This is a major redesign of how sandbox configuration works and aims to
fix https://github.com/openai/codex/issues/1248. Specifically, it
replaces `sandbox_permissions` in `config.toml` (and the
`-s`/`--sandbox-permission` CLI flags) with a "table" with effectively
three variants:
```toml
# Safest option: full disk is read-only, but writes and network access are disallowed.
[sandbox]
mode = "read-only"
# The cwd of the Codex task is writable, as well as $TMPDIR on macOS.
# writable_roots can be used to specify additional writable folders.
[sandbox]
mode = "workspace-write"
writable_roots = [] # Optional, defaults to the empty list.
network_access = false # Optional, defaults to false.
# Disable sandboxing: use at your own risk!!!
[sandbox]
mode = "danger-full-access"
```
This should make sandboxing easier to reason about. While we have
dropped support for `-s`, the way it works now is:
- no flags => `read-only`
- `--full-auto` => `workspace-write`
- currently, there is no way to specify `danger-full-access` via a CLI
flag, but we will revisit that as part of
https://github.com/openai/codex/issues/1254
Outstanding issue:
- As noted in the `TODO` on `SandboxPolicy::is_unrestricted()`, we are
still conflating sandbox preferences with approval preferences in that
case, which needs to be cleaned up.
I noticed that `/clear` wasn't fully clearing chat history; it would
clear the chat history widgets _in the UI_, but the LLM still had access
to information from previous messages.
This PR renames `/clear` to `/new` for clarity as per Michael's
suggestion, resetting `app_state` to a fresh `ChatWidget`.
Users were running into issues with glibc mismatches on arm64 linux. In
the past, we did not provide a musl build for arm64 Linux because we had
trouble getting the openssl dependency to build correctly. Though today
I just tried the same trick in `Cargo.toml` that we were doing for
`x86_64-unknown-linux-musl` (using `openssl-sys` with `features =
["vendored"]`), so I'm not sure what problem we had in the past the
builds "just worked" today!
Though one tweak that did have to be made is that the integration tests
for Seccomp/Landlock empirically require longer timeouts on arm64 linux,
or at least on the `ubuntu-24.04-arm` GitHub Runner. As such, we change
the timeouts for arm64 in `codex-rs/linux-sandbox/tests/landlock.rs`.
Though in solving this problem, I decided I needed a turnkey solution
for testing the Linux build(s) from my Mac laptop, so this PR introduces
`.devcontainer/Dockerfile` and `.devcontainer/devcontainer.json` to
facilitate this. Detailed instructions are in `.devcontainer/README.md`.
We will update `dotslash-config.json` and other release-related scripts
in a follow-up PR.
This does not implement the full Login with ChatGPT experience, but it
should unblock people.
**What works**
* The `codex` multitool now has a `login` subcommand, so you can run
`codex login`, which should write `CODEX_HOME/auth.json` if you complete
the flow successfully. The TUI will now read the `OPENAI_API_KEY` from
`auth.json`.
* The TUI should refresh the token if it has expired and the necessary
information is in `auth.json`.
* There is a `LoginScreen` in the TUI that tells you to run `codex
login` if both (1) your model provider expects to use `OPENAI_API_KEY`
as its env var, and (2) `OPENAI_API_KEY` is not set.
**What does not work**
* The `LoginScreen` does not support the login flow from within the TUI.
Instead, it tells you to quit, run `codex login`, and then run `codex`
again.
* `codex exec` does read from `auth.json` yet, nor does it direct the
user to go through the login flow if `OPENAI_API_KEY` is not be found.
* The `maybeRedeemCredits()` function from `get-api-key.tsx` has not
been ported from TypeScript to `login_with_chatgpt.py` yet:
a67a67f325/codex-cli/src/utils/get-api-key.tsx (L84-L89)
**Implementation**
Currently, the OAuth flow requires running a local webserver on
`127.0.0.1:1455`. It seemed wasteful to incur the additional binary cost
of a webserver dependency in the Rust CLI just to support login, so
instead we implement this logic in Python, as Python has a `http.server`
module as part of its standard library. Specifically, we bundle the
contents of a single Python file as a string in the Rust CLI and then
use it to spawn a subprocess as `python3 -c
{{SOURCE_FOR_PYTHON_SERVER}}`.
As such, the most significant files in this PR are:
```
codex-rs/login/src/login_with_chatgpt.py
codex-rs/login/src/lib.rs
```
Now that the CLI may load `OPENAI_API_KEY` from the environment _or_
`CODEX_HOME/auth.json`, we need a new abstraction for reading/writing
this variable, so we introduce:
```
codex-rs/core/src/openai_api_key.rs
```
Note that `std::env::set_var()` is [rightfully] `unsafe` in Rust 2024,
so we use a LazyLock<RwLock<Option<String>>> to store `OPENAI_API_KEY`
so it is read in a thread-safe manner.
Ultimately, it should be possible to go through the entire login flow
from the TUI. This PR introduces a placeholder `LoginScreen` UI for that
right now, though the new `codex login` subcommand introduced in this PR
should be a viable workaround until the UI is ready.
**Testing**
Because the login flow is currently implemented in a standalone Python
file, you can test it without building any Rust code as follows:
```
rm -rf /tmp/codex_home && mkdir /tmp/codex_home
CODEX_HOME=/tmp/codex_home python3 codex-rs/login/src/login_with_chatgpt.py
```
For reference:
* the original TypeScript implementation was introduced in
https://github.com/openai/codex/pull/963
* support for redeeming credits was later added in
https://github.com/openai/codex/pull/974
This PR overhauls how active tool calls and completed tool calls are
displayed:
1. More use of colour to indicate success/failure and distinguish
between components like tool name+arguments
2. Previously, the entire `CallToolResult` was serialized to JSON and
pretty-printed. Now, we extract each individual `CallToolResultContent`
and print those
1. The previous solution was wasting space by unnecessarily showing
details of the `CallToolResult` struct to users, without formatting the
actual tool call results nicely
2. We're now able to show users more information from tool results in
less space, with nicer formatting when tools return JSON results
### Before:
<img width="1251" alt="Screenshot 2025-06-03 at 11 24 26"
src="https://github.com/user-attachments/assets/5a58f222-219c-4c53-ace7-d887194e30cf"
/>
### After:
<img width="1265" alt="image"
src="https://github.com/user-attachments/assets/99fe54d0-9ebe-406a-855b-7aa529b91274"
/>
## Future Work
1. Integrate image tool result handling better. We should be able to
display images even if they're not the first `CallToolResultContent`
2. Users should have some way to view the full version of truncated tool
results
3. It would be nice to add some left padding for tool results, make it
more clear that they are results. This is doable, just a little fiddly
due to the way `first_visible_line` scrolling works
4. There's almost certainly a better way to format JSON than "all on 1
line with spaces to make Ratatui wrapping work". But I think that works
OK for now.
This fixes a longstanding error in the Rust CLI where `codex.rs`
contained an errant `is_first_turn` check that would exclude the user
instructions for subsequent "turns" of a conversation when using the
responses API (i.e., when `previous_response_id` existed).
While here, renames `Prompt.instructions` to `Prompt.user_instructions`
since we now have quite a few levels of instructions floating around.
Also removed an unnecessary use of `clone()` in
`Prompt.get_full_instructions()`.
As explained in detail in the doc comment for `ParseMode::Lenient`, we
have observed that GPT-4.1 does not always generate a valid invocation
of `apply_patch`. Fortunately, the error is predictable, so we introduce
some new logic to the `codex-apply-patch` crate to recover from this
error.
Because we would like to avoid this becoming a de facto standard (as it
would be incompatible if `apply_patch` were provided as an actual
executable, unless we also introduced the lenient behavior in the
executable, as well), we require passing `ParseMode::Lenient` to
`parse_patch_text()` to make it clear that the caller is opting into
supporting this special case.
Note the analogous change to the TypeScript CLI was
https://github.com/openai/codex/pull/930. In addition to changing the
accepted input to `apply_patch`, it also introduced additional
instructions for the model, which we include in this PR.
Note that `apply-patch` does not depend on either `regex` or
`regex-lite`, so some of the checks are slightly more verbose to avoid
introducing this dependency.
That said, this PR does not leverage the existing
`extract_heredoc_body_from_apply_patch_command()`, which depends on
`tree-sitter` and `tree-sitter-bash`:
5a5aa89914/codex-rs/apply-patch/src/lib.rs (L191-L246)
though perhaps it should.
Previous to this PR, we always set `reasoning` when making a request
using the Responses API:
d7245cbbc9/codex-rs/core/src/client.rs (L108-L111)
Though if you tried to use the Rust CLI with `--model gpt-4.1`, this
would fail with:
```shell
"Unsupported parameter: 'reasoning.effort' is not supported with this model."
```
We take a cue from the TypeScript CLI, which does a check on the model
name:
d7245cbbc9/codex-cli/src/utils/agent/agent-loop.ts (L786-L789)
This PR does a similar check, though also adds support for the following
config options:
```
model_reasoning_effort = "low" | "medium" | "high" | "none"
model_reasoning_summary = "auto" | "concise" | "detailed" | "none"
```
This way, if you have a model whose name happens to start with `"o"` (or
`"codex"`?), you can set these to `"none"` to explicitly disable
reasoning, if necessary. (That said, it seems unlikely anyone would use
the Responses API with non-OpenAI models, but we provide an escape
hatch, anyway.)
This PR also updates both the TUI and `codex exec` to show `reasoning
effort` and `reasoning summaries` in the header.
Prior to this PR, there were two big misses in `chat_completions.rs`:
1. The loop in `stream_chat_completions()` was only including items of
type `ResponseItem::Message` when building up the `"messages"` JSON for
the `POST` request to the `chat/completions` endpoint. This fixes things
by ensuring other variants (`FunctionCall`, `LocalShellCall`, and
`FunctionCallOutput`) are included, as well.
2. In `process_chat_sse()`, we were not recording tool calls and were
only emitting items of type
`ResponseEvent::OutputItemDone(ResponseItem::Message)` to the stream.
Now we introduce `FunctionCallState`, which is used to accumulate the
`delta`s of type `tool_calls`, so we can ultimately emit a
`ResponseItem::FunctionCall`, when appropriate.
While function calling now appears to work for chat completions with my
local testing, I believe that there are still edge cases that are not
covered and that this codepath would benefit from a battery of
integration tests. (As part of that further cleanup, we should also work
to support streaming responses in the UI.)
The other important part of this PR is some cleanup in
`core/src/codex.rs`. In particular, it was hard to reason about how
`run_task()` was building up the list of messages to include in a
request across the various cases:
- Responses API
- Chat Completions API
- Responses API used in concert with ZDR
I like to think things are a bit cleaner now where:
- `zdr_transcript` (if present) contains all messages in the history of
the conversation, which includes function call outputs that have not
been sent back to the model yet
- `pending_input` includes any messages the user has submitted while the
turn is in flight that need to be injected as part of the next `POST` to
the model
- `input_for_next_turn` includes the tool call outputs that have not
been sent back to the model yet
This PR introduces a `hide_agent_reasoning` config option (that defaults
to `false`) that users can enable to make the output less verbose by
suppressing reasoning output.
To test, verified that this includes agent reasoning in the output:
```
echo hello | just exec
```
whereas this does not:
```
echo hello | just exec --config hide_agent_reasoning=false
```
This required changing `ts_println!()` to take `$self:ident`, which is a
bit more verbose, but the usability improvement seems worth it.
Also eliminated an unnecessary `.to_string()` while here.
Fixes:
* Instantiate `EventProcessor` earlier in `lib.rs` so
`print_config_summary()` can be an instance method of it and leverage
its various `Style` fields to ensure it honors `with_ansi` properly.
* After printing the config summary, print out user's prompt with the
heading `User instructions:`. As noted in the comment, now that we can
read the instructions via stdin as of #1178, it is helpful to the user
to ensure they know what instructions were given to Codex.
* Use same colors/bold/italic settings for headers as the TUI, making
the output a bit easier to read.
This attempts to make `codex exec` more flexible in how the prompt can
be passed:
* as before, it can be passed as a single string argument
* if `-` is passed as the value, the prompt is read from stdin
* if no argument is passed _and stdin is a tty_, prints a warning to
stderr that no prompt was specified an exits non-zero.
* if no argument is passed _and stdin is NOT a tty_, prints `Reading
prompt from stdin...` to stderr to let the user know that Codex will
wait until it reads EOF from stdin to proceed. (You can repro this case
by doing `yes | just exec` since stdin is not a TTY in that case but it
also never reaches EOF).
The main motivator behind this PR is that `stream_chat_completions()`
was not adding the `"tools"` entry to the payload posted to the
`/chat/completions` endpoint. This (1) refactors the existing logic to
build up the `"tools"` JSON from `client.rs` into `openai_tools.rs`, and
(2) updates the use of responses API (`client.rs`) and chat completions
API (`chat_completions.rs`) to both use it.
Note this PR alone is not sufficient to get tool calling from chat
completions working: that is done in
https://github.com/openai/codex/pull/1167.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1177).
* #1167
* __->__ #1177
The way these definitions worked before, they did not handle quoted args
with spaces properly.
For example, if you had `/tmp/test-just/printlen.py` as:
```python
#!/usr/bin/env python3
import sys
print(len(sys.argv))
```
and your `justfile` was:
```
printlen *args:
/tmp/test-just/printlen.py {{args}}
```
Then:
```shell
$ just printlen foo bar
3
$ just printlen 'foo bar'
3
```
which is not what we want: `'foo bar'` should be treated as one
argument.
The fix is to use
[positional-arguments](515e806b51/README.md (L1131)):
```
set positional-arguments
printlen *args:
/tmp/test-just/printlen.py "$@"
```
The output of an MCP server tool call can be one of several types, but
to date, we treated all outputs as text by showing the serialized JSON
as the "tool output" in Codex:
25a9949c49/codex-rs/mcp-types/src/lib.rs (L96-L101)
This PR adds support for the `ImageContent` variant so we can now
display an image output from an MCP tool call.
In making this change, we introduce a new
`ResponseInputItem::McpToolCallOutput` variant so that we can work with
the `mcp_types::CallToolResult` directly when the function call is made
to an MCP server.
Though arguably the more significant change is the introduction of
`HistoryCell::CompletedMcpToolCallWithImageOutput`, which is a cell that
uses `ratatui_image` to render an image into the terminal. To support
this, we introduce `ImageRenderCache`, cache a
`ratatui_image::picker::Picker`, and `ensure_image_cache()` to cache the
appropriate scaled image data and dimensions based on the current
terminal size.
To test, I created a minimal `package.json`:
```json
{
"name": "kitty-mcp",
"version": "1.0.0",
"type": "module",
"description": "MCP that returns image of kitty",
"main": "index.js",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.12.0"
}
}
```
with the following `index.js` to define the MCP server:
```js
#!/usr/bin/env node
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { readFile } from "node:fs/promises";
import { join } from "node:path";
const IMAGE_URI = "image://Ada.png";
const server = new McpServer({
name: "Demo",
version: "1.0.0",
});
server.tool(
"get-cat-image",
"If you need a cat image, this tool will provide one.",
async () => ({
content: [
{ type: "image", data: await getAdaPngBase64(), mimeType: "image/png" },
],
})
);
server.resource("Ada the Cat", IMAGE_URI, async (uri) => {
const base64Image = await getAdaPngBase64();
return {
contents: [
{
uri: uri.href,
mimeType: "image/png",
blob: base64Image,
},
],
};
});
async function getAdaPngBase64() {
const __dirname = new URL(".", import.meta.url).pathname;
// From 9705ce2c59/assets/Ada.png
const filePath = join(__dirname, "Ada.png");
const imageData = await readFile(filePath);
const base64Image = imageData.toString("base64");
return base64Image;
}
const transport = new StdioServerTransport();
await server.connect(transport);
```
With the local changes from this PR, I added the following to my
`config.toml`:
```toml
[mcp_servers.kitty]
command = "node"
args = ["/Users/mbolin/code/kitty-mcp/index.js"]
```
Running the TUI from source:
```
cargo run --bin codex -- --model o3 'I need a picture of a cat'
```
I get:
<img width="732" alt="image"
src="https://github.com/user-attachments/assets/bf80b721-9ca0-4d81-aec7-77d6899e2869"
/>
Now, that said, I have only tested in iTerm and there is definitely some
funny business with getting an accurate character-to-pixel ratio
(sometimes the `CompletedMcpToolCallWithImageOutput` thinks it needs 10
rows to render instead of 4), so there is still work to be done here.
The motivation behind this PR is to make it so a `HistoryCell` is more
like a `WidgetRef` that knows how to render itself into a `Rect` so that
it can be backed by something other than a `Vec<Line>`. Because a
`HistoryCell` is intended to appear in a scrollable list, we want to
ensure the stack of cells can be scrolled one `Line` at a time even if
the `HistoryCell` is not backed by a `Vec<Line>` itself.
To this end, we introduce the `CellWidget` trait whose key method is:
```
fn render_window(&self, first_visible_line: usize, area: Rect, buf: &mut Buffer);
```
The `first_visible_line` param is what differs from
`WidgetRef::render_ref()`, as a `CellWidget` needs to know the offset
into its "full view" at which it should start rendering.
The bookkeeping in `ConversationHistoryWidget` has been updated
accordingly to ensure each `CellWidget` in the history is rendered
appropriately.
This PR introduces support for `-c`/`--config` so users can override
individual config values on the command line using `--config
name=value`. Example:
```
codex --config model=o4-mini
```
Making it possible to set arbitrary config values on the command line
results in a more flexible configuration scheme and makes it easier to
provide single-line examples that can be copy-pasted from documentation.
Effectively, it means there are four levels of configuration for some
values:
- Default value (e.g., `model` currently defaults to `o4-mini`)
- Value in `config.toml` (e.g., user could override the default to be
`model = "o3"` in their `config.toml`)
- Specifying `-c` or `--config` to override `model` (e.g., user can
include `-c model=o3` in their list of args to Codex)
- If available, a config-specific flag can be used, which takes
precedence over `-c` (e.g., user can specify `--model o3` in their list
of args to Codex)
Now that it is possible to specify anything that could be configured in
`config.toml` on the command line using `-c`, we do not need to have a
custom flag for every possible config option (which can clutter the
output of `--help`). To that end, as part of this PR, we drop support
for the `--disable-response-storage` flag, as users can now specify `-c
disable_response_storage=true` to get the equivalent functionality.
Under the hood, this works by loading the `config.toml` into a
`toml::Value`. Then for each `key=value`, we create a small synthetic
TOML file with `value` so that we can run the TOML parser to get the
equivalent `toml::Value`. We then parse `key` to determine the point in
the original `toml::Value` to do the insert/replace. Once all of the
overrides from `-c` args have been applied, the `toml::Value` is
deserialized into a `ConfigToml` and then the `ConfigOverrides` are
applied, as before.
I discovered that if I ran `codex <PROMPT>` in a cwd that was not a Git
repo, Codex did not automatically run `<PROMPT>` after I accepted the
Git warning. It appears that we were not managing the `AppState`
transition correctly, so this fixes the bug and ensures the Codex
session does not start until the user accepts the Git warning.
In particular, we now create the `ChatWidget` lazily and store it in the
`AppState::Chat` variant.
Historically, we spawned the Seatbelt and Landlock sandboxes in
substantially different ways:
For **Seatbelt**, we would run `/usr/bin/sandbox-exec` with our policy
specified as an arg followed by the original command:
d1de7bb383/codex-rs/core/src/exec.rs (L147-L219)
For **Landlock/Seccomp**, we would do
`tokio::runtime::Builder::new_current_thread()`, _invoke
Landlock/Seccomp APIs to modify the permissions of that new thread_, and
then spawn the command:
d1de7bb383/codex-rs/core/src/exec_linux.rs (L28-L49)
While it is neat that Landlock/Seccomp supports applying a policy to
only one thread without having to apply it to the entire process, it
requires us to maintain two different codepaths and is a bit harder to
reason about. The tipping point was
https://github.com/openai/codex/pull/1061, in which we had to start
building up the `env` in an unexpected way for the existing
Landlock/Seccomp approach to continue to work.
This PR overhauls things so that we do similar things for Mac and Linux.
It turned out that we were already building our own "helper binary"
comparable to Mac's `sandbox-exec` as part of the `cli` crate:
d1de7bb383/codex-rs/cli/Cargo.toml (L10-L12)
We originally created this to build a small binary to include with the
Node.js version of the Codex CLI to provide support for Linux
sandboxing.
Though the sticky bit is that, at this point, we still want to deploy
the Rust version of Codex as a single, standalone binary rather than a
CLI and a supporting sandboxing binary. To satisfy this goal, we use
"the arg0 trick," in which we:
* use `std::env::current_exe()` to get the path to the CLI that is
currently running
* use the CLI as the `program` for the `Command`
* set `"codex-linux-sandbox"` as arg0 for the `Command`
A CLI that supports sandboxing should check arg0 at the start of the
program. If it is `"codex-linux-sandbox"`, it must invoke
`codex_linux_sandbox::run_main()`, which runs the CLI as if it were
`codex-linux-sandbox`. When acting as `codex-linux-sandbox`, we make the
appropriate Landlock/Seccomp API calls and then use `execvp(3)` to spawn
the original command, so do _replace_ the process rather than spawn a
subprocess. Incidentally, we do this before starting the Tokio runtime,
so the process should only have one thread when `execvp(3)` is called.
Because the `core` crate that needs to spawn the Linux sandboxing is not
a CLI in its own right, this means that every CLI that includes `core`
and relies on this behavior has to (1) implement it and (2) provide the
path to the sandboxing executable. While the path is almost always
`std::env::current_exe()`, we needed to make this configurable for
integration tests, so `Config` now has a `codex_linux_sandbox_exe:
Option<PathBuf>` property to facilitate threading this through,
introduced in https://github.com/openai/codex/pull/1089.
This common pattern is now captured in
`codex_linux_sandbox::run_with_sandbox()` and all of the `main.rs`
functions that should use it have been updated as part of this PR.
The `codex-linux-sandbox` crate added to the Cargo workspace as part of
this PR now has the bulk of the Landlock/Seccomp logic, which makes
`core` a bit simpler. Indeed, `core/src/exec_linux.rs` and
`core/src/landlock.rs` were removed/ported as part of this PR. I also
moved the unit tests for this code into an integration test,
`linux-sandbox/tests/landlock.rs`, in which I use
`env!("CARGO_BIN_EXE_codex-linux-sandbox")` as the value for
`codex_linux_sandbox_exe` since `std::env::current_exe()` is not
appropriate in that case.
https://github.com/openai/codex/pull/1086 is a work-in-progress to make
Linux sandboxing work more like Seatbelt where, for the command we want
to sandbox, we build up the command and then hand it, and some sandbox
configuration flags, to another command to set up the sandbox and then
run it.
In the case of Seatbelt, macOS provides this helper binary and provides
it at `/usr/bin/sandbox-exec`. For Linux, we have to build our own and
pass it through (which is what #1086 does), so this makes the new
`codex_linux_sandbox_exe` available on `Config` so that it will later be
available in `exec.rs` when we need it in #1086.
To date, when handling `shell` and `local_shell` tool calls, we were
spawning new processes using the environment inherited from the Codex
process itself. This means that the sensitive `OPENAI_API_KEY` that
Codex needs to talk to OpenAI models was made available to everything
run by `shell` and `local_shell`. While there are cases where that might
be useful, it does not seem like a good default.
This PR introduces a complex `shell_environment_policy` config option to
control the `env` used with these tool calls. It is inevitably a bit
complex so that it is possible to override individual components of the
policy so without having to restate the entire thing.
Details are in the updated `README.md` in this PR, but here is the
relevant bit that explains the individual fields of
`shell_environment_policy`:
| Field | Type | Default | Description |
| ------------------------- | -------------------------- | ------- |
-----------------------------------------------------------------------------------------------------------------------------------------------
|
| `inherit` | string | `core` | Starting template for the
environment:<br>`core` (`HOME`, `PATH`, `USER`, …), `all` (clone full
parent env), or `none` (start empty). |
| `ignore_default_excludes` | boolean | `false` | When `false`, Codex
removes any var whose **name** contains `KEY`, `SECRET`, or `TOKEN`
(case-insensitive) before other rules run. |
| `exclude` | array<string> | `[]` | Case-insensitive glob
patterns to drop after the default filter.<br>Examples: `"AWS_*"`,
`"AZURE_*"`. |
| `set` | table<string,string> | `{}` | Explicit key/value
overrides or additions – always win over inherited values. |
| `include_only` | array<string> | `[]` | If non-empty, a
whitelist of patterns; only variables that match _one_ pattern survive
the final step. (Generally used with `inherit = "all"`.) |
In particular, note that the default is `inherit = "core"`, so:
* if you have extra env variables that you want to inherit from the
parent process, use `inherit = "all"` and then specify `include_only`
* if you have extra env variables where you want to hardcode the values,
the default `inherit = "core"` will work fine, but then you need to
specify `set`
This configuration is not battle-tested, so we will probably still have
to play with it a bit. `core/src/exec_env.rs` has the critical business
logic as well as unit tests.
Though if nothing else, previous to this change:
```
$ cargo run --bin codex -- debug seatbelt -- printenv OPENAI_API_KEY
# ...prints OPENAI_API_KEY...
```
But after this change it does not print anything (as desired).
One final thing to call out about this PR is that the
`configure_command!` macro we use in `core/src/exec.rs` has to do some
complex logic with respect to how it builds up the `env` for the process
being spawned under Landlock/seccomp. Specifically, doing
`cmd.env_clear()` followed by `cmd.envs(&$env_map)` (which is arguably
the most intuitive way to do it) caused the Landlock unit tests to fail
because the processes spawned by the unit tests started failing in
unexpected ways! If we forgo `env_clear()` in favor of updating env vars
one at a time, the tests still pass. The comment in the code talks about
this a bit, and while I would like to investigate this more, I need to
move on for the moment, but I do plan to come back to it to fully
understand what is going on. For example, this suggests that we might
not be able to spawn a C program that calls `env_clear()`, which would
be...weird. We may still have to fiddle with our Landlock config if that
is the case.
Now the `exec` output starts with something like:
```
--------
workdir: /Users/mbolin/code/codex/codex-rs
model: o3
provider: openai
approval: Never
sandbox: SandboxPolicy { permissions: [DiskFullReadAccess, DiskWritePlatformUserTempFolder, DiskWritePlatformGlobalTempFolder, DiskWriteCwd, DiskWriteFolder { folder: "/Users/mbolin/.pyenv/shims" }] }
--------
```
which makes it easier to reason about when looking at logs.
`config.rs` is already quite long without these definitions. Since they
have no real dependencies of their own, let's move them to their own
file so `config.rs` can focus on the business logic of loading a config.
This introduces an experimental `--output-last-message` flag that can be
used to identify a file where the final message from the agent will be
written. Two use cases:
- Ultimately, we will likely add a `--quiet` option to `exec`, but even
if the user does not want any output written to the terminal, they
probably want to know what the agent did. Writing the output to a file
makes it possible to get that information in a clean way.
- Relatedly, when using `exec` in CI, it is easier to review the
transcript written "normally," (i.e., not as JSON or something with
extra escapes), but getting programmatic access to the last message is
likely helpful, so writing the last message to a file gets the best of
both worlds.
I am calling this "experimental" because it is possible that we are
overfitting and will want a more general solution to this problem that
would justify removing this flag.
Prior to this PR, I would frequently see glyphs from previous frames
"bleed" through like this:
I think this was due to two issues (now addressed in this PR):
* We were not making use of `ratatui::widgets::Clear` to clear out the
buffer before drawing into it.
* To calculate the `width` used with `wrapped_line_count_for_cell()`, we
were not accounting for the scrollbar.
* Now we calculate `effective_width` using
`inner.width.saturating_sub(1)` where the `1` is for the scrollbar.
* We compute `text_area` using `effective_with` and pass the `text_area`
to `paragraph.render()`.
* We eliminate the conditional `needs_scrollbar` check and always call
`render(Scrollbar)`
I suspect this bug was introduced in
https://github.com/openai/codex/pull/937, though I did not try to
verify: I'm just happy that it appears to be fixed!
Previously, if the first user message was sent with the command
invocation, e.g.:
```
$ cargo run --bin codex 'hello'
```
Then the user message was added as the first entry in the history and
then `is_first_event` would be `false` here:
031df77dfb/codex-rs/tui/src/conversation_history_widget.rs (L178-L179)
which would prevent the "welcome" message with things like the the model
version from displaying.
The fix in this PR is twofold:
* Reorganize the logic so the `ChatWidget` constructor stores
`initial_user_message` rather than sending it right away. Now inside
`handle_codex_event()`, it waits for the `SessionConfigured` event and
sends the `initial_user_message`, if it exists.
* In `conversation_history_widget.rs`, `add_session_info()` checks to
see whether a `WelcomeMessage` exists in the history when determining
the value of `has_welcome_message`. By construction, we expect that
`WelcomeMessage` is always the first message (in which case the existing
`let is_first_event = self.entries.is_empty();` logic would be sound),
but we decide to be extra defensive in case an `EventMsg::Error` is
processed before `EventMsg::SessionConfigured`.
I did a bit of research to understand why I could not use my mouse to
drag to select text to copy to the clipboard in iTerm.
Apparently https://github.com/openai/codex/pull/641 to enable mousewheel
scrolling broke this functionality. It seems that, unless we put in a
bit of effort, we can have drag-to-select or scrolling, but not both.
Though if you know the trick to hold down `Option` will dragging with
the mouse in iTerm, you can probably get by with this. (I did not know
about this option prior to researching this issue.)
Nevertheless, users may still prefer to disable mouse capture
altogether, so this PR introduces:
* the ability to set `tui.disable_mouse_capture = true` in `config.toml`
to disable mouse capture
* a new command, `/toggle-mouse-mode` to toggle mouse capture
The new `codex-mini-latest` model expects a new tool with `{"type":
"local_shell"}`. Its contract is similar to the existing `function` tool
with `"name": "shell"`, so this takes the `local_shell` tool call into
`ExecParams` and sends it through the existing
`handle_container_exec_with_params()` code path.
This also adds the following logic when adding the default set of tools
to a request:
```rust
let default_tools = if self.model.starts_with("codex") {
&DEFAULT_CODEX_MODEL_TOOLS
} else {
&DEFAULT_TOOLS
};
```
That is, if the model name starts with `"codex"`, we add `{"type":
"local_shell"}` to the list of tools; otherwise, we add the
aforementioned `shell` tool.
To test this, I ran the TUI with `-m codex-mini-latest` and verified
that it used the `local_shell` tool. Though I also had some entries in
`[mcp_servers]` in my personal `config.toml`. The `codex-mini-latest`
model seemed eager to try the tools from the MCP servers first, so I
have personally commented them out for now, so keep an eye out if you're
testing `codex-mini-latest`!
Perhaps we should include more details with `{"type": "local_shell"}` or
update the following:
fd0b1b0208/codex-rs/core/prompt.md
For reference, the corresponding change in the TypeScript CLI is
https://github.com/openai/codex/pull/951.
If you run a codex instance outside of the current working directory
from where you launched the codex binary it won't be able to apply
patches correctly, even if the sandbox policy allows it. This manifests
weird behaviours, such as
* Reading the same filename in the binary working directory, and
overwriting it in the session working directory. e.g. if you have a
`readme` in both folders it will overwrite the readme in the session
working directory with the readme in the binary working directory
*applied with the suggested patch*.
* The LLM ends up in weird loops trying to verify and debug why the
apply_patch won't work, and it can result in it applying patches by
manually writing python or javascript if it figures out that either is
supported by the system instead.
I added a test-case to ensure that the patch contents are based on the
cwd.
## Issue: mixing relative & absolute paths in apply_patch
1. The apply_patch tool use relative paths based on the session working
directory.
2. `unified_diff_from_chunks` eventually ends up [reading the source
file](https://github.com/reflectionai/codex/blob/main/codex-rs/apply-patch/src/lib.rs#L410)
to figure out what the diff is, by using the relative path.
3. The changes are targeted using an absolute path derived from the
current working directory.
The end-result in case session working directory differs from the binary
working directory: we get the diff for a file relative to the binary
working directory, and apply it on a file in the session working
directory.
