This PR completes the conversion of non-interactive `codex exec` to use
app server rather than directly using core events and methods.
### Summary
- move `codex-exec` off exec-owned `AuthManager` and `ThreadManager`
state
- route exec bootstrap, resume, and auth refresh through existing
app-server paths
- replace legacy `codex/event/*` decoding in exec with typed app-server
notification handling
- update human and JSONL exec output adapters to translate existing
app-server notifications only
- clean up "app server client" layer by eliminating support for legacy
notifications; this is no longer needed
- remove exposure of `authManager` and `threadManager` from "app server
client" layer
### Testing
- `exec` has pretty extensive unit and integration tests already, and
these all pass
- In addition, I asked Codex to put together a comprehensive manual set
of tests to cover all of the `codex exec` functionality (including
command-line options), and it successfully generated and ran these tests
## Why
`codex-rs/core/src/lib.rs` re-exported a broad set of types and modules
from `codex-protocol` and `codex-shell-command`. That made it easy for
workspace crates to import those APIs through `codex-core`, which in
turn hides dependency edges and makes it harder to reduce compile-time
coupling over time.
This change removes those public re-exports so call sites must import
from the source crates directly. Even when a crate still depends on
`codex-core` today, this makes dependency boundaries explicit and
unblocks future work to drop `codex-core` dependencies where possible.
## What Changed
- Removed public re-exports from `codex-rs/core/src/lib.rs` for:
- `codex_protocol::protocol` and related protocol/model types (including
`InitialHistory`)
- `codex_protocol::config_types` (`protocol_config_types`)
- `codex_shell_command::{bash, is_dangerous_command, is_safe_command,
parse_command, powershell}`
- Migrated workspace Rust call sites to import directly from:
- `codex_protocol::protocol`
- `codex_protocol::config_types`
- `codex_protocol::models`
- `codex_shell_command`
- Added explicit `Cargo.toml` dependencies (`codex-protocol` /
`codex-shell-command`) in crates that now import those crates directly.
- Kept `codex-core` internal modules compiling by using `pub(crate)`
aliases in `core/src/lib.rs` (internal-only, not part of the public
API).
- Updated the two utility crates that can already drop a `codex-core`
dependency edge entirely:
- `codex-utils-approval-presets`
- `codex-utils-cli`
## Verification
- `cargo test -p codex-utils-approval-presets`
- `cargo test -p codex-utils-cli`
- `cargo check --workspace --all-targets`
- `just clippy`
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>
Codex created this PR from the following prompt:
> upgrade this entire repo to Rust 1.89. Note that this requires
updating codex-rs/rust-toolchain.toml as well as the workflows in
.github/. Make sure that things are "clippy clean" as this change will
likely uncover new Clippy errors. `just fmt` and `cargo clippy --tests`
are sufficient to check for correctness
Note this modifies a lot of lines because it folds nested `if`
statements using `&&`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2465).
* #2467
* __->__ #2465
- Added a `/status` command, which will be useful when we update the
home screen to print less status.
- Moved `create_config_summary_entries` to common since it's used in a
few places.
- Noticed we inconsistently had periods in slash command descriptions
and just removed them everywhere.
- Noticed the diff description was overflowing so made it shorter.
To date, we have a number of hardcoded OpenAI model slug checks spread
throughout the codebase, which makes it hard to audit the various
special cases for each model. To mitigate this issue, this PR introduces
the idea of a `ModelFamily` that has fields to represent the existing
special cases, such as `supports_reasoning_summaries` and
`uses_local_shell_tool`.
There is a `find_family_for_model()` function that maps the raw model
slug to a `ModelFamily`. This function hardcodes all the knowledge about
the special attributes for each model. This PR then replaces the
hardcoded model name checks with checks against a `ModelFamily`.
Note `ModelFamily` is now available as `Config::model_family`. We should
ultimately remove `Config::model` in favor of
`Config::model_family::slug`.
Previously, `codex exec` was printing `Warning: no file to write last
message to` as a warning to stderr even though `--output-last-message`
was not specified, which is wrong. This fixes the code and changes
`handle_last_message()` so that it is only called when
`last_message_path` is `Some`.
This is designed to facilitate programmatic use of Codex in a more
lightweight way than using `codex mcp`.
Passing `--json` to `codex exec` will print each event as a line of JSON
to stdout. Note that it does not print the individual tokens as they are
streamed, only full messages, as this is aimed at programmatic use
rather than to power UI.
<img width="1348" height="1307" alt="image"
src="https://github.com/user-attachments/assets/fc7908de-b78d-46e4-a6ff-c85de28415c7"
/>
I changed the existing `EventProcessor` into a trait and moved the
implementation to `EventProcessorWithHumanOutput`. Then I introduced an
alternative implementation, `EventProcessorWithJsonOutput`. The `--json`
flag determines which implementation to use.
- Added support for message and reasoning deltas
- Skipped adding the support in the cli and tui for later
- Commented a failing test (wrong merge) that needs fix in a separate
PR.
Side note: I think we need to disable merge when the CI don't pass.
When using the OpenAI Responses API, we now record the `usage` field for
a `"response.completed"` event, which includes metrics about the number
of tokens consumed. We also introduce `openai_model_info.rs`, which
includes current data about the most common OpenAI models available via
the API (specifically `context_window` and `max_output_tokens`). If
Codex does not recognize the model, you can set `model_context_window`
and `model_max_output_tokens` explicitly in `config.toml`.
When then introduce a new event type to `protocol.rs`, `TokenCount`,
which includes the `TokenUsage` for the most recent turn.
Finally, we update the TUI to record the running sum of tokens used so
the percentage of available context window remaining can be reported via
the placeholder text for the composer:
We could certainly get much fancier with this (such as reporting the
estimated cost of the conversation), but for now, we are just trying to
achieve feature parity with the TypeScript CLI.
Though arguably this improves upon the TypeScript CLI, as the TypeScript
CLI uses heuristics to estimate the number of tokens used rather than
using the `usage` information directly:
https://github.com/openai/codex/blob/296996d74e345b1b05d8c3451a06ace21c5ada96/codex-cli/src/utils/approximate-tokens-used.ts#L3-L16
Fixes https://github.com/openai/codex/issues/1242
Previous to this PR, we always set `reasoning` when making a request
using the Responses API:
https://github.com/openai/codex/blob/d7245cbbc9d8ff5446da45e5951761103492476d/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:
https://github.com/openai/codex/blob/d7245cbbc9d8ff5446da45e5951761103492476d/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.
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.
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:
https://github.com/openai/codex/blob/25a9949c49194d5a64de54a11bcc5b4724ac9bd5/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 https://github.com/benjajaja/ratatui-image/blob/9705ce2c59ec669abbce2924cbfd1f5ae22c9860/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.
Now the `exec` output starts with something like:
```
--------
workdir: /Users/mbolin/code/codex/codex-rs
model: o3
provider: openai
approval: Never
sandbox: SandboxPolicy { permissions: [DiskFullReadAccess, DiskWritePlatformUserTempFolder, DiskWritePlatformGlobalTempFolder, DiskWriteCwd, DiskWriteFolder { folder: "/Users/mbolin/.pyenv/shims" }] }
--------
```
which makes it easier to reason about when looking at logs.
This introduces an experimental `--output-last-message` flag that can be
used to identify a file where the final message from the agent will be
written. Two use cases:
- Ultimately, we will likely add a `--quiet` option to `exec`, but even
if the user does not want any output written to the terminal, they
probably want to know what the agent did. Writing the output to a file
makes it possible to get that information in a clean way.
- Relatedly, when using `exec` in CI, it is easier to review the
transcript written "normally," (i.e., not as JSON or something with
extra escapes), but getting programmatic access to the last message is
likely helpful, so writing the last message to a file gets the best of
both worlds.
I am calling this "experimental" because it is possible that we are
overfitting and will want a more general solution to this problem that
would justify removing this flag.
When I originally wrote `elapsed.rs`, I realized we were using both
`std::time` and `chrono` with no real benefit of having both. We should
try to keep the `exec` subcommand trim (as it also buildable as a
standalone executable), so this helps tighten things up.
This is a large change to support a "history" feature like you would
expect in a shell like Bash.
History events are recorded in `$CODEX_HOME/history.jsonl`. Because it
is a JSONL file, it is straightforward to append new entries (as opposed
to the TypeScript file that uses `$CODEX_HOME/history.json`, so to be
valid JSON, each new entry entails rewriting the entire file). Because
it is possible for there to be multiple instances of Codex CLI writing
to `history.jsonl` at once, we use advisory file locking when working
with `history.jsonl` in `codex-rs/core/src/message_history.rs`.
Because we believe history is a sufficiently useful feature, we enable
it by default. Though to provide some safety, we set the file
permissions of `history.jsonl` to be `o600` so that other users on the
system cannot read the user's history. We do not yet support a default
list of `SENSITIVE_PATTERNS` as the TypeScript CLI does:
https://github.com/openai/codex/blob/3fdf9df1335ac9501e3fb0e61715359145711e8b/codex-cli/src/utils/storage/command-history.ts#L10-L17
We are going to take a more conservative approach to this list in the
Rust CLI. For example, while `/\b[A-Za-z0-9-_]{20,}\b/` might exclude
sensitive information like API tokens, it would also exclude valuable
information such as references to Git commits.
As noted in the updated documentation, users can opt-out of history by
adding the following to `config.toml`:
```toml
[history]
persistence = "none"
```
Because `history.jsonl` could, in theory, be quite large, we take a[n
arguably overly pedantic] approach in reading history entries into
memory. Specifically, we start by telling the client the current number
of entries in the history file (`history_entry_count`) as well as the
inode (`history_log_id`) of `history.jsonl` (see the new fields on
`SessionConfiguredEvent`).
The client is responsible for keeping new entries in memory to create a
"local history," but if the user hits up enough times to go "past" the
end of local history, then the client should use the new
`GetHistoryEntryRequest` in the protocol to fetch older entries.
Specifically, it should pass the `history_log_id` it was given
originally and work backwards from `history_entry_count`. (It should
really fetch history in batches rather than one-at-a-time, but that is
something we can improve upon in subsequent PRs.)
The motivation behind this crazy scheme is that it is designed to defend
against:
* The `history.jsonl` being truncated during the session such that the
index into the history is no longer consistent with what had been read
up to that point. We do not yet have logic to enforce a `max_bytes` for
`history.jsonl`, but once we do, we will aspire to implement it in a way
that should result in a new inode for the file on most systems.
* New items from concurrent Codex CLI sessions amending to the history.
Because, in absence of truncation, `history.jsonl` is an append-only
log, so long as the client reads backwards from `history_entry_count`,
it should always get a consistent view of history. (That said, it will
not be able to read _new_ commands from concurrent sessions, but perhaps
we will introduce a `/` command to reload latest history or something
down the road.)
Admittedly, my testing of this feature thus far has been fairly light. I
expect we will find bugs and introduce enhancements/fixes going forward.
For now, this removes the `#[non_exhaustive]` directive on `EventMsg` so
that we are forced to handle all `EventMsg` by default. (We may revisit
this if/when we publish `core/` as a `lib` crate.) For now, it is
helpful to have this as a forcing function because we have effectively
two UIs (`tui` and `exec`) and usually when we add a new variant to
`EventMsg`, we want to be sure that we update both.
https://github.com/openai/codex/pull/922 did this for the
`SessionConfigured` enum variant, and I think it is generally helpful to
be able to work with the values as each enum variant as their own type,
so this converts the remaining variants and updates all of the
callsites.
Added a simple unit test to verify that the JSON-serialized version of
`Event` does not have any unexpected nesting.
I started this PR because I wanted to share the `format_duration()`
utility function in `codex-rs/exec/src/event_processor.rs` with the TUI.
The question was: where to put it?
`core` should have as few dependencies as possible, so moving it there
would introduce a dependency on `chrono`, which seemed undesirable.
`core` already had this `cli` feature to deal with a similar situation
around sharing common utility functions, so I decided to:
* make `core` feature-free
* introduce `common`
* `common` can have as many "special interest" features as it needs,
each of which can declare their own deps
* the first two features of common are `cli` and `elapsed`
In practice, this meant updating a number of `Cargo.toml` files,
replacing this line:
```toml
codex-core = { path = "../core", features = ["cli"] }
```
with these:
```toml
codex-core = { path = "../core" }
codex-common = { path = "../common", features = ["cli"] }
```
Moving `format_duration()` into its own file gave it some "breathing
room" to add a unit test, so I had Codex generate some tests and new
support for durations over 1 minute.
In order to expose Codex via an MCP server, I realized that we should be
taking `cwd` as a parameter rather than assuming
`std::env::current_dir()` as the `cwd`. Specifically, the user may want
to start a session in a directory other than the one where the MCP
server has been started.
This PR makes `cwd: PathBuf` a required field of `Session` and threads
it all the way through, though I think there is still an issue with not
honoring `workdir` for `apply_patch`, which is something we also had to
fix in the TypeScript version: https://github.com/openai/codex/pull/556.
This also adds `-C`/`--cd` to change the cwd via the command line.
To test, I ran:
```
cargo run --bin codex -- exec -C /tmp 'show the output of ls'
```
and verified it showed the contents of my `/tmp` folder instead of
`$PWD`.
Eric Traut ·
Michael Bolin ·
pakrym-oai ·
ae ·
Pavel Bezglasny ·
aibrahim-oai ·
Rene Leonhardt ·
