Compare commits

..

1 Commits

Author SHA1 Message Date
Michael Bolin
7c94e4cab9 feat: exec-command-mcp 2025-08-20 13:59:42 -07:00
911 changed files with 19723 additions and 66012 deletions

View File

@@ -1,50 +0,0 @@
name: 🧑‍💻 VS Code Extension
description: Report an issue with the VS Code extension
labels:
- extension
- needs triage
body:
- type: markdown
attributes:
value: |
Before submitting a new issue, please search for existing issues to see if your issue has already been reported.
If it has, please add a 👍 reaction (no need to leave a comment) to the existing issue instead of creating a new one.
- type: input
id: version
attributes:
label: What version of the VS Code extension are you using?
- type: input
id: ide
attributes:
label: Which IDE are you using?
description: Like `VS Code`, `Cursor`, `Windsurf`, etc.
- type: input
id: platform
attributes:
label: What platform is your computer?
description: |
For MacOS and Linux: copy the output of `uname -mprs`
For Windows: copy the output of `"$([Environment]::OSVersion | ForEach-Object VersionString) $(if ([Environment]::Is64BitOperatingSystem) { "x64" } else { "x86" })"` in the PowerShell console
- type: textarea
id: steps
attributes:
label: What steps can reproduce the bug?
description: Explain the bug and provide a code snippet that can reproduce it.
validations:
required: true
- type: textarea
id: expected
attributes:
label: What is the expected behavior?
description: If possible, please provide text instead of a screenshot.
- type: textarea
id: actual
attributes:
label: What do you see instead?
description: If possible, please provide text instead of a screenshot.
- type: textarea
id: notes
attributes:
label: Additional information
description: Is there anything else you think we should know?

1
.github/actions/codex/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
/node_modules/

View File

@@ -0,0 +1,8 @@
printWidth = 80
quoteProps = "consistent"
semi = true
tabWidth = 2
trailingComma = "all"
# Preserve existing behavior for markdown/text wrapping.
proseWrap = "preserve"

140
.github/actions/codex/README.md vendored Normal file
View File

@@ -0,0 +1,140 @@
# openai/codex-action
`openai/codex-action` is a GitHub Action that facilitates the use of [Codex](https://github.com/openai/codex) on GitHub issues and pull requests. Using the action, associate **labels** to run Codex with the appropriate prompt for the given context. Codex will respond by posting comments or creating PRs, whichever you specify!
Here is a sample workflow that uses `openai/codex-action`:
```yaml
name: Codex
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
jobs:
codex:
if: ... # optional, but can be effective in conserving CI resources
runs-on: ubuntu-latest
# TODO(mbolin): Need to verify if/when `write` is necessary.
permissions:
contents: write
issues: write
pull-requests: write
steps:
# By default, Codex runs network disabled using --full-auto, so perform
# any setup that requires network (such as installing dependencies)
# before openai/codex-action.
- name: Checkout repository
uses: actions/checkout@v4
- name: Run Codex
uses: openai/codex-action@latest
with:
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
github_token: ${{ secrets.GITHUB_TOKEN }}
```
See sample usage in [`codex.yml`](../../workflows/codex.yml).
## Triggering the Action
Using the sample workflow above, we have:
```yaml
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
```
which means our workflow will be triggered when any of the following events occur:
- a label is added to an issue
- a label is added to a pull request against the `main` branch
### Label-Based Triggers
To define a GitHub label that should trigger Codex, create a file named `.github/codex/labels/LABEL-NAME.md` in your repository where `LABEL-NAME` is the name of the label. The content of the file is the prompt template to use when the label is added (see more on [Prompt Template Variables](#prompt-template-variables) below).
For example, if the file `.github/codex/labels/codex-review.md` exists, then:
- Adding the `codex-review` label will trigger the workflow containing the `openai/codex-action` GitHub Action.
- When `openai/codex-action` starts, it will replace the `codex-review` label with `codex-review-in-progress`.
- When `openai/codex-action` is finished, it will replace the `codex-review-in-progress` label with `codex-review-completed`.
If Codex sees that either `codex-review-in-progress` or `codex-review-completed` is already present, it will not perform the action.
As determined by the [default config](./src/default-label-config.ts), Codex will act on the following labels by default:
- Adding the `codex-review` label to a pull request will have Codex review the PR and add it to the PR as a comment.
- Adding the `codex-triage` label to an issue will have Codex investigate the issue and report its findings as a comment.
- Adding the `codex-issue-fix` label to an issue will have Codex attempt to fix the issue and create a PR wit the fix, if any.
## Action Inputs
The `openai/codex-action` GitHub Action takes the following inputs
### `openai_api_key` (required)
Set your `OPENAI_API_KEY` as a [repository secret](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions). See **Secrets and varaibles** then **Actions** in the settings for your GitHub repo.
Note that the secret name does not have to be `OPENAI_API_KEY`. For example, you might want to name it `CODEX_OPENAI_API_KEY` and then configure it on `openai/codex-action` as follows:
```yaml
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
```
### `github_token` (required)
This is required so that Codex can post a comment or create a PR. Set this value on the action as follows:
```yaml
github_token: ${{ secrets.GITHUB_TOKEN }}
```
### `codex_args`
A whitespace-delimited list of arguments to pass to Codex. Defaults to `--full-auto`, but if you want to override the default model to use `o3`:
```yaml
codex_args: "--full-auto --model o3"
```
For more complex configurations, use the `codex_home` input.
### `codex_home`
If set, the value to use for the `$CODEX_HOME` environment variable when running Codex. As explained [in the docs](https://github.com/openai/codex/tree/main/codex-rs#readme), this folder can contain the `config.toml` to configure Codex, custom instructions, and log files.
This should be a relative path within your repo.
## Prompt Template Variables
As shown above, `"prompt"` and `"promptPath"` are used to define prompt templates that will be populated and passed to Codex in response to certain events. All template variables are of the form `{CODEX_ACTION_...}` and the supported values are defined below.
### `CODEX_ACTION_ISSUE_TITLE`
If the action was triggered on a GitHub issue, this is the issue title.
Specifically it is read as the `.issue.title` from the `$GITHUB_EVENT_PATH`.
### `CODEX_ACTION_ISSUE_BODY`
If the action was triggered on a GitHub issue, this is the issue body.
Specifically it is read as the `.issue.body` from the `$GITHUB_EVENT_PATH`.
### `CODEX_ACTION_GITHUB_EVENT_PATH`
The value of the `$GITHUB_EVENT_PATH` environment variable, which is the path to the file that contains the JSON payload for the event that triggered the workflow. Codex can use `jq` to read only the fields of interest from this file.
### `CODEX_ACTION_PR_DIFF`
If the action was triggered on a pull request, this is the diff between the base and head commits of the PR. It is the output from `git diff`.
Note that the content of the diff could be quite large, so is generally safer to point Codex at `CODEX_ACTION_GITHUB_EVENT_PATH` and let it decide how it wants to explore the change.

125
.github/actions/codex/action.yml vendored Normal file
View File

@@ -0,0 +1,125 @@
name: "Codex [reusable action]"
description: "A reusable action that runs a Codex model."
inputs:
openai_api_key:
description: "The value to use as the OPENAI_API_KEY environment variable when running Codex."
required: true
trigger_phrase:
description: "Text to trigger Codex from a PR/issue body or comment."
required: false
default: ""
github_token:
description: "Token so Codex can comment on the PR or issue."
required: true
codex_args:
description: "A whitespace-delimited list of arguments to pass to Codex. Due to limitations in YAML, arguments with spaces are not supported. For more complex configurations, use the `codex_home` input."
required: false
default: "--config hide_agent_reasoning=true --full-auto"
codex_home:
description: "Value to use as the CODEX_HOME environment variable when running Codex."
required: false
codex_release_tag:
description: "The release tag of the Codex model to run, e.g., 'rust-v0.3.0'. Defaults to the latest release."
required: false
default: ""
runs:
using: "composite"
steps:
# Do this in Bash so we do not even bother to install Bun if the sender does
# not have write access to the repo.
- name: Verify user has write access to the repo.
env:
GH_TOKEN: ${{ github.token }}
shell: bash
run: |
set -euo pipefail
PERMISSION=$(gh api \
"/repos/${GITHUB_REPOSITORY}/collaborators/${{ github.event.sender.login }}/permission" \
| jq -r '.permission')
if [[ "$PERMISSION" != "admin" && "$PERMISSION" != "write" ]]; then
exit 1
fi
- name: Download Codex
env:
GH_TOKEN: ${{ github.token }}
shell: bash
run: |
set -euo pipefail
# Determine OS/arch and corresponding Codex artifact name.
uname_s=$(uname -s)
uname_m=$(uname -m)
case "$uname_s" in
Linux*) os="linux" ;;
Darwin*) os="apple-darwin" ;;
*) echo "Unsupported operating system: $uname_s"; exit 1 ;;
esac
case "$uname_m" in
x86_64*) arch="x86_64" ;;
arm64*|aarch64*) arch="aarch64" ;;
*) echo "Unsupported architecture: $uname_m"; exit 1 ;;
esac
# linux builds differentiate between musl and gnu.
if [[ "$os" == "linux" ]]; then
if [[ "$arch" == "x86_64" ]]; then
triple="${arch}-unknown-linux-musl"
else
# Only other supported linux build is aarch64 gnu.
triple="${arch}-unknown-linux-gnu"
fi
else
# macOS
triple="${arch}-apple-darwin"
fi
# Note that if we start baking version numbers into the artifact name,
# we will need to update this action.yml file to match.
artifact="codex-${triple}.tar.gz"
TAG_ARG="${{ inputs.codex_release_tag }}"
# The usage is `gh release download [<tag>] [flags]`, so if TAG_ARG
# is empty, we do not pass it so we can default to the latest release.
gh release download ${TAG_ARG:+$TAG_ARG} --repo openai/codex \
--pattern "$artifact" --output - \
| tar xzO > /usr/local/bin/codex
chmod +x /usr/local/bin/codex
# Display Codex version to confirm binary integrity.
codex --version
- name: Install Bun
uses: oven-sh/setup-bun@v2
with:
bun-version: 1.2.11
- name: Install dependencies
shell: bash
run: |
cd ${{ github.action_path }}
bun install --production
- name: Run Codex
shell: bash
run: bun run ${{ github.action_path }}/src/main.ts
# Process args plus environment variables often have a max of 128 KiB,
# so we should fit within that limit?
env:
INPUT_CODEX_ARGS: ${{ inputs.codex_args || '' }}
INPUT_CODEX_HOME: ${{ inputs.codex_home || ''}}
INPUT_TRIGGER_PHRASE: ${{ inputs.trigger_phrase || '' }}
OPENAI_API_KEY: ${{ inputs.openai_api_key }}
GITHUB_TOKEN: ${{ inputs.github_token }}
GITHUB_EVENT_ACTION: ${{ github.event.action || '' }}
GITHUB_EVENT_LABEL_NAME: ${{ github.event.label.name || '' }}
GITHUB_EVENT_ISSUE_NUMBER: ${{ github.event.issue.number || '' }}
GITHUB_EVENT_ISSUE_BODY: ${{ github.event.issue.body || '' }}
GITHUB_EVENT_REVIEW_BODY: ${{ github.event.review.body || '' }}
GITHUB_EVENT_COMMENT_BODY: ${{ github.event.comment.body || '' }}

91
.github/actions/codex/bun.lock vendored Normal file
View File

@@ -0,0 +1,91 @@
{
"lockfileVersion": 1,
"workspaces": {
"": {
"name": "codex-action",
"dependencies": {
"@actions/core": "^1.11.1",
"@actions/github": "^6.0.1",
},
"devDependencies": {
"@types/bun": "^1.2.20",
"@types/node": "^24.3.0",
"prettier": "^3.6.2",
"typescript": "^5.9.2",
},
},
},
"packages": {
"@actions/core": ["@actions/core@1.11.1", "", { "dependencies": { "@actions/exec": "^1.1.1", "@actions/http-client": "^2.0.1" } }, "sha512-hXJCSrkwfA46Vd9Z3q4cpEpHB1rL5NG04+/rbqW9d3+CSvtB1tYe8UTpAlixa1vj0m/ULglfEK2UKxMGxCxv5A=="],
"@actions/exec": ["@actions/exec@1.1.1", "", { "dependencies": { "@actions/io": "^1.0.1" } }, "sha512-+sCcHHbVdk93a0XT19ECtO/gIXoxvdsgQLzb2fE2/5sIZmWQuluYyjPQtrtTHdU1YzTZ7bAPN4sITq2xi1679w=="],
"@actions/github": ["@actions/github@6.0.1", "", { "dependencies": { "@actions/http-client": "^2.2.0", "@octokit/core": "^5.0.1", "@octokit/plugin-paginate-rest": "^9.2.2", "@octokit/plugin-rest-endpoint-methods": "^10.4.0", "@octokit/request": "^8.4.1", "@octokit/request-error": "^5.1.1", "undici": "^5.28.5" } }, "sha512-xbZVcaqD4XnQAe35qSQqskb3SqIAfRyLBrHMd/8TuL7hJSz2QtbDwnNM8zWx4zO5l2fnGtseNE3MbEvD7BxVMw=="],
"@actions/http-client": ["@actions/http-client@2.2.3", "", { "dependencies": { "tunnel": "^0.0.6", "undici": "^5.25.4" } }, "sha512-mx8hyJi/hjFvbPokCg4uRd4ZX78t+YyRPtnKWwIl+RzNaVuFpQHfmlGVfsKEJN8LwTCvL+DfVgAM04XaHkm6bA=="],
"@actions/io": ["@actions/io@1.1.3", "", {}, "sha512-wi9JjgKLYS7U/z8PPbco+PvTb/nRWjeoFlJ1Qer83k/3C5PHQi28hiVdeE2kHXmIL99mQFawx8qt/JPjZilJ8Q=="],
"@fastify/busboy": ["@fastify/busboy@2.1.1", "", {}, "sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA=="],
"@octokit/auth-token": ["@octokit/auth-token@4.0.0", "", {}, "sha512-tY/msAuJo6ARbK6SPIxZrPBms3xPbfwBrulZe0Wtr/DIY9lje2HeV1uoebShn6mx7SjCHif6EjMvoREj+gZ+SA=="],
"@octokit/core": ["@octokit/core@5.2.1", "", { "dependencies": { "@octokit/auth-token": "^4.0.0", "@octokit/graphql": "^7.1.0", "@octokit/request": "^8.4.1", "@octokit/request-error": "^5.1.1", "@octokit/types": "^13.0.0", "before-after-hook": "^2.2.0", "universal-user-agent": "^6.0.0" } }, "sha512-dKYCMuPO1bmrpuogcjQ8z7ICCH3FP6WmxpwC03yjzGfZhj9fTJg6+bS1+UAplekbN2C+M61UNllGOOoAfGCrdQ=="],
"@octokit/endpoint": ["@octokit/endpoint@9.0.6", "", { "dependencies": { "@octokit/types": "^13.1.0", "universal-user-agent": "^6.0.0" } }, "sha512-H1fNTMA57HbkFESSt3Y9+FBICv+0jFceJFPWDePYlR/iMGrwM5ph+Dd4XRQs+8X+PUFURLQgX9ChPfhJ/1uNQw=="],
"@octokit/graphql": ["@octokit/graphql@7.1.1", "", { "dependencies": { "@octokit/request": "^8.4.1", "@octokit/types": "^13.0.0", "universal-user-agent": "^6.0.0" } }, "sha512-3mkDltSfcDUoa176nlGoA32RGjeWjl3K7F/BwHwRMJUW/IteSa4bnSV8p2ThNkcIcZU2umkZWxwETSSCJf2Q7g=="],
"@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
"@octokit/plugin-paginate-rest": ["@octokit/plugin-paginate-rest@9.2.2", "", { "dependencies": { "@octokit/types": "^12.6.0" }, "peerDependencies": { "@octokit/core": "5" } }, "sha512-u3KYkGF7GcZnSD/3UP0S7K5XUFT2FkOQdcfXZGZQPGv3lm4F2Xbf71lvjldr8c1H3nNbF+33cLEkWYbokGWqiQ=="],
"@octokit/plugin-rest-endpoint-methods": ["@octokit/plugin-rest-endpoint-methods@10.4.1", "", { "dependencies": { "@octokit/types": "^12.6.0" }, "peerDependencies": { "@octokit/core": "5" } }, "sha512-xV1b+ceKV9KytQe3zCVqjg+8GTGfDYwaT1ATU5isiUyVtlVAO3HNdzpS4sr4GBx4hxQ46s7ITtZrAsxG22+rVg=="],
"@octokit/request": ["@octokit/request@8.4.1", "", { "dependencies": { "@octokit/endpoint": "^9.0.6", "@octokit/request-error": "^5.1.1", "@octokit/types": "^13.1.0", "universal-user-agent": "^6.0.0" } }, "sha512-qnB2+SY3hkCmBxZsR/MPCybNmbJe4KAlfWErXq+rBKkQJlbjdJeS85VI9r8UqeLYLvnAenU8Q1okM/0MBsAGXw=="],
"@octokit/request-error": ["@octokit/request-error@5.1.1", "", { "dependencies": { "@octokit/types": "^13.1.0", "deprecation": "^2.0.0", "once": "^1.4.0" } }, "sha512-v9iyEQJH6ZntoENr9/yXxjuezh4My67CBSu9r6Ve/05Iu5gNgnisNWOsoJHTP6k0Rr0+HQIpnH+kyammu90q/g=="],
"@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
"@types/bun": ["@types/bun@1.2.20", "", { "dependencies": { "bun-types": "1.2.20" } }, "sha512-dX3RGzQ8+KgmMw7CsW4xT5ITBSCrSbfHc36SNT31EOUg/LA9JWq0VDdEXDRSe1InVWpd2yLUM1FUF/kEOyTzYA=="],
"@types/node": ["@types/node@24.3.0", "", { "dependencies": { "undici-types": "~7.10.0" } }, "sha512-aPTXCrfwnDLj4VvXrm+UUCQjNEvJgNA8s5F1cvwQU+3KNltTOkBm1j30uNLyqqPNe7gE3KFzImYoZEfLhp4Yow=="],
"@types/react": ["@types/react@19.1.8", "", { "dependencies": { "csstype": "^3.0.2" } }, "sha512-AwAfQ2Wa5bCx9WP8nZL2uMZWod7J7/JSplxbTmBQ5ms6QpqNYm672H0Vu9ZVKVngQ+ii4R/byguVEUZQyeg44g=="],
"before-after-hook": ["before-after-hook@2.2.3", "", {}, "sha512-NzUnlZexiaH/46WDhANlyR2bXRopNg4F/zuSA3OpZnllCUgRaOF2znDioDWrmbNVsuZk6l9pMquQB38cfBZwkQ=="],
"bun-types": ["bun-types@1.2.20", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-pxTnQYOrKvdOwyiyd/7sMt9yFOenN004Y6O4lCcCUoKVej48FS5cvTw9geRaEcB9TsDZaJKAxPTVvi8tFsVuXA=="],
"csstype": ["csstype@3.1.3", "", {}, "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="],
"deprecation": ["deprecation@2.3.1", "", {}, "sha512-xmHIy4F3scKVwMsQ4WnVaS8bHOx0DmVwRywosKhaILI0ywMDWPtBSku2HNxRvF7jtwDRsoEwYQSfbxj8b7RlJQ=="],
"once": ["once@1.4.0", "", { "dependencies": { "wrappy": "1" } }, "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w=="],
"prettier": ["prettier@3.6.2", "", { "bin": { "prettier": "bin/prettier.cjs" } }, "sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ=="],
"tunnel": ["tunnel@0.0.6", "", {}, "sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg=="],
"typescript": ["typescript@5.9.2", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-CWBzXQrc/qOkhidw1OzBTQuYRbfyxDXJMVJ1XNwUHGROVmuaeiEm3OslpZ1RV96d7SKKjZKrSJu3+t/xlw3R9A=="],
"undici": ["undici@5.29.0", "", { "dependencies": { "@fastify/busboy": "^2.0.0" } }, "sha512-raqeBD6NQK4SkWhQzeYKd1KmIG6dllBOTt55Rmkt4HtI9mwdWtJljnrXjAFUBLTSN67HWrOIZ3EPF4kjUw80Bg=="],
"undici-types": ["undici-types@7.10.0", "", {}, "sha512-t5Fy/nfn+14LuOc2KNYg75vZqClpAiqscVvMygNnlsHBFpSXdJaYtXMcdNLpl/Qvc3P2cB3s6lOV51nqsFq4ag=="],
"universal-user-agent": ["universal-user-agent@6.0.1", "", {}, "sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ=="],
"wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
"@octokit/plugin-paginate-rest/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],
"@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],
"bun-types/@types/node": ["@types/node@24.2.1", "", { "dependencies": { "undici-types": "~7.10.0" } }, "sha512-DRh5K+ka5eJic8CjH7td8QpYEV6Zo10gfRkjHCO3weqZHWDtAaSTFtl4+VMqOJ4N5jcuhZ9/l+yy8rVgw7BQeQ=="],
"@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],
"@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],
}
}

21
.github/actions/codex/package.json vendored Normal file
View File

@@ -0,0 +1,21 @@
{
"name": "codex-action",
"version": "0.0.0",
"private": true,
"scripts": {
"format": "prettier --check src",
"format:fix": "prettier --write src",
"test": "bun test",
"typecheck": "tsc"
},
"dependencies": {
"@actions/core": "^1.11.1",
"@actions/github": "^6.0.1"
},
"devDependencies": {
"@types/bun": "^1.2.20",
"@types/node": "^24.3.0",
"prettier": "^3.6.2",
"typescript": "^5.9.2"
}
}

View File

@@ -0,0 +1,85 @@
import * as github from "@actions/github";
import type { EnvContext } from "./env-context";
/**
* Add an "eyes" reaction to the entity (issue, issue comment, or pull request
* review comment) that triggered the current Codex invocation.
*
* The purpose is to provide immediate feedback to the user similar to the
* *-in-progress label flow indicating that the bot has acknowledged the
* request and is working on it.
*
* We attempt to add the reaction best suited for the current GitHub event:
*
* • issues → POST /repos/{owner}/{repo}/issues/{issue_number}/reactions
* • issue_comment → POST /repos/{owner}/{repo}/issues/comments/{comment_id}/reactions
* • pull_request_review_comment → POST /repos/{owner}/{repo}/pulls/comments/{comment_id}/reactions
*
* If the specific target is unavailable (e.g. unexpected payload shape) we
* silently skip instead of failing the whole action because the reaction is
* merely cosmetic.
*/
export async function addEyesReaction(ctx: EnvContext): Promise<void> {
const octokit = ctx.getOctokit();
const { owner, repo } = github.context.repo;
const eventName = github.context.eventName;
try {
switch (eventName) {
case "issue_comment": {
const commentId = (github.context.payload as any)?.comment?.id;
if (commentId) {
await octokit.rest.reactions.createForIssueComment({
owner,
repo,
comment_id: commentId,
content: "eyes",
});
return;
}
break;
}
case "pull_request_review_comment": {
const commentId = (github.context.payload as any)?.comment?.id;
if (commentId) {
await octokit.rest.reactions.createForPullRequestReviewComment({
owner,
repo,
comment_id: commentId,
content: "eyes",
});
return;
}
break;
}
case "issues": {
const issueNumber = github.context.issue.number;
if (issueNumber) {
await octokit.rest.reactions.createForIssue({
owner,
repo,
issue_number: issueNumber,
content: "eyes",
});
return;
}
break;
}
default: {
// Fallback: try to react to the issue/PR if we have a number.
const issueNumber = github.context.issue.number;
if (issueNumber) {
await octokit.rest.reactions.createForIssue({
owner,
repo,
issue_number: issueNumber,
content: "eyes",
});
}
}
}
} catch (error) {
// Do not fail the action if reaction creation fails log and continue.
console.warn(`Failed to add \"eyes\" reaction: ${error}`);
}
}

53
.github/actions/codex/src/comment.ts vendored Normal file
View File

@@ -0,0 +1,53 @@
import type { EnvContext } from "./env-context";
import { runCodex } from "./run-codex";
import { postComment } from "./post-comment";
import { addEyesReaction } from "./add-reaction";
/**
* Handle `issue_comment` and `pull_request_review_comment` events once we know
* the action is supported.
*/
export async function onComment(ctx: EnvContext): Promise<void> {
const triggerPhrase = ctx.tryGet("INPUT_TRIGGER_PHRASE");
if (!triggerPhrase) {
console.warn("Empty trigger phrase: skipping.");
return;
}
// Attempt to get the body of the comment from the environment. Depending on
// the event type either `GITHUB_EVENT_COMMENT_BODY` (issue & PR comments) or
// `GITHUB_EVENT_REVIEW_BODY` (PR reviews) is set.
const commentBody =
ctx.tryGetNonEmpty("GITHUB_EVENT_COMMENT_BODY") ??
ctx.tryGetNonEmpty("GITHUB_EVENT_REVIEW_BODY") ??
ctx.tryGetNonEmpty("GITHUB_EVENT_ISSUE_BODY");
if (!commentBody) {
console.warn("Comment body not found in environment: skipping.");
return;
}
// Check if the trigger phrase is present.
if (!commentBody.includes(triggerPhrase)) {
console.log(
`Trigger phrase '${triggerPhrase}' not found: nothing to do for this comment.`,
);
return;
}
// Derive the prompt by removing the trigger phrase. Remove only the first
// occurrence to keep any additional occurrences that might be meaningful.
const prompt = commentBody.replace(triggerPhrase, "").trim();
if (prompt.length === 0) {
console.warn("Prompt is empty after removing trigger phrase: skipping");
return;
}
// Provide immediate feedback that we are working on the request.
await addEyesReaction(ctx);
// Run Codex and post the response as a new comment.
const lastMessage = await runCodex(prompt, ctx);
await postComment(lastMessage, ctx);
}

11
.github/actions/codex/src/config.ts vendored Normal file
View File

@@ -0,0 +1,11 @@
import { readdirSync, statSync } from "fs";
import * as path from "path";
export interface Config {
labels: Record<string, LabelConfig>;
}
export interface LabelConfig {
/** Returns the prompt template. */
getPromptTemplate(): string;
}

View File

@@ -0,0 +1,44 @@
import type { Config } from "./config";
export function getDefaultConfig(): Config {
return {
labels: {
"codex-investigate-issue": {
getPromptTemplate: () =>
`
Troubleshoot whether the reported issue is valid.
Provide a concise and respectful comment summarizing the findings.
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}
`.trim(),
},
"codex-code-review": {
getPromptTemplate: () =>
`
Review this PR and respond with a very concise final message, formatted in Markdown.
There should be a summary of the changes (1-2 sentences) and a few bullet points if necessary.
Then provide the **review** (1-2 sentences plus bullet points, friendly tone).
{CODEX_ACTION_GITHUB_EVENT_PATH} contains the JSON that triggered this GitHub workflow. It contains the \`base\` and \`head\` refs that define this PR. Both refs are available locally.
`.trim(),
},
"codex-attempt-fix": {
getPromptTemplate: () =>
`
Attempt to solve the reported issue.
If a code change is required, create a new branch, commit the fix, and open a pull-request that resolves the problem.
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}
`.trim(),
},
},
};
}

116
.github/actions/codex/src/env-context.ts vendored Normal file
View File

@@ -0,0 +1,116 @@
/*
* Centralised access to environment variables used by the Codex GitHub
* Action.
*
* To enable proper unit-testing we avoid reading from `process.env` at module
* initialisation time. Instead a `EnvContext` object is created (usually from
* the real `process.env`) and passed around explicitly or where that is not
* yet practical imported as the shared `defaultContext` singleton. Tests can
* create their own context backed by a stubbed map of variables without having
* to mutate global state.
*/
import { fail } from "./fail";
import * as github from "@actions/github";
export interface EnvContext {
/**
* Return the value for a given environment variable or terminate the action
* via `fail` if it is missing / empty.
*/
get(name: string): string;
/**
* Attempt to read an environment variable. Returns the value when present;
* otherwise returns undefined (does not call `fail`).
*/
tryGet(name: string): string | undefined;
/**
* Attempt to read an environment variable. Returns non-empty string value or
* null if unset or empty string.
*/
tryGetNonEmpty(name: string): string | null;
/**
* Return a memoised Octokit instance authenticated via the token resolved
* from the provided argument (when defined) or the environment variables
* `GITHUB_TOKEN`/`GH_TOKEN`.
*
* Subsequent calls return the same cached instance to avoid spawning
* multiple REST clients within a single action run.
*/
getOctokit(token?: string): ReturnType<typeof github.getOctokit>;
}
/** Internal helper *not* exported. */
function _getRequiredEnv(
name: string,
env: Record<string, string | undefined>,
): string | undefined {
const value = env[name];
// Avoid leaking secrets into logs while still logging non-secret variables.
if (name.endsWith("KEY") || name.endsWith("TOKEN")) {
if (value) {
console.log(`value for ${name} was found`);
}
} else {
console.log(`${name}=${value}`);
}
return value;
}
/** Create a context backed by the supplied environment map (defaults to `process.env`). */
export function createEnvContext(
env: Record<string, string | undefined> = process.env,
): EnvContext {
// Lazily instantiated Octokit client shared across this context.
let cachedOctokit: ReturnType<typeof github.getOctokit> | null = null;
return {
get(name: string): string {
const value = _getRequiredEnv(name, env);
if (value == null) {
fail(`Missing required environment variable: ${name}`);
}
return value;
},
tryGet(name: string): string | undefined {
return _getRequiredEnv(name, env);
},
tryGetNonEmpty(name: string): string | null {
const value = _getRequiredEnv(name, env);
return value == null || value === "" ? null : value;
},
getOctokit(token?: string) {
if (cachedOctokit) {
return cachedOctokit;
}
// Determine the token to authenticate with.
const githubToken = token ?? env["GITHUB_TOKEN"] ?? env["GH_TOKEN"];
if (!githubToken) {
fail(
"Unable to locate a GitHub token. `github_token` should have been set on the action.",
);
}
cachedOctokit = github.getOctokit(githubToken!);
return cachedOctokit;
},
};
}
/**
* Shared context built from the actual `process.env`. Production code that is
* not yet refactored to receive a context explicitly may import and use this
* singleton. Tests should avoid the singleton and instead pass their own
* context to the functions they exercise.
*/
export const defaultContext: EnvContext = createEnvContext();

4
.github/actions/codex/src/fail.ts vendored Normal file
View File

@@ -0,0 +1,4 @@
export function fail(message: string): never {
console.error(message);
process.exit(1);
}

149
.github/actions/codex/src/git-helpers.ts vendored Normal file
View File

@@ -0,0 +1,149 @@
import { spawnSync } from "child_process";
import * as github from "@actions/github";
import { EnvContext } from "./env-context";
function runGit(args: string[], silent = true): string {
console.info(`Running git ${args.join(" ")}`);
const res = spawnSync("git", args, {
encoding: "utf8",
stdio: silent ? ["ignore", "pipe", "pipe"] : "inherit",
});
if (res.error) {
throw res.error;
}
if (res.status !== 0) {
// Return stderr so caller may handle; else throw.
throw new Error(
`git ${args.join(" ")} failed with code ${res.status}: ${res.stderr}`,
);
}
return res.stdout.trim();
}
function stageAllChanges() {
runGit(["add", "-A"]);
}
function hasStagedChanges(): boolean {
const res = spawnSync("git", ["diff", "--cached", "--quiet", "--exit-code"]);
return res.status !== 0;
}
function ensureOnBranch(
issueNumber: number,
protectedBranches: string[],
suggestedSlug?: string,
): string {
let branch = "";
try {
branch = runGit(["symbolic-ref", "--short", "-q", "HEAD"]);
} catch {
branch = "";
}
// If detached HEAD or on a protected branch, create a new branch.
if (!branch || protectedBranches.includes(branch)) {
if (suggestedSlug) {
const safeSlug = suggestedSlug
.toLowerCase()
.replace(/[^\w\s-]/g, "")
.trim()
.replace(/\s+/g, "-");
branch = `codex-fix-${issueNumber}-${safeSlug}`;
} else {
branch = `codex-fix-${issueNumber}-${Date.now()}`;
}
runGit(["switch", "-c", branch]);
}
return branch;
}
function commitIfNeeded(issueNumber: number) {
if (hasStagedChanges()) {
runGit([
"commit",
"-m",
`fix: automated fix for #${issueNumber} via Codex`,
]);
}
}
function pushBranch(branch: string, githubToken: string, ctx: EnvContext) {
const repoSlug = ctx.get("GITHUB_REPOSITORY"); // owner/repo
const remoteUrl = `https://x-access-token:${githubToken}@github.com/${repoSlug}.git`;
runGit(["push", "--force-with-lease", "-u", remoteUrl, `HEAD:${branch}`]);
}
/**
* If this returns a string, it is the URL of the created PR.
*/
export async function maybePublishPRForIssue(
issueNumber: number,
lastMessage: string,
ctx: EnvContext,
): Promise<string | undefined> {
// Only proceed if GITHUB_TOKEN available.
const githubToken =
ctx.tryGetNonEmpty("GITHUB_TOKEN") ?? ctx.tryGetNonEmpty("GH_TOKEN");
if (!githubToken) {
console.warn("No GitHub token - skipping PR creation.");
return undefined;
}
// Print `git status` for debugging.
runGit(["status"]);
// Stage any remaining changes so they can be committed and pushed.
stageAllChanges();
const octokit = ctx.getOctokit(githubToken);
const { owner, repo } = github.context.repo;
// Determine default branch to treat as protected.
let defaultBranch = "main";
try {
const repoInfo = await octokit.rest.repos.get({ owner, repo });
defaultBranch = repoInfo.data.default_branch ?? "main";
} catch (e) {
console.warn(`Failed to get default branch, assuming 'main': ${e}`);
}
const sanitizedMessage = lastMessage.replace(/\u2022/g, "-");
const [summaryLine] = sanitizedMessage.split(/\r?\n/);
const branch = ensureOnBranch(issueNumber, [defaultBranch, "master"], summaryLine);
commitIfNeeded(issueNumber);
pushBranch(branch, githubToken, ctx);
// Try to find existing PR for this branch
const headParam = `${owner}:${branch}`;
const existing = await octokit.rest.pulls.list({
owner,
repo,
head: headParam,
state: "open",
});
if (existing.data.length > 0) {
return existing.data[0].html_url;
}
// Determine base branch (default to main)
let baseBranch = "main";
try {
const repoInfo = await octokit.rest.repos.get({ owner, repo });
baseBranch = repoInfo.data.default_branch ?? "main";
} catch (e) {
console.warn(`Failed to get default branch, assuming 'main': ${e}`);
}
const pr = await octokit.rest.pulls.create({
owner,
repo,
title: summaryLine,
head: branch,
base: baseBranch,
body: sanitizedMessage,
});
return pr.data.html_url;
}

16
.github/actions/codex/src/git-user.ts vendored Normal file
View File

@@ -0,0 +1,16 @@
export function setGitHubActionsUser(): void {
const commands = [
["git", "config", "--global", "user.name", "github-actions[bot]"],
[
"git",
"config",
"--global",
"user.email",
"41898282+github-actions[bot]@users.noreply.github.com",
],
];
for (const command of commands) {
Bun.spawnSync(command);
}
}

View File

@@ -0,0 +1,11 @@
import * as pathMod from "path";
import { EnvContext } from "./env-context";
export function resolveWorkspacePath(path: string, ctx: EnvContext): string {
if (pathMod.isAbsolute(path)) {
return path;
} else {
const workspace = ctx.get("GITHUB_WORKSPACE");
return pathMod.join(workspace, path);
}
}

View File

@@ -0,0 +1,56 @@
import type { Config, LabelConfig } from "./config";
import { getDefaultConfig } from "./default-label-config";
import { readFileSync, readdirSync, statSync } from "fs";
import * as path from "path";
/**
* Build an in-memory configuration object by scanning the repository for
* Markdown templates located in `.github/codex/labels`.
*
* Each `*.md` file in that directory represents a label that can trigger the
* Codex GitHub Action. The filename **without** the extension is interpreted
* as the label name, e.g. `codex-review.md` ➜ `codex-review`.
*
* For every such label we derive the corresponding `doneLabel` by appending
* the suffix `-completed`.
*/
export function loadConfig(workspace: string): Config {
const labelsDir = path.join(workspace, ".github", "codex", "labels");
let entries: string[];
try {
entries = readdirSync(labelsDir);
} catch {
// If the directory is missing, return the default configuration.
return getDefaultConfig();
}
const labels: Record<string, LabelConfig> = {};
for (const entry of entries) {
if (!entry.endsWith(".md")) {
continue;
}
const fullPath = path.join(labelsDir, entry);
if (!statSync(fullPath).isFile()) {
continue;
}
const labelName = entry.slice(0, -3); // trim ".md"
labels[labelName] = new FileLabelConfig(fullPath);
}
return { labels };
}
class FileLabelConfig implements LabelConfig {
constructor(private readonly promptPath: string) {}
getPromptTemplate(): string {
return readFileSync(this.promptPath, "utf8");
}
}

80
.github/actions/codex/src/main.ts vendored Executable file
View File

@@ -0,0 +1,80 @@
#!/usr/bin/env bun
import type { Config } from "./config";
import { defaultContext, EnvContext } from "./env-context";
import { loadConfig } from "./load-config";
import { setGitHubActionsUser } from "./git-user";
import { onLabeled } from "./process-label";
import { ensureBaseAndHeadCommitsForPRAreAvailable } from "./prompt-template";
import { performAdditionalValidation } from "./verify-inputs";
import { onComment } from "./comment";
import { onReview } from "./review";
async function main(): Promise<void> {
const ctx: EnvContext = defaultContext;
// Build the configuration dynamically by scanning `.github/codex/labels`.
const GITHUB_WORKSPACE = ctx.get("GITHUB_WORKSPACE");
const config: Config = loadConfig(GITHUB_WORKSPACE);
// Optionally perform additional validation of prompt template files.
performAdditionalValidation(config, GITHUB_WORKSPACE);
const GITHUB_EVENT_NAME = ctx.get("GITHUB_EVENT_NAME");
const GITHUB_EVENT_ACTION = ctx.get("GITHUB_EVENT_ACTION");
// Set user.name and user.email to a bot before Codex runs, just in case it
// creates a commit.
setGitHubActionsUser();
switch (GITHUB_EVENT_NAME) {
case "issues": {
if (GITHUB_EVENT_ACTION === "labeled") {
await onLabeled(config, ctx);
return;
} else if (GITHUB_EVENT_ACTION === "opened") {
await onComment(ctx);
return;
}
break;
}
case "issue_comment": {
if (GITHUB_EVENT_ACTION === "created") {
await onComment(ctx);
return;
}
break;
}
case "pull_request": {
if (GITHUB_EVENT_ACTION === "labeled") {
await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
await onLabeled(config, ctx);
return;
}
break;
}
case "pull_request_review": {
await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
if (GITHUB_EVENT_ACTION === "submitted") {
await onReview(ctx);
return;
}
break;
}
case "pull_request_review_comment": {
await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
if (GITHUB_EVENT_ACTION === "created") {
await onComment(ctx);
return;
}
break;
}
}
console.warn(
`Unsupported action '${GITHUB_EVENT_ACTION}' for event '${GITHUB_EVENT_NAME}'.`,
);
}
main();

View File

@@ -0,0 +1,62 @@
import { fail } from "./fail";
import * as github from "@actions/github";
import { EnvContext } from "./env-context";
/**
* Post a comment to the issue / pull request currently in scope.
*
* Provide the environment context so that token lookup (inside getOctokit) does
* not rely on global state.
*/
export async function postComment(
commentBody: string,
ctx: EnvContext,
): Promise<void> {
// Append a footer with a link back to the workflow run, if available.
const footer = buildWorkflowRunFooter(ctx);
const bodyWithFooter = footer ? `${commentBody}${footer}` : commentBody;
const octokit = ctx.getOctokit();
console.info("Got Octokit instance for posting comment");
const { owner, repo } = github.context.repo;
const issueNumber = github.context.issue.number;
if (!issueNumber) {
console.warn(
"No issue or pull_request number found in GitHub context; skipping comment creation.",
);
return;
}
try {
console.info("Calling octokit.rest.issues.createComment()");
await octokit.rest.issues.createComment({
owner,
repo,
issue_number: issueNumber,
body: bodyWithFooter,
});
} catch (error) {
fail(`Failed to create comment via GitHub API: ${error}`);
}
}
/**
* Helper to build a Markdown fragment linking back to the workflow run that
* generated the current comment. Returns `undefined` if required environment
* variables are missing e.g. when running outside of GitHub Actions so we
* can gracefully skip the footer in those cases.
*/
function buildWorkflowRunFooter(ctx: EnvContext): string | undefined {
const serverUrl =
ctx.tryGetNonEmpty("GITHUB_SERVER_URL") ?? "https://github.com";
const repository = ctx.tryGetNonEmpty("GITHUB_REPOSITORY");
const runId = ctx.tryGetNonEmpty("GITHUB_RUN_ID");
if (!repository || !runId) {
return undefined;
}
const url = `${serverUrl}/${repository}/actions/runs/${runId}`;
return `\n\n---\n*[_View workflow run_](${url})*`;
}

View File

@@ -0,0 +1,226 @@
import { fail } from "./fail";
import { EnvContext } from "./env-context";
import { renderPromptTemplate } from "./prompt-template";
import { postComment } from "./post-comment";
import { runCodex } from "./run-codex";
import * as github from "@actions/github";
import { Config, LabelConfig } from "./config";
import { maybePublishPRForIssue } from "./git-helpers";
export async function onLabeled(
config: Config,
ctx: EnvContext,
): Promise<void> {
const GITHUB_EVENT_LABEL_NAME = ctx.get("GITHUB_EVENT_LABEL_NAME");
const labelConfig = config.labels[GITHUB_EVENT_LABEL_NAME] as
| LabelConfig
| undefined;
if (!labelConfig) {
fail(
`Label \`${GITHUB_EVENT_LABEL_NAME}\` not found in config: ${JSON.stringify(config)}`,
);
}
await processLabelConfig(ctx, GITHUB_EVENT_LABEL_NAME, labelConfig);
}
/**
* Wrapper that handles `-in-progress` and `-completed` semantics around the core lint/fix/review
* processing. It will:
*
* - Skip execution if the `-in-progress` or `-completed` label is already present.
* - Mark the PR/issue as `-in-progress`.
* - After successful execution, mark the PR/issue as `-completed`.
*/
async function processLabelConfig(
ctx: EnvContext,
label: string,
labelConfig: LabelConfig,
): Promise<void> {
const octokit = ctx.getOctokit();
const { owner, repo, issueNumber, labelNames } =
await getCurrentLabels(octokit);
const inProgressLabel = `${label}-in-progress`;
const completedLabel = `${label}-completed`;
for (const markerLabel of [inProgressLabel, completedLabel]) {
if (labelNames.includes(markerLabel)) {
console.log(
`Label '${markerLabel}' already present on issue/PR #${issueNumber}. Skipping Codex action.`,
);
// Clean up: remove the triggering label to avoid confusion and re-runs.
await addAndRemoveLabels(octokit, {
owner,
repo,
issueNumber,
remove: markerLabel,
});
return;
}
}
// Mark the PR/issue as in progress.
await addAndRemoveLabels(octokit, {
owner,
repo,
issueNumber,
add: inProgressLabel,
remove: label,
});
// Run the core Codex processing.
await processLabel(ctx, label, labelConfig);
// Mark the PR/issue as completed.
await addAndRemoveLabels(octokit, {
owner,
repo,
issueNumber,
add: completedLabel,
remove: inProgressLabel,
});
}
async function processLabel(
ctx: EnvContext,
label: string,
labelConfig: LabelConfig,
): Promise<void> {
const template = labelConfig.getPromptTemplate();
// If this is a review label, prepend explicit PR-diff scoping guidance to
// reduce out-of-scope feedback. Do this before rendering so placeholders in
// the guidance (e.g., {CODEX_ACTION_GITHUB_EVENT_PATH}) are substituted.
const isReview = label.toLowerCase().includes("review");
const reviewScopeGuidance = `
PR Diff Scope
- Only review changes between the PR's merge-base and head; do not comment on commits or files outside this range.
- Derive the base/head SHAs from the event JSON at {CODEX_ACTION_GITHUB_EVENT_PATH}, then compute and use the PR diff for all analysis and comments.
Commands to determine scope
- Resolve SHAs:
- BASE_SHA=$(jq -r '.pull_request.base.sha // .pull_request.base.ref' "{CODEX_ACTION_GITHUB_EVENT_PATH}")
- HEAD_SHA=$(jq -r '.pull_request.head.sha // .pull_request.head.ref' "{CODEX_ACTION_GITHUB_EVENT_PATH}")
- BASE_SHA=$(git rev-parse "$BASE_SHA")
- HEAD_SHA=$(git rev-parse "$HEAD_SHA")
- Prefer triple-dot (merge-base) semantics for PR diffs:
- Changed commits: git log --oneline "$BASE_SHA...$HEAD_SHA"
- Changed files: git diff --name-status "$BASE_SHA...$HEAD_SHA"
- Review hunks: git diff -U0 "$BASE_SHA...$HEAD_SHA"
Review rules
- Anchor every comment to a file and hunk present in git diff "$BASE_SHA...$HEAD_SHA".
- If you mention context outside the diff, label it as "Follow-up (outside this PR scope)" and keep it brief (<=2 bullets).
- Do not critique commits or files not reachable in the PR range (merge-base(base, head) → head).
`.trim();
const effectiveTemplate = isReview
? `${reviewScopeGuidance}\n\n${template}`
: template;
const populatedTemplate = await renderPromptTemplate(effectiveTemplate, ctx);
// Always run Codex and post the resulting message as a comment.
let commentBody = await runCodex(populatedTemplate, ctx);
// Current heuristic: only try to create a PR if "attempt" or "fix" is in the
// label name. (Yes, we plan to evolve this.)
if (label.indexOf("fix") !== -1 || label.indexOf("attempt") !== -1) {
console.info(`label ${label} indicates we should attempt to create a PR`);
const prUrl = await maybeFixIssue(ctx, commentBody);
if (prUrl) {
commentBody += `\n\n---\nOpened pull request: ${prUrl}`;
}
} else {
console.info(
`label ${label} does not indicate we should attempt to create a PR`,
);
}
await postComment(commentBody, ctx);
}
async function maybeFixIssue(
ctx: EnvContext,
lastMessage: string,
): Promise<string | undefined> {
// Attempt to create a PR out of any changes Codex produced.
const issueNumber = github.context.issue.number!; // exists for issues triggering this path
try {
return await maybePublishPRForIssue(issueNumber, lastMessage, ctx);
} catch (e) {
console.warn(`Failed to publish PR: ${e}`);
}
}
async function getCurrentLabels(
octokit: ReturnType<typeof github.getOctokit>,
): Promise<{
owner: string;
repo: string;
issueNumber: number;
labelNames: Array<string>;
}> {
const { owner, repo } = github.context.repo;
const issueNumber = github.context.issue.number;
if (!issueNumber) {
fail("No issue or pull_request number found in GitHub context.");
}
const { data: issueData } = await octokit.rest.issues.get({
owner,
repo,
issue_number: issueNumber,
});
const labelNames =
issueData.labels?.map((label: any) =>
typeof label === "string" ? label : label.name,
) ?? [];
return { owner, repo, issueNumber, labelNames };
}
async function addAndRemoveLabels(
octokit: ReturnType<typeof github.getOctokit>,
opts: {
owner: string;
repo: string;
issueNumber: number;
add?: string;
remove?: string;
},
): Promise<void> {
const { owner, repo, issueNumber, add, remove } = opts;
if (add) {
try {
await octokit.rest.issues.addLabels({
owner,
repo,
issue_number: issueNumber,
labels: [add],
});
} catch (error) {
console.warn(`Failed to add label '${add}': ${error}`);
}
}
if (remove) {
try {
await octokit.rest.issues.removeLabel({
owner,
repo,
issue_number: issueNumber,
name: remove,
});
} catch (error) {
console.warn(`Failed to remove label '${remove}': ${error}`);
}
}
}

View File

@@ -0,0 +1,284 @@
/*
* Utilities to render Codex prompt templates.
*
* A template is a Markdown (or plain-text) file that may contain one or more
* placeholders of the form `{CODEX_ACTION_<NAME>}`. At runtime these
* placeholders are substituted with dynamically generated content. Each
* placeholder is resolved **exactly once** even if it appears multiple times
* in the same template.
*/
import { readFile } from "fs/promises";
import { EnvContext } from "./env-context";
// ---------------------------------------------------------------------------
// Helpers
// ---------------------------------------------------------------------------
/**
* Lazily caches parsed `$GITHUB_EVENT_PATH` contents keyed by the file path so
* we only hit the filesystem once per unique event payload.
*/
const githubEventDataCache: Map<string, Promise<any>> = new Map();
function getGitHubEventData(ctx: EnvContext): Promise<any> {
const eventPath = ctx.get("GITHUB_EVENT_PATH");
let cached = githubEventDataCache.get(eventPath);
if (!cached) {
cached = readFile(eventPath, "utf8").then((raw) => JSON.parse(raw));
githubEventDataCache.set(eventPath, cached);
}
return cached;
}
async function runCommand(args: Array<string>): Promise<string> {
const result = Bun.spawnSync(args, {
stdout: "pipe",
stderr: "pipe",
});
if (result.success) {
return result.stdout.toString();
}
console.error(`Error running ${JSON.stringify(args)}: ${result.stderr}`);
return "";
}
// ---------------------------------------------------------------------------
// Public API
// ---------------------------------------------------------------------------
// Regex that captures the variable name without the surrounding { } braces.
const VAR_REGEX = /\{(CODEX_ACTION_[A-Z0-9_]+)\}/g;
// Cache individual placeholder values so each one is resolved at most once per
// process even if many templates reference it.
const placeholderCache: Map<string, Promise<string>> = new Map();
/**
* Parse a template string, resolve all placeholders and return the rendered
* result.
*/
export async function renderPromptTemplate(
template: string,
ctx: EnvContext,
): Promise<string> {
// ---------------------------------------------------------------------
// 1) Gather all *unique* placeholders present in the template.
// ---------------------------------------------------------------------
const variables = new Set<string>();
for (const match of template.matchAll(VAR_REGEX)) {
variables.add(match[1]);
}
// ---------------------------------------------------------------------
// 2) Kick off (or reuse) async resolution for each variable.
// ---------------------------------------------------------------------
for (const variable of variables) {
if (!placeholderCache.has(variable)) {
placeholderCache.set(variable, resolveVariable(variable, ctx));
}
}
// ---------------------------------------------------------------------
// 3) Await completion so we can perform a simple synchronous replace below.
// ---------------------------------------------------------------------
const resolvedEntries: [string, string][] = [];
for (const [key, promise] of placeholderCache.entries()) {
resolvedEntries.push([key, await promise]);
}
const resolvedMap = new Map<string, string>(resolvedEntries);
// ---------------------------------------------------------------------
// 4) Replace each occurrence. We use replace with a callback to ensure
// correct substitution even if variable names overlap (they shouldn't,
// but better safe than sorry).
// ---------------------------------------------------------------------
return template.replace(VAR_REGEX, (_, varName: string) => {
return resolvedMap.get(varName) ?? "";
});
}
export async function ensureBaseAndHeadCommitsForPRAreAvailable(
ctx: EnvContext,
): Promise<{ baseSha: string; headSha: string } | null> {
const prShas = await getPrShas(ctx);
if (prShas == null) {
console.warn("Unable to resolve PR branches");
return null;
}
const event = await getGitHubEventData(ctx);
const pr = event.pull_request;
if (!pr) {
console.warn("event.pull_request is not defined - unexpected");
return null;
}
const workspace = ctx.get("GITHUB_WORKSPACE");
// Refs (branch names)
const baseRef: string | undefined = pr.base?.ref;
const headRef: string | undefined = pr.head?.ref;
// Clone URLs
const baseRemoteUrl: string | undefined = pr.base?.repo?.clone_url;
const headRemoteUrl: string | undefined = pr.head?.repo?.clone_url;
if (!baseRef || !headRef || !baseRemoteUrl || !headRemoteUrl) {
console.warn(
"Missing PR ref or remote URL information - cannot fetch commits",
);
return null;
}
// Ensure we have the base branch.
await runCommand([
"git",
"-C",
workspace,
"fetch",
"--no-tags",
"origin",
baseRef,
]);
// Ensure we have the head branch.
if (headRemoteUrl === baseRemoteUrl) {
// Same repository the commit is available from `origin`.
await runCommand([
"git",
"-C",
workspace,
"fetch",
"--no-tags",
"origin",
headRef,
]);
} else {
// Fork make sure a `pr` remote exists that points at the fork. Attempting
// to add a remote that already exists causes git to error, so we swallow
// any non-zero exit codes from that specific command.
await runCommand([
"git",
"-C",
workspace,
"remote",
"add",
"pr",
headRemoteUrl,
]);
// Whether adding succeeded or the remote already existed, attempt to fetch
// the head ref from the `pr` remote.
await runCommand([
"git",
"-C",
workspace,
"fetch",
"--no-tags",
"pr",
headRef,
]);
}
return prShas;
}
// ---------------------------------------------------------------------------
// Internal helpers still exported for use by other modules.
// ---------------------------------------------------------------------------
export async function resolvePrDiff(ctx: EnvContext): Promise<string> {
const prShas = await ensureBaseAndHeadCommitsForPRAreAvailable(ctx);
if (prShas == null) {
console.warn("Unable to resolve PR branches");
return "";
}
const workspace = ctx.get("GITHUB_WORKSPACE");
const { baseSha, headSha } = prShas;
return runCommand([
"git",
"-C",
workspace,
"diff",
"--color=never",
`${baseSha}..${headSha}`,
]);
}
// ---------------------------------------------------------------------------
// Placeholder resolution
// ---------------------------------------------------------------------------
async function resolveVariable(name: string, ctx: EnvContext): Promise<string> {
switch (name) {
case "CODEX_ACTION_ISSUE_TITLE": {
const event = await getGitHubEventData(ctx);
const issue = event.issue ?? event.pull_request;
return issue?.title ?? "";
}
case "CODEX_ACTION_ISSUE_BODY": {
const event = await getGitHubEventData(ctx);
const issue = event.issue ?? event.pull_request;
return issue?.body ?? "";
}
case "CODEX_ACTION_GITHUB_EVENT_PATH": {
return ctx.get("GITHUB_EVENT_PATH");
}
case "CODEX_ACTION_BASE_REF": {
const event = await getGitHubEventData(ctx);
return event?.pull_request?.base?.ref ?? "";
}
case "CODEX_ACTION_HEAD_REF": {
const event = await getGitHubEventData(ctx);
return event?.pull_request?.head?.ref ?? "";
}
case "CODEX_ACTION_PR_DIFF": {
return resolvePrDiff(ctx);
}
// -------------------------------------------------------------------
// Add new template variables here.
// -------------------------------------------------------------------
default: {
// Unknown variable leave it blank to avoid leaking placeholders to the
// final prompt. The alternative would be to `fail()` here, but silently
// ignoring unknown placeholders is more forgiving and better matches the
// behaviour of typical template engines.
console.warn(`Unknown template variable: ${name}`);
return "";
}
}
}
async function getPrShas(
ctx: EnvContext,
): Promise<{ baseSha: string; headSha: string } | null> {
const event = await getGitHubEventData(ctx);
const pr = event.pull_request;
if (!pr) {
console.warn("event.pull_request is not defined");
return null;
}
// Prefer explicit SHAs if available to avoid relying on local branch names.
const baseSha: string | undefined = pr.base?.sha;
const headSha: string | undefined = pr.head?.sha;
if (!baseSha || !headSha) {
console.warn("one of base or head is not defined on event.pull_request");
return null;
}
return { baseSha, headSha };
}

42
.github/actions/codex/src/review.ts vendored Normal file
View File

@@ -0,0 +1,42 @@
import type { EnvContext } from "./env-context";
import { runCodex } from "./run-codex";
import { postComment } from "./post-comment";
import { addEyesReaction } from "./add-reaction";
/**
* Handle `pull_request_review` events. We treat the review body the same way
* as a normal comment.
*/
export async function onReview(ctx: EnvContext): Promise<void> {
const triggerPhrase = ctx.tryGet("INPUT_TRIGGER_PHRASE");
if (!triggerPhrase) {
console.warn("Empty trigger phrase: skipping.");
return;
}
const reviewBody = ctx.tryGet("GITHUB_EVENT_REVIEW_BODY");
if (!reviewBody) {
console.warn("Review body not found in environment: skipping.");
return;
}
if (!reviewBody.includes(triggerPhrase)) {
console.log(
`Trigger phrase '${triggerPhrase}' not found: nothing to do for this review.`,
);
return;
}
const prompt = reviewBody.replace(triggerPhrase, "").trim();
if (prompt.length === 0) {
console.warn("Prompt is empty after removing trigger phrase: skipping.");
return;
}
await addEyesReaction(ctx);
const lastMessage = await runCodex(prompt, ctx);
await postComment(lastMessage, ctx);
}

58
.github/actions/codex/src/run-codex.ts vendored Normal file
View File

@@ -0,0 +1,58 @@
import { fail } from "./fail";
import { EnvContext } from "./env-context";
import { tmpdir } from "os";
import { join } from "node:path";
import { readFile, mkdtemp } from "fs/promises";
import { resolveWorkspacePath } from "./github-workspace";
/**
* Runs the Codex CLI with the provided prompt and returns the output written
* to the "last message" file.
*/
export async function runCodex(
prompt: string,
ctx: EnvContext,
): Promise<string> {
const OPENAI_API_KEY = ctx.get("OPENAI_API_KEY");
const tempDirPath = await mkdtemp(join(tmpdir(), "codex-"));
const lastMessageOutput = join(tempDirPath, "codex-prompt.md");
// Use the unified CLI and its `exec` subcommand instead of the old
// standalone `codex-exec` binary.
const args = ["/usr/local/bin/codex", "exec"];
const inputCodexArgs = ctx.tryGet("INPUT_CODEX_ARGS")?.trim();
if (inputCodexArgs) {
args.push(...inputCodexArgs.split(/\s+/));
}
args.push("--output-last-message", lastMessageOutput, prompt);
const env: Record<string, string> = { ...process.env, OPENAI_API_KEY };
const INPUT_CODEX_HOME = ctx.tryGet("INPUT_CODEX_HOME");
if (INPUT_CODEX_HOME) {
env.CODEX_HOME = resolveWorkspacePath(INPUT_CODEX_HOME, ctx);
}
console.log(`Running Codex: ${JSON.stringify(args)}`);
const result = Bun.spawnSync(args, {
stdout: "inherit",
stderr: "inherit",
env,
});
if (!result.success) {
fail(`Codex failed: see above for details.`);
}
// Read the output generated by Codex.
let lastMessage: string;
try {
lastMessage = await readFile(lastMessageOutput, "utf8");
} catch (err) {
fail(`Failed to read Codex output at '${lastMessageOutput}': ${err}`);
}
return lastMessage;
}

View File

@@ -0,0 +1,33 @@
// Validate the inputs passed to the composite action.
// The script currently ensures that the provided configuration file exists and
// matches the expected schema.
import type { Config } from "./config";
import { existsSync } from "fs";
import * as path from "path";
import { fail } from "./fail";
export function performAdditionalValidation(config: Config, workspace: string) {
// Additional validation: ensure referenced prompt files exist and are Markdown.
for (const [label, details] of Object.entries(config.labels)) {
// Determine which prompt key is present (the schema guarantees exactly one).
const promptPathStr =
(details as any).prompt ?? (details as any).promptPath;
if (promptPathStr) {
const promptPath = path.isAbsolute(promptPathStr)
? promptPathStr
: path.join(workspace, promptPathStr);
if (!existsSync(promptPath)) {
fail(`Prompt file for label '${label}' not found: ${promptPath}`);
}
if (!promptPath.endsWith(".md")) {
fail(
`Prompt file for label '${label}' must be a .md file (got ${promptPathStr}).`,
);
}
}
}
}

15
.github/actions/codex/tsconfig.json vendored Normal file
View File

@@ -0,0 +1,15 @@
{
"compilerOptions": {
"lib": ["ESNext"],
"target": "ESNext",
"module": "ESNext",
"moduleDetection": "force",
"moduleResolution": "bundler",
"noEmit": true,
"strict": true,
"skipLibCheck": true
},
"include": ["src"]
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 2.9 MiB

After

Width:  |  Height:  |  Size: 410 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.1 MiB

After

Width:  |  Height:  |  Size: 412 KiB

View File

@@ -24,7 +24,3 @@ updates:
directory: /
schedule:
interval: weekly
- package-ecosystem: rust-toolchain
directory: codex-rs
schedule:
interval: weekly

View File

@@ -21,38 +21,6 @@
"windows-x86_64": {
"regex": "^codex-x86_64-pc-windows-msvc\\.exe\\.zst$",
"path": "codex.exe"
},
"windows-aarch64": {
"regex": "^codex-aarch64-pc-windows-msvc\\.exe\\.zst$",
"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

@@ -1,6 +1,6 @@
# 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
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.

View File

@@ -1,7 +1,7 @@
name: ci
on:
pull_request: {}
pull_request: { branches: [main] }
push: { branches: [main] }
jobs:
@@ -14,40 +14,40 @@ jobs:
- 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
uses: actions/setup-node@v4
with:
node-version: 22
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
version: 10.8.1
run_install: false
- name: Get pnpm store directory
id: pnpm-cache
shell: bash
run: |
echo "store_path=$(pnpm store path --silent)" >> $GITHUB_OUTPUT
- name: Setup pnpm cache
uses: actions/cache@v4
with:
path: ${{ steps.pnpm-cache.outputs.store_path }}
key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/pnpm-lock.yaml') }}
restore-keys: |
${{ runner.os }}-pnpm-store-
- name: Install dependencies
run: pnpm install --frozen-lockfile
run: pnpm install
# build_npm_package.py requires DotSlash when staging releases.
- uses: facebook/install-dotslash@v2
# Run all tasks using workspace filters
- name: Stage npm package
id: stage_npm_package
- name: Ensure staging a release works.
env:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
CODEX_VERSION=0.40.0
PACK_OUTPUT="${RUNNER_TEMP}/codex-npm.tgz"
python3 ./codex-cli/scripts/build_npm_package.py \
--release-version "$CODEX_VERSION" \
--pack-output "$PACK_OUTPUT"
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 }}
run: ./codex-cli/scripts/stage_release.sh
- name: Ensure root README.md contains only ASCII and certain Unicode code points
run: ./scripts/asciicheck.py README.md

View File

@@ -22,7 +22,6 @@ jobs:
- name: Annotate locations with typos
uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
- name: Codespell
uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2.1
uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2
with:
ignore_words_file: .codespellignore
skip: frame*.txt

64
.github/workflows/codex.yml vendored Normal file
View File

@@ -0,0 +1,64 @@
name: Codex
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
jobs:
codex:
# This `if` check provides complex filtering logic to avoid running Codex
# on every PR. Admittedly, one thing this does not verify is whether the
# sender has write access to the repo: that must be done as part of a
# runtime step.
#
# Note the label values should match the ones in the .github/codex/labels
# folder.
if: |
(github.event_name == 'issues' && (
(github.event.action == 'labeled' && (github.event.label.name == 'codex-attempt' || github.event.label.name == 'codex-triage'))
)) ||
(github.event_name == 'pull_request' && github.event.action == 'labeled' && (github.event.label.name == 'codex-review' || github.event.label.name == 'codex-rust-review'))
runs-on: ubuntu-latest
permissions:
contents: write # can push or create branches
issues: write # for comments + labels on issues/PRs
pull-requests: write # for PR comments/labels
steps:
# TODO: Consider adding an optional mode (--dry-run?) to actions/codex
# that verifies whether Codex should actually be run for this event.
# (For example, it may be rejected because the sender does not have
# write access to the repo.) The benefit would be two-fold:
# 1. As the first step of this job, it gives us a chance to add a reaction
# or comment to the PR/issue ASAP to "ack" the request.
# 2. It saves resources by skipping the clone and setup steps below if
# Codex is not going to run.
- name: Checkout repository
uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.89
with:
targets: x86_64-unknown-linux-gnu
components: clippy
- uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
${{ github.workspace }}/codex-rs/target/
key: cargo-ubuntu-24.04-x86_64-unknown-linux-gnu-${{ hashFiles('**/Cargo.lock') }}
# Note it is possible that the `verify` step internal to Run Codex will
# fail, in which case the work to setup the repo was worthless :(
- name: Run Codex
uses: ./.github/actions/codex
with:
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
github_token: ${{ secrets.GITHUB_TOKEN }}
codex_home: ./.github/codex/home

View File

@@ -57,31 +57,11 @@ jobs:
working-directory: codex-rs
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
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:
@@ -120,30 +100,19 @@ jobs:
- runner: windows-latest
target: x86_64-pc-windows-msvc
profile: dev
- runner: windows-11-arm
target: aarch64-pc-windows-msvc
profile: dev
# Also run representative release builds on Mac and Linux because
# there could be release-only build errors we want to catch.
# Hopefully this also pre-populates the build cache to speed up
# releases.
- runner: macos-14
target: aarch64-apple-darwin
profile: release
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
profile: release
- runner: windows-latest
target: x86_64-pc-windows-msvc
profile: release
- runner: windows-11-arm
target: aarch64-pc-windows-msvc
profile: release
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
with:
targets: ${{ matrix.target }}
components: clippy
@@ -165,7 +134,7 @@ jobs:
- name: cargo clippy
id: clippy
run: cargo clippy --target ${{ matrix.target }} --all-features --tests --profile ${{ matrix.profile }} -- -D warnings
run: cargo clippy --target ${{ matrix.target }} --all-features --tests -- -D warnings
# Running `cargo build` from the workspace root builds the workspace using
# the union of all features from third-party crates. This can mask errors
@@ -180,17 +149,12 @@ jobs:
find . -name Cargo.toml -mindepth 2 -maxdepth 2 -print0 \
| xargs -0 -n1 -I{} bash -c 'cd "$(dirname "{}")" && cargo check --profile ${{ matrix.profile }}'
- uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: nextest
version: 0.9.103
- name: tests
- name: cargo test
id: test
# Tests take too long for release builds to run them on every PR.
# `cargo test` takes too long for release builds to run them on every PR
if: ${{ matrix.profile != 'release' }}
continue-on-error: true
run: cargo nextest run --all-features --no-fail-fast --target ${{ matrix.target }}
run: cargo test --all-features --target ${{ matrix.target }} --profile ${{ matrix.profile }}
env:
RUST_BACKTRACE: 1
@@ -207,7 +171,7 @@ jobs:
# --- Gatherer job that you mark as the ONLY required status -----------------
results:
name: CI results (required)
needs: [changed, general, cargo_shear, lint_build_test]
needs: [changed, general, lint_build_test]
if: always()
runs-on: ubuntu-24.04
steps:
@@ -215,7 +179,6 @@ jobs:
shell: bash
run: |
echo "general: ${{ needs.general.result }}"
echo "shear : ${{ needs.cargo_shear.result }}"
echo "matrix : ${{ needs.lint_build_test.result }}"
# If nothing relevant changed (PR touching only root README, etc.),
@@ -227,5 +190,4 @@ jobs:
# Otherwise require the jobs to have succeeded
[[ '${{ 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

@@ -72,12 +72,10 @@ jobs:
target: aarch64-unknown-linux-gnu
- runner: windows-latest
target: x86_64-pc-windows-msvc
- runner: windows-11-arm
target: aarch64-pc-windows-msvc
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
with:
targets: ${{ matrix.target }}
@@ -89,7 +87,7 @@ jobs:
~/.cargo/registry/cache/
~/.cargo/git/db/
${{ github.workspace }}/codex-rs/target/
key: cargo-${{ matrix.runner }}-${{ matrix.target }}-release-${{ hashFiles('**/Cargo.lock') }}
key: cargo-release-${{ matrix.runner }}-${{ matrix.target }}-release-${{ hashFiles('**/Cargo.lock') }}
- if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
name: Install musl build tools
@@ -97,7 +95,7 @@ jobs:
sudo apt install -y musl-tools pkg-config
- name: Cargo build
run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
run: cargo build --target ${{ matrix.target }} --release --bin codex
- name: Stage artifacts
shell: bash
@@ -107,17 +105,10 @@ jobs:
if [[ "${{ 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' }}
name: Install zstd
shell: powershell
run: choco install -y zstandard
- name: Compress artifacts
shell: bash
run: |
@@ -169,14 +160,6 @@ 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: ${{ steps.npm_publish_settings.outputs.npm_tag }}
steps:
- name: Checkout repository
@@ -197,50 +180,21 @@ jobs:
version="${GITHUB_REF_NAME#rust-v}"
echo "name=${version}" >> $GITHUB_OUTPUT
- 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
# build_npm_package.py requires DotSlash when staging releases.
- uses: facebook/install-dotslash@v2
- name: Stage codex CLI npm package
- name: Stage npm package
env:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
TMP_DIR="${RUNNER_TEMP}/npm-stage"
./codex-cli/scripts/build_npm_package.py \
--package codex \
python3 codex-cli/scripts/stage_rust_release.py \
--release-version "${{ steps.release_name.outputs.name }}" \
--staging-dir "${TMP_DIR}" \
--pack-output "${GITHUB_WORKSPACE}/dist/npm/codex-npm-${{ steps.release_name.outputs.name }}.tgz"
- name: Stage responses API proxy npm package
env:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
TMP_DIR="${RUNNER_TEMP}/npm-stage-responses"
./codex-cli/scripts/build_npm_package.py \
--package codex-responses-api-proxy \
--release-version "${{ steps.release_name.outputs.name }}" \
--staging-dir "${TMP_DIR}" \
--pack-output "${GITHUB_WORKSPACE}/dist/npm/codex-responses-api-proxy-npm-${{ steps.release_name.outputs.name }}.tgz"
--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"
- name: Create GitHub Release
uses: softprops/action-gh-release@v2
@@ -258,85 +212,3 @@ 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
# 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-${VERSION}.tgz"
)
for tarball in "${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

View File

@@ -1,7 +1,3 @@
/codex-cli/dist
/codex-cli/node_modules
pnpm-lock.yaml
prompt.md
*_prompt.md
*_instructions.md

View File

@@ -1,11 +1,5 @@
{
"recommendations": [
"rust-lang.rust-analyzer",
"tamasfe.even-better-toml",
"vadimcn.vscode-lldb",
// Useful if touching files in .github/workflows, though most
// contributors will not be doing that?
// "github.vscode-github-actions",
]
}

View File

@@ -2,17 +2,15 @@
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`
- Crate names are prefixed with `codex-`. For examole, 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.
Run `just fmt` (in `codex-rs` directory) automatically after making Rust code changes; do not ask for approval to run it. Before finalizing a change to `codex-rs`, run `just fix -p <project>` (in `codex-rs` directory) to fix any linter issues in the code. Prefer scoping with `-p` to avoid slow workspacewide Clippy builds; only run `just fix` without `-p` if you changed shared crates. Additionally, run the tests:
Before finalizing a change to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix` (in `codex-rs` directory) to fix any linter issues in the code. Additionally, run the tests:
1. Run the test for the specific project that was changed. For example, if changes were made in `codex-rs/tui`, run `cargo test -p codex-tui`.
2. Once those pass, if any changes were made in common, core, or protocol, run the complete test suite with `cargo test --all-features`.
When running interactively, ask the user before running `just fix` to finalize. `just fmt` does not require approval. project-specific or individual tests can be run without asking the user, but do ask the user before running the complete test suite.
## TUI style conventions
@@ -27,26 +25,7 @@ See `codex-rs/tui/styles.md`.
- Example: patch summary file lines
- Desired: vec![" └ ".into(), "M".red(), " ".dim(), "tui/src/app.rs".dim()]
### TUI Styling (ratatui)
- Prefer Stylize helpers: use "text".dim(), .bold(), .cyan(), .italic(), .underlined() instead of manual Style where possible.
- Prefer simple conversions: use "text".into() for spans and vec![…].into() for lines; when inference is ambiguous (e.g., Paragraph::new/Cell::from), use Line::from(spans) or Span::from(text).
- Computed styles: if the Style is computed at runtime, using `Span::styled` is OK (`Span::from(text).set_style(style)` is also acceptable).
- Avoid hardcoded white: do not use `.white()`; prefer the default foreground (no color).
- Chaining: combine helpers by chaining for readability (e.g., url.cyan().underlined()).
- Single items: prefer "text".into(); use Line::from(text) or Span::from(text) only when the target type isnt obvious from context, or when using .into() would require extra type annotations.
- Building lines: use vec![…].into() to construct a Line when the target type is obvious and no extra type annotations are needed; otherwise use Line::from(vec![…]).
- Avoid churn: dont refactor between equivalent forms (Span::styled ↔ set_style, Line::from ↔ .into()) without a clear readability or functional gain; follow filelocal conventions and do not introduce type annotations solely to satisfy .into().
- Compactness: prefer the form that stays on one line after rustfmt; if only one of Line::from(vec![…]) or vec![…].into() avoids wrapping, choose that. If both wrap, pick the one with fewer wrapped lines.
### Text wrapping
- Always use textwrap::wrap to wrap plain strings.
- If you have a ratatui Line and you want to wrap it, use the helpers in tui/src/wrapping.rs, e.g. word_wrap_lines / word_wrap_line.
- If you need to indent wrapped lines, use the initial_indent / subsequent_indent options from RtOptions if you can, rather than writing custom logic.
- If you have a list of lines and you need to prefix them all with some prefix (optionally different on the first vs subsequent lines), use the `prefix_lines` helper from line_utils.
## Tests
### Snapshot tests
## Snapshot tests
This repo uses snapshot tests (via `insta`), especially in `codex-rs/tui`, to validate rendered output. When UI or text output changes intentionally, update the snapshots as follows:
@@ -61,7 +40,3 @@ This repo uses snapshot tests (via `insta`), especially in `codex-rs/tui`, to va
If you dont have the tool:
- `cargo install cargo-insta`
### Test assertions
- Tests should use pretty_assertions::assert_eq for clearer diffs. Import this at the top of the test module if it isn't already.

View File

@@ -1 +1,211 @@
The changelog can be found on the [releases page](https://github.com/openai/codex/releases)
# Changelog
You can install any of these versions: `npm install -g codex@version`
## `0.1.2505172129`
### 🪲 Bug Fixes
- Add node version check (#1007)
- Persist token after refresh (#1006)
## `0.1.2505171619`
- `codex --login` + `codex --free` (#998)
## `0.1.2505161800`
- Sign in with chatgpt credits (#974)
- Add support for OpenAI tool type, local_shell (#961)
## `0.1.2505161243`
- Sign in with chatgpt (#963)
- Session history viewer (#912)
- Apply patch issue when using different cwd (#942)
- Diff command for filenames with special characters (#954)
## `0.1.2505160811`
- `codex-mini-latest` (#951)
## `0.1.2505140839`
### 🪲 Bug Fixes
- Gpt-4.1 apply_patch handling (#930)
- Add support for fileOpener in config.json (#911)
- Patch in #366 and #367 for marked-terminal (#916)
- Remember to set lastIndex = 0 on shared RegExp (#918)
- Always load version from package.json at runtime (#909)
- Tweak the label for citations for better rendering (#919)
- Tighten up some logic around session timestamps and ids (#922)
- Change EventMsg enum so every variant takes a single struct (#925)
- Reasoning default to medium, show workdir when supplied (#931)
- Test_dev_null_write() was not using echo as intended (#923)
## `0.1.2504301751`
### 🚀 Features
- User config api key (#569)
- `@mention` files in codex (#701)
- Add `--reasoning` CLI flag (#314)
- Lower default retry wait time and increase number of tries (#720)
- Add common package registries domains to allowed-domains list (#414)
### 🪲 Bug Fixes
- Insufficient quota message (#758)
- Input keyboard shortcut opt+delete (#685)
- `/diff` should include untracked files (#686)
- Only allow running without sandbox if explicitly marked in safe container (#699)
- Tighten up check for /usr/bin/sandbox-exec (#710)
- Check if sandbox-exec is available (#696)
- Duplicate messages in quiet mode (#680)
## `0.1.2504251709`
### 🚀 Features
- Add openai model info configuration (#551)
- Added provider to run quiet mode function (#571)
- Create parent directories when creating new files (#552)
- Print bug report URL in terminal instead of opening browser (#510) (#528)
- Add support for custom provider configuration in the user config (#537)
- Add support for OpenAI-Organization and OpenAI-Project headers (#626)
- Add specific instructions for creating API keys in error msg (#581)
- Enhance toCodePoints to prevent potential unicode 14 errors (#615)
- More native keyboard navigation in multiline editor (#655)
- Display error on selection of invalid model (#594)
### 🪲 Bug Fixes
- Model selection (#643)
- Nits in apply patch (#640)
- Input keyboard shortcuts (#676)
- `apply_patch` unicode characters (#625)
- Don't clear turn input before retries (#611)
- More loosely match context for apply_patch (#610)
- Update bug report template - there is no --revision flag (#614)
- Remove outdated copy of text input and external editor feature (#670)
- Remove unreachable "disableResponseStorage" logic flow introduced in #543 (#573)
- Non-openai mode - fix for gemini content: null, fix 429 to throw before stream (#563)
- Only allow going up in history when not already in history if input is empty (#654)
- Do not grant "node" user sudo access when using run_in_container.sh (#627)
- Update scripts/build_container.sh to use pnpm instead of npm (#631)
- Update lint-staged config to use pnpm --filter (#582)
- Non-openai mode - don't default temp and top_p (#572)
- Fix error catching when checking for updates (#597)
- Close stdin when running an exec tool call (#636)
## `0.1.2504221401`
### 🚀 Features
- Show actionable errors when api keys are missing (#523)
- Add CLI `--version` flag (#492)
### 🪲 Bug Fixes
- Agent loop for ZDR (`disableResponseStorage`) (#543)
- Fix relative `workdir` check for `apply_patch` (#556)
- Minimal mid-stream #429 retry loop using existing back-off (#506)
- Inconsistent usage of base URL and API key (#507)
- Remove requirement for api key for ollama (#546)
- Support `[provider]_BASE_URL` (#542)
## `0.1.2504220136`
### 🚀 Features
- Add support for ZDR orgs (#481)
- Include fractional portion of chunk that exceeds stdout/stderr limit (#497)
## `0.1.2504211509`
### 🚀 Features
- Support multiple providers via Responses-Completion transformation (#247)
- Add user-defined safe commands configuration and approval logic #380 (#386)
- Allow switching approval modes when prompted to approve an edit/command (#400)
- Add support for `/diff` command autocomplete in TerminalChatInput (#431)
- Auto-open model selector if user selects deprecated model (#427)
- Read approvalMode from config file (#298)
- `/diff` command to view git diff (#426)
- Tab completions for file paths (#279)
- Add /command autocomplete (#317)
- Allow multi-line input (#438)
### 🪲 Bug Fixes
- `full-auto` support in quiet mode (#374)
- Enable shell option for child process execution (#391)
- Configure husky and lint-staged for pnpm monorepo (#384)
- Command pipe execution by improving shell detection (#437)
- Name of the file not matching the name of the component (#354)
- Allow proper exit from new Switch approval mode dialog (#453)
- Ensure /clear resets context and exclude system messages from approximateTokenUsed count (#443)
- `/clear` now clears terminal screen and resets context left indicator (#425)
- Correct fish completion function name in CLI script (#485)
- Auto-open model-selector when model is not found (#448)
- Remove unnecessary isLoggingEnabled() checks (#420)
- Improve test reliability for `raw-exec` (#434)
- Unintended tear down of agent loop (#483)
- Remove extraneous type casts (#462)
## `0.1.2504181820`
### 🚀 Features
- Add `/bug` report command (#312)
- Notify when a newer version is available (#333)
### 🪲 Bug Fixes
- Update context left display logic in TerminalChatInput component (#307)
- Improper spawn of sh on Windows Powershell (#318)
- `/bug` report command, thinking indicator (#381)
- Include pnpm lock file (#377)
## `0.1.2504172351`
### 🚀 Features
- Add Nix flake for reproducible development environments (#225)
### 🪲 Bug Fixes
- Handle invalid commands (#304)
- Raw-exec-process-group.test improve reliability and error handling (#280)
- Canonicalize the writeable paths used in seatbelt policy (#275)
## `0.1.2504172304`
### 🚀 Features
- Add shell completion subcommand (#138)
- Add command history persistence (#152)
- Shell command explanation option (#173)
- Support bun fallback runtime for codex CLI (#282)
- Add notifications for MacOS using Applescript (#160)
- Enhance image path detection in input processing (#189)
- `--config`/`-c` flag to open global instructions in nvim (#158)
- Update position of cursor when navigating input history with arrow keys to the end of the text (#255)
### 🪲 Bug Fixes
- Correct word deletion logic for trailing spaces (Ctrl+Backspace) (#131)
- Improve Windows compatibility for CLI commands and sandbox (#261)
- Correct typos in thinking texts (transcendent & parroting) (#108)
- Add empty vite config file to prevent resolving to parent (#273)
- Update regex to better match the retry error messages (#266)
- Add missing "as" in prompt prefix in agent loop (#186)
- Allow continuing after interrupting assistant (#178)
- Standardize filename to kebab-case 🐍➡️🥙 (#302)
- Small update to bug report template (#288)
- Duplicated message on model change (#276)
- Typos in prompts and comments (#195)
- Check workdir before spawn (#221)
<!-- generated - do not edit -->

681
README.md
View File

@@ -1,31 +1,77 @@
<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>
</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"><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">
<img src="./.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" />
<img src="./.github/codex-cli-splash.png" alt="Codex CLI splash" width="50%" />
</p>
---
<details>
<summary><strong>Table of contents</strong></summary>
<!-- Begin ToC -->
- [Quickstart](#quickstart)
- [Installing and running Codex CLI](#installing-and-running-codex-cli)
- [Using Codex with your ChatGPT plan](#using-codex-with-your-chatgpt-plan)
- [Connecting on a "Headless" Machine](#connecting-on-a-headless-machine)
- [Authenticate locally and copy your credentials to the "headless" machine](#authenticate-locally-and-copy-your-credentials-to-the-headless-machine)
- [Connecting through VPS or remote](#connecting-through-vps-or-remote)
- [Usage-based billing alternative: Use an OpenAI API key](#usage-based-billing-alternative-use-an-openai-api-key)
- [Forcing a specific auth method (advanced)](#forcing-a-specific-auth-method-advanced)
- [Choosing Codex's level of autonomy](#choosing-codexs-level-of-autonomy)
- [**1. Read/write**](#1-readwrite)
- [**2. Read-only**](#2-read-only)
- [**3. Advanced configuration**](#3-advanced-configuration)
- [Can I run without ANY approvals?](#can-i-run-without-any-approvals)
- [Fine-tuning in `config.toml`](#fine-tuning-in-configtoml)
- [Example prompts](#example-prompts)
- [Running with a prompt as input](#running-with-a-prompt-as-input)
- [Using Open Source Models](#using-open-source-models)
- [Platform sandboxing details](#platform-sandboxing-details)
- [Experimental technology disclaimer](#experimental-technology-disclaimer)
- [System requirements](#system-requirements)
- [CLI reference](#cli-reference)
- [Memory & project docs](#memory--project-docs)
- [Non-interactive / CI mode](#non-interactive--ci-mode)
- [Model Context Protocol (MCP)](#model-context-protocol-mcp)
- [Tracing / verbose logging](#tracing--verbose-logging)
- [DotSlash](#dotslash)
- [Configuration](#configuration)
- [FAQ](#faq)
- [Zero data retention (ZDR) usage](#zero-data-retention-zdr-usage)
- [Codex open source fund](#codex-open-source-fund)
- [Contributing](#contributing)
- [Development workflow](#development-workflow)
- [Writing high-impact code changes](#writing-high-impact-code-changes)
- [Opening a pull request](#opening-a-pull-request)
- [Review process](#review-process)
- [Community values](#community-values)
- [Getting help](#getting-help)
- [Contributor license agreement (CLA)](#contributor-license-agreement-cla)
- [Quick fixes](#quick-fixes)
- [Releasing `codex`](#releasing-codex)
- [Security & responsible AI](#security--responsible-ai)
- [License](#license)
<!-- End ToC -->
</details>
---
## Quickstart
### Installing and running Codex CLI
Install globally with your preferred package manager. If you use npm:
Install globally with your preferred package manager:
```shell
npm install -g @openai/codex
```
Alternatively, if you use Homebrew:
```shell
brew install codex
npm install -g @openai/codex # Alternatively: `brew install codex`
```
Then simply run `codex` to get started:
@@ -53,48 +99,597 @@ Each archive contains a single entry with the platform baked into the name (e.g.
### Using Codex with your ChatGPT plan
<p align="center">
<img src="./.github/codex-cli-login.png" alt="Codex CLI login" width="80%" />
<img src="./.github/codex-cli-login.png" alt="Codex CLI login" width="50%" />
</p>
Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan. [Learn more about what's included in your ChatGPT plan](https://help.openai.com/en/articles/11369540-codex-in-chatgpt).
Run `codex` and select **Sign in with ChatGPT**. You'll need a Plus, Pro, or Team ChatGPT account, and will get access to our latest models, including `gpt-5`, at no extra cost to your plan. (Enterprise is coming soon.)
You can also use Codex with an API key, but this requires [additional setup](./docs/authentication.md#usage-based-billing-alternative-use-an-openai-api-key). If you previously used an API key for usage-based billing, see the [migration steps](./docs/authentication.md#migrating-from-usage-based-billing-api-key). If you're having trouble with login, please comment on [this issue](https://github.com/openai/codex/issues/1243).
> Important: If you've used the Codex CLI before, follow these steps to migrate from usage-based billing with your API key:
>
> 1. Update the CLI and ensure `codex --version` is `0.20.0` or later
> 2. Delete `~/.codex/auth.json` (this should be `C:\Users\USERNAME\.codex\auth.json` on Windows)
> 3. Run `codex login` again
### Model Context Protocol (MCP)
If you encounter problems with the login flow, please comment on [this issue](https://github.com/openai/codex/issues/1243).
Codex CLI supports [MCP servers](./docs/advanced.md#model-context-protocol-mcp). Enable by adding an `mcp_servers` section to your `~/.codex/config.toml`.
### Connecting on a "Headless" Machine
Today, the login process entails running a server on `localhost:1455`. If you are on a "headless" server, such as a Docker container or are `ssh`'d into a remote machine, loading `localhost:1455` in the browser on your local machine will not automatically connect to the webserver running on the _headless_ machine, so you must use one of the following workarounds:
### Configuration
#### Authenticate locally and copy your credentials to the "headless" machine
Codex CLI supports a rich set of configuration options, with preferences stored in `~/.codex/config.toml`. For full configuration options, see [Configuration](./docs/config.md).
The easiest solution is likely to run through the `codex login` process on your local machine such that `localhost:1455` _is_ accessible in your web browser. When you complete the authentication process, an `auth.json` file should be available at `$CODEX_HOME/auth.json` (on Mac/Linux, `$CODEX_HOME` defaults to `~/.codex` whereas on Windows, it defaults to `%USERPROFILE%\.codex`).
Because the `auth.json` file is not tied to a specific host, once you complete the authentication flow locally, you can copy the `$CODEX_HOME/auth.json` file to the headless machine and then `codex` should "just work" on that machine. Note to copy a file to a Docker container, you can do:
```shell
# substitute MY_CONTAINER with the name or id of your Docker container:
CONTAINER_HOME=$(docker exec MY_CONTAINER printenv HOME)
docker exec MY_CONTAINER mkdir -p "$CONTAINER_HOME/.codex"
docker cp auth.json MY_CONTAINER:"$CONTAINER_HOME/.codex/auth.json"
```
whereas if you are `ssh`'d into a remote machine, you likely want to use [`scp`](https://en.wikipedia.org/wiki/Secure_copy_protocol):
```shell
ssh user@remote 'mkdir -p ~/.codex'
scp ~/.codex/auth.json user@remote:~/.codex/auth.json
```
or try this one-liner:
```shell
ssh user@remote 'mkdir -p ~/.codex && cat > ~/.codex/auth.json' < ~/.codex/auth.json
```
#### Connecting through VPS or remote
If you run Codex on a remote machine (VPS/server) without a local browser, the login helper starts a server on `localhost:1455` on the remote host. To complete login in your local browser, forward that port to your machine before starting the login flow:
```bash
# From your local machine
ssh -L 1455:localhost:1455 <user>@<remote-host>
```
Then, in that SSH session, run `codex` and select "Sign in with ChatGPT". When prompted, open the printed URL (it will be `http://localhost:1455/...`) in your local browser. The traffic will be tunneled to the remote server.
### Usage-based billing alternative: Use an OpenAI API key
If you prefer to pay-as-you-go, you can still authenticate with your OpenAI API key by setting it as an environment variable:
```shell
export OPENAI_API_KEY="your-api-key-here"
```
Notes:
- This command only sets the key for your current terminal session, which we recommend. To set it for all future sessions, you can also add the `export` line to your shell's configuration file (e.g., `~/.zshrc`).
- If you have signed in with ChatGPT, Codex will default to using your ChatGPT credits. If you wish to use your API key, use the `/logout` command to clear your ChatGPT authentication.
#### Forcing a specific auth method (advanced)
You can explicitly choose which authentication Codex should prefer when both are available.
- To always use your API key (even when ChatGPT auth exists), set:
```toml
# ~/.codex/config.toml
preferred_auth_method = "apikey"
```
Or override ad-hoc via CLI:
```bash
codex --config preferred_auth_method="apikey"
```
- To prefer ChatGPT auth (default), set:
```toml
# ~/.codex/config.toml
preferred_auth_method = "chatgpt"
```
Notes:
- When `preferred_auth_method = "apikey"` and an API key is available, the login screen is skipped.
- When `preferred_auth_method = "chatgpt"` (default), Codex prefers ChatGPT auth if present; if only an API key is present, it will use the API key. Certain account types may also require API-key mode.
### Choosing Codex's level of autonomy
We always recommend running Codex in its default sandbox that gives you strong guardrails around what the agent can do. The default sandbox prevents it from editing files outside its workspace, or from accessing the network.
When you launch Codex in a new folder, it detects whether the folder is version controlled and recommends one of two levels of autonomy:
#### **1. Read/write**
- Codex can run commands and write files in the workspace without approval.
- To write files in other folders, access network, update git or perform other actions protected by the sandbox, Codex will need your permission.
- By default, the workspace includes the current directory, as well as temporary directories like `/tmp`. You can see what directories are in the workspace with the `/status` command. See the docs for how to customize this behavior.
- Advanced: You can manually specify this configuration by running `codex --sandbox workspace-write --ask-for-approval on-request`
- This is the recommended default for version-controlled folders.
#### **2. Read-only**
- Codex can run read-only commands without approval.
- To edit files, access network, or perform other actions protected by the sandbox, Codex will need your permission.
- Advanced: You can manually specify this configuration by running `codex --sandbox read-only --ask-for-approval on-request`
- This is the recommended default non-version-controlled folders.
#### **3. Advanced configuration**
Codex gives you fine-grained control over the sandbox with the `--sandbox` option, and over when it requests approval with the `--ask-for-approval` option. Run `codex help` for more on these options.
#### Can I run without ANY approvals?
Yes, run codex non-interactively with `--ask-for-approval never`. This option works with all `--sandbox` options, so you still have full control over Codex's level of autonomy. It will make its best attempt with whatever contrainsts you provide. For example:
- Use `codex --ask-for-approval never --sandbox read-only` when you are running many agents to answer questions in parallel in the same workspace.
- Use `codex --ask-for-approval never --sandbox workspace-write` when you want the agent to non-interactively take time to produce the best outcome, with strong guardrails around its behavior.
- Use `codex --ask-for-approval never --sandbox danger-full-access` to dangerously give the agent full autonomy. Because this disables important safety mechanisms, we recommend against using this unless running Codex in an isolated environment.
#### Fine-tuning in `config.toml`
```toml
# approval mode
approval_policy = "untrusted"
sandbox_mode = "read-only"
# full-auto mode
approval_policy = "on-request"
sandbox_mode = "workspace-write"
# Optional: allow network in workspace-write mode
[sandbox_workspace_write]
network_access = true
```
You can also save presets as **profiles**:
```toml
[profiles.full_auto]
approval_policy = "on-request"
sandbox_mode = "workspace-write"
[profiles.readonly_quiet]
approval_policy = "never"
sandbox_mode = "read-only"
```
### Example prompts
Below are a few bite-size examples you can copy-paste. Replace the text in quotes with your own task. See the [prompting guide](https://github.com/openai/codex/blob/main/codex-cli/examples/prompting_guide.md) for more tips and usage patterns.
| ✨ | What you type | What happens |
| --- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| 1 | `codex "Refactor the Dashboard component to React Hooks"` | Codex rewrites the class component, runs `npm test`, and shows the diff. |
| 2 | `codex "Generate SQL migrations for adding a users table"` | Infers your ORM, creates migration files, and runs them in a sandboxed DB. |
| 3 | `codex "Write unit tests for utils/date.ts"` | Generates tests, executes them, and iterates until they pass. |
| 4 | `codex "Bulk-rename *.jpeg -> *.jpg with git mv"` | Safely renames files and updates imports/usages. |
| 5 | `codex "Explain what this regex does: ^(?=.*[A-Z]).{8,}$"` | Outputs a step-by-step human explanation. |
| 6 | `codex "Carefully review this repo, and propose 3 high impact well-scoped PRs"` | Suggests impactful PRs in the current codebase. |
| 7 | `codex "Look for vulnerabilities and create a security review report"` | Finds and explains security bugs. |
## Running with a prompt as input
You can also run Codex CLI with a prompt as input:
```shell
codex "explain this codebase to me"
```
```shell
codex --full-auto "create the fanciest todo-list app"
```
That's it - Codex will scaffold a file, run it inside a sandbox, install any
missing dependencies, and show you the live result. Approve the changes and
they'll be committed to your working directory.
## Using Open Source Models
<details>
<summary><strong>Use <code>--profile</code> to use other models</strong></summary>
Codex also allows you to use other providers that support the OpenAI Chat Completions (or Responses) API.
To do so, you must first define custom [providers](./config.md#model_providers) in `~/.codex/config.toml`. For example, the provider for a standard Ollama setup would be defined as follows:
```toml
[model_providers.ollama]
name = "Ollama"
base_url = "http://localhost:11434/v1"
```
The `base_url` will have `/chat/completions` appended to it to build the full URL for the request.
For providers that also require an `Authorization` header of the form `Bearer: SECRET`, an `env_key` can be specified, which indicates the environment variable to read to use as the value of `SECRET` when making a request:
```toml
[model_providers.openrouter]
name = "OpenRouter"
base_url = "https://openrouter.ai/api/v1"
env_key = "OPENROUTER_API_KEY"
```
Providers that speak the Responses API are also supported by adding `wire_api = "responses"` as part of the definition. Accessing OpenAI models via Azure is an example of such a provider, though it also requires specifying additional `query_params` that need to be appended to the request URL:
```toml
[model_providers.azure]
name = "Azure"
# Make sure you set the appropriate subdomain for this URL.
base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"
env_key = "AZURE_OPENAI_API_KEY" # Or "OPENAI_API_KEY", whichever you use.
# Newer versions appear to support the responses API, see https://github.com/openai/codex/pull/1321
query_params = { api-version = "2025-04-01-preview" }
wire_api = "responses"
```
Once you have defined a provider you wish to use, you can configure it as your default provider as follows:
```toml
model_provider = "azure"
```
> [!TIP]
> If you find yourself experimenting with a variety of models and providers, then you likely want to invest in defining a _profile_ for each configuration like so:
```toml
[profiles.o3]
model_provider = "azure"
model = "o3"
[profiles.mistral]
model_provider = "ollama"
model = "mistral"
```
This way, you can specify one command-line argument (.e.g., `--profile o3`, `--profile mistral`) to override multiple settings together.
</details>
Codex can run fully locally against an OpenAI-compatible OSS host (like Ollama) using the `--oss` flag:
- Interactive UI:
- codex --oss
- Non-interactive (programmatic) mode:
- echo "Refactor utils" | codex exec --oss
Model selection when using `--oss`:
- If you omit `-m/--model`, Codex defaults to -m gpt-oss:20b and will verify it exists locally (downloading if needed).
- To pick a different size, pass one of:
- -m "gpt-oss:20b"
- -m "gpt-oss:120b"
Point Codex at your own OSS host:
- By default, `--oss` talks to http://localhost:11434/v1.
- To use a different host, set one of these environment variables before running Codex:
- CODEX_OSS_BASE_URL, for example:
- CODEX_OSS_BASE_URL="http://my-ollama.example.com:11434/v1" codex --oss -m gpt-oss:20b
- or CODEX_OSS_PORT (when the host is localhost):
- CODEX_OSS_PORT=11434 codex --oss
Advanced: you can persist this in your config instead of environment variables by overriding the built-in `oss` provider in `~/.codex/config.toml`:
```toml
[model_providers.oss]
name = "Open Source"
base_url = "http://my-ollama.example.com:11434/v1"
```
---
### Docs & FAQ
### Platform sandboxing details
- [**Getting started**](./docs/getting-started.md)
- [CLI usage](./docs/getting-started.md#cli-usage)
- [Running with a prompt as input](./docs/getting-started.md#running-with-a-prompt-as-input)
- [Example prompts](./docs/getting-started.md#example-prompts)
- [Memory with AGENTS.md](./docs/getting-started.md#memory-with-agentsmd)
- [Configuration](./docs/config.md)
- [**Sandbox & approvals**](./docs/sandbox.md)
- [**Authentication**](./docs/authentication.md)
- [Auth methods](./docs/authentication.md#forcing-a-specific-auth-method-advanced)
- [Login on a "Headless" machine](./docs/authentication.md#connecting-on-a-headless-machine)
- [**Advanced**](./docs/advanced.md)
- [Non-interactive / CI mode](./docs/advanced.md#non-interactive--ci-mode)
- [Tracing / verbose logging](./docs/advanced.md#tracing--verbose-logging)
- [Model Context Protocol (MCP)](./docs/advanced.md#model-context-protocol-mcp)
- [**Zero data retention (ZDR)**](./docs/zdr.md)
- [**Contributing**](./docs/contributing.md)
- [**Install & build**](./docs/install.md)
- [System Requirements](./docs/install.md#system-requirements)
- [DotSlash](./docs/install.md#dotslash)
- [Build from source](./docs/install.md#build-from-source)
- [**FAQ**](./docs/faq.md)
- [**Open source fund**](./docs/open-source-fund.md)
The mechanism Codex uses to implement the sandbox policy depends on your OS:
- **macOS 12+** uses **Apple Seatbelt** and runs commands using `sandbox-exec` with a profile (`-p`) that corresponds to the `--sandbox` that was specified.
- **Linux** uses a combination of Landlock/seccomp APIs to enforce the `sandbox` configuration.
Note that when running Linux in a containerized environment such as Docker, sandboxing may not work if the host/container configuration does not support the necessary Landlock/seccomp APIs. In such cases, we recommend configuring your Docker container so that it provides the sandbox guarantees you are looking for and then running `codex` with `--sandbox danger-full-access` (or, more simply, the `--dangerously-bypass-approvals-and-sandbox` flag) within your container.
---
## Experimental technology disclaimer
Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. We're building it in the open with the community and welcome:
- Bug reports
- Feature requests
- Pull requests
- Good vibes
Help us improve by filing issues or submitting PRs (see the section below for how to contribute)!
---
## System requirements
| Requirement | Details |
| --------------------------- | --------------------------------------------------------------- |
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 **via WSL2** |
| Git (optional, recommended) | 2.23+ for built-in PR helpers |
| RAM | 4-GB minimum (8-GB recommended) |
---
## CLI reference
| Command | Purpose | Example |
| ------------------ | ---------------------------------- | ------------------------------- |
| `codex` | Interactive TUI | `codex` |
| `codex "..."` | Initial prompt for interactive TUI | `codex "fix lint errors"` |
| `codex exec "..."` | Non-interactive "automation mode" | `codex exec "explain utils.ts"` |
Key flags: `--model/-m`, `--ask-for-approval/-a`.
---
## Memory & project docs
You can give Codex extra instructions and guidance using `AGENTS.md` files. Codex looks for `AGENTS.md` files in the following places, and merges them top-down:
1. `~/.codex/AGENTS.md` - personal global guidance
2. `AGENTS.md` at repo root - shared project notes
3. `AGENTS.md` in the current working directory - sub-folder/feature specifics
---
## Non-interactive / CI mode
Run Codex head-less in pipelines. Example GitHub Action step:
```yaml
- name: Update changelog via Codex
run: |
npm install -g @openai/codex
export OPENAI_API_KEY="${{ secrets.OPENAI_KEY }}"
codex exec --full-auto "update CHANGELOG for next release"
```
## Model Context Protocol (MCP)
The Codex CLI can be configured to leverage MCP servers by defining an [`mcp_servers`](./codex-rs/config.md#mcp_servers) section in `~/.codex/config.toml`. It is intended to mirror how tools such as Claude and Cursor define `mcpServers` in their respective JSON config files, though the Codex format is slightly different since it uses TOML rather than JSON, e.g.:
```toml
# IMPORTANT: the top-level key is `mcp_servers` rather than `mcpServers`.
[mcp_servers.server-name]
command = "npx"
args = ["-y", "mcp-server"]
env = { "API_KEY" = "value" }
```
> [!TIP]
> It is somewhat experimental, but the Codex CLI can also be run as an MCP _server_ via `codex mcp`. If you launch it with an MCP client such as `npx @modelcontextprotocol/inspector codex mcp` and send it a `tools/list` request, you will see that there is only one tool, `codex`, that accepts a grab-bag of inputs, including a catch-all `config` map for anything you might want to override. Feel free to play around with it and provide feedback via GitHub issues.
## Tracing / verbose logging
Because Codex is written in Rust, it honors the `RUST_LOG` environment variable to configure its logging behavior.
The TUI defaults to `RUST_LOG=codex_core=info,codex_tui=info` and log messages are written to `~/.codex/log/codex-tui.log`, so you can leave the following running in a separate terminal to monitor log messages as they are written:
```
tail -F ~/.codex/log/codex-tui.log
```
By comparison, the non-interactive mode (`codex exec`) defaults to `RUST_LOG=error`, but messages are printed inline, so there is no need to monitor a separate file.
See the Rust documentation on [`RUST_LOG`](https://docs.rs/env_logger/latest/env_logger/#enabling-logging) for more information on the configuration options.
---
### DotSlash
The GitHub Release also contains a [DotSlash](https://dotslash-cli.com/) file for the Codex CLI named `codex`. Using a DotSlash file makes it possible to make a lightweight commit to source control to ensure all contributors use the same version of an executable, regardless of what platform they use for development.
</details>
<details>
<summary><strong>Build from source</strong></summary>
```bash
# Clone the repository and navigate to the root of the Cargo workspace.
git clone https://github.com/openai/codex.git
cd codex/codex-rs
# Install the Rust toolchain, if necessary.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
source "$HOME/.cargo/env"
rustup component add rustfmt
rustup component add clippy
# Build Codex.
cargo build
# Launch the TUI with a sample prompt.
cargo run --bin codex -- "explain this codebase to me"
# After making changes, ensure the code is clean.
cargo fmt -- --config imports_granularity=Item
cargo clippy --tests
# Run the tests.
cargo test
```
</details>
---
## Configuration
Codex supports a rich set of configuration options documented in [`codex-rs/config.md`](./codex-rs/config.md).
By default, Codex loads its configuration from `~/.codex/config.toml`.
Though `--config` can be used to set/override ad-hoc config values for individual invocations of `codex`.
---
## FAQ
<details>
<summary>OpenAI released a model called Codex in 2021 - is this related?</summary>
In 2021, OpenAI released Codex, an AI system designed to generate code from natural language prompts. That original Codex model was deprecated as of March 2023 and is separate from the CLI tool.
</details>
<details>
<summary>Which models are supported?</summary>
Any model available with [Responses API](https://platform.openai.com/docs/api-reference/responses). The default is `o4-mini`, but pass `--model gpt-4.1` or set `model: gpt-4.1` in your config file to override.
</details>
<details>
<summary>Why does <code>o3</code> or <code>o4-mini</code> not work for me?</summary>
It's possible that your [API account needs to be verified](https://help.openai.com/en/articles/10910291-api-organization-verification) in order to start streaming responses and seeing chain of thought summaries from the API. If you're still running into issues, please let us know!
</details>
<details>
<summary>How do I stop Codex from editing my files?</summary>
Codex runs model-generated commands in a sandbox. If a proposed command or file change doesn't look right, you can simply type **n** to deny the command or give the model feedback.
</details>
<details>
<summary>Does it work on Windows?</summary>
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex has been tested on macOS and Linux with Node 22.
</details>
---
## Zero data retention (ZDR) usage
Codex CLI **does** support OpenAI organizations with [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) enabled. If your OpenAI organization has Zero Data Retention enabled and you still encounter errors such as:
```
OpenAI rejected the request. Error details: Status: 400, Code: unsupported_parameter, Type: invalid_request_error, Message: 400 Previous response cannot be used for this organization due to Zero Data Retention.
```
Ensure you are running `codex` with `--config disable_response_storage=true` or add this line to `~/.codex/config.toml` to avoid specifying the command line option each time:
```toml
disable_response_storage = true
```
See [the configuration documentation on `disable_response_storage`](./codex-rs/config.md#disable_response_storage) for details.
---
## Codex open source fund
We're excited to launch a **$1 million initiative** supporting open source projects that use Codex CLI and other OpenAI models.
- Grants are awarded up to **$25,000** API credits.
- Applications are reviewed **on a rolling basis**.
**Interested? [Apply here](https://openai.com/form/codex-open-source-fund/).**
---
## Contributing
This project is under active development and the code will likely change pretty significantly.
**At the moment, we only plan to prioritize reviewing external contributions for bugs or security fixes.**
If you want to add a new feature or change the behavior of an existing one, please open an issue proposing the feature and get approval from an OpenAI team member before spending time building it.
**New contributions that don't go through this process may be closed** if they aren't aligned with our current roadmap or conflict with other priorities/upcoming features.
### Development workflow
- Create a _topic branch_ from `main` - e.g. `feat/interactive-prompt`.
- Keep your changes focused. Multiple unrelated fixes should be opened as separate PRs.
- Following the [development setup](#development-workflow) instructions above, ensure your change is free of lint warnings and test failures.
### Writing high-impact code changes
1. **Start with an issue.** Open a new one or comment on an existing discussion so we can agree on the solution before code is written.
2. **Add or update tests.** Every new feature or bug-fix should come with test coverage that fails before your change and passes afterwards. 100% coverage is not required, but aim for meaningful assertions.
3. **Document behaviour.** If your change affects user-facing behaviour, update the README, inline help (`codex --help`), or relevant example projects.
4. **Keep commits atomic.** Each commit should compile and the tests should pass. This makes reviews and potential rollbacks easier.
### Opening a pull request
- Fill in the PR template (or include similar information) - **What? Why? How?**
- Run **all** checks locally (`cargo test && cargo clippy --tests && cargo fmt -- --config imports_granularity=Item`). CI failures that could have been caught locally slow down the process.
- Make sure your branch is up-to-date with `main` and that you have resolved merge conflicts.
- Mark the PR as **Ready for review** only when you believe it is in a merge-able state.
### Review process
1. One maintainer will be assigned as a primary reviewer.
2. If your PR adds a new feature that was not previously discussed and approved, we may choose to close your PR (see [Contributing](#contributing)).
3. We may ask for changes - please do not take this personally. We value the work, but we also value consistency and long-term maintainability.
5. When there is consensus that the PR meets the bar, a maintainer will squash-and-merge.
### Community values
- **Be kind and inclusive.** Treat others with respect; we follow the [Contributor Covenant](https://www.contributor-covenant.org/).
- **Assume good intent.** Written communication is hard - err on the side of generosity.
- **Teach & learn.** If you spot something confusing, open an issue or PR with improvements.
### Getting help
If you run into problems setting up the project, would like feedback on an idea, or just want to say _hi_ - please open a Discussion or jump into the relevant issue. We are happy to help.
Together we can make Codex CLI an incredible tool. **Happy hacking!** :rocket:
### Contributor license agreement (CLA)
All contributors **must** accept the CLA. The process is lightweight:
1. Open your pull request.
2. Paste the following comment (or reply `recheck` if you've signed before):
```text
I have read the CLA Document and I hereby sign the CLA
```
3. The CLA-Assistant bot records your signature in the repo and marks the status check as passed.
No special Git commands, email attachments, or commit footers required.
#### Quick fixes
| Scenario | Command |
| ----------------- | ------------------------------------------------ |
| Amend last commit | `git commit --amend -s --no-edit && git push -f` |
The **DCO check** blocks merges until every commit in the PR carries the footer (with squash this is just the one).
### Releasing `codex`
_For admins only._
Make sure you are on `main` and have no local changes. Then run:
```shell
VERSION=0.2.0 # Can also be 0.2.0-alpha.1 or any valid Rust version.
./codex-rs/scripts/create_github_release.sh "$VERSION"
```
This will make a local commit on top of `main` with `version` set to `$VERSION` in `codex-rs/Cargo.toml` (note that on `main`, we leave the version as `version = "0.0.0"`).
This will push the commit using the tag `rust-v${VERSION}`, which in turn kicks off [the release workflow](.github/workflows/rust-release.yml). This will create a new GitHub Release named `$VERSION`.
If everything looks good in the generated GitHub Release, uncheck the **pre-release** box so it is the latest release.
Create a PR to update [`Formula/c/codex.rb`](https://github.com/Homebrew/homebrew-core/blob/main/Formula/c/codex.rb) on Homebrew.
---
## Security & responsible AI
Have you discovered a vulnerability or have concerns about model output? Please e-mail **security@openai.com** and we will respond promptly.
---

View File

@@ -1 +1,7 @@
/vendor/
# Added by ./scripts/install_native_deps.sh
/bin/codex-aarch64-apple-darwin
/bin/codex-aarch64-unknown-linux-musl
/bin/codex-linux-sandbox-arm64
/bin/codex-linux-sandbox-x64
/bin/codex-x86_64-apple-darwin
/bin/codex-x86_64-unknown-linux-musl

View File

@@ -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 | **16 or newer** (Node 20 LTS recommended) |
| Node.js | **22 or newer** (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 is regularly tested on macOS and Linux with Node 20+, and also supports Node 16.
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex has been tested on macOS and Linux with Node 22.
</details>

View File

@@ -1,8 +1,6 @@
#!/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";
@@ -42,11 +40,10 @@ switch (platform) {
case "win32":
switch (arch) {
case "x64":
targetTriple = "x86_64-pc-windows-msvc";
targetTriple = "x86_64-pc-windows-msvc.exe";
break;
case "arm64":
targetTriple = "aarch64-pc-windows-msvc";
break;
// We do not build this today, fall through...
default:
break;
}
@@ -59,16 +56,31 @@ if (!targetTriple) {
throw new Error(`Unsupported platform: ${platform} (${arch})`);
}
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);
const binaryPath = path.join(__dirname, "..", "bin", `codex-${targetTriple}`);
// Use an asynchronous spawn instead of spawnSync so that Node is able to
// respond to signals (e.g. Ctrl-C / SIGINT) while the native binary is
// executing. This allows us to forward those signals to the child process
// and guarantees that when either the child terminates or the parent
// receives a fatal signal, both processes exit in a predictable manner.
const { spawn } = await import("child_process");
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" ? ";" : ":";
@@ -81,9 +93,9 @@ function getUpdatedPath(newDirs) {
}
const additionalDirs = [];
const pathDir = path.join(archRoot, "path");
if (existsSync(pathDir)) {
additionalDirs.push(pathDir);
const rgDir = await resolveRgDir();
if (rgDir) {
additionalDirs.push(rgDir);
}
const updatedPath = getUpdatedPath(additionalDirs);

View File

@@ -1,79 +0,0 @@
#!/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

@@ -2,16 +2,117 @@
"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": ">=16"
"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"
}
}
}

View File

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

View File

@@ -5,7 +5,5 @@ Run the following:
To build the 0.2.x or later version of the npm module, which runs the Rust version of the CLI, build it as follows:
```bash
./codex-cli/scripts/build_npm_package.py --release-version 0.6.0
./codex-cli/scripts/stage_rust_release.py --release-version 0.6.0
```
Note this will create `./codex-cli/vendor/` as a side-effect.

View File

@@ -1,307 +0,0 @@
#!/usr/bin/env python3
"""Stage and optionally package the @openai/codex npm module."""
import argparse
import json
import re
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"
GITHUB_REPO = "openai/codex"
# The docs are not clear on what the expected value/format of
# workflow/workflowName is:
# https://cli.github.com/manual/gh_run_list
WORKFLOW_NAME = ".github/workflows/rust-release.yml"
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"),
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. When provided, the script also resolves the "
"matching rust-release workflow unless --workflow-url is supplied."
),
)
parser.add_argument(
"--workflow-url",
help="Optional GitHub Actions workflow run URL used to download native binaries.",
)
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.",
)
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)
workflow_url = args.workflow_url
resolved_head_sha: str | None = None
if not workflow_url:
if release_version:
workflow = resolve_release_workflow(version)
workflow_url = workflow["url"]
resolved_head_sha = workflow.get("headSha")
else:
workflow_url = resolve_latest_alpha_workflow_url()
elif release_version:
try:
workflow = resolve_release_workflow(version)
resolved_head_sha = workflow.get("headSha")
except Exception:
resolved_head_sha = None
if release_version and resolved_head_sha:
print(f"should `git checkout {resolved_head_sha}`")
if not workflow_url:
raise RuntimeError("Unable to determine workflow URL for native binaries.")
install_native_binaries(staging_dir, workflow_url, package)
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"
)
else:
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 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:
bin_dir = staging_dir / "bin"
bin_dir.mkdir(parents=True, exist_ok=True)
if package == "codex":
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":
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"
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
with open(staging_dir / "package.json", "w", encoding="utf-8") as out:
json.dump(package_json, out, indent=2)
out.write("\n")
def install_native_binaries(staging_dir: Path, workflow_url: str, package: str) -> None:
package_components = {
"codex": ["codex", "rg"],
"codex-responses-api-proxy": ["codex-responses-api-proxy"],
}
components = package_components.get(package)
if components is None:
raise RuntimeError(f"Unknown package '{package}'.")
cmd = ["./scripts/install_native_deps.py", "--workflow-url", workflow_url]
for component in components:
cmd.extend(["--component", component])
cmd.append(str(staging_dir))
subprocess.check_call(cmd, cwd=CODEX_CLI_ROOT)
def resolve_latest_alpha_workflow_url() -> str:
version = determine_latest_alpha_version()
workflow = resolve_release_workflow(version)
return workflow["url"]
def determine_latest_alpha_version() -> str:
releases = list_releases()
best_key: tuple[int, int, int, int] | None = None
best_version: str | None = None
pattern = re.compile(r"^rust-v(\d+)\.(\d+)\.(\d+)-alpha\.(\d+)$")
for release in releases:
tag = release.get("tag_name", "")
match = pattern.match(tag)
if not match:
continue
key = tuple(int(match.group(i)) for i in range(1, 5))
if best_key is None or key > best_key:
best_key = key
best_version = (
f"{match.group(1)}.{match.group(2)}.{match.group(3)}-alpha.{match.group(4)}"
)
if best_version is None:
raise RuntimeError("No alpha releases found when resolving workflow URL.")
return best_version
def list_releases() -> list[dict]:
stdout = subprocess.check_output(
["gh", "api", f"/repos/{GITHUB_REPO}/releases?per_page=100"],
text=True,
)
try:
releases = json.loads(stdout or "[]")
except json.JSONDecodeError as exc:
raise RuntimeError("Unable to parse releases JSON.") from exc
if not isinstance(releases, list):
raise RuntimeError("Unexpected response when listing releases.")
return releases
def resolve_release_workflow(version: str) -> dict:
stdout = subprocess.check_output(
[
"gh",
"run",
"list",
"--branch",
f"rust-v{version}",
"--json",
"workflowName,url,headSha",
"--workflow",
WORKFLOW_NAME,
"--jq",
"first(.[])",
],
text=True,
)
workflow = json.loads(stdout or "[]")
if not workflow:
raise RuntimeError(f"Unable to find rust-release workflow for version {version}.")
return workflow
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

@@ -1,383 +0,0 @@
#!/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

@@ -0,0 +1,91 @@
#!/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/16840150768" # rust-v0.20.0-alpha.2
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"
echo "Installed native dependencies into $BIN_DIR"

View File

@@ -0,0 +1,120 @@
#!/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

@@ -0,0 +1,70 @@
#!/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())

1840
codex-rs/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -7,22 +7,18 @@ members = [
"common",
"core",
"exec",
"exec-command-mcp",
"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",
"tui",
"utils/readiness",
]
resolver = "2"
@@ -34,175 +30,13 @@ version = "0.0.0"
# edition.
edition = "2024"
[workspace.dependencies]
# Internal
codex-ansi-escape = { path = "ansi-escape" }
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-process-hardening = { path = "process-hardening" }
codex-protocol = { path = "protocol" }
codex-protocol-ts = { path = "protocol-ts" }
codex-rmcp-client = { path = "rmcp-client" }
codex-tui = { path = "tui" }
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"
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 = "*"
os_info = "3.12.0"
owo-colors = "4.2.0"
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"
tracing = "0.1.41"
tracing-appender = "0.2.3"
tracing-subscriber = "0.3.20"
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

@@ -4,26 +4,26 @@ 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`:
Today, the easiest way to install Codex is via `npm`, though we plan to publish Codex to other package managers soon.
```shell
npm i -g @openai/codex
npm i -g @openai/codex@native
codex
```
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).
You can also download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
## What's new in the Rust CLI
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.
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!
### Config
Codex supports a rich set of configuration options. Note that the Rust CLI uses `config.toml` instead of `config.json`. See [`docs/config.md`](../docs/config.md) for details.
Codex supports a rich set of configuration options. Note that the Rust CLI uses `config.toml` instead of `config.json`. See [`config.md`](./config.md) for details.
### Model Context Protocol Support
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.
Codex CLI functions as an MCP client that can connect to MCP servers on startup. See the [`mcp_servers`](./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:
@@ -33,9 +33,9 @@ npx @modelcontextprotocol/inspector codex mcp
### 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.
You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](./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 programmatically/non-interactively
### `codex exec` to run Codex programmatially/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.
@@ -43,12 +43,6 @@ To run Codex non-interactively, run `codex exec PROMPT` (you can also pass the p
Typing `@` triggers a fuzzy-filename search over the workspace root. Use up/down to select among the results and Tab or Enter to replace the `@` with the selected path. You can use Esc to cancel the search.
### EscEsc to edit a previous message
When the chat composer is empty, press Esc to prime “backtrack” mode. Press Esc again to open a transcript preview highlighting the last user message; press Esc repeatedly to step to older user messages. Press Enter to confirm and Codex will fork the conversation from that point, trim the visible transcript accordingly, and prefill the composer with the selected user message so you can edit and resubmit it.
In the transcript preview, the footer shows an `Esc edit prev` hint while editing is active.
### `--cd`/`-C` flag
Sometimes it is not convenient to `cd` to the directory you want Codex to use as the "working root" before running Codex. Fortunately, `codex` supports a `--cd` option so you can specify whatever folder you want. You can confirm that Codex is honoring `--cd` by double-checking the **workdir** it reports in the TUI at the start of a new session.

View File

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

View File

@@ -9,7 +9,7 @@ use ratatui::text::Text;
pub fn ansi_escape_line(s: &str) -> Line<'static> {
let text = ansi_escape(s);
match text.lines.as_slice() {
[] => "".into(),
[] => Line::from(""),
[only] => only.clone(),
[first, rest @ ..] => {
tracing::warn!("ansi_escape_line: expected a single line, got {first:?} and {rest:?}");

View File

@@ -7,21 +7,16 @@ version = { workspace = true }
name = "codex_apply_patch"
path = "src/lib.rs"
[[bin]]
name = "apply_patch"
path = "src/main.rs"
[lints]
workspace = true
[dependencies]
anyhow = { workspace = true }
similar = { workspace = true }
thiserror = { workspace = true }
tree-sitter = { workspace = true }
tree-sitter-bash = { workspace = true }
anyhow = "1"
similar = "2.7.0"
thiserror = "2.0.12"
tree-sitter = "0.25.8"
tree-sitter-bash = "0.25.0"
[dev-dependencies]
assert_cmd = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
pretty_assertions = "1.4.1"
tempfile = "3.13.0"

View File

@@ -1,23 +1,17 @@
## `apply_patch`
To edit files, ALWAYS use the `shell` tool with `apply_patch` CLI. `apply_patch` effectively allows you to execute a diff/patch against a file, but the format of the diff specification is unique to this task, so pay careful attention to these instructions. To use the `apply_patch` CLI, you should call the shell tool with the following structure:
Use the `apply_patch` shell command to edit files.
Your patch language is a strippeddown, fileoriented diff format designed to be easy to parse and safe to apply. You can think of it as a highlevel envelope:
```bash
{"cmd": ["apply_patch", "<<'EOF'\\n*** Begin Patch\\n[YOUR_PATCH]\\n*** End Patch\\nEOF\\n"], "workdir": "..."}
```
*** Begin Patch
[ one or more file sections ]
*** End Patch
Where [YOUR_PATCH] is the actual content of your patch, specified in the following V4A diff format.
Within that envelope, you get a sequence of file operations.
You MUST include a header to specify the action you are taking.
Each operation starts with one of three headers:
*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
*** Delete File: <path> - remove an existing file. Nothing follows.
*** Update File: <path> - patch an existing file in place (optionally with a rename).
May be immediately followed by *** Move to: <new path> if you want to rename the file.
Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
Within a hunk each line starts with:
*** [ACTION] File: [path/to/file] -> ACTION can be one of Add, Update, or Delete.
For each snippet of code that needs to be changed, repeat the following:
[context_before] -> See below for further instructions on context.
- [old_code] -> Precede the old code with a minus sign.
+ [new_code] -> Precede the new, replacement code with a plus sign.
[context_after] -> See below for further instructions on context.
For instructions on [context_before] and [context_after]:
- By default, show 3 lines of code immediately above and 3 lines immediately below each change. If a change is within 3 lines of a previous change, do NOT duplicate the first changes [context_after] lines in the second changes [context_before] lines.
@@ -31,45 +25,16 @@ For instructions on [context_before] and [context_after]:
- If a code block is repeated so many times in a class or function such that even a single `@@` statement and 3 lines of context cannot uniquely identify the snippet of code, you can use multiple `@@` statements to jump to the right context. For instance:
@@ class BaseClass
@@ def method():
@@ def method():
[3 lines of pre-context]
- [old_code]
+ [new_code]
[3 lines of post-context]
The full grammar definition is below:
Patch := Begin { FileOp } End
Begin := "*** Begin Patch" NEWLINE
End := "*** End Patch" NEWLINE
FileOp := AddFile | DeleteFile | UpdateFile
AddFile := "*** Add File: " path NEWLINE { "+" line NEWLINE }
DeleteFile := "*** Delete File: " path NEWLINE
UpdateFile := "*** Update File: " path NEWLINE [ MoveTo ] { Hunk }
MoveTo := "*** Move to: " newPath NEWLINE
Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
HunkLine := (" " | "-" | "+") text NEWLINE
A full patch can combine several operations:
*** Begin Patch
*** Add File: hello.txt
+Hello world
*** Update File: src/app.py
*** Move to: src/main.py
@@ def greet():
-print("Hi")
+print("Hello, world!")
*** Delete File: obsolete.txt
*** End Patch
It is important to remember:
- You must include a header with your intended action (Add/Delete/Update)
- You must prefix new lines with `+` even when creating a new file
- File references can only be relative, NEVER ABSOLUTE.
You can invoke apply_patch like:
Note, then, that we do not use line numbers in this diff format, as the context is enough to uniquely identify code. An example of a message that you might pass as "input" to this function, in order to apply a patch, is shown below.
```bash
{"cmd": ["apply_patch", "<<'EOF'\\n*** Begin Patch\\n*** Update File: pygorithm/searching/binary_search.py\\n@@ class BaseClass\\n@@ def search():\\n- pass\\n+ raise NotImplementedError()\\n@@ class Subclass\\n@@ def search():\\n- pass\\n+ raise NotImplementedError()\\n*** End Patch\\nEOF\\n"], "workdir": "..."}
```
shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
```
File references can only be relative, NEVER ABSOLUTE. After the apply_patch command is run, it will always say "Done!", regardless of whether the patch was successfully applied or not. However, you can determine if there are issue and errors by looking at any warnings or logging lines printed BEFORE the "Done!" is output.

View File

@@ -1,12 +1,10 @@
mod parser;
mod seek_sequence;
mod standalone_executable;
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;
@@ -19,18 +17,11 @@ use similar::TextDiff;
use thiserror::Error;
use tree_sitter::LanguageError;
use tree_sitter::Parser;
use tree_sitter::Query;
use tree_sitter::QueryCursor;
use tree_sitter::StreamingIterator;
use tree_sitter_bash::LANGUAGE as BASH;
pub use standalone_executable::main;
/// Detailed instructions for gpt-4.1 on how to use the `apply_patch` tool.
pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_tool_instructions.md");
const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
#[derive(Debug, Error, PartialEq)]
pub enum ApplyPatchError {
#[error(transparent)]
@@ -40,11 +31,6 @@ 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 {
@@ -93,29 +79,25 @@ pub enum MaybeApplyPatch {
pub struct ApplyPatchArgs {
pub patch: String,
pub hunks: Vec<Hunk>,
pub workdir: Option<String>,
}
pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
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) {
Ok(mut source) => {
source.workdir = workdir;
MaybeApplyPatch::Body(source)
}
[bash, flag, script]
if bash == "bash"
&& flag == "-lc"
&& script.trim_start().starts_with("apply_patch") =>
{
match extract_heredoc_body_from_apply_patch_command(script) {
Ok(body) => match parse_patch(&body) {
Ok(source) => MaybeApplyPatch::Body(source),
Err(e) => MaybeApplyPatch::PatchParseError(e),
},
Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch) => {
MaybeApplyPatch::NotApplyPatch
}
Err(e) => MaybeApplyPatch::ShellParseError(e),
}
}
@@ -128,9 +110,7 @@ pub enum ApplyPatchFileChange {
Add {
content: String,
},
Delete {
content: String,
},
Delete,
Update {
unified_diff: String,
move_path: Option<PathBuf>,
@@ -214,63 +194,17 @@ 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,
hunks,
workdir,
}) => {
let effective_cwd = workdir
.as_ref()
.map(|dir| {
let path = Path::new(dir);
if path.is_absolute() {
path.to_path_buf()
} else {
cwd.join(path)
}
})
.unwrap_or_else(|| cwd.to_path_buf());
MaybeApplyPatch::Body(ApplyPatchArgs { patch, hunks }) => {
let mut changes = HashMap::new();
for hunk in hunks {
let path = hunk.resolve_path(&effective_cwd);
let path = hunk.resolve_path(cwd);
match hunk {
Hunk::AddFile { contents, .. } => {
changes.insert(path, ApplyPatchFileChange::Add { content: contents });
}
Hunk::DeleteFile { .. } => {
let content = match std::fs::read_to_string(&path) {
Ok(content) => content,
Err(e) => {
return MaybeApplyPatchVerified::CorrectnessError(
ApplyPatchError::IoError(IoError {
context: format!("Failed to read {}", path.display()),
source: e,
}),
);
}
};
changes.insert(path, ApplyPatchFileChange::Delete { content });
changes.insert(path, ApplyPatchFileChange::Delete);
}
Hunk::UpdateFile {
move_path, chunks, ..
@@ -298,7 +232,7 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
MaybeApplyPatchVerified::Body(ApplyPatchAction {
changes,
patch,
cwd: effective_cwd,
cwd: cwd.to_path_buf(),
})
}
MaybeApplyPatch::ShellParseError(e) => MaybeApplyPatchVerified::ShellParseError(e),
@@ -307,96 +241,30 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
}
}
/// Extract the heredoc body (and optional `cd` workdir) from a `bash -lc` script
/// that invokes the apply_patch tool using a heredoc.
/// Attempts to extract a heredoc_body object from a string bash command like:
/// Optimistically
///
/// Supported toplevel forms (must be the only toplevel statement):
/// - `apply_patch <<'EOF'\n...\nEOF`
/// - `cd <path> && apply_patch <<'EOF'\n...\nEOF`
/// ```bash
/// bash -lc 'apply_patch <<EOF\n***Begin Patch\n...EOF'
/// ```
///
/// Notes about matching:
/// - Parsed with Treesitter Bash and a strict query that uses anchors so the
/// heredocredirected statement is the only toplevel statement.
/// - The connector between `cd` and `apply_patch` must be `&&` (not `|` or `||`).
/// - Exactly one positional `word` argument is allowed for `cd` (no flags, no quoted
/// strings, no second argument).
/// - The apply command is validated inquery via `#any-of?` to allow `apply_patch`
/// or `applypatch`.
/// - Preceding or trailing commands (e.g., `echo ...;` or `... && echo done`) do not match.
/// # Arguments
///
/// Returns `(heredoc_body, Some(path))` when the `cd` variant matches, or
/// `(heredoc_body, None)` for the direct form. Errors are returned if the script
/// cannot be parsed or does not match the allowed patterns.
fn extract_apply_patch_from_bash(
/// * `src` - A string slice that holds the full command
///
/// # Returns
///
/// This function returns a `Result` which is:
///
/// * `Ok(String)` - The heredoc body if the extraction is successful.
/// * `Err(anyhow::Error)` - An error if the extraction fails.
///
fn extract_heredoc_body_from_apply_patch_command(
src: &str,
) -> std::result::Result<(String, Option<String>), ExtractHeredocError> {
// This function uses a Tree-sitter query to recognize one of two
// whole-script forms, each expressed as a single top-level statement:
//
// 1. apply_patch <<'EOF'\n...\nEOF
// 2. cd <path> && apply_patch <<'EOF'\n...\nEOF
//
// Key ideas when reading the query:
// - dots (`.`) between named nodes enforces adjacency among named children and
// anchor to the start/end of the expression.
// - we match a single redirected_statement directly under program with leading
// and trailing anchors (`.`). This ensures it is the only top-level statement
// (so prefixes like `echo ...;` or suffixes like `... && echo done` do not match).
//
// Overall, we want to be conservative and only match the intended forms, as other
// forms are likely to be model errors, or incorrectly interpreted by later code.
//
// If you're editing this query, it's helpful to start by creating a debugging binary
// which will let you see the AST of an arbitrary bash script passed in, and optionally
// 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: LazyLock<Query> = LazyLock::new(|| {
let language = BASH.into();
#[expect(clippy::expect_used)]
Query::new(
&language,
r#"
(
program
. (redirected_statement
body: (command
name: (command_name (word) @apply_name) .)
(#any-of? @apply_name "apply_patch" "applypatch")
redirect: (heredoc_redirect
. (heredoc_start)
. (heredoc_body) @heredoc
. (heredoc_end)
.))
.)
(
program
. (redirected_statement
body: (list
. (command
name: (command_name (word) @cd_name) .
argument: [
(word) @cd_path
(string (string_content) @cd_path)
(raw_string) @cd_raw_string
] .)
"&&"
. (command
name: (command_name (word) @apply_name))
.)
(#eq? @cd_name "cd")
(#any-of? @apply_name "apply_patch" "applypatch")
redirect: (heredoc_redirect
. (heredoc_start)
. (heredoc_body) @heredoc
. (heredoc_end)
.))
.)
"#,
)
.expect("valid bash query")
});
) -> std::result::Result<String, ExtractHeredocError> {
if !src.trim_start().starts_with("apply_patch") {
return Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch);
}
let lang = BASH.into();
let mut parser = Parser::new();
@@ -408,55 +276,26 @@ fn extract_apply_patch_from_bash(
.ok_or(ExtractHeredocError::FailedToParsePatchIntoAst)?;
let bytes = src.as_bytes();
let root = tree.root_node();
let mut c = tree.root_node().walk();
let mut cursor = QueryCursor::new();
let mut matches = cursor.matches(&APPLY_PATCH_QUERY, root, bytes);
while let Some(m) = matches.next() {
let mut heredoc_text: Option<String> = None;
let mut cd_path: Option<String> = None;
loop {
let node = c.node();
if node.kind() == "heredoc_body" {
let text = node
.utf8_text(bytes)
.map_err(ExtractHeredocError::HeredocNotUtf8)?;
return Ok(text.trim_end_matches('\n').to_owned());
}
for capture in m.captures.iter() {
let name = APPLY_PATCH_QUERY.capture_names()[capture.index as usize];
match name {
"heredoc" => {
let text = capture
.node
.utf8_text(bytes)
.map_err(ExtractHeredocError::HeredocNotUtf8)?
.trim_end_matches('\n')
.to_string();
heredoc_text = Some(text);
}
"cd_path" => {
let text = capture
.node
.utf8_text(bytes)
.map_err(ExtractHeredocError::HeredocNotUtf8)?
.to_string();
cd_path = Some(text);
}
"cd_raw_string" => {
let raw = capture
.node
.utf8_text(bytes)
.map_err(ExtractHeredocError::HeredocNotUtf8)?;
let trimmed = raw
.strip_prefix('\'')
.and_then(|s| s.strip_suffix('\''))
.unwrap_or(raw);
cd_path = Some(trimmed.to_string());
}
_ => {}
if c.goto_first_child() {
continue;
}
while !c.goto_next_sibling() {
if !c.goto_parent() {
return Err(ExtractHeredocError::FailedToFindHeredocBody);
}
}
if let Some(heredoc) = heredoc_text {
return Ok((heredoc, cd_path));
}
}
Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch)
}
#[derive(Debug, PartialEq)]
@@ -648,18 +487,21 @@ fn derive_new_contents_from_chunks(
}
};
let mut original_lines: Vec<String> = original_contents.split('\n').map(String::from).collect();
let mut original_lines: Vec<String> = original_contents
.split('\n')
.map(|s| s.to_string())
.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(String::is_empty) {
if original_lines.last().is_some_and(|s| s.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(String::is_empty) {
if !new_lines.last().is_some_and(|s| s.is_empty()) {
new_lines.push(String::new());
}
let new_contents = new_lines.join("\n");
@@ -703,7 +545,7 @@ 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(String::is_empty) {
let insertion_idx = if original_lines.last().is_some_and(|s| s.is_empty()) {
original_lines.len() - 1
} else {
original_lines.len()
@@ -729,11 +571,11 @@ fn compute_replacements(
let mut new_slice: &[String] = &chunk.new_lines;
if found.is_none() && pattern.last().is_some_and(String::is_empty) {
if found.is_none() && pattern.last().is_some_and(|s| s.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(String::is_empty) {
if new_slice.last().is_some_and(|s| s.is_empty()) {
new_slice = &new_slice[..new_slice.len() - 1];
}
@@ -750,15 +592,13 @@ fn compute_replacements(
line_index = start_idx + pattern.len();
} else {
return Err(ApplyPatchError::ComputeReplacements(format!(
"Failed to find expected lines in {}:\n{}",
path.display(),
chunk.old_lines.join("\n"),
"Failed to find expected lines {:?} in {}",
chunk.old_lines,
path.display()
)));
}
}
replacements.sort_by(|(lhs_idx, _, _), (rhs_idx, _, _)| lhs_idx.cmp(rhs_idx));
Ok(replacements)
}
@@ -845,7 +685,6 @@ 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.
@@ -854,72 +693,7 @@ mod tests {
}
fn strs_to_strings(strs: &[&str]) -> Vec<String> {
strs.iter().map(ToString::to_string).collect()
}
// Test helpers to reduce repetition when building bash -lc heredoc scripts
fn args_bash(script: &str) -> Vec<String> {
strs_to_strings(&["bash", "-lc", script])
}
fn heredoc_script(prefix: &str) -> String {
format!(
"{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH"
)
}
fn heredoc_script_ps(prefix: &str, suffix: &str) -> String {
format!(
"{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH{suffix}"
)
}
fn expected_single_add() -> Vec<Hunk> {
vec![Hunk::AddFile {
path: PathBuf::from("foo"),
contents: "hi\n".to_string(),
}]
}
fn assert_match(script: &str, expected_workdir: Option<&str>) {
let args = args_bash(script);
match maybe_parse_apply_patch(&args) {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
assert_eq!(workdir.as_deref(), expected_workdir);
assert_eq!(hunks, expected_single_add());
}
result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
}
}
fn assert_not_match(script: &str) {
let args = args_bash(script);
assert!(matches!(
maybe_parse_apply_patch(&args),
MaybeApplyPatch::NotApplyPatch
));
}
#[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)
));
strs.iter().map(|s| s.to_string()).collect()
}
#[test]
@@ -934,7 +708,7 @@ mod tests {
]);
match maybe_parse_apply_patch(&args) {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, .. }) => {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, patch: _ }) => {
assert_eq!(
hunks,
vec![Hunk::AddFile {
@@ -959,7 +733,7 @@ mod tests {
]);
match maybe_parse_apply_patch(&args) {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, .. }) => {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, patch: _ }) => {
assert_eq!(
hunks,
vec![Hunk::AddFile {
@@ -974,15 +748,10 @@ mod tests {
#[test]
fn test_heredoc() {
assert_match(&heredoc_script(""), None);
}
#[test]
fn test_heredoc_applypatch() {
let args = strs_to_strings(&[
"bash",
"-lc",
r#"applypatch <<'PATCH'
r#"apply_patch <<'PATCH'
*** Begin Patch
*** Add File: foo
+hi
@@ -991,8 +760,7 @@ PATCH"#,
]);
match maybe_parse_apply_patch(&args) {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
assert_eq!(workdir, None);
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, patch: _ }) => {
assert_eq!(
hunks,
vec![Hunk::AddFile {
@@ -1005,69 +773,6 @@ PATCH"#,
}
}
#[test]
fn test_heredoc_with_leading_cd() {
assert_match(&heredoc_script("cd foo && "), Some("foo"));
}
#[test]
fn test_cd_with_semicolon_is_ignored() {
assert_not_match(&heredoc_script("cd foo; "));
}
#[test]
fn test_cd_or_apply_patch_is_ignored() {
assert_not_match(&heredoc_script("cd bar || "));
}
#[test]
fn test_cd_pipe_apply_patch_is_ignored() {
assert_not_match(&heredoc_script("cd bar | "));
}
#[test]
fn test_cd_single_quoted_path_with_spaces() {
assert_match(&heredoc_script("cd 'foo bar' && "), Some("foo bar"));
}
#[test]
fn test_cd_double_quoted_path_with_spaces() {
assert_match(&heredoc_script("cd \"foo bar\" && "), Some("foo bar"));
}
#[test]
fn test_echo_and_apply_patch_is_ignored() {
assert_not_match(&heredoc_script("echo foo && "));
}
#[test]
fn test_apply_patch_with_arg_is_ignored() {
let script = "apply_patch foo <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH";
assert_not_match(script);
}
#[test]
fn test_double_cd_then_apply_patch_is_ignored() {
assert_not_match(&heredoc_script("cd foo && cd bar && "));
}
#[test]
fn test_cd_two_args_is_ignored() {
assert_not_match(&heredoc_script("cd foo bar && "));
}
#[test]
fn test_cd_then_apply_patch_then_extra_is_ignored() {
let script = heredoc_script_ps("cd bar && ", " && echo done");
assert_not_match(&script);
}
#[test]
fn test_echo_then_cd_and_apply_patch_is_ignored() {
// Ensure preceding commands before the `cd && apply_patch <<...` sequence do not match.
assert_not_match(&heredoc_script("echo foo; cd bar && "));
}
#[test]
fn test_add_file_hunk_creates_file_with_contents() {
let dir = tempdir().unwrap();
@@ -1265,33 +970,6 @@ 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

@@ -1,3 +0,0 @@
pub fn main() -> ! {
codex_apply_patch::main()
}

View File

@@ -175,11 +175,7 @@ fn parse_patch_text(patch: &str, mode: ParseMode) -> Result<ApplyPatchArgs, Pars
remaining_lines = &remaining_lines[hunk_lines..]
}
let patch = lines.join("\n");
Ok(ApplyPatchArgs {
hunks,
patch,
workdir: None,
})
Ok(ApplyPatchArgs { hunks, patch })
}
/// Checks the start and end lines of the patch text for `apply_patch`,
@@ -590,8 +586,7 @@ fn test_parse_patch_lenient() {
parse_patch_text(&patch_text_in_heredoc, ParseMode::Lenient),
Ok(ApplyPatchArgs {
hunks: expected_patch.clone(),
patch: patch_text.to_string(),
workdir: None,
patch: patch_text.to_string()
})
);
@@ -604,8 +599,7 @@ fn test_parse_patch_lenient() {
parse_patch_text(&patch_text_in_single_quoted_heredoc, ParseMode::Lenient),
Ok(ApplyPatchArgs {
hunks: expected_patch.clone(),
patch: patch_text.to_string(),
workdir: None,
patch: patch_text.to_string()
})
);
@@ -617,9 +611,8 @@ fn test_parse_patch_lenient() {
assert_eq!(
parse_patch_text(&patch_text_in_double_quoted_heredoc, ParseMode::Lenient),
Ok(ApplyPatchArgs {
hunks: expected_patch,
patch: patch_text.to_string(),
workdir: None,
hunks: expected_patch.clone(),
patch: patch_text.to_string()
})
);
@@ -637,7 +630,7 @@ 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)
Err(expected_error.clone())
);
assert_eq!(
parse_patch_text(&patch_text_with_missing_closing_heredoc, ParseMode::Lenient),

View File

@@ -112,10 +112,9 @@ 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(ToString::to_string).collect()
strings.iter().map(|s| s.to_string()).collect()
}
#[test]

View File

@@ -1,59 +0,0 @@
use std::io::Read;
use std::io::Write;
pub fn main() -> ! {
let exit_code = run_main();
std::process::exit(exit_code);
}
/// We would prefer to return `std::process::ExitCode`, but its `exit_process()`
/// method is still a nightly API and we want main() to return !.
pub fn run_main() -> i32 {
// Expect either one argument (the full apply_patch payload) or read it from stdin.
let mut args = std::env::args_os();
let _argv0 = args.next();
let patch_arg = match args.next() {
Some(arg) => match arg.into_string() {
Ok(s) => s,
Err(_) => {
eprintln!("Error: apply_patch requires a UTF-8 PATCH argument.");
return 1;
}
},
None => {
// No argument provided; attempt to read the patch from stdin.
let mut buf = String::new();
match std::io::stdin().read_to_string(&mut buf) {
Ok(_) => {
if buf.is_empty() {
eprintln!("Usage: apply_patch 'PATCH'\n echo 'PATCH' | apply-patch");
return 2;
}
buf
}
Err(err) => {
eprintln!("Error: Failed to read PATCH from stdin.\n{err}");
return 1;
}
}
}
};
// Refuse extra args to avoid ambiguity.
if args.next().is_some() {
eprintln!("Error: apply_patch accepts exactly one argument.");
return 2;
}
let mut stdout = std::io::stdout();
let mut stderr = std::io::stderr();
match crate::apply_patch(&patch_arg, &mut stdout, &mut stderr) {
Ok(()) => {
// Flush to ensure output ordering when used in pipelines.
let _ = stdout.flush();
0
}
Err(_) => 1,
}
}

View File

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

View File

@@ -1,90 +0,0 @@
use assert_cmd::prelude::*;
use std::fs;
use std::process::Command;
use tempfile::tempdir;
#[test]
fn test_apply_patch_cli_add_and_update() -> anyhow::Result<()> {
let tmp = tempdir()?;
let file = "cli_test.txt";
let absolute_path = tmp.path().join(file);
// 1) Add a file
let add_patch = format!(
r#"*** Begin Patch
*** Add File: {file}
+hello
*** End Patch"#
);
Command::cargo_bin("apply_patch")
.expect("should find apply_patch binary")
.arg(add_patch)
.current_dir(tmp.path())
.assert()
.success()
.stdout(format!("Success. Updated the following files:\nA {file}\n"));
assert_eq!(fs::read_to_string(&absolute_path)?, "hello\n");
// 2) Update the file
let update_patch = format!(
r#"*** Begin Patch
*** Update File: {file}
@@
-hello
+world
*** End Patch"#
);
Command::cargo_bin("apply_patch")
.expect("should find apply_patch binary")
.arg(update_patch)
.current_dir(tmp.path())
.assert()
.success()
.stdout(format!("Success. Updated the following files:\nM {file}\n"));
assert_eq!(fs::read_to_string(&absolute_path)?, "world\n");
Ok(())
}
#[test]
fn test_apply_patch_cli_stdin_add_and_update() -> anyhow::Result<()> {
let tmp = tempdir()?;
let file = "cli_test_stdin.txt";
let absolute_path = tmp.path().join(file);
// 1) Add a file via stdin
let add_patch = format!(
r#"*** Begin Patch
*** Add File: {file}
+hello
*** End Patch"#
);
let mut cmd =
assert_cmd::Command::cargo_bin("apply_patch").expect("should find apply_patch binary");
cmd.current_dir(tmp.path());
cmd.write_stdin(add_patch)
.assert()
.success()
.stdout(format!("Success. Updated the following files:\nA {file}\n"));
assert_eq!(fs::read_to_string(&absolute_path)?, "hello\n");
// 2) Update the file via stdin
let update_patch = format!(
r#"*** Begin Patch
*** Update File: {file}
@@
-hello
+world
*** End Patch"#
);
let mut cmd =
assert_cmd::Command::cargo_bin("apply_patch").expect("should find apply_patch binary");
cmd.current_dir(tmp.path());
cmd.write_stdin(update_patch)
.assert()
.success()
.stdout(format!("Success. Updated the following files:\nM {file}\n"));
assert_eq!(fs::read_to_string(&absolute_path)?, "world\n");
Ok(())
}

View File

@@ -1 +0,0 @@
mod cli;

View File

@@ -11,10 +11,9 @@ path = "src/lib.rs"
workspace = true
[dependencies]
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"] }
anyhow = "1"
codex-apply-patch = { path = "../apply-patch" }
codex-core = { path = "../core" }
codex-linux-sandbox = { path = "../linux-sandbox" }
dotenvy = "0.15.7"
tokio = { version = "1", features = ["rt-multi-thread"] }

View File

@@ -3,13 +3,6 @@ use std::path::Path;
use std::path::PathBuf;
use codex_core::CODEX_APPLY_PATCH_ARG1;
#[cfg(unix)]
use std::os::unix::fs::symlink;
use tempfile::TempDir;
const LINUX_SANDBOX_ARG0: &str = "codex-linux-sandbox";
const APPLY_PATCH_ARG0: &str = "apply_patch";
const MISSPELLED_APPLY_PATCH_ARG0: &str = "applypatch";
/// While we want to deploy the Codex CLI as a single executable for simplicity,
/// we also want to expose some of its functionality as distinct CLIs, so we use
@@ -21,7 +14,8 @@ const MISSPELLED_APPLY_PATCH_ARG0: &str = "applypatch";
/// `codex-linux-sandbox` we *directly* execute
/// [`codex_linux_sandbox::run_main`] (which never returns). Otherwise we:
///
/// 1. Load `.env` values from `~/.codex/.env` before creating any threads.
/// 1. Use [`dotenvy::from_path`] and [`dotenvy::dotenv`] to modify the
/// environment before creating any threads.
/// 2. Construct a Tokio multi-thread runtime.
/// 3. Derive the path to the current executable (so children can re-invoke the
/// sandbox) when running on Linux.
@@ -45,16 +39,14 @@ where
.and_then(|s| s.to_str())
.unwrap_or("");
if exe_name == LINUX_SANDBOX_ARG0 {
if exe_name == "codex-linux-sandbox" {
// Safety: [`run_main`] never returns.
codex_linux_sandbox::run_main();
} else if exe_name == APPLY_PATCH_ARG0 || exe_name == MISSPELLED_APPLY_PATCH_ARG0 {
codex_apply_patch::main();
}
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(str::to_owned));
let patch_arg = args.next().and_then(|s| s.to_str().map(|s| s.to_owned()));
let exit_code = match patch_arg {
Some(patch_arg) => {
let mut stdout = std::io::stdout();
@@ -76,19 +68,6 @@ where
// before creating any threads/the Tokio runtime.
load_dotenv();
// Retain the TempDir so it exists for the lifetime of the invocation of
// this executable. Admittedly, we could invoke `keep()` on it, but it
// would be nice to avoid leaving temporary directories behind, if possible.
let _path_entry = match prepend_path_entry_for_apply_patch() {
Ok(path_entry) => Some(path_entry),
Err(err) => {
// It is possible that Codex will proceed successfully even if
// updating the PATH fails, so warn the user and move on.
eprintln!("WARNING: proceeding, even though we could not update PATH: {err}");
None
}
};
// Regular invocation create a Tokio runtime and execute the provided
// async entry-point.
let runtime = tokio::runtime::Runtime::new()?;
@@ -105,7 +84,7 @@ where
const ILLEGAL_ENV_VAR_PREFIX: &str = "CODEX_";
/// Load env vars from ~/.codex/.env.
/// Load env vars from ~/.codex/.env and `$(pwd)/.env`.
///
/// Security: Do not allow `.env` files to create or modify any variables
/// with names starting with `CODEX_`.
@@ -115,6 +94,10 @@ fn load_dotenv() {
{
set_filtered(iter);
}
if let Ok(iter) = dotenvy::dotenv_iter() {
set_filtered(iter);
}
}
/// Helper to set vars from a dotenvy iterator while filtering out `CODEX_` keys.
@@ -130,67 +113,3 @@ where
}
}
}
/// Creates a temporary directory with either:
///
/// - UNIX: `apply_patch` symlink to the current executable
/// - WINDOWS: `apply_patch.bat` batch script to invoke the current executable
/// with the "secret" --codex-run-as-apply-patch flag.
///
/// This temporary directory is prepended to the PATH environment variable so
/// that `apply_patch` can be on the PATH without requiring the user to
/// install a separate `apply_patch` executable, simplifying the deployment of
/// Codex CLI.
///
/// IMPORTANT: This function modifies the PATH environment variable, so it MUST
/// be called before multiple threads are spawned.
fn prepend_path_entry_for_apply_patch() -> std::io::Result<TempDir> {
let temp_dir = TempDir::new()?;
let path = temp_dir.path();
for filename in &[APPLY_PATCH_ARG0, MISSPELLED_APPLY_PATCH_ARG0] {
let exe = std::env::current_exe()?;
#[cfg(unix)]
{
let link = path.join(filename);
symlink(&exe, &link)?;
}
#[cfg(windows)]
{
let batch_script = path.join(format!("{filename}.bat"));
std::fs::write(
&batch_script,
format!(
r#"@echo off
"{}" {CODEX_APPLY_PATCH_ARG1} %*
"#,
exe.display()
),
)?;
}
}
#[cfg(unix)]
const PATH_SEPARATOR: &str = ":";
#[cfg(windows)]
const PATH_SEPARATOR: &str = ";";
let path_element = path.display();
let updated_path_env_var = match std::env::var("PATH") {
Ok(existing_path) => {
format!("{path_element}{PATH_SEPARATOR}{existing_path}")
}
Err(_) => {
format!("{path_element}")
}
};
unsafe {
std::env::set_var("PATH", updated_path_env_var);
}
Ok(temp_dir)
}

View File

@@ -7,13 +7,15 @@ version = { workspace = true }
workspace = true
[dependencies]
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"] }
anyhow = "1"
clap = { version = "4", features = ["derive"] }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
codex-login = { path = "../login" }
reqwest = { version = "0.12", features = ["json", "stream"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tokio = { version = "1", features = ["full"] }
[dev-dependencies]
tempfile = { workspace = true }
tempfile = "3"

View File

@@ -1,5 +1,5 @@
use codex_core::config::Config;
use codex_core::default_client::create_client;
use codex_core::user_agent::get_codex_user_agent;
use crate::chatgpt_token::get_chatgpt_token_data;
use crate::chatgpt_token::init_chatgpt_token_from_auth;
@@ -16,7 +16,7 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
init_chatgpt_token_from_auth(&config.codex_home).await?;
// Make direct HTTP request to ChatGPT backend API with the token
let client = create_client();
let client = reqwest::Client::new();
let url = format!("{chatgpt_base_url}{path}");
let token =
@@ -31,6 +31,7 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
.bearer_auth(&token.access_token)
.header("chatgpt-account-id", account_id?)
.header("Content-Type", "application/json")
.header("User-Agent", get_codex_user_agent(None))
.send()
.await
.context("Failed to send request")?;

View File

@@ -1,9 +1,10 @@
use codex_core::CodexAuth;
use codex_login::AuthMode;
use codex_login::CodexAuth;
use std::path::Path;
use std::sync::LazyLock;
use std::sync::RwLock;
use codex_core::token_data::TokenData;
use codex_login::TokenData;
static CHATGPT_TOKEN: LazyLock<RwLock<Option<TokenData>>> = LazyLock::new(|| RwLock::new(None));
@@ -19,7 +20,7 @@ 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) -> std::io::Result<()> {
let auth = CodexAuth::from_codex_home(codex_home)?;
let auth = CodexAuth::from_codex_home(codex_home, AuthMode::ChatGPT)?;
if let Some(auth) = auth {
let token_data = auth.get_token_data().await?;
set_chatgpt_token_data(token_data);

View File

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

View File

@@ -1,2 +0,0 @@
// Aggregates all former standalone integration tests as modules.
mod apply_command_e2e;

View File

@@ -15,36 +15,26 @@ path = "src/lib.rs"
workspace = true
[dependencies]
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive"] }
clap_complete = { 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-protocol-ts = { workspace = true }
codex-tui = { workspace = true }
ctor = { workspace = true }
owo-colors = { workspace = true }
serde_json = { workspace = true }
supports-color = { workspace = true }
tokio = { workspace = true, features = [
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 = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tracing = { workspace = true }
tracing-subscriber = { workspace = true }
[dev-dependencies]
assert_cmd = { workspace = true }
predicates = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
tracing = "0.1.41"
tracing-subscriber = "0.3.19"
codex-protocol-ts = { path = "../protocol-ts" }

View File

@@ -64,6 +64,7 @@ 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()
@@ -74,29 +75,13 @@ 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,
cwd,
&config.sandbox_policy,
sandbox_policy_cwd.as_path(),
stdio_policy,
env,
)
.await?
spawn_command_under_seatbelt(command, &config.sandbox_policy, cwd, stdio_policy, env)
.await?
}
SandboxType::Landlock => {
#[expect(clippy::expect_used)]
@@ -106,9 +91,8 @@ async fn run_command_under_sandbox(
spawn_command_under_linux_sandbox(
codex_linux_sandbox_exe,
command,
cwd,
&config.sandbox_policy,
sandbox_policy_cwd.as_path(),
cwd,
stdio_policy,
env,
)

View File

@@ -1,13 +1,15 @@
use codex_common::CliConfigOverrides;
use codex_core::CodexAuth;
use codex_core::auth::CLIENT_ID;
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::AuthMode;
use codex_login::CLIENT_ID;
use codex_login::CodexAuth;
use codex_login::OPENAI_API_KEY_ENV_VAR;
use codex_login::ServerOptions;
use codex_login::login_with_api_key;
use codex_login::logout;
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) -> std::io::Result<()> {
@@ -58,11 +60,19 @@ pub async fn run_login_with_api_key(
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) {
match CodexAuth::from_codex_home(&config.codex_home, config.preferred_auth_method) {
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

@@ -14,15 +14,9 @@ use codex_cli::login::run_logout;
use codex_cli::proto;
use codex_common::CliConfigOverrides;
use codex_exec::Cli as ExecCli;
use codex_tui::AppExitInfo;
use codex_tui::Cli as TuiCli;
use owo_colors::OwoColorize;
use std::path::PathBuf;
use supports_color::Stream;
mod mcp_cmd;
use crate::mcp_cmd::McpCli;
use crate::proto::ProtoCli;
/// Codex CLI
@@ -62,8 +56,8 @@ enum Subcommand {
/// Remove stored authentication credentials.
Logout(LogoutCommand),
/// [experimental] Run Codex as an MCP server and manage MCP servers.
Mcp(McpCli),
/// Experimental: run Codex as an MCP server.
Mcp,
/// Run the Protocol stream via stdin/stdout
#[clap(visible_alias = "p")]
@@ -79,9 +73,6 @@ 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),
@@ -94,21 +85,6 @@ 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)]
@@ -159,62 +135,6 @@ 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}");
}
}
pub(crate) const CODEX_SECURE_MODE_ENV_VAR: &str = "CODEX_SECURE_MODE";
/// As early as possible in the process lifecycle, apply hardening measures
/// if the CODEX_SECURE_MODE environment variable is set to "1".
#[ctor::ctor]
fn pre_main_hardening() {
let secure_mode = match std::env::var(CODEX_SECURE_MODE_ENV_VAR) {
Ok(value) => value,
Err(_) => return,
};
if secure_mode == "1" {
codex_process_hardening::pre_main_hardening();
}
// Always clear this env var so child processes don't inherit it.
unsafe {
std::env::remove_var(CODEX_SECURE_MODE_ENV_VAR);
}
}
fn main() -> anyhow::Result<()> {
arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
cli_main(codex_linux_sandbox_exe).await?;
@@ -223,52 +143,26 @@ fn main() -> anyhow::Result<()> {
}
async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()> {
let MultitoolCli {
config_overrides: root_config_overrides,
mut interactive,
subcommand,
} = MultitoolCli::parse();
let cli = MultitoolCli::parse();
match subcommand {
match cli.subcommand {
None => {
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);
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));
}
}
Some(Subcommand::Exec(mut exec_cli)) => {
prepend_config_flags(
&mut exec_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut exec_cli.config_overrides, cli.config_overrides);
codex_exec::run_main(exec_cli, codex_linux_sandbox_exe).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(codex_linux_sandbox_exe).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::Mcp) => {
codex_mcp_server::run_main(codex_linux_sandbox_exe).await?;
}
Some(Subcommand::Login(mut login_cli)) => {
prepend_config_flags(
&mut login_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut login_cli.config_overrides, cli.config_overrides);
match login_cli.action {
Some(LoginSubcommand::Status) => {
run_login_status(login_cli.config_overrides).await;
@@ -283,17 +177,11 @@ 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,
root_config_overrides.clone(),
);
prepend_config_flags(&mut logout_cli.config_overrides, cli.config_overrides);
run_logout(logout_cli.config_overrides).await;
}
Some(Subcommand::Proto(mut proto_cli)) => {
prepend_config_flags(
&mut proto_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut proto_cli.config_overrides, cli.config_overrides);
proto::run_main(proto_cli).await?;
}
Some(Subcommand::Completion(completion_cli)) => {
@@ -301,10 +189,7 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
}
Some(Subcommand::Debug(debug_args)) => match debug_args.cmd {
DebugCommand::Seatbelt(mut seatbelt_cli) => {
prepend_config_flags(
&mut seatbelt_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut seatbelt_cli.config_overrides, cli.config_overrides);
codex_cli::debug_sandbox::run_command_under_seatbelt(
seatbelt_cli,
codex_linux_sandbox_exe,
@@ -312,10 +197,7 @@ 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,
root_config_overrides.clone(),
);
prepend_config_flags(&mut landlock_cli.config_overrides, cli.config_overrides);
codex_cli::debug_sandbox::run_command_under_landlock(
landlock_cli,
codex_linux_sandbox_exe,
@@ -324,10 +206,7 @@ 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,
root_config_overrides.clone(),
);
prepend_config_flags(&mut apply_cli.config_overrides, cli.config_overrides);
run_apply_command(apply_cli, None).await?;
}
Some(Subcommand::GenerateTs(gen_cli)) => {
@@ -349,256 +228,8 @@ 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::mcp_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);
}
}

View File

@@ -1,461 +0,0 @@
use std::collections::HashMap;
use std::path::PathBuf;
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 cmd: Option<McpSubcommand>,
}
#[derive(Debug, clap::Subcommand)]
pub enum McpSubcommand {
/// [experimental] Run the Codex MCP server (stdio transport).
Serve,
/// [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, codex_linux_sandbox_exe: Option<PathBuf>) -> Result<()> {
let McpCli {
config_overrides,
cmd,
} = self;
let subcommand = cmd.unwrap_or(McpSubcommand::Serve);
match subcommand {
McpSubcommand::Serve => {
codex_mcp_server::run_main(codex_linux_sandbox_exe, config_overrides).await?;
}
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

@@ -2,7 +2,6 @@ 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;
@@ -37,8 +36,7 @@ pub async fn run_main(opts: ProtoCli) -> anyhow::Result<()> {
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()));
let conversation_manager = ConversationManager::default();
let NewConversation {
conversation_id: _,
conversation,

View File

@@ -1,95 +0,0 @@
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

@@ -1,104 +0,0 @@
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

View File

@@ -7,11 +7,11 @@ version = { workspace = true }
workspace = true
[dependencies]
clap = { workspace = true, features = ["derive", "wrap_help"], optional = true }
codex-core = { workspace = true }
codex-protocol = { workspace = true }
serde = { workspace = true, optional = true }
toml = { workspace = true, optional = true }
clap = { version = "4", features = ["derive", "wrap_help"], optional = true }
codex-core = { path = "../core" }
codex-protocol = { path = "../protocol" }
serde = { version = "1", optional = true }
toml = { version = "0.9", optional = true }
[features]
# Separate feature so that `clap` is not a mandatory dependency.

View File

@@ -1,46 +0,0 @@
use codex_core::protocol::AskForApproval;
use codex_core::protocol::SandboxPolicy;
/// A simple preset pairing an approval policy with a sandbox policy.
#[derive(Debug, Clone)]
pub struct ApprovalPreset {
/// Stable identifier for the preset.
pub id: &'static str,
/// Display label shown in UIs.
pub label: &'static str,
/// Short human description shown next to the label in UIs.
pub description: &'static str,
/// Approval policy to apply.
pub approval: AskForApproval,
/// Sandbox policy to apply.
pub sandbox: SandboxPolicy,
}
/// Built-in list of approval presets that pair approval and sandbox policy.
///
/// Keep this UI-agnostic so it can be reused by both TUI and MCP server.
pub fn builtin_approval_presets() -> Vec<ApprovalPreset> {
vec![
ApprovalPreset {
id: "read-only",
label: "Read Only",
description: "Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network",
approval: AskForApproval::OnRequest,
sandbox: SandboxPolicy::ReadOnly,
},
ApprovalPreset {
id: "auto",
label: "Auto",
description: "Codex can read files, make edits, and run commands in the workspace. Codex requires approval to work outside the workspace or access network",
approval: AskForApproval::OnRequest,
sandbox: SandboxPolicy::new_workspace_write_policy(),
},
ApprovalPreset {
id: "full-access",
label: "Full Access",
description: "Codex can read files, make edits, and run commands with network access, without approval. Exercise caution",
approval: AskForApproval::Never,
sandbox: SandboxPolicy::DangerFullAccess,
},
]
}

View File

@@ -17,10 +17,7 @@ pub fn create_config_summary_entries(config: &Config) -> Vec<(&'static str, Stri
{
entries.push((
"reasoning effort",
config
.model_reasoning_effort
.map(|effort| effort.to_string())
.unwrap_or_else(|| "none".to_string()),
config.model_reasoning_effort.to_string(),
));
entries.push((
"reasoning summaries",

View File

@@ -2,7 +2,7 @@ use std::time::Duration;
use std::time::Instant;
/// Returns a string representing the elapsed time since `start_time` like
/// "1m 15s" or "1.50s".
/// "1m15s" or "1.50s".
pub fn format_elapsed(start_time: Instant) -> String {
format_duration(start_time.elapsed())
}
@@ -12,7 +12,7 @@ pub fn format_elapsed(start_time: Instant) -> String {
/// Formatting rules:
/// * < 1 s -> "{milli}ms"
/// * < 60 s -> "{sec:.2}s" (two decimal places)
/// * >= 60 s -> "{min}m {sec:02}s"
/// * >= 60 s -> "{min}m{sec:02}s"
pub fn format_duration(duration: Duration) -> String {
let millis = duration.as_millis() as i64;
format_elapsed_millis(millis)
@@ -26,7 +26,7 @@ fn format_elapsed_millis(millis: i64) -> String {
} else {
let minutes = millis / 60_000;
let seconds = (millis % 60_000) / 1000;
format!("{minutes}m {seconds:02}s")
format!("{minutes}m{seconds:02}s")
}
}
@@ -61,18 +61,12 @@ mod tests {
fn test_format_duration_minutes() {
// Durations ≥ 1 minute should be printed mmss.
let dur = Duration::from_millis(75_000); // 1m15s
assert_eq!(format_duration(dur), "1m 15s");
assert_eq!(format_duration(dur), "1m15s");
let dur_exact = Duration::from_millis(60_000); // 1m0s
assert_eq!(format_duration(dur_exact), "1m 00s");
assert_eq!(format_duration(dur_exact), "1m00s");
let dur_long = Duration::from_millis(3_601_000);
assert_eq!(format_duration(dur_long), "60m 01s");
}
#[test]
fn test_format_duration_one_hour_has_space() {
let dur_hour = Duration::from_millis(3_600_000);
assert_eq!(format_duration(dur_hour), "60m 00s");
assert_eq!(format_duration(dur_long), "60m01s");
}
}

View File

@@ -31,6 +31,3 @@ pub use config_summary::create_config_summary_entries;
pub mod fuzzy_match;
// Shared model presets used by TUI and MCP server
pub mod model_presets;
// Shared approval presets (AskForApproval + Sandbox) used by TUI and MCP server
// Not to be confused with AskForApproval, which we should probably rename to EscalationPolicy.
pub mod approval_presets;

View File

@@ -1,5 +1,4 @@
use codex_core::protocol_config_types::ReasoningEffort;
use codex_protocol::mcp_protocol::AuthMode;
/// A simple preset pairing a model slug with a reasoning effort.
#[derive(Debug, Clone, Copy)]
@@ -13,61 +12,43 @@ pub struct ModelPreset {
/// Model slug (e.g., "gpt-5").
pub model: &'static str,
/// Reasoning effort to apply for this preset.
pub effort: Option<ReasoningEffort>,
pub effort: ReasoningEffort,
}
const PRESETS: &[ModelPreset] = &[
ModelPreset {
id: "gpt-5-codex-low",
label: "gpt-5-codex low",
description: "",
model: "gpt-5-codex",
effort: Some(ReasoningEffort::Low),
},
ModelPreset {
id: "gpt-5-codex-medium",
label: "gpt-5-codex medium",
description: "",
model: "gpt-5-codex",
effort: Some(ReasoningEffort::Medium),
},
ModelPreset {
id: "gpt-5-codex-high",
label: "gpt-5-codex high",
description: "",
model: "gpt-5-codex",
effort: Some(ReasoningEffort::High),
},
ModelPreset {
id: "gpt-5-minimal",
label: "gpt-5 minimal",
description: "— fastest responses with limited reasoning; ideal for coding, instructions, or lightweight tasks",
model: "gpt-5",
effort: Some(ReasoningEffort::Minimal),
},
ModelPreset {
id: "gpt-5-low",
label: "gpt-5 low",
description: "— balances speed with some reasoning; useful for straightforward queries and short explanations",
model: "gpt-5",
effort: Some(ReasoningEffort::Low),
},
ModelPreset {
id: "gpt-5-medium",
label: "gpt-5 medium",
description: "— default setting; provides a solid balance of reasoning depth and latency for general-purpose tasks",
model: "gpt-5",
effort: Some(ReasoningEffort::Medium),
},
ModelPreset {
id: "gpt-5-high",
label: "gpt-5 high",
description: "— maximizes reasoning depth for complex or ambiguous problems",
model: "gpt-5",
effort: Some(ReasoningEffort::High),
},
];
pub fn builtin_model_presets(_auth_mode: Option<AuthMode>) -> Vec<ModelPreset> {
PRESETS.to_vec()
/// Built-in list of model presets that pair a model with a reasoning effort.
///
/// Keep this UI-agnostic so it can be reused by both TUI and MCP server.
pub fn builtin_model_presets() -> &'static [ModelPreset] {
// Order reflects effort from minimal to high.
const PRESETS: &[ModelPreset] = &[
ModelPreset {
id: "gpt-5-minimal",
label: "gpt-5 minimal",
description: "— Fastest responses with very limited reasoning; ideal for coding, instructions, or lightweight tasks.",
model: "gpt-5",
effort: ReasoningEffort::Minimal,
},
ModelPreset {
id: "gpt-5-low",
label: "gpt-5 low",
description: "— Balances speed with some reasoning; useful for straightforward queries and short explanations.",
model: "gpt-5",
effort: ReasoningEffort::Low,
},
ModelPreset {
id: "gpt-5-medium",
label: "gpt-5 medium",
description: "— Default setting; provides a solid balance of reasoning depth and latency for general-purpose tasks.",
model: "gpt-5",
effort: ReasoningEffort::Medium,
},
ModelPreset {
id: "gpt-5-high",
label: "gpt-5 high",
description: "— Maximizes reasoning depth for complex or ambiguous problems.",
model: "gpt-5",
effort: ReasoningEffort::High,
},
];
PRESETS
}

View File

@@ -1,6 +1,535 @@
# Configuration docs moved
# Config
This file has moved. Please see the latest configuration documentation here:
Codex supports several mechanisms for setting config values:
- Full config docs: [docs/config.md](../docs/config.md)
- MCP servers section: [docs/config.md#mcp_servers](../docs/config.md#mcp_servers)
- Config-specific command-line flags, such as `--model o3` (highest precedence).
- A generic `-c`/`--config` flag that takes a `key=value` pair, such as `--config model="o3"`.
- The key can contain dots to set a value deeper than the root, e.g. `--config model_providers.openai.wire_api="chat"`.
- Values can contain objects, such as `--config shell_environment_policy.include_only=["PATH", "HOME", "USER"]`.
- For consistency with `config.toml`, values are in TOML format rather than JSON format, so use `{a = 1, b = 2}` rather than `{"a": 1, "b": 2}`.
- If `value` cannot be parsed as a valid TOML value, it is treated as a string value. This means that both `-c model="o3"` and `-c model=o3` are equivalent.
- The `$CODEX_HOME/config.toml` configuration file where the `CODEX_HOME` environment value defaults to `~/.codex`. (Note `CODEX_HOME` will also be where logs and other Codex-related information are stored.)
Both the `--config` flag and the `config.toml` file support the following options:
## model
The model that Codex should use.
```toml
model = "o3" # overrides the default of "gpt-5"
```
## model_providers
This option lets you override and amend the default set of model providers bundled with Codex. This value is a map where the key is the value to use with `model_provider` to select the corresponding provider.
For example, if you wanted to add a provider that uses the OpenAI 4o model via the chat completions API, then you could add the following configuration:
```toml
# Recall that in TOML, root keys must be listed before tables.
model = "gpt-4o"
model_provider = "openai-chat-completions"
[model_providers.openai-chat-completions]
# Name of the provider that will be displayed in the Codex UI.
name = "OpenAI using Chat Completions"
# The path `/chat/completions` will be amended to this URL to make the POST
# request for the chat completions.
base_url = "https://api.openai.com/v1"
# If `env_key` is set, identifies an environment variable that must be set when
# using Codex with this provider. The value of the environment variable must be
# non-empty and will be used in the `Bearer TOKEN` HTTP header for the POST request.
env_key = "OPENAI_API_KEY"
# Valid values for wire_api are "chat" and "responses". Defaults to "chat" if omitted.
wire_api = "chat"
# If necessary, extra query params that need to be added to the URL.
# See the Azure example below.
query_params = {}
```
Note this makes it possible to use Codex CLI with non-OpenAI models, so long as they use a wire API that is compatible with the OpenAI chat completions API. For example, you could define the following provider to use Codex CLI with Ollama running locally:
```toml
[model_providers.ollama]
name = "Ollama"
base_url = "http://localhost:11434/v1"
```
Or a third-party provider (using a distinct environment variable for the API key):
```toml
[model_providers.mistral]
name = "Mistral"
base_url = "https://api.mistral.ai/v1"
env_key = "MISTRAL_API_KEY"
```
Note that Azure requires `api-version` to be passed as a query parameter, so be sure to specify it as part of `query_params` when defining the Azure provider:
```toml
[model_providers.azure]
name = "Azure"
# Make sure you set the appropriate subdomain for this URL.
base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"
env_key = "AZURE_OPENAI_API_KEY" # Or "OPENAI_API_KEY", whichever you use.
query_params = { api-version = "2025-04-01-preview" }
```
It is also possible to configure a provider to include extra HTTP headers with a request. These can be hardcoded values (`http_headers`) or values read from environment variables (`env_http_headers`):
```toml
[model_providers.example]
# name, base_url, ...
# This will add the HTTP header `X-Example-Header` with value `example-value`
# to each request to the model provider.
http_headers = { "X-Example-Header" = "example-value" }
# This will add the HTTP header `X-Example-Features` with the value of the
# `EXAMPLE_FEATURES` environment variable to each request to the model provider
# _if_ the environment variable is set and its value is non-empty.
env_http_headers = { "X-Example-Features": "EXAMPLE_FEATURES" }
```
### Per-provider network tuning
The following optional settings control retry behaviour and streaming idle timeouts **per model provider**. They must be specified inside the corresponding `[model_providers.<id>]` block in `config.toml`. (Older releases accepted toplevel keys; those are now ignored.)
Example:
```toml
[model_providers.openai]
name = "OpenAI"
base_url = "https://api.openai.com/v1"
env_key = "OPENAI_API_KEY"
# network tuning overrides (all optional; falls back to builtin defaults)
request_max_retries = 4 # retry failed HTTP requests
stream_max_retries = 10 # retry dropped SSE streams
stream_idle_timeout_ms = 300000 # 5m idle timeout
```
#### request_max_retries
How many times Codex will retry a failed HTTP request to the model provider. Defaults to `4`.
#### stream_max_retries
Number of times Codex will attempt to reconnect when a streaming response is interrupted. Defaults to `10`.
#### stream_idle_timeout_ms
How long Codex will wait for activity on a streaming response before treating the connection as lost. Defaults to `300_000` (5 minutes).
## model_provider
Identifies which provider to use from the `model_providers` map. Defaults to `"openai"`. You can override the `base_url` for the built-in `openai` provider via the `OPENAI_BASE_URL` environment variable.
Note that if you override `model_provider`, then you likely want to override
`model`, as well. For example, if you are running ollama with Mistral locally,
then you would need to add the following to your config in addition to the new entry in the `model_providers` map:
```toml
model_provider = "ollama"
model = "mistral"
```
## approval_policy
Determines when the user should be prompted to approve whether Codex can execute a command:
```toml
# Codex has hardcoded logic that defines a set of "trusted" commands.
# Setting the approval_policy to `untrusted` means that Codex will prompt the
# user before running a command not in the "trusted" set.
#
# See https://github.com/openai/codex/issues/1260 for the plan to enable
# end-users to define their own trusted commands.
approval_policy = "untrusted"
```
If you want to be notified whenever a command fails, use "on-failure":
```toml
# If the command fails when run in the sandbox, Codex asks for permission to
# retry the command outside the sandbox.
approval_policy = "on-failure"
```
If you want the model to run until it decides that it needs to ask you for escalated permissions, use "on-request":
```toml
# The model decides when to escalate
approval_policy = "on-request"
```
Alternatively, you can have the model run until it is done, and never ask to run a command with escalated permissions:
```toml
# User is never prompted: if the command fails, Codex will automatically try
# something out. Note the `exec` subcommand always uses this mode.
approval_policy = "never"
```
## profiles
A _profile_ is a collection of configuration values that can be set together. Multiple profiles can be defined in `config.toml` and you can specify the one you
want to use at runtime via the `--profile` flag.
Here is an example of a `config.toml` that defines multiple profiles:
```toml
model = "o3"
approval_policy = "unless-allow-listed"
disable_response_storage = false
# Setting `profile` is equivalent to specifying `--profile o3` on the command
# line, though the `--profile` flag can still be used to override this value.
profile = "o3"
[model_providers.openai-chat-completions]
name = "OpenAI using Chat Completions"
base_url = "https://api.openai.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"
[profiles.o3]
model = "o3"
model_provider = "openai"
approval_policy = "never"
model_reasoning_effort = "high"
model_reasoning_summary = "detailed"
[profiles.gpt3]
model = "gpt-3.5-turbo"
model_provider = "openai-chat-completions"
[profiles.zdr]
model = "o3"
model_provider = "openai"
approval_policy = "on-failure"
disable_response_storage = true
```
Users can specify config values at multiple levels. Order of precedence is as follows:
1. custom command-line argument, e.g., `--model o3`
2. as part of a profile, where the `--profile` is specified via a CLI (or in the config file itself)
3. as an entry in `config.toml`, e.g., `model = "o3"`
4. the default value that comes with Codex CLI (i.e., Codex CLI defaults to `gpt-5`)
## model_reasoning_effort
If the selected model is known to support reasoning (for example: `o3`, `o4-mini`, `codex-*`, `gpt-5`), reasoning is enabled by default when using the Responses API. As explained in the [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning), this can be set to:
- `"minimal"`
- `"low"`
- `"medium"` (default)
- `"high"`
Note: to minimize reasoning, choose `"minimal"`.
## model_reasoning_summary
If the model name starts with `"o"` (as in `"o3"` or `"o4-mini"`) or `"codex"`, reasoning is enabled by default when using the Responses API. As explained in the [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#reasoning-summaries), this can be set to:
- `"auto"` (default)
- `"concise"`
- `"detailed"`
To disable reasoning summaries, set `model_reasoning_summary` to `"none"` in your config:
```toml
model_reasoning_summary = "none" # disable reasoning summaries
```
## model_supports_reasoning_summaries
By default, `reasoning` is only set on requests to OpenAI models that are known to support them. To force `reasoning` to set on requests to the current model, you can force this behavior by setting the following in `config.toml`:
```toml
model_supports_reasoning_summaries = true
```
## sandbox_mode
Codex executes model-generated shell commands inside an OS-level sandbox.
In most cases you can pick the desired behaviour with a single option:
```toml
# same as `--sandbox read-only`
sandbox_mode = "read-only"
```
The default policy is `read-only`, which means commands can read any file on
disk, but attempts to write a file or access the network will be blocked.
A more relaxed policy is `workspace-write`. When specified, the current working directory for the Codex task will be writable (as well as `$TMPDIR` on macOS). Note that the CLI defaults to using the directory where it was spawned as `cwd`, though this can be overridden using `--cwd/-C`.
On macOS (and soon Linux), all writable roots (including `cwd`) that contain a `.git/` folder _as an immediate child_ will configure the `.git/` folder to be read-only while the rest of the Git repository will be writable. This means that commands like `git commit` will fail, by default (as it entails writing to `.git/`), and will require Codex to ask for permission.
```toml
# same as `--sandbox workspace-write`
sandbox_mode = "workspace-write"
# Extra settings that only apply when `sandbox = "workspace-write"`.
[sandbox_workspace_write]
# By default, the cwd for the Codex session will be writable as well as $TMPDIR
# (if set) and /tmp (if it exists). Setting the respective options to `true`
# will override those defaults.
exclude_tmpdir_env_var = false
exclude_slash_tmp = false
# Optional list of _additional_ writable roots beyond $TMPDIR and /tmp.
writable_roots = ["/Users/YOU/.pyenv/shims"]
# Allow the command being run inside the sandbox to make outbound network
# requests. Disabled by default.
network_access = false
```
To disable sandboxing altogether, specify `danger-full-access` like so:
```toml
# same as `--sandbox danger-full-access`
sandbox_mode = "danger-full-access"
```
This is reasonable to use if Codex is running in an environment that provides its own sandboxing (such as a Docker container) such that further sandboxing is unnecessary.
Though using this option may also be necessary if you try to use Codex in environments where its native sandboxing mechanisms are unsupported, such as older Linux kernels or on Windows.
## mcp_servers
Defines the list of MCP servers that Codex can consult for tool use. Currently, only servers that are launched by executing a program that communicate over stdio are supported. For servers that use the SSE transport, consider an adapter like [mcp-proxy](https://github.com/sparfenyuk/mcp-proxy).
**Note:** Codex may cache the list of tools and resources from an MCP server so that Codex can include this information in context at startup without spawning all the servers. This is designed to save resources by loading MCP servers lazily.
This config option is comparable to how Claude and Cursor define `mcpServers` in their respective JSON config files, though because Codex uses TOML for its config language, the format is slightly different. For example, the following config in JSON:
```json
{
"mcpServers": {
"server-name": {
"command": "npx",
"args": ["-y", "mcp-server"],
"env": {
"API_KEY": "value"
}
}
}
}
```
Should be represented as follows in `~/.codex/config.toml`:
```toml
# IMPORTANT: the top-level key is `mcp_servers` rather than `mcpServers`.
[mcp_servers.server-name]
command = "npx"
args = ["-y", "mcp-server"]
env = { "API_KEY" = "value" }
```
## disable_response_storage
Currently, customers whose accounts are set to use Zero Data Retention (ZDR) must set `disable_response_storage` to `true` so that Codex uses an alternative to the Responses API that works with ZDR:
```toml
disable_response_storage = true
```
## shell_environment_policy
Codex spawns subprocesses (e.g. when executing a `local_shell` tool-call suggested by the assistant). By default it now passes **your full environment** to those subprocesses. You can tune this behavior via the **`shell_environment_policy`** block in `config.toml`:
```toml
[shell_environment_policy]
# inherit can be "all" (default), "core", or "none"
inherit = "core"
# set to true to *skip* the filter for `"*KEY*"` and `"*TOKEN*"`
ignore_default_excludes = false
# exclude patterns (case-insensitive globs)
exclude = ["AWS_*", "AZURE_*"]
# force-set / override values
set = { CI = "1" }
# if provided, *only* vars matching these patterns are kept
include_only = ["PATH", "HOME"]
```
| Field | Type | Default | Description |
| ------------------------- | -------------------------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| `inherit` | string | `all` | Starting template for the environment:<br>`all` (clone full parent env), `core` (`HOME`, `PATH`, `USER`, …), or `none` (start empty). |
| `ignore_default_excludes` | boolean | `false` | When `false`, Codex removes any var whose **name** contains `KEY`, `SECRET`, or `TOKEN` (case-insensitive) before other rules run. |
| `exclude` | array&lt;string&gt; | `[]` | Case-insensitive glob patterns to drop after the default filter.<br>Examples: `"AWS_*"`, `"AZURE_*"`. |
| `set` | table&lt;string,string&gt; | `{}` | Explicit key/value overrides or additions always win over inherited values. |
| `include_only` | array&lt;string&gt; | `[]` | If non-empty, a whitelist of patterns; only variables that match _one_ pattern survive the final step. (Generally used with `inherit = "all"`.) |
The patterns are **glob style**, not full regular expressions: `*` matches any
number of characters, `?` matches exactly one, and character classes like
`[A-Z]`/`[^0-9]` are supported. Matching is always **case-insensitive**. This
syntax is documented in code as `EnvironmentVariablePattern` (see
`core/src/config_types.rs`).
If you just need a clean slate with a few custom entries you can write:
```toml
[shell_environment_policy]
inherit = "none"
set = { PATH = "/usr/bin", MY_FLAG = "1" }
```
Currently, `CODEX_SANDBOX_NETWORK_DISABLED=1` is also added to the environment, assuming network is disabled. This is not configurable.
## notify
Specify a program that will be executed to get notified about events generated by Codex. Note that the program will receive the notification argument as a string of JSON, e.g.:
```json
{
"type": "agent-turn-complete",
"turn-id": "12345",
"input-messages": ["Rename `foo` to `bar` and update the callsites."],
"last-assistant-message": "Rename complete and verified `cargo build` succeeds."
}
```
The `"type"` property will always be set. Currently, `"agent-turn-complete"` is the only notification type that is supported.
As an example, here is a Python script that parses the JSON and decides whether to show a desktop push notification using [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS:
```python
#!/usr/bin/env python3
import json
import subprocess
import sys
def main() -> int:
if len(sys.argv) != 2:
print("Usage: notify.py <NOTIFICATION_JSON>")
return 1
try:
notification = json.loads(sys.argv[1])
except json.JSONDecodeError:
return 1
match notification_type := notification.get("type"):
case "agent-turn-complete":
assistant_message = notification.get("last-assistant-message")
if assistant_message:
title = f"Codex: {assistant_message}"
else:
title = "Codex: Turn Complete!"
input_messages = notification.get("input_messages", [])
message = " ".join(input_messages)
title += message
case _:
print(f"not sending a push notification for: {notification_type}")
return 0
subprocess.check_output(
[
"terminal-notifier",
"-title",
title,
"-message",
message,
"-group",
"codex",
"-ignoreDnD",
"-activate",
"com.googlecode.iterm2",
]
)
return 0
if __name__ == "__main__":
sys.exit(main())
```
To have Codex use this script for notifications, you would configure it via `notify` in `~/.codex/config.toml` using the appropriate path to `notify.py` on your computer:
```toml
notify = ["python3", "/Users/mbolin/.codex/notify.py"]
```
## history
By default, Codex CLI records messages sent to the model in `$CODEX_HOME/history.jsonl`. Note that on UNIX, the file permissions are set to `o600`, so it should only be readable and writable by the owner.
To disable this behavior, configure `[history]` as follows:
```toml
[history]
persistence = "none" # "save-all" is the default value
```
## file_opener
Identifies the editor/URI scheme to use for hyperlinking citations in model output. If set, citations to files in the model output will be hyperlinked using the specified URI scheme so they can be ctrl/cmd-clicked from the terminal to open them.
For example, if the model output includes a reference such as `【F:/home/user/project/main.py†L42-L50】`, then this would be rewritten to link to the URI `vscode://file/home/user/project/main.py:42`.
Note this is **not** a general editor setting (like `$EDITOR`), as it only accepts a fixed set of values:
- `"vscode"` (default)
- `"vscode-insiders"`
- `"windsurf"`
- `"cursor"`
- `"none"` to explicitly disable this feature
Currently, `"vscode"` is the default, though Codex does not verify VS Code is installed. As such, `file_opener` may default to `"none"` or something else in the future.
## hide_agent_reasoning
Codex intermittently emits "reasoning" events that show the model's internal "thinking" before it produces a final answer. Some users may find these events distracting, especially in CI logs or minimal terminal output.
Setting `hide_agent_reasoning` to `true` suppresses these events in **both** the TUI as well as the headless `exec` sub-command:
```toml
hide_agent_reasoning = true # defaults to false
```
## show_raw_agent_reasoning
Surfaces the models raw chain-of-thought ("raw reasoning content") when available.
Notes:
- Only takes effect if the selected model/provider actually emits raw reasoning content. Many models do not. When unsupported, this option has no visible effect.
- Raw reasoning may include intermediate thoughts or sensitive context. Enable only if acceptable for your workflow.
Example:
```toml
show_raw_agent_reasoning = true # defaults to false
```
## model_context_window
The size of the context window for the model, in tokens.
In general, Codex knows the context window for the most common OpenAI models, but if you are using a new model with an old version of the Codex CLI, then you can use `model_context_window` to tell Codex what value to use to determine how much context is left during a conversation.
## model_max_output_tokens
This is analogous to `model_context_window`, but for the maximum number of output tokens for the model.
## project_doc_max_bytes
Maximum number of bytes to read from an `AGENTS.md` file to include in the instructions sent with the first turn of a session. Defaults to 32 KiB.
## tui
Options that are specific to the TUI.
```toml
[tui]
# More to come here
```

View File

@@ -4,7 +4,6 @@ name = "codex-core"
version = { workspace = true }
[lib]
doctest = false
name = "codex_core"
path = "src/lib.rs"
@@ -12,85 +11,73 @@ path = "src/lib.rs"
workspace = true
[dependencies]
anyhow = { workspace = true }
askama = { workspace = true }
async-channel = { workspace = true }
async-trait = { workspace = true }
base64 = { workspace = true }
bytes = { workspace = true }
chrono = { workspace = true, features = ["serde"] }
codex-apply-patch = { workspace = true }
codex-file-search = { workspace = true }
codex-mcp-client = { workspace = true }
codex-rmcp-client = { workspace = true }
codex-protocol = { workspace = true }
dirs = { workspace = true }
env-flags = { workspace = true }
eventsource-stream = { workspace = true }
futures = { workspace = true }
indexmap = { workspace = true }
libc = { workspace = true }
mcp-types = { workspace = true }
os_info = { workspace = true }
portable-pty = { workspace = true }
rand = { workspace = true }
regex-lite = { workspace = true }
reqwest = { workspace = true, features = ["json", "stream"] }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
sha1 = { workspace = true }
shlex = { workspace = true }
similar = { workspace = true }
strum_macros = { workspace = true }
tempfile = { workspace = true }
thiserror = { workspace = true }
time = { workspace = true, features = [
"formatting",
"parsing",
"local-offset",
"macros",
] }
tokio = { workspace = true, features = [
anyhow = "1"
async-channel = "2.3.1"
base64 = "0.22"
bytes = "1.10.1"
chrono = { version = "0.4", features = ["serde"] }
codex-apply-patch = { path = "../apply-patch" }
codex-login = { path = "../login" }
codex-mcp-client = { path = "../mcp-client" }
codex-protocol = { path = "../protocol" }
dirs = "6"
env-flags = "0.1.1"
eventsource-stream = "0.2.3"
futures = "0.3"
libc = "0.2.175"
mcp-types = { path = "../mcp-types" }
mime_guess = "2.0"
os_info = "3.12.0"
rand = "0.9"
regex-lite = "0.1.6"
reqwest = { version = "0.12", features = ["json", "stream"] }
serde = { version = "1", features = ["derive"] }
serde_bytes = "0.11"
serde_json = "1"
sha1 = "0.10.6"
shlex = "1.3.0"
similar = "2.7.0"
strum_macros = "0.27.2"
tempfile = "3"
thiserror = "2.0.12"
time = { version = "0.3", features = ["formatting", "local-offset", "macros"] }
tokio = { version = "1", features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tokio-util = { workspace = true }
toml = { workspace = true }
toml_edit = { workspace = true }
tracing = { workspace = true, features = ["log"] }
tree-sitter = { workspace = true }
tree-sitter-bash = { workspace = true }
uuid = { workspace = true, features = ["serde", "v4"] }
which = { workspace = true }
wildmatch = { workspace = true }
tokio-util = "0.7.16"
toml = "0.9.5"
toml_edit = "0.23.3"
tracing = { version = "0.1.41", features = ["log"] }
tree-sitter = "0.25.8"
tree-sitter-bash = "0.25.0"
uuid = { version = "1", features = ["serde", "v4"] }
whoami = "1.6.0"
wildmatch = "2.4.0"
[target.'cfg(target_os = "linux")'.dependencies]
landlock = { workspace = true }
seccompiler = { workspace = true }
landlock = "0.4.1"
seccompiler = "0.5.0"
# Build OpenSSL from source for musl builds.
[target.x86_64-unknown-linux-musl.dependencies]
openssl-sys = { workspace = true, features = ["vendored"] }
openssl-sys = { version = "*", features = ["vendored"] }
# Build OpenSSL from source for musl builds.
[target.aarch64-unknown-linux-musl.dependencies]
openssl-sys = { workspace = true, features = ["vendored"] }
openssl-sys = { version = "*", features = ["vendored"] }
[dev-dependencies]
assert_cmd = { workspace = true }
core_test_support = { workspace = true }
escargot = { workspace = true }
maplit = { workspace = true }
predicates = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
tokio-test = { workspace = true }
walkdir = { workspace = true }
wiremock = { workspace = true }
[package.metadata.cargo-shear]
ignored = ["openssl-sys"]
assert_cmd = "2"
core_test_support = { path = "tests/common" }
maplit = "1.0.2"
predicates = "3"
pretty_assertions = "1.4.1"
tempfile = "3"
tokio-test = "0.4"
walkdir = "2.5.0"
wiremock = "0.6"

View File

@@ -1,104 +0,0 @@
You are Codex, based on GPT-5. You are running as a coding agent in the Codex CLI on a user's computer.
## General
- The arguments to `shell` will be passed to execvp(). Most terminal commands should be prefixed with ["bash", "-lc"].
- Always set the `workdir` param when using the shell function. Do not use `cd` unless absolutely necessary.
- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
## Editing constraints
- Default to ASCII when editing or creating files. Only introduce non-ASCII or other Unicode characters when there is a clear justification and the file already uses them.
- Add succinct code comments that explain what is going on if code is not self-explanatory. You should not add comments like "Assigns the value to the variable", but a brief comment might be useful ahead of a complex code block that the user would otherwise have to spend time parsing out. Usage of these comments should be rare.
- You may be in a dirty git worktree.
* NEVER revert existing changes you did not make unless explicitly requested, since these changes were made by the user.
* If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, don't revert those changes.
* If the changes are in files you've touched recently, you should read carefully and understand how you can work with the changes rather than reverting them.
* If the changes are in unrelated files, just ignore them and don't revert them.
- While you are working, you might notice unexpected changes that you didn't make. If this happens, STOP IMMEDIATELY and ask the user how they would like to proceed.
## Plan tool
When using the planning tool:
- Skip using the planning tool for straightforward tasks (roughly the easiest 25%).
- Do not make single-step plans.
- When you made a plan, update it after having performed one of the sub-tasks that you shared on the plan.
## Codex CLI harness, sandboxing, and approvals
The Codex CLI harness supports several different configurations for sandboxing and escalation approvals that the user can choose from.
Filesystem sandboxing defines which files can be read or written. The options for `sandbox_mode` are:
- **read-only**: The sandbox only permits reading files.
- **workspace-write**: The sandbox permits reading files, and editing files in `cwd` and `writable_roots`. Editing files in other directories requires approval.
- **danger-full-access**: No filesystem sandboxing - all commands are permitted.
Network sandboxing defines whether network can be accessed without approval. Options for `network_access` are:
- **restricted**: Requires approval
- **enabled**: No approval needed
Approvals are your mechanism to get user consent to run shell commands without the sandbox. Possible configuration options for `approval_policy` are
- **untrusted**: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
- **on-failure**: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
- **on-request**: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for it in the `shell` command description.)
- **never**: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is paired with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
When you are running with `approval_policy == on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /var)
- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval. ALWAYS proceed to use the `with_escalated_permissions` and `justification` parameters - do not message the user before requesting approval for the command.
- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
- (for all of these, you should weigh alternative paths that do not require approval)
When `sandbox_mode` is set to read-only, you'll need to request approval for any command that isn't a read.
You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing enabled, and approval on-failure.
Although they introduce friction to the user because your work is paused until the user responds, you should leverage them when necessary to accomplish important work. If the completing the task requires escalated permissions, Do not let these settings or the sandbox deter you from attempting to accomplish the user's task unless it is set to "never", in which case never ask for approvals.
When requesting approval to execute a command that will require escalated privileges:
- Provide the `with_escalated_permissions` parameter with the boolean value true
- Include a short, 1 sentence explanation for why you need to enable `with_escalated_permissions` in the justification parameter
## Special user requests
- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such as `date`), you should do so.
- If the user asks for a "review", default to a code review mindset: prioritise identifying bugs, risks, behavioural regressions, and missing tests. Findings must be the primary focus of the response - keep summaries or overviews brief and only after enumerating the issues. Present findings first (ordered by severity with file/line references), follow with open questions or assumptions, and offer a change-summary only as a secondary detail. If no findings are discovered, state that explicitly and mention any residual risks or testing gaps.
## Presenting your work and final message
You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
- Default: be very concise; friendly coding teammate tone.
- Ask only when needed; suggest ideas; mirror the user's style.
- For substantial work, summarize clearly; follow finalanswer formatting.
- Skip heavy formatting for simple confirmations.
- Don't dump large files you've written; reference paths only.
- No "save/copy this file" - User is on the same machine.
- Offer logical next steps (tests, commits, build) briefly; add verify steps if you couldn't do something.
- For code changes:
* Lead with a quick explanation of the change, and then give more details on the context covering where and why a change was made. Do not start this explanation with "summary", just jump right in.
* If there are natural next steps the user may want to take, suggest them at the end of your response. Do not make suggestions if there are no natural next steps.
* When suggesting multiple options, use numeric lists for the suggestions so the user can quickly respond with a single number.
- The user does not command execution outputs. When asked to show the output of a command (e.g. `git show`), relay the important details in your answer or summarize the key lines so the user understands the result.
### Final answer structure and style guidelines
- Plain text; CLI handles styling. Use structure only when it helps scanability.
- Headers: optional; short Title Case (1-3 words) wrapped in **…**; no blank line before the first bullet; add only if they truly help.
- Bullets: use - ; merge related points; keep to one line when possible; 46 per list ordered by importance; keep phrasing consistent.
- Monospace: backticks for commands/paths/env vars/code ids and inline examples; use for literal keyword bullets; never combine with **.
- Code samples or multi-line snippets should be wrapped in fenced code blocks; add a language hint whenever obvious.
- Structure: group related bullets; order sections general → specific → supporting; for subsections, start with a bolded keyword bullet, then items; match complexity to the task.
- Tone: collaborative, concise, factual; present tense, active voice; selfcontained; no "above/below"; parallel wording.
- Don'ts: no nested bullets/hierarchies; no ANSI codes; don't cram unrelated keywords; keep keyword lists short—wrap/reformat if long; avoid naming formatting styles in answers.
- Adaptation: code explanations → precise, structured with code refs; simple tasks → lead with outcome; big changes → logical walkthrough + rationale + next actions; casual one-offs → plain sentences, no headers/bullets.
- File References: When referencing files in your response, make sure to include the relevant start line and always follow the below rules:
* Use inline code to make file paths clickable.
* Each reference should have a stand alone path. Even if it's the same file.
* Accepted: absolute, workspacerelative, a/ or b/ diff prefixes, or bare filename/suffix.
* Line/column (1based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
* Do not use URIs like file://, vscode://, or https://.
* Do not provide range of lines
* Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5

View File

@@ -14,18 +14,6 @@ Within this context, Codex refers to the open-source agentic coding interface (n
Your default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
# AGENTS.md spec
- Repos often contain AGENTS.md files. These files can appear anywhere within the repository.
- These files are a way for humans to give you (the agent) instructions or tips for working within the container.
- Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.
- Instructions in AGENTS.md files:
- The scope of an AGENTS.md file is the entire directory tree rooted at the folder that contains it.
- For every file you touch in the final patch, you must obey instructions in any AGENTS.md file whose scope includes that file.
- Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the file states otherwise.
- More-deeply-nested AGENTS.md files take precedence in the case of conflicting instructions.
- Direct system/developer/user instructions (as part of a prompt) take precedence over AGENTS.md instructions.
- The contents of the AGENTS.md file at the root of the repo and any directories from the CWD up to the root are included with the developer message and don't need to be re-read. When working in a subdirectory of CWD, or a directory outside the CWD, check for any AGENTS.md files that may be applicable.
## Responsiveness
### Preamble messages
@@ -146,6 +134,14 @@ If completing the user's task requires writing or modifying files, your code and
- Do not use one-letter variable names unless explicitly requested.
- NEVER output inline citations like "【F:README.md†L5-L14】" in your outputs. The CLI is not able to render these so they will just be broken in the UI. Instead, if you output valid filepaths, users will be able to click on them to open the files in their editor.
## Testing your work
If the codebase has tests or the ability to build or run, you should use them to verify that your work is complete. Generally, your testing philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests, or where the patterns don't indicate so.
Once you're confident in correctness, use formatting commands to ensure that your code is well formatted. These commands can take time so you should run them on as precise a target as possible. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.
For all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
## Sandbox and approvals
The Codex CLI harness supports several different sandboxing, and approval configurations that the user can choose from.
@@ -181,22 +177,6 @@ Note that when sandboxing is set to read-only, you'll need to request approval f
You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing ON, and approval on-failure.
## Validating your work
If the codebase has tests or the ability to build or run, consider using them to verify that your work is complete.
When testing, your philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests.
Similarly, once you're confident in correctness, you can suggest or use formatting commands to ensure that your code is well formatted. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.
For all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
Be mindful of whether to run validation commands proactively. In the absence of behavioral guidance:
- When running in non-interactive approval modes like **never** or **on-failure**, proactively run tests, lint and do whatever you need to ensure you've completed the task.
- When working in interactive approval modes like **untrusted**, or **on-request**, hold off on running tests or lint commands until the user is ready for you to finalize your output, because these commands take time to run and slow down iteration. Instead suggest what you want to do next, and let the user confirm first.
- When working on test-related tasks, such as adding tests, fixing tests, or reproducing a bug to verify behavior, you may proactively run tests regardless of approval mode. Use your judgement to decide whether this is a test-related task.
## Ambition vs. precision
For tasks that have no prior context (i.e. the user is starting something brand new), you should feel free to be ambitious and demonstrate creativity with your implementation.
@@ -240,6 +220,7 @@ You are producing plain text that will later be styled by the CLI. Follow these
**Bullets**
- Use `-` followed by a space for every bullet.
- Bold the keyword, then colon + concise description.
- Merge related points when possible; avoid a bullet for every trivial detail.
- Keep bullets to one line unless breaking for clarity is unavoidable.
- Group into short lists (46 bullets) ordered by importance.
@@ -251,16 +232,6 @@ You are producing plain text that will later be styled by the CLI. Follow these
- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.
- Never mix monospace and bold markers; choose one based on whether its a keyword (`**`) or inline code/path (`` ` ``).
**File References**
When referencing files in your response, make sure to include the relevant start line and always follow the below rules:
* Use inline code to make file paths clickable.
* Each reference should have a stand alone path. Even if it's the same file.
* Accepted: absolute, workspacerelative, a/ or b/ diff prefixes, or bare filename/suffix.
* Line/column (1based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
* Do not use URIs like file://, vscode://, or https://.
* Do not provide range of lines
* Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5
**Structure**
- Place related bullets together; dont mix unrelated concepts in the same section.
@@ -294,10 +265,68 @@ For casual greetings, acknowledgements, or other one-off conversational messages
## Shell commands
When using the shell, you must adhere to the following guidelines:
Do NOT use `shell`. Use only `functions_exec_command` and `functions_write_stdin`.
- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
- Read files in chunks with a max chunk size of 250 lines. Do not use python scripts to attempt to output larger chunks of a file. Command line output will be truncated after 10 kilobytes or 256 lines of output, regardless of the command used.
## `apply_patch`
Your patch language is a strippeddown, fileoriented diff format designed to be easy to parse and safe to apply. You can think of it as a highlevel envelope:
**_ Begin Patch
[ one or more file sections ]
_** End Patch
Within that envelope, you get a sequence of file operations.
You MUST include a header to specify the action you are taking.
Each operation starts with one of three headers:
**_ Add File: <path> - create a new file. Every following line is a + line (the initial contents).
_** Delete File: <path> - remove an existing file. Nothing follows.
\*\*\* Update File: <path> - patch an existing file in place (optionally with a rename).
May be immediately followed by \*\*\* Move to: <new path> if you want to rename the file.
Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
Within a hunk each line starts with:
- for inserted text,
* for removed text, or
space ( ) for context.
At the end of a truncated hunk you can emit \*\*\* End of File.
Patch := Begin { FileOp } End
Begin := "**_ Begin Patch" NEWLINE
End := "_** End Patch" NEWLINE
FileOp := AddFile | DeleteFile | UpdateFile
AddFile := "**_ Add File: " path NEWLINE { "+" line NEWLINE }
DeleteFile := "_** Delete File: " path NEWLINE
UpdateFile := "**_ Update File: " path NEWLINE [ MoveTo ] { Hunk }
MoveTo := "_** Move to: " newPath NEWLINE
Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
HunkLine := (" " | "-" | "+") text NEWLINE
A full patch can combine several operations:
**_ Begin Patch
_** Add File: hello.txt
+Hello world
**_ Update File: src/app.py
_** Move to: src/main.py
@@ def greet():
-print("Hi")
+print("Hello, world!")
**_ Delete File: obsolete.txt
_** End Patch
It is important to remember:
- You must include a header with your intended action (Add/Delete/Update)
- You must prefix new lines with `+` even when creating a new file
You can invoke apply_patch like:
```
shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
```
## `update_plan`

View File

@@ -1,87 +0,0 @@
# Review guidelines:
You are acting as a reviewer for a proposed code change made by another engineer.
Below are some default guidelines for determining whether the original author would appreciate the issue being flagged.
These are not the final word in determining whether an issue is a bug. In many cases, you will encounter other, more specific guidelines. These may be present elsewhere in a developer message, a user message, a file, or even elsewhere in this system message.
Those guidelines should be considered to override these general instructions.
Here are the general guidelines for determining whether something is a bug and should be flagged.
1. It meaningfully impacts the accuracy, performance, security, or maintainability of the code.
2. The bug is discrete and actionable (i.e. not a general issue with the codebase or a combination of multiple issues).
3. Fixing the bug does not demand a level of rigor that is not present in the rest of the codebase (e.g. one doesn't need very detailed comments and input validation in a repository of one-off scripts in personal projects)
4. The bug was introduced in the commit (pre-existing bugs should not be flagged).
5. The author of the original PR would likely fix the issue if they were made aware of it.
6. The bug does not rely on unstated assumptions about the codebase or author's intent.
7. It is not enough to speculate that a change may disrupt another part of the codebase, to be considered a bug, one must identify the other parts of the code that are provably affected.
8. The bug is clearly not just an intentional change by the original author.
When flagging a bug, you will also provide an accompanying comment. Once again, these guidelines are not the final word on how to construct a comment -- defer to any subsequent guidelines that you encounter.
1. The comment should be clear about why the issue is a bug.
2. The comment should appropriately communicate the severity of the issue. It should not claim that an issue is more severe than it actually is.
3. The comment should be brief. The body should be at most 1 paragraph. It should not introduce line breaks within the natural language flow unless it is necessary for the code fragment.
4. The comment should not include any chunks of code longer than 3 lines. Any code chunks should be wrapped in markdown inline code tags or a code block.
5. The comment should clearly and explicitly communicate the scenarios, environments, or inputs that are necessary for the bug to arise. The comment should immediately indicate that the issue's severity depends on these factors.
6. The comment's tone should be matter-of-fact and not accusatory or overly positive. It should read as a helpful AI assistant suggestion without sounding too much like a human reviewer.
7. The comment should be written such that the original author can immediately grasp the idea without close reading.
8. The comment should avoid excessive flattery and comments that are not helpful to the original author. The comment should avoid phrasing like "Great job ...", "Thanks for ...".
Below are some more detailed guidelines that you should apply to this specific review.
HOW MANY FINDINGS TO RETURN:
Output all findings that the original author would fix if they knew about it. If there is no finding that a person would definitely love to see and fix, prefer outputting no findings. Do not stop at the first qualifying finding. Continue until you've listed every qualifying finding.
GUIDELINES:
- Ignore trivial style unless it obscures meaning or violates documented standards.
- Use one comment per distinct issue (or a multi-line range if necessary).
- Use ```suggestion blocks ONLY for concrete replacement code (minimal lines; no commentary inside the block).
- In every ```suggestion block, preserve the exact leading whitespace of the replaced lines (spaces vs tabs, number of spaces).
- Do NOT introduce or remove outer indentation levels unless that is the actual fix.
The comments will be presented in the code review as inline comments. You should avoid providing unnecessary location details in the comment body. Always keep the line range as short as possible for interpreting the issue. Avoid ranges longer than 510 lines; instead, choose the most suitable subrange that pinpoints the problem.
At the beginning of the finding title, tag the bug with priority level. For example "[P1] Un-padding slices along wrong tensor dimensions". [P0] Drop everything to fix. Blocking release, operations, or major usage. Only use for universal issues that do not depend on any assumptions about the inputs. · [P1] Urgent. Should be addressed in the next cycle · [P2] Normal. To be fixed eventually · [P3] Low. Nice to have.
Additionally, include a numeric priority field in the JSON output for each finding: set "priority" to 0 for P0, 1 for P1, 2 for P2, or 3 for P3. If a priority cannot be determined, omit the field or use null.
At the end of your findings, output an "overall correctness" verdict of whether or not the patch should be considered "correct".
Correct implies that existing code and tests will not break, and the patch is free of bugs and other blocking issues.
Ignore non-blocking issues such as style, formatting, typos, documentation, and other nits.
FORMATTING GUIDELINES:
The finding description should be one paragraph.
OUTPUT FORMAT:
## Output schema — MUST MATCH *exactly*
```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, optional>,
"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>
}
```
* **Do not** wrap the JSON in markdown fences or extra prose.
* The code_location field is required and must include absolute_file_path and line_range.
*Line ranges must be as short as possible for interpreting the issue (avoid ranges over 510 lines; pick the most suitable subrange).
* The code_location should overlap with the diff.
* Do not generate a PR fix.

View File

@@ -1,6 +1,7 @@
use crate::codex::Session;
use crate::codex::TurnContext;
use crate::function_tool::FunctionCallError;
use crate::models::FunctionCallOutputPayload;
use crate::models::ResponseInputItem;
use crate::protocol::FileChange;
use crate::protocol::ReviewDecision;
use crate::safety::SafetyCheck;
@@ -16,7 +17,7 @@ pub(crate) enum InternalApplyPatchInvocation {
/// The `apply_patch` call was handled programmatically, without any sort
/// of sandbox, because the user explicitly approved it. This is the
/// result to use with the `shell` function call that contained `apply_patch`.
Output(Result<String, FunctionCallError>),
Output(ResponseInputItem),
/// The `apply_patch` call was approved, either automatically because it
/// appears that it should be allowed based on the user's sandbox policy
@@ -32,6 +33,12 @@ pub(crate) struct ApplyPatchExec {
pub(crate) user_explicitly_approved_this_action: bool,
}
impl From<ResponseInputItem> for InternalApplyPatchInvocation {
fn from(item: ResponseInputItem) -> Self {
InternalApplyPatchInvocation::Output(item)
}
}
pub(crate) async fn apply_patch(
sess: &Session,
turn_context: &TurnContext,
@@ -70,15 +77,25 @@ pub(crate) async fn apply_patch(
})
}
ReviewDecision::Denied | ReviewDecision::Abort => {
InternalApplyPatchInvocation::Output(Err(FunctionCallError::RespondToModel(
"patch rejected by user".to_string(),
)))
ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: "patch rejected by user".to_string(),
success: Some(false),
},
}
.into()
}
}
}
SafetyCheck::Reject { reason } => InternalApplyPatchInvocation::Output(Err(
FunctionCallError::RespondToModel(format!("patch rejected: {reason}")),
)),
SafetyCheck::Reject { reason } => ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: format!("patch rejected: {reason}"),
success: Some(false),
},
}
.into(),
}
}
@@ -92,9 +109,7 @@ pub(crate) fn convert_apply_patch_to_protocol(
ApplyPatchFileChange::Add { content } => FileChange::Add {
content: content.clone(),
},
ApplyPatchFileChange::Delete { content } => FileChange::Delete {
content: content.clone(),
},
ApplyPatchFileChange::Delete => FileChange::Delete,
ApplyPatchFileChange::Update {
unified_diff,
move_path,

View File

@@ -1,662 +0,0 @@
use chrono::DateTime;
use chrono::Utc;
use serde::Deserialize;
use serde::Serialize;
use std::env;
use std::fs::File;
use std::fs::OpenOptions;
use std::io::Read;
use std::io::Write;
#[cfg(unix)]
use std::os::unix::fs::OpenOptionsExt;
use std::path::Path;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::Mutex;
use std::time::Duration;
use codex_protocol::mcp_protocol::AuthMode;
use crate::token_data::PlanType;
use crate::token_data::TokenData;
use crate::token_data::parse_id_token;
#[derive(Debug, Clone)]
pub struct CodexAuth {
pub mode: AuthMode,
pub(crate) api_key: Option<String>,
pub(crate) auth_dot_json: Arc<Mutex<Option<AuthDotJson>>>,
pub(crate) auth_file: PathBuf,
pub(crate) client: reqwest::Client,
}
impl PartialEq for CodexAuth {
fn eq(&self, other: &Self) -> bool {
self.mode == other.mode
}
}
impl CodexAuth {
pub async fn refresh_token(&self) -> Result<String, std::io::Error> {
let token_data = self
.get_current_token_data()
.ok_or(std::io::Error::other("Token data is not available."))?;
let token = token_data.refresh_token;
let refresh_response = try_refresh_token(token, &self.client)
.await
.map_err(std::io::Error::other)?;
let updated = update_tokens(
&self.auth_file,
refresh_response.id_token,
refresh_response.access_token,
refresh_response.refresh_token,
)
.await?;
if let Ok(mut auth_lock) = self.auth_dot_json.lock() {
*auth_lock = Some(updated.clone());
}
let access = match updated.tokens {
Some(t) => t.access_token,
None => {
return Err(std::io::Error::other(
"Token data is not available after refresh.",
));
}
};
Ok(access)
}
/// Loads the available auth information from the auth.json.
pub fn from_codex_home(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
load_auth(codex_home)
}
pub async fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
let auth_dot_json: Option<AuthDotJson> = self.get_current_auth_json();
match auth_dot_json {
Some(AuthDotJson {
tokens: Some(mut tokens),
last_refresh: Some(last_refresh),
..
}) => {
if last_refresh < Utc::now() - chrono::Duration::days(28) {
let refresh_response = tokio::time::timeout(
Duration::from_secs(60),
try_refresh_token(tokens.refresh_token.clone(), &self.client),
)
.await
.map_err(|_| {
std::io::Error::other("timed out while refreshing OpenAI API key")
})?
.map_err(std::io::Error::other)?;
let updated_auth_dot_json = update_tokens(
&self.auth_file,
refresh_response.id_token,
refresh_response.access_token,
refresh_response.refresh_token,
)
.await?;
tokens = updated_auth_dot_json
.tokens
.clone()
.ok_or(std::io::Error::other(
"Token data is not available after refresh.",
))?;
#[expect(clippy::unwrap_used)]
let mut auth_lock = self.auth_dot_json.lock().unwrap();
*auth_lock = Some(updated_auth_dot_json);
}
Ok(tokens)
}
_ => Err(std::io::Error::other("Token data is not available.")),
}
}
pub async fn get_token(&self) -> Result<String, std::io::Error> {
match self.mode {
AuthMode::ApiKey => Ok(self.api_key.clone().unwrap_or_default()),
AuthMode::ChatGPT => {
let id_token = self.get_token_data().await?.access_token;
Ok(id_token)
}
}
}
pub fn get_account_id(&self) -> Option<String> {
self.get_current_token_data().and_then(|t| t.account_id)
}
pub(crate) fn get_plan_type(&self) -> Option<PlanType> {
self.get_current_token_data()
.and_then(|t| t.id_token.chatgpt_plan_type)
}
fn get_current_auth_json(&self) -> Option<AuthDotJson> {
#[expect(clippy::unwrap_used)]
self.auth_dot_json.lock().unwrap().clone()
}
fn get_current_token_data(&self) -> Option<TokenData> {
self.get_current_auth_json().and_then(|t| t.tokens)
}
/// Consider this private to integration tests.
pub fn create_dummy_chatgpt_auth_for_testing() -> Self {
let auth_dot_json = AuthDotJson {
openai_api_key: None,
tokens: Some(TokenData {
id_token: Default::default(),
access_token: "Access Token".to_string(),
refresh_token: "test".to_string(),
account_id: Some("account_id".to_string()),
}),
last_refresh: Some(Utc::now()),
};
let auth_dot_json = Arc::new(Mutex::new(Some(auth_dot_json)));
Self {
api_key: None,
mode: AuthMode::ChatGPT,
auth_file: PathBuf::new(),
auth_dot_json,
client: crate::default_client::create_client(),
}
}
fn from_api_key_with_client(api_key: &str, client: reqwest::Client) -> Self {
Self {
api_key: Some(api_key.to_owned()),
mode: AuthMode::ApiKey,
auth_file: PathBuf::new(),
auth_dot_json: Arc::new(Mutex::new(None)),
client,
}
}
pub fn from_api_key(api_key: &str) -> Self {
Self::from_api_key_with_client(api_key, crate::default_client::create_client())
}
}
pub const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
pub fn read_openai_api_key_from_env() -> Option<String> {
env::var(OPENAI_API_KEY_ENV_VAR)
.ok()
.map(|value| value.trim().to_string())
.filter(|value| !value.is_empty())
}
pub fn get_auth_file(codex_home: &Path) -> PathBuf {
codex_home.join("auth.json")
}
/// Delete the auth.json file inside `codex_home` if it exists. Returns `Ok(true)`
/// if a file was removed, `Ok(false)` if no auth file was present.
pub fn logout(codex_home: &Path) -> std::io::Result<bool> {
let auth_file = get_auth_file(codex_home);
match std::fs::remove_file(&auth_file) {
Ok(_) => Ok(true),
Err(err) if err.kind() == std::io::ErrorKind::NotFound => Ok(false),
Err(err) => Err(err),
}
}
/// Writes an `auth.json` that contains only the API key.
pub fn login_with_api_key(codex_home: &Path, api_key: &str) -> std::io::Result<()> {
let auth_dot_json = AuthDotJson {
openai_api_key: Some(api_key.to_string()),
tokens: None,
last_refresh: None,
};
write_auth_json(&get_auth_file(codex_home), &auth_dot_json)
}
fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
let auth_file = get_auth_file(codex_home);
let client = crate::default_client::create_client();
let auth_dot_json = match try_read_auth_json(&auth_file) {
Ok(auth) => auth,
Err(e) => {
return Err(e);
}
};
let AuthDotJson {
openai_api_key: auth_json_api_key,
tokens,
last_refresh,
} = auth_dot_json;
// Prefer AuthMode.ApiKey if it's set in the auth.json.
if let Some(api_key) = &auth_json_api_key {
return Ok(Some(CodexAuth::from_api_key_with_client(api_key, client)));
}
Ok(Some(CodexAuth {
api_key: None,
mode: AuthMode::ChatGPT,
auth_file,
auth_dot_json: Arc::new(Mutex::new(Some(AuthDotJson {
openai_api_key: None,
tokens,
last_refresh,
}))),
client,
}))
}
/// Attempt to read and refresh the `auth.json` file in the given `CODEX_HOME` directory.
/// Returns the full AuthDotJson structure after refreshing if necessary.
pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
let mut file = File::open(auth_file)?;
let mut contents = String::new();
file.read_to_string(&mut contents)?;
let auth_dot_json: AuthDotJson = serde_json::from_str(&contents)?;
Ok(auth_dot_json)
}
pub fn write_auth_json(auth_file: &Path, auth_dot_json: &AuthDotJson) -> std::io::Result<()> {
if let Some(parent) = auth_file.parent() {
std::fs::create_dir_all(parent)?;
}
let json_data = serde_json::to_string_pretty(auth_dot_json)?;
let mut options = OpenOptions::new();
options.truncate(true).write(true).create(true);
#[cfg(unix)]
{
options.mode(0o600);
}
let mut file = options.open(auth_file)?;
file.write_all(json_data.as_bytes())?;
file.flush()?;
Ok(())
}
async fn update_tokens(
auth_file: &Path,
id_token: String,
access_token: Option<String>,
refresh_token: Option<String>,
) -> std::io::Result<AuthDotJson> {
let mut auth_dot_json = try_read_auth_json(auth_file)?;
let tokens = auth_dot_json.tokens.get_or_insert_with(TokenData::default);
tokens.id_token = parse_id_token(&id_token).map_err(std::io::Error::other)?;
if let Some(access_token) = access_token {
tokens.access_token = access_token;
}
if let Some(refresh_token) = refresh_token {
tokens.refresh_token = refresh_token;
}
auth_dot_json.last_refresh = Some(Utc::now());
write_auth_json(auth_file, &auth_dot_json)?;
Ok(auth_dot_json)
}
async fn try_refresh_token(
refresh_token: String,
client: &reqwest::Client,
) -> std::io::Result<RefreshResponse> {
let refresh_request = RefreshRequest {
client_id: CLIENT_ID,
grant_type: "refresh_token",
refresh_token,
scope: "openid profile email",
};
// Use shared client factory to include standard headers
let response = client
.post("https://auth.openai.com/oauth/token")
.header("Content-Type", "application/json")
.json(&refresh_request)
.send()
.await
.map_err(std::io::Error::other)?;
if response.status().is_success() {
let refresh_response = response
.json::<RefreshResponse>()
.await
.map_err(std::io::Error::other)?;
Ok(refresh_response)
} else {
Err(std::io::Error::other(format!(
"Failed to refresh token: {}",
response.status()
)))
}
}
#[derive(Serialize)]
struct RefreshRequest {
client_id: &'static str,
grant_type: &'static str,
refresh_token: String,
scope: &'static str,
}
#[derive(Deserialize, Clone)]
struct RefreshResponse {
id_token: String,
access_token: Option<String>,
refresh_token: Option<String>,
}
/// Expected structure for $CODEX_HOME/auth.json.
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq)]
pub struct AuthDotJson {
#[serde(rename = "OPENAI_API_KEY")]
pub openai_api_key: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub tokens: Option<TokenData>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub last_refresh: Option<DateTime<Utc>>,
}
// Shared constant for token refresh (client id used for oauth token refresh flow)
pub const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
use std::sync::RwLock;
/// Internal cached auth state.
#[derive(Clone, Debug)]
struct CachedAuth {
auth: Option<CodexAuth>,
}
#[cfg(test)]
mod tests {
use super::*;
use crate::token_data::IdTokenInfo;
use crate::token_data::KnownPlan;
use crate::token_data::PlanType;
use base64::Engine;
use pretty_assertions::assert_eq;
use serde::Serialize;
use serde_json::json;
use tempfile::tempdir;
const LAST_REFRESH: &str = "2025-08-06T20:41:36.232376Z";
#[tokio::test]
async fn roundtrip_auth_dot_json() {
let codex_home = tempdir().unwrap();
let _ = write_auth_file(
AuthFileParams {
openai_api_key: None,
chatgpt_plan_type: "pro".to_string(),
},
codex_home.path(),
)
.expect("failed to write auth file");
let file = get_auth_file(codex_home.path());
let auth_dot_json = try_read_auth_json(&file).unwrap();
write_auth_json(&file, &auth_dot_json).unwrap();
let same_auth_dot_json = try_read_auth_json(&file).unwrap();
assert_eq!(auth_dot_json, same_auth_dot_json);
}
#[test]
fn login_with_api_key_overwrites_existing_auth_json() {
let dir = tempdir().unwrap();
let auth_path = dir.path().join("auth.json");
let stale_auth = json!({
"OPENAI_API_KEY": "sk-old",
"tokens": {
"id_token": "stale.header.payload",
"access_token": "stale-access",
"refresh_token": "stale-refresh",
"account_id": "stale-acc"
}
});
std::fs::write(
&auth_path,
serde_json::to_string_pretty(&stale_auth).unwrap(),
)
.unwrap();
super::login_with_api_key(dir.path(), "sk-new").expect("login_with_api_key should succeed");
let auth = super::try_read_auth_json(&auth_path).expect("auth.json should parse");
assert_eq!(auth.openai_api_key.as_deref(), Some("sk-new"));
assert!(auth.tokens.is_none(), "tokens should be cleared");
}
#[tokio::test]
async fn pro_account_with_no_api_key_uses_chatgpt_auth() {
let codex_home = tempdir().unwrap();
let fake_jwt = write_auth_file(
AuthFileParams {
openai_api_key: None,
chatgpt_plan_type: "pro".to_string(),
},
codex_home.path(),
)
.expect("failed to write auth file");
let CodexAuth {
api_key,
mode,
auth_dot_json,
auth_file: _,
..
} = super::load_auth(codex_home.path()).unwrap().unwrap();
assert_eq!(None, api_key);
assert_eq!(AuthMode::ChatGPT, mode);
let guard = auth_dot_json.lock().unwrap();
let auth_dot_json = guard.as_ref().expect("AuthDotJson should exist");
assert_eq!(
&AuthDotJson {
openai_api_key: None,
tokens: Some(TokenData {
id_token: IdTokenInfo {
email: Some("user@example.com".to_string()),
chatgpt_plan_type: Some(PlanType::Known(KnownPlan::Pro)),
raw_jwt: fake_jwt,
},
access_token: "test-access-token".to_string(),
refresh_token: "test-refresh-token".to_string(),
account_id: None,
}),
last_refresh: Some(
DateTime::parse_from_rfc3339(LAST_REFRESH)
.unwrap()
.with_timezone(&Utc)
),
},
auth_dot_json
)
}
#[tokio::test]
async fn loads_api_key_from_auth_json() {
let dir = tempdir().unwrap();
let auth_file = dir.path().join("auth.json");
std::fs::write(
auth_file,
r#"{"OPENAI_API_KEY":"sk-test-key","tokens":null,"last_refresh":null}"#,
)
.unwrap();
let auth = super::load_auth(dir.path()).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key, Some("sk-test-key".to_string()));
assert!(auth.get_token_data().await.is_err());
}
#[test]
fn logout_removes_auth_file() -> Result<(), std::io::Error> {
let dir = tempdir()?;
let auth_dot_json = AuthDotJson {
openai_api_key: Some("sk-test-key".to_string()),
tokens: None,
last_refresh: None,
};
write_auth_json(&get_auth_file(dir.path()), &auth_dot_json)?;
assert!(dir.path().join("auth.json").exists());
let removed = logout(dir.path())?;
assert!(removed);
assert!(!dir.path().join("auth.json").exists());
Ok(())
}
struct AuthFileParams {
openai_api_key: Option<String>,
chatgpt_plan_type: String,
}
fn write_auth_file(params: AuthFileParams, codex_home: &Path) -> std::io::Result<String> {
let auth_file = get_auth_file(codex_home);
// Create a minimal valid JWT for the id_token field.
#[derive(Serialize)]
struct Header {
alg: &'static str,
typ: &'static str,
}
let header = Header {
alg: "none",
typ: "JWT",
};
let payload = serde_json::json!({
"email": "user@example.com",
"email_verified": true,
"https://api.openai.com/auth": {
"chatgpt_account_id": "bc3618e3-489d-4d49-9362-1561dc53ba53",
"chatgpt_plan_type": params.chatgpt_plan_type,
"chatgpt_user_id": "user-12345",
"user_id": "user-12345",
}
});
let b64 = |b: &[u8]| base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(b);
let header_b64 = b64(&serde_json::to_vec(&header)?);
let payload_b64 = b64(&serde_json::to_vec(&payload)?);
let signature_b64 = b64(b"sig");
let fake_jwt = format!("{header_b64}.{payload_b64}.{signature_b64}");
let auth_json_data = json!({
"OPENAI_API_KEY": params.openai_api_key,
"tokens": {
"id_token": fake_jwt,
"access_token": "test-access-token",
"refresh_token": "test-refresh-token"
},
"last_refresh": LAST_REFRESH,
});
let auth_json = serde_json::to_string_pretty(&auth_json_data)?;
std::fs::write(auth_file, auth_json)?;
Ok(fake_jwt)
}
}
/// Central manager providing a single source of truth for auth.json derived
/// authentication data. It loads once (or on preference change) and then
/// hands out cloned `CodexAuth` values so the rest of the program has a
/// consistent snapshot.
///
/// External modifications to `auth.json` will NOT be observed until
/// `reload()` is called explicitly. This matches the design goal of avoiding
/// different parts of the program seeing inconsistent auth data midrun.
#[derive(Debug)]
pub struct AuthManager {
codex_home: PathBuf,
inner: RwLock<CachedAuth>,
}
impl AuthManager {
/// Create a new manager loading the initial auth using the provided
/// preferred auth method. Errors loading auth are swallowed; `auth()` will
/// simply return `None` in that case so callers can treat it as an
/// unauthenticated state.
pub fn new(codex_home: PathBuf) -> Self {
let auth = CodexAuth::from_codex_home(&codex_home).ok().flatten();
Self {
codex_home,
inner: RwLock::new(CachedAuth { auth }),
}
}
/// Create an AuthManager with a specific CodexAuth, for testing only.
pub fn from_auth_for_testing(auth: CodexAuth) -> Arc<Self> {
let cached = CachedAuth { auth: Some(auth) };
Arc::new(Self {
codex_home: PathBuf::new(),
inner: RwLock::new(cached),
})
}
/// Current cached auth (clone). May be `None` if not logged in or load failed.
pub fn auth(&self) -> Option<CodexAuth> {
self.inner.read().ok().and_then(|c| c.auth.clone())
}
/// Force a reload of the auth information from auth.json. Returns
/// whether the auth value changed.
pub fn reload(&self) -> bool {
let new_auth = CodexAuth::from_codex_home(&self.codex_home).ok().flatten();
if let Ok(mut guard) = self.inner.write() {
let changed = !AuthManager::auths_equal(&guard.auth, &new_auth);
guard.auth = new_auth;
changed
} else {
false
}
}
fn auths_equal(a: &Option<CodexAuth>, b: &Option<CodexAuth>) -> bool {
match (a, b) {
(None, None) => true,
(Some(a), Some(b)) => a == b,
_ => false,
}
}
/// Convenience constructor returning an `Arc` wrapper.
pub fn shared(codex_home: PathBuf) -> Arc<Self> {
Arc::new(Self::new(codex_home))
}
/// Attempt to refresh the current auth token (if any). On success, reload
/// the auth state from disk so other components observe refreshed token.
pub async fn refresh_token(&self) -> std::io::Result<Option<String>> {
let auth = match self.auth() {
Some(a) => a,
None => return Ok(None),
};
match auth.refresh_token().await {
Ok(token) => {
// Reload to pick up persisted changes.
self.reload();
Ok(Some(token))
}
Err(e) => Err(e),
}
}
/// Log out by deleting the ondisk auth.json (if present). Returns Ok(true)
/// if a file was removed, Ok(false) if no auth file existed. On success,
/// reloads the inmemory auth cache so callers immediately observe the
/// unauthenticated state.
pub fn logout(&self) -> std::io::Result<bool> {
let removed = super::auth::logout(&self.codex_home)?;
// Always reload to clear any cached auth (even if file absent).
self.reload();
Ok(removed)
}
}

View File

@@ -1,4 +1,3 @@
use tree_sitter::Node;
use tree_sitter::Parser;
use tree_sitter::Tree;
use tree_sitter_bash::LANGUAGE as BASH;
@@ -74,9 +73,6 @@ pub fn try_parse_word_only_commands_sequence(tree: &Tree, src: &str) -> Option<V
}
}
// Walk uses a stack (LIFO), so re-sort by position to restore source order.
command_nodes.sort_by_key(Node::start_byte);
let mut commands = Vec::new();
for node in command_nodes {
if let Some(words) = parse_plain_command_from_node(node, src) {
@@ -88,21 +84,6 @@ pub fn try_parse_word_only_commands_sequence(tree: &Tree, src: &str) -> Option<V
Some(commands)
}
/// Returns the sequence of plain commands within a `bash -lc "..."` invocation
/// when the script only contains word-only commands joined by safe operators.
pub fn parse_bash_lc_plain_commands(command: &[String]) -> Option<Vec<Vec<String>>> {
let [bash, flag, script] = command else {
return None;
};
if bash != "bash" || flag != "-lc" {
return None;
}
let tree = try_parse_bash(script)?;
try_parse_word_only_commands_sequence(&tree, script)
}
fn parse_plain_command_from_node(cmd: tree_sitter::Node, src: &str) -> Option<Vec<String>> {
if cmd.kind() != "command" {
return None;
@@ -169,10 +150,10 @@ mod tests {
let src = "ls && pwd; echo 'hi there' | wc -l";
let cmds = parse_seq(src).unwrap();
let expected: Vec<Vec<String>> = vec![
vec!["ls".to_string()],
vec!["pwd".to_string()],
vec!["echo".to_string(), "hi there".to_string()],
vec!["wc".to_string(), "-l".to_string()],
vec!["echo".to_string(), "hi there".to_string()],
vec!["pwd".to_string()],
vec!["ls".to_string()],
];
assert_eq!(cmds, expected);
}

View File

@@ -22,11 +22,11 @@ use crate::client_common::ResponseStream;
use crate::error::CodexErr;
use crate::error::Result;
use crate::model_family::ModelFamily;
use crate::models::ContentItem;
use crate::models::ReasoningItemContent;
use crate::models::ResponseItem;
use crate::openai_tools::create_tools_json_for_chat_completions_api;
use crate::util::backoff;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ReasoningItemContent;
use codex_protocol::models::ResponseItem;
/// Implementation for the classic Chat Completions API.
pub(crate) async fn stream_chat_completions(
@@ -35,12 +35,6 @@ pub(crate) async fn stream_chat_completions(
client: &reqwest::Client,
provider: &ModelProviderInfo,
) -> Result<ResponseStream> {
if prompt.output_schema.is_some() {
return Err(CodexErr::UnsupportedOperation(
"output_schema is not supported for Chat Completions API".to_string(),
));
}
// Build messages array
let mut messages = Vec::<serde_json::Value>::new();
@@ -49,107 +43,7 @@ pub(crate) async fn stream_chat_completions(
let input = prompt.get_formatted_input();
// Pre-scan: map Reasoning blocks to the adjacent assistant anchor after the last user.
// - If the last emitted message is a user message, drop all reasoning.
// - Otherwise, for each Reasoning item after the last user message, attach it
// to the immediate previous assistant message (stop turns) or the immediate
// next assistant anchor (tool-call turns: function/local shell call, or assistant message).
let mut reasoning_by_anchor_index: std::collections::HashMap<usize, String> =
std::collections::HashMap::new();
// Determine the last role that would be emitted to Chat Completions.
let mut last_emitted_role: Option<&str> = None;
for item in &input {
match item {
ResponseItem::Message { role, .. } => last_emitted_role = Some(role.as_str()),
ResponseItem::FunctionCall { .. } | ResponseItem::LocalShellCall { .. } => {
last_emitted_role = Some("assistant")
}
ResponseItem::FunctionCallOutput { .. } => last_emitted_role = Some("tool"),
ResponseItem::Reasoning { .. } | ResponseItem::Other => {}
ResponseItem::CustomToolCall { .. } => {}
ResponseItem::CustomToolCallOutput { .. } => {}
ResponseItem::WebSearchCall { .. } => {}
}
}
// Find the last user message index in the input.
let mut last_user_index: Option<usize> = None;
for (idx, item) in input.iter().enumerate() {
if let ResponseItem::Message { role, .. } = item
&& role == "user"
{
last_user_index = Some(idx);
}
}
// Attach reasoning only if the conversation does not end with a user message.
if !matches!(last_emitted_role, Some("user")) {
for (idx, item) in input.iter().enumerate() {
// Only consider reasoning that appears after the last user message.
if let Some(u_idx) = last_user_index
&& idx <= u_idx
{
continue;
}
if let ResponseItem::Reasoning {
content: Some(items),
..
} = item
{
let mut text = String::new();
for c in items {
match c {
ReasoningItemContent::ReasoningText { text: t }
| ReasoningItemContent::Text { text: t } => text.push_str(t),
}
}
if text.trim().is_empty() {
continue;
}
// Prefer immediate previous assistant message (stop turns)
let mut attached = false;
if idx > 0
&& let ResponseItem::Message { role, .. } = &input[idx - 1]
&& role == "assistant"
{
reasoning_by_anchor_index
.entry(idx - 1)
.and_modify(|v| v.push_str(&text))
.or_insert(text.clone());
attached = true;
}
// Otherwise, attach to immediate next assistant anchor (tool-calls or assistant message)
if !attached && idx + 1 < input.len() {
match &input[idx + 1] {
ResponseItem::FunctionCall { .. } | ResponseItem::LocalShellCall { .. } => {
reasoning_by_anchor_index
.entry(idx + 1)
.and_modify(|v| v.push_str(&text))
.or_insert(text.clone());
}
ResponseItem::Message { role, .. } if role == "assistant" => {
reasoning_by_anchor_index
.entry(idx + 1)
.and_modify(|v| v.push_str(&text))
.or_insert(text.clone());
}
_ => {}
}
}
}
}
}
// Track last assistant text we emitted to avoid duplicate assistant messages
// in the outbound Chat Completions payload (can happen if a final
// aggregated assistant message was recorded alongside an earlier partial).
let mut last_assistant_text: Option<String> = None;
for (idx, item) in input.iter().enumerate() {
match item {
ResponseItem::Message { role, content, .. } => {
let mut text = String::new();
@@ -162,24 +56,7 @@ pub(crate) async fn stream_chat_completions(
_ => {}
}
}
// Skip exact-duplicate assistant messages.
if role == "assistant" {
if let Some(prev) = &last_assistant_text
&& prev == &text
{
continue;
}
last_assistant_text = Some(text.clone());
}
let mut msg = json!({"role": role, "content": text});
if role == "assistant"
&& let Some(reasoning) = reasoning_by_anchor_index.get(&idx)
&& let Some(obj) = msg.as_object_mut()
{
obj.insert("reasoning".to_string(), json!(reasoning));
}
messages.push(msg);
messages.push(json!({"role": role, "content": text}));
}
ResponseItem::FunctionCall {
name,
@@ -187,7 +64,7 @@ pub(crate) async fn stream_chat_completions(
call_id,
..
} => {
let mut msg = json!({
messages.push(json!({
"role": "assistant",
"content": null,
"tool_calls": [{
@@ -198,13 +75,7 @@ pub(crate) async fn stream_chat_completions(
"arguments": arguments,
}
}]
});
if let Some(reasoning) = reasoning_by_anchor_index.get(&idx)
&& let Some(obj) = msg.as_object_mut()
{
obj.insert("reasoning".to_string(), json!(reasoning));
}
messages.push(msg);
}));
}
ResponseItem::LocalShellCall {
id,
@@ -213,7 +84,7 @@ pub(crate) async fn stream_chat_completions(
action,
} => {
// Confirm with API team.
let mut msg = json!({
messages.push(json!({
"role": "assistant",
"content": null,
"tool_calls": [{
@@ -222,13 +93,7 @@ pub(crate) async fn stream_chat_completions(
"status": status,
"action": action,
}]
});
if let Some(reasoning) = reasoning_by_anchor_index.get(&idx)
&& let Some(obj) = msg.as_object_mut()
{
obj.insert("reasoning".to_string(), json!(reasoning));
}
messages.push(msg);
}));
}
ResponseItem::FunctionCallOutput { call_id, output } => {
messages.push(json!({
@@ -237,36 +102,7 @@ pub(crate) async fn stream_chat_completions(
"content": output.content,
}));
}
ResponseItem::CustomToolCall {
id,
call_id: _,
name,
input,
status: _,
} => {
messages.push(json!({
"role": "assistant",
"content": null,
"tool_calls": [{
"id": id,
"type": "custom",
"custom": {
"name": name,
"input": input,
}
}]
}));
}
ResponseItem::CustomToolCallOutput { call_id, output } => {
messages.push(json!({
"role": "tool",
"tool_call_id": call_id,
"content": output,
}));
}
ResponseItem::Reasoning { .. }
| ResponseItem::WebSearchCall { .. }
| ResponseItem::Other => {
ResponseItem::Reasoning { .. } | ResponseItem::Other => {
// Omit these items from the conversation history.
continue;
}
@@ -466,10 +302,7 @@ async fn process_chat_sse<S>(
// Some providers stream `reasoning` as a plain string while others
// nest the text under an object (e.g. `{ "reasoning": { "text": "…" } }`).
if let Some(reasoning_val) = choice.get("delta").and_then(|d| d.get("reasoning")) {
let mut maybe_text = reasoning_val
.as_str()
.map(str::to_string)
.filter(|s| !s.is_empty());
let mut maybe_text = reasoning_val.as_str().map(|s| s.to_string());
if maybe_text.is_none() && reasoning_val.is_object() {
if let Some(s) = reasoning_val
@@ -488,39 +321,12 @@ async fn process_chat_sse<S>(
}
if let Some(reasoning) = maybe_text {
// Accumulate so we can emit a terminal Reasoning item at the end.
reasoning_text.push_str(&reasoning);
let _ = tx_event
.send(Ok(ResponseEvent::ReasoningContentDelta(reasoning)))
.await;
}
}
// Some providers only include reasoning on the final message object.
if let Some(message_reasoning) = choice.get("message").and_then(|m| m.get("reasoning"))
{
// Accept either a plain string or an object with { text | content }
if let Some(s) = message_reasoning.as_str() {
if !s.is_empty() {
reasoning_text.push_str(s);
let _ = tx_event
.send(Ok(ResponseEvent::ReasoningContentDelta(s.to_string())))
.await;
}
} else if let Some(obj) = message_reasoning.as_object()
&& let Some(s) = obj
.get("text")
.and_then(|v| v.as_str())
.or_else(|| obj.get("content").and_then(|v| v.as_str()))
&& !s.is_empty()
{
reasoning_text.push_str(s);
let _ = tx_event
.send(Ok(ResponseEvent::ReasoningContentDelta(s.to_string())))
.await;
}
}
// Handle streaming function / tool calls.
if let Some(tool_calls) = choice
.get("delta")
@@ -676,55 +482,29 @@ where
// do NOT emit yet. Forward any other item (e.g. FunctionCall) right
// away so downstream consumers see it.
let is_assistant_message = matches!(
&item,
codex_protocol::models::ResponseItem::Message { role, .. } if role == "assistant"
);
let is_assistant_delta = matches!(&item, crate::models::ResponseItem::Message { role, .. } if role == "assistant");
if is_assistant_message {
match this.mode {
AggregateMode::AggregatedOnly => {
// Only use the final assistant message if we have not
// seen any deltas; otherwise, deltas already built the
// cumulative text and this would duplicate it.
if this.cumulative.is_empty()
&& let codex_protocol::models::ResponseItem::Message {
content,
..
} = &item
&& let Some(text) = content.iter().find_map(|c| match c {
codex_protocol::models::ContentItem::OutputText {
text,
} => Some(text),
_ => None,
})
{
this.cumulative.push_str(text);
}
// Swallow assistant message here; emit on Completed.
continue;
}
AggregateMode::Streaming => {
// In streaming mode, if we have not seen any deltas, forward
// the final assistant message directly. If deltas were seen,
// suppress the final message to avoid duplication.
if this.cumulative.is_empty() {
return Poll::Ready(Some(Ok(ResponseEvent::OutputItemDone(
item,
))));
} else {
continue;
}
}
if is_assistant_delta {
// Only use the final assistant message if we have not
// seen any deltas; otherwise, deltas already built the
// cumulative text and this would duplicate it.
if this.cumulative.is_empty()
&& let crate::models::ResponseItem::Message { content, .. } = &item
&& let Some(text) = content.iter().find_map(|c| match c {
crate::models::ContentItem::OutputText { text } => Some(text),
_ => None,
})
{
this.cumulative.push_str(text);
}
// Swallow assistant message here; emit on Completed.
continue;
}
// Not an assistant message forward immediately.
return Poll::Ready(Some(Ok(ResponseEvent::OutputItemDone(item))));
}
Poll::Ready(Some(Ok(ResponseEvent::RateLimits(snapshot)))) => {
return Poll::Ready(Some(Ok(ResponseEvent::RateLimits(snapshot))));
}
Poll::Ready(Some(Ok(ResponseEvent::Completed {
response_id,
token_usage,
@@ -735,32 +515,26 @@ where
if !this.cumulative_reasoning.is_empty()
&& matches!(this.mode, AggregateMode::AggregatedOnly)
{
let aggregated_reasoning =
codex_protocol::models::ResponseItem::Reasoning {
id: String::new(),
summary: Vec::new(),
content: Some(vec![
codex_protocol::models::ReasoningItemContent::ReasoningText {
text: std::mem::take(&mut this.cumulative_reasoning),
},
]),
encrypted_content: None,
};
let aggregated_reasoning = crate::models::ResponseItem::Reasoning {
id: String::new(),
summary: Vec::new(),
content: Some(vec![
crate::models::ReasoningItemContent::ReasoningText {
text: std::mem::take(&mut this.cumulative_reasoning),
},
]),
encrypted_content: None,
};
this.pending
.push_back(ResponseEvent::OutputItemDone(aggregated_reasoning));
emitted_any = true;
}
// Always emit the final aggregated assistant message when any
// content deltas have been observed. In AggregatedOnly mode this
// is the sole assistant output; in Streaming mode this finalizes
// the streamed deltas into a terminal OutputItemDone so callers
// can persist/render the message once per turn.
if !this.cumulative.is_empty() {
let aggregated_message = codex_protocol::models::ResponseItem::Message {
let aggregated_message = crate::models::ResponseItem::Message {
id: None,
role: "assistant".to_string(),
content: vec![codex_protocol::models::ContentItem::OutputText {
content: vec![crate::models::ContentItem::OutputText {
text: std::mem::take(&mut this.cumulative),
}],
};
@@ -818,9 +592,6 @@ where
Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryPartAdded))) => {
continue;
}
Poll::Ready(Some(Ok(ResponseEvent::WebSearchCallBegin { call_id }))) => {
return Poll::Ready(Some(Ok(ResponseEvent::WebSearchCallBegin { call_id })));
}
}
}
}

View File

@@ -3,16 +3,13 @@ use std::path::Path;
use std::sync::OnceLock;
use std::time::Duration;
use crate::AuthManager;
use crate::auth::CodexAuth;
use bytes::Bytes;
use codex_protocol::mcp_protocol::AuthMode;
use codex_protocol::mcp_protocol::ConversationId;
use codex_login::AuthMode;
use codex_login::CodexAuth;
use eventsource_stream::Eventsource;
use futures::prelude::*;
use regex_lite::Regex;
use reqwest::StatusCode;
use reqwest::header::HeaderMap;
use serde::Deserialize;
use serde::Serialize;
use serde_json::Value;
@@ -22,6 +19,7 @@ use tokio_util::io::ReaderStream;
use tracing::debug;
use tracing::trace;
use tracing::warn;
use uuid::Uuid;
use crate::chat_completions::AggregateStreamExt;
use crate::chat_completions::stream_chat_completions;
@@ -30,9 +28,7 @@ use crate::client_common::ResponseEvent;
use crate::client_common::ResponseStream;
use crate::client_common::ResponsesApiRequest;
use crate::client_common::create_reasoning_param_for_request;
use crate::client_common::create_text_param_for_request;
use crate::config::Config;
use crate::default_client::create_client;
use crate::error::CodexErr;
use crate::error::Result;
use crate::error::UsageLimitReachedError;
@@ -40,16 +36,13 @@ use crate::flags::CODEX_RS_SSE_FIXTURE;
use crate::model_family::ModelFamily;
use crate::model_provider_info::ModelProviderInfo;
use crate::model_provider_info::WireApi;
use crate::openai_model_info::get_model_info;
use crate::models::ResponseItem;
use crate::openai_tools::create_tools_json_for_responses_api;
use crate::protocol::RateLimitSnapshot;
use crate::protocol::RateLimitWindow;
use crate::protocol::TokenUsage;
use crate::token_data::PlanType;
use crate::user_agent::get_codex_user_agent;
use crate::util::backoff;
use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
use codex_protocol::models::ResponseItem;
use std::sync::Arc;
#[derive(Debug, Deserialize)]
@@ -60,60 +53,41 @@ struct ErrorResponse {
#[derive(Debug, Deserialize)]
struct Error {
r#type: Option<String>,
#[allow(dead_code)]
code: Option<String>,
message: Option<String>,
// Optional fields available on "usage_limit_reached" and "usage_not_included" errors
plan_type: Option<PlanType>,
resets_in_seconds: Option<u64>,
}
#[derive(Debug, Clone)]
pub struct ModelClient {
config: Arc<Config>,
auth_manager: Option<Arc<AuthManager>>,
auth: Option<CodexAuth>,
client: reqwest::Client,
provider: ModelProviderInfo,
conversation_id: ConversationId,
effort: Option<ReasoningEffortConfig>,
session_id: Uuid,
effort: ReasoningEffortConfig,
summary: ReasoningSummaryConfig,
}
impl ModelClient {
pub fn new(
config: Arc<Config>,
auth_manager: Option<Arc<AuthManager>>,
auth: Option<CodexAuth>,
provider: ModelProviderInfo,
effort: Option<ReasoningEffortConfig>,
effort: ReasoningEffortConfig,
summary: ReasoningSummaryConfig,
conversation_id: ConversationId,
session_id: Uuid,
) -> Self {
let client = create_client();
Self {
config,
auth_manager,
client,
auth,
client: reqwest::Client::new(),
provider,
conversation_id,
session_id,
effort,
summary,
}
}
pub fn get_model_context_window(&self) -> Option<u64> {
self.config
.model_context_window
.or_else(|| get_model_info(&self.config.model_family).map(|info| info.context_window))
}
pub fn get_auto_compact_token_limit(&self) -> Option<i64> {
self.config.model_auto_compact_token_limit.or_else(|| {
get_model_info(&self.config.model_family).and_then(|info| info.auto_compact_token_limit)
})
}
/// Dispatches to either the Responses or Chat implementation depending on
/// the provider config. Public callers always invoke `stream()` the
/// specialised helpers are private to avoid accidental misuse.
@@ -166,7 +140,11 @@ impl ModelClient {
return stream_from_fixture(path, self.provider.clone()).await;
}
let auth_manager = self.auth_manager.clone();
let auth = self.auth.clone();
let auth_mode = auth.as_ref().map(|a| a.mode);
let store = prompt.store && auth_mode != Some(AuthMode::ChatGPT);
let full_instructions = prompt.get_full_instructions(&self.config.model_family);
let tools_json = create_tools_json_for_responses_api(&prompt.tools)?;
@@ -176,7 +154,9 @@ impl ModelClient {
self.summary,
);
let include: Vec<String> = if reasoning.is_some() {
// Request encrypted COT if we are not storing responses,
// otherwise reasoning items will be referenced by ID
let include: Vec<String> = if !store && reasoning.is_some() {
vec!["reasoning.encrypted_content".to_string()]
} else {
vec![]
@@ -184,32 +164,6 @@ impl ModelClient {
let input_with_instructions = prompt.get_formatted_input();
let verbosity = match &self.config.model_family.family {
family if family == "gpt-5" => self.config.model_verbosity,
_ => {
if self.config.model_verbosity.is_some() {
warn!(
"model_verbosity is set but ignored for non-gpt-5 model family: {}",
self.config.model_family.family
);
}
None
}
};
// Only include `text.verbosity` for GPT-5 family models
let text = create_text_param_for_request(verbosity, &prompt.output_schema);
// In general, we want to explicitly send `store: false` when using the Responses API,
// but in practice, the Azure Responses API rejects `store: false`:
//
// - 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
//
// For Azure, we send `store: true` and preserve reasoning item IDs.
let azure_workaround = self.provider.is_azure_responses_endpoint();
let payload = ResponsesApiRequest {
model: &self.config.model,
instructions: &full_instructions,
@@ -218,180 +172,140 @@ impl ModelClient {
tool_choice: "auto",
parallel_tool_calls: false,
reasoning,
store: azure_workaround,
store,
stream: true,
include,
prompt_cache_key: Some(self.conversation_id.to_string()),
text,
prompt_cache_key: Some(self.session_id.to_string()),
};
let mut payload_json = serde_json::to_value(&payload)?;
if azure_workaround {
attach_item_ids(&mut payload_json, &input_with_instructions);
}
let max_attempts = self.provider.request_max_retries();
for attempt in 0..=max_attempts {
match self
.attempt_stream_responses(&payload_json, &auth_manager)
.await
{
Ok(stream) => {
return Ok(stream);
}
Err(StreamAttemptError::Fatal(e)) => {
return Err(e);
}
Err(retryable_attempt_error) => {
if attempt == max_attempts {
return Err(retryable_attempt_error.into_error());
}
tokio::time::sleep(retryable_attempt_error.delay(attempt)).await;
}
}
}
unreachable!("stream_responses_attempt should always return");
}
/// Single attempt to start a streaming Responses API call.
async fn attempt_stream_responses(
&self,
payload_json: &Value,
auth_manager: &Option<Arc<AuthManager>>,
) -> std::result::Result<ResponseStream, StreamAttemptError> {
// Always fetch the latest auth in case a prior attempt refreshed the token.
let auth = auth_manager.as_ref().and_then(|m| m.auth());
let mut attempt = 0;
let max_retries = self.provider.request_max_retries();
trace!(
"POST to {}: {:?}",
"POST to {}: {}",
self.provider.get_full_url(&auth),
serde_json::to_string(payload_json)
serde_json::to_string(&payload)?
);
let mut req_builder = self
.provider
.create_request_builder(&self.client, &auth)
.await
.map_err(StreamAttemptError::Fatal)?;
loop {
attempt += 1;
req_builder = req_builder
.header("OpenAI-Beta", "responses=experimental")
// Send session_id for compatibility.
.header("conversation_id", self.conversation_id.to_string())
.header("session_id", self.conversation_id.to_string())
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(payload_json);
let mut req_builder = self
.provider
.create_request_builder(&self.client, &auth)
.await?;
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Some(account_id) = auth.get_account_id()
{
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
req_builder = req_builder
.header("OpenAI-Beta", "responses=experimental")
.header("session_id", self.session_id.to_string())
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload);
let res = req_builder.send().await;
if let Ok(resp) = &res {
trace!(
"Response status: {}, cf-ray: {}",
resp.status(),
resp.headers()
.get("cf-ray")
.map(|v| v.to_str().unwrap_or_default())
.unwrap_or_default()
);
}
match res {
Ok(resp) if resp.status().is_success() => {
let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
if let Some(snapshot) = parse_rate_limit_snapshot(resp.headers())
&& tx_event
.send(Ok(ResponseEvent::RateLimits(snapshot)))
.await
.is_err()
{
debug!("receiver dropped rate limit snapshot event");
}
// spawn task to process SSE
let stream = resp.bytes_stream().map_err(CodexErr::Reqwest);
tokio::spawn(process_sse(
stream,
tx_event,
self.provider.stream_idle_timeout(),
));
Ok(ResponseStream { rx_event })
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Some(account_id) = auth.get_account_id()
{
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
Ok(res) => {
let status = res.status();
// Pull out RetryAfter header if present.
let retry_after_secs = res
.headers()
.get(reqwest::header::RETRY_AFTER)
.and_then(|v| v.to_str().ok())
.and_then(|s| s.parse::<u64>().ok());
let retry_after = retry_after_secs.map(|s| Duration::from_millis(s * 1_000));
let originator = self
.config
.internal_originator
.as_deref()
.unwrap_or("codex_cli_rs");
req_builder = req_builder.header("originator", originator);
req_builder = req_builder.header("User-Agent", get_codex_user_agent(Some(originator)));
if status == StatusCode::UNAUTHORIZED
&& let Some(manager) = auth_manager.as_ref()
&& manager.auth().is_some()
{
let _ = manager.refresh_token().await;
let res = req_builder.send().await;
if let Ok(resp) = &res {
trace!(
"Response status: {}, request-id: {}",
resp.status(),
resp.headers()
.get("x-request-id")
.map(|v| v.to_str().unwrap_or_default())
.unwrap_or_default()
);
}
match res {
Ok(resp) if resp.status().is_success() => {
let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
// spawn task to process SSE
let stream = resp.bytes_stream().map_err(CodexErr::Reqwest);
tokio::spawn(process_sse(
stream,
tx_event,
self.provider.stream_idle_timeout(),
));
return Ok(ResponseStream { rx_event });
}
Ok(res) => {
let status = res.status();
// The OpenAI Responses endpoint returns structured JSON bodies even for 4xx/5xx
// errors. When we bubble early with only the HTTP status the caller sees an opaque
// "unexpected status 400 Bad Request" which makes debugging nearly impossible.
// Instead, read (and include) the response text so higher layers and users see the
// exact error message (e.g. "Unknown parameter: 'input[0].metadata'"). The body is
// small and this branch only runs on error paths so the extra allocation is
// negligible.
if !(status == StatusCode::TOO_MANY_REQUESTS
|| status == StatusCode::UNAUTHORIZED
|| status.is_server_error())
{
// Surface the error body to callers. Use `unwrap_or_default` per Clippy.
let body = res.text().await.unwrap_or_default();
return Err(StreamAttemptError::Fatal(CodexErr::UnexpectedStatus(
status, body,
)));
}
// Pull out RetryAfter header if present.
let retry_after_secs = res
.headers()
.get(reqwest::header::RETRY_AFTER)
.and_then(|v| v.to_str().ok())
.and_then(|s| s.parse::<u64>().ok());
if status == StatusCode::TOO_MANY_REQUESTS {
let rate_limit_snapshot = parse_rate_limit_snapshot(res.headers());
let body = res.json::<ErrorResponse>().await.ok();
if let Some(ErrorResponse { error }) = body {
if error.r#type.as_deref() == Some("usage_limit_reached") {
// Prefer the plan_type provided in the error message if present
// because it's more up to date than the one encoded in the auth
// token.
let plan_type = error
.plan_type
.or_else(|| auth.as_ref().and_then(CodexAuth::get_plan_type));
let resets_in_seconds = error.resets_in_seconds;
let codex_err = CodexErr::UsageLimitReached(UsageLimitReachedError {
plan_type,
resets_in_seconds,
rate_limits: rate_limit_snapshot,
});
return Err(StreamAttemptError::Fatal(codex_err));
} else if error.r#type.as_deref() == Some("usage_not_included") {
return Err(StreamAttemptError::Fatal(CodexErr::UsageNotIncluded));
// The OpenAI Responses endpoint returns structured JSON bodies even for 4xx/5xx
// errors. When we bubble early with only the HTTP status the caller sees an opaque
// "unexpected status 400 Bad Request" which makes debugging nearly impossible.
// Instead, read (and include) the response text so higher layers and users see the
// exact error message (e.g. "Unknown parameter: 'input[0].metadata'"). The body is
// small and this branch only runs on error paths so the extra allocation is
// negligible.
if !(status == StatusCode::TOO_MANY_REQUESTS || status.is_server_error()) {
// Surface the error body to callers. Use `unwrap_or_default` per Clippy.
let body = res.text().await.unwrap_or_default();
return Err(CodexErr::UnexpectedStatus(status, body));
}
if status == StatusCode::TOO_MANY_REQUESTS {
let body = res.json::<ErrorResponse>().await.ok();
if let Some(ErrorResponse {
error:
Error {
r#type: Some(error_type),
..
},
}) = body
{
if error_type == "usage_limit_reached" {
return Err(CodexErr::UsageLimitReached(UsageLimitReachedError {
plan_type: auth.and_then(|a| a.get_plan_type()),
}));
} else if error_type == "usage_not_included" {
return Err(CodexErr::UsageNotIncluded);
}
}
}
}
Err(StreamAttemptError::RetryableHttpError {
status,
retry_after,
})
if attempt > max_retries {
if status == StatusCode::INTERNAL_SERVER_ERROR {
return Err(CodexErr::InternalServerError);
}
return Err(CodexErr::RetryLimit(status));
}
let delay = retry_after_secs
.map(|s| Duration::from_millis(s * 1_000))
.unwrap_or_else(|| backoff(attempt));
tokio::time::sleep(delay).await;
}
Err(e) => {
if attempt > max_retries {
return Err(e.into());
}
let delay = backoff(attempt);
tokio::time::sleep(delay).await;
}
}
Err(e) => Err(StreamAttemptError::RetryableTransportError(e.into())),
}
}
@@ -410,7 +324,7 @@ impl ModelClient {
}
/// Returns the current reasoning effort setting.
pub fn get_reasoning_effort(&self) -> Option<ReasoningEffortConfig> {
pub fn get_reasoning_effort(&self) -> ReasoningEffortConfig {
self.effort
}
@@ -419,49 +333,8 @@ impl ModelClient {
self.summary
}
pub fn get_auth_manager(&self) -> Option<Arc<AuthManager>> {
self.auth_manager.clone()
}
}
enum StreamAttemptError {
RetryableHttpError {
status: StatusCode,
retry_after: Option<Duration>,
},
RetryableTransportError(CodexErr),
Fatal(CodexErr),
}
impl StreamAttemptError {
/// attempt is 0-based.
fn delay(&self, attempt: u64) -> Duration {
// backoff() uses 1-based attempts.
let backoff_attempt = attempt + 1;
match self {
Self::RetryableHttpError { retry_after, .. } => {
retry_after.unwrap_or_else(|| backoff(backoff_attempt))
}
Self::RetryableTransportError { .. } => backoff(backoff_attempt),
Self::Fatal(_) => {
// Should not be called on Fatal errors.
Duration::from_secs(0)
}
}
}
fn into_error(self) -> CodexErr {
match self {
Self::RetryableHttpError { status, .. } => {
if status == StatusCode::INTERNAL_SERVER_ERROR {
CodexErr::InternalServerError
} else {
CodexErr::RetryLimit(status)
}
}
Self::RetryableTransportError(error) => error,
Self::Fatal(error) => error,
}
pub fn get_auth(&self) -> Option<CodexAuth> {
self.auth.clone()
}
}
@@ -474,6 +347,9 @@ struct SseEvent {
delta: Option<String>,
}
#[derive(Debug, Deserialize)]
struct ResponseCreated {}
#[derive(Debug, Deserialize)]
struct ResponseCompleted {
id: String,
@@ -493,15 +369,9 @@ impl From<ResponseCompletedUsage> for TokenUsage {
fn from(val: ResponseCompletedUsage) -> Self {
TokenUsage {
input_tokens: val.input_tokens,
cached_input_tokens: val
.input_tokens_details
.map(|d| d.cached_tokens)
.unwrap_or(0),
cached_input_tokens: val.input_tokens_details.map(|d| d.cached_tokens),
output_tokens: val.output_tokens,
reasoning_output_tokens: val
.output_tokens_details
.map(|d| d.reasoning_tokens)
.unwrap_or(0),
reasoning_output_tokens: val.output_tokens_details.map(|d| d.reasoning_tokens),
total_tokens: val.total_tokens,
}
}
@@ -517,90 +387,6 @@ struct ResponseCompletedOutputTokensDetails {
reasoning_tokens: u64,
}
fn attach_item_ids(payload_json: &mut Value, original_items: &[ResponseItem]) {
let Some(input_value) = payload_json.get_mut("input") else {
return;
};
let serde_json::Value::Array(items) = input_value else {
return;
};
for (value, item) in items.iter_mut().zip(original_items.iter()) {
if let ResponseItem::Reasoning { id, .. }
| ResponseItem::Message { id: Some(id), .. }
| ResponseItem::WebSearchCall { id: Some(id), .. }
| ResponseItem::FunctionCall { id: Some(id), .. }
| ResponseItem::LocalShellCall { id: Some(id), .. }
| ResponseItem::CustomToolCall { id: Some(id), .. } = item
{
if id.is_empty() {
continue;
}
if let Some(obj) = value.as_object_mut() {
obj.insert("id".to_string(), Value::String(id.clone()));
}
}
}
}
fn parse_rate_limit_snapshot(headers: &HeaderMap) -> Option<RateLimitSnapshot> {
let primary = parse_rate_limit_window(
headers,
"x-codex-primary-used-percent",
"x-codex-primary-window-minutes",
"x-codex-primary-reset-after-seconds",
);
let secondary = parse_rate_limit_window(
headers,
"x-codex-secondary-used-percent",
"x-codex-secondary-window-minutes",
"x-codex-secondary-reset-after-seconds",
);
Some(RateLimitSnapshot { primary, secondary })
}
fn parse_rate_limit_window(
headers: &HeaderMap,
used_percent_header: &str,
window_minutes_header: &str,
resets_header: &str,
) -> Option<RateLimitWindow> {
let used_percent: Option<f64> = parse_header_f64(headers, used_percent_header);
used_percent.and_then(|used_percent| {
let window_minutes = parse_header_u64(headers, window_minutes_header);
let resets_in_seconds = parse_header_u64(headers, resets_header);
let has_data = used_percent != 0.0
|| window_minutes.is_some_and(|minutes| minutes != 0)
|| resets_in_seconds.is_some_and(|seconds| seconds != 0);
has_data.then_some(RateLimitWindow {
used_percent,
window_minutes,
resets_in_seconds,
})
})
}
fn parse_header_f64(headers: &HeaderMap, name: &str) -> Option<f64> {
parse_header_str(headers, name)?
.parse::<f64>()
.ok()
.filter(|v| v.is_finite())
}
fn parse_header_u64(headers: &HeaderMap, name: &str) -> Option<u64> {
parse_header_str(headers, name)?.parse::<u64>().ok()
}
fn parse_header_str<'a>(headers: &'a HeaderMap, name: &str) -> Option<&'a str> {
headers.get(name)?.to_str().ok()
}
async fn process_sse<S>(
stream: S,
tx_event: mpsc::Sender<Result<ResponseEvent>>,
@@ -658,8 +444,7 @@ async fn process_sse<S>(
}
};
let raw = sse.data.clone();
trace!("SSE event: {}", raw);
trace!("SSE event: {}", sse.data);
let event: SseEvent = match serde_json::from_str(&sse.data) {
Ok(event) => event,
@@ -768,27 +553,11 @@ async fn process_sse<S>(
}
"response.content_part.done"
| "response.function_call_arguments.delta"
| "response.custom_tool_call_input.delta"
| "response.custom_tool_call_input.done" // also emitted as response.output_item.done
| "response.in_progress"
| "response.output_text.done" => {}
"response.output_item.added" => {
if let Some(item) = event.item.as_ref() {
// Detect web_search_call begin and forward a synthetic event upstream.
if let Some(ty) = item.get("type").and_then(|v| v.as_str())
&& ty == "web_search_call"
{
let call_id = item
.get("id")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
let ev = ResponseEvent::WebSearchCallBegin { call_id };
if tx_event.send(Ok(ev)).await.is_err() {
return;
}
}
}
| "response.output_item.added"
| "response.output_text.done" => {
// Currently, we ignore this event, but we handle it
// separately to skip the logging message in the `other` case.
}
"response.reasoning_summary_part.added" => {
// Boundary between reasoning summary sections (e.g., titles).
@@ -798,7 +567,7 @@ async fn process_sse<S>(
}
}
"response.reasoning_summary_text.done" => {}
_ => {}
other => debug!(other, "sse event"),
}
}
}
@@ -1194,8 +963,6 @@ mod tests {
r#type: None,
message: Some("Rate limit reached for gpt-5 in organization org- on tokens per min (TPM): Limit 1, Used 1, Requested 19304. Please try again in 28ms. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
plan_type: None,
resets_in_seconds: None
};
let delay = try_parse_retry_after(&err);
@@ -1208,43 +975,8 @@ mod tests {
r#type: None,
message: Some("Rate limit reached for gpt-5 in organization <ORG> on tokens per min (TPM): Limit 30000, Used 6899, Requested 24050. Please try again in 1.898s. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
plan_type: None,
resets_in_seconds: None
};
let delay = try_parse_retry_after(&err);
assert_eq!(delay, Some(Duration::from_secs_f64(1.898)));
}
#[test]
fn error_response_deserializes_old_schema_known_plan_type_and_serializes_back() {
use crate::token_data::KnownPlan;
use crate::token_data::PlanType;
let json = r#"{"error":{"type":"usage_limit_reached","plan_type":"pro","resets_in_seconds":3600}}"#;
let resp: ErrorResponse =
serde_json::from_str(json).expect("should deserialize old schema");
assert!(matches!(
resp.error.plan_type,
Some(PlanType::Known(KnownPlan::Pro))
));
let plan_json = serde_json::to_string(&resp.error.plan_type).expect("serialize plan_type");
assert_eq!(plan_json, "\"pro\"");
}
#[test]
fn error_response_deserializes_old_schema_unknown_plan_type_and_serializes_back() {
use crate::token_data::PlanType;
let json =
r#"{"error":{"type":"usage_limit_reached","plan_type":"vip","resets_in_seconds":60}}"#;
let resp: ErrorResponse =
serde_json::from_str(json).expect("should deserialize old schema");
assert!(matches!(resp.error.plan_type, Some(PlanType::Unknown(ref s)) if s == "vip"));
let plan_json = serde_json::to_string(&resp.error.plan_type).expect("serialize plan_type");
assert_eq!(plan_json, "\"vip\"");
}
}

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