=argparse.SUPPRESS,
)
parser.add_argument(
"--pack-output",
type=Path,
help="Path where the generated npm tarball should be written.",
)
parser.add_argument(
"--vendor-src",
type=Path,
help="Directory containing pre-installed native binaries to bundle (vendor root).",
)
return parser.parse_args()
def main() -> int:
args = parse_args()
package = args.package
version = args.version
release_version = args.release_version
if release_version:
if version and version != release_version:
raise RuntimeError("--version and --release-version must match when both are provided.")
version = release_version
if not version:
raise RuntimeError("Must specify --version or --release-version.")
staging_dir, created_temp = prepare_staging_dir(args.staging_dir)
try:
stage_sources(staging_dir, version, package)
vendor_src = args.vendor_src.resolve() if args.vendor_src else None
native_components = PACKAGE_NATIVE_COMPONENTS.get(package, [])
if native_components:
if vendor_src is None:
components_str = ", ".join(native_components)
raise RuntimeError(
"Native components "
f"({components_str}) required for package '{package}'. Provide --vendor-src "
"pointing to a directory containing pre-installed binaries."
)
copy_native_binaries(vendor_src, staging_dir, native_components)
if release_version:
staging_dir_str = str(staging_dir)
if package == "codex":
print(
f"Staged version {version} for release in {staging_dir_str}\n\n"
"Verify the CLI:\n"
f" node {staging_dir_str}/bin/codex.js --version\n"
f" node {staging_dir_str}/bin/codex.js --help\n\n"
)
elif package == "codex-responses-api-proxy":
print(
f"Staged version {version} for release in {staging_dir_str}\n\n"
"Verify the responses API proxy:\n"
f" node {staging_dir_str}/bin/codex-responses-api-proxy.js --help\n\n"
)
else:
print(
f"Staged version {version} for release in {staging_dir_str}\n\n"
"Verify the SDK contents:\n"
f" ls {staging_dir_str}/dist\n"
f" ls {staging_dir_str}/vendor\n"
" node -e \"import('./dist/index.js').then(() => console.log('ok'))\"\n\n"
)
else:
print(f"Staged package in {staging_dir}")
if args.pack_output is not None:
output_path = run_npm_pack(staging_dir, args.pack_output)
print(f"npm pack output written to {output_path}")
finally:
if created_temp:
# Preserve the staging directory for further inspection.
pass
return 0
def prepare_staging_dir(staging_dir: Path | None) -> tuple[Path, bool]:
if staging_dir is not None:
staging_dir = staging_dir.resolve()
staging_dir.mkdir(parents=True, exist_ok=True)
if any(staging_dir.iterdir()):
raise RuntimeError(f"Staging directory {staging_dir} is not empty.")
return staging_dir, False
temp_dir = Path(tempfile.mkdtemp(prefix="codex-npm-stage-"))
return temp_dir, True
def stage_sources(staging_dir: Path, version: str, package: str) -> None:
if package == "codex":
bin_dir = staging_dir / "bin"
bin_dir.mkdir(parents=True, exist_ok=True)
shutil.copy2(CODEX_CLI_ROOT / "bin" / "codex.js", bin_dir / "codex.js")
rg_manifest = CODEX_CLI_ROOT / "bin" / "rg"
if rg_manifest.exists():
shutil.copy2(rg_manifest, bin_dir / "rg")
readme_src = REPO_ROOT / "README.md"
if readme_src.exists():
shutil.copy2(readme_src, staging_dir / "README.md")
package_json_path = CODEX_CLI_ROOT / "package.json"
elif package == "codex-responses-api-proxy":
bin_dir = staging_dir / "bin"
bin_dir.mkdir(parents=True, exist_ok=True)
launcher_src = RESPONSES_API_PROXY_NPM_ROOT / "bin" / "codex-responses-api-proxy.js"
shutil.copy2(launcher_src, bin_dir / "codex-responses-api-proxy.js")
readme_src = RESPONSES_API_PROXY_NPM_ROOT / "README.md"
if readme_src.exists():
shutil.copy2(readme_src, staging_dir / "README.md")
package_json_path = RESPONSES_API_PROXY_NPM_ROOT / "package.json"
elif package == "codex-sdk":
package_json_path = CODEX_SDK_ROOT / "package.json"
stage_codex_sdk_sources(staging_dir)
else:
raise RuntimeError(f"Unknown package '{package}'.")
with open(package_json_path, "r", encoding="utf-8") as fh:
package_json = json.load(fh)
package_json["version"] = version
if package == "codex-sdk":
scripts = package_json.get("scripts")
if isinstance(scripts, dict):
scripts.pop("prepare", None)
files = package_json.get("files")
if isinstance(files, list):
if "vendor" not in files:
files.append("vendor")
else:
package_json["files"] = ["dist", "vendor"]
with open(staging_dir / "package.json", "w", encoding="utf-8") as out:
json.dump(package_json, out, indent=2)
out.write("\n")
def run_command(cmd: list[str], cwd: Path | None = None) -> None:
print("+", " ".join(cmd))
subprocess.run(cmd, cwd=cwd, check=True)
def stage_codex_sdk_sources(staging_dir: Path) -> None:
package_root = CODEX_SDK_ROOT
run_command(["pnpm", "install", "--frozen-lockfile"], cwd=package_root)
run_command(["pnpm", "run", "build"], cwd=package_root)
dist_src = package_root / "dist"
if not dist_src.exists():
raise RuntimeError("codex-sdk build did not produce a dist directory.")
shutil.copytree(dist_src, staging_dir / "dist")
readme_src = package_root / "README.md"
if readme_src.exists():
shutil.copy2(readme_src, staging_dir / "README.md")
license_src = REPO_ROOT / "LICENSE"
if license_src.exists():
shutil.copy2(license_src, staging_dir / "LICENSE")
def copy_native_binaries(vendor_src: Path, staging_dir: Path, components: list[str]) -> None:
vendor_src = vendor_src.resolve()
if not vendor_src.exists():
raise RuntimeError(f"Vendor source directory not found: {vendor_src}")
components_set = {component for component in components if component in COMPONENT_DEST_DIR}
if not components_set:
return
vendor_dest = staging_dir / "vendor"
if vendor_dest.exists():
shutil.rmtree(vendor_dest)
vendor_dest.mkdir(parents=True, exist_ok=True)
for target_dir in vendor_src.iterdir():
if not target_dir.is_dir():
continue
dest_target_dir = vendor_dest / target_dir.name
dest_target_dir.mkdir(parents=True, exist_ok=True)
for component in components_set:
dest_dir_name = COMPONENT_DEST_DIR.get(component)
if dest_dir_name is None:
continue
src_component_dir = target_dir / dest_dir_name
if not src_component_dir.exists():
raise RuntimeError(
f"Missing native component '{component}' in vendor source: {src_component_dir}"
)
dest_component_dir = dest_target_dir / dest_dir_name
if dest_component_dir.exists():
shutil.rmtree(dest_component_dir)
shutil.copytree(src_component_dir, dest_component_dir)
def run_npm_pack(staging_dir: Path, output_path: Path) -> Path:
output_path = output_path.resolve()
output_path.parent.mkdir(parents=True, exist_ok=True)
with tempfile.TemporaryDirectory(prefix="codex-npm-pack-") as pack_dir_str:
pack_dir = Path(pack_dir_str)
stdout = subprocess.check_output(
["npm", "pack", "--json", "--pack-destination", str(pack_dir)],
cwd=staging_dir,
text=True,
)
try:
pack_output = json.loads(stdout)
except json.JSONDecodeError as exc:
raise RuntimeError("Failed to parse npm pack output.") from exc
if not pack_output:
raise RuntimeError("npm pack did not produce an output tarball.")
tarball_name = pack_output[0].get("filename") or pack_output[0].get("name")
if not tarball_name:
raise RuntimeError("Unable to determine npm pack output filename.")
tarball_path = pack_dir / tarball_name
if not tarball_path.exists():
raise RuntimeError(f"Expected npm pack output not found: {tarball_path}")
shutil.move(str(tarball_path), output_path)
return output_path
if __name__ == "__main__":
import sys
sys.exit(main())

View File

@@ -0,0 +1,383 @@
#!/usr/bin/env python3
"""Install Codex native binaries (Rust CLI plus ripgrep helpers)."""
import argparse
import json
import os
import shutil
import subprocess
import tarfile
import tempfile
import zipfile
from dataclasses import dataclass
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path
from typing import Iterable, Sequence
from urllib.parse import urlparse
from urllib.request import urlopen
SCRIPT_DIR = Path(__file__).resolve().parent
CODEX_CLI_ROOT = SCRIPT_DIR.parent
DEFAULT_WORKFLOW_URL = "https://github.com/openai/codex/actions/runs/17952349351" # rust-v0.40.0
VENDOR_DIR_NAME = "vendor"
RG_MANIFEST = CODEX_CLI_ROOT / "bin" / "rg"
BINARY_TARGETS = (
"x86_64-unknown-linux-musl",
"aarch64-unknown-linux-musl",
"x86_64-apple-darwin",
"aarch64-apple-darwin",
"x86_64-pc-windows-msvc",
"aarch64-pc-windows-msvc",
)
@dataclass(frozen=True)
class BinaryComponent:
artifact_prefix: str # matches the artifact filename prefix (e.g. codex-<target>.zst)
dest_dir: str # directory under vendor/<target>/ where the binary is installed
binary_basename: str # executable name inside dest_dir (before optional .exe)
BINARY_COMPONENTS = {
"codex": BinaryComponent(
artifact_prefix="codex",
dest_dir="codex",
binary_basename="codex",
),
"codex-responses-api-proxy": BinaryComponent(
artifact_prefix="codex-responses-api-proxy",
dest_dir="codex-responses-api-proxy",
binary_basename="codex-responses-api-proxy",
),
}
RG_TARGET_PLATFORM_PAIRS: list[tuple[str, str]] = [
("x86_64-unknown-linux-musl", "linux-x86_64"),
("aarch64-unknown-linux-musl", "linux-aarch64"),
("x86_64-apple-darwin", "macos-x86_64"),
("aarch64-apple-darwin", "macos-aarch64"),
("x86_64-pc-windows-msvc", "windows-x86_64"),
("aarch64-pc-windows-msvc", "windows-aarch64"),
]
RG_TARGET_TO_PLATFORM = {target: platform for target, platform in RG_TARGET_PLATFORM_PAIRS}
DEFAULT_RG_TARGETS = [target for target, _ in RG_TARGET_PLATFORM_PAIRS]
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Install native Codex binaries.")
parser.add_argument(
"--workflow-url",
help=(
"GitHub Actions workflow URL that produced the artifacts. Defaults to a "
"known good run when omitted."
),
)
parser.add_argument(
"--component",
dest="components",
action="append",
choices=tuple(list(BINARY_COMPONENTS) + ["rg"]),
help=(
"Limit installation to the specified components."
" May be repeated. Defaults to 'codex' and 'rg'."
),
)
parser.add_argument(
"root",
nargs="?",
type=Path,
help=(
"Directory containing package.json for the staged package. If omitted, the "
"repository checkout is used."
),
)
return parser.parse_args()
def main() -> int:
args = parse_args()
codex_cli_root = (args.root or CODEX_CLI_ROOT).resolve()
vendor_dir = codex_cli_root / VENDOR_DIR_NAME
vendor_dir.mkdir(parents=True, exist_ok=True)
components = args.components or ["codex", "rg"]
workflow_url = (args.workflow_url or DEFAULT_WORKFLOW_URL).strip()
if not workflow_url:
workflow_url = DEFAULT_WORKFLOW_URL
workflow_id = workflow_url.rstrip("/").split("/")[-1]
print(f"Downloading native artifacts from workflow {workflow_id}...")
with tempfile.TemporaryDirectory(prefix="codex-native-artifacts-") as artifacts_dir_str:
artifacts_dir = Path(artifacts_dir_str)
_download_artifacts(workflow_id, artifacts_dir)
install_binary_components(
artifacts_dir,
vendor_dir,
BINARY_TARGETS,
[name for name in components if name in BINARY_COMPONENTS],
)
if "rg" in components:
print("Fetching ripgrep binaries...")
fetch_rg(vendor_dir, DEFAULT_RG_TARGETS, manifest_path=RG_MANIFEST)
print(f"Installed native dependencies into {vendor_dir}")
return 0
def fetch_rg(
vendor_dir: Path,
targets: Sequence[str] | None = None,
*,
manifest_path: Path,
) -> list[Path]:
"""Download ripgrep binaries described by the DotSlash manifest."""
if targets is None:
targets = DEFAULT_RG_TARGETS
if not manifest_path.exists():
raise FileNotFoundError(f"DotSlash manifest not found: {manifest_path}")
manifest = _load_manifest(manifest_path)
platforms = manifest.get("platforms", {})
vendor_dir.mkdir(parents=True, exist_ok=True)
targets = list(targets)
if not targets:
return []
task_configs: list[tuple[str, str, dict]] = []
for target in targets:
platform_key = RG_TARGET_TO_PLATFORM.get(target)
if platform_key is None:
raise ValueError(f"Unsupported ripgrep target '{target}'.")
platform_info = platforms.get(platform_key)
if platform_info is None:
raise RuntimeError(f"Platform '{platform_key}' not found in manifest {manifest_path}.")
task_configs.append((target, platform_key, platform_info))
results: dict[str, Path] = {}
max_workers = min(len(task_configs), max(1, (os.cpu_count() or 1)))
print("Installing ripgrep binaries for targets: " + ", ".join(targets))
with ThreadPoolExecutor(max_workers=max_workers) as executor:
future_map = {
executor.submit(
_fetch_single_rg,
vendor_dir,
target,
platform_key,
platform_info,
manifest_path,
): target
for target, platform_key, platform_info in task_configs
}
for future in as_completed(future_map):
target = future_map[future]
results[target] = future.result()
print(f" installed ripgrep for {target}")
return [results[target] for target in targets]
def _download_artifacts(workflow_id: str, dest_dir: Path) -> None:
cmd = [
"gh",
"run",
"download",
"--dir",
str(dest_dir),
"--repo",
"openai/codex",
workflow_id,
]
subprocess.check_call(cmd)
def install_binary_components(
artifacts_dir: Path,
vendor_dir: Path,
targets: Iterable[str],
component_names: Sequence[str],
) -> None:
selected_components = [BINARY_COMPONENTS[name] for name in component_names if name in BINARY_COMPONENTS]
if not selected_components:
return
targets = list(targets)
if not targets:
return
for component in selected_components:
print(
f"Installing {component.binary_basename} binaries for targets: "
+ ", ".join(targets)
)
max_workers = min(len(targets), max(1, (os.cpu_count() or 1)))
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = {
executor.submit(
_install_single_binary,
artifacts_dir,
vendor_dir,
target,
component,
): target
for target in targets
}
for future in as_completed(futures):
installed_path = future.result()
print(f" installed {installed_path}")
def _install_single_binary(
artifacts_dir: Path,
vendor_dir: Path,
target: str,
component: BinaryComponent,
) -> Path:
artifact_subdir = artifacts_dir / target
archive_name = _archive_name_for_target(component.artifact_prefix, target)
archive_path = artifact_subdir / archive_name
if not archive_path.exists():
raise FileNotFoundError(f"Expected artifact not found: {archive_path}")
dest_dir = vendor_dir / target / component.dest_dir
dest_dir.mkdir(parents=True, exist_ok=True)
binary_name = (
f"{component.binary_basename}.exe" if "windows" in target else component.binary_basename
)
dest = dest_dir / binary_name
dest.unlink(missing_ok=True)
extract_archive(archive_path, "zst", None, dest)
if "windows" not in target:
dest.chmod(0o755)
return dest
def _archive_name_for_target(artifact_prefix: str, target: str) -> str:
if "windows" in target:
return f"{artifact_prefix}-{target}.exe.zst"
return f"{artifact_prefix}-{target}.zst"
def _fetch_single_rg(
vendor_dir: Path,
target: str,
platform_key: str,
platform_info: dict,
manifest_path: Path,
) -> Path:
providers = platform_info.get("providers", [])
if not providers:
raise RuntimeError(f"No providers listed for platform '{platform_key}' in {manifest_path}.")
url = providers[0]["url"]
archive_format = platform_info.get("format", "zst")
archive_member = platform_info.get("path")
dest_dir = vendor_dir / target / "path"
dest_dir.mkdir(parents=True, exist_ok=True)
is_windows = platform_key.startswith("win")
binary_name = "rg.exe" if is_windows else "rg"
dest = dest_dir / binary_name
with tempfile.TemporaryDirectory() as tmp_dir_str:
tmp_dir = Path(tmp_dir_str)
archive_filename = os.path.basename(urlparse(url).path)
download_path = tmp_dir / archive_filename
_download_file(url, download_path)
dest.unlink(missing_ok=True)
extract_archive(download_path, archive_format, archive_member, dest)
if not is_windows:
dest.chmod(0o755)
return dest
def _download_file(url: str, dest: Path) -> None:
dest.parent.mkdir(parents=True, exist_ok=True)
with urlopen(url) as response, open(dest, "wb") as out:
shutil.copyfileobj(response, out)
def extract_archive(
archive_path: Path,
archive_format: str,
archive_member: str | None,
dest: Path,
) -> None:
dest.parent.mkdir(parents=True, exist_ok=True)
if archive_format == "zst":
output_path = archive_path.parent / dest.name
subprocess.check_call(
["zstd", "-f", "-d", str(archive_path), "-o", str(output_path)]
)
shutil.move(str(output_path), dest)
return
if archive_format == "tar.gz":
if not archive_member:
raise RuntimeError("Missing 'path' for tar.gz archive in DotSlash manifest.")
with tarfile.open(archive_path, "r:gz") as tar:
try:
member = tar.getmember(archive_member)
except KeyError as exc:
raise RuntimeError(
f"Entry '{archive_member}' not found in archive {archive_path}."
) from exc
tar.extract(member, path=archive_path.parent, filter="data")
extracted = archive_path.parent / archive_member
shutil.move(str(extracted), dest)
return
if archive_format == "zip":
if not archive_member:
raise RuntimeError("Missing 'path' for zip archive in DotSlash manifest.")
with zipfile.ZipFile(archive_path) as archive:
try:
with archive.open(archive_member) as src, open(dest, "wb") as out:
shutil.copyfileobj(src, out)
except KeyError as exc:
raise RuntimeError(
f"Entry '{archive_member}' not found in archive {archive_path}."
) from exc
return
raise RuntimeError(f"Unsupported archive format '{archive_format}'.")
def _load_manifest(manifest_path: Path) -> dict:
cmd = ["dotslash", "--", "parse", str(manifest_path)]
stdout = subprocess.check_output(cmd, text=True)
try:
manifest = json.loads(stdout)
except json.JSONDecodeError as exc:
raise RuntimeError(f"Invalid DotSlash manifest output from {manifest_path}.") from exc
if not isinstance(manifest, dict):
raise RuntimeError(
f"Unexpected DotSlash manifest structure for {manifest_path}: {type(manifest)!r}"
)
return manifest
if __name__ == "__main__":
import sys
sys.exit(main())

View File

@@ -1,94 +0,0 @@
#!/usr/bin/env bash
# Install native runtime dependencies for codex-cli.
#
# Usage
# install_native_deps.sh [--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=""
# 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/17417194663" # rust-v0.28.0
while [[ $# -gt 0 ]]; do
case "$1" in
--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 "$WORKFLOW_ID"
# x64 Linux
zstd -d "$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 "$BIN_DIR/codex-aarch64-apple-darwin"
# x64 Windows
zstd -d "$ARTIFACTS_DIR/x86_64-pc-windows-msvc/codex-x86_64-pc-windows-msvc.exe.zst" \
-o "$BIN_DIR/codex-x86_64-pc-windows-msvc.exe"
# ARM64 Windows
zstd -d "$ARTIFACTS_DIR/aarch64-pc-windows-msvc/codex-aarch64-pc-windows-msvc.exe.zst" \
-o "$BIN_DIR/codex-aarch64-pc-windows-msvc.exe"
echo "Installed native dependencies into $BIN_DIR"

View File

@@ -1,120 +0,0 @@
#!/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.
# -h|--help : Print usage.
#
# -----------------------------------------------------------------------------
set -euo pipefail
# Helper - usage / flag parsing
usage() {
cat <<EOF
Usage: $(basename "$0") [--tmp DIR] [--version VERSION]
Options
--tmp DIR Use DIR to stage the release (defaults to a fresh mktemp dir)
--version Specify the version to release (defaults to a timestamp-based version)
-h, --help Show this help
Legacy positional argument: the first non-flag argument is still interpreted
as the temporary directory (for backwards compatibility) but is deprecated.
EOF
exit "${1:-0}"
}
TMPDIR=""
# 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#*=}"
;;
--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 "$CODEX_CLI_ROOT" >/dev/null
# 1. Build the JS artifacts ---------------------------------------------------
# Paths inside the staged package
mkdir -p "$TMPDIR/bin"
cp -r bin/codex.js "$TMPDIR/bin/codex.js"
cp ../README.md "$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)
./scripts/install_native_deps.sh --workflow-url "$WORKFLOW_URL" "$TMPDIR"
popd >/dev/null
echo "Staged version $VERSION for release in $TMPDIR"
echo "Verify the CLI:"
echo " node ${TMPDIR}/bin/codex.js --version"
echo " node ${TMPDIR}/bin/codex.js --help"
# Print final hint for convenience
echo "Next: cd \"$TMPDIR\" && npm publish"

View File

@@ -1,70 +0,0 @@
#!/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.
Optionally pass `--tmp` to control the temporary staging directory that will be
forwarded to stage_release.sh.
"""
)
parser.add_argument(
"--release-version", required=True, help="Version to release, e.g., 0.3.0"
)
parser.add_argument(
"--tmp",
help="Optional path to stage the npm package; forwarded to stage_release.sh",
)
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()
cmd = [
str(current_dir / "stage_release.sh"),
"--version",
version,
"--workflow-url",
workflow["url"],
]
if args.tmp:
cmd.extend(["--tmp", args.tmp])
stage_release = subprocess.run(cmd)
stage_release.check_returncode()
return 0
if __name__ == "__main__":
sys.exit(main())

2534
codex-rs/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,23 +1,37 @@
[workspace]
members = [
"backend-client",
"ansi-escape",
"app-server",
"app-server-protocol",
"apply-patch",
"arg0",
"codex-backend-openapi-models",
"cloud-tasks",
"cloud-tasks-client",
"cli",
"common",
"core",
"exec",
"execpolicy",
"file-search",
"git-tooling",
"linux-sandbox",
"login",
"mcp-client",
"mcp-server",
"mcp-types",
"ollama",
"process-hardening",
"protocol",
"protocol-ts",
"rmcp-client",
"responses-api-proxy",
"otel",
"tui",
"git-apply",
"utils/json-to-toml",
"utils/readiness",
]
resolver = "2"
@@ -29,14 +43,190 @@ version = "0.0.0"
# edition.
edition = "2024"
[workspace.dependencies]
# Internal
app_test_support = { path = "app-server/tests/common" }
codex-ansi-escape = { path = "ansi-escape" }
codex-app-server = { path = "app-server" }
codex-app-server-protocol = { path = "app-server-protocol" }
codex-apply-patch = { path = "apply-patch" }
codex-arg0 = { path = "arg0" }
codex-chatgpt = { path = "chatgpt" }
codex-common = { path = "common" }
codex-core = { path = "core" }
codex-exec = { path = "exec" }
codex-file-search = { path = "file-search" }
codex-git-tooling = { path = "git-tooling" }
codex-linux-sandbox = { path = "linux-sandbox" }
codex-login = { path = "login" }
codex-mcp-client = { path = "mcp-client" }
codex-mcp-server = { path = "mcp-server" }
codex-ollama = { path = "ollama" }
codex-otel = { path = "otel" }
codex-process-hardening = { path = "process-hardening" }
codex-protocol = { path = "protocol" }
codex-protocol-ts = { path = "protocol-ts" }
codex-responses-api-proxy = { path = "responses-api-proxy" }
codex-rmcp-client = { path = "rmcp-client" }
codex-tui = { path = "tui" }
codex-utils-json-to-toml = { path = "utils/json-to-toml" }
codex-utils-readiness = { path = "utils/readiness" }
core_test_support = { path = "core/tests/common" }
mcp-types = { path = "mcp-types" }
mcp_test_support = { path = "mcp-server/tests/common" }
# External
allocative = "0.3.3"
ansi-to-tui = "7.0.0"
anyhow = "1"
arboard = "3"
askama = "0.12"
assert_cmd = "2"
async-channel = "2.3.1"
async-stream = "0.3.6"
async-trait = "0.1.89"
base64 = "0.22.1"
bytes = "1.10.1"
chrono = "0.4.42"
clap = "4"
clap_complete = "4"
color-eyre = "0.6.3"
crossterm = "0.28.1"
ctor = "0.5.0"
derive_more = "2"
diffy = "0.4.2"
dirs = "6"
dotenvy = "0.15.7"
dunce = "1.0.4"
env-flags = "0.1.1"
env_logger = "0.11.5"
escargot = "0.5"
eventsource-stream = "0.2.3"
futures = "0.3"
icu_decimal = "2.0.0"
icu_locale_core = "2.0.0"
ignore = "0.4.23"
image = { version = "^0.25.8", default-features = false }
indexmap = "2.6.0"
insta = "1.43.2"
itertools = "0.14.0"
landlock = "0.4.1"
lazy_static = "1"
libc = "0.2.175"
log = "0.4"
maplit = "1.0.2"
mime_guess = "2.0.5"
multimap = "0.10.0"
nucleo-matcher = "0.3.1"
openssl-sys = "*"
opentelemetry = "0.30.0"
opentelemetry-appender-tracing = "0.30.0"
opentelemetry-otlp = "0.30.0"
opentelemetry-semantic-conventions = "0.30.0"
opentelemetry_sdk = "0.30.0"
os_info = "3.12.0"
owo-colors = "4.2.0"
paste = "1.0.15"
path-absolutize = "3.1.1"
path-clean = "1.0.1"
pathdiff = "0.2"
portable-pty = "0.9.0"
predicates = "3"
pretty_assertions = "1.4.1"
pulldown-cmark = "0.10"
rand = "0.9"
ratatui = "0.29.0"
regex-lite = "0.1.7"
reqwest = "0.12"
schemars = "0.8.22"
seccompiler = "0.5.0"
serde = "1"
serde_json = "1"
serde_with = "3.14"
sha1 = "0.10.6"
sha2 = "0.10"
shlex = "1.3.0"
similar = "2.7.0"
starlark = "0.13.0"
strum = "0.27.2"
strum_macros = "0.27.2"
supports-color = "3.0.2"
sys-locale = "0.3.2"
tempfile = "3.23.0"
textwrap = "0.16.2"
thiserror = "2.0.16"
time = "0.3"
tiny_http = "0.12"
tokio = "1"
tokio-stream = "0.1.17"
tokio-test = "0.4"
tokio-util = "0.7.16"
toml = "0.9.5"
toml_edit = "0.23.4"
tonic = "0.13.1"
tracing = "0.1.41"
tracing-appender = "0.2.3"
tracing-subscriber = "0.3.20"
tracing-test = "0.2.5"
tree-sitter = "0.25.9"
tree-sitter-bash = "0.25.0"
ts-rs = "11"
unicode-segmentation = "1.12.0"
unicode-width = "0.2"
url = "2"
urlencoding = "2.1"
uuid = "1"
vt100 = "0.16.2"
walkdir = "2.5.0"
webbrowser = "1.0"
which = "6"
wildmatch = "2.5.0"
wiremock = "0.6"
zeroize = "1.8.1"
[workspace.lints]
rust = {}
[workspace.lints.clippy]
expect_used = "deny"
identity_op = "deny"
manual_clamp = "deny"
manual_filter = "deny"
manual_find = "deny"
manual_flatten = "deny"
manual_map = "deny"
manual_memcpy = "deny"
manual_non_exhaustive = "deny"
manual_ok_or = "deny"
manual_range_contains = "deny"
manual_retain = "deny"
manual_strip = "deny"
manual_try_fold = "deny"
manual_unwrap_or = "deny"
needless_borrow = "deny"
needless_borrowed_reference = "deny"
needless_collect = "deny"
needless_late_init = "deny"
needless_option_as_deref = "deny"
needless_question_mark = "deny"
needless_update = "deny"
redundant_clone = "deny"
redundant_closure = "deny"
redundant_closure_for_method_calls = "deny"
redundant_static_lifetimes = "deny"
trivially_copy_pass_by_ref = "deny"
uninlined_format_args = "deny"
unnecessary_filter_map = "deny"
unnecessary_lazy_evaluations = "deny"
unnecessary_sort_by = "deny"
unnecessary_to_owned = "deny"
unwrap_used = "deny"
# cargo-shear cannot see the platform-specific openssl-sys usage, so we
# silence the false positive here instead of deleting a real dependency.
[workspace.metadata.cargo-shear]
ignored = ["openssl-sys", "codex-utils-readiness"]
[profile.release]
lto = "fat"
# Because we bundle some of these executables with the TypeScript CLI, we

View File

@@ -4,18 +4,18 @@ We provide Codex CLI as a standalone, native executable to ensure a zero-depende
## Installing Codex
Today, the easiest way to install Codex is via `npm`, though we plan to publish Codex to other package managers soon.
Today, the easiest way to install Codex is via `npm`:
```shell
npm i -g @openai/codex@native
npm i -g @openai/codex
codex
```
You can also download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
You can also install via Homebrew (`brew install codex`) or download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
## What's new in the Rust CLI
While we are [working to close the gap between the TypeScript and Rust implementations of Codex CLI](https://github.com/openai/codex/issues/1262), note that the Rust CLI has a number of features that the TypeScript CLI does not!
The Rust implementation is now the maintained Codex CLI and serves as the default experience. It includes a number of features that the legacy TypeScript CLI never supported.
### Config
@@ -25,17 +25,19 @@ Codex supports a rich set of configuration options. Note that the Rust CLI uses
Codex CLI functions as an MCP client that can connect to MCP servers on startup. See the [`mcp_servers`](../docs/config.md#mcp_servers) section in the configuration documentation for details.
It is still experimental, but you can also launch Codex as an MCP _server_ by running `codex mcp`. Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
It is still experimental, but you can also launch Codex as an MCP _server_ by running `codex mcp-server`. Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
```shell
npx @modelcontextprotocol/inspector codex mcp
npx @modelcontextprotocol/inspector codex mcp-server
```
Use `codex mcp` to add/list/get/remove MCP server launchers defined in `config.toml`, and `codex mcp-server` to run the MCP server directly.
### Notifications
You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS.
### `codex exec` to run Codex programmatially/non-interactively
### `codex exec` to run Codex programmatically/non-interactively
To run Codex non-interactively, run `codex exec PROMPT` (you can also pass the prompt via `stdin`) and Codex will work on your task until it decides that it is done and exits. Output is printed to the terminal directly. You can set the `RUST_LOG` environment variable to see more about what's going on.

View File

@@ -8,9 +8,9 @@ name = "codex_ansi_escape"
path = "src/lib.rs"
[dependencies]
ansi-to-tui = "7.0.0"
ratatui = { version = "0.29.0", features = [
ansi-to-tui = { workspace = true }
ratatui = { workspace = true, features = [
"unstable-rendered-line-info",
"unstable-widget-ref",
] }
tracing = { version = "0.1.41", features = ["log"] }
tracing = { workspace = true, features = ["log"] }

View File

@@ -0,0 +1,24 @@
[package]
edition = "2024"
name = "codex-app-server-protocol"
version = { workspace = true }
[lib]
name = "codex_app_server_protocol"
path = "src/lib.rs"
[lints]
workspace = true
[dependencies]
codex-protocol = { workspace = true }
paste = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
strum_macros = { workspace = true }
ts-rs = { workspace = true }
uuid = { workspace = true, features = ["serde", "v7"] }
[dev-dependencies]
anyhow = { workspace = true }
pretty_assertions = { workspace = true }

View File

@@ -0,0 +1,67 @@
//! We do not do true JSON-RPC 2.0, as we neither send nor expect the
//! "jsonrpc": "2.0" field.
use serde::Deserialize;
use serde::Serialize;
use ts_rs::TS;
pub const JSONRPC_VERSION: &str = "2.0";
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, Hash, Eq, TS)]
#[serde(untagged)]
pub enum RequestId {
String(String),
#[ts(type = "number")]
Integer(i64),
}
pub type Result = serde_json::Value;
/// Refers to any valid JSON-RPC object that can be decoded off the wire, or encoded to be sent.
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
#[serde(untagged)]
pub enum JSONRPCMessage {
Request(JSONRPCRequest),
Notification(JSONRPCNotification),
Response(JSONRPCResponse),
Error(JSONRPCError),
}
/// A request that expects a response.
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
pub struct JSONRPCRequest {
pub id: RequestId,
pub method: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub params: Option<serde_json::Value>,
}
/// A notification which does not expect a response.
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
pub struct JSONRPCNotification {
pub method: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub params: Option<serde_json::Value>,
}
/// A successful (non-error) response to a request.
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
pub struct JSONRPCResponse {
pub id: RequestId,
pub result: Result,
}
/// A response to a request that indicates an error occurred.
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
pub struct JSONRPCError {
pub error: JSONRPCErrorError,
pub id: RequestId,
}
#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
pub struct JSONRPCErrorError {
pub code: i64,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub data: Option<serde_json::Value>,
pub message: String,
}

View File

@@ -0,0 +1,5 @@
mod jsonrpc_lite;
mod protocol;
pub use jsonrpc_lite::*;
pub use protocol::*;

View File

@@ -1,58 +1,27 @@
use std::collections::HashMap;
use std::fmt::Display;
use std::path::PathBuf;
use crate::config_types::ReasoningEffort;
use crate::config_types::ReasoningSummary;
use crate::config_types::SandboxMode;
use crate::config_types::Verbosity;
use crate::protocol::AskForApproval;
use crate::protocol::EventMsg;
use crate::protocol::FileChange;
use crate::protocol::ReviewDecision;
use crate::protocol::SandboxPolicy;
use crate::protocol::TurnAbortReason;
use mcp_types::RequestId;
use crate::JSONRPCNotification;
use crate::JSONRPCRequest;
use crate::RequestId;
use codex_protocol::ConversationId;
use codex_protocol::config_types::ReasoningEffort;
use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::config_types::SandboxMode;
use codex_protocol::config_types::Verbosity;
use codex_protocol::protocol::AskForApproval;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::FileChange;
use codex_protocol::protocol::ReviewDecision;
use codex_protocol::protocol::SandboxPolicy;
use codex_protocol::protocol::TurnAbortReason;
use paste::paste;
use serde::Deserialize;
use serde::Serialize;
use strum_macros::Display;
use ts_rs::TS;
use uuid::Uuid;
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize, TS, Hash)]
#[ts(type = "string")]
pub struct ConversationId(pub Uuid);
impl ConversationId {
pub fn new() -> Self {
Self(Uuid::new_v4())
}
}
impl Default for ConversationId {
fn default() -> Self {
Self::new()
}
}
impl Display for ConversationId {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "{}", self.0)
}
}
impl From<Uuid> for ConversationId {
fn from(value: Uuid) -> Self {
Self(value)
}
}
impl From<ConversationId> for Uuid {
fn from(value: ConversationId) -> Self {
value.0
}
}
#[derive(Serialize, Deserialize, Clone, Debug, PartialEq, TS)]
#[ts(type = "string")]
pub struct GitSha(pub String);
@@ -63,98 +32,168 @@ impl GitSha {
}
}
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, TS)]
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, Display, TS)]
#[serde(rename_all = "lowercase")]
pub enum AuthMode {
ApiKey,
ChatGPT,
}
/// Request from the client to the server.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(tag = "method", rename_all = "camelCase")]
pub enum ClientRequest {
/// Generates an `enum ClientRequest` where each variant is a request that the
/// client can send to the server. Each variant has associated `params` and
/// `response` types. Also generates a `export_client_responses()` function to
/// export all response types to TypeScript.
macro_rules! client_request_definitions {
(
$(
$(#[$variant_meta:meta])*
$variant:ident {
params: $(#[$params_meta:meta])* $params:ty,
response: $response:ty,
}
),* $(,)?
) => {
/// Request from the client to the server.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(tag = "method", rename_all = "camelCase")]
pub enum ClientRequest {
$(
$(#[$variant_meta])*
$variant {
#[serde(rename = "id")]
request_id: RequestId,
$(#[$params_meta])*
params: $params,
},
)*
}
pub fn export_client_responses(
out_dir: &::std::path::Path,
) -> ::std::result::Result<(), ::ts_rs::ExportError> {
$(
<$response as ::ts_rs::TS>::export_all_to(out_dir)?;
)*
Ok(())
}
};
}
client_request_definitions! {
Initialize {
params: InitializeParams,
response: InitializeResponse,
},
NewConversation {
#[serde(rename = "id")]
request_id: RequestId,
params: NewConversationParams,
response: NewConversationResponse,
},
/// List recorded Codex conversations (rollouts) with optional pagination and search.
ListConversations {
#[serde(rename = "id")]
request_id: RequestId,
params: ListConversationsParams,
response: ListConversationsResponse,
},
/// Resume a recorded Codex conversation from a rollout file.
ResumeConversation {
#[serde(rename = "id")]
request_id: RequestId,
params: ResumeConversationParams,
response: ResumeConversationResponse,
},
ArchiveConversation {
params: ArchiveConversationParams,
response: ArchiveConversationResponse,
},
SendUserMessage {
#[serde(rename = "id")]
request_id: RequestId,
params: SendUserMessageParams,
response: SendUserMessageResponse,
},
SendUserTurn {
#[serde(rename = "id")]
request_id: RequestId,
params: SendUserTurnParams,
response: SendUserTurnResponse,
},
InterruptConversation {
#[serde(rename = "id")]
request_id: RequestId,
params: InterruptConversationParams,
response: InterruptConversationResponse,
},
AddConversationListener {
#[serde(rename = "id")]
request_id: RequestId,
params: AddConversationListenerParams,
response: AddConversationSubscriptionResponse,
},
RemoveConversationListener {
#[serde(rename = "id")]
request_id: RequestId,
params: RemoveConversationListenerParams,
response: RemoveConversationSubscriptionResponse,
},
GitDiffToRemote {
#[serde(rename = "id")]
request_id: RequestId,
params: GitDiffToRemoteParams,
response: GitDiffToRemoteResponse,
},
LoginApiKey {
params: LoginApiKeyParams,
response: LoginApiKeyResponse,
},
LoginChatGpt {
#[serde(rename = "id")]
request_id: RequestId,
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: LoginChatGptResponse,
},
CancelLoginChatGpt {
#[serde(rename = "id")]
request_id: RequestId,
params: CancelLoginChatGptParams,
response: CancelLoginChatGptResponse,
},
LogoutChatGpt {
#[serde(rename = "id")]
request_id: RequestId,
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: LogoutChatGptResponse,
},
GetAuthStatus {
#[serde(rename = "id")]
request_id: RequestId,
params: GetAuthStatusParams,
response: GetAuthStatusResponse,
},
GetUserSavedConfig {
#[serde(rename = "id")]
request_id: RequestId,
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: GetUserSavedConfigResponse,
},
SetDefaultModel {
params: SetDefaultModelParams,
response: SetDefaultModelResponse,
},
GetUserAgent {
#[serde(rename = "id")]
request_id: RequestId,
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: GetUserAgentResponse,
},
UserInfo {
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: UserInfoResponse,
},
FuzzyFileSearch {
params: FuzzyFileSearchParams,
response: FuzzyFileSearchResponse,
},
/// Execute a command (argv vector) under the server's sandbox.
ExecOneOffCommand {
#[serde(rename = "id")]
request_id: RequestId,
params: ExecOneOffCommandParams,
response: ExecOneOffCommandResponse,
},
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
#[serde(rename_all = "camelCase")]
pub struct InitializeParams {
pub client_info: ClientInfo,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
#[serde(rename_all = "camelCase")]
pub struct ClientInfo {
pub name: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub title: Option<String>,
pub version: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct InitializeResponse {
pub user_agent: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
#[serde(rename_all = "camelCase")]
pub struct NewConversationParams {
@@ -203,6 +242,10 @@ pub struct NewConversationParams {
pub struct NewConversationResponse {
pub conversation_id: ConversationId,
pub model: String,
/// Note this could be ignored by the model.
#[serde(skip_serializing_if = "Option::is_none")]
pub reasoning_effort: Option<ReasoningEffort>,
pub rollout_path: PathBuf,
}
#[derive(Serialize, Deserialize, Debug, Clone, TS)]
@@ -262,10 +305,32 @@ pub struct AddConversationSubscriptionResponse {
pub subscription_id: Uuid,
}
/// The [`ConversationId`] must match the `rollout_path`.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct ArchiveConversationParams {
pub conversation_id: ConversationId,
pub rollout_path: PathBuf,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct ArchiveConversationResponse {}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct RemoveConversationSubscriptionResponse {}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct LoginApiKeyParams {
pub api_key: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct LoginApiKeyResponse {}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct LoginChatGptResponse {
@@ -334,7 +399,7 @@ pub struct ExecOneOffCommandParams {
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct ExecArbitraryCommandResponse {
pub struct ExecOneOffCommandResponse {
pub exit_code: i32,
pub stdout: String,
pub stderr: String,
@@ -345,9 +410,14 @@ pub struct ExecArbitraryCommandResponse {
pub struct GetAuthStatusResponse {
#[serde(skip_serializing_if = "Option::is_none")]
pub auth_method: Option<AuthMode>,
pub preferred_auth_method: AuthMode,
#[serde(skip_serializing_if = "Option::is_none")]
pub auth_token: Option<String>,
// Indicates that auth method must be valid to use the server.
// This can be false if using a custom provider that is configured
// with requires_openai_auth == false.
#[serde(skip_serializing_if = "Option::is_none")]
pub requires_openai_auth: Option<bool>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
@@ -356,12 +426,38 @@ pub struct GetUserAgentResponse {
pub user_agent: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct UserInfoResponse {
/// Note: `alleged_user_email` is not currently verified. We read it from
/// the local auth.json, which the user could theoretically modify. In the
/// future, we may add logic to verify the email against the server before
/// returning it.
pub alleged_user_email: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct GetUserSavedConfigResponse {
pub config: UserSavedConfig,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct SetDefaultModelParams {
/// If set to None, this means `model` should be cleared in config.toml.
#[serde(skip_serializing_if = "Option::is_none")]
pub model: Option<String>,
/// If set to None, this means `model_reasoning_effort` should be cleared
/// in config.toml.
#[serde(skip_serializing_if = "Option::is_none")]
pub reasoning_effort: Option<ReasoningEffort>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct SetDefaultModelResponse {}
/// UserSavedConfig contains a subset of the config. It is meant to expose mcp
/// client-configurable settings that can be specified in the NewConversation
/// and SendUserTurn requests.
@@ -451,7 +547,8 @@ pub struct SendUserTurnParams {
pub approval_policy: AskForApproval,
pub sandbox_policy: SandboxPolicy,
pub model: String,
pub effort: ReasoningEffort,
#[serde(skip_serializing_if = "Option::is_none")]
pub effort: Option<ReasoningEffort>,
pub summary: ReasoningSummary,
}
@@ -506,30 +603,74 @@ pub enum InputItem {
},
}
// TODO(mbolin): Need test to ensure these constants match the enum variants.
/// Generates an `enum ServerRequest` where each variant is a request that the
/// server can send to the client along with the corresponding params and
/// response types. It also generates helper types used by the app/server
/// infrastructure (payload enum, request constructor, and export helpers).
macro_rules! server_request_definitions {
(
$(
$(#[$variant_meta:meta])*
$variant:ident
),* $(,)?
) => {
paste! {
/// Request initiated from the server and sent to the client.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(tag = "method", rename_all = "camelCase")]
pub enum ServerRequest {
$(
$(#[$variant_meta])*
$variant {
#[serde(rename = "id")]
request_id: RequestId,
params: [<$variant Params>],
},
)*
}
pub const APPLY_PATCH_APPROVAL_METHOD: &str = "applyPatchApproval";
pub const EXEC_COMMAND_APPROVAL_METHOD: &str = "execCommandApproval";
#[derive(Debug, Clone, PartialEq)]
pub enum ServerRequestPayload {
$( $variant([<$variant Params>]), )*
}
/// Request initiated from the server and sent to the client.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(tag = "method", rename_all = "camelCase")]
pub enum ServerRequest {
impl ServerRequestPayload {
pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
match self {
$(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
}
}
}
}
pub fn export_server_responses(
out_dir: &::std::path::Path,
) -> ::std::result::Result<(), ::ts_rs::ExportError> {
paste! {
$(<[<$variant Response>] as ::ts_rs::TS>::export_all_to(out_dir)?;)*
}
Ok(())
}
};
}
impl TryFrom<JSONRPCRequest> for ServerRequest {
type Error = serde_json::Error;
fn try_from(value: JSONRPCRequest) -> Result<Self, Self::Error> {
serde_json::from_value(serde_json::to_value(value)?)
}
}
server_request_definitions! {
/// Request to approve a patch.
ApplyPatchApproval {
#[serde(rename = "id")]
request_id: RequestId,
params: ApplyPatchApprovalParams,
},
ApplyPatchApproval,
/// Request to exec a command.
ExecCommandApproval {
#[serde(rename = "id")]
request_id: RequestId,
params: ExecCommandApprovalParams,
},
ExecCommandApproval,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct ApplyPatchApprovalParams {
pub conversation_id: ConversationId,
/// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
@@ -546,6 +687,7 @@ pub struct ApplyPatchApprovalParams {
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct ExecCommandApprovalParams {
pub conversation_id: ConversationId,
/// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
@@ -567,6 +709,32 @@ pub struct ApplyPatchApprovalResponse {
pub decision: ReviewDecision,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
#[ts(rename_all = "camelCase")]
pub struct FuzzyFileSearchParams {
pub query: String,
pub roots: Vec<String>,
// if provided, will cancel any previous request that used the same value
#[serde(skip_serializing_if = "Option::is_none")]
pub cancellation_token: Option<String>,
}
/// Superset of [`codex_file_search::FileMatch`]
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
pub struct FuzzyFileSearchResult {
pub root: String,
pub path: String,
pub score: u32,
#[serde(skip_serializing_if = "Option::is_none")]
pub indices: Option<Vec<u32>>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
pub struct FuzzyFileSearchResponse {
pub files: Vec<FuzzyFileSearchResult>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct LoginChatGptCompleteNotification {
@@ -576,6 +744,34 @@ pub struct LoginChatGptCompleteNotification {
pub error: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, TS)]
#[serde(rename_all = "camelCase")]
pub struct SessionConfiguredNotification {
/// Name left as session_id instead of conversation_id for backwards compatibility.
pub session_id: ConversationId,
/// Tell the client what model is being queried.
pub model: String,
/// The effort the model is putting into reasoning about the user's request.
#[serde(skip_serializing_if = "Option::is_none")]
pub reasoning_effort: Option<ReasoningEffort>,
/// Identifier of the history log file (inode on Unix, 0 otherwise).
pub history_log_id: u64,
/// Current number of entries in the history log.
#[ts(type = "number")]
pub history_entry_count: usize,
/// Optional initial messages (as events) for resumed sessions.
/// When present, UIs can use these to seed the history.
#[serde(skip_serializing_if = "Option::is_none")]
pub initial_messages: Option<Vec<EventMsg>>,
pub rollout_path: PathBuf,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
#[serde(rename_all = "camelCase")]
pub struct AuthStatusChangeNotification {
@@ -584,7 +780,8 @@ pub struct AuthStatusChangeNotification {
pub auth_method: Option<AuthMode>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS, Display)]
/// Notification sent from the server to the client.
#[derive(Serialize, Deserialize, Debug, Clone, TS, Display)]
#[serde(tag = "method", content = "params", rename_all = "camelCase")]
#[strum(serialize_all = "camelCase")]
pub enum ServerNotification {
@@ -593,6 +790,9 @@ pub enum ServerNotification {
/// ChatGPT login flow completed
LoginChatGptComplete(LoginChatGptCompleteNotification),
/// The special session configured event for a new or resumed conversation.
SessionConfigured(SessionConfiguredNotification),
}
impl ServerNotification {
@@ -600,22 +800,40 @@ impl ServerNotification {
match self {
ServerNotification::AuthStatusChange(params) => serde_json::to_value(params),
ServerNotification::LoginChatGptComplete(params) => serde_json::to_value(params),
ServerNotification::SessionConfigured(params) => serde_json::to_value(params),
}
}
}
impl TryFrom<JSONRPCNotification> for ServerNotification {
type Error = serde_json::Error;
fn try_from(value: JSONRPCNotification) -> Result<Self, Self::Error> {
serde_json::from_value(serde_json::to_value(value)?)
}
}
/// Notification sent from the client to the server.
#[derive(Serialize, Deserialize, Debug, Clone, TS, Display)]
#[serde(tag = "method", content = "params", rename_all = "camelCase")]
#[strum(serialize_all = "camelCase")]
pub enum ClientNotification {
Initialized,
}
#[cfg(test)]
mod tests {
use super::*;
use anyhow::Result;
use pretty_assertions::assert_eq;
use serde_json::json;
#[test]
fn serialize_new_conversation() {
fn serialize_new_conversation() -> Result<()> {
let request = ClientRequest::NewConversation {
request_id: RequestId::Integer(42),
params: NewConversationParams {
model: Some("gpt-5".to_string()),
model: Some("gpt-5-codex".to_string()),
profile: None,
cwd: None,
approval_policy: Some(AskForApproval::OnRequest),
@@ -631,17 +849,83 @@ mod tests {
"method": "newConversation",
"id": 42,
"params": {
"model": "gpt-5",
"model": "gpt-5-codex",
"approvalPolicy": "on-request"
}
}),
serde_json::to_value(&request).unwrap(),
serde_json::to_value(&request)?,
);
Ok(())
}
#[test]
fn test_conversation_id_default_is_not_zeroes() {
let id = ConversationId::default();
assert_ne!(id.0, Uuid::nil());
fn conversation_id_serializes_as_plain_string() -> Result<()> {
let id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
assert_eq!(
json!("67e55044-10b1-426f-9247-bb680e5fe0c8"),
serde_json::to_value(id)?
);
Ok(())
}
#[test]
fn conversation_id_deserializes_from_plain_string() -> Result<()> {
let id: ConversationId =
serde_json::from_value(json!("67e55044-10b1-426f-9247-bb680e5fe0c8"))?;
assert_eq!(
ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?,
id,
);
Ok(())
}
#[test]
fn serialize_client_notification() -> Result<()> {
let notification = ClientNotification::Initialized;
// Note there is no "params" field for this notification.
assert_eq!(
json!({
"method": "initialized",
}),
serde_json::to_value(&notification)?,
);
Ok(())
}
#[test]
fn serialize_server_request() -> Result<()> {
let conversation_id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
let params = ExecCommandApprovalParams {
conversation_id,
call_id: "call-42".to_string(),
command: vec!["echo".to_string(), "hello".to_string()],
cwd: PathBuf::from("/tmp"),
reason: Some("because tests".to_string()),
};
let request = ServerRequest::ExecCommandApproval {
request_id: RequestId::Integer(7),
params: params.clone(),
};
assert_eq!(
json!({
"method": "execCommandApproval",
"id": 7,
"params": {
"conversationId": "67e55044-10b1-426f-9247-bb680e5fe0c8",
"callId": "call-42",
"command": ["echo", "hello"],
"cwd": "/tmp",
"reason": "because tests",
}
}),
serde_json::to_value(&request)?,
);
let payload = ServerRequestPayload::ExecCommandApproval(params);
assert_eq!(payload.request_with_id(RequestId::Integer(7)), request);
Ok(())
}
}

View File

@@ -0,0 +1,49 @@
[package]
edition = "2024"
name = "codex-app-server"
version = { workspace = true }
[[bin]]
name = "codex-app-server"
path = "src/main.rs"
[lib]
name = "codex_app_server"
path = "src/lib.rs"
[lints]
workspace = true
[dependencies]
anyhow = { workspace = true }
codex-arg0 = { workspace = true }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
codex-file-search = { workspace = true }
codex-login = { workspace = true }
codex-protocol = { workspace = true }
codex-app-server-protocol = { workspace = true }
codex-utils-json-to-toml = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
tokio = { workspace = true, features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tracing = { workspace = true, features = ["log"] }
tracing-subscriber = { workspace = true, features = ["env-filter", "fmt"] }
uuid = { workspace = true, features = ["serde", "v7"] }
[dev-dependencies]
app_test_support = { workspace = true }
assert_cmd = { workspace = true }
base64 = { workspace = true }
core_test_support = { workspace = true }
os_info = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
toml = { workspace = true }
wiremock = { workspace = true }

View File

@@ -1,8 +1,54 @@
use crate::error_code::INTERNAL_ERROR_CODE;
use crate::error_code::INVALID_REQUEST_ERROR_CODE;
use crate::json_to_toml::json_to_toml;
use crate::fuzzy_file_search::run_fuzzy_file_search;
use crate::outgoing_message::OutgoingMessageSender;
use crate::outgoing_message::OutgoingNotification;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
use codex_app_server_protocol::ApplyPatchApprovalParams;
use codex_app_server_protocol::ApplyPatchApprovalResponse;
use codex_app_server_protocol::ArchiveConversationParams;
use codex_app_server_protocol::ArchiveConversationResponse;
use codex_app_server_protocol::AuthStatusChangeNotification;
use codex_app_server_protocol::ClientRequest;
use codex_app_server_protocol::ConversationSummary;
use codex_app_server_protocol::ExecCommandApprovalParams;
use codex_app_server_protocol::ExecCommandApprovalResponse;
use codex_app_server_protocol::ExecOneOffCommandParams;
use codex_app_server_protocol::ExecOneOffCommandResponse;
use codex_app_server_protocol::FuzzyFileSearchParams;
use codex_app_server_protocol::FuzzyFileSearchResponse;
use codex_app_server_protocol::GetUserAgentResponse;
use codex_app_server_protocol::GetUserSavedConfigResponse;
use codex_app_server_protocol::GitDiffToRemoteResponse;
use codex_app_server_protocol::InputItem as WireInputItem;
use codex_app_server_protocol::InterruptConversationParams;
use codex_app_server_protocol::InterruptConversationResponse;
use codex_app_server_protocol::JSONRPCErrorError;
use codex_app_server_protocol::ListConversationsParams;
use codex_app_server_protocol::ListConversationsResponse;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::LoginApiKeyResponse;
use codex_app_server_protocol::LoginChatGptCompleteNotification;
use codex_app_server_protocol::LoginChatGptResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RemoveConversationListenerParams;
use codex_app_server_protocol::RemoveConversationSubscriptionResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::Result as JsonRpcResult;
use codex_app_server_protocol::ResumeConversationParams;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserMessageResponse;
use codex_app_server_protocol::SendUserTurnParams;
use codex_app_server_protocol::SendUserTurnResponse;
use codex_app_server_protocol::ServerNotification;
use codex_app_server_protocol::ServerRequestPayload;
use codex_app_server_protocol::SessionConfiguredNotification;
use codex_app_server_protocol::SetDefaultModelParams;
use codex_app_server_protocol::SetDefaultModelResponse;
use codex_app_server_protocol::UserInfoResponse;
use codex_app_server_protocol::UserSavedConfig;
use codex_core::AuthManager;
use codex_core::CodexConversation;
use codex_core::ConversationManager;
@@ -11,10 +57,16 @@ use codex_core::NewConversation;
use codex_core::RolloutRecorder;
use codex_core::SessionMeta;
use codex_core::auth::CLIENT_ID;
use codex_core::auth::get_auth_file;
use codex_core::auth::login_with_api_key;
use codex_core::auth::try_read_auth_json;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::config::ConfigToml;
use codex_core::config::load_config_as_toml;
use codex_core::config_edit::CONFIG_KEY_EFFORT;
use codex_core::config_edit::CONFIG_KEY_MODEL;
use codex_core::config_edit::persist_overrides_and_clear_if_none;
use codex_core::default_client::get_codex_user_agent;
use codex_core::exec::ExecParams;
use codex_core::exec_env::create_env;
@@ -30,55 +82,25 @@ use codex_core::protocol::ReviewDecision;
use codex_login::ServerOptions as LoginServerOptions;
use codex_login::ShutdownHandle;
use codex_login::run_login_server;
use codex_protocol::mcp_protocol::APPLY_PATCH_APPROVAL_METHOD;
use codex_protocol::mcp_protocol::AddConversationListenerParams;
use codex_protocol::mcp_protocol::AddConversationSubscriptionResponse;
use codex_protocol::mcp_protocol::ApplyPatchApprovalParams;
use codex_protocol::mcp_protocol::ApplyPatchApprovalResponse;
use codex_protocol::mcp_protocol::AuthMode;
use codex_protocol::mcp_protocol::AuthStatusChangeNotification;
use codex_protocol::mcp_protocol::ClientRequest;
use codex_protocol::mcp_protocol::ConversationId;
use codex_protocol::mcp_protocol::ConversationSummary;
use codex_protocol::mcp_protocol::EXEC_COMMAND_APPROVAL_METHOD;
use codex_protocol::mcp_protocol::ExecArbitraryCommandResponse;
use codex_protocol::mcp_protocol::ExecCommandApprovalParams;
use codex_protocol::mcp_protocol::ExecCommandApprovalResponse;
use codex_protocol::mcp_protocol::ExecOneOffCommandParams;
use codex_protocol::mcp_protocol::GetUserAgentResponse;
use codex_protocol::mcp_protocol::GetUserSavedConfigResponse;
use codex_protocol::mcp_protocol::GitDiffToRemoteResponse;
use codex_protocol::mcp_protocol::InputItem as WireInputItem;
use codex_protocol::mcp_protocol::InterruptConversationParams;
use codex_protocol::mcp_protocol::InterruptConversationResponse;
use codex_protocol::mcp_protocol::ListConversationsParams;
use codex_protocol::mcp_protocol::ListConversationsResponse;
use codex_protocol::mcp_protocol::LoginChatGptCompleteNotification;
use codex_protocol::mcp_protocol::LoginChatGptResponse;
use codex_protocol::mcp_protocol::NewConversationParams;
use codex_protocol::mcp_protocol::NewConversationResponse;
use codex_protocol::mcp_protocol::RemoveConversationListenerParams;
use codex_protocol::mcp_protocol::RemoveConversationSubscriptionResponse;
use codex_protocol::mcp_protocol::ResumeConversationParams;
use codex_protocol::mcp_protocol::SendUserMessageParams;
use codex_protocol::mcp_protocol::SendUserMessageResponse;
use codex_protocol::mcp_protocol::SendUserTurnParams;
use codex_protocol::mcp_protocol::SendUserTurnResponse;
use codex_protocol::mcp_protocol::ServerNotification;
use codex_protocol::mcp_protocol::UserSavedConfig;
use codex_protocol::ConversationId;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ResponseItem;
use codex_protocol::protocol::InputMessageKind;
use codex_protocol::protocol::USER_MESSAGE_BEGIN;
use mcp_types::JSONRPCErrorError;
use mcp_types::RequestId;
use codex_utils_json_to_toml::json_to_toml;
use std::collections::HashMap;
use std::ffi::OsStr;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering;
use std::time::Duration;
use tokio::select;
use tokio::sync::Mutex;
use tokio::sync::oneshot;
use tracing::error;
use tracing::info;
use tracing::warn;
use uuid::Uuid;
// Duration before a ChatGPT login attempt is abandoned.
@@ -106,6 +128,7 @@ pub(crate) struct CodexMessageProcessor {
active_login: Arc<Mutex<Option<ActiveLogin>>>,
// Queue of pending interrupt requests per conversation. We reply when TurnAborted arrives.
pending_interrupts: Arc<Mutex<HashMap<ConversationId, Vec<RequestId>>>>,
pending_fuzzy_searches: Arc<Mutex<HashMap<String, Arc<AtomicBool>>>>,
}
impl CodexMessageProcessor {
@@ -125,11 +148,15 @@ impl CodexMessageProcessor {
conversation_listeners: HashMap::new(),
active_login: Arc::new(Mutex::new(None)),
pending_interrupts: Arc::new(Mutex::new(HashMap::new())),
pending_fuzzy_searches: Arc::new(Mutex::new(HashMap::new())),
}
}
pub async fn process_request(&mut self, request: ClientRequest) {
match request {
ClientRequest::Initialize { .. } => {
panic!("Initialize should be handled in MessageProcessor");
}
ClientRequest::NewConversation { request_id, params } => {
// Do not tokio::spawn() to process new_conversation()
// asynchronously because we need to ensure the conversation is
@@ -142,6 +169,9 @@ impl CodexMessageProcessor {
ClientRequest::ResumeConversation { request_id, params } => {
self.handle_resume_conversation(request_id, params).await;
}
ClientRequest::ArchiveConversation { request_id, params } => {
self.archive_conversation(request_id, params).await;
}
ClientRequest::SendUserMessage { request_id, params } => {
self.send_user_message(request_id, params).await;
}
@@ -160,40 +190,96 @@ impl CodexMessageProcessor {
ClientRequest::GitDiffToRemote { request_id, params } => {
self.git_diff_to_origin(request_id, params.cwd).await;
}
ClientRequest::LoginChatGpt { request_id } => {
ClientRequest::LoginApiKey { request_id, params } => {
self.login_api_key(request_id, params).await;
}
ClientRequest::LoginChatGpt {
request_id,
params: _,
} => {
self.login_chatgpt(request_id).await;
}
ClientRequest::CancelLoginChatGpt { request_id, params } => {
self.cancel_login_chatgpt(request_id, params.login_id).await;
}
ClientRequest::LogoutChatGpt { request_id } => {
ClientRequest::LogoutChatGpt {
request_id,
params: _,
} => {
self.logout_chatgpt(request_id).await;
}
ClientRequest::GetAuthStatus { request_id, params } => {
self.get_auth_status(request_id, params).await;
}
ClientRequest::GetUserSavedConfig { request_id } => {
ClientRequest::GetUserSavedConfig {
request_id,
params: _,
} => {
self.get_user_saved_config(request_id).await;
}
ClientRequest::GetUserAgent { request_id } => {
ClientRequest::SetDefaultModel { request_id, params } => {
self.set_default_model(request_id, params).await;
}
ClientRequest::GetUserAgent {
request_id,
params: _,
} => {
self.get_user_agent(request_id).await;
}
ClientRequest::UserInfo {
request_id,
params: _,
} => {
self.get_user_info(request_id).await;
}
ClientRequest::FuzzyFileSearch { request_id, params } => {
self.fuzzy_file_search(request_id, params).await;
}
ClientRequest::ExecOneOffCommand { request_id, params } => {
self.exec_one_off_command(request_id, params).await;
}
}
}
async fn login_api_key(&mut self, request_id: RequestId, params: LoginApiKeyParams) {
{
let mut guard = self.active_login.lock().await;
if let Some(active) = guard.take() {
active.drop();
}
}
match login_with_api_key(&self.config.codex_home, &params.api_key) {
Ok(()) => {
self.auth_manager.reload();
self.outgoing
.send_response(request_id, LoginApiKeyResponse {})
.await;
let payload = AuthStatusChangeNotification {
auth_method: self.auth_manager.auth().map(|auth| auth.mode),
};
self.outgoing
.send_server_notification(ServerNotification::AuthStatusChange(payload))
.await;
}
Err(err) => {
let error = JSONRPCErrorError {
code: INTERNAL_ERROR_CODE,
message: format!("failed to save api key: {err}"),
data: None,
};
self.outgoing.send_error(request_id, error).await;
}
}
}
async fn login_chatgpt(&mut self, request_id: RequestId) {
let config = self.config.as_ref();
let opts = LoginServerOptions {
open_browser: false,
..LoginServerOptions::new(
config.codex_home.clone(),
CLIENT_ID.to_string(),
config.responses_originator_header.clone(),
)
..LoginServerOptions::new(config.codex_home.clone(), CLIENT_ID.to_string())
};
enum LoginChatGptReply {
@@ -300,7 +386,7 @@ impl CodexMessageProcessor {
self.outgoing
.send_response(
request_id,
codex_protocol::mcp_protocol::CancelLoginChatGptResponse {},
codex_app_server_protocol::CancelLoginChatGptResponse {},
)
.await;
} else {
@@ -336,12 +422,12 @@ impl CodexMessageProcessor {
self.outgoing
.send_response(
request_id,
codex_protocol::mcp_protocol::LogoutChatGptResponse {},
codex_app_server_protocol::LogoutChatGptResponse {},
)
.await;
// Send auth status change notification reflecting the current auth mode
// after logout (which may fall back to API key via env var).
// after logout.
let current_auth_method = self.auth_manager.auth().map(|auth| auth.mode);
let payload = AuthStatusChangeNotification {
auth_method: current_auth_method,
@@ -354,9 +440,8 @@ impl CodexMessageProcessor {
async fn get_auth_status(
&self,
request_id: RequestId,
params: codex_protocol::mcp_protocol::GetAuthStatusParams,
params: codex_app_server_protocol::GetAuthStatusParams,
) {
let preferred_auth_method: AuthMode = self.auth_manager.preferred_auth_method();
let include_token = params.include_token.unwrap_or(false);
let do_refresh = params.refresh_token.unwrap_or(false);
@@ -364,37 +449,51 @@ impl CodexMessageProcessor {
tracing::warn!("failed to refresh token while getting auth status: {err}");
}
let response = match self.auth_manager.auth() {
Some(auth) => {
let (reported_auth_method, token_opt) = match auth.get_token().await {
Ok(token) if !token.is_empty() => {
let tok = if include_token { Some(token) } else { None };
(Some(auth.mode), tok)
}
Ok(_) => (None, None),
Err(err) => {
tracing::warn!("failed to get token for auth status: {err}");
(None, None)
}
};
codex_protocol::mcp_protocol::GetAuthStatusResponse {
auth_method: reported_auth_method,
preferred_auth_method,
auth_token: token_opt,
}
}
None => codex_protocol::mcp_protocol::GetAuthStatusResponse {
// Determine whether auth is required based on the active model provider.
// If a custom provider is configured with `requires_openai_auth == false`,
// then no auth step is required; otherwise, default to requiring auth.
let requires_openai_auth = self.config.model_provider.requires_openai_auth;
let response = if !requires_openai_auth {
codex_app_server_protocol::GetAuthStatusResponse {
auth_method: None,
preferred_auth_method,
auth_token: None,
},
requires_openai_auth: Some(false),
}
} else {
match self.auth_manager.auth() {
Some(auth) => {
let auth_mode = auth.mode;
let (reported_auth_method, token_opt) = match auth.get_token().await {
Ok(token) if !token.is_empty() => {
let tok = if include_token { Some(token) } else { None };
(Some(auth_mode), tok)
}
Ok(_) => (None, None),
Err(err) => {
tracing::warn!("failed to get token for auth status: {err}");
(None, None)
}
};
codex_app_server_protocol::GetAuthStatusResponse {
auth_method: reported_auth_method,
auth_token: token_opt,
requires_openai_auth: Some(true),
}
}
None => codex_app_server_protocol::GetAuthStatusResponse {
auth_method: None,
auth_token: None,
requires_openai_auth: Some(true),
},
}
};
self.outgoing.send_response(request_id, response).await;
}
async fn get_user_agent(&self, request_id: RequestId) {
let user_agent = get_codex_user_agent(Some(&self.config.responses_originator_header));
let user_agent = get_codex_user_agent();
let response = GetUserAgentResponse { user_agent };
self.outgoing.send_response(request_id, response).await;
}
@@ -434,6 +533,52 @@ impl CodexMessageProcessor {
self.outgoing.send_response(request_id, response).await;
}
async fn get_user_info(&self, request_id: RequestId) {
// Read alleged user email from auth.json (best-effort; not verified).
let auth_path = get_auth_file(&self.config.codex_home);
let alleged_user_email = match try_read_auth_json(&auth_path) {
Ok(auth) => auth.tokens.and_then(|t| t.id_token.email),
Err(_) => None,
};
let response = UserInfoResponse { alleged_user_email };
self.outgoing.send_response(request_id, response).await;
}
async fn set_default_model(&self, request_id: RequestId, params: SetDefaultModelParams) {
let SetDefaultModelParams {
model,
reasoning_effort,
} = params;
let effort_str = reasoning_effort.map(|effort| effort.to_string());
let overrides: [(&[&str], Option<&str>); 2] = [
(&[CONFIG_KEY_MODEL], model.as_deref()),
(&[CONFIG_KEY_EFFORT], effort_str.as_deref()),
];
match persist_overrides_and_clear_if_none(
&self.config.codex_home,
self.config.active_profile.as_deref(),
&overrides,
)
.await
{
Ok(()) => {
let response = SetDefaultModelResponse {};
self.outgoing.send_response(request_id, response).await;
}
Err(err) => {
let error = JSONRPCErrorError {
code: INTERNAL_ERROR_CODE,
message: format!("failed to persist overrides: {err}"),
data: None,
};
self.outgoing.send_error(request_id, error).await;
}
}
}
async fn exec_one_off_command(&self, request_id: RequestId, params: ExecOneOffCommandParams) {
tracing::debug!("ExecOneOffCommand params: {params:?}");
@@ -473,19 +618,21 @@ impl CodexMessageProcessor {
let codex_linux_sandbox_exe = self.config.codex_linux_sandbox_exe.clone();
let outgoing = self.outgoing.clone();
let req_id = request_id;
let sandbox_cwd = self.config.cwd.clone();
tokio::spawn(async move {
match codex_core::exec::process_exec_tool_call(
exec_params,
sandbox_type,
&effective_policy,
sandbox_cwd.as_path(),
&codex_linux_sandbox_exe,
None,
)
.await
{
Ok(output) => {
let response = ExecArbitraryCommandResponse {
let response = ExecOneOffCommandResponse {
exit_code: output.exit_code,
stdout: output.stdout.text,
stderr: output.stderr.text,
@@ -528,6 +675,8 @@ impl CodexMessageProcessor {
let response = NewConversationResponse {
conversation_id,
model: session_configured.model,
reasoning_effort: session_configured.reasoning_effort,
rollout_path: session_configured.rollout_path,
};
self.outgoing.send_response(request_id, response).await;
}
@@ -632,11 +781,19 @@ impl CodexMessageProcessor {
session_configured,
..
}) => {
let event = Event {
id: "".to_string(),
msg: EventMsg::SessionConfigured(session_configured.clone()),
};
self.outgoing.send_event_as_notification(&event, None).await;
self.outgoing
.send_server_notification(ServerNotification::SessionConfigured(
SessionConfiguredNotification {
session_id: session_configured.session_id,
model: session_configured.model.clone(),
reasoning_effort: session_configured.reasoning_effort,
history_log_id: session_configured.history_log_id,
history_entry_count: session_configured.history_entry_count,
initial_messages: session_configured.initial_messages.clone(),
rollout_path: session_configured.rollout_path.clone(),
},
))
.await;
let initial_messages = session_configured.initial_messages.map(|msgs| {
msgs.into_iter()
.filter(|event| {
@@ -651,7 +808,7 @@ impl CodexMessageProcessor {
});
// Reply with conversation id + model and initial messages (when present)
let response = codex_protocol::mcp_protocol::ResumeConversationResponse {
let response = codex_app_server_protocol::ResumeConversationResponse {
conversation_id,
model: session_configured.model.clone(),
initial_messages,
@@ -669,6 +826,141 @@ impl CodexMessageProcessor {
}
}
async fn archive_conversation(&self, request_id: RequestId, params: ArchiveConversationParams) {
let ArchiveConversationParams {
conversation_id,
rollout_path,
} = params;
// Verify that the rollout path is in the sessions directory or else
// a malicious client could specify an arbitrary path.
let rollout_folder = self.config.codex_home.join(codex_core::SESSIONS_SUBDIR);
let canonical_rollout_path = tokio::fs::canonicalize(&rollout_path).await;
let canonical_rollout_path = if let Ok(path) = canonical_rollout_path
&& path.starts_with(&rollout_folder)
{
path
} else {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: format!(
"rollout path `{}` must be in sessions directory",
rollout_path.display()
),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
};
let required_suffix = format!("{conversation_id}.jsonl");
let Some(file_name) = canonical_rollout_path.file_name().map(OsStr::to_owned) else {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: format!(
"rollout path `{}` missing file name",
rollout_path.display()
),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
};
if !file_name
.to_string_lossy()
.ends_with(required_suffix.as_str())
{
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: format!(
"rollout path `{}` does not match conversation id {conversation_id}",
rollout_path.display()
),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
}
let removed_conversation = self
.conversation_manager
.remove_conversation(&conversation_id)
.await;
if let Some(conversation) = removed_conversation {
info!("conversation {conversation_id} was active; shutting down");
let conversation_clone = conversation.clone();
let notify = Arc::new(tokio::sync::Notify::new());
let notify_clone = notify.clone();
// Establish the listener for ShutdownComplete before submitting
// Shutdown so it is not missed.
let is_shutdown = tokio::spawn(async move {
loop {
select! {
_ = notify_clone.notified() => {
break;
}
event = conversation_clone.next_event() => {
if let Ok(event) = event && matches!(event.msg, EventMsg::ShutdownComplete) {
break;
}
}
}
}
});
// Request shutdown.
match conversation.submit(Op::Shutdown).await {
Ok(_) => {
// Successfully submitted Shutdown; wait before proceeding.
select! {
_ = is_shutdown => {
// Normal shutdown: proceed with archive.
}
_ = tokio::time::sleep(Duration::from_secs(10)) => {
warn!("conversation {conversation_id} shutdown timed out; proceeding with archive");
notify.notify_one();
}
}
}
Err(err) => {
error!("failed to submit Shutdown to conversation {conversation_id}: {err}");
notify.notify_one();
// Perhaps we lost a shutdown race, so let's continue to
// clean up the .jsonl file.
}
}
}
// Move the .jsonl file to the archived sessions subdir.
let result: std::io::Result<()> = async {
let archive_folder = self
.config
.codex_home
.join(codex_core::ARCHIVED_SESSIONS_SUBDIR);
tokio::fs::create_dir_all(&archive_folder).await?;
tokio::fs::rename(&canonical_rollout_path, &archive_folder.join(&file_name)).await?;
Ok(())
}
.await;
match result {
Ok(()) => {
let response = ArchiveConversationResponse {};
self.outgoing.send_response(request_id, response).await;
}
Err(err) => {
let error = JSONRPCErrorError {
code: INTERNAL_ERROR_CODE,
message: format!("failed to archive conversation: {err}"),
data: None,
};
self.outgoing.send_error(request_id, error).await;
}
}
}
async fn send_user_message(&self, request_id: RequestId, params: SendUserMessageParams) {
let SendUserMessageParams {
conversation_id,
@@ -754,6 +1046,7 @@ impl CodexMessageProcessor {
model,
effort,
summary,
final_output_json_schema: None,
})
.await;
@@ -911,6 +1204,46 @@ impl CodexMessageProcessor {
}
}
}
async fn fuzzy_file_search(&mut self, request_id: RequestId, params: FuzzyFileSearchParams) {
let FuzzyFileSearchParams {
query,
roots,
cancellation_token,
} = params;
let cancel_flag = match cancellation_token.clone() {
Some(token) => {
let mut pending_fuzzy_searches = self.pending_fuzzy_searches.lock().await;
// if a cancellation_token is provided and a pending_request exists for
// that token, cancel it
if let Some(existing) = pending_fuzzy_searches.get(&token) {
existing.store(true, Ordering::Relaxed);
}
let flag = Arc::new(AtomicBool::new(false));
pending_fuzzy_searches.insert(token.clone(), flag.clone());
flag
}
None => Arc::new(AtomicBool::new(false)),
};
let results = match query.as_str() {
"" => vec![],
_ => run_fuzzy_file_search(query, roots, cancel_flag.clone()).await,
};
if let Some(token) = cancellation_token {
let mut pending_fuzzy_searches = self.pending_fuzzy_searches.lock().await;
if let Some(current_flag) = pending_fuzzy_searches.get(&token)
&& Arc::ptr_eq(current_flag, &cancel_flag)
{
pending_fuzzy_searches.remove(&token);
}
}
let response = FuzzyFileSearchResponse { files: results };
self.outgoing.send_response(request_id, response).await;
}
}
async fn apply_bespoke_event_handling(
@@ -935,9 +1268,8 @@ async fn apply_bespoke_event_handling(
reason,
grant_root,
};
let value = serde_json::to_value(&params).unwrap_or_default();
let rx = outgoing
.send_request(APPLY_PATCH_APPROVAL_METHOD, Some(value))
.send_request(ServerRequestPayload::ApplyPatchApproval(params))
.await;
// TODO(mbolin): Enforce a timeout so this task does not live indefinitely?
tokio::spawn(async move {
@@ -957,9 +1289,8 @@ async fn apply_bespoke_event_handling(
cwd,
reason,
};
let value = serde_json::to_value(&params).unwrap_or_default();
let rx = outgoing
.send_request(EXEC_COMMAND_APPROVAL_METHOD, Some(value))
.send_request(ServerRequestPayload::ExecCommandApproval(params))
.await;
// TODO(mbolin): Enforce a timeout so this task does not live indefinitely?
@@ -1004,6 +1335,7 @@ fn derive_config_from_params(
} = params;
let overrides = ConfigOverrides {
model,
review_model: None,
config_profile: profile,
cwd: cwd.map(PathBuf::from),
approval_policy,
@@ -1029,7 +1361,7 @@ fn derive_config_from_params(
async fn on_patch_approval_response(
event_id: String,
receiver: oneshot::Receiver<mcp_types::Result>,
receiver: oneshot::Receiver<JsonRpcResult>,
codex: Arc<CodexConversation>,
) {
let response = receiver.await;
@@ -1071,7 +1403,7 @@ async fn on_patch_approval_response(
async fn on_exec_approval_response(
event_id: String,
receiver: oneshot::Receiver<mcp_types::Result>,
receiver: oneshot::Receiver<JsonRpcResult>,
conversation: Arc<CodexConversation>,
) {
let response = receiver.await;
@@ -1110,10 +1442,7 @@ fn extract_conversation_summary(
head: &[serde_json::Value],
) -> Option<ConversationSummary> {
let session_meta = match head.first() {
Some(first_line) => match serde_json::from_value::<SessionMeta>(first_line.clone()) {
Ok(session_meta) => session_meta,
Err(..) => return None,
},
Some(first_line) => serde_json::from_value::<SessionMeta>(first_line.clone()).ok()?,
None => return None,
};
@@ -1157,20 +1486,24 @@ fn extract_conversation_summary(
#[cfg(test)]
mod tests {
use super::*;
use anyhow::Result;
use pretty_assertions::assert_eq;
use serde_json::json;
#[test]
fn extract_conversation_summary_prefers_plain_user_messages() {
let conversation_id =
ConversationId(Uuid::parse_str("3f941c35-29b3-493b-b0a4-e25800d9aeb0").unwrap());
fn extract_conversation_summary_prefers_plain_user_messages() -> Result<()> {
let conversation_id = ConversationId::from_string("3f941c35-29b3-493b-b0a4-e25800d9aeb0")?;
let timestamp = Some("2025-09-05T16:53:11.850Z".to_string());
let path = PathBuf::from("rollout.jsonl");
let head = vec![
json!({
"id": conversation_id.0,
"id": conversation_id.to_string(),
"timestamp": timestamp,
"cwd": "/",
"originator": "codex",
"cli_version": "0.0.0",
"instructions": null
}),
json!({
"type": "message",
@@ -1199,5 +1532,6 @@ mod tests {
);
assert_eq!(summary.path, path);
assert_eq!(summary.preview, "Count to 5");
Ok(())
}
}

View File

@@ -0,0 +1,2 @@
pub(crate) const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
pub(crate) const INTERNAL_ERROR_CODE: i64 = -32603;

View File

@@ -0,0 +1,84 @@
use std::num::NonZero;
use std::num::NonZeroUsize;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::atomic::AtomicBool;
use codex_app_server_protocol::FuzzyFileSearchResult;
use codex_file_search as file_search;
use tokio::task::JoinSet;
use tracing::warn;
const LIMIT_PER_ROOT: usize = 50;
const MAX_THREADS: usize = 12;
const COMPUTE_INDICES: bool = true;
pub(crate) async fn run_fuzzy_file_search(
query: String,
roots: Vec<String>,
cancellation_flag: Arc<AtomicBool>,
) -> Vec<FuzzyFileSearchResult> {
#[expect(clippy::expect_used)]
let limit_per_root =
NonZero::new(LIMIT_PER_ROOT).expect("LIMIT_PER_ROOT should be a valid non-zero usize");
let cores = std::thread::available_parallelism()
.map(std::num::NonZero::get)
.unwrap_or(1);
let threads = cores.min(MAX_THREADS);
let threads_per_root = (threads / roots.len()).max(1);
let threads = NonZero::new(threads_per_root).unwrap_or(NonZeroUsize::MIN);
let mut files: Vec<FuzzyFileSearchResult> = Vec::new();
let mut join_set = JoinSet::new();
for root in roots {
let search_dir = PathBuf::from(&root);
let query = query.clone();
let cancel_flag = cancellation_flag.clone();
join_set.spawn_blocking(move || {
match file_search::run(
query.as_str(),
limit_per_root,
&search_dir,
Vec::new(),
threads,
cancel_flag,
COMPUTE_INDICES,
) {
Ok(res) => Ok((root, res)),
Err(err) => Err((root, err)),
}
});
}
while let Some(res) = join_set.join_next().await {
match res {
Ok(Ok((root, res))) => {
for m in res.matches {
let result = FuzzyFileSearchResult {
root: root.clone(),
path: m.path,
score: m.score,
indices: m.indices,
};
files.push(result);
}
}
Ok(Err((root, err))) => {
warn!("fuzzy-file-search in dir '{root}' failed: {err}");
}
Err(err) => {
warn!("fuzzy-file-search join_next failed: {err}");
}
}
}
files.sort_by(file_search::cmp_by_score_desc_then_path_asc::<
FuzzyFileSearchResult,
_,
_,
>(|f| f.score, |f| f.path.as_str()));
files
}

View File

@@ -0,0 +1,139 @@
#![deny(clippy::print_stdout, clippy::print_stderr)]
use std::io::ErrorKind;
use std::io::Result as IoResult;
use std::path::PathBuf;
use codex_common::CliConfigOverrides;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_app_server_protocol::JSONRPCMessage;
use tokio::io::AsyncBufReadExt;
use tokio::io::AsyncWriteExt;
use tokio::io::BufReader;
use tokio::io::{self};
use tokio::sync::mpsc;
use tracing::debug;
use tracing::error;
use tracing::info;
use tracing_subscriber::EnvFilter;
use crate::message_processor::MessageProcessor;
use crate::outgoing_message::OutgoingMessage;
use crate::outgoing_message::OutgoingMessageSender;
mod codex_message_processor;
mod error_code;
mod fuzzy_file_search;
mod message_processor;
mod outgoing_message;
/// Size of the bounded channels used to communicate between tasks. The value
/// is a balance between throughput and memory usage 128 messages should be
/// plenty for an interactive CLI.
const CHANNEL_CAPACITY: usize = 128;
pub async fn run_main(
codex_linux_sandbox_exe: Option<PathBuf>,
cli_config_overrides: CliConfigOverrides,
) -> IoResult<()> {
// Install a simple subscriber so `tracing` output is visible. Users can
// control the log level with `RUST_LOG`.
tracing_subscriber::fmt()
.with_writer(std::io::stderr)
.with_env_filter(EnvFilter::from_default_env())
.init();
// Set up channels.
let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
let (outgoing_tx, mut outgoing_rx) = mpsc::unbounded_channel::<OutgoingMessage>();
// Task: read from stdin, push to `incoming_tx`.
let stdin_reader_handle = tokio::spawn({
async move {
let stdin = io::stdin();
let reader = BufReader::new(stdin);
let mut lines = reader.lines();
while let Some(line) = lines.next_line().await.unwrap_or_default() {
match serde_json::from_str::<JSONRPCMessage>(&line) {
Ok(msg) => {
if incoming_tx.send(msg).await.is_err() {
// Receiver gone nothing left to do.
break;
}
}
Err(e) => error!("Failed to deserialize JSONRPCMessage: {e}"),
}
}
debug!("stdin reader finished (EOF)");
}
});
// Parse CLI overrides once and derive the base Config eagerly so later
// components do not need to work with raw TOML values.
let cli_kv_overrides = cli_config_overrides.parse_overrides().map_err(|e| {
std::io::Error::new(
ErrorKind::InvalidInput,
format!("error parsing -c overrides: {e}"),
)
})?;
let config = Config::load_with_cli_overrides(cli_kv_overrides, ConfigOverrides::default())
.map_err(|e| {
std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
})?;
// Task: process incoming messages.
let processor_handle = tokio::spawn({
let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
let mut processor = MessageProcessor::new(
outgoing_message_sender,
codex_linux_sandbox_exe,
std::sync::Arc::new(config),
);
async move {
while let Some(msg) = incoming_rx.recv().await {
match msg {
JSONRPCMessage::Request(r) => processor.process_request(r).await,
JSONRPCMessage::Response(r) => processor.process_response(r).await,
JSONRPCMessage::Notification(n) => processor.process_notification(n).await,
JSONRPCMessage::Error(e) => processor.process_error(e),
}
}
info!("processor task exited (channel closed)");
}
});
// Task: write outgoing messages to stdout.
let stdout_writer_handle = tokio::spawn(async move {
let mut stdout = io::stdout();
while let Some(outgoing_message) = outgoing_rx.recv().await {
let Ok(value) = serde_json::to_value(outgoing_message) else {
error!("Failed to convert OutgoingMessage to JSON value");
continue;
};
match serde_json::to_string(&value) {
Ok(mut json) => {
json.push('\n');
if let Err(e) = stdout.write_all(json.as_bytes()).await {
error!("Failed to write to stdout: {e}");
break;
}
}
Err(e) => error!("Failed to serialize JSONRPCMessage: {e}"),
}
}
info!("stdout writer exited (channel closed)");
});
// Wait for all tasks to finish. The typical exit path is the stdin reader
// hitting EOF which, once it drops `incoming_tx`, propagates shutdown to
// the processor and then to the stdout task.
let _ = tokio::join!(stdin_reader_handle, processor_handle, stdout_writer_handle);
Ok(())
}

View File

@@ -0,0 +1,10 @@
use codex_app_server::run_main;
use codex_arg0::arg0_dispatch_or_else;
use codex_common::CliConfigOverrides;
fn main() -> anyhow::Result<()> {
arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
run_main(codex_linux_sandbox_exe, CliConfigOverrides::default()).await?;
Ok(())
})
}

View File

@@ -0,0 +1,133 @@
use std::path::PathBuf;
use crate::codex_message_processor::CodexMessageProcessor;
use crate::error_code::INVALID_REQUEST_ERROR_CODE;
use crate::outgoing_message::OutgoingMessageSender;
use codex_app_server_protocol::ClientInfo;
use codex_app_server_protocol::ClientRequest;
use codex_app_server_protocol::InitializeResponse;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCErrorError;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCRequest;
use codex_app_server_protocol::JSONRPCResponse;
use codex_core::AuthManager;
use codex_core::ConversationManager;
use codex_core::config::Config;
use codex_core::default_client::USER_AGENT_SUFFIX;
use codex_core::default_client::get_codex_user_agent;
use std::sync::Arc;
pub(crate) struct MessageProcessor {
outgoing: Arc<OutgoingMessageSender>,
codex_message_processor: CodexMessageProcessor,
initialized: bool,
}
impl MessageProcessor {
/// Create a new `MessageProcessor`, retaining a handle to the outgoing
/// `Sender` so handlers can enqueue messages to be written to stdout.
pub(crate) fn new(
outgoing: OutgoingMessageSender,
codex_linux_sandbox_exe: Option<PathBuf>,
config: Arc<Config>,
) -> Self {
let outgoing = Arc::new(outgoing);
let auth_manager = AuthManager::shared(config.codex_home.clone());
let conversation_manager = Arc::new(ConversationManager::new(auth_manager.clone()));
let codex_message_processor = CodexMessageProcessor::new(
auth_manager,
conversation_manager,
outgoing.clone(),
codex_linux_sandbox_exe,
config,
);
Self {
outgoing,
codex_message_processor,
initialized: false,
}
}
pub(crate) async fn process_request(&mut self, request: JSONRPCRequest) {
let request_id = request.id.clone();
if let Ok(request_json) = serde_json::to_value(request)
&& let Ok(codex_request) = serde_json::from_value::<ClientRequest>(request_json)
{
match codex_request {
// Handle Initialize internally so CodexMessageProcessor does not have to concern
// itself with the `initialized` bool.
ClientRequest::Initialize { request_id, params } => {
if self.initialized {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Already initialized".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
} else {
let ClientInfo {
name,
title: _title,
version,
} = params.client_info;
let user_agent_suffix = format!("{name}; {version}");
if let Ok(mut suffix) = USER_AGENT_SUFFIX.lock() {
*suffix = Some(user_agent_suffix);
}
let user_agent = get_codex_user_agent();
let response = InitializeResponse { user_agent };
self.outgoing.send_response(request_id, response).await;
self.initialized = true;
return;
}
}
_ => {
if !self.initialized {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Not initialized".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
}
}
}
self.codex_message_processor
.process_request(codex_request)
.await;
} else {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Invalid request".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
}
}
pub(crate) async fn process_notification(&self, notification: JSONRPCNotification) {
// Currently, we do not expect to receive any notifications from the
// client, so we just log them.
tracing::info!("<- notification: {:?}", notification);
}
/// Handle a standalone JSON-RPC response originating from the peer.
pub(crate) async fn process_response(&mut self, response: JSONRPCResponse) {
tracing::info!("<- response: {:?}", response);
let JSONRPCResponse { id, result, .. } = response;
self.outgoing.notify_client_response(id, result).await
}
/// Handle an error object received from the peer.
pub(crate) fn process_error(&mut self, err: JSONRPCError) {
tracing::error!("<- error: {:?}", err);
}
}

View File

@@ -0,0 +1,174 @@
use std::collections::HashMap;
use std::sync::atomic::AtomicI64;
use std::sync::atomic::Ordering;
use codex_app_server_protocol::JSONRPCErrorError;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::Result;
use codex_app_server_protocol::ServerNotification;
use codex_app_server_protocol::ServerRequest;
use codex_app_server_protocol::ServerRequestPayload;
use serde::Serialize;
use tokio::sync::Mutex;
use tokio::sync::mpsc;
use tokio::sync::oneshot;
use tracing::warn;
use crate::error_code::INTERNAL_ERROR_CODE;
/// Sends messages to the client and manages request callbacks.
pub(crate) struct OutgoingMessageSender {
next_request_id: AtomicI64,
sender: mpsc::UnboundedSender<OutgoingMessage>,
request_id_to_callback: Mutex<HashMap<RequestId, oneshot::Sender<Result>>>,
}
impl OutgoingMessageSender {
pub(crate) fn new(sender: mpsc::UnboundedSender<OutgoingMessage>) -> Self {
Self {
next_request_id: AtomicI64::new(0),
sender,
request_id_to_callback: Mutex::new(HashMap::new()),
}
}
pub(crate) async fn send_request(
&self,
request: ServerRequestPayload,
) -> oneshot::Receiver<Result> {
let id = RequestId::Integer(self.next_request_id.fetch_add(1, Ordering::Relaxed));
let outgoing_message_id = id.clone();
let (tx_approve, rx_approve) = oneshot::channel();
{
let mut request_id_to_callback = self.request_id_to_callback.lock().await;
request_id_to_callback.insert(id, tx_approve);
}
let outgoing_message =
OutgoingMessage::Request(request.request_with_id(outgoing_message_id));
let _ = self.sender.send(outgoing_message);
rx_approve
}
pub(crate) async fn notify_client_response(&self, id: RequestId, result: Result) {
let entry = {
let mut request_id_to_callback = self.request_id_to_callback.lock().await;
request_id_to_callback.remove_entry(&id)
};
match entry {
Some((id, sender)) => {
if let Err(err) = sender.send(result) {
warn!("could not notify callback for {id:?} due to: {err:?}");
}
}
None => {
warn!("could not find callback for {id:?}");
}
}
}
pub(crate) async fn send_response<T: Serialize>(&self, id: RequestId, response: T) {
match serde_json::to_value(response) {
Ok(result) => {
let outgoing_message = OutgoingMessage::Response(OutgoingResponse { id, result });
let _ = self.sender.send(outgoing_message);
}
Err(err) => {
self.send_error(
id,
JSONRPCErrorError {
code: INTERNAL_ERROR_CODE,
message: format!("failed to serialize response: {err}"),
data: None,
},
)
.await;
}
}
}
pub(crate) async fn send_server_notification(&self, notification: ServerNotification) {
let _ = self
.sender
.send(OutgoingMessage::AppServerNotification(notification));
}
/// All notifications should be migrated to [`ServerNotification`] and
/// [`OutgoingMessage::Notification`] should be removed.
pub(crate) async fn send_notification(&self, notification: OutgoingNotification) {
let outgoing_message = OutgoingMessage::Notification(notification);
let _ = self.sender.send(outgoing_message);
}
pub(crate) async fn send_error(&self, id: RequestId, error: JSONRPCErrorError) {
let outgoing_message = OutgoingMessage::Error(OutgoingError { id, error });
let _ = self.sender.send(outgoing_message);
}
}
/// Outgoing message from the server to the client.
#[derive(Debug, Clone, Serialize)]
#[serde(untagged)]
pub(crate) enum OutgoingMessage {
Request(ServerRequest),
Notification(OutgoingNotification),
/// AppServerNotification is specific to the case where this is run as an
/// "app server" as opposed to an MCP server.
AppServerNotification(ServerNotification),
Response(OutgoingResponse),
Error(OutgoingError),
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingNotification {
pub method: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub params: Option<serde_json::Value>,
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingResponse {
pub id: RequestId,
pub result: Result,
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingError {
pub error: JSONRPCErrorError,
pub id: RequestId,
}
#[cfg(test)]
mod tests {
use codex_app_server_protocol::LoginChatGptCompleteNotification;
use pretty_assertions::assert_eq;
use serde_json::json;
use uuid::Uuid;
use super::*;
#[test]
fn verify_server_notification_serialization() {
let notification =
ServerNotification::LoginChatGptComplete(LoginChatGptCompleteNotification {
login_id: Uuid::nil(),
success: true,
error: None,
});
let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
assert_eq!(
json!({
"method": "loginChatGptComplete",
"params": {
"loginId": Uuid::nil(),
"success": true,
},
}),
serde_json::to_value(jsonrpc_notification)
.expect("ensure the strum macros serialize the method field correctly"),
"ensure the strum macros serialize the method field correctly"
);
}
}

View File

@@ -0,0 +1,3 @@
// Single integration test binary that aggregates all test modules.
// The submodules live in `tests/suite/`.
mod suite;

View File

@@ -0,0 +1,21 @@
[package]
edition = "2024"
name = "app_test_support"
version = { workspace = true }
[lib]
path = "lib.rs"
[dependencies]
anyhow = { workspace = true }
assert_cmd = { workspace = true }
codex-app-server-protocol = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true, features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
] }
wiremock = { workspace = true }

View File

@@ -0,0 +1,17 @@
mod mcp_process;
mod mock_model_server;
mod responses;
use codex_app_server_protocol::JSONRPCResponse;
pub use mcp_process::McpProcess;
pub use mock_model_server::create_mock_chat_completions_server;
pub use responses::create_apply_patch_sse_response;
pub use responses::create_final_assistant_message_sse_response;
pub use responses::create_shell_sse_response;
use serde::de::DeserializeOwned;
pub fn to_response<T: DeserializeOwned>(response: JSONRPCResponse) -> anyhow::Result<T> {
let value = serde_json::to_value(response.result)?;
let codex_response = serde_json::from_value(value)?;
Ok(codex_response)
}

View File

@@ -0,0 +1,502 @@
use std::collections::VecDeque;
use std::path::Path;
use std::process::Stdio;
use std::sync::atomic::AtomicI64;
use std::sync::atomic::Ordering;
use tokio::io::AsyncBufReadExt;
use tokio::io::AsyncWriteExt;
use tokio::io::BufReader;
use tokio::process::Child;
use tokio::process::ChildStdin;
use tokio::process::ChildStdout;
use anyhow::Context;
use assert_cmd::prelude::*;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::ArchiveConversationParams;
use codex_app_server_protocol::CancelLoginChatGptParams;
use codex_app_server_protocol::ClientInfo;
use codex_app_server_protocol::ClientNotification;
use codex_app_server_protocol::GetAuthStatusParams;
use codex_app_server_protocol::InitializeParams;
use codex_app_server_protocol::InterruptConversationParams;
use codex_app_server_protocol::ListConversationsParams;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::RemoveConversationListenerParams;
use codex_app_server_protocol::ResumeConversationParams;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserTurnParams;
use codex_app_server_protocol::ServerRequest;
use codex_app_server_protocol::SetDefaultModelParams;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCMessage;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCRequest;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use std::process::Command as StdCommand;
use tokio::process::Command;
pub struct McpProcess {
next_request_id: AtomicI64,
/// Retain this child process until the client is dropped. The Tokio runtime
/// will make a "best effort" to reap the process after it exits, but it is
/// not a guarantee. See the `kill_on_drop` documentation for details.
#[allow(dead_code)]
process: Child,
stdin: ChildStdin,
stdout: BufReader<ChildStdout>,
pending_user_messages: VecDeque<JSONRPCNotification>,
}
impl McpProcess {
pub async fn new(codex_home: &Path) -> anyhow::Result<Self> {
Self::new_with_env(codex_home, &[]).await
}
/// Creates a new MCP process, allowing tests to override or remove
/// specific environment variables for the child process only.
///
/// Pass a tuple of (key, Some(value)) to set/override, or (key, None) to
/// remove a variable from the child's environment.
pub async fn new_with_env(
codex_home: &Path,
env_overrides: &[(&str, Option<&str>)],
) -> anyhow::Result<Self> {
// Use assert_cmd to locate the binary path and then switch to tokio::process::Command
let std_cmd = StdCommand::cargo_bin("codex-app-server")
.context("should find binary for codex-mcp-server")?;
let program = std_cmd.get_program().to_owned();
let mut cmd = Command::new(program);
cmd.stdin(Stdio::piped());
cmd.stdout(Stdio::piped());
cmd.stderr(Stdio::piped());
cmd.env("CODEX_HOME", codex_home);
cmd.env("RUST_LOG", "debug");
for (k, v) in env_overrides {
match v {
Some(val) => {
cmd.env(k, val);
}
None => {
cmd.env_remove(k);
}
}
}
let mut process = cmd
.kill_on_drop(true)
.spawn()
.context("codex-mcp-server proc should start")?;
let stdin = process
.stdin
.take()
.ok_or_else(|| anyhow::format_err!("mcp should have stdin fd"))?;
let stdout = process
.stdout
.take()
.ok_or_else(|| anyhow::format_err!("mcp should have stdout fd"))?;
let stdout = BufReader::new(stdout);
// Forward child's stderr to our stderr so failures are visible even
// when stdout/stderr are captured by the test harness.
if let Some(stderr) = process.stderr.take() {
let mut stderr_reader = BufReader::new(stderr).lines();
tokio::spawn(async move {
while let Ok(Some(line)) = stderr_reader.next_line().await {
eprintln!("[mcp stderr] {line}");
}
});
}
Ok(Self {
next_request_id: AtomicI64::new(0),
process,
stdin,
stdout,
pending_user_messages: VecDeque::new(),
})
}
/// Performs the initialization handshake with the MCP server.
pub async fn initialize(&mut self) -> anyhow::Result<()> {
let params = Some(serde_json::to_value(InitializeParams {
client_info: ClientInfo {
name: "codex-app-server-tests".to_string(),
title: None,
version: "0.1.0".to_string(),
},
})?);
let req_id = self.send_request("initialize", params).await?;
let initialized = self.read_jsonrpc_message().await?;
let JSONRPCMessage::Response(response) = initialized else {
unreachable!("expected JSONRPCMessage::Response for initialize, got {initialized:?}");
};
if response.id != RequestId::Integer(req_id) {
anyhow::bail!(
"initialize response id mismatch: expected {}, got {:?}",
req_id,
response.id
);
}
// Send notifications/initialized to ack the response.
self.send_notification(ClientNotification::Initialized)
.await?;
Ok(())
}
/// Send a `newConversation` JSON-RPC request.
pub async fn send_new_conversation_request(
&mut self,
params: NewConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("newConversation", params).await
}
/// Send an `archiveConversation` JSON-RPC request.
pub async fn send_archive_conversation_request(
&mut self,
params: ArchiveConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("archiveConversation", params).await
}
/// Send an `addConversationListener` JSON-RPC request.
pub async fn send_add_conversation_listener_request(
&mut self,
params: AddConversationListenerParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("addConversationListener", params).await
}
/// Send a `sendUserMessage` JSON-RPC request with a single text item.
pub async fn send_send_user_message_request(
&mut self,
params: SendUserMessageParams,
) -> anyhow::Result<i64> {
// Wire format expects variants in camelCase; text item uses external tagging.
let params = Some(serde_json::to_value(params)?);
self.send_request("sendUserMessage", params).await
}
/// Send a `removeConversationListener` JSON-RPC request.
pub async fn send_remove_conversation_listener_request(
&mut self,
params: RemoveConversationListenerParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("removeConversationListener", params)
.await
}
/// Send a `sendUserTurn` JSON-RPC request.
pub async fn send_send_user_turn_request(
&mut self,
params: SendUserTurnParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("sendUserTurn", params).await
}
/// Send a `interruptConversation` JSON-RPC request.
pub async fn send_interrupt_conversation_request(
&mut self,
params: InterruptConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("interruptConversation", params).await
}
/// Send a `getAuthStatus` JSON-RPC request.
pub async fn send_get_auth_status_request(
&mut self,
params: GetAuthStatusParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("getAuthStatus", params).await
}
/// Send a `getUserSavedConfig` JSON-RPC request.
pub async fn send_get_user_saved_config_request(&mut self) -> anyhow::Result<i64> {
self.send_request("getUserSavedConfig", None).await
}
/// Send a `getUserAgent` JSON-RPC request.
pub async fn send_get_user_agent_request(&mut self) -> anyhow::Result<i64> {
self.send_request("getUserAgent", None).await
}
/// Send a `userInfo` JSON-RPC request.
pub async fn send_user_info_request(&mut self) -> anyhow::Result<i64> {
self.send_request("userInfo", None).await
}
/// Send a `setDefaultModel` JSON-RPC request.
pub async fn send_set_default_model_request(
&mut self,
params: SetDefaultModelParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("setDefaultModel", params).await
}
/// Send a `listConversations` JSON-RPC request.
pub async fn send_list_conversations_request(
&mut self,
params: ListConversationsParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("listConversations", params).await
}
/// Send a `resumeConversation` JSON-RPC request.
pub async fn send_resume_conversation_request(
&mut self,
params: ResumeConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("resumeConversation", params).await
}
/// Send a `loginApiKey` JSON-RPC request.
pub async fn send_login_api_key_request(
&mut self,
params: LoginApiKeyParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("loginApiKey", params).await
}
/// Send a `loginChatGpt` JSON-RPC request.
pub async fn send_login_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
self.send_request("loginChatGpt", None).await
}
/// Send a `cancelLoginChatGpt` JSON-RPC request.
pub async fn send_cancel_login_chat_gpt_request(
&mut self,
params: CancelLoginChatGptParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("cancelLoginChatGpt", params).await
}
/// Send a `logoutChatGpt` JSON-RPC request.
pub async fn send_logout_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
self.send_request("logoutChatGpt", None).await
}
/// Send a `fuzzyFileSearch` JSON-RPC request.
pub async fn send_fuzzy_file_search_request(
&mut self,
query: &str,
roots: Vec<String>,
cancellation_token: Option<String>,
) -> anyhow::Result<i64> {
let mut params = serde_json::json!({
"query": query,
"roots": roots,
});
if let Some(token) = cancellation_token {
params["cancellationToken"] = serde_json::json!(token);
}
self.send_request("fuzzyFileSearch", Some(params)).await
}
async fn send_request(
&mut self,
method: &str,
params: Option<serde_json::Value>,
) -> anyhow::Result<i64> {
let request_id = self.next_request_id.fetch_add(1, Ordering::Relaxed);
let message = JSONRPCMessage::Request(JSONRPCRequest {
id: RequestId::Integer(request_id),
method: method.to_string(),
params,
});
self.send_jsonrpc_message(message).await?;
Ok(request_id)
}
pub async fn send_response(
&mut self,
id: RequestId,
result: serde_json::Value,
) -> anyhow::Result<()> {
self.send_jsonrpc_message(JSONRPCMessage::Response(JSONRPCResponse { id, result }))
.await
}
pub async fn send_notification(
&mut self,
notification: ClientNotification,
) -> anyhow::Result<()> {
let value = serde_json::to_value(notification)?;
self.send_jsonrpc_message(JSONRPCMessage::Notification(JSONRPCNotification {
method: value
.get("method")
.and_then(|m| m.as_str())
.ok_or_else(|| anyhow::format_err!("notification missing method field"))?
.to_string(),
params: value.get("params").cloned(),
}))
.await
}
async fn send_jsonrpc_message(&mut self, message: JSONRPCMessage) -> anyhow::Result<()> {
eprintln!("writing message to stdin: {message:?}");
let payload = serde_json::to_string(&message)?;
self.stdin.write_all(payload.as_bytes()).await?;
self.stdin.write_all(b"\n").await?;
self.stdin.flush().await?;
Ok(())
}
async fn read_jsonrpc_message(&mut self) -> anyhow::Result<JSONRPCMessage> {
let mut line = String::new();
self.stdout.read_line(&mut line).await?;
let message = serde_json::from_str::<JSONRPCMessage>(&line)?;
eprintln!("read message from stdout: {message:?}");
Ok(message)
}
pub async fn read_stream_until_request_message(&mut self) -> anyhow::Result<ServerRequest> {
eprintln!("in read_stream_until_request_message()");
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(notification) => {
eprintln!("notification: {notification:?}");
self.enqueue_user_message(notification);
}
JSONRPCMessage::Request(jsonrpc_request) => {
return jsonrpc_request.try_into().with_context(
|| "failed to deserialize ServerRequest from JSONRPCRequest",
);
}
JSONRPCMessage::Error(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
}
JSONRPCMessage::Response(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
}
}
}
}
pub async fn read_stream_until_response_message(
&mut self,
request_id: RequestId,
) -> anyhow::Result<JSONRPCResponse> {
eprintln!("in read_stream_until_response_message({request_id:?})");
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(notification) => {
eprintln!("notification: {notification:?}");
self.enqueue_user_message(notification);
}
JSONRPCMessage::Request(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
}
JSONRPCMessage::Error(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
}
JSONRPCMessage::Response(jsonrpc_response) => {
if jsonrpc_response.id == request_id {
return Ok(jsonrpc_response);
}
}
}
}
}
pub async fn read_stream_until_error_message(
&mut self,
request_id: RequestId,
) -> anyhow::Result<JSONRPCError> {
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(notification) => {
eprintln!("notification: {notification:?}");
self.enqueue_user_message(notification);
}
JSONRPCMessage::Request(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
}
JSONRPCMessage::Response(_) => {
// Keep scanning; we're waiting for an error with matching id.
}
JSONRPCMessage::Error(err) => {
if err.id == request_id {
return Ok(err);
}
}
}
}
}
pub async fn read_stream_until_notification_message(
&mut self,
method: &str,
) -> anyhow::Result<JSONRPCNotification> {
eprintln!("in read_stream_until_notification_message({method})");
if let Some(notification) = self.take_pending_notification_by_method(method) {
return Ok(notification);
}
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(notification) => {
if notification.method == method {
return Ok(notification);
}
self.enqueue_user_message(notification);
}
JSONRPCMessage::Request(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
}
JSONRPCMessage::Error(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
}
JSONRPCMessage::Response(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
}
}
}
}
fn take_pending_notification_by_method(&mut self, method: &str) -> Option<JSONRPCNotification> {
if let Some(pos) = self
.pending_user_messages
.iter()
.position(|notification| notification.method == method)
{
return self.pending_user_messages.remove(pos);
}
None
}
fn enqueue_user_message(&mut self, notification: JSONRPCNotification) {
if notification.method == "codex/event/user_message" {
self.pending_user_messages.push_back(notification);
}
}
}

View File

@@ -0,0 +1,47 @@
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::Respond;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;
/// Create a mock server that will provide the responses, in order, for
/// requests to the `/v1/chat/completions` endpoint.
pub async fn create_mock_chat_completions_server(responses: Vec<String>) -> MockServer {
let server = MockServer::start().await;
let num_calls = responses.len();
let seq_responder = SeqResponder {
num_calls: AtomicUsize::new(0),
responses,
};
Mock::given(method("POST"))
.and(path("/v1/chat/completions"))
.respond_with(seq_responder)
.expect(num_calls as u64)
.mount(&server)
.await;
server
}
struct SeqResponder {
num_calls: AtomicUsize,
responses: Vec<String>,
}
impl Respond for SeqResponder {
fn respond(&self, _: &wiremock::Request) -> ResponseTemplate {
let call_num = self.num_calls.fetch_add(1, Ordering::SeqCst);
match self.responses.get(call_num) {
Some(response) => ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(response.clone(), "text/event-stream"),
None => panic!("no response for {call_num}"),
}
}
}

View File

@@ -0,0 +1,95 @@
use serde_json::json;
use std::path::Path;
pub fn create_shell_sse_response(
command: Vec<String>,
workdir: Option<&Path>,
timeout_ms: Option<u64>,
call_id: &str,
) -> anyhow::Result<String> {
// The `arguments`` for the `shell` tool is a serialized JSON object.
let tool_call_arguments = serde_json::to_string(&json!({
"command": command,
"workdir": workdir.map(|w| w.to_string_lossy()),
"timeout": timeout_ms
}))?;
let tool_call = json!({
"choices": [
{
"delta": {
"tool_calls": [
{
"id": call_id,
"function": {
"name": "shell",
"arguments": tool_call_arguments
}
}
]
},
"finish_reason": "tool_calls"
}
]
});
let sse = format!(
"data: {}\n\ndata: DONE\n\n",
serde_json::to_string(&tool_call)?
);
Ok(sse)
}
pub fn create_final_assistant_message_sse_response(message: &str) -> anyhow::Result<String> {
let assistant_message = json!({
"choices": [
{
"delta": {
"content": message
},
"finish_reason": "stop"
}
]
});
let sse = format!(
"data: {}\n\ndata: DONE\n\n",
serde_json::to_string(&assistant_message)?
);
Ok(sse)
}
pub fn create_apply_patch_sse_response(
patch_content: &str,
call_id: &str,
) -> anyhow::Result<String> {
// Use shell command to call apply_patch with heredoc format
let shell_command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
let tool_call_arguments = serde_json::to_string(&json!({
"command": ["bash", "-lc", shell_command]
}))?;
let tool_call = json!({
"choices": [
{
"delta": {
"tool_calls": [
{
"id": call_id,
"function": {
"name": "shell",
"arguments": tool_call_arguments
}
}
]
},
"finish_reason": "tool_calls"
}
]
});
let sse = format!(
"data: {}\n\ndata: DONE\n\n",
serde_json::to_string(&tool_call)?
);
Ok(sse)
}

View File

@@ -0,0 +1,105 @@
use std::path::Path;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::ArchiveConversationParams;
use codex_app_server_protocol::ArchiveConversationResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RequestId;
use codex_core::ARCHIVED_SESSIONS_SUBDIR;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn archive_conversation_moves_rollout_into_archived_directory() {
let codex_home = TempDir::new().expect("create temp dir");
create_config_toml(codex_home.path()).expect("write config.toml");
let mut mcp = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("initialize timeout")
.expect("initialize request");
let new_request_id = mcp
.send_new_conversation_request(NewConversationParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await
.expect("send newConversation");
let new_response: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(new_request_id)),
)
.await
.expect("newConversation timeout")
.expect("newConversation response");
let NewConversationResponse {
conversation_id,
rollout_path,
..
} = to_response::<NewConversationResponse>(new_response)
.expect("deserialize newConversation response");
assert!(
rollout_path.exists(),
"expected rollout path {} to exist",
rollout_path.display()
);
let archive_request_id = mcp
.send_archive_conversation_request(ArchiveConversationParams {
conversation_id,
rollout_path: rollout_path.clone(),
})
.await
.expect("send archiveConversation");
let archive_response: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(archive_request_id)),
)
.await
.expect("archiveConversation timeout")
.expect("archiveConversation response");
let _: ArchiveConversationResponse =
to_response::<ArchiveConversationResponse>(archive_response)
.expect("deserialize archiveConversation response");
let archived_directory = codex_home.path().join(ARCHIVED_SESSIONS_SUBDIR);
let archived_rollout_path =
archived_directory.join(rollout_path.file_name().unwrap_or_else(|| {
panic!("rollout path {} missing file name", rollout_path.display())
}));
assert!(
!rollout_path.exists(),
"expected rollout path {} to be moved",
rollout_path.display()
);
assert!(
archived_rollout_path.exists(),
"expected archived rollout path {} to exist",
archived_rollout_path.display()
);
}
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(config_toml, config_contents())
}
fn config_contents() -> &'static str {
r#"model = "mock-model"
approval_policy = "never"
sandbox_mode = "read-only"
"#
}

View File

@@ -1,24 +1,31 @@
use std::path::Path;
use codex_core::auth::login_with_api_key;
use codex_protocol::mcp_protocol::AuthMode;
use codex_protocol::mcp_protocol::GetAuthStatusParams;
use codex_protocol::mcp_protocol::GetAuthStatusResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::to_response;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::AuthMode;
use codex_app_server_protocol::GetAuthStatusParams;
use codex_app_server_protocol::GetAuthStatusResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::LoginApiKeyResponse;
use codex_app_server_protocol::RequestId;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
// Helper to create a config.toml; mirrors create_conversation.rs
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
fn create_config_toml_custom_provider(
codex_home: &Path,
requires_openai_auth: bool,
) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
let requires_line = if requires_openai_auth {
"requires_openai_auth = true\n"
} else {
""
};
let contents = format!(
r#"
model = "mock-model"
approval_policy = "never"
@@ -32,16 +39,49 @@ base_url = "http://127.0.0.1:0/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
{requires_line}
"#
);
std::fs::write(config_toml, contents)
}
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "danger-full-access"
"#,
)
}
async fn login_with_api_key_via_request(mcp: &mut McpProcess, api_key: &str) {
let request_id = mcp
.send_login_api_key_request(LoginApiKeyParams {
api_key: api_key.to_string(),
})
.await
.unwrap_or_else(|e| panic!("send loginApiKey: {e}"));
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await
.unwrap_or_else(|e| panic!("loginApiKey timeout: {e}"))
.unwrap_or_else(|e| panic!("loginApiKey response: {e}"));
let _: LoginApiKeyResponse =
to_response(resp).unwrap_or_else(|e| panic!("deserialize login response: {e}"));
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_auth_status_no_auth() {
let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
create_config_toml(codex_home.path()).expect("write config.toml");
create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
let mut mcp = McpProcess::new(codex_home.path())
let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)])
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
@@ -72,8 +112,7 @@ async fn get_auth_status_no_auth() {
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_auth_status_with_api_key() {
let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
create_config_toml(codex_home.path()).expect("write config.toml");
login_with_api_key(codex_home.path(), "sk-test-key").expect("seed api key");
create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
let mut mcp = McpProcess::new(codex_home.path())
.await
@@ -83,6 +122,8 @@ async fn get_auth_status_with_api_key() {
.expect("init timeout")
.expect("init failed");
login_with_api_key_via_request(&mut mcp, "sk-test-key").await;
let request_id = mcp
.send_get_auth_status_request(GetAuthStatusParams {
include_token: Some(true),
@@ -101,14 +142,13 @@ async fn get_auth_status_with_api_key() {
let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
assert_eq!(status.auth_method, Some(AuthMode::ApiKey));
assert_eq!(status.auth_token, Some("sk-test-key".to_string()));
assert_eq!(status.preferred_auth_method, AuthMode::ChatGPT);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_auth_status_with_api_key_no_include_token() {
async fn get_auth_status_with_api_key_when_auth_not_required() {
let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
create_config_toml(codex_home.path()).expect("write config.toml");
login_with_api_key(codex_home.path(), "sk-test-key").expect("seed api key");
create_config_toml_custom_provider(codex_home.path(), false)
.unwrap_or_else(|err| panic!("write config.toml: {err}"));
let mut mcp = McpProcess::new(codex_home.path())
.await
@@ -118,6 +158,48 @@ async fn get_auth_status_with_api_key_no_include_token() {
.expect("init timeout")
.expect("init failed");
login_with_api_key_via_request(&mut mcp, "sk-test-key").await;
let request_id = mcp
.send_get_auth_status_request(GetAuthStatusParams {
include_token: Some(true),
refresh_token: Some(false),
})
.await
.expect("send getAuthStatus");
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await
.expect("getAuthStatus timeout")
.expect("getAuthStatus response");
let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
assert_eq!(status.auth_method, None, "expected no auth method");
assert_eq!(status.auth_token, None, "expected no token");
assert_eq!(
status.requires_openai_auth,
Some(false),
"requires_openai_auth should be false",
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_auth_status_with_api_key_no_include_token() {
let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
let mut mcp = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
login_with_api_key_via_request(&mut mcp, "sk-test-key").await;
// Build params via struct so None field is omitted in wire JSON.
let params = GetAuthStatusParams {
include_token: None,
@@ -138,5 +220,4 @@ async fn get_auth_status_with_api_key_no_include_token() {
let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
assert_eq!(status.auth_method, Some(AuthMode::ApiKey));
assert!(status.auth_token.is_none(), "token must be omitted");
assert_eq!(status.preferred_auth_method, AuthMode::ChatGPT);
}

View File

@@ -1,29 +1,35 @@
use std::path::Path;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::create_shell_sse_response;
use app_test_support::to_response;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
use codex_app_server_protocol::ExecCommandApprovalParams;
use codex_app_server_protocol::InputItem;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RemoveConversationListenerParams;
use codex_app_server_protocol::RemoveConversationSubscriptionResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserMessageResponse;
use codex_app_server_protocol::SendUserTurnParams;
use codex_app_server_protocol::SendUserTurnResponse;
use codex_app_server_protocol::ServerRequest;
use codex_core::protocol::AskForApproval;
use codex_core::protocol::SandboxPolicy;
use codex_core::protocol_config_types::ReasoningEffort;
use codex_core::protocol_config_types::ReasoningSummary;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_protocol::mcp_protocol::AddConversationListenerParams;
use codex_protocol::mcp_protocol::AddConversationSubscriptionResponse;
use codex_protocol::mcp_protocol::EXEC_COMMAND_APPROVAL_METHOD;
use codex_protocol::mcp_protocol::NewConversationParams;
use codex_protocol::mcp_protocol::NewConversationResponse;
use codex_protocol::mcp_protocol::RemoveConversationListenerParams;
use codex_protocol::mcp_protocol::RemoveConversationSubscriptionResponse;
use codex_protocol::mcp_protocol::SendUserMessageParams;
use codex_protocol::mcp_protocol::SendUserMessageResponse;
use codex_protocol::mcp_protocol::SendUserTurnParams;
use codex_protocol::mcp_protocol::SendUserTurnResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::create_final_assistant_message_sse_response;
use mcp_test_support::create_mock_chat_completions_server;
use mcp_test_support::create_shell_sse_response;
use mcp_test_support::to_response;
use mcp_types::JSONRPCNotification;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use codex_protocol::config_types::SandboxMode;
use codex_protocol::protocol::Event;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::InputMessageKind;
use pretty_assertions::assert_eq;
use std::env;
use tempfile::TempDir;
@@ -90,6 +96,8 @@ async fn test_codex_jsonrpc_conversation_flow() {
let NewConversationResponse {
conversation_id,
model,
reasoning_effort: _,
rollout_path: _,
} = new_conv_resp;
assert_eq!(model, "mock-model");
@@ -113,7 +121,7 @@ async fn test_codex_jsonrpc_conversation_flow() {
let send_user_id = mcp
.send_send_user_message_request(SendUserMessageParams {
conversation_id,
items: vec![codex_protocol::mcp_protocol::InputItem::Text {
items: vec![codex_app_server_protocol::InputItem::Text {
text: "text".to_string(),
}],
})
@@ -263,7 +271,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
let send_user_id = mcp
.send_send_user_message_request(SendUserMessageParams {
conversation_id,
items: vec![codex_protocol::mcp_protocol::InputItem::Text {
items: vec![codex_app_server_protocol::InputItem::Text {
text: "run python".to_string(),
}],
})
@@ -288,11 +296,28 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
.await
.expect("waiting for exec approval request timeout")
.expect("exec approval request");
assert_eq!(request.method, EXEC_COMMAND_APPROVAL_METHOD);
let ServerRequest::ExecCommandApproval { request_id, params } = request else {
panic!("expected ExecCommandApproval request, got: {request:?}");
};
assert_eq!(
ExecCommandApprovalParams {
conversation_id,
call_id: "call1".to_string(),
command: vec![
"python3".to_string(),
"-c".to_string(),
"print(42)".to_string(),
],
cwd: working_directory.clone(),
reason: None,
},
params
);
// Approve so the first turn can complete
mcp.send_response(
request.id,
request_id,
serde_json::json!({ "decision": codex_core::protocol::ReviewDecision::Approved }),
)
.await
@@ -311,14 +336,14 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
let send_turn_id = mcp
.send_send_user_turn_request(SendUserTurnParams {
conversation_id,
items: vec![codex_protocol::mcp_protocol::InputItem::Text {
items: vec![codex_app_server_protocol::InputItem::Text {
text: "run python again".to_string(),
}],
cwd: working_directory.clone(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: "mock-model".to_string(),
effort: ReasoningEffort::Medium,
effort: Some(ReasoningEffort::Medium),
summary: ReasoningSummary::Auto,
})
.await
@@ -347,6 +372,234 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
}
// Helper: minimal config.toml pointing at mock provider.
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
if 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;
}
let tmp = TempDir::new().expect("tmp dir");
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home).expect("create codex home dir");
let workspace_root = tmp.path().join("workspace");
std::fs::create_dir(&workspace_root).expect("create workspace root");
let first_cwd = workspace_root.join("turn1");
let second_cwd = workspace_root.join("turn2");
std::fs::create_dir(&first_cwd).expect("create first cwd");
std::fs::create_dir(&second_cwd).expect("create second cwd");
let responses = vec![
create_shell_sse_response(
vec![
"bash".to_string(),
"-lc".to_string(),
"echo first turn".to_string(),
],
None,
Some(5000),
"call-first",
)
.expect("create first shell response"),
create_final_assistant_message_sse_response("done first")
.expect("create first final assistant message"),
create_shell_sse_response(
vec![
"bash".to_string(),
"-lc".to_string(),
"echo second turn".to_string(),
],
None,
Some(5000),
"call-second",
)
.expect("create second shell response"),
create_final_assistant_message_sse_response("done second")
.expect("create second final assistant message"),
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri()).expect("write config");
let mut mcp = McpProcess::new(&codex_home)
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
let new_conv_id = mcp
.send_new_conversation_request(NewConversationParams {
cwd: Some(first_cwd.to_string_lossy().into_owned()),
approval_policy: Some(AskForApproval::Never),
sandbox: Some(SandboxMode::WorkspaceWrite),
..Default::default()
})
.await
.expect("send newConversation");
let new_conv_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
)
.await
.expect("newConversation timeout")
.expect("newConversation resp");
let NewConversationResponse {
conversation_id,
model,
..
} = to_response::<NewConversationResponse>(new_conv_resp)
.expect("deserialize newConversation response");
let add_listener_id = mcp
.send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
.await
.expect("send addConversationListener");
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
)
.await
.expect("addConversationListener timeout")
.expect("addConversationListener resp");
let first_turn_id = mcp
.send_send_user_turn_request(SendUserTurnParams {
conversation_id,
items: vec![InputItem::Text {
text: "first turn".to_string(),
}],
cwd: first_cwd.clone(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::WorkspaceWrite {
writable_roots: vec![first_cwd.clone()],
network_access: false,
exclude_tmpdir_env_var: false,
exclude_slash_tmp: false,
},
model: model.clone(),
effort: Some(ReasoningEffort::Medium),
summary: ReasoningSummary::Auto,
})
.await
.expect("send first sendUserTurn");
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(first_turn_id)),
)
.await
.expect("sendUserTurn 1 timeout")
.expect("sendUserTurn 1 resp");
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_complete 1 timeout")
.expect("task_complete 1 notification");
let second_turn_id = mcp
.send_send_user_turn_request(SendUserTurnParams {
conversation_id,
items: vec![InputItem::Text {
text: "second turn".to_string(),
}],
cwd: second_cwd.clone(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::DangerFullAccess,
model: model.clone(),
effort: Some(ReasoningEffort::Medium),
summary: ReasoningSummary::Auto,
})
.await
.expect("send second sendUserTurn");
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(second_turn_id)),
)
.await
.expect("sendUserTurn 2 timeout")
.expect("sendUserTurn 2 resp");
let mut env_message: Option<String> = None;
let second_cwd_str = second_cwd.to_string_lossy().into_owned();
for _ in 0..10 {
let notification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/user_message"),
)
.await
.expect("user_message timeout")
.expect("user_message notification");
let params = notification
.params
.clone()
.expect("user_message should include params");
let event: Event = serde_json::from_value(params).expect("deserialize user_message event");
if let EventMsg::UserMessage(user) = event.msg
&& matches!(user.kind, Some(InputMessageKind::EnvironmentContext))
&& user.message.contains(&second_cwd_str)
{
env_message = Some(user.message);
break;
}
}
let env_message = env_message.expect("expected environment context update");
assert!(
env_message.contains("<sandbox_mode>danger-full-access</sandbox_mode>"),
"env context should reflect new sandbox mode: {env_message}"
);
assert!(
env_message.contains("<network_access>enabled</network_access>"),
"env context should enable network access for danger-full-access policy: {env_message}"
);
assert!(
env_message.contains(&second_cwd_str),
"env context should include updated cwd: {env_message}"
);
let exec_begin_notification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/exec_command_begin"),
)
.await
.expect("exec_command_begin timeout")
.expect("exec_command_begin notification");
let params = exec_begin_notification
.params
.clone()
.expect("exec_command_begin params");
let event: Event = serde_json::from_value(params).expect("deserialize exec begin event");
let exec_begin = match event.msg {
EventMsg::ExecCommandBegin(exec_begin) => exec_begin,
other => panic!("expected ExecCommandBegin event, got {other:?}"),
};
assert_eq!(
exec_begin.cwd, second_cwd,
"exec turn should run from updated cwd"
);
assert_eq!(
exec_begin.command,
vec![
"bash".to_string(),
"-lc".to_string(),
"echo second turn".to_string()
],
"exec turn should run expected command"
);
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_complete 2 timeout")
.expect("task_complete 2 notification");
}
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(

View File

@@ -1,20 +1,20 @@
use std::collections::HashMap;
use std::path::Path;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::GetUserSavedConfigResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::Profile;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SandboxSettings;
use codex_app_server_protocol::Tools;
use codex_app_server_protocol::UserSavedConfig;
use codex_core::protocol::AskForApproval;
use codex_protocol::config_types::ReasoningEffort;
use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::config_types::SandboxMode;
use codex_protocol::config_types::Verbosity;
use codex_protocol::mcp_protocol::GetUserSavedConfigResponse;
use codex_protocol::mcp_protocol::Profile;
use codex_protocol::mcp_protocol::SandboxSettings;
use codex_protocol::mcp_protocol::Tools;
use codex_protocol::mcp_protocol::UserSavedConfig;
use mcp_test_support::McpProcess;
use mcp_test_support::to_response;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
use tokio::time::timeout;
@@ -26,7 +26,7 @@ fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
std::fs::write(
config_toml,
r#"
model = "gpt-5"
model = "gpt-5-codex"
approval_policy = "on-request"
sandbox_mode = "workspace-write"
model_reasoning_summary = "detailed"
@@ -92,7 +92,7 @@ async fn get_config_toml_parses_all_fields() {
exclude_tmpdir_env_var: Some(true),
exclude_slash_tmp: Some(true),
}),
model: Some("gpt-5".into()),
model: Some("gpt-5-codex".into()),
model_reasoning_effort: Some(ReasoningEffort::High),
model_reasoning_summary: Some(ReasoningSummary::Detailed),
model_verbosity: Some(Verbosity::Medium),

View File

@@ -1,18 +1,18 @@
use std::path::Path;
use codex_protocol::mcp_protocol::AddConversationListenerParams;
use codex_protocol::mcp_protocol::AddConversationSubscriptionResponse;
use codex_protocol::mcp_protocol::InputItem;
use codex_protocol::mcp_protocol::NewConversationParams;
use codex_protocol::mcp_protocol::NewConversationResponse;
use codex_protocol::mcp_protocol::SendUserMessageParams;
use codex_protocol::mcp_protocol::SendUserMessageResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::create_final_assistant_message_sse_response;
use mcp_test_support::create_mock_chat_completions_server;
use mcp_test_support::to_response;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::to_response;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
use codex_app_server_protocol::InputItem;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserMessageResponse;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
@@ -59,6 +59,8 @@ async fn test_conversation_create_and_send_message_ok() {
let NewConversationResponse {
conversation_id,
model,
reasoning_effort: _,
rollout_path: _,
} = to_response::<NewConversationResponse>(new_conv_resp)
.expect("deserialize newConversation response");
assert_eq!(model, "o3");

View File

@@ -0,0 +1,104 @@
use app_test_support::McpProcess;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn test_fuzzy_file_search_sorts_and_includes_indices() {
// Prepare a temporary Codex home and a separate root with test files.
let codex_home = TempDir::new().expect("create temp codex home");
let root = TempDir::new().expect("create temp search root");
// Create files designed to have deterministic ordering for query "abc".
std::fs::write(root.path().join("abc"), "x").expect("write file abc");
std::fs::write(root.path().join("abcde"), "x").expect("write file abcx");
std::fs::write(root.path().join("abexy"), "x").expect("write file abcx");
std::fs::write(root.path().join("zzz.txt"), "x").expect("write file zzz");
// Start MCP server and initialize.
let mut mcp = McpProcess::new(codex_home.path()).await.expect("spawn mcp");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
let root_path = root.path().to_string_lossy().to_string();
// Send fuzzyFileSearch request.
let request_id = mcp
.send_fuzzy_file_search_request("abe", vec![root_path.clone()], None)
.await
.expect("send fuzzyFileSearch");
// Read response and verify shape and ordering.
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await
.expect("fuzzyFileSearch timeout")
.expect("fuzzyFileSearch resp");
let value = resp.result;
assert_eq!(
value,
json!({
"files": [
{ "root": root_path.clone(), "path": "abexy", "score": 88, "indices": [0, 1, 2] },
{ "root": root_path.clone(), "path": "abcde", "score": 74, "indices": [0, 1, 4] },
]
})
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn test_fuzzy_file_search_accepts_cancellation_token() {
let codex_home = TempDir::new().expect("create temp codex home");
let root = TempDir::new().expect("create temp search root");
std::fs::write(root.path().join("alpha.txt"), "contents").expect("write alpha");
let mut mcp = McpProcess::new(codex_home.path()).await.expect("spawn mcp");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
let root_path = root.path().to_string_lossy().to_string();
let request_id = mcp
.send_fuzzy_file_search_request("alp", vec![root_path.clone()], None)
.await
.expect("send fuzzyFileSearch");
let request_id_2 = mcp
.send_fuzzy_file_search_request(
"alp",
vec![root_path.clone()],
Some(request_id.to_string()),
)
.await
.expect("send fuzzyFileSearch");
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id_2)),
)
.await
.expect("fuzzyFileSearch timeout")
.expect("fuzzyFileSearch resp");
let files = resp
.result
.get("files")
.and_then(|value| value.as_array())
.cloned()
.expect("files array");
assert_eq!(files.len(), 1);
assert_eq!(files[0]["root"], root_path);
assert_eq!(files[0]["path"], "alpha.txt");
}

View File

@@ -1,37 +1,32 @@
#![cfg(unix)]
// Support code lives in the `mcp_test_support` crate under tests/common.
// Support code lives in the `app_test_support` crate under tests/common.
use std::path::Path;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::InterruptConversationParams;
use codex_app_server_protocol::InterruptConversationResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserMessageResponse;
use codex_core::protocol::TurnAbortReason;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_protocol::mcp_protocol::AddConversationListenerParams;
use codex_protocol::mcp_protocol::InterruptConversationParams;
use codex_protocol::mcp_protocol::InterruptConversationResponse;
use codex_protocol::mcp_protocol::NewConversationParams;
use codex_protocol::mcp_protocol::NewConversationResponse;
use codex_protocol::mcp_protocol::SendUserMessageParams;
use codex_protocol::mcp_protocol::SendUserMessageResponse;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use core_test_support::skip_if_no_network;
use tempfile::TempDir;
use tokio::time::timeout;
use mcp_test_support::McpProcess;
use mcp_test_support::create_mock_chat_completions_server;
use mcp_test_support::create_shell_sse_response;
use mcp_test_support::to_response;
use app_test_support::McpProcess;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::create_shell_sse_response;
use app_test_support::to_response;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn test_shell_command_interruption() {
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;
}
skip_if_no_network!();
if let Err(err) = shell_command_interruption().await {
panic!("failure: {err}");
@@ -105,7 +100,7 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
let send_user_id = mcp
.send_send_user_message_request(SendUserMessageParams {
conversation_id,
items: vec![codex_protocol::mcp_protocol::InputItem::Text {
items: vec![codex_app_server_protocol::InputItem::Text {
text: "run first sleep command".to_string(),
}],
})

View File

@@ -1,16 +1,18 @@
use std::fs;
use std::path::Path;
use codex_protocol::mcp_protocol::ListConversationsParams;
use codex_protocol::mcp_protocol::ListConversationsResponse;
use codex_protocol::mcp_protocol::NewConversationParams; // reused for overrides shape
use codex_protocol::mcp_protocol::ResumeConversationParams;
use codex_protocol::mcp_protocol::ResumeConversationResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::to_response;
use mcp_types::JSONRPCNotification;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::ListConversationsParams;
use codex_app_server_protocol::ListConversationsResponse;
use codex_app_server_protocol::NewConversationParams; // reused for overrides shape
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ResumeConversationParams;
use codex_app_server_protocol::ResumeConversationResponse;
use codex_app_server_protocol::ServerNotification;
use codex_app_server_protocol::SessionConfiguredNotification;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
@@ -111,23 +113,28 @@ async fn test_list_and_resume_conversations() {
.await
.expect("send resumeConversation");
// Expect a codex/event notification with msg.type == session_configured
// Expect a codex/event notification with msg.type == sessionConfigured
let notification: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event"),
mcp.read_stream_until_notification_message("sessionConfigured"),
)
.await
.expect("session_configured notification timeout")
.expect("session_configured notification");
// Basic shape assertion: ensure event type is session_configured
let msg_type = notification
.params
.as_ref()
.and_then(|p| p.get("msg"))
.and_then(|m| m.get("type"))
.and_then(|t| t.as_str())
.unwrap_or("");
assert_eq!(msg_type, "session_configured");
.expect("sessionConfigured notification timeout")
.expect("sessionConfigured notification");
let session_configured: ServerNotification = notification
.try_into()
.expect("deserialize sessionConfigured notification");
// Basic shape assertion: ensure event type is sessionConfigured
let ServerNotification::SessionConfigured(SessionConfiguredNotification {
model,
rollout_path,
..
}) = session_configured
else {
unreachable!("expected sessionConfigured notification");
};
assert_eq!(model, "o3");
assert_eq!(items[0].path.clone(), rollout_path);
// Then the response for resumeConversation
let resume_resp: JSONRPCResponse = timeout(
@@ -142,7 +149,7 @@ async fn test_list_and_resume_conversations() {
} = to_response::<ResumeConversationResponse>(resume_resp)
.expect("deserialize resumeConversation response");
// conversation id should be a valid UUID
let _: uuid::Uuid = conversation_id.into();
assert!(!conversation_id.to_string().is_empty());
}
fn create_fake_rollout(codex_home: &Path, filename_ts: &str, meta_rfc3339: &str, preview: &str) {
@@ -156,14 +163,45 @@ fn create_fake_rollout(codex_home: &Path, filename_ts: &str, meta_rfc3339: &str,
let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
let mut lines = Vec::new();
// Meta line with timestamp
lines.push(json!({"timestamp": meta_rfc3339, "id": uuid}).to_string());
// Minimal user message entry as a persisted response item
// Meta line with timestamp (flattened meta in payload for new schema)
lines.push(
json!({
"type":"message",
"role":"user",
"content":[{"type":"input_text","text": preview}]
"timestamp": meta_rfc3339,
"type": "session_meta",
"payload": {
"id": uuid,
"timestamp": meta_rfc3339,
"cwd": "/",
"originator": "codex",
"cli_version": "0.0.0",
"instructions": null
}
})
.to_string(),
);
// Minimal user message entry as a persisted response item (with envelope timestamp)
lines.push(
json!({
"timestamp": meta_rfc3339,
"type":"response_item",
"payload": {
"type":"message",
"role":"user",
"content":[{"type":"input_text","text": preview}]
}
})
.to_string(),
);
// Add a matching user message event line to satisfy filters
lines.push(
json!({
"timestamp": meta_rfc3339,
"type":"event_msg",
"payload": {
"type":"user_message",
"message": preview,
"kind": "plain"
}
})
.to_string(),
);

View File

@@ -1,17 +1,17 @@
use std::path::Path;
use std::time::Duration;
use codex_core::auth::login_with_api_key;
use codex_protocol::mcp_protocol::CancelLoginChatGptParams;
use codex_protocol::mcp_protocol::CancelLoginChatGptResponse;
use codex_protocol::mcp_protocol::GetAuthStatusParams;
use codex_protocol::mcp_protocol::GetAuthStatusResponse;
use codex_protocol::mcp_protocol::LoginChatGptResponse;
use codex_protocol::mcp_protocol::LogoutChatGptResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::to_response;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::CancelLoginChatGptParams;
use codex_app_server_protocol::CancelLoginChatGptResponse;
use codex_app_server_protocol::GetAuthStatusParams;
use codex_app_server_protocol::GetAuthStatusResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::LoginChatGptResponse;
use codex_app_server_protocol::LogoutChatGptResponse;
use codex_app_server_protocol::RequestId;
use codex_login::login_with_api_key;
use tempfile::TempDir;
use tokio::time::timeout;
@@ -46,7 +46,7 @@ async fn logout_chatgpt_removes_auth() {
login_with_api_key(codex_home.path(), "sk-test-key").expect("seed api key");
assert!(codex_home.path().join("auth.json").exists());
let mut mcp = McpProcess::new(codex_home.path())
let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)])
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
@@ -95,7 +95,7 @@ async fn logout_chatgpt_removes_auth() {
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn login_and_cancel_chatgpt() {
let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
create_config_toml(codex_home.path()).expect("write config.toml");
create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
let mut mcp = McpProcess::new(codex_home.path())
.await

View File

@@ -0,0 +1,13 @@
mod archive_conversation;
mod auth;
mod codex_message_processor_flow;
mod config;
mod create_conversation;
mod fuzzy_file_search;
mod interrupt;
mod list_resume;
mod login;
mod send_message;
mod set_default_model;
mod user_agent;
mod user_info;

View File

@@ -1,20 +1,20 @@
use std::path::Path;
use codex_protocol::mcp_protocol::AddConversationListenerParams;
use codex_protocol::mcp_protocol::AddConversationSubscriptionResponse;
use codex_protocol::mcp_protocol::ConversationId;
use codex_protocol::mcp_protocol::InputItem;
use codex_protocol::mcp_protocol::NewConversationParams;
use codex_protocol::mcp_protocol::NewConversationResponse;
use codex_protocol::mcp_protocol::SendUserMessageParams;
use codex_protocol::mcp_protocol::SendUserMessageResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::create_final_assistant_message_sse_response;
use mcp_test_support::create_mock_chat_completions_server;
use mcp_test_support::to_response;
use mcp_types::JSONRPCNotification;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::to_response;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
use codex_app_server_protocol::InputItem;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserMessageResponse;
use codex_protocol::ConversationId;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
use tokio::time::timeout;
@@ -136,7 +136,7 @@ async fn test_send_message_session_not_found() {
.expect("timeout")
.expect("init");
let unknown = ConversationId(uuid::Uuid::new_v4());
let unknown = ConversationId::new();
let req_id = mcp
.send_send_user_message_request(SendUserMessageParams {
conversation_id: unknown,

View File

@@ -0,0 +1,76 @@
use std::path::Path;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SetDefaultModelParams;
use codex_app_server_protocol::SetDefaultModelResponse;
use codex_core::config::ConfigToml;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn set_default_model_persists_overrides() {
let codex_home = TempDir::new().expect("create tempdir");
create_config_toml(codex_home.path()).expect("write config.toml");
let mut mcp = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
let params = SetDefaultModelParams {
model: Some("gpt-4.1".to_string()),
reasoning_effort: None,
};
let request_id = mcp
.send_set_default_model_request(params)
.await
.expect("send setDefaultModel");
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await
.expect("setDefaultModel timeout")
.expect("setDefaultModel response");
let _: SetDefaultModelResponse =
to_response(resp).expect("deserialize setDefaultModel response");
let config_path = codex_home.path().join("config.toml");
let config_contents = tokio::fs::read_to_string(&config_path)
.await
.expect("read config.toml");
let config_toml: ConfigToml = toml::from_str(&config_contents).expect("parse config.toml");
assert_eq!(
ConfigToml {
model: Some("gpt-4.1".to_string()),
model_reasoning_effort: None,
..Default::default()
},
config_toml,
);
}
// Helper to create a config.toml; mirrors create_conversation.rs
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
r#"
model = "gpt-5-codex"
model_reasoning_effort = "medium"
"#,
)
}

View File

@@ -1,10 +1,8 @@
use codex_core::default_client::DEFAULT_ORIGINATOR;
use codex_core::default_client::get_codex_user_agent;
use codex_protocol::mcp_protocol::GetUserAgentResponse;
use mcp_test_support::McpProcess;
use mcp_test_support::to_response;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::GetUserAgentResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
use tokio::time::timeout;
@@ -35,11 +33,18 @@ async fn get_user_agent_returns_current_codex_user_agent() {
.expect("getUserAgent timeout")
.expect("getUserAgent response");
let os_info = os_info::get();
let user_agent = format!(
"codex_cli_rs/0.0.0 ({} {}; {}) {} (codex-app-server-tests; 0.1.0)",
os_info.os_type(),
os_info.version(),
os_info.architecture().unwrap_or("unknown"),
codex_core::terminal::user_agent()
);
let received: GetUserAgentResponse =
to_response(response).expect("deserialize getUserAgent response");
let expected = GetUserAgentResponse {
user_agent: get_codex_user_agent(Some(DEFAULT_ORIGINATOR)),
};
let expected = GetUserAgentResponse { user_agent };
assert_eq!(received, expected);
}

View File

@@ -0,0 +1,78 @@
use std::time::Duration;
use anyhow::Context;
use app_test_support::McpProcess;
use app_test_support::to_response;
use base64::Engine;
use base64::engine::general_purpose::URL_SAFE_NO_PAD;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::UserInfoResponse;
use codex_core::auth::AuthDotJson;
use codex_core::auth::get_auth_file;
use codex_core::auth::write_auth_json;
use codex_core::token_data::IdTokenInfo;
use codex_core::token_data::TokenData;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: Duration = Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_info_returns_email_from_auth_json() {
let codex_home = TempDir::new().expect("create tempdir");
let auth_path = get_auth_file(codex_home.path());
let mut id_token = IdTokenInfo::default();
id_token.email = Some("user@example.com".to_string());
id_token.raw_jwt = encode_id_token_with_email("user@example.com").expect("encode id token");
let auth = AuthDotJson {
openai_api_key: None,
tokens: Some(TokenData {
id_token,
access_token: "access".to_string(),
refresh_token: "refresh".to_string(),
account_id: None,
}),
last_refresh: None,
};
write_auth_json(&auth_path, &auth).expect("write auth.json");
let mut mcp = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("initialize timeout")
.expect("initialize request");
let request_id = mcp.send_user_info_request().await.expect("send userInfo");
let response: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await
.expect("userInfo timeout")
.expect("userInfo response");
let received: UserInfoResponse = to_response(response).expect("deserialize userInfo response");
let expected = UserInfoResponse {
alleged_user_email: Some("user@example.com".to_string()),
};
assert_eq!(received, expected);
}
fn encode_id_token_with_email(email: &str) -> anyhow::Result<String> {
let header_b64 = URL_SAFE_NO_PAD.encode(
serde_json::to_vec(&json!({ "alg": "none", "typ": "JWT" }))
.context("serialize jwt header")?,
);
let payload =
serde_json::to_vec(&json!({ "email": email })).context("serialize jwt payload")?;
let payload_b64 = URL_SAFE_NO_PAD.encode(payload);
Ok(format!("{header_b64}.{payload_b64}.signature"))
}

View File

@@ -15,14 +15,13 @@ path = "src/main.rs"
workspace = true
[dependencies]
anyhow = "1"
similar = "2.7.0"
thiserror = "2.0.16"
tree-sitter = "0.25.9"
tree-sitter-bash = "0.25.0"
once_cell = "1"
anyhow = { workspace = true }
similar = { workspace = true }
thiserror = { workspace = true }
tree-sitter = { workspace = true }
tree-sitter-bash = { workspace = true }
[dev-dependencies]
assert_cmd = "2"
pretty_assertions = "1.4.1"
tempfile = "3.13.0"
assert_cmd = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }

View File

@@ -6,10 +6,10 @@ use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
use std::str::Utf8Error;
use std::sync::LazyLock;
use anyhow::Context;
use anyhow::Result;
use once_cell::sync::Lazy;
pub use parser::Hunk;
pub use parser::ParseError;
use parser::ParseError::*;
@@ -40,6 +40,11 @@ pub enum ApplyPatchError {
/// Error that occurs while computing replacements when applying patch chunks
#[error("{0}")]
ComputeReplacements(String),
/// A raw patch body was provided without an explicit `apply_patch` invocation.
#[error(
"patch detected without explicit call to apply_patch. Rerun as [\"apply_patch\", \"<patch>\"]"
)]
ImplicitInvocation,
}
impl From<std::io::Error> for ApplyPatchError {
@@ -93,10 +98,12 @@ pub struct ApplyPatchArgs {
pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
match argv {
// Direct invocation: apply_patch <patch>
[cmd, body] if APPLY_PATCH_COMMANDS.contains(&cmd.as_str()) => match parse_patch(body) {
Ok(source) => MaybeApplyPatch::Body(source),
Err(e) => MaybeApplyPatch::PatchParseError(e),
},
// Bash heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
[bash, flag, script] if bash == "bash" && flag == "-lc" => {
match extract_apply_patch_from_bash(script) {
Ok((body, workdir)) => match parse_patch(&body) {
@@ -207,6 +214,26 @@ impl ApplyPatchAction {
/// cwd must be an absolute path so that we can resolve relative paths in the
/// patch.
pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApplyPatchVerified {
// Detect a raw patch body passed directly as the command or as the body of a bash -lc
// script. In these cases, report an explicit error rather than applying the patch.
match argv {
[body] => {
if parse_patch(body).is_ok() {
return MaybeApplyPatchVerified::CorrectnessError(
ApplyPatchError::ImplicitInvocation,
);
}
}
[bash, flag, script] if bash == "bash" && flag == "-lc" => {
if parse_patch(script).is_ok() {
return MaybeApplyPatchVerified::CorrectnessError(
ApplyPatchError::ImplicitInvocation,
);
}
}
_ => {}
}
match maybe_parse_apply_patch(argv) {
MaybeApplyPatch::Body(ApplyPatchArgs {
patch,
@@ -324,7 +351,7 @@ fn extract_apply_patch_from_bash(
// also run an arbitrary query against the AST. This is useful for understanding
// how tree-sitter parses the script and whether the query syntax is correct. Be sure
// to test both positive and negative cases.
static APPLY_PATCH_QUERY: Lazy<Query> = Lazy::new(|| {
static APPLY_PATCH_QUERY: LazyLock<Query> = LazyLock::new(|| {
let language = BASH.into();
#[expect(clippy::expect_used)]
Query::new(
@@ -621,21 +648,18 @@ fn derive_new_contents_from_chunks(
}
};
let mut original_lines: Vec<String> = original_contents
.split('\n')
.map(|s| s.to_string())
.collect();
let mut original_lines: Vec<String> = original_contents.split('\n').map(String::from).collect();
// Drop the trailing empty element that results from the final newline so
// that line counts match the behaviour of standard `diff`.
if original_lines.last().is_some_and(|s| s.is_empty()) {
if original_lines.last().is_some_and(String::is_empty) {
original_lines.pop();
}
let replacements = compute_replacements(&original_lines, path, chunks)?;
let new_lines = apply_replacements(original_lines, &replacements);
let mut new_lines = new_lines;
if !new_lines.last().is_some_and(|s| s.is_empty()) {
if !new_lines.last().is_some_and(String::is_empty) {
new_lines.push(String::new());
}
let new_contents = new_lines.join("\n");
@@ -679,7 +703,7 @@ fn compute_replacements(
if chunk.old_lines.is_empty() {
// Pure addition (no old lines). We'll add them at the end or just
// before the final empty line if one exists.
let insertion_idx = if original_lines.last().is_some_and(|s| s.is_empty()) {
let insertion_idx = if original_lines.last().is_some_and(String::is_empty) {
original_lines.len() - 1
} else {
original_lines.len()
@@ -705,11 +729,11 @@ fn compute_replacements(
let mut new_slice: &[String] = &chunk.new_lines;
if found.is_none() && pattern.last().is_some_and(|s| s.is_empty()) {
if found.is_none() && pattern.last().is_some_and(String::is_empty) {
// Retry without the trailing empty line which represents the final
// newline in the file.
pattern = &pattern[..pattern.len() - 1];
if new_slice.last().is_some_and(|s| s.is_empty()) {
if new_slice.last().is_some_and(String::is_empty) {
new_slice = &new_slice[..new_slice.len() - 1];
}
@@ -726,13 +750,15 @@ fn compute_replacements(
line_index = start_idx + pattern.len();
} else {
return Err(ApplyPatchError::ComputeReplacements(format!(
"Failed to find expected lines {:?} in {}",
chunk.old_lines,
path.display()
"Failed to find expected lines in {}:\n{}",
path.display(),
chunk.old_lines.join("\n"),
)));
}
}
replacements.sort_by(|(lhs_idx, _, _), (rhs_idx, _, _)| lhs_idx.cmp(rhs_idx));
Ok(replacements)
}
@@ -819,6 +845,7 @@ mod tests {
use super::*;
use pretty_assertions::assert_eq;
use std::fs;
use std::string::ToString;
use tempfile::tempdir;
/// Helper to construct a patch with the given body.
@@ -827,7 +854,7 @@ mod tests {
}
fn strs_to_strings(strs: &[&str]) -> Vec<String> {
strs.iter().map(|s| s.to_string()).collect()
strs.iter().map(ToString::to_string).collect()
}
// Test helpers to reduce repetition when building bash -lc heredoc scripts
@@ -873,6 +900,28 @@ mod tests {
));
}
#[test]
fn test_implicit_patch_single_arg_is_error() {
let patch = "*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch".to_string();
let args = vec![patch];
let dir = tempdir().unwrap();
assert!(matches!(
maybe_parse_apply_patch_verified(&args, dir.path()),
MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation)
));
}
#[test]
fn test_implicit_patch_bash_script_is_error() {
let script = "*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch";
let args = args_bash(script);
let dir = tempdir().unwrap();
assert!(matches!(
maybe_parse_apply_patch_verified(&args, dir.path()),
MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation)
));
}
#[test]
fn test_literal() {
let args = strs_to_strings(&[
@@ -1216,6 +1265,33 @@ PATCH"#,
assert_eq!(contents, "a\nB\nc\nd\nE\nf\ng\n");
}
#[test]
fn test_pure_addition_chunk_followed_by_removal() {
let dir = tempdir().unwrap();
let path = dir.path().join("panic.txt");
fs::write(&path, "line1\nline2\nline3\n").unwrap();
let patch = wrap_patch(&format!(
r#"*** Update File: {}
@@
+after-context
+second-line
@@
line1
-line2
-line3
+line2-replacement"#,
path.display()
));
let mut stdout = Vec::new();
let mut stderr = Vec::new();
apply_patch(&patch, &mut stdout, &mut stderr).unwrap();
let contents = fs::read_to_string(path).unwrap();
assert_eq!(
contents,
"line1\nline2-replacement\nafter-context\nsecond-line\n"
);
}
/// Ensure that patches authored with ASCII characters can update lines that
/// contain typographic Unicode punctuation (e.g. EN DASH, NON-BREAKING
/// HYPHEN). Historically `git apply` succeeds in such scenarios but our

View File

@@ -617,7 +617,7 @@ fn test_parse_patch_lenient() {
assert_eq!(
parse_patch_text(&patch_text_in_double_quoted_heredoc, ParseMode::Lenient),
Ok(ApplyPatchArgs {
hunks: expected_patch.clone(),
hunks: expected_patch,
patch: patch_text.to_string(),
workdir: None,
})
@@ -637,7 +637,7 @@ fn test_parse_patch_lenient() {
"<<EOF\n*** Begin Patch\n*** Update File: file2.py\nEOF\n".to_string();
assert_eq!(
parse_patch_text(&patch_text_with_missing_closing_heredoc, ParseMode::Strict),
Err(expected_error.clone())
Err(expected_error)
);
assert_eq!(
parse_patch_text(&patch_text_with_missing_closing_heredoc, ParseMode::Lenient),

View File

@@ -112,9 +112,10 @@ pub(crate) fn seek_sequence(
#[cfg(test)]
mod tests {
use super::seek_sequence;
use std::string::ToString;
fn to_vec(strings: &[&str]) -> Vec<String> {
strings.iter().map(|s| s.to_string()).collect()
strings.iter().map(ToString::to_string).collect()
}
#[test]

View File

@@ -11,10 +11,10 @@ path = "src/lib.rs"
workspace = true
[dependencies]
anyhow = "1"
codex-apply-patch = { path = "../apply-patch" }
codex-core = { path = "../core" }
codex-linux-sandbox = { path = "../linux-sandbox" }
dotenvy = "0.15.7"
tempfile = "3"
tokio = { version = "1", features = ["rt-multi-thread"] }
anyhow = { workspace = true }
codex-apply-patch = { workspace = true }
codex-core = { workspace = true }
codex-linux-sandbox = { workspace = true }
dotenvy = { workspace = true }
tempfile = { workspace = true }
tokio = { workspace = true, features = ["rt-multi-thread"] }

View File

@@ -54,7 +54,7 @@ where
let argv1 = args.next().unwrap_or_default();
if argv1 == CODEX_APPLY_PATCH_ARG1 {
let patch_arg = args.next().and_then(|s| s.to_str().map(|s| s.to_owned()));
let patch_arg = args.next().and_then(|s| s.to_str().map(str::to_owned));
let exit_code = match patch_arg {
Some(patch_arg) => {
let mut stdout = std::io::stdout();

View File

@@ -0,0 +1,18 @@
[package]
name = "codex-backend-client"
version = "0.0.0"
edition = "2024"
publish = false
[lib]
path = "src/lib.rs"
[dependencies]
anyhow = "1"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] }
codex-backend-openapi-models = { path = "../codex-backend-openapi-models" }
[dev-dependencies]
pretty_assertions = "1"

View File

@@ -0,0 +1,244 @@
use crate::types::CodeTaskDetailsResponse;
use crate::types::PaginatedListTaskListItem;
use crate::types::TurnAttemptsSiblingTurnsResponse;
use anyhow::Result;
use reqwest::header::AUTHORIZATION;
use reqwest::header::CONTENT_TYPE;
use reqwest::header::HeaderMap;
use reqwest::header::HeaderName;
use reqwest::header::HeaderValue;
use reqwest::header::USER_AGENT;
use serde::de::DeserializeOwned;
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum PathStyle {
/// /api/codex/…
CodexApi,
/// /wham/…
ChatGptApi,
}
impl PathStyle {
pub fn from_base_url(base_url: &str) -> Self {
if base_url.contains("/backend-api") {
PathStyle::ChatGptApi
} else {
PathStyle::CodexApi
}
}
}
#[derive(Clone, Debug)]
pub struct Client {
base_url: String,
http: reqwest::Client,
bearer_token: Option<String>,
user_agent: Option<HeaderValue>,
chatgpt_account_id: Option<String>,
path_style: PathStyle,
}
impl Client {
pub fn new(base_url: impl Into<String>) -> Result<Self> {
let mut base_url = base_url.into();
// Normalize common ChatGPT hostnames to include /backend-api so we hit the WHAM paths.
// Also trim trailing slashes for consistent URL building.
while base_url.ends_with('/') {
base_url.pop();
}
if (base_url.starts_with("https://chatgpt.com")
|| base_url.starts_with("https://chat.openai.com"))
&& !base_url.contains("/backend-api")
{
base_url = format!("{base_url}/backend-api");
}
let http = reqwest::Client::builder().build()?;
let path_style = PathStyle::from_base_url(&base_url);
Ok(Self {
base_url,
http,
bearer_token: None,
user_agent: None,
chatgpt_account_id: None,
path_style,
})
}
pub fn with_bearer_token(mut self, token: impl Into<String>) -> Self {
self.bearer_token = Some(token.into());
self
}
pub fn with_user_agent(mut self, ua: impl Into<String>) -> Self {
if let Ok(hv) = HeaderValue::from_str(&ua.into()) {
self.user_agent = Some(hv);
}
self
}
pub fn with_chatgpt_account_id(mut self, account_id: impl Into<String>) -> Self {
self.chatgpt_account_id = Some(account_id.into());
self
}
pub fn with_path_style(mut self, style: PathStyle) -> Self {
self.path_style = style;
self
}
fn headers(&self) -> HeaderMap {
let mut h = HeaderMap::new();
if let Some(ua) = &self.user_agent {
h.insert(USER_AGENT, ua.clone());
} else {
h.insert(USER_AGENT, HeaderValue::from_static("codex-cli"));
}
if let Some(token) = &self.bearer_token {
let value = format!("Bearer {token}");
if let Ok(hv) = HeaderValue::from_str(&value) {
h.insert(AUTHORIZATION, hv);
}
}
if let Some(acc) = &self.chatgpt_account_id
&& let Ok(name) = HeaderName::from_bytes(b"ChatGPT-Account-Id")
&& let Ok(hv) = HeaderValue::from_str(acc)
{
h.insert(name, hv);
}
h
}
async fn exec_request(
&self,
req: reqwest::RequestBuilder,
method: &str,
url: &str,
) -> Result<(String, String)> {
let res = req.send().await?;
let status = res.status();
let ct = res
.headers()
.get(CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.unwrap_or("")
.to_string();
let body = res.text().await.unwrap_or_default();
if !status.is_success() {
anyhow::bail!("{method} {url} failed: {status}; content-type={ct}; body={body}");
}
Ok((body, ct))
}
fn decode_json<T: DeserializeOwned>(&self, url: &str, ct: &str, body: &str) -> Result<T> {
match serde_json::from_str::<T>(body) {
Ok(v) => Ok(v),
Err(e) => {
anyhow::bail!("Decode error for {url}: {e}; content-type={ct}; body={body}");
}
}
}
pub async fn list_tasks(
&self,
limit: Option<i32>,
task_filter: Option<&str>,
environment_id: Option<&str>,
) -> Result<PaginatedListTaskListItem> {
let url = match self.path_style {
PathStyle::CodexApi => format!("{}/api/codex/tasks/list", self.base_url),
PathStyle::ChatGptApi => format!("{}/wham/tasks/list", self.base_url),
};
let req = self.http.get(&url).headers(self.headers());
let req = if let Some(lim) = limit {
req.query(&[("limit", lim)])
} else {
req
};
let req = if let Some(tf) = task_filter {
req.query(&[("task_filter", tf)])
} else {
req
};
let req = if let Some(id) = environment_id {
req.query(&[("environment_id", id)])
} else {
req
};
let (body, ct) = self.exec_request(req, "GET", &url).await?;
self.decode_json::<PaginatedListTaskListItem>(&url, &ct, &body)
}
pub async fn get_task_details(&self, task_id: &str) -> Result<CodeTaskDetailsResponse> {
let (parsed, _body, _ct) = self.get_task_details_with_body(task_id).await?;
Ok(parsed)
}
pub async fn get_task_details_with_body(
&self,
task_id: &str,
) -> Result<(CodeTaskDetailsResponse, String, String)> {
let url = match self.path_style {
PathStyle::CodexApi => format!("{}/api/codex/tasks/{}", self.base_url, task_id),
PathStyle::ChatGptApi => format!("{}/wham/tasks/{}", self.base_url, task_id),
};
let req = self.http.get(&url).headers(self.headers());
let (body, ct) = self.exec_request(req, "GET", &url).await?;
let parsed: CodeTaskDetailsResponse = self.decode_json(&url, &ct, &body)?;
Ok((parsed, body, ct))
}
pub async fn list_sibling_turns(
&self,
task_id: &str,
turn_id: &str,
) -> Result<TurnAttemptsSiblingTurnsResponse> {
let url = match self.path_style {
PathStyle::CodexApi => format!(
"{}/api/codex/tasks/{}/turns/{}/sibling_turns",
self.base_url, task_id, turn_id
),
PathStyle::ChatGptApi => format!(
"{}/wham/tasks/{}/turns/{}/sibling_turns",
self.base_url, task_id, turn_id
),
};
let req = self.http.get(&url).headers(self.headers());
let (body, ct) = self.exec_request(req, "GET", &url).await?;
self.decode_json::<TurnAttemptsSiblingTurnsResponse>(&url, &ct, &body)
}
/// Create a new task (user turn) by POSTing to the appropriate backend path
/// based on `path_style`. Returns the created task id.
pub async fn create_task(&self, request_body: serde_json::Value) -> Result<String> {
let url = match self.path_style {
PathStyle::CodexApi => format!("{}/api/codex/tasks", self.base_url),
PathStyle::ChatGptApi => format!("{}/wham/tasks", self.base_url),
};
let req = self
.http
.post(&url)
.headers(self.headers())
.header(CONTENT_TYPE, HeaderValue::from_static("application/json"))
.json(&request_body);
let (body, ct) = self.exec_request(req, "POST", &url).await?;
// Extract id from JSON: prefer `task.id`; fallback to top-level `id` when present.
match serde_json::from_str::<serde_json::Value>(&body) {
Ok(v) => {
if let Some(id) = v
.get("task")
.and_then(|t| t.get("id"))
.and_then(|s| s.as_str())
{
Ok(id.to_string())
} else if let Some(id) = v.get("id").and_then(|s| s.as_str()) {
Ok(id.to_string())
} else {
anyhow::bail!(
"POST {url} succeeded but no task id found; content-type={ct}; body={body}"
);
}
}
Err(e) => anyhow::bail!("Decode error for {url}: {e}; content-type={ct}; body={body}"),
}
}
}

View File

@@ -0,0 +1,9 @@
mod client;
pub mod types;
pub use client::Client;
pub use types::CodeTaskDetailsResponse;
pub use types::CodeTaskDetailsResponseExt;
pub use types::PaginatedListTaskListItem;
pub use types::TaskListItem;
pub use types::TurnAttemptsSiblingTurnsResponse;

View File

@@ -0,0 +1,369 @@
pub use codex_backend_openapi_models::models::PaginatedListTaskListItem;
pub use codex_backend_openapi_models::models::TaskListItem;
use serde::Deserialize;
use serde::de::Deserializer;
use serde_json::Value;
use std::collections::HashMap;
/// Hand-rolled models for the Cloud Tasks task-details response.
/// The generated OpenAPI models are pretty bad. This is a half-step
/// towards hand-rolling them.
#[derive(Clone, Debug, Deserialize)]
pub struct CodeTaskDetailsResponse {
#[serde(default)]
pub current_user_turn: Option<Turn>,
#[serde(default)]
pub current_assistant_turn: Option<Turn>,
#[serde(default)]
pub current_diff_task_turn: Option<Turn>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct Turn {
#[serde(default)]
pub id: Option<String>,
#[serde(default)]
pub attempt_placement: Option<i64>,
#[serde(default, rename = "turn_status")]
pub turn_status: Option<String>,
#[serde(default, deserialize_with = "deserialize_vec")]
pub sibling_turn_ids: Vec<String>,
#[serde(default, deserialize_with = "deserialize_vec")]
pub input_items: Vec<TurnItem>,
#[serde(default, deserialize_with = "deserialize_vec")]
pub output_items: Vec<TurnItem>,
#[serde(default)]
pub worklog: Option<Worklog>,
#[serde(default)]
pub error: Option<TurnError>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct TurnItem {
#[serde(rename = "type", default)]
pub kind: String,
#[serde(default)]
pub role: Option<String>,
#[serde(default, deserialize_with = "deserialize_vec")]
pub content: Vec<ContentFragment>,
#[serde(default)]
pub diff: Option<String>,
#[serde(default)]
pub output_diff: Option<DiffPayload>,
}
#[derive(Clone, Debug, Deserialize)]
#[serde(untagged)]
pub enum ContentFragment {
Structured(StructuredContent),
Text(String),
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct StructuredContent {
#[serde(rename = "content_type", default)]
pub content_type: Option<String>,
#[serde(default)]
pub text: Option<String>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct DiffPayload {
#[serde(default)]
pub diff: Option<String>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct Worklog {
#[serde(default, deserialize_with = "deserialize_vec")]
pub messages: Vec<WorklogMessage>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct WorklogMessage {
#[serde(default)]
pub author: Option<Author>,
#[serde(default)]
pub content: Option<WorklogContent>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct Author {
#[serde(default)]
pub role: Option<String>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct WorklogContent {
#[serde(default)]
pub parts: Vec<ContentFragment>,
}
#[derive(Clone, Debug, Default, Deserialize)]
pub struct TurnError {
#[serde(default)]
pub code: Option<String>,
#[serde(default)]
pub message: Option<String>,
}
impl ContentFragment {
fn text(&self) -> Option<&str> {
match self {
ContentFragment::Structured(inner) => {
if inner
.content_type
.as_deref()
.map(|ct| ct.eq_ignore_ascii_case("text"))
.unwrap_or(false)
{
inner.text.as_deref().filter(|s| !s.is_empty())
} else {
None
}
}
ContentFragment::Text(raw) => {
if raw.trim().is_empty() {
None
} else {
Some(raw.as_str())
}
}
}
}
}
impl TurnItem {
fn text_values(&self) -> Vec<String> {
self.content
.iter()
.filter_map(|fragment| fragment.text().map(str::to_string))
.collect()
}
fn diff_text(&self) -> Option<String> {
if self.kind == "output_diff" {
if let Some(diff) = &self.diff
&& !diff.is_empty()
{
return Some(diff.clone());
}
} else if self.kind == "pr"
&& let Some(payload) = &self.output_diff
&& let Some(diff) = &payload.diff
&& !diff.is_empty()
{
return Some(diff.clone());
}
None
}
}
impl Turn {
fn unified_diff(&self) -> Option<String> {
self.output_items.iter().find_map(TurnItem::diff_text)
}
fn message_texts(&self) -> Vec<String> {
let mut out: Vec<String> = self
.output_items
.iter()
.filter(|item| item.kind == "message")
.flat_map(TurnItem::text_values)
.collect();
if let Some(log) = &self.worklog {
for message in &log.messages {
if message.is_assistant() {
out.extend(message.text_values());
}
}
}
out
}
fn user_prompt(&self) -> Option<String> {
let parts: Vec<String> = self
.input_items
.iter()
.filter(|item| item.kind == "message")
.filter(|item| {
item.role
.as_deref()
.map(|r| r.eq_ignore_ascii_case("user"))
.unwrap_or(true)
})
.flat_map(TurnItem::text_values)
.collect();
if parts.is_empty() {
None
} else {
Some(parts.join(
"
",
))
}
}
fn error_summary(&self) -> Option<String> {
self.error.as_ref().and_then(TurnError::summary)
}
}
impl WorklogMessage {
fn is_assistant(&self) -> bool {
self.author
.as_ref()
.and_then(|a| a.role.as_deref())
.map(|role| role.eq_ignore_ascii_case("assistant"))
.unwrap_or(false)
}
fn text_values(&self) -> Vec<String> {
self.content
.as_ref()
.map(|content| {
content
.parts
.iter()
.filter_map(|fragment| fragment.text().map(str::to_string))
.collect()
})
.unwrap_or_default()
}
}
impl TurnError {
fn summary(&self) -> Option<String> {
let code = self.code.as_deref().unwrap_or("");
let message = self.message.as_deref().unwrap_or("");
match (code.is_empty(), message.is_empty()) {
(true, true) => None,
(false, true) => Some(code.to_string()),
(true, false) => Some(message.to_string()),
(false, false) => Some(format!("{code}: {message}")),
}
}
}
pub trait CodeTaskDetailsResponseExt {
/// Attempt to extract a unified diff string from the assistant or diff turn.
fn unified_diff(&self) -> Option<String>;
/// Extract assistant text output messages (no diff) from current turns.
fn assistant_text_messages(&self) -> Vec<String>;
/// Extract the user's prompt text from the current user turn, when present.
fn user_text_prompt(&self) -> Option<String>;
/// Extract an assistant error message (if the turn failed and provided one).
fn assistant_error_message(&self) -> Option<String>;
}
impl CodeTaskDetailsResponseExt for CodeTaskDetailsResponse {
fn unified_diff(&self) -> Option<String> {
[
self.current_diff_task_turn.as_ref(),
self.current_assistant_turn.as_ref(),
]
.into_iter()
.flatten()
.find_map(Turn::unified_diff)
}
fn assistant_text_messages(&self) -> Vec<String> {
let mut out = Vec::new();
for turn in [
self.current_diff_task_turn.as_ref(),
self.current_assistant_turn.as_ref(),
]
.into_iter()
.flatten()
{
out.extend(turn.message_texts());
}
out
}
fn user_text_prompt(&self) -> Option<String> {
self.current_user_turn.as_ref().and_then(Turn::user_prompt)
}
fn assistant_error_message(&self) -> Option<String> {
self.current_assistant_turn
.as_ref()
.and_then(Turn::error_summary)
}
}
fn deserialize_vec<'de, D, T>(deserializer: D) -> Result<Vec<T>, D::Error>
where
D: Deserializer<'de>,
T: Deserialize<'de>,
{
Option::<Vec<T>>::deserialize(deserializer).map(|opt| opt.unwrap_or_default())
}
#[derive(Clone, Debug, Deserialize)]
pub struct TurnAttemptsSiblingTurnsResponse {
#[serde(default)]
pub sibling_turns: Vec<HashMap<String, Value>>,
}
#[cfg(test)]
mod tests {
use super::*;
use pretty_assertions::assert_eq;
fn fixture(name: &str) -> CodeTaskDetailsResponse {
let json = match name {
"diff" => include_str!("../tests/fixtures/task_details_with_diff.json"),
"error" => include_str!("../tests/fixtures/task_details_with_error.json"),
other => panic!("unknown fixture {other}"),
};
serde_json::from_str(json).expect("fixture should deserialize")
}
#[test]
fn unified_diff_prefers_current_diff_task_turn() {
let details = fixture("diff");
let diff = details.unified_diff().expect("diff present");
assert!(diff.contains("diff --git"));
}
#[test]
fn unified_diff_falls_back_to_pr_output_diff() {
let details = fixture("error");
let diff = details.unified_diff().expect("diff from pr output");
assert!(diff.contains("lib.rs"));
}
#[test]
fn assistant_text_messages_extracts_text_content() {
let details = fixture("diff");
let messages = details.assistant_text_messages();
assert_eq!(messages, vec!["Assistant response".to_string()]);
}
#[test]
fn user_text_prompt_joins_parts_with_spacing() {
let details = fixture("diff");
let prompt = details.user_text_prompt().expect("prompt present");
assert_eq!(
prompt,
"First line
Second line"
);
}
#[test]
fn assistant_error_message_combines_code_and_message() {
let details = fixture("error");
let msg = details
.assistant_error_message()
.expect("error should be present");
assert_eq!(msg, "APPLY_FAILED: Patch could not be applied");
}
}

View File

@@ -0,0 +1,38 @@
{
"task": {
"id": "task_123",
"title": "Refactor cloud task client",
"archived": false,
"external_pull_requests": []
},
"current_user_turn": {
"input_items": [
{
"type": "message",
"role": "user",
"content": [
{ "content_type": "text", "text": "First line" },
{ "content_type": "text", "text": "Second line" }
]
}
]
},
"current_assistant_turn": {
"output_items": [
{
"type": "message",
"content": [
{ "content_type": "text", "text": "Assistant response" }
]
}
]
},
"current_diff_task_turn": {
"output_items": [
{
"type": "output_diff",
"diff": "diff --git a/src/main.rs b/src/main.rs\n+fn main() { println!(\"hi\"); }\n"
}
]
}
}

View File

@@ -0,0 +1,22 @@
{
"task": {
"id": "task_456",
"title": "Investigate failure",
"archived": false,
"external_pull_requests": []
},
"current_assistant_turn": {
"output_items": [
{
"type": "pr",
"output_diff": {
"diff": "diff --git a/lib.rs b/lib.rs\n+pub fn hello() {}\n"
}
}
],
"error": {
"code": "APPLY_FAILED",
"message": "Patch could not be applied"
}
}
}

View File

@@ -7,15 +7,14 @@ version = { workspace = true }
workspace = true
[dependencies]
anyhow = "1"
clap = { version = "4", features = ["derive"] }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
codex-protocol = { path = "../protocol" }
reqwest = { version = "0.12", features = ["json", "stream"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tokio = { version = "1", features = ["full"] }
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive"] }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
tokio = { workspace = true, features = ["full"] }
codex-git-apply = { path = "../git-apply" }
[dev-dependencies]
tempfile = "3"
tempfile = { workspace = true }

View File

@@ -31,7 +31,7 @@ pub async fn run_apply_command(
ConfigOverrides::default(),
)?;
init_chatgpt_token_from_auth(&config.codex_home, &config.responses_originator_header).await?;
init_chatgpt_token_from_auth(&config.codex_home).await?;
let task_response = get_task(&config, apply_cli.task_id).await?;
apply_diff_from_task(task_response, cwd).await
@@ -56,46 +56,24 @@ pub async fn apply_diff_from_task(
}
async fn apply_diff(diff: &str, cwd: Option<PathBuf>) -> anyhow::Result<()> {
let mut cmd = tokio::process::Command::new("git");
if let Some(cwd) = cwd {
cmd.current_dir(cwd);
}
let toplevel_output = cmd
.args(vec!["rev-parse", "--show-toplevel"])
.output()
.await?;
if !toplevel_output.status.success() {
anyhow::bail!("apply must be run from a git repository.");
}
let repo_root = String::from_utf8(toplevel_output.stdout)?
.trim()
.to_string();
let mut git_apply_cmd = tokio::process::Command::new("git")
.args(vec!["apply", "--3way"])
.current_dir(&repo_root)
.stdin(std::process::Stdio::piped())
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()?;
if let Some(mut stdin) = git_apply_cmd.stdin.take() {
tokio::io::AsyncWriteExt::write_all(&mut stdin, diff.as_bytes()).await?;
drop(stdin);
}
let output = git_apply_cmd.wait_with_output().await?;
if !output.status.success() {
let cwd = cwd.unwrap_or(std::env::current_dir().unwrap_or_else(|_| std::env::temp_dir()));
let req = codex_git_apply::ApplyGitRequest {
cwd,
diff: diff.to_string(),
revert: false,
preflight: false,
};
let res = codex_git_apply::apply_git_patch(&req)?;
if res.exit_code != 0 {
anyhow::bail!(
"Git apply failed with status {}: {}",
output.status,
String::from_utf8_lossy(&output.stderr)
"Git apply failed (applied={}, skipped={}, conflicts={})\nstdout:\n{}\nstderr:\n{}",
res.applied_paths.len(),
res.skipped_paths.len(),
res.conflicted_paths.len(),
res.stdout,
res.stderr
);
}
println!("Successfully applied diff");
Ok(())
}

View File

@@ -13,10 +13,10 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
path: String,
) -> anyhow::Result<T> {
let chatgpt_base_url = &config.chatgpt_base_url;
init_chatgpt_token_from_auth(&config.codex_home, &config.responses_originator_header).await?;
init_chatgpt_token_from_auth(&config.codex_home).await?;
// Make direct HTTP request to ChatGPT backend API with the token
let client = create_client(&config.responses_originator_header);
let client = create_client();
let url = format!("{chatgpt_base_url}{path}");
let token =
@@ -44,6 +44,6 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
} else {
let status = response.status();
let body = response.text().await.unwrap_or_default();
anyhow::bail!("Request failed with status {}: {}", status, body)
anyhow::bail!("Request failed with status {status}: {body}")
}
}

View File

@@ -1,5 +1,4 @@
use codex_core::CodexAuth;
use codex_protocol::mcp_protocol::AuthMode;
use std::path::Path;
use std::sync::LazyLock;
use std::sync::RwLock;
@@ -19,11 +18,8 @@ pub fn set_chatgpt_token_data(value: TokenData) {
}
/// Initialize the ChatGPT token from auth.json file
pub async fn init_chatgpt_token_from_auth(
codex_home: &Path,
originator: &str,
) -> std::io::Result<()> {
let auth = CodexAuth::from_codex_home(codex_home, AuthMode::ChatGPT, originator)?;
pub async fn init_chatgpt_token_from_auth(codex_home: &Path) -> std::io::Result<()> {
let auth = CodexAuth::from_codex_home(codex_home)?;
if let Some(auth) = auth {
let token_data = auth.get_token_data().await?;
set_chatgpt_token_data(token_data);

View File

@@ -15,26 +15,38 @@ path = "src/lib.rs"
workspace = true
[dependencies]
anyhow = "1"
clap = { version = "4", features = ["derive"] }
clap_complete = "4"
codex-arg0 = { path = "../arg0" }
codex-chatgpt = { path = "../chatgpt" }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
codex-exec = { path = "../exec" }
codex-login = { path = "../login" }
codex-mcp-server = { path = "../mcp-server" }
codex-protocol = { path = "../protocol" }
codex-tui = { path = "../tui" }
serde_json = "1"
tokio = { version = "1", features = [
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive"] }
clap_complete = { workspace = true }
codex-app-server = { workspace = true }
codex-arg0 = { workspace = true }
codex-chatgpt = { workspace = true }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
codex-exec = { workspace = true }
codex-login = { workspace = true }
codex-mcp-server = { workspace = true }
codex-process-hardening = { workspace = true }
codex-protocol = { workspace = true }
codex-app-server-protocol = { workspace = true }
codex-protocol-ts = { workspace = true }
codex-responses-api-proxy = { workspace = true }
codex-tui = { workspace = true }
codex-cloud-tasks = { path = "../cloud-tasks" }
ctor = { workspace = true }
owo-colors = { workspace = true }
serde_json = { workspace = true }
supports-color = { workspace = true }
tokio = { workspace = true, features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tracing = "0.1.41"
tracing-subscriber = "0.3.19"
codex-protocol-ts = { path = "../protocol-ts" }
[dev-dependencies]
assert_cmd = { workspace = true }
predicates = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }

View File

@@ -64,7 +64,6 @@ async fn run_command_under_sandbox(
sandbox_type: SandboxType,
) -> anyhow::Result<()> {
let sandbox_mode = create_sandbox_mode(full_auto);
let cwd = std::env::current_dir()?;
let config = Config::load_with_cli_overrides(
config_overrides
.parse_overrides()
@@ -75,13 +74,29 @@ async fn run_command_under_sandbox(
..Default::default()
},
)?;
// In practice, this should be `std::env::current_dir()` because this CLI
// does not support `--cwd`, but let's use the config value for consistency.
let cwd = config.cwd.clone();
// For now, we always use the same cwd for both the command and the
// sandbox policy. In the future, we could add a CLI option to set them
// separately.
let sandbox_policy_cwd = cwd.clone();
let stdio_policy = StdioPolicy::Inherit;
let env = create_env(&config.shell_environment_policy);
let mut child = match sandbox_type {
SandboxType::Seatbelt => {
spawn_command_under_seatbelt(command, &config.sandbox_policy, cwd, stdio_policy, env)
.await?
spawn_command_under_seatbelt(
command,
cwd,
&config.sandbox_policy,
sandbox_policy_cwd.as_path(),
stdio_policy,
env,
)
.await?
}
SandboxType::Landlock => {
#[expect(clippy::expect_used)]
@@ -91,8 +106,9 @@ async fn run_command_under_sandbox(
spawn_command_under_linux_sandbox(
codex_linux_sandbox_exe,
command,
&config.sandbox_policy,
cwd,
&config.sandbox_policy,
sandbox_policy_cwd.as_path(),
stdio_policy,
env,
)

View File

@@ -1,7 +1,6 @@
pub mod debug_sandbox;
mod exit_status;
pub mod login;
pub mod proto;
use clap::Parser;
use codex_common::CliConfigOverrides;

View File

@@ -1,19 +1,18 @@
use codex_app_server_protocol::AuthMode;
use codex_common::CliConfigOverrides;
use codex_core::CodexAuth;
use codex_core::auth::CLIENT_ID;
use codex_core::auth::OPENAI_API_KEY_ENV_VAR;
use codex_core::auth::login_with_api_key;
use codex_core::auth::logout;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_login::ServerOptions;
use codex_login::run_device_code_login;
use codex_login::run_login_server;
use codex_protocol::mcp_protocol::AuthMode;
use std::env;
use std::path::PathBuf;
pub async fn login_with_chatgpt(codex_home: PathBuf, originator: String) -> std::io::Result<()> {
let opts = ServerOptions::new(codex_home, CLIENT_ID.to_string(), originator);
pub async fn login_with_chatgpt(codex_home: PathBuf) -> std::io::Result<()> {
let opts = ServerOptions::new(codex_home, CLIENT_ID.to_string());
let server = run_login_server(opts)?;
eprintln!(
@@ -27,12 +26,7 @@ pub async fn login_with_chatgpt(codex_home: PathBuf, originator: String) -> std:
pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) -> ! {
let config = load_config_or_exit(cli_config_overrides);
match login_with_chatgpt(
config.codex_home,
config.responses_originator_header.clone(),
)
.await
{
match login_with_chatgpt(config.codex_home).await {
Ok(_) => {
eprintln!("Successfully logged in");
std::process::exit(0);
@@ -62,26 +56,40 @@ pub async fn run_login_with_api_key(
}
}
/// Login using the OAuth device code flow.
pub async fn run_login_with_device_code(
cli_config_overrides: CliConfigOverrides,
issuer_base_url: Option<String>,
client_id: Option<String>,
) -> ! {
let config = load_config_or_exit(cli_config_overrides);
let mut opts = ServerOptions::new(
config.codex_home,
client_id.unwrap_or(CLIENT_ID.to_string()),
);
if let Some(iss) = issuer_base_url {
opts.issuer = iss;
}
match run_device_code_login(opts).await {
Ok(()) => {
eprintln!("Successfully logged in");
std::process::exit(0);
}
Err(e) => {
eprintln!("Error logging in with device code: {e}");
std::process::exit(1);
}
}
}
pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
let config = load_config_or_exit(cli_config_overrides);
match CodexAuth::from_codex_home(
&config.codex_home,
config.preferred_auth_method,
&config.responses_originator_header,
) {
match CodexAuth::from_codex_home(&config.codex_home) {
Ok(Some(auth)) => match auth.mode {
AuthMode::ApiKey => match auth.get_token().await {
Ok(api_key) => {
eprintln!("Logged in using an API key - {}", safe_format_key(&api_key));
if let Ok(env_api_key) = env::var(OPENAI_API_KEY_ENV_VAR)
&& env_api_key == api_key
{
eprintln!(
" API loaded from OPENAI_API_KEY environment variable or .env file"
);
}
std::process::exit(0);
}
Err(e) => {

View File

@@ -10,14 +10,21 @@ use codex_cli::SeatbeltCommand;
use codex_cli::login::run_login_status;
use codex_cli::login::run_login_with_api_key;
use codex_cli::login::run_login_with_chatgpt;
use codex_cli::login::run_login_with_device_code;
use codex_cli::login::run_logout;
use codex_cli::proto;
use codex_cloud_tasks::Cli as CloudTasksCli;
use codex_common::CliConfigOverrides;
use codex_exec::Cli as ExecCli;
use codex_responses_api_proxy::Args as ResponsesApiProxyArgs;
use codex_tui::AppExitInfo;
use codex_tui::Cli as TuiCli;
use owo_colors::OwoColorize;
use std::path::PathBuf;
use supports_color::Stream;
use crate::proto::ProtoCli;
mod mcp_cmd;
use crate::mcp_cmd::McpCli;
/// Codex CLI
///
@@ -56,12 +63,14 @@ enum Subcommand {
/// Remove stored authentication credentials.
Logout(LogoutCommand),
/// Experimental: run Codex as an MCP server.
Mcp,
/// [experimental] Run Codex as an MCP server and manage MCP servers.
Mcp(McpCli),
/// Run the Protocol stream via stdin/stdout
#[clap(visible_alias = "p")]
Proto(ProtoCli),
/// [experimental] Run the Codex MCP server (stdio transport).
McpServer,
/// [experimental] Run the app server.
AppServer,
/// Generate shell completion scripts.
Completion(CompletionCommand),
@@ -73,9 +82,19 @@ enum Subcommand {
#[clap(visible_alias = "a")]
Apply(ApplyCommand),
/// Resume a previous interactive session (picker by default; use --last to continue the most recent).
Resume(ResumeCommand),
/// Internal: generate TypeScript protocol bindings.
#[clap(hide = true)]
GenerateTs(GenerateTsCommand),
/// [EXPERIMENTAL] Browse tasks from Codex Cloud and apply changes locally.
#[clap(name = "cloud", alias = "cloud-tasks")]
Cloud(CloudTasksCli),
/// Internal: run the responses API proxy.
#[clap(hide = true)]
ResponsesApiProxy(ResponsesApiProxyArgs),
}
#[derive(Debug, Parser)]
@@ -85,6 +104,21 @@ struct CompletionCommand {
shell: Shell,
}
#[derive(Debug, Parser)]
struct ResumeCommand {
/// Conversation/session id (UUID). When provided, resumes this session.
/// If omitted, use --last to pick the most recent recorded session.
#[arg(value_name = "SESSION_ID")]
session_id: Option<String>,
/// Continue the most recent session without showing the picker.
#[arg(long = "last", default_value_t = false, conflicts_with = "session_id")]
last: bool,
#[clap(flatten)]
config_overrides: TuiCli,
}
#[derive(Debug, Parser)]
struct DebugArgs {
#[command(subcommand)]
@@ -108,6 +142,20 @@ struct LoginCommand {
#[arg(long = "api-key", value_name = "API_KEY")]
api_key: Option<String>,
/// EXPERIMENTAL: Use device code flow (not yet supported)
/// This feature is experimental and may changed in future releases.
#[arg(long = "experimental_use-device-code", hide = true)]
use_device_code: bool,
/// EXPERIMENTAL: Use custom OAuth issuer base URL (advanced)
/// Override the OAuth issuer base URL (advanced)
#[arg(long = "experimental_issuer", value_name = "URL", hide = true)]
issuer_base_url: Option<String>,
/// EXPERIMENTAL: Use custom OAuth client ID (advanced)
#[arg(long = "experimental_client-id", value_name = "CLIENT_ID", hide = true)]
client_id: Option<String>,
#[command(subcommand)]
action: Option<LoginSubcommand>,
}
@@ -135,6 +183,49 @@ struct GenerateTsCommand {
prettier: Option<PathBuf>,
}
fn format_exit_messages(exit_info: AppExitInfo, color_enabled: bool) -> Vec<String> {
let AppExitInfo {
token_usage,
conversation_id,
} = exit_info;
if token_usage.is_zero() {
return Vec::new();
}
let mut lines = vec![format!(
"{}",
codex_core::protocol::FinalOutput::from(token_usage)
)];
if let Some(session_id) = conversation_id {
let resume_cmd = format!("codex resume {session_id}");
let command = if color_enabled {
resume_cmd.cyan().to_string()
} else {
resume_cmd
};
lines.push(format!("To continue this session, run {command}"));
}
lines
}
fn print_exit_messages(exit_info: AppExitInfo) {
let color_enabled = supports_color::on(Stream::Stdout).is_some();
for line in format_exit_messages(exit_info, color_enabled) {
println!("{line}");
}
}
/// As early as possible in the process lifecycle, apply hardening measures. We
/// skip this in debug builds to avoid interfering with debugging.
#[ctor::ctor]
#[cfg(not(debug_assertions))]
fn pre_main_hardening() {
codex_process_hardening::pre_main_hardening();
}
fn main() -> anyhow::Result<()> {
arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
cli_main(codex_linux_sandbox_exe).await?;
@@ -143,32 +234,71 @@ fn main() -> anyhow::Result<()> {
}
async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()> {
let cli = MultitoolCli::parse();
let MultitoolCli {
config_overrides: root_config_overrides,
mut interactive,
subcommand,
} = MultitoolCli::parse();
match cli.subcommand {
match subcommand {
None => {
let mut tui_cli = cli.interactive;
prepend_config_flags(&mut tui_cli.config_overrides, cli.config_overrides);
let usage = codex_tui::run_main(tui_cli, codex_linux_sandbox_exe).await?;
if !usage.is_zero() {
println!("{}", codex_core::protocol::FinalOutput::from(usage));
}
prepend_config_flags(
&mut interactive.config_overrides,
root_config_overrides.clone(),
);
let exit_info = codex_tui::run_main(interactive, codex_linux_sandbox_exe).await?;
print_exit_messages(exit_info);
}
Some(Subcommand::Exec(mut exec_cli)) => {
prepend_config_flags(&mut exec_cli.config_overrides, cli.config_overrides);
prepend_config_flags(
&mut exec_cli.config_overrides,
root_config_overrides.clone(),
);
codex_exec::run_main(exec_cli, codex_linux_sandbox_exe).await?;
}
Some(Subcommand::Mcp) => {
codex_mcp_server::run_main(codex_linux_sandbox_exe, cli.config_overrides).await?;
Some(Subcommand::McpServer) => {
codex_mcp_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
}
Some(Subcommand::Mcp(mut mcp_cli)) => {
// Propagate any root-level config overrides (e.g. `-c key=value`).
prepend_config_flags(&mut mcp_cli.config_overrides, root_config_overrides.clone());
mcp_cli.run().await?;
}
Some(Subcommand::AppServer) => {
codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
}
Some(Subcommand::Resume(ResumeCommand {
session_id,
last,
config_overrides,
})) => {
interactive = finalize_resume_interactive(
interactive,
root_config_overrides.clone(),
session_id,
last,
config_overrides,
);
codex_tui::run_main(interactive, codex_linux_sandbox_exe).await?;
}
Some(Subcommand::Login(mut login_cli)) => {
prepend_config_flags(&mut login_cli.config_overrides, cli.config_overrides);
prepend_config_flags(
&mut login_cli.config_overrides,
root_config_overrides.clone(),
);
match login_cli.action {
Some(LoginSubcommand::Status) => {
run_login_status(login_cli.config_overrides).await;
}
None => {
if let Some(api_key) = login_cli.api_key {
if login_cli.use_device_code {
run_login_with_device_code(
login_cli.config_overrides,
login_cli.issuer_base_url,
login_cli.client_id,
)
.await;
} else if let Some(api_key) = login_cli.api_key {
run_login_with_api_key(login_cli.config_overrides, api_key).await;
} else {
run_login_with_chatgpt(login_cli.config_overrides).await;
@@ -177,19 +307,28 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
}
}
Some(Subcommand::Logout(mut logout_cli)) => {
prepend_config_flags(&mut logout_cli.config_overrides, cli.config_overrides);
prepend_config_flags(
&mut logout_cli.config_overrides,
root_config_overrides.clone(),
);
run_logout(logout_cli.config_overrides).await;
}
Some(Subcommand::Proto(mut proto_cli)) => {
prepend_config_flags(&mut proto_cli.config_overrides, cli.config_overrides);
proto::run_main(proto_cli).await?;
}
Some(Subcommand::Completion(completion_cli)) => {
print_completion(completion_cli);
}
Some(Subcommand::Cloud(mut cloud_cli)) => {
prepend_config_flags(
&mut cloud_cli.config_overrides,
root_config_overrides.clone(),
);
codex_cloud_tasks::run_main(cloud_cli, codex_linux_sandbox_exe).await?;
}
Some(Subcommand::Debug(debug_args)) => match debug_args.cmd {
DebugCommand::Seatbelt(mut seatbelt_cli) => {
prepend_config_flags(&mut seatbelt_cli.config_overrides, cli.config_overrides);
prepend_config_flags(
&mut seatbelt_cli.config_overrides,
root_config_overrides.clone(),
);
codex_cli::debug_sandbox::run_command_under_seatbelt(
seatbelt_cli,
codex_linux_sandbox_exe,
@@ -197,7 +336,10 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
.await?;
}
DebugCommand::Landlock(mut landlock_cli) => {
prepend_config_flags(&mut landlock_cli.config_overrides, cli.config_overrides);
prepend_config_flags(
&mut landlock_cli.config_overrides,
root_config_overrides.clone(),
);
codex_cli::debug_sandbox::run_command_under_landlock(
landlock_cli,
codex_linux_sandbox_exe,
@@ -206,9 +348,16 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
}
},
Some(Subcommand::Apply(mut apply_cli)) => {
prepend_config_flags(&mut apply_cli.config_overrides, cli.config_overrides);
prepend_config_flags(
&mut apply_cli.config_overrides,
root_config_overrides.clone(),
);
run_apply_command(apply_cli, None).await?;
}
Some(Subcommand::ResponsesApiProxy(args)) => {
tokio::task::spawn_blocking(move || codex_responses_api_proxy::run_main(args))
.await??;
}
Some(Subcommand::GenerateTs(gen_cli)) => {
codex_protocol_ts::generate_ts(&gen_cli.out_dir, gen_cli.prettier.as_deref())?;
}
@@ -228,8 +377,256 @@ fn prepend_config_flags(
.splice(0..0, cli_config_overrides.raw_overrides);
}
/// Build the final `TuiCli` for a `codex resume` invocation.
fn finalize_resume_interactive(
mut interactive: TuiCli,
root_config_overrides: CliConfigOverrides,
session_id: Option<String>,
last: bool,
resume_cli: TuiCli,
) -> TuiCli {
// Start with the parsed interactive CLI so resume shares the same
// configuration surface area as `codex` without additional flags.
let resume_session_id = session_id;
interactive.resume_picker = resume_session_id.is_none() && !last;
interactive.resume_last = last;
interactive.resume_session_id = resume_session_id;
// Merge resume-scoped flags and overrides with highest precedence.
merge_resume_cli_flags(&mut interactive, resume_cli);
// Propagate any root-level config overrides (e.g. `-c key=value`).
prepend_config_flags(&mut interactive.config_overrides, root_config_overrides);
interactive
}
/// Merge flags provided to `codex resume` so they take precedence over any
/// root-level flags. Only overrides fields explicitly set on the resume-scoped
/// CLI. Also appends `-c key=value` overrides with highest precedence.
fn merge_resume_cli_flags(interactive: &mut TuiCli, resume_cli: TuiCli) {
if let Some(model) = resume_cli.model {
interactive.model = Some(model);
}
if resume_cli.oss {
interactive.oss = true;
}
if let Some(profile) = resume_cli.config_profile {
interactive.config_profile = Some(profile);
}
if let Some(sandbox) = resume_cli.sandbox_mode {
interactive.sandbox_mode = Some(sandbox);
}
if let Some(approval) = resume_cli.approval_policy {
interactive.approval_policy = Some(approval);
}
if resume_cli.full_auto {
interactive.full_auto = true;
}
if resume_cli.dangerously_bypass_approvals_and_sandbox {
interactive.dangerously_bypass_approvals_and_sandbox = true;
}
if let Some(cwd) = resume_cli.cwd {
interactive.cwd = Some(cwd);
}
if resume_cli.web_search {
interactive.web_search = true;
}
if !resume_cli.images.is_empty() {
interactive.images = resume_cli.images;
}
if let Some(prompt) = resume_cli.prompt {
interactive.prompt = Some(prompt);
}
interactive
.config_overrides
.raw_overrides
.extend(resume_cli.config_overrides.raw_overrides);
}
fn print_completion(cmd: CompletionCommand) {
let mut app = MultitoolCli::command();
let name = "codex";
generate(cmd.shell, &mut app, name, &mut std::io::stdout());
}
#[cfg(test)]
mod tests {
use super::*;
use codex_core::protocol::TokenUsage;
use codex_protocol::ConversationId;
fn finalize_from_args(args: &[&str]) -> TuiCli {
let cli = MultitoolCli::try_parse_from(args).expect("parse");
let MultitoolCli {
interactive,
config_overrides: root_overrides,
subcommand,
} = cli;
let Subcommand::Resume(ResumeCommand {
session_id,
last,
config_overrides: resume_cli,
}) = subcommand.expect("resume present")
else {
unreachable!()
};
finalize_resume_interactive(interactive, root_overrides, session_id, last, resume_cli)
}
fn sample_exit_info(conversation: Option<&str>) -> AppExitInfo {
let token_usage = TokenUsage {
output_tokens: 2,
total_tokens: 2,
..Default::default()
};
AppExitInfo {
token_usage,
conversation_id: conversation
.map(ConversationId::from_string)
.map(Result::unwrap),
}
}
#[test]
fn format_exit_messages_skips_zero_usage() {
let exit_info = AppExitInfo {
token_usage: TokenUsage::default(),
conversation_id: None,
};
let lines = format_exit_messages(exit_info, false);
assert!(lines.is_empty());
}
#[test]
fn format_exit_messages_includes_resume_hint_without_color() {
let exit_info = sample_exit_info(Some("123e4567-e89b-12d3-a456-426614174000"));
let lines = format_exit_messages(exit_info, false);
assert_eq!(
lines,
vec![
"Token usage: total=2 input=0 output=2".to_string(),
"To continue this session, run codex resume 123e4567-e89b-12d3-a456-426614174000"
.to_string(),
]
);
}
#[test]
fn format_exit_messages_applies_color_when_enabled() {
let exit_info = sample_exit_info(Some("123e4567-e89b-12d3-a456-426614174000"));
let lines = format_exit_messages(exit_info, true);
assert_eq!(lines.len(), 2);
assert!(lines[1].contains("\u{1b}[36m"));
}
#[test]
fn resume_model_flag_applies_when_no_root_flags() {
let interactive = finalize_from_args(["codex", "resume", "-m", "gpt-5-test"].as_ref());
assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_picker_logic_none_and_not_last() {
let interactive = finalize_from_args(["codex", "resume"].as_ref());
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_picker_logic_last() {
let interactive = finalize_from_args(["codex", "resume", "--last"].as_ref());
assert!(!interactive.resume_picker);
assert!(interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_picker_logic_with_session_id() {
let interactive = finalize_from_args(["codex", "resume", "1234"].as_ref());
assert!(!interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id.as_deref(), Some("1234"));
}
#[test]
fn resume_merges_option_flags_and_full_auto() {
let interactive = finalize_from_args(
[
"codex",
"resume",
"sid",
"--oss",
"--full-auto",
"--search",
"--sandbox",
"workspace-write",
"--ask-for-approval",
"on-request",
"-m",
"gpt-5-test",
"-p",
"my-profile",
"-C",
"/tmp",
"-i",
"/tmp/a.png,/tmp/b.png",
]
.as_ref(),
);
assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
assert!(interactive.oss);
assert_eq!(interactive.config_profile.as_deref(), Some("my-profile"));
assert!(matches!(
interactive.sandbox_mode,
Some(codex_common::SandboxModeCliArg::WorkspaceWrite)
));
assert!(matches!(
interactive.approval_policy,
Some(codex_common::ApprovalModeCliArg::OnRequest)
));
assert!(interactive.full_auto);
assert_eq!(
interactive.cwd.as_deref(),
Some(std::path::Path::new("/tmp"))
);
assert!(interactive.web_search);
let has_a = interactive
.images
.iter()
.any(|p| p == std::path::Path::new("/tmp/a.png"));
let has_b = interactive
.images
.iter()
.any(|p| p == std::path::Path::new("/tmp/b.png"));
assert!(has_a && has_b);
assert!(!interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id.as_deref(), Some("sid"));
}
#[test]
fn resume_merges_dangerously_bypass_flag() {
let interactive = finalize_from_args(
[
"codex",
"resume",
"--dangerously-bypass-approvals-and-sandbox",
]
.as_ref(),
);
assert!(interactive.dangerously_bypass_approvals_and_sandbox);
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
}

453
codex-rs/cli/src/mcp_cmd.rs Normal file
View File

@@ -0,0 +1,453 @@
use std::collections::HashMap;
use anyhow::Context;
use anyhow::Result;
use anyhow::anyhow;
use anyhow::bail;
use codex_common::CliConfigOverrides;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::config::find_codex_home;
use codex_core::config::load_global_mcp_servers;
use codex_core::config::write_global_mcp_servers;
use codex_core::config_types::McpServerConfig;
use codex_core::config_types::McpServerTransportConfig;
/// [experimental] Launch Codex as an MCP server or manage configured MCP servers.
///
/// Subcommands:
/// - `serve` — run the MCP server on stdio
/// - `list` — list configured servers (with `--json`)
/// - `get` — show a single server (with `--json`)
/// - `add` — add a server launcher entry to `~/.codex/config.toml`
/// - `remove` — delete a server entry
#[derive(Debug, clap::Parser)]
pub struct McpCli {
#[clap(flatten)]
pub config_overrides: CliConfigOverrides,
#[command(subcommand)]
pub subcommand: McpSubcommand,
}
#[derive(Debug, clap::Subcommand)]
pub enum McpSubcommand {
/// [experimental] List configured MCP servers.
List(ListArgs),
/// [experimental] Show details for a configured MCP server.
Get(GetArgs),
/// [experimental] Add a global MCP server entry.
Add(AddArgs),
/// [experimental] Remove a global MCP server entry.
Remove(RemoveArgs),
}
#[derive(Debug, clap::Parser)]
pub struct ListArgs {
/// Output the configured servers as JSON.
#[arg(long)]
pub json: bool,
}
#[derive(Debug, clap::Parser)]
pub struct GetArgs {
/// Name of the MCP server to display.
pub name: String,
/// Output the server configuration as JSON.
#[arg(long)]
pub json: bool,
}
#[derive(Debug, clap::Parser)]
pub struct AddArgs {
/// Name for the MCP server configuration.
pub name: String,
/// Environment variables to set when launching the server.
#[arg(long, value_parser = parse_env_pair, value_name = "KEY=VALUE")]
pub env: Vec<(String, String)>,
/// Command to launch the MCP server.
#[arg(trailing_var_arg = true, num_args = 1..)]
pub command: Vec<String>,
}
#[derive(Debug, clap::Parser)]
pub struct RemoveArgs {
/// Name of the MCP server configuration to remove.
pub name: String,
}
impl McpCli {
pub async fn run(self) -> Result<()> {
let McpCli {
config_overrides,
subcommand,
} = self;
match subcommand {
McpSubcommand::List(args) => {
run_list(&config_overrides, args)?;
}
McpSubcommand::Get(args) => {
run_get(&config_overrides, args)?;
}
McpSubcommand::Add(args) => {
run_add(&config_overrides, args)?;
}
McpSubcommand::Remove(args) => {
run_remove(&config_overrides, args)?;
}
}
Ok(())
}
}
fn run_add(config_overrides: &CliConfigOverrides, add_args: AddArgs) -> Result<()> {
// Validate any provided overrides even though they are not currently applied.
config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
let AddArgs { name, env, command } = add_args;
validate_server_name(&name)?;
let mut command_parts = command.into_iter();
let command_bin = command_parts
.next()
.ok_or_else(|| anyhow!("command is required"))?;
let command_args: Vec<String> = command_parts.collect();
let env_map = if env.is_empty() {
None
} else {
let mut map = HashMap::new();
for (key, value) in env {
map.insert(key, value);
}
Some(map)
};
let codex_home = find_codex_home().context("failed to resolve CODEX_HOME")?;
let mut servers = load_global_mcp_servers(&codex_home)
.with_context(|| format!("failed to load MCP servers from {}", codex_home.display()))?;
let new_entry = McpServerConfig {
transport: McpServerTransportConfig::Stdio {
command: command_bin,
args: command_args,
env: env_map,
},
startup_timeout_sec: None,
tool_timeout_sec: None,
};
servers.insert(name.clone(), new_entry);
write_global_mcp_servers(&codex_home, &servers)
.with_context(|| format!("failed to write MCP servers to {}", codex_home.display()))?;
println!("Added global MCP server '{name}'.");
Ok(())
}
fn run_remove(config_overrides: &CliConfigOverrides, remove_args: RemoveArgs) -> Result<()> {
config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
let RemoveArgs { name } = remove_args;
validate_server_name(&name)?;
let codex_home = find_codex_home().context("failed to resolve CODEX_HOME")?;
let mut servers = load_global_mcp_servers(&codex_home)
.with_context(|| format!("failed to load MCP servers from {}", codex_home.display()))?;
let removed = servers.remove(&name).is_some();
if removed {
write_global_mcp_servers(&codex_home, &servers)
.with_context(|| format!("failed to write MCP servers to {}", codex_home.display()))?;
}
if removed {
println!("Removed global MCP server '{name}'.");
} else {
println!("No MCP server named '{name}' found.");
}
Ok(())
}
fn run_list(config_overrides: &CliConfigOverrides, list_args: ListArgs) -> Result<()> {
let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
.context("failed to load configuration")?;
let mut entries: Vec<_> = config.mcp_servers.iter().collect();
entries.sort_by(|(a, _), (b, _)| a.cmp(b));
if list_args.json {
let json_entries: Vec<_> = entries
.into_iter()
.map(|(name, cfg)| {
let transport = match &cfg.transport {
McpServerTransportConfig::Stdio { command, args, env } => serde_json::json!({
"type": "stdio",
"command": command,
"args": args,
"env": env,
}),
McpServerTransportConfig::StreamableHttp { url, bearer_token } => {
serde_json::json!({
"type": "streamable_http",
"url": url,
"bearer_token": bearer_token,
})
}
};
serde_json::json!({
"name": name,
"transport": transport,
"startup_timeout_sec": cfg
.startup_timeout_sec
.map(|timeout| timeout.as_secs_f64()),
"tool_timeout_sec": cfg
.tool_timeout_sec
.map(|timeout| timeout.as_secs_f64()),
})
})
.collect();
let output = serde_json::to_string_pretty(&json_entries)?;
println!("{output}");
return Ok(());
}
if entries.is_empty() {
println!("No MCP servers configured yet. Try `codex mcp add my-tool -- my-command`.");
return Ok(());
}
let mut stdio_rows: Vec<[String; 4]> = Vec::new();
let mut http_rows: Vec<[String; 3]> = Vec::new();
for (name, cfg) in entries {
match &cfg.transport {
McpServerTransportConfig::Stdio { command, args, env } => {
let args_display = if args.is_empty() {
"-".to_string()
} else {
args.join(" ")
};
let env_display = match env.as_ref() {
None => "-".to_string(),
Some(map) if map.is_empty() => "-".to_string(),
Some(map) => {
let mut pairs: Vec<_> = map.iter().collect();
pairs.sort_by(|(a, _), (b, _)| a.cmp(b));
pairs
.into_iter()
.map(|(k, v)| format!("{k}={v}"))
.collect::<Vec<_>>()
.join(", ")
}
};
stdio_rows.push([name.clone(), command.clone(), args_display, env_display]);
}
McpServerTransportConfig::StreamableHttp { url, bearer_token } => {
let has_bearer = if bearer_token.is_some() {
"True"
} else {
"False"
};
http_rows.push([name.clone(), url.clone(), has_bearer.into()]);
}
}
}
if !stdio_rows.is_empty() {
let mut widths = ["Name".len(), "Command".len(), "Args".len(), "Env".len()];
for row in &stdio_rows {
for (i, cell) in row.iter().enumerate() {
widths[i] = widths[i].max(cell.len());
}
}
println!(
"{:<name_w$} {:<cmd_w$} {:<args_w$} {:<env_w$}",
"Name",
"Command",
"Args",
"Env",
name_w = widths[0],
cmd_w = widths[1],
args_w = widths[2],
env_w = widths[3],
);
for row in &stdio_rows {
println!(
"{:<name_w$} {:<cmd_w$} {:<args_w$} {:<env_w$}",
row[0],
row[1],
row[2],
row[3],
name_w = widths[0],
cmd_w = widths[1],
args_w = widths[2],
env_w = widths[3],
);
}
}
if !stdio_rows.is_empty() && !http_rows.is_empty() {
println!();
}
if !http_rows.is_empty() {
let mut widths = ["Name".len(), "Url".len(), "Has Bearer Token".len()];
for row in &http_rows {
for (i, cell) in row.iter().enumerate() {
widths[i] = widths[i].max(cell.len());
}
}
println!(
"{:<name_w$} {:<url_w$} {:<token_w$}",
"Name",
"Url",
"Has Bearer Token",
name_w = widths[0],
url_w = widths[1],
token_w = widths[2],
);
for row in &http_rows {
println!(
"{:<name_w$} {:<url_w$} {:<token_w$}",
row[0],
row[1],
row[2],
name_w = widths[0],
url_w = widths[1],
token_w = widths[2],
);
}
}
Ok(())
}
fn run_get(config_overrides: &CliConfigOverrides, get_args: GetArgs) -> Result<()> {
let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
.context("failed to load configuration")?;
let Some(server) = config.mcp_servers.get(&get_args.name) else {
bail!("No MCP server named '{name}' found.", name = get_args.name);
};
if get_args.json {
let transport = match &server.transport {
McpServerTransportConfig::Stdio { command, args, env } => serde_json::json!({
"type": "stdio",
"command": command,
"args": args,
"env": env,
}),
McpServerTransportConfig::StreamableHttp { url, bearer_token } => serde_json::json!({
"type": "streamable_http",
"url": url,
"bearer_token": bearer_token,
}),
};
let output = serde_json::to_string_pretty(&serde_json::json!({
"name": get_args.name,
"transport": transport,
"startup_timeout_sec": server
.startup_timeout_sec
.map(|timeout| timeout.as_secs_f64()),
"tool_timeout_sec": server
.tool_timeout_sec
.map(|timeout| timeout.as_secs_f64()),
}))?;
println!("{output}");
return Ok(());
}
println!("{}", get_args.name);
match &server.transport {
McpServerTransportConfig::Stdio { command, args, env } => {
println!(" transport: stdio");
println!(" command: {command}");
let args_display = if args.is_empty() {
"-".to_string()
} else {
args.join(" ")
};
println!(" args: {args_display}");
let env_display = match env.as_ref() {
None => "-".to_string(),
Some(map) if map.is_empty() => "-".to_string(),
Some(map) => {
let mut pairs: Vec<_> = map.iter().collect();
pairs.sort_by(|(a, _), (b, _)| a.cmp(b));
pairs
.into_iter()
.map(|(k, v)| format!("{k}={v}"))
.collect::<Vec<_>>()
.join(", ")
}
};
println!(" env: {env_display}");
}
McpServerTransportConfig::StreamableHttp { url, bearer_token } => {
println!(" transport: streamable_http");
println!(" url: {url}");
let bearer = bearer_token.as_deref().unwrap_or("-");
println!(" bearer_token: {bearer}");
}
}
if let Some(timeout) = server.startup_timeout_sec {
println!(" startup_timeout_sec: {}", timeout.as_secs_f64());
}
if let Some(timeout) = server.tool_timeout_sec {
println!(" tool_timeout_sec: {}", timeout.as_secs_f64());
}
println!(" remove: codex mcp remove {}", get_args.name);
Ok(())
}
fn parse_env_pair(raw: &str) -> Result<(String, String), String> {
let mut parts = raw.splitn(2, '=');
let key = parts
.next()
.map(str::trim)
.filter(|s| !s.is_empty())
.ok_or_else(|| "environment entries must be in KEY=VALUE form".to_string())?;
let value = parts
.next()
.map(str::to_string)
.ok_or_else(|| "environment entries must be in KEY=VALUE form".to_string())?;
Ok((key.to_string(), value))
}
fn validate_server_name(name: &str) -> Result<()> {
let is_valid = !name.is_empty()
&& name
.chars()
.all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_');
if is_valid {
Ok(())
} else {
bail!("invalid server name '{name}' (use letters, numbers, '-', '_')");
}
}

View File

@@ -1,136 +0,0 @@
use std::io::IsTerminal;
use clap::Parser;
use codex_common::CliConfigOverrides;
use codex_core::AuthManager;
use codex_core::ConversationManager;
use codex_core::NewConversation;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::protocol::Event;
use codex_core::protocol::EventMsg;
use codex_core::protocol::Submission;
use tokio::io::AsyncBufReadExt;
use tokio::io::BufReader;
use tracing::error;
use tracing::info;
#[derive(Debug, Parser)]
pub struct ProtoCli {
#[clap(skip)]
pub config_overrides: CliConfigOverrides,
}
pub async fn run_main(opts: ProtoCli) -> anyhow::Result<()> {
if std::io::stdin().is_terminal() {
anyhow::bail!("Protocol mode expects stdin to be a pipe, not a terminal");
}
tracing_subscriber::fmt()
.with_writer(std::io::stderr)
.init();
let ProtoCli { config_overrides } = opts;
let overrides_vec = config_overrides
.parse_overrides()
.map_err(anyhow::Error::msg)?;
let config = Config::load_with_cli_overrides(overrides_vec, ConfigOverrides::default())?;
// Use conversation_manager API to start a conversation
let conversation_manager = ConversationManager::new(AuthManager::shared(
config.codex_home.clone(),
config.preferred_auth_method,
config.responses_originator_header.clone(),
));
let NewConversation {
conversation_id: _,
conversation,
session_configured,
} = conversation_manager.new_conversation(config).await?;
// Simulate streaming the session_configured event.
let synthetic_event = Event {
// Fake id value.
id: "".to_string(),
msg: EventMsg::SessionConfigured(session_configured),
};
let session_configured_event = match serde_json::to_string(&synthetic_event) {
Ok(s) => s,
Err(e) => {
error!("Failed to serialize session_configured: {e}");
return Err(anyhow::Error::from(e));
}
};
println!("{session_configured_event}");
// Task that reads JSON lines from stdin and forwards to Submission Queue
let sq_fut = {
let conversation = conversation.clone();
async move {
let stdin = BufReader::new(tokio::io::stdin());
let mut lines = stdin.lines();
loop {
let result = tokio::select! {
_ = tokio::signal::ctrl_c() => {
break
},
res = lines.next_line() => res,
};
match result {
Ok(Some(line)) => {
let line = line.trim();
if line.is_empty() {
continue;
}
match serde_json::from_str::<Submission>(line) {
Ok(sub) => {
if let Err(e) = conversation.submit_with_id(sub).await {
error!("{e:#}");
break;
}
}
Err(e) => {
error!("invalid submission: {e}");
}
}
}
_ => {
info!("Submission queue closed");
break;
}
}
}
}
};
// Task that reads events from the agent and prints them as JSON lines to stdout
let eq_fut = async move {
loop {
let event = tokio::select! {
_ = tokio::signal::ctrl_c() => break,
event = conversation.next_event() => event,
};
match event {
Ok(event) => {
let event_str = match serde_json::to_string(&event) {
Ok(s) => s,
Err(e) => {
error!("Failed to serialize event: {e}");
continue;
}
};
println!("{event_str}");
}
Err(e) => {
error!("{e:#}");
break;
}
}
}
info!("Event queue closed");
};
tokio::join!(sq_fut, eq_fut);
Ok(())
}

View File

@@ -0,0 +1,95 @@
use std::path::Path;
use anyhow::Result;
use codex_core::config::load_global_mcp_servers;
use codex_core::config_types::McpServerTransportConfig;
use predicates::str::contains;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
fn codex_command(codex_home: &Path) -> Result<assert_cmd::Command> {
let mut cmd = assert_cmd::Command::cargo_bin("codex")?;
cmd.env("CODEX_HOME", codex_home);
Ok(cmd)
}
#[test]
fn add_and_remove_server_updates_global_config() -> Result<()> {
let codex_home = TempDir::new()?;
let mut add_cmd = codex_command(codex_home.path())?;
add_cmd
.args(["mcp", "add", "docs", "--", "echo", "hello"])
.assert()
.success()
.stdout(contains("Added global MCP server 'docs'."));
let servers = load_global_mcp_servers(codex_home.path())?;
assert_eq!(servers.len(), 1);
let docs = servers.get("docs").expect("server should exist");
match &docs.transport {
McpServerTransportConfig::Stdio { command, args, env } => {
assert_eq!(command, "echo");
assert_eq!(args, &vec!["hello".to_string()]);
assert!(env.is_none());
}
other => panic!("unexpected transport: {other:?}"),
}
let mut remove_cmd = codex_command(codex_home.path())?;
remove_cmd
.args(["mcp", "remove", "docs"])
.assert()
.success()
.stdout(contains("Removed global MCP server 'docs'."));
let servers = load_global_mcp_servers(codex_home.path())?;
assert!(servers.is_empty());
let mut remove_again_cmd = codex_command(codex_home.path())?;
remove_again_cmd
.args(["mcp", "remove", "docs"])
.assert()
.success()
.stdout(contains("No MCP server named 'docs' found."));
let servers = load_global_mcp_servers(codex_home.path())?;
assert!(servers.is_empty());
Ok(())
}
#[test]
fn add_with_env_preserves_key_order_and_values() -> Result<()> {
let codex_home = TempDir::new()?;
let mut add_cmd = codex_command(codex_home.path())?;
add_cmd
.args([
"mcp",
"add",
"envy",
"--env",
"FOO=bar",
"--env",
"ALPHA=beta",
"--",
"python",
"server.py",
])
.assert()
.success();
let servers = load_global_mcp_servers(codex_home.path())?;
let envy = servers.get("envy").expect("server should exist");
let env = match &envy.transport {
McpServerTransportConfig::Stdio { env: Some(env), .. } => env,
other => panic!("unexpected transport: {other:?}"),
};
assert_eq!(env.len(), 2);
assert_eq!(env.get("FOO"), Some(&"bar".to_string()));
assert_eq!(env.get("ALPHA"), Some(&"beta".to_string()));
Ok(())
}

View File

@@ -0,0 +1,104 @@
use std::path::Path;
use anyhow::Result;
use predicates::str::contains;
use pretty_assertions::assert_eq;
use serde_json::Value as JsonValue;
use serde_json::json;
use tempfile::TempDir;
fn codex_command(codex_home: &Path) -> Result<assert_cmd::Command> {
let mut cmd = assert_cmd::Command::cargo_bin("codex")?;
cmd.env("CODEX_HOME", codex_home);
Ok(cmd)
}
#[test]
fn list_shows_empty_state() -> Result<()> {
let codex_home = TempDir::new()?;
let mut cmd = codex_command(codex_home.path())?;
let output = cmd.args(["mcp", "list"]).output()?;
assert!(output.status.success());
let stdout = String::from_utf8(output.stdout)?;
assert!(stdout.contains("No MCP servers configured yet."));
Ok(())
}
#[test]
fn list_and_get_render_expected_output() -> Result<()> {
let codex_home = TempDir::new()?;
let mut add = codex_command(codex_home.path())?;
add.args([
"mcp",
"add",
"docs",
"--env",
"TOKEN=secret",
"--",
"docs-server",
"--port",
"4000",
])
.assert()
.success();
let mut list_cmd = codex_command(codex_home.path())?;
let list_output = list_cmd.args(["mcp", "list"]).output()?;
assert!(list_output.status.success());
let stdout = String::from_utf8(list_output.stdout)?;
assert!(stdout.contains("Name"));
assert!(stdout.contains("docs"));
assert!(stdout.contains("docs-server"));
assert!(stdout.contains("TOKEN=secret"));
let mut list_json_cmd = codex_command(codex_home.path())?;
let json_output = list_json_cmd.args(["mcp", "list", "--json"]).output()?;
assert!(json_output.status.success());
let stdout = String::from_utf8(json_output.stdout)?;
let parsed: JsonValue = serde_json::from_str(&stdout)?;
assert_eq!(
parsed,
json!([
{
"name": "docs",
"transport": {
"type": "stdio",
"command": "docs-server",
"args": [
"--port",
"4000"
],
"env": {
"TOKEN": "secret"
}
},
"startup_timeout_sec": null,
"tool_timeout_sec": null
}
]
)
);
let mut get_cmd = codex_command(codex_home.path())?;
let get_output = get_cmd.args(["mcp", "get", "docs"]).output()?;
assert!(get_output.status.success());
let stdout = String::from_utf8(get_output.stdout)?;
assert!(stdout.contains("docs"));
assert!(stdout.contains("transport: stdio"));
assert!(stdout.contains("command: docs-server"));
assert!(stdout.contains("args: --port 4000"));
assert!(stdout.contains("env: TOKEN=secret"));
assert!(stdout.contains("remove: codex mcp remove docs"));
let mut get_json_cmd = codex_command(codex_home.path())?;
get_json_cmd
.args(["mcp", "get", "docs", "--json"])
.assert()
.success()
.stdout(contains("\"name\": \"docs\""));
Ok(())
}

View File

@@ -0,0 +1,27 @@
[package]
name = "codex-cloud-tasks-client"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_cloud_tasks_client"
path = "src/lib.rs"
[lints]
workspace = true
[features]
default = ["online"]
online = ["dep:codex-backend-client"]
mock = []
[dependencies]
anyhow = "1"
async-trait = "0.1"
chrono = { version = "0.4", features = ["serde"] }
diffy = "0.4.2"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
thiserror = "2.0.12"
codex-backend-client = { path = "../backend-client", optional = true }
codex-git-apply = { path = "../git-apply" }

View File

@@ -0,0 +1,158 @@
use chrono::DateTime;
use chrono::Utc;
use serde::Deserialize;
use serde::Serialize;
pub type Result<T> = std::result::Result<T, CloudTaskError>;
#[derive(Debug, thiserror::Error)]
pub enum CloudTaskError {
#[error("unimplemented: {0}")]
Unimplemented(&'static str),
#[error("http error: {0}")]
Http(String),
#[error("io error: {0}")]
Io(String),
#[error("{0}")]
Msg(String),
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
#[serde(transparent)]
pub struct TaskId(pub String);
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "kebab-case")]
pub enum TaskStatus {
Pending,
Ready,
Applied,
Error,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct TaskSummary {
pub id: TaskId,
pub title: String,
pub status: TaskStatus,
pub updated_at: DateTime<Utc>,
/// Backend environment identifier (when available)
pub environment_id: Option<String>,
/// Human-friendly environment label (when available)
pub environment_label: Option<String>,
pub summary: DiffSummary,
/// True when the backend reports this task as a code review.
#[serde(default)]
pub is_review: bool,
/// Number of assistant attempts (best-of-N), when reported by the backend.
#[serde(default)]
pub attempt_total: Option<usize>,
}
#[derive(Clone, Copy, Debug, PartialEq, Eq, Default)]
pub enum AttemptStatus {
Pending,
InProgress,
Completed,
Failed,
Cancelled,
#[default]
Unknown,
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct TurnAttempt {
pub turn_id: String,
pub attempt_placement: Option<i64>,
pub created_at: Option<DateTime<Utc>>,
pub status: AttemptStatus,
pub diff: Option<String>,
pub messages: Vec<String>,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum ApplyStatus {
Success,
Partial,
Error,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct ApplyOutcome {
pub applied: bool,
pub status: ApplyStatus,
pub message: String,
#[serde(default)]
pub skipped_paths: Vec<String>,
#[serde(default)]
pub conflict_paths: Vec<String>,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct CreatedTask {
pub id: TaskId,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Default)]
pub struct DiffSummary {
pub files_changed: usize,
pub lines_added: usize,
pub lines_removed: usize,
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct TaskText {
pub prompt: Option<String>,
pub messages: Vec<String>,
pub turn_id: Option<String>,
pub sibling_turn_ids: Vec<String>,
pub attempt_placement: Option<i64>,
pub attempt_status: AttemptStatus,
}
impl Default for TaskText {
fn default() -> Self {
Self {
prompt: None,
messages: Vec::new(),
turn_id: None,
sibling_turn_ids: Vec::new(),
attempt_placement: None,
attempt_status: AttemptStatus::Unknown,
}
}
}
#[async_trait::async_trait]
pub trait CloudBackend: Send + Sync {
async fn list_tasks(&self, env: Option<&str>) -> Result<Vec<TaskSummary>>;
async fn get_task_diff(&self, id: TaskId) -> Result<Option<String>>;
/// Return assistant output messages (no diff) when available.
async fn get_task_messages(&self, id: TaskId) -> Result<Vec<String>>;
/// Return the creating prompt and assistant messages (when available).
async fn get_task_text(&self, id: TaskId) -> Result<TaskText>;
/// Return any sibling attempts (best-of-N) for the given assistant turn.
async fn list_sibling_attempts(
&self,
task: TaskId,
turn_id: String,
) -> Result<Vec<TurnAttempt>>;
/// Dry-run apply (preflight) that validates whether the patch would apply cleanly.
/// Never modifies the working tree. When `diff_override` is supplied, the provided diff is
/// used instead of re-fetching the task details so callers can apply alternate attempts.
async fn apply_task_preflight(
&self,
id: TaskId,
diff_override: Option<String>,
) -> Result<ApplyOutcome>;
async fn apply_task(&self, id: TaskId, diff_override: Option<String>) -> Result<ApplyOutcome>;
async fn create_task(
&self,
env_id: &str,
prompt: &str,
git_ref: &str,
qa_mode: bool,
best_of_n: usize,
) -> Result<CreatedTask>;
}

View File

@@ -0,0 +1,769 @@
use crate::ApplyOutcome;
use crate::ApplyStatus;
use crate::AttemptStatus;
use crate::CloudBackend;
use crate::CloudTaskError;
use crate::DiffSummary;
use crate::Result;
use crate::TaskId;
use crate::TaskStatus;
use crate::TaskSummary;
use crate::TurnAttempt;
use crate::api::TaskText;
use chrono::DateTime;
use chrono::Utc;
use codex_backend_client as backend;
use codex_backend_client::CodeTaskDetailsResponseExt;
#[derive(Clone)]
pub struct HttpClient {
pub base_url: String,
backend: backend::Client,
}
impl HttpClient {
pub fn new(base_url: impl Into<String>) -> anyhow::Result<Self> {
let base_url = base_url.into();
let backend = backend::Client::new(base_url.clone())?;
Ok(Self { base_url, backend })
}
pub fn with_bearer_token(mut self, token: impl Into<String>) -> Self {
self.backend = self.backend.clone().with_bearer_token(token);
self
}
pub fn with_user_agent(mut self, ua: impl Into<String>) -> Self {
self.backend = self.backend.clone().with_user_agent(ua);
self
}
pub fn with_chatgpt_account_id(mut self, account_id: impl Into<String>) -> Self {
self.backend = self.backend.clone().with_chatgpt_account_id(account_id);
self
}
fn tasks_api(&self) -> api::Tasks<'_> {
api::Tasks::new(self)
}
fn attempts_api(&self) -> api::Attempts<'_> {
api::Attempts::new(self)
}
fn apply_api(&self) -> api::Apply<'_> {
api::Apply::new(self)
}
}
#[async_trait::async_trait]
impl CloudBackend for HttpClient {
async fn list_tasks(&self, env: Option<&str>) -> Result<Vec<TaskSummary>> {
self.tasks_api().list(env).await
}
async fn get_task_diff(&self, id: TaskId) -> Result<Option<String>> {
self.tasks_api().diff(id).await
}
async fn get_task_messages(&self, id: TaskId) -> Result<Vec<String>> {
self.tasks_api().messages(id).await
}
async fn get_task_text(&self, id: TaskId) -> Result<TaskText> {
self.tasks_api().task_text(id).await
}
async fn list_sibling_attempts(
&self,
task: TaskId,
turn_id: String,
) -> Result<Vec<TurnAttempt>> {
self.attempts_api().list(task, turn_id).await
}
async fn apply_task(&self, id: TaskId, diff_override: Option<String>) -> Result<ApplyOutcome> {
self.apply_api().run(id, diff_override, false).await
}
async fn apply_task_preflight(
&self,
id: TaskId,
diff_override: Option<String>,
) -> Result<ApplyOutcome> {
self.apply_api().run(id, diff_override, true).await
}
async fn create_task(
&self,
env_id: &str,
prompt: &str,
git_ref: &str,
qa_mode: bool,
best_of_n: usize,
) -> Result<crate::CreatedTask> {
self.tasks_api()
.create(env_id, prompt, git_ref, qa_mode, best_of_n)
.await
}
}
mod api {
use super::*;
use serde_json::Value;
use std::cmp::Ordering;
use std::collections::HashMap;
pub(crate) struct Tasks<'a> {
base_url: &'a str,
backend: &'a backend::Client,
}
impl<'a> Tasks<'a> {
pub(crate) fn new(client: &'a HttpClient) -> Self {
Self {
base_url: &client.base_url,
backend: &client.backend,
}
}
pub(crate) async fn list(&self, env: Option<&str>) -> Result<Vec<TaskSummary>> {
let resp = self
.backend
.list_tasks(Some(20), Some("current"), env)
.await
.map_err(|e| CloudTaskError::Http(format!("list_tasks failed: {e}")))?;
let tasks: Vec<TaskSummary> = resp
.items
.into_iter()
.map(map_task_list_item_to_summary)
.collect();
append_error_log(&format!(
"http.list_tasks: env={} items={}",
env.unwrap_or("<all>"),
tasks.len()
));
Ok(tasks)
}
pub(crate) async fn diff(&self, id: TaskId) -> Result<Option<String>> {
let (details, body, ct) = self
.details_with_body(&id.0)
.await
.map_err(|e| CloudTaskError::Http(format!("get_task_details failed: {e}")))?;
if let Some(diff) = details.unified_diff() {
return Ok(Some(diff));
}
let _ = (body, ct);
Ok(None)
}
pub(crate) async fn messages(&self, id: TaskId) -> Result<Vec<String>> {
let (details, body, ct) = self
.details_with_body(&id.0)
.await
.map_err(|e| CloudTaskError::Http(format!("get_task_details failed: {e}")))?;
let mut msgs = details.assistant_text_messages();
if msgs.is_empty() {
msgs.extend(extract_assistant_messages_from_body(&body));
}
if !msgs.is_empty() {
return Ok(msgs);
}
if let Some(err) = details.assistant_error_message() {
return Ok(vec![format!("Task failed: {err}")]);
}
let url = match details_path(self.base_url, &id.0) {
Some(url) => url,
None => format!("{}/api/codex/tasks/{}", self.base_url, id.0),
};
Err(CloudTaskError::Http(format!(
"No assistant text messages in response. GET {url}; content-type={ct}; body={body}"
)))
}
pub(crate) async fn task_text(&self, id: TaskId) -> Result<TaskText> {
let (details, body, _ct) = self
.details_with_body(&id.0)
.await
.map_err(|e| CloudTaskError::Http(format!("get_task_details failed: {e}")))?;
let prompt = details.user_text_prompt();
let mut messages = details.assistant_text_messages();
if messages.is_empty() {
messages.extend(extract_assistant_messages_from_body(&body));
}
let assistant_turn = details.current_assistant_turn.as_ref();
let turn_id = assistant_turn.and_then(|turn| turn.id.clone());
let sibling_turn_ids = assistant_turn
.map(|turn| turn.sibling_turn_ids.clone())
.unwrap_or_default();
let attempt_placement = assistant_turn.and_then(|turn| turn.attempt_placement);
let attempt_status = attempt_status_from_str(
assistant_turn.and_then(|turn| turn.turn_status.as_deref()),
);
Ok(TaskText {
prompt,
messages,
turn_id,
sibling_turn_ids,
attempt_placement,
attempt_status,
})
}
pub(crate) async fn create(
&self,
env_id: &str,
prompt: &str,
git_ref: &str,
qa_mode: bool,
best_of_n: usize,
) -> Result<crate::CreatedTask> {
let mut input_items: Vec<serde_json::Value> = Vec::new();
input_items.push(serde_json::json!({
"type": "message",
"role": "user",
"content": [{ "content_type": "text", "text": prompt }]
}));
if let Ok(diff) = std::env::var("CODEX_STARTING_DIFF")
&& !diff.is_empty()
{
input_items.push(serde_json::json!({
"type": "pre_apply_patch",
"output_diff": { "diff": diff }
}));
}
let mut request_body = serde_json::json!({
"new_task": {
"environment_id": env_id,
"branch": git_ref,
"run_environment_in_qa_mode": qa_mode,
},
"input_items": input_items,
});
if best_of_n > 1
&& let Some(obj) = request_body.as_object_mut()
{
obj.insert(
"metadata".to_string(),
serde_json::json!({ "best_of_n": best_of_n }),
);
}
match self.backend.create_task(request_body).await {
Ok(id) => {
append_error_log(&format!(
"new_task: created id={id} env={} prompt_chars={}",
env_id,
prompt.chars().count()
));
Ok(crate::CreatedTask { id: TaskId(id) })
}
Err(e) => {
append_error_log(&format!(
"new_task: create failed env={} prompt_chars={}: {}",
env_id,
prompt.chars().count(),
e
));
Err(CloudTaskError::Http(format!("create_task failed: {e}")))
}
}
}
async fn details_with_body(
&self,
id: &str,
) -> anyhow::Result<(backend::CodeTaskDetailsResponse, String, String)> {
let (parsed, body, ct) = self.backend.get_task_details_with_body(id).await?;
Ok((parsed, body, ct))
}
}
pub(crate) struct Attempts<'a> {
backend: &'a backend::Client,
}
impl<'a> Attempts<'a> {
pub(crate) fn new(client: &'a HttpClient) -> Self {
Self {
backend: &client.backend,
}
}
pub(crate) async fn list(&self, task: TaskId, turn_id: String) -> Result<Vec<TurnAttempt>> {
let resp = self
.backend
.list_sibling_turns(&task.0, &turn_id)
.await
.map_err(|e| CloudTaskError::Http(format!("list_sibling_turns failed: {e}")))?;
let mut attempts: Vec<TurnAttempt> = resp
.sibling_turns
.iter()
.filter_map(turn_attempt_from_map)
.collect();
attempts.sort_by(compare_attempts);
Ok(attempts)
}
}
pub(crate) struct Apply<'a> {
backend: &'a backend::Client,
}
impl<'a> Apply<'a> {
pub(crate) fn new(client: &'a HttpClient) -> Self {
Self {
backend: &client.backend,
}
}
pub(crate) async fn run(
&self,
task_id: TaskId,
diff_override: Option<String>,
preflight: bool,
) -> Result<ApplyOutcome> {
let id = task_id.0.clone();
let diff = match diff_override {
Some(diff) => diff,
None => {
let details = self.backend.get_task_details(&id).await.map_err(|e| {
CloudTaskError::Http(format!("get_task_details failed: {e}"))
})?;
details.unified_diff().ok_or_else(|| {
CloudTaskError::Msg(format!("No diff available for task {id}"))
})?
}
};
if !is_unified_diff(&diff) {
let summary = summarize_patch_for_logging(&diff);
let mode = if preflight { "preflight" } else { "apply" };
append_error_log(&format!(
"apply_error: id={id} mode={mode} format=non-unified; {summary}"
));
return Ok(ApplyOutcome {
applied: false,
status: ApplyStatus::Error,
message: "Expected unified git diff; backend returned an incompatible format."
.to_string(),
skipped_paths: Vec::new(),
conflict_paths: Vec::new(),
});
}
let req = codex_git_apply::ApplyGitRequest {
cwd: std::env::current_dir().unwrap_or_else(|_| std::env::temp_dir()),
diff: diff.clone(),
revert: false,
preflight,
};
let r = codex_git_apply::apply_git_patch(&req)
.map_err(|e| CloudTaskError::Io(format!("git apply failed to run: {e}")))?;
let status = if r.exit_code == 0 {
ApplyStatus::Success
} else if !r.applied_paths.is_empty() || !r.conflicted_paths.is_empty() {
ApplyStatus::Partial
} else {
ApplyStatus::Error
};
let applied = matches!(status, ApplyStatus::Success) && !preflight;
let message = if preflight {
match status {
ApplyStatus::Success => {
format!("Preflight passed for task {id} (applies cleanly)")
}
ApplyStatus::Partial => format!(
"Preflight: patch does not fully apply for task {id} (applied={}, skipped={}, conflicts={})",
r.applied_paths.len(),
r.skipped_paths.len(),
r.conflicted_paths.len()
),
ApplyStatus::Error => format!(
"Preflight failed for task {id} (applied={}, skipped={}, conflicts={})",
r.applied_paths.len(),
r.skipped_paths.len(),
r.conflicted_paths.len()
),
}
} else {
match status {
ApplyStatus::Success => format!(
"Applied task {id} locally ({} files)",
r.applied_paths.len()
),
ApplyStatus::Partial => format!(
"Apply partially succeeded for task {id} (applied={}, skipped={}, conflicts={})",
r.applied_paths.len(),
r.skipped_paths.len(),
r.conflicted_paths.len()
),
ApplyStatus::Error => format!(
"Apply failed for task {id} (applied={}, skipped={}, conflicts={})",
r.applied_paths.len(),
r.skipped_paths.len(),
r.conflicted_paths.len()
),
}
};
if matches!(status, ApplyStatus::Partial | ApplyStatus::Error)
|| (preflight && !matches!(status, ApplyStatus::Success))
{
let mut log = String::new();
let summary = summarize_patch_for_logging(&diff);
let mode = if preflight { "preflight" } else { "apply" };
use std::fmt::Write as _;
let _ = writeln!(
&mut log,
"apply_result: mode={} id={} status={:?} applied={} skipped={} conflicts={} cmd={}",
mode,
id,
status,
r.applied_paths.len(),
r.skipped_paths.len(),
r.conflicted_paths.len(),
r.cmd_for_log
);
let _ = writeln!(
&mut log,
"stdout_tail=\n{}\nstderr_tail=\n{}",
tail(&r.stdout, 2000),
tail(&r.stderr, 2000)
);
let _ = writeln!(&mut log, "{summary}");
let _ = writeln!(
&mut log,
"----- PATCH BEGIN -----\n{diff}\n----- PATCH END -----"
);
append_error_log(&log);
}
Ok(ApplyOutcome {
applied,
status,
message,
skipped_paths: r.skipped_paths,
conflict_paths: r.conflicted_paths,
})
}
}
fn details_path(base_url: &str, id: &str) -> Option<String> {
if base_url.contains("/backend-api") {
Some(format!("{base_url}/wham/tasks/{id}"))
} else if base_url.contains("/api/codex") {
Some(format!("{base_url}/tasks/{id}"))
} else {
None
}
}
fn extract_assistant_messages_from_body(body: &str) -> Vec<String> {
let mut msgs = Vec::new();
if let Ok(full) = serde_json::from_str::<serde_json::Value>(body)
&& let Some(arr) = full
.get("current_assistant_turn")
.and_then(|v| v.get("worklog"))
.and_then(|v| v.get("messages"))
.and_then(|v| v.as_array())
{
for m in arr {
let is_assistant = m
.get("author")
.and_then(|a| a.get("role"))
.and_then(|r| r.as_str())
== Some("assistant");
if !is_assistant {
continue;
}
if let Some(parts) = m
.get("content")
.and_then(|c| c.get("parts"))
.and_then(|p| p.as_array())
{
for p in parts {
if let Some(s) = p.as_str() {
if !s.is_empty() {
msgs.push(s.to_string());
}
continue;
}
if let Some(obj) = p.as_object()
&& obj.get("content_type").and_then(|t| t.as_str()) == Some("text")
&& let Some(txt) = obj.get("text").and_then(|t| t.as_str())
{
msgs.push(txt.to_string());
}
}
}
}
}
msgs
}
fn turn_attempt_from_map(turn: &HashMap<String, Value>) -> Option<TurnAttempt> {
let turn_id = turn.get("id").and_then(Value::as_str)?.to_string();
let attempt_placement = turn.get("attempt_placement").and_then(Value::as_i64);
let created_at = parse_timestamp_value(turn.get("created_at"));
let status = attempt_status_from_str(turn.get("turn_status").and_then(Value::as_str));
let diff = extract_diff_from_turn(turn);
let messages = extract_assistant_messages_from_turn(turn);
Some(TurnAttempt {
turn_id,
attempt_placement,
created_at,
status,
diff,
messages,
})
}
fn compare_attempts(a: &TurnAttempt, b: &TurnAttempt) -> Ordering {
match (a.attempt_placement, b.attempt_placement) {
(Some(lhs), Some(rhs)) => lhs.cmp(&rhs),
(Some(_), None) => Ordering::Less,
(None, Some(_)) => Ordering::Greater,
(None, None) => match (a.created_at, b.created_at) {
(Some(lhs), Some(rhs)) => lhs.cmp(&rhs),
(Some(_), None) => Ordering::Less,
(None, Some(_)) => Ordering::Greater,
(None, None) => a.turn_id.cmp(&b.turn_id),
},
}
}
fn extract_diff_from_turn(turn: &HashMap<String, Value>) -> Option<String> {
let items = turn.get("output_items").and_then(Value::as_array)?;
for item in items {
match item.get("type").and_then(Value::as_str) {
Some("output_diff") => {
if let Some(diff) = item.get("diff").and_then(Value::as_str)
&& !diff.is_empty()
{
return Some(diff.to_string());
}
}
Some("pr") => {
if let Some(diff) = item
.get("output_diff")
.and_then(Value::as_object)
.and_then(|od| od.get("diff"))
.and_then(Value::as_str)
&& !diff.is_empty()
{
return Some(diff.to_string());
}
}
_ => {}
}
}
None
}
fn extract_assistant_messages_from_turn(turn: &HashMap<String, Value>) -> Vec<String> {
let mut msgs = Vec::new();
if let Some(items) = turn.get("output_items").and_then(Value::as_array) {
for item in items {
if item.get("type").and_then(Value::as_str) != Some("message") {
continue;
}
if let Some(content) = item.get("content").and_then(Value::as_array) {
for part in content {
if part.get("content_type").and_then(Value::as_str) == Some("text")
&& let Some(txt) = part.get("text").and_then(Value::as_str)
&& !txt.is_empty()
{
msgs.push(txt.to_string());
}
}
}
}
}
msgs
}
fn attempt_status_from_str(raw: Option<&str>) -> AttemptStatus {
match raw.unwrap_or_default() {
"failed" => AttemptStatus::Failed,
"completed" => AttemptStatus::Completed,
"in_progress" => AttemptStatus::InProgress,
"pending" => AttemptStatus::Pending,
_ => AttemptStatus::Pending,
}
}
fn parse_timestamp_value(v: Option<&Value>) -> Option<DateTime<Utc>> {
let ts = v?.as_f64()?;
let secs = ts as i64;
let nanos = ((ts - secs as f64) * 1_000_000_000.0) as u32;
Some(DateTime::<Utc>::from(
std::time::UNIX_EPOCH + std::time::Duration::new(secs.max(0) as u64, nanos),
))
}
fn map_task_list_item_to_summary(src: backend::TaskListItem) -> TaskSummary {
let status_display = src.task_status_display.as_ref();
TaskSummary {
id: TaskId(src.id),
title: src.title,
status: map_status(status_display),
updated_at: parse_updated_at(src.updated_at.as_ref()),
environment_id: None,
environment_label: env_label_from_status_display(status_display),
summary: diff_summary_from_status_display(status_display),
is_review: src
.pull_requests
.as_ref()
.is_some_and(|prs| !prs.is_empty()),
attempt_total: attempt_total_from_status_display(status_display),
}
}
fn map_status(v: Option<&HashMap<String, Value>>) -> TaskStatus {
if let Some(val) = v {
if let Some(turn) = val
.get("latest_turn_status_display")
.and_then(Value::as_object)
&& let Some(s) = turn.get("turn_status").and_then(Value::as_str)
{
return match s {
"failed" => TaskStatus::Error,
"completed" => TaskStatus::Ready,
"in_progress" => TaskStatus::Pending,
"pending" => TaskStatus::Pending,
"cancelled" => TaskStatus::Error,
_ => TaskStatus::Pending,
};
}
if let Some(state) = val.get("state").and_then(Value::as_str) {
return match state {
"pending" => TaskStatus::Pending,
"ready" => TaskStatus::Ready,
"applied" => TaskStatus::Applied,
"error" => TaskStatus::Error,
_ => TaskStatus::Pending,
};
}
}
TaskStatus::Pending
}
fn parse_updated_at(ts: Option<&f64>) -> DateTime<Utc> {
if let Some(v) = ts {
let secs = *v as i64;
let nanos = ((*v - secs as f64) * 1_000_000_000.0) as u32;
return DateTime::<Utc>::from(
std::time::UNIX_EPOCH + std::time::Duration::new(secs.max(0) as u64, nanos),
);
}
Utc::now()
}
fn env_label_from_status_display(v: Option<&HashMap<String, Value>>) -> Option<String> {
let map = v?;
map.get("environment_label")
.and_then(Value::as_str)
.map(str::to_string)
}
fn diff_summary_from_status_display(v: Option<&HashMap<String, Value>>) -> DiffSummary {
let mut out = DiffSummary::default();
let Some(map) = v else { return out };
let latest = map
.get("latest_turn_status_display")
.and_then(Value::as_object);
let Some(latest) = latest else { return out };
if let Some(ds) = latest.get("diff_stats").and_then(Value::as_object) {
if let Some(n) = ds.get("files_modified").and_then(Value::as_i64) {
out.files_changed = n.max(0) as usize;
}
if let Some(n) = ds.get("lines_added").and_then(Value::as_i64) {
out.lines_added = n.max(0) as usize;
}
if let Some(n) = ds.get("lines_removed").and_then(Value::as_i64) {
out.lines_removed = n.max(0) as usize;
}
}
out
}
fn attempt_total_from_status_display(v: Option<&HashMap<String, Value>>) -> Option<usize> {
let map = v?;
let latest = map
.get("latest_turn_status_display")
.and_then(Value::as_object)?;
let siblings = latest.get("sibling_turn_ids").and_then(Value::as_array)?;
Some(siblings.len().saturating_add(1))
}
fn is_unified_diff(diff: &str) -> bool {
let t = diff.trim_start();
if t.starts_with("diff --git ") {
return true;
}
let has_dash_headers = diff.contains("\n--- ") && diff.contains("\n+++ ");
let has_hunk = diff.contains("\n@@ ") || diff.starts_with("@@ ");
has_dash_headers && has_hunk
}
fn tail(s: &str, max: usize) -> String {
if s.len() <= max {
s.to_string()
} else {
s[s.len() - max..].to_string()
}
}
fn summarize_patch_for_logging(patch: &str) -> String {
let trimmed = patch.trim_start();
let kind = if trimmed.starts_with("*** Begin Patch") {
"codex-patch"
} else if trimmed.starts_with("diff --git ") || trimmed.contains("\n*** End Patch\n") {
"git-diff"
} else if trimmed.starts_with("@@ ") || trimmed.contains("\n@@ ") {
"unified-diff"
} else {
"unknown"
};
let lines = patch.lines().count();
let chars = patch.len();
let cwd = std::env::current_dir()
.ok()
.map(|p| p.display().to_string())
.unwrap_or_else(|| "<unknown>".to_string());
let head: String = patch.lines().take(20).collect::<Vec<&str>>().join("\n");
let head_trunc = if head.len() > 800 {
format!("{}", &head[..800])
} else {
head
};
format!(
"patch_summary: kind={kind} lines={lines} chars={chars} cwd={cwd} ; head=\n{head_trunc}"
)
}
}
fn append_error_log(message: &str) {
let ts = Utc::now().to_rfc3339();
if let Ok(mut f) = std::fs::OpenOptions::new()
.create(true)
.append(true)
.open("error.log")
{
use std::io::Write as _;
let _ = writeln!(f, "[{ts}] {message}");
}
}

View File

@@ -0,0 +1,29 @@
mod api;
pub use api::ApplyOutcome;
pub use api::ApplyStatus;
pub use api::AttemptStatus;
pub use api::CloudBackend;
pub use api::CloudTaskError;
pub use api::CreatedTask;
pub use api::DiffSummary;
pub use api::Result;
pub use api::TaskId;
pub use api::TaskStatus;
pub use api::TaskSummary;
pub use api::TaskText;
pub use api::TurnAttempt;
#[cfg(feature = "mock")]
mod mock;
#[cfg(feature = "online")]
mod http;
#[cfg(feature = "mock")]
pub use mock::MockClient;
#[cfg(feature = "online")]
pub use http::HttpClient;
// Reusable apply engine now lives in the shared crate `codex-git-apply`.

View File

@@ -0,0 +1,180 @@
use crate::ApplyOutcome;
use crate::AttemptStatus;
use crate::CloudBackend;
use crate::DiffSummary;
use crate::Result;
use crate::TaskId;
use crate::TaskStatus;
use crate::TaskSummary;
use crate::TurnAttempt;
use crate::api::TaskText;
use chrono::Utc;
#[derive(Clone, Default)]
pub struct MockClient;
#[async_trait::async_trait]
impl CloudBackend for MockClient {
async fn list_tasks(&self, _env: Option<&str>) -> Result<Vec<TaskSummary>> {
// Slightly vary content by env to aid tests that rely on the mock
let rows = match _env {
Some("env-A") => vec![("T-2000", "A: First", TaskStatus::Ready)],
Some("env-B") => vec![
("T-3000", "B: One", TaskStatus::Ready),
("T-3001", "B: Two", TaskStatus::Pending),
],
_ => vec![
("T-1000", "Update README formatting", TaskStatus::Ready),
("T-1001", "Fix clippy warnings in core", TaskStatus::Pending),
("T-1002", "Add contributing guide", TaskStatus::Ready),
],
};
let environment_id = _env.map(str::to_string);
let environment_label = match _env {
Some("env-A") => Some("Env A".to_string()),
Some("env-B") => Some("Env B".to_string()),
Some(other) => Some(other.to_string()),
None => Some("Global".to_string()),
};
let mut out = Vec::new();
for (id_str, title, status) in rows {
let id = TaskId(id_str.to_string());
let diff = mock_diff_for(&id);
let (a, d) = count_from_unified(&diff);
out.push(TaskSummary {
id,
title: title.to_string(),
status,
updated_at: Utc::now(),
environment_id: environment_id.clone(),
environment_label: environment_label.clone(),
summary: DiffSummary {
files_changed: 1,
lines_added: a,
lines_removed: d,
},
is_review: false,
attempt_total: Some(if id_str == "T-1000" { 2 } else { 1 }),
});
}
Ok(out)
}
async fn get_task_diff(&self, id: TaskId) -> Result<Option<String>> {
Ok(Some(mock_diff_for(&id)))
}
async fn get_task_messages(&self, _id: TaskId) -> Result<Vec<String>> {
Ok(vec![
"Mock assistant output: this task contains no diff.".to_string(),
])
}
async fn get_task_text(&self, _id: TaskId) -> Result<TaskText> {
Ok(TaskText {
prompt: Some("Why is there no diff?".to_string()),
messages: vec!["Mock assistant output: this task contains no diff.".to_string()],
turn_id: Some("mock-turn".to_string()),
sibling_turn_ids: Vec::new(),
attempt_placement: Some(0),
attempt_status: AttemptStatus::Completed,
})
}
async fn apply_task(&self, id: TaskId, _diff_override: Option<String>) -> Result<ApplyOutcome> {
Ok(ApplyOutcome {
applied: true,
status: crate::ApplyStatus::Success,
message: format!("Applied task {} locally (mock)", id.0),
skipped_paths: Vec::new(),
conflict_paths: Vec::new(),
})
}
async fn apply_task_preflight(
&self,
id: TaskId,
_diff_override: Option<String>,
) -> Result<ApplyOutcome> {
Ok(ApplyOutcome {
applied: false,
status: crate::ApplyStatus::Success,
message: format!("Preflight passed for task {} (mock)", id.0),
skipped_paths: Vec::new(),
conflict_paths: Vec::new(),
})
}
async fn list_sibling_attempts(
&self,
task: TaskId,
_turn_id: String,
) -> Result<Vec<TurnAttempt>> {
if task.0 == "T-1000" {
return Ok(vec![TurnAttempt {
turn_id: "T-1000-attempt-2".to_string(),
attempt_placement: Some(1),
created_at: Some(Utc::now()),
status: AttemptStatus::Completed,
diff: Some(mock_diff_for(&task)),
messages: vec!["Mock alternate attempt".to_string()],
}]);
}
Ok(Vec::new())
}
async fn create_task(
&self,
env_id: &str,
prompt: &str,
git_ref: &str,
qa_mode: bool,
best_of_n: usize,
) -> Result<crate::CreatedTask> {
let _ = (env_id, prompt, git_ref, qa_mode, best_of_n);
let id = format!("task_local_{}", chrono::Utc::now().timestamp_millis());
Ok(crate::CreatedTask { id: TaskId(id) })
}
}
fn mock_diff_for(id: &TaskId) -> String {
match id.0.as_str() {
"T-1000" => {
"diff --git a/README.md b/README.md\nindex 000000..111111 100644\n--- a/README.md\n+++ b/README.md\n@@ -1,2 +1,3 @@\n Intro\n-Hello\n+Hello, world!\n+Task: T-1000\n".to_string()
}
"T-1001" => {
"diff --git a/core/src/lib.rs b/core/src/lib.rs\nindex 000000..111111 100644\n--- a/core/src/lib.rs\n+++ b/core/src/lib.rs\n@@ -1,2 +1,1 @@\n-use foo;\n use bar;\n".to_string()
}
_ => {
"diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md\nindex 000000..111111 100644\n--- /dev/null\n+++ b/CONTRIBUTING.md\n@@ -0,0 +1,3 @@\n+## Contributing\n+Please open PRs.\n+Thanks!\n".to_string()
}
}
}
fn count_from_unified(diff: &str) -> (usize, usize) {
if let Ok(patch) = diffy::Patch::from_str(diff) {
patch
.hunks()
.iter()
.flat_map(diffy::Hunk::lines)
.fold((0, 0), |(a, d), l| match l {
diffy::Line::Insert(_) => (a + 1, d),
diffy::Line::Delete(_) => (a, d + 1),
_ => (a, d),
})
} else {
let mut a = 0;
let mut d = 0;
for l in diff.lines() {
if l.starts_with("+++") || l.starts_with("---") || l.starts_with("@@") {
continue;
}
match l.as_bytes().first() {
Some(b'+') => a += 1,
Some(b'-') => d += 1,
_ => {}
}
}
(a, d)
}
}

View File

@@ -0,0 +1,36 @@
[package]
name = "codex-cloud-tasks"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_cloud_tasks"
path = "src/lib.rs"
[lints]
workspace = true
[dependencies]
anyhow = "1"
clap = { version = "4", features = ["derive"] }
codex-common = { path = "../common", features = ["cli"] }
tokio = { version = "1", features = ["macros", "rt-multi-thread"] }
tracing = { version = "0.1.41", features = ["log"] }
tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
codex-cloud-tasks-client = { path = "../cloud-tasks-client", features = ["mock", "online"] }
ratatui = { version = "0.29.0" }
crossterm = { version = "0.28.1", features = ["event-stream"] }
tokio-stream = "0.1.17"
chrono = { version = "0.4", features = ["serde"] }
codex-login = { path = "../login" }
codex-core = { path = "../core" }
throbber-widgets-tui = "0.8.0"
base64 = "0.22"
serde_json = "1"
reqwest = { version = "0.12", features = ["json"] }
serde = { version = "1", features = ["derive"] }
unicode-width = "0.1"
codex-tui = { path = "../tui" }
[dev-dependencies]
async-trait = "0.1"

View File

@@ -0,0 +1,482 @@
use std::time::Duration;
// Environment filter data models for the TUI
#[derive(Clone, Debug, Default)]
pub struct EnvironmentRow {
pub id: String,
pub label: Option<String>,
pub is_pinned: bool,
pub repo_hints: Option<String>, // e.g., "openai/codex"
}
#[derive(Clone, Debug, Default)]
pub struct EnvModalState {
pub query: String,
pub selected: usize,
}
#[derive(Clone, Debug, Default)]
pub struct BestOfModalState {
pub selected: usize,
}
#[derive(Clone, Debug, Copy, PartialEq, Eq)]
pub enum ApplyResultLevel {
Success,
Partial,
Error,
}
#[derive(Clone, Debug)]
pub struct ApplyModalState {
pub task_id: TaskId,
pub title: String,
pub result_message: Option<String>,
pub result_level: Option<ApplyResultLevel>,
pub skipped_paths: Vec<String>,
pub conflict_paths: Vec<String>,
pub diff_override: Option<String>,
}
use crate::scrollable_diff::ScrollableDiff;
use codex_cloud_tasks_client::CloudBackend;
use codex_cloud_tasks_client::TaskId;
use codex_cloud_tasks_client::TaskSummary;
use throbber_widgets_tui::ThrobberState;
#[derive(Default)]
pub struct App {
pub tasks: Vec<TaskSummary>,
pub selected: usize,
pub status: String,
pub diff_overlay: Option<DiffOverlay>,
pub throbber: ThrobberState,
pub refresh_inflight: bool,
pub details_inflight: bool,
// Environment filter state
pub env_filter: Option<String>,
pub env_modal: Option<EnvModalState>,
pub apply_modal: Option<ApplyModalState>,
pub best_of_modal: Option<BestOfModalState>,
pub environments: Vec<EnvironmentRow>,
pub env_last_loaded: Option<std::time::Instant>,
pub env_loading: bool,
pub env_error: Option<String>,
// New Task page
pub new_task: Option<crate::new_task::NewTaskPage>,
pub best_of_n: usize,
// Apply preflight spinner state
pub apply_preflight_inflight: bool,
// Apply action spinner state
pub apply_inflight: bool,
// Background enrichment coordination
pub list_generation: u64,
pub in_flight: std::collections::HashSet<String>,
// Background enrichment caches were planned; currently unused.
}
impl App {
pub fn new() -> Self {
Self {
tasks: Vec::new(),
selected: 0,
status: "Press r to refresh".to_string(),
diff_overlay: None,
throbber: ThrobberState::default(),
refresh_inflight: false,
details_inflight: false,
env_filter: None,
env_modal: None,
apply_modal: None,
best_of_modal: None,
environments: Vec::new(),
env_last_loaded: None,
env_loading: false,
env_error: None,
new_task: None,
best_of_n: 1,
apply_preflight_inflight: false,
apply_inflight: false,
list_generation: 0,
in_flight: std::collections::HashSet::new(),
}
}
pub fn next(&mut self) {
if self.tasks.is_empty() {
return;
}
self.selected = (self.selected + 1).min(self.tasks.len().saturating_sub(1));
}
pub fn prev(&mut self) {
if self.tasks.is_empty() {
return;
}
if self.selected > 0 {
self.selected -= 1;
}
}
}
pub async fn load_tasks(
backend: &dyn CloudBackend,
env: Option<&str>,
) -> anyhow::Result<Vec<TaskSummary>> {
// In later milestones, add a small debounce, spinner, and error display.
let tasks = tokio::time::timeout(Duration::from_secs(5), backend.list_tasks(env)).await??;
// Hide review-only tasks from the main list.
let filtered: Vec<TaskSummary> = tasks.into_iter().filter(|t| !t.is_review).collect();
Ok(filtered)
}
pub struct DiffOverlay {
pub title: String,
pub task_id: TaskId,
pub sd: ScrollableDiff,
pub base_can_apply: bool,
pub diff_lines: Vec<String>,
pub text_lines: Vec<String>,
pub prompt: Option<String>,
pub attempts: Vec<AttemptView>,
pub selected_attempt: usize,
pub current_view: DetailView,
pub base_turn_id: Option<String>,
pub sibling_turn_ids: Vec<String>,
pub attempt_total_hint: Option<usize>,
}
#[derive(Clone, Debug, Default)]
pub struct AttemptView {
pub turn_id: Option<String>,
pub status: codex_cloud_tasks_client::AttemptStatus,
pub attempt_placement: Option<i64>,
pub diff_lines: Vec<String>,
pub text_lines: Vec<String>,
pub prompt: Option<String>,
pub diff_raw: Option<String>,
}
impl AttemptView {
pub fn has_diff(&self) -> bool {
!self.diff_lines.is_empty()
}
pub fn has_text(&self) -> bool {
!self.text_lines.is_empty() || self.prompt.is_some()
}
}
impl DiffOverlay {
pub fn new(task_id: TaskId, title: String, attempt_total_hint: Option<usize>) -> Self {
let mut sd = ScrollableDiff::new();
sd.set_content(Vec::new());
Self {
title,
task_id,
sd,
base_can_apply: false,
diff_lines: Vec::new(),
text_lines: Vec::new(),
prompt: None,
attempts: vec![AttemptView::default()],
selected_attempt: 0,
current_view: DetailView::Prompt,
base_turn_id: None,
sibling_turn_ids: Vec::new(),
attempt_total_hint,
}
}
pub fn current_attempt(&self) -> Option<&AttemptView> {
self.attempts.get(self.selected_attempt)
}
pub fn base_attempt_mut(&mut self) -> &mut AttemptView {
if self.attempts.is_empty() {
self.attempts.push(AttemptView::default());
}
&mut self.attempts[0]
}
pub fn set_view(&mut self, view: DetailView) {
self.current_view = view;
self.apply_selection_to_fields();
}
pub fn expected_attempts(&self) -> Option<usize> {
self.attempt_total_hint.or({
if self.attempts.is_empty() {
None
} else {
Some(self.attempts.len())
}
})
}
pub fn attempt_count(&self) -> usize {
self.attempts.len()
}
pub fn attempt_display_total(&self) -> usize {
self.expected_attempts()
.unwrap_or_else(|| self.attempts.len().max(1))
}
pub fn step_attempt(&mut self, delta: isize) -> bool {
let total = self.attempts.len();
if total <= 1 {
return false;
}
let total_isize = total as isize;
let current = self.selected_attempt as isize;
let mut next = current + delta;
next = ((next % total_isize) + total_isize) % total_isize;
let next = next as usize;
self.selected_attempt = next;
self.apply_selection_to_fields();
true
}
pub fn current_can_apply(&self) -> bool {
matches!(self.current_view, DetailView::Diff)
&& self
.current_attempt()
.and_then(|attempt| attempt.diff_raw.as_ref())
.map(|diff| !diff.is_empty())
.unwrap_or(false)
}
pub fn apply_selection_to_fields(&mut self) {
let (diff_lines, text_lines, prompt) = if let Some(attempt) = self.current_attempt() {
(
attempt.diff_lines.clone(),
attempt.text_lines.clone(),
attempt.prompt.clone(),
)
} else {
self.diff_lines.clear();
self.text_lines.clear();
self.prompt = None;
self.sd.set_content(vec!["<loading attempt>".to_string()]);
return;
};
self.diff_lines = diff_lines.clone();
self.text_lines = text_lines.clone();
self.prompt = prompt;
match self.current_view {
DetailView::Diff => {
if diff_lines.is_empty() {
self.sd.set_content(vec!["<no diff available>".to_string()]);
} else {
self.sd.set_content(diff_lines);
}
}
DetailView::Prompt => {
if text_lines.is_empty() {
self.sd.set_content(vec!["<no output>".to_string()]);
} else {
self.sd.set_content(text_lines);
}
}
}
}
}
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum DetailView {
Diff,
Prompt,
}
/// Internal app events delivered from background tasks.
/// These let the UI event loop remain responsive and keep the spinner animating.
#[derive(Debug)]
pub enum AppEvent {
TasksLoaded {
env: Option<String>,
result: anyhow::Result<Vec<TaskSummary>>,
},
// Background diff summary events were planned; removed for now to keep code minimal.
/// Autodetection of a likely environment id finished
EnvironmentAutodetected(anyhow::Result<crate::env_detect::AutodetectSelection>),
/// Background completion of environment list fetch
EnvironmentsLoaded(anyhow::Result<Vec<EnvironmentRow>>),
DetailsDiffLoaded {
id: TaskId,
title: String,
diff: String,
},
DetailsMessagesLoaded {
id: TaskId,
title: String,
messages: Vec<String>,
prompt: Option<String>,
turn_id: Option<String>,
sibling_turn_ids: Vec<String>,
attempt_placement: Option<i64>,
attempt_status: codex_cloud_tasks_client::AttemptStatus,
},
DetailsFailed {
id: TaskId,
title: String,
error: String,
},
AttemptsLoaded {
id: TaskId,
attempts: Vec<codex_cloud_tasks_client::TurnAttempt>,
},
/// Background completion of new task submission
NewTaskSubmitted(Result<codex_cloud_tasks_client::CreatedTask, String>),
/// Background completion of apply preflight when opening modal or on demand
ApplyPreflightFinished {
id: TaskId,
title: String,
message: String,
level: ApplyResultLevel,
skipped: Vec<String>,
conflicts: Vec<String>,
},
/// Background completion of apply action (actual patch application)
ApplyFinished {
id: TaskId,
result: std::result::Result<codex_cloud_tasks_client::ApplyOutcome, String>,
},
}
// Convenience aliases; currently unused.
#[cfg(test)]
mod tests {
use super::*;
use chrono::Utc;
struct FakeBackend {
// maps env key to titles
by_env: std::collections::HashMap<Option<String>, Vec<&'static str>>,
}
#[async_trait::async_trait]
impl codex_cloud_tasks_client::CloudBackend for FakeBackend {
async fn list_tasks(
&self,
env: Option<&str>,
) -> codex_cloud_tasks_client::Result<Vec<TaskSummary>> {
let key = env.map(str::to_string);
let titles = self
.by_env
.get(&key)
.cloned()
.unwrap_or_else(|| vec!["default-a", "default-b"]);
let mut out = Vec::new();
for (i, t) in titles.into_iter().enumerate() {
out.push(TaskSummary {
id: TaskId(format!("T-{i}")),
title: t.to_string(),
status: codex_cloud_tasks_client::TaskStatus::Ready,
updated_at: Utc::now(),
environment_id: env.map(str::to_string),
environment_label: None,
summary: codex_cloud_tasks_client::DiffSummary::default(),
is_review: false,
attempt_total: Some(1),
});
}
Ok(out)
}
async fn get_task_diff(
&self,
_id: TaskId,
) -> codex_cloud_tasks_client::Result<Option<String>> {
Err(codex_cloud_tasks_client::CloudTaskError::Unimplemented(
"not used in test",
))
}
async fn get_task_messages(
&self,
_id: TaskId,
) -> codex_cloud_tasks_client::Result<Vec<String>> {
Ok(vec![])
}
async fn get_task_text(
&self,
_id: TaskId,
) -> codex_cloud_tasks_client::Result<codex_cloud_tasks_client::TaskText> {
Ok(codex_cloud_tasks_client::TaskText {
prompt: Some("Example prompt".to_string()),
messages: Vec::new(),
turn_id: Some("fake-turn".to_string()),
sibling_turn_ids: Vec::new(),
attempt_placement: Some(0),
attempt_status: codex_cloud_tasks_client::AttemptStatus::Completed,
})
}
async fn list_sibling_attempts(
&self,
_task: TaskId,
_turn_id: String,
) -> codex_cloud_tasks_client::Result<Vec<codex_cloud_tasks_client::TurnAttempt>> {
Ok(Vec::new())
}
async fn apply_task(
&self,
_id: TaskId,
_diff_override: Option<String>,
) -> codex_cloud_tasks_client::Result<codex_cloud_tasks_client::ApplyOutcome> {
Err(codex_cloud_tasks_client::CloudTaskError::Unimplemented(
"not used in test",
))
}
async fn apply_task_preflight(
&self,
_id: TaskId,
_diff_override: Option<String>,
) -> codex_cloud_tasks_client::Result<codex_cloud_tasks_client::ApplyOutcome> {
Err(codex_cloud_tasks_client::CloudTaskError::Unimplemented(
"not used in test",
))
}
async fn create_task(
&self,
_env_id: &str,
_prompt: &str,
_git_ref: &str,
_qa_mode: bool,
_best_of_n: usize,
) -> codex_cloud_tasks_client::Result<codex_cloud_tasks_client::CreatedTask> {
Err(codex_cloud_tasks_client::CloudTaskError::Unimplemented(
"not used in test",
))
}
}
#[tokio::test]
async fn load_tasks_uses_env_parameter() {
// Arrange: env-specific task titles
let mut by_env = std::collections::HashMap::new();
by_env.insert(None, vec!["root-1", "root-2"]);
by_env.insert(Some("env-A".to_string()), vec!["A-1"]);
by_env.insert(Some("env-B".to_string()), vec!["B-1", "B-2", "B-3"]);
let backend = FakeBackend { by_env };
// Act + Assert
let root = load_tasks(&backend, None).await.unwrap();
assert_eq!(root.len(), 2);
assert_eq!(root[0].title, "root-1");
let a = load_tasks(&backend, Some("env-A")).await.unwrap();
assert_eq!(a.len(), 1);
assert_eq!(a[0].title, "A-1");
let b = load_tasks(&backend, Some("env-B")).await.unwrap();
assert_eq!(b.len(), 3);
assert_eq!(b[2].title, "B-3");
}
}

View File

@@ -0,0 +1,9 @@
use clap::Parser;
use codex_common::CliConfigOverrides;
#[derive(Parser, Debug, Default)]
#[command(version)]
pub struct Cli {
#[clap(skip)]
pub config_overrides: CliConfigOverrides,
}

View File

@@ -0,0 +1,361 @@
use reqwest::header::CONTENT_TYPE;
use reqwest::header::HeaderMap;
use std::collections::HashMap;
use tracing::info;
use tracing::warn;
#[derive(Debug, Clone, serde::Deserialize)]
struct CodeEnvironment {
id: String,
#[serde(default)]
label: Option<String>,
#[serde(default)]
is_pinned: Option<bool>,
#[serde(default)]
task_count: Option<i64>,
}
#[derive(Debug, Clone)]
pub struct AutodetectSelection {
pub id: String,
pub label: Option<String>,
}
pub async fn autodetect_environment_id(
base_url: &str,
headers: &HeaderMap,
desired_label: Option<String>,
) -> anyhow::Result<AutodetectSelection> {
// 1) Try repo-specific environments based on local git origins (GitHub only, like VSCode)
let origins = get_git_origins();
crate::append_error_log(format!("env: git origins: {origins:?}"));
let mut by_repo_envs: Vec<CodeEnvironment> = Vec::new();
for origin in &origins {
if let Some((owner, repo)) = parse_owner_repo(origin) {
let url = if base_url.contains("/backend-api") {
format!(
"{}/wham/environments/by-repo/{}/{}/{}",
base_url, "github", owner, repo
)
} else {
format!(
"{}/api/codex/environments/by-repo/{}/{}/{}",
base_url, "github", owner, repo
)
};
crate::append_error_log(format!("env: GET {url}"));
match get_json::<Vec<CodeEnvironment>>(&url, headers).await {
Ok(mut list) => {
crate::append_error_log(format!(
"env: by-repo returned {} env(s) for {owner}/{repo}",
list.len(),
));
by_repo_envs.append(&mut list);
}
Err(e) => crate::append_error_log(format!(
"env: by-repo fetch failed for {owner}/{repo}: {e}"
)),
}
}
}
if let Some(env) = pick_environment_row(&by_repo_envs, desired_label.as_deref()) {
return Ok(AutodetectSelection {
id: env.id.clone(),
label: env.label.as_deref().map(str::to_owned),
});
}
// 2) Fallback to the full list
let list_url = if base_url.contains("/backend-api") {
format!("{base_url}/wham/environments")
} else {
format!("{base_url}/api/codex/environments")
};
crate::append_error_log(format!("env: GET {list_url}"));
// Fetch and log the full environments JSON for debugging
let http = reqwest::Client::builder().build()?;
let res = http.get(&list_url).headers(headers.clone()).send().await?;
let status = res.status();
let ct = res
.headers()
.get(CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.unwrap_or("")
.to_string();
let body = res.text().await.unwrap_or_default();
crate::append_error_log(format!("env: status={status} content-type={ct}"));
match serde_json::from_str::<serde_json::Value>(&body) {
Ok(v) => {
let pretty = serde_json::to_string_pretty(&v).unwrap_or(body.clone());
crate::append_error_log(format!("env: /environments JSON (pretty):\n{pretty}"));
}
Err(_) => crate::append_error_log(format!("env: /environments (raw):\n{body}")),
}
if !status.is_success() {
anyhow::bail!("GET {list_url} failed: {status}; content-type={ct}; body={body}");
}
let all_envs: Vec<CodeEnvironment> = serde_json::from_str(&body).map_err(|e| {
anyhow::anyhow!("Decode error for {list_url}: {e}; content-type={ct}; body={body}")
})?;
if let Some(env) = pick_environment_row(&all_envs, desired_label.as_deref()) {
return Ok(AutodetectSelection {
id: env.id.clone(),
label: env.label.as_deref().map(str::to_owned),
});
}
anyhow::bail!("no environments available")
}
fn pick_environment_row(
envs: &[CodeEnvironment],
desired_label: Option<&str>,
) -> Option<CodeEnvironment> {
if envs.is_empty() {
return None;
}
if let Some(label) = desired_label {
let lc = label.to_lowercase();
if let Some(e) = envs
.iter()
.find(|e| e.label.as_deref().unwrap_or("").to_lowercase() == lc)
{
crate::append_error_log(format!("env: matched by label: {label} -> {}", e.id));
return Some(e.clone());
}
}
if envs.len() == 1 {
crate::append_error_log("env: single environment available; selecting it");
return Some(envs[0].clone());
}
if let Some(e) = envs.iter().find(|e| e.is_pinned.unwrap_or(false)) {
crate::append_error_log(format!("env: selecting pinned environment: {}", e.id));
return Some(e.clone());
}
// Highest task_count as heuristic
if let Some(e) = envs
.iter()
.max_by_key(|e| e.task_count.unwrap_or(0))
.or_else(|| envs.first())
{
crate::append_error_log(format!("env: selecting by task_count/first: {}", e.id));
return Some(e.clone());
}
None
}
async fn get_json<T: serde::de::DeserializeOwned>(
url: &str,
headers: &HeaderMap,
) -> anyhow::Result<T> {
let http = reqwest::Client::builder().build()?;
let res = http.get(url).headers(headers.clone()).send().await?;
let status = res.status();
let ct = res
.headers()
.get(CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.unwrap_or("")
.to_string();
let body = res.text().await.unwrap_or_default();
crate::append_error_log(format!("env: status={status} content-type={ct}"));
if !status.is_success() {
anyhow::bail!("GET {url} failed: {status}; content-type={ct}; body={body}");
}
let parsed = serde_json::from_str::<T>(&body).map_err(|e| {
anyhow::anyhow!("Decode error for {url}: {e}; content-type={ct}; body={body}")
})?;
Ok(parsed)
}
fn get_git_origins() -> Vec<String> {
// Prefer: git config --get-regexp remote\..*\.url
let out = std::process::Command::new("git")
.args(["config", "--get-regexp", "remote\\..*\\.url"])
.output();
if let Ok(ok) = out
&& ok.status.success()
{
let s = String::from_utf8_lossy(&ok.stdout);
let mut urls = Vec::new();
for line in s.lines() {
if let Some((_, url)) = line.split_once(' ') {
urls.push(url.trim().to_string());
}
}
if !urls.is_empty() {
return uniq(urls);
}
}
// Fallback: git remote -v
let out = std::process::Command::new("git")
.args(["remote", "-v"])
.output();
if let Ok(ok) = out
&& ok.status.success()
{
let s = String::from_utf8_lossy(&ok.stdout);
let mut urls = Vec::new();
for line in s.lines() {
let parts: Vec<&str> = line.split_whitespace().collect();
if parts.len() >= 2 {
urls.push(parts[1].to_string());
}
}
if !urls.is_empty() {
return uniq(urls);
}
}
Vec::new()
}
fn uniq(mut v: Vec<String>) -> Vec<String> {
v.sort();
v.dedup();
v
}
fn parse_owner_repo(url: &str) -> Option<(String, String)> {
// Normalize common prefixes and handle multiple SSH/HTTPS variants.
let mut s = url.trim().to_string();
// Drop protocol scheme for ssh URLs
if let Some(rest) = s.strip_prefix("ssh://") {
s = rest.to_string();
}
// Accept any user before @github.com (e.g., git@, org-123@)
if let Some(idx) = s.find("@github.com:") {
let rest = &s[idx + "@github.com:".len()..];
let rest = rest.trim_start_matches('/').trim_end_matches(".git");
let mut parts = rest.splitn(2, '/');
let owner = parts.next()?.to_string();
let repo = parts.next()?.to_string();
crate::append_error_log(format!("env: parsed SSH GitHub origin => {owner}/{repo}"));
return Some((owner, repo));
}
// HTTPS or git protocol
for prefix in [
"https://github.com/",
"http://github.com/",
"git://github.com/",
"github.com/",
] {
if let Some(rest) = s.strip_prefix(prefix) {
let rest = rest.trim_start_matches('/').trim_end_matches(".git");
let mut parts = rest.splitn(2, '/');
let owner = parts.next()?.to_string();
let repo = parts.next()?.to_string();
crate::append_error_log(format!("env: parsed HTTP GitHub origin => {owner}/{repo}"));
return Some((owner, repo));
}
}
None
}
/// List environments for the current repo(s) with a fallback to the global list.
/// Returns a de-duplicated, sorted set suitable for the TUI modal.
pub async fn list_environments(
base_url: &str,
headers: &HeaderMap,
) -> anyhow::Result<Vec<crate::app::EnvironmentRow>> {
let mut map: HashMap<String, crate::app::EnvironmentRow> = HashMap::new();
// 1) By-repo lookup for each parsed GitHub origin
let origins = get_git_origins();
for origin in &origins {
if let Some((owner, repo)) = parse_owner_repo(origin) {
let url = if base_url.contains("/backend-api") {
format!(
"{}/wham/environments/by-repo/{}/{}/{}",
base_url, "github", owner, repo
)
} else {
format!(
"{}/api/codex/environments/by-repo/{}/{}/{}",
base_url, "github", owner, repo
)
};
match get_json::<Vec<CodeEnvironment>>(&url, headers).await {
Ok(list) => {
info!("env_tui: by-repo {}:{} -> {} envs", owner, repo, list.len());
for e in list {
let entry =
map.entry(e.id.clone())
.or_insert_with(|| crate::app::EnvironmentRow {
id: e.id.clone(),
label: e.label.clone(),
is_pinned: e.is_pinned.unwrap_or(false),
repo_hints: Some(format!("{owner}/{repo}")),
});
// Merge: keep label if present, or use new; accumulate pinned flag
if entry.label.is_none() {
entry.label = e.label.clone();
}
entry.is_pinned = entry.is_pinned || e.is_pinned.unwrap_or(false);
if entry.repo_hints.is_none() {
entry.repo_hints = Some(format!("{owner}/{repo}"));
}
}
}
Err(e) => {
warn!(
"env_tui: by-repo fetch failed for {}/{}: {}",
owner, repo, e
);
}
}
}
}
// 2) Fallback to the full list; on error return what we have if any.
let list_url = if base_url.contains("/backend-api") {
format!("{base_url}/wham/environments")
} else {
format!("{base_url}/api/codex/environments")
};
match get_json::<Vec<CodeEnvironment>>(&list_url, headers).await {
Ok(list) => {
info!("env_tui: global list -> {} envs", list.len());
for e in list {
let entry = map
.entry(e.id.clone())
.or_insert_with(|| crate::app::EnvironmentRow {
id: e.id.clone(),
label: e.label.clone(),
is_pinned: e.is_pinned.unwrap_or(false),
repo_hints: None,
});
if entry.label.is_none() {
entry.label = e.label.clone();
}
entry.is_pinned = entry.is_pinned || e.is_pinned.unwrap_or(false);
}
}
Err(e) => {
if map.is_empty() {
return Err(e);
} else {
warn!(
"env_tui: global list failed; using by-repo results only: {}",
e
);
}
}
}
let mut rows: Vec<crate::app::EnvironmentRow> = map.into_values().collect();
rows.sort_by(|a, b| {
// pinned first
let p = b.is_pinned.cmp(&a.is_pinned);
if p != std::cmp::Ordering::Equal {
return p;
}
// then label (ci), then id
let al = a.label.as_deref().unwrap_or("").to_lowercase();
let bl = b.label.as_deref().unwrap_or("").to_lowercase();
let l = al.cmp(&bl);
if l != std::cmp::Ordering::Equal {
return l;
}
a.id.cmp(&b.id)
});
Ok(rows)
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,35 @@
use codex_tui::ComposerInput;
pub struct NewTaskPage {
pub composer: ComposerInput,
pub submitting: bool,
pub env_id: Option<String>,
pub best_of_n: usize,
}
impl NewTaskPage {
pub fn new(env_id: Option<String>, best_of_n: usize) -> Self {
let mut composer = ComposerInput::new();
composer.set_hint_items(vec![
("", "send"),
("Shift+⏎", "newline"),
("Ctrl+O", "env"),
("Ctrl+N", "attempts"),
("Ctrl+C", "quit"),
]);
Self {
composer,
submitting: false,
env_id,
best_of_n,
}
}
// Additional helpers can be added as usage evolves.
}
impl Default for NewTaskPage {
fn default() -> Self {
Self::new(None, 1)
}
}

View File

@@ -0,0 +1,176 @@
use unicode_width::UnicodeWidthChar;
use unicode_width::UnicodeWidthStr;
/// Scroll position and geometry for a vertical scroll view.
#[derive(Clone, Copy, Debug, Default)]
pub struct ScrollViewState {
pub scroll: u16,
pub viewport_h: u16,
pub content_h: u16,
}
impl ScrollViewState {
pub fn clamp(&mut self) {
let max_scroll = self.content_h.saturating_sub(self.viewport_h);
if self.scroll > max_scroll {
self.scroll = max_scroll;
}
}
}
/// A simple, local scrollable view for diffs or message text.
///
/// Owns raw lines, caches wrapped lines for a given width, and maintains
/// a small scroll state that is clamped whenever geometry shrinks.
#[derive(Clone, Debug, Default)]
pub struct ScrollableDiff {
raw: Vec<String>,
wrapped: Vec<String>,
wrapped_src_idx: Vec<usize>,
wrap_cols: Option<u16>,
pub state: ScrollViewState,
}
impl ScrollableDiff {
pub fn new() -> Self {
Self::default()
}
/// Replace the raw content lines. Does not rewrap immediately; call `set_width` next.
pub fn set_content(&mut self, lines: Vec<String>) {
self.raw = lines;
self.wrapped.clear();
self.wrapped_src_idx.clear();
self.state.content_h = 0;
// Force rewrap on next set_width even if width is unchanged
self.wrap_cols = None;
}
/// Set the wrap width. If changed, rebuild wrapped lines and clamp scroll.
pub fn set_width(&mut self, width: u16) {
if self.wrap_cols == Some(width) {
return;
}
self.wrap_cols = Some(width);
self.rewrap(width);
self.state.clamp();
}
/// Update viewport height and clamp scroll if needed.
pub fn set_viewport(&mut self, height: u16) {
self.state.viewport_h = height;
self.state.clamp();
}
/// Return the cached wrapped lines. Call `set_width` first when area changes.
pub fn wrapped_lines(&self) -> &[String] {
&self.wrapped
}
pub fn wrapped_src_indices(&self) -> &[usize] {
&self.wrapped_src_idx
}
pub fn raw_line_at(&self, idx: usize) -> &str {
self.raw.get(idx).map(String::as_str).unwrap_or("")
}
/// Scroll by a signed delta; clamps to content.
pub fn scroll_by(&mut self, delta: i16) {
let s = self.state.scroll as i32 + delta as i32;
self.state.scroll = s.clamp(0, self.max_scroll() as i32) as u16;
}
/// Page by a signed delta; typically viewport_h - 1.
pub fn page_by(&mut self, delta: i16) {
self.scroll_by(delta);
}
pub fn to_top(&mut self) {
self.state.scroll = 0;
}
pub fn to_bottom(&mut self) {
self.state.scroll = self.max_scroll();
}
/// Optional percent scrolled; None when not enough geometry is known.
pub fn percent_scrolled(&self) -> Option<u8> {
if self.state.content_h == 0 || self.state.viewport_h == 0 {
return None;
}
if self.state.content_h <= self.state.viewport_h {
return None;
}
let visible_bottom = self.state.scroll.saturating_add(self.state.viewport_h) as f32;
let pct = (visible_bottom / self.state.content_h as f32 * 100.0).round();
Some(pct.clamp(0.0, 100.0) as u8)
}
fn max_scroll(&self) -> u16 {
self.state.content_h.saturating_sub(self.state.viewport_h)
}
fn rewrap(&mut self, width: u16) {
if width == 0 {
self.wrapped = self.raw.clone();
self.state.content_h = self.wrapped.len() as u16;
return;
}
let max_cols = width as usize;
let mut out: Vec<String> = Vec::new();
let mut out_idx: Vec<usize> = Vec::new();
for (raw_idx, raw) in self.raw.iter().enumerate() {
// Normalize tabs for width accounting (MVP: 4 spaces).
let raw = raw.replace('\t', " ");
if raw.is_empty() {
out.push(String::new());
out_idx.push(raw_idx);
continue;
}
let mut line = String::new();
let mut line_cols = 0usize;
let mut last_soft_idx: Option<usize> = None; // last whitespace or punctuation break
for (_i, ch) in raw.char_indices() {
if ch == '\n' {
out.push(std::mem::take(&mut line));
out_idx.push(raw_idx);
line_cols = 0;
last_soft_idx = None;
continue;
}
let w = UnicodeWidthChar::width(ch).unwrap_or(0);
if line_cols.saturating_add(w) > max_cols {
if let Some(split) = last_soft_idx {
let (prefix, rest) = line.split_at(split);
out.push(prefix.trim_end().to_string());
out_idx.push(raw_idx);
line = rest.trim_start().to_string();
last_soft_idx = None;
// retry add current ch now that line may be shorter
} else if !line.is_empty() {
out.push(std::mem::take(&mut line));
out_idx.push(raw_idx);
}
}
if ch.is_whitespace()
|| matches!(
ch,
',' | ';' | '.' | ':' | ')' | ']' | '}' | '|' | '/' | '?' | '!' | '-' | '_'
)
{
last_soft_idx = Some(line.len());
}
line.push(ch);
line_cols = UnicodeWidthStr::width(line.as_str());
}
if !line.is_empty() {
out.push(line);
out_idx.push(raw_idx);
}
}
self.wrapped = out;
self.wrapped_src_idx = out_idx;
self.state.content_h = self.wrapped.len() as u16;
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,93 @@
use base64::Engine as _;
use chrono::Utc;
use reqwest::header::HeaderMap;
pub fn set_user_agent_suffix(suffix: &str) {
if let Ok(mut guard) = codex_core::default_client::USER_AGENT_SUFFIX.lock() {
guard.replace(suffix.to_string());
}
}
pub fn append_error_log(message: impl AsRef<str>) {
let ts = Utc::now().to_rfc3339();
if let Ok(mut f) = std::fs::OpenOptions::new()
.create(true)
.append(true)
.open("error.log")
{
use std::io::Write as _;
let _ = writeln!(f, "[{ts}] {}", message.as_ref());
}
}
/// Normalize the configured base URL to a canonical form used by the backend client.
/// - trims trailing '/'
/// - appends '/backend-api' for ChatGPT hosts when missing
pub fn normalize_base_url(input: &str) -> String {
let mut base_url = input.to_string();
while base_url.ends_with('/') {
base_url.pop();
}
if (base_url.starts_with("https://chatgpt.com")
|| base_url.starts_with("https://chat.openai.com"))
&& !base_url.contains("/backend-api")
{
base_url = format!("{base_url}/backend-api");
}
base_url
}
/// Extract the ChatGPT account id from a JWT token, when present.
pub fn extract_chatgpt_account_id(token: &str) -> Option<String> {
let mut parts = token.split('.');
let (_h, payload_b64, _s) = match (parts.next(), parts.next(), parts.next()) {
(Some(h), Some(p), Some(s)) if !h.is_empty() && !p.is_empty() && !s.is_empty() => (h, p, s),
_ => return None,
};
let payload_bytes = base64::engine::general_purpose::URL_SAFE_NO_PAD
.decode(payload_b64)
.ok()?;
let v: serde_json::Value = serde_json::from_slice(&payload_bytes).ok()?;
v.get("https://api.openai.com/auth")
.and_then(|auth| auth.get("chatgpt_account_id"))
.and_then(|id| id.as_str())
.map(str::to_string)
}
/// Build headers for ChatGPT-backed requests: `User-Agent`, optional `Authorization`,
/// and optional `ChatGPT-Account-Id`.
pub async fn build_chatgpt_headers() -> HeaderMap {
use reqwest::header::AUTHORIZATION;
use reqwest::header::HeaderName;
use reqwest::header::HeaderValue;
use reqwest::header::USER_AGENT;
set_user_agent_suffix("codex_cloud_tasks_tui");
let ua = codex_core::default_client::get_codex_user_agent();
let mut headers = HeaderMap::new();
headers.insert(
USER_AGENT,
HeaderValue::from_str(&ua).unwrap_or(HeaderValue::from_static("codex-cli")),
);
if let Ok(home) = codex_core::config::find_codex_home() {
let am = codex_login::AuthManager::new(home);
if let Some(auth) = am.auth()
&& let Ok(tok) = auth.get_token().await
&& !tok.is_empty()
{
let v = format!("Bearer {tok}");
if let Ok(hv) = HeaderValue::from_str(&v) {
headers.insert(AUTHORIZATION, hv);
}
if let Some(acc) = auth
.get_account_id()
.or_else(|| extract_chatgpt_account_id(&tok))
&& let Ok(name) = HeaderName::from_bytes(b"ChatGPT-Account-Id")
&& let Ok(hv) = HeaderValue::from_str(&acc)
{
headers.insert(name, hv);
}
}
}
headers
}

View File

@@ -0,0 +1,22 @@
use codex_cloud_tasks_client::CloudBackend;
use codex_cloud_tasks_client::MockClient;
#[tokio::test]
async fn mock_backend_varies_by_env() {
let client = MockClient;
let root = CloudBackend::list_tasks(&client, None).await.unwrap();
assert!(root.iter().any(|t| t.title.contains("Update README")));
let a = CloudBackend::list_tasks(&client, Some("env-A"))
.await
.unwrap();
assert_eq!(a.len(), 1);
assert_eq!(a[0].title, "A: First");
let b = CloudBackend::list_tasks(&client, Some("env-B"))
.await
.unwrap();
assert_eq!(b.len(), 2);
assert!(b[0].title.starts_with("B: "));
}

0
codex-rs/code Normal file
View File

View File

@@ -0,0 +1,17 @@
[package]
name = "codex-backend-openapi-models"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_backend_openapi_models"
path = "src/lib.rs"
# Important: generated code often violates our workspace lints.
# Allow unwrap/expect in this crate so the workspace builds cleanly
# after models are regenerated.
# Lint overrides are applied in src/lib.rs via crate attributes
[dependencies]
serde = { version = "1", features = ["derive"] }
serde_json = "1"

View File

@@ -0,0 +1,6 @@
#![allow(clippy::unwrap_used, clippy::expect_used)]
// Re-export generated OpenAPI models.
// The regen script populates `src/models/*.rs` and writes `src/models/mod.rs`.
// This module intentionally contains no hand-written types.
pub mod models;

Some files were not shown because too many files have changed in this diff Show More