mirror of
https://github.com/openai/codex.git
synced 2026-02-04 16:03:46 +00:00
Compare commits
63 Commits
seratch-pa
...
dev/javi/c
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
557731d7d6 | ||
|
|
8ac87edd64 | ||
|
|
bba09a89e2 | ||
|
|
8958283edd | ||
|
|
3f8184034f | ||
|
|
f7cb2f87a0 | ||
|
|
9dbe7284d2 | ||
|
|
b8e8454b3f | ||
|
|
bbcfd63aba | ||
|
|
6209d49520 | ||
|
|
c3a8b96a60 | ||
|
|
c9ca63dc1e | ||
|
|
ed06f90fb3 | ||
|
|
f09170b574 | ||
|
|
1e9e703b96 | ||
|
|
74d2741729 | ||
|
|
e5611aab07 | ||
|
|
4e9ad23864 | ||
|
|
3e309805ae | ||
|
|
488a40211a | ||
|
|
903178eeeb | ||
|
|
6e4c9d5243 | ||
|
|
459363e17b | ||
|
|
ffe585387b | ||
|
|
0cec0770e2 | ||
|
|
2d2f66f9c5 | ||
|
|
d0e06f74e2 | ||
|
|
4b6c6ce98f | ||
|
|
5df04c8a13 | ||
|
|
3d8bca7814 | ||
|
|
3eb11c10d0 | ||
|
|
bd65c4db87 | ||
|
|
b367790d9b | ||
|
|
435154ce93 | ||
|
|
fb3f6456cf | ||
|
|
f2603a4e50 | ||
|
|
eb161116f0 | ||
|
|
c229a67312 | ||
|
|
aa5fc5855d | ||
|
|
db98d2ce25 | ||
|
|
274d9b413f | ||
|
|
8192cf147e | ||
|
|
d32e4f25cf | ||
|
|
a4d34235bc | ||
|
|
d085f73a2a | ||
|
|
ab9250e714 | ||
|
|
e5283b6126 | ||
|
|
d63e44ae29 | ||
|
|
17e5077507 | ||
|
|
b1079187e4 | ||
|
|
ae8f772ef2 | ||
|
|
468a8b4c38 | ||
|
|
cb32f9c64e | ||
|
|
907afc9425 | ||
|
|
7f7d1e30f3 | ||
|
|
568d6f819f | ||
|
|
251c4c2ba9 | ||
|
|
a6c346b9e1 | ||
|
|
e307040f10 | ||
|
|
7d67e54628 | ||
|
|
295ca27e98 | ||
|
|
7b20db942a | ||
|
|
ee2ccb5cb6 |
50
.github/ISSUE_TEMPLATE/5-vs-code-extension.yml
vendored
Normal file
50
.github/ISSUE_TEMPLATE/5-vs-code-extension.yml
vendored
Normal file
@@ -0,0 +1,50 @@
|
||||
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
1
.github/actions/codex/.gitignore
vendored
@@ -1 +0,0 @@
|
||||
/node_modules/
|
||||
8
.github/actions/codex/.prettierrc.toml
vendored
8
.github/actions/codex/.prettierrc.toml
vendored
@@ -1,8 +0,0 @@
|
||||
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
140
.github/actions/codex/README.md
vendored
@@ -1,140 +0,0 @@
|
||||
# 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
125
.github/actions/codex/action.yml
vendored
@@ -1,125 +0,0 @@
|
||||
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
91
.github/actions/codex/bun.lock
vendored
@@ -1,91 +0,0 @@
|
||||
{
|
||||
"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
21
.github/actions/codex/package.json
vendored
@@ -1,21 +0,0 @@
|
||||
{
|
||||
"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"
|
||||
}
|
||||
}
|
||||
85
.github/actions/codex/src/add-reaction.ts
vendored
85
.github/actions/codex/src/add-reaction.ts
vendored
@@ -1,85 +0,0 @@
|
||||
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: ${error}`);
|
||||
}
|
||||
}
|
||||
53
.github/actions/codex/src/comment.ts
vendored
53
.github/actions/codex/src/comment.ts
vendored
@@ -1,53 +0,0 @@
|
||||
import type { EnvContext } from "./env-context";
|
||||
import { runCodex } from "./run-codex";
|
||||
import { postComment } from "./post-comment";
|
||||
import { addEyesReaction } from "./add-reaction";
|
||||
|
||||
/**
|
||||
* Handle `issue_comment` and `pull_request_review_comment` events once we know
|
||||
* the action is supported.
|
||||
*/
|
||||
export async function onComment(ctx: EnvContext): Promise<void> {
|
||||
const triggerPhrase = ctx.tryGet("INPUT_TRIGGER_PHRASE");
|
||||
if (!triggerPhrase) {
|
||||
console.warn("Empty trigger phrase: skipping.");
|
||||
return;
|
||||
}
|
||||
|
||||
// Attempt to get the body of the comment from the environment. Depending on
|
||||
// the event type either `GITHUB_EVENT_COMMENT_BODY` (issue & PR comments) or
|
||||
// `GITHUB_EVENT_REVIEW_BODY` (PR reviews) is set.
|
||||
const commentBody =
|
||||
ctx.tryGetNonEmpty("GITHUB_EVENT_COMMENT_BODY") ??
|
||||
ctx.tryGetNonEmpty("GITHUB_EVENT_REVIEW_BODY") ??
|
||||
ctx.tryGetNonEmpty("GITHUB_EVENT_ISSUE_BODY");
|
||||
|
||||
if (!commentBody) {
|
||||
console.warn("Comment body not found in environment: skipping.");
|
||||
return;
|
||||
}
|
||||
|
||||
// Check if the trigger phrase is present.
|
||||
if (!commentBody.includes(triggerPhrase)) {
|
||||
console.log(
|
||||
`Trigger phrase '${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
11
.github/actions/codex/src/config.ts
vendored
@@ -1,11 +0,0 @@
|
||||
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;
|
||||
}
|
||||
@@ -1,44 +0,0 @@
|
||||
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
116
.github/actions/codex/src/env-context.ts
vendored
@@ -1,116 +0,0 @@
|
||||
/*
|
||||
* 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
4
.github/actions/codex/src/fail.ts
vendored
@@ -1,4 +0,0 @@
|
||||
export function fail(message: string): never {
|
||||
console.error(message);
|
||||
process.exit(1);
|
||||
}
|
||||
149
.github/actions/codex/src/git-helpers.ts
vendored
149
.github/actions/codex/src/git-helpers.ts
vendored
@@ -1,149 +0,0 @@
|
||||
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
16
.github/actions/codex/src/git-user.ts
vendored
@@ -1,16 +0,0 @@
|
||||
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);
|
||||
}
|
||||
}
|
||||
11
.github/actions/codex/src/github-workspace.ts
vendored
11
.github/actions/codex/src/github-workspace.ts
vendored
@@ -1,11 +0,0 @@
|
||||
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);
|
||||
}
|
||||
}
|
||||
56
.github/actions/codex/src/load-config.ts
vendored
56
.github/actions/codex/src/load-config.ts
vendored
@@ -1,56 +0,0 @@
|
||||
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
80
.github/actions/codex/src/main.ts
vendored
@@ -1,80 +0,0 @@
|
||||
#!/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 '${GITHUB_EVENT_NAME}'.`,
|
||||
);
|
||||
}
|
||||
|
||||
main();
|
||||
62
.github/actions/codex/src/post-comment.ts
vendored
62
.github/actions/codex/src/post-comment.ts
vendored
@@ -1,62 +0,0 @@
|
||||
import { fail } from "./fail";
|
||||
import * as github from "@actions/github";
|
||||
import { EnvContext } from "./env-context";
|
||||
|
||||
/**
|
||||
* Post a comment to the issue / pull request currently in scope.
|
||||
*
|
||||
* Provide the environment context so that token lookup (inside getOctokit) does
|
||||
* not rely on global state.
|
||||
*/
|
||||
export async function postComment(
|
||||
commentBody: string,
|
||||
ctx: EnvContext,
|
||||
): Promise<void> {
|
||||
// Append a footer with a link back to the workflow run, if available.
|
||||
const footer = buildWorkflowRunFooter(ctx);
|
||||
const bodyWithFooter = footer ? `${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_](${url})*`;
|
||||
}
|
||||
226
.github/actions/codex/src/process-label.ts
vendored
226
.github/actions/codex/src/process-label.ts
vendored
@@ -1,226 +0,0 @@
|
||||
import { fail } from "./fail";
|
||||
import { EnvContext } from "./env-context";
|
||||
import { renderPromptTemplate } from "./prompt-template";
|
||||
|
||||
import { postComment } from "./post-comment";
|
||||
import { runCodex } from "./run-codex";
|
||||
|
||||
import * as github from "@actions/github";
|
||||
import { Config, LabelConfig } from "./config";
|
||||
import { maybePublishPRForIssue } from "./git-helpers";
|
||||
|
||||
export async function onLabeled(
|
||||
config: Config,
|
||||
ctx: EnvContext,
|
||||
): Promise<void> {
|
||||
const GITHUB_EVENT_LABEL_NAME = ctx.get("GITHUB_EVENT_LABEL_NAME");
|
||||
const labelConfig = config.labels[GITHUB_EVENT_LABEL_NAME] as
|
||||
| LabelConfig
|
||||
| undefined;
|
||||
if (!labelConfig) {
|
||||
fail(
|
||||
`Label \`${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}': ${error}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
284
.github/actions/codex/src/prompt-template.ts
vendored
284
.github/actions/codex/src/prompt-template.ts
vendored
@@ -1,284 +0,0 @@
|
||||
/*
|
||||
* Utilities to render Codex prompt templates.
|
||||
*
|
||||
* A template is a Markdown (or plain-text) file that may contain one or more
|
||||
* placeholders of the form `{CODEX_ACTION_<NAME>}`. At runtime these
|
||||
* placeholders are substituted with dynamically generated content. Each
|
||||
* placeholder is resolved **exactly once** even if it appears multiple times
|
||||
* in the same template.
|
||||
*/
|
||||
|
||||
import { readFile } from "fs/promises";
|
||||
|
||||
import { EnvContext } from "./env-context";
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Helpers
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Lazily caches parsed `$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: ${name}`);
|
||||
return "";
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function getPrShas(
|
||||
ctx: EnvContext,
|
||||
): Promise<{ baseSha: string; headSha: string } | null> {
|
||||
const event = await getGitHubEventData(ctx);
|
||||
const pr = event.pull_request;
|
||||
if (!pr) {
|
||||
console.warn("event.pull_request is not defined");
|
||||
return null;
|
||||
}
|
||||
|
||||
// Prefer explicit SHAs if available to avoid relying on local branch names.
|
||||
const baseSha: string | undefined = pr.base?.sha;
|
||||
const headSha: string | undefined = pr.head?.sha;
|
||||
|
||||
if (!baseSha || !headSha) {
|
||||
console.warn("one of base or head is not defined on event.pull_request");
|
||||
return null;
|
||||
}
|
||||
|
||||
return { baseSha, headSha };
|
||||
}
|
||||
42
.github/actions/codex/src/review.ts
vendored
42
.github/actions/codex/src/review.ts
vendored
@@ -1,42 +0,0 @@
|
||||
import type { EnvContext } from "./env-context";
|
||||
import { runCodex } from "./run-codex";
|
||||
import { postComment } from "./post-comment";
|
||||
import { addEyesReaction } from "./add-reaction";
|
||||
|
||||
/**
|
||||
* Handle `pull_request_review` events. We treat the review body the same way
|
||||
* as a normal comment.
|
||||
*/
|
||||
export async function onReview(ctx: EnvContext): Promise<void> {
|
||||
const triggerPhrase = ctx.tryGet("INPUT_TRIGGER_PHRASE");
|
||||
if (!triggerPhrase) {
|
||||
console.warn("Empty trigger phrase: skipping.");
|
||||
return;
|
||||
}
|
||||
|
||||
const reviewBody = ctx.tryGet("GITHUB_EVENT_REVIEW_BODY");
|
||||
|
||||
if (!reviewBody) {
|
||||
console.warn("Review body not found in environment: skipping.");
|
||||
return;
|
||||
}
|
||||
|
||||
if (!reviewBody.includes(triggerPhrase)) {
|
||||
console.log(
|
||||
`Trigger phrase '${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
58
.github/actions/codex/src/run-codex.ts
vendored
@@ -1,58 +0,0 @@
|
||||
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}': ${err}`);
|
||||
}
|
||||
|
||||
return lastMessage;
|
||||
}
|
||||
33
.github/actions/codex/src/verify-inputs.ts
vendored
33
.github/actions/codex/src/verify-inputs.ts
vendored
@@ -1,33 +0,0 @@
|
||||
// Validate the inputs passed to the composite action.
|
||||
// The script currently ensures that the provided configuration file exists and
|
||||
// matches the expected schema.
|
||||
|
||||
import type { Config } from "./config";
|
||||
|
||||
import { existsSync } from "fs";
|
||||
import * as path from "path";
|
||||
import { fail } from "./fail";
|
||||
|
||||
export function performAdditionalValidation(config: Config, workspace: string) {
|
||||
// Additional validation: ensure referenced prompt files exist and are Markdown.
|
||||
for (const [label, details] of Object.entries(config.labels)) {
|
||||
// Determine which prompt key is present (the schema guarantees exactly one).
|
||||
const promptPathStr =
|
||||
(details as any).prompt ?? (details as any).promptPath;
|
||||
|
||||
if (promptPathStr) {
|
||||
const promptPath = path.isAbsolute(promptPathStr)
|
||||
? promptPathStr
|
||||
: path.join(workspace, promptPathStr);
|
||||
|
||||
if (!existsSync(promptPath)) {
|
||||
fail(`Prompt file for label '${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
15
.github/actions/codex/tsconfig.json
vendored
@@ -1,15 +0,0 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"lib": ["ESNext"],
|
||||
"target": "ESNext",
|
||||
"module": "ESNext",
|
||||
"moduleDetection": "force",
|
||||
"moduleResolution": "bundler",
|
||||
|
||||
"noEmit": true,
|
||||
"strict": true,
|
||||
"skipLibCheck": true
|
||||
},
|
||||
|
||||
"include": ["src"]
|
||||
}
|
||||
BIN
.github/codex-cli-login.png
vendored
BIN
.github/codex-cli-login.png
vendored
Binary file not shown.
|
Before Width: | Height: | Size: 410 KiB After Width: | Height: | Size: 2.9 MiB |
BIN
.github/codex-cli-splash.png
vendored
BIN
.github/codex-cli-splash.png
vendored
Binary file not shown.
|
Before Width: | Height: | Size: 412 KiB After Width: | Height: | Size: 3.1 MiB |
64
.github/workflows/codex.yml
vendored
64
.github/workflows/codex.yml
vendored
@@ -1,64 +0,0 @@
|
||||
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/
|
||||
${{ github.workspace }}/codex-rs/target/
|
||||
key: cargo-ubuntu-24.04-x86_64-unknown-linux-gnu-dev-${{ 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
|
||||
@@ -11,6 +11,7 @@ In the codex-rs folder where the rust code lives:
|
||||
Before finalizing a change to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix -p <project>` (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 these commands to finalize.
|
||||
|
||||
## TUI style conventions
|
||||
|
||||
|
||||
212
CHANGELOG.md
212
CHANGELOG.md
@@ -1,211 +1 @@
|
||||
# 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 -->
|
||||
The changelog can be found on the [releases page](https://github.com/openai/codex/releases)
|
||||
|
||||
675
README.md
675
README.md
@@ -5,65 +5,11 @@
|
||||
<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="50%" />
|
||||
<img src="./.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" />
|
||||
</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
|
||||
@@ -99,607 +45,52 @@ 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="50%" />
|
||||
<img src="./.github/codex-cli-login.png" alt="Codex CLI login" width="80%" />
|
||||
</p>
|
||||
|
||||
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.)
|
||||
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).
|
||||
|
||||
> 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
|
||||
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).
|
||||
|
||||
If you encounter problems with the login flow, please comment on [this issue](https://github.com/openai/codex/issues/1243).
|
||||
### Model Context Protocol (MCP)
|
||||
|
||||
### Connecting on a "Headless" Machine
|
||||
Codex CLI supports [MCP servers](./docs/advanced.md#model-context-protocol-mcp). Enable by adding an `mcp_servers` section to your `~/.codex/config.toml`.
|
||||
|
||||
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:
|
||||
|
||||
#### Authenticate locally and copy your credentials to the "headless" machine
|
||||
### Configuration
|
||||
|
||||
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"
|
||||
```
|
||||
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).
|
||||
|
||||
---
|
||||
|
||||
### Platform sandboxing details
|
||||
|
||||
By default, Codex CLI runs code and shell commands inside a restricted sandbox to protect your system.
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Not all tool calls are sandboxed. Specifically, **trusted Model Context Protocol (MCP) tool calls** are executed outside of the sandbox.
|
||||
> This is intentional: MCP tools are explicitly configured and trusted by you, and they often need to connect to **external applications or services** (e.g. issue trackers, databases, messaging systems).
|
||||
> Running them outside the sandbox allows Codex to integrate with these external systems without being blocked by sandbox restrictions.
|
||||
|
||||
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.
|
||||
### Docs & FAQ
|
||||
|
||||
- [**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--project-docs)
|
||||
- [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)
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
This repository is licensed under the [Apache-2.0 License](LICENSE).
|
||||
|
||||
|
||||
7
codex-rs/Cargo.lock
generated
7
codex-rs/Cargo.lock
generated
@@ -754,7 +754,7 @@ dependencies = [
|
||||
"tokio-test",
|
||||
"tokio-util",
|
||||
"toml 0.9.5",
|
||||
"toml_edit 0.23.3",
|
||||
"toml_edit 0.23.4",
|
||||
"tracing",
|
||||
"tree-sitter",
|
||||
"tree-sitter-bash",
|
||||
@@ -1001,6 +1001,7 @@ dependencies = [
|
||||
"tui-markdown",
|
||||
"unicode-segmentation",
|
||||
"unicode-width 0.1.14",
|
||||
"url",
|
||||
"uuid",
|
||||
"vt100",
|
||||
]
|
||||
@@ -5195,9 +5196,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "toml_edit"
|
||||
version = "0.23.3"
|
||||
version = "0.23.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "17d3b47e6b7a040216ae5302712c94d1cf88c95b47efa80e2c59ce96c878267e"
|
||||
checksum = "7211ff1b8f0d3adae1663b7da9ffe396eabe1ca25f0b0bee42b0da29a9ddce93"
|
||||
dependencies = [
|
||||
"indexmap 2.10.0",
|
||||
"toml_datetime 0.7.0",
|
||||
|
||||
@@ -34,6 +34,7 @@ rust = {}
|
||||
|
||||
[workspace.lints.clippy]
|
||||
expect_used = "deny"
|
||||
uninlined_format_args = "deny"
|
||||
unwrap_used = "deny"
|
||||
|
||||
[profile.release]
|
||||
|
||||
@@ -19,11 +19,11 @@ While we are [working to close the gap between the TypeScript and Rust implement
|
||||
|
||||
### Config
|
||||
|
||||
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.
|
||||
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.
|
||||
|
||||
### Model Context Protocol Support
|
||||
|
||||
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.
|
||||
Codex CLI functions as an MCP client that can connect to MCP servers on startup. See the [`mcp_servers`](../docs/config.md#mcp_servers) section in the configuration documentation for details.
|
||||
|
||||
It is still experimental, but you can also launch Codex as an MCP _server_ by running `codex mcp`. Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
|
||||
|
||||
@@ -33,7 +33,7 @@ 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](./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](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS.
|
||||
|
||||
### `codex exec` to run Codex programmatially/non-interactively
|
||||
|
||||
|
||||
@@ -1,564 +1,6 @@
|
||||
# Config
|
||||
# Configuration docs moved
|
||||
|
||||
Codex supports several mechanisms for setting config values:
|
||||
This file has moved. Please see the latest configuration documentation here:
|
||||
|
||||
- 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 top‑level 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 built‑in 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_verbosity
|
||||
|
||||
Controls output length/detail on GPT‑5 family models when using the Responses API. Supported values:
|
||||
|
||||
- `"low"`
|
||||
- `"medium"` (default when omitted)
|
||||
- `"high"`
|
||||
|
||||
When set, Codex includes a `text` object in the request payload with the configured verbosity, for example: `"text": { "verbosity": "low" }`.
|
||||
|
||||
Example:
|
||||
|
||||
```toml
|
||||
model = "gpt-5"
|
||||
model_verbosity = "low"
|
||||
```
|
||||
|
||||
Note: This applies only to providers using the Responses API. Chat Completions providers are unaffected.
|
||||
|
||||
## 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.
|
||||
|
||||
## Approval presets
|
||||
|
||||
Codex provides three main Approval Presets:
|
||||
|
||||
- Read Only: Codex can read files and answer questions; edits, running commands, and network access require approval.
|
||||
- Auto: Codex can read files, make edits, and run commands in the workspace without approval; asks for approval outside the workspace or for network access.
|
||||
- Full Access: Full disk and network access without prompts; extremely risky.
|
||||
|
||||
You can further customize how Codex runs at the command line using the `--ask-for-approval` and `--sandbox` options.
|
||||
|
||||
## 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<string> | `[]` | Case-insensitive glob patterns to drop after the default filter.<br>Examples: `"AWS_*"`, `"AZURE_*"`. |
|
||||
| `set` | table<string,string> | `{}` | Explicit key/value overrides or additions – always win over inherited values. |
|
||||
| `include_only` | array<string> | `[]` | If non-empty, a whitelist of patterns; only variables that match _one_ pattern survive the final step. (Generally used with `inherit = "all"`.) |
|
||||
|
||||
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 model’s 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
|
||||
```
|
||||
- Full config docs: [docs/config.md](../docs/config.md)
|
||||
- MCP servers section: [docs/config.md#mcp_servers](../docs/config.md#mcp_servers)
|
||||
@@ -52,7 +52,7 @@ tokio = { version = "1", features = [
|
||||
] }
|
||||
tokio-util = "0.7.16"
|
||||
toml = "0.9.5"
|
||||
toml_edit = "0.23.3"
|
||||
toml_edit = "0.23.4"
|
||||
tracing = { version = "0.1.41", features = ["log"] }
|
||||
tree-sitter = "0.25.8"
|
||||
tree-sitter-bash = "0.25.0"
|
||||
|
||||
@@ -134,14 +134,6 @@ 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.
|
||||
@@ -177,6 +169,22 @@ 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.
|
||||
|
||||
@@ -129,7 +129,9 @@ pub(crate) async fn stream_chat_completions(
|
||||
"content": output,
|
||||
}));
|
||||
}
|
||||
ResponseItem::Reasoning { .. } | ResponseItem::Other => {
|
||||
ResponseItem::Reasoning { .. }
|
||||
| ResponseItem::WebSearchCall { .. }
|
||||
| ResponseItem::Other => {
|
||||
// Omit these items from the conversation history.
|
||||
continue;
|
||||
}
|
||||
@@ -623,11 +625,8 @@ where
|
||||
Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryPartAdded))) => {
|
||||
continue;
|
||||
}
|
||||
Poll::Ready(Some(Ok(ResponseEvent::WebSearchCallBegin { .. }))) => {
|
||||
return Poll::Ready(Some(Ok(ResponseEvent::WebSearchCallBegin {
|
||||
call_id: String::new(),
|
||||
query: None,
|
||||
})));
|
||||
Poll::Ready(Some(Ok(ResponseEvent::WebSearchCallBegin { call_id }))) => {
|
||||
return Poll::Ready(Some(Ok(ResponseEvent::WebSearchCallBegin { call_id })));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
use std::io::BufRead;
|
||||
use std::path::Path;
|
||||
use std::sync::OnceLock;
|
||||
use std::time::Duration;
|
||||
|
||||
use bytes::Bytes;
|
||||
@@ -8,7 +7,6 @@ use codex_login::AuthManager;
|
||||
use codex_login::AuthMode;
|
||||
use eventsource_stream::Eventsource;
|
||||
use futures::prelude::*;
|
||||
use regex_lite::Regex;
|
||||
use reqwest::StatusCode;
|
||||
use serde::Deserialize;
|
||||
use serde::Serialize;
|
||||
@@ -37,6 +35,7 @@ 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::openai_tools::create_tools_json_for_responses_api;
|
||||
use crate::protocol::TokenUsage;
|
||||
use crate::user_agent::get_codex_user_agent;
|
||||
@@ -54,8 +53,11 @@ struct ErrorResponse {
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct Error {
|
||||
r#type: Option<String>,
|
||||
code: Option<String>,
|
||||
message: Option<String>,
|
||||
|
||||
// Optional fields available on "usage_limit_reached" and "usage_not_included" errors
|
||||
plan_type: Option<String>,
|
||||
resets_in_seconds: Option<u64>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
@@ -89,6 +91,12 @@ impl ModelClient {
|
||||
}
|
||||
}
|
||||
|
||||
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))
|
||||
}
|
||||
|
||||
/// 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.
|
||||
@@ -142,28 +150,17 @@ impl ModelClient {
|
||||
}
|
||||
|
||||
let auth_manager = self.auth_manager.clone();
|
||||
let auth = auth_manager.as_ref().and_then(|m| m.auth());
|
||||
|
||||
let auth_mode = auth.as_ref().map(|a| a.mode);
|
||||
let auth_mode = auth_manager
|
||||
.as_ref()
|
||||
.and_then(|m| m.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 mut tools_json = create_tools_json_for_responses_api(&prompt.tools)?;
|
||||
// ChatGPT backend expects the preview name for web search.
|
||||
if auth_mode == Some(AuthMode::ChatGPT) {
|
||||
for tool in &mut tools_json {
|
||||
if let Some(map) = tool.as_object_mut()
|
||||
&& map.get("type").and_then(|v| v.as_str()) == Some("web_search")
|
||||
{
|
||||
map.insert(
|
||||
"type".to_string(),
|
||||
serde_json::Value::String("web_search_preview".to_string()),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let tools_json = create_tools_json_for_responses_api(&prompt.tools)?;
|
||||
let reasoning = create_reasoning_param_for_request(
|
||||
&self.config.model_family,
|
||||
self.effort,
|
||||
@@ -211,15 +208,18 @@ impl ModelClient {
|
||||
let mut attempt = 0;
|
||||
let max_retries = self.provider.request_max_retries();
|
||||
|
||||
trace!(
|
||||
"POST to {}: {}",
|
||||
self.provider.get_full_url(&auth),
|
||||
serde_json::to_string(&payload)?
|
||||
);
|
||||
|
||||
loop {
|
||||
attempt += 1;
|
||||
|
||||
// Always fetch the latest auth in case a prior attempt refreshed the token.
|
||||
let auth = auth_manager.as_ref().and_then(|m| m.auth());
|
||||
|
||||
trace!(
|
||||
"POST to {}: {}",
|
||||
self.provider.get_full_url(&auth),
|
||||
serde_json::to_string(&payload)?
|
||||
);
|
||||
|
||||
let mut req_builder = self
|
||||
.provider
|
||||
.create_request_builder(&self.client, &auth)
|
||||
@@ -303,19 +303,20 @@ impl ModelClient {
|
||||
|
||||
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" {
|
||||
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.and_then(|a| a.get_plan_type()));
|
||||
let resets_in_seconds = error.resets_in_seconds;
|
||||
return Err(CodexErr::UsageLimitReached(UsageLimitReachedError {
|
||||
plan_type: auth.and_then(|a| a.get_plan_type()),
|
||||
plan_type,
|
||||
resets_in_seconds,
|
||||
}));
|
||||
} else if error_type == "usage_not_included" {
|
||||
} else if error.r#type.as_deref() == Some("usage_not_included") {
|
||||
return Err(CodexErr::UsageNotIncluded);
|
||||
}
|
||||
}
|
||||
@@ -563,9 +564,8 @@ async fn process_sse<S>(
|
||||
if let Some(error) = error {
|
||||
match serde_json::from_value::<Error>(error.clone()) {
|
||||
Ok(error) => {
|
||||
let delay = try_parse_retry_after(&error);
|
||||
let message = error.message.unwrap_or_default();
|
||||
response_error = Some(CodexErr::Stream(message, delay));
|
||||
response_error = Some(CodexErr::Stream(message, None));
|
||||
}
|
||||
Err(e) => {
|
||||
debug!("failed to parse ErrorResponse: {e}");
|
||||
@@ -593,11 +593,9 @@ async fn process_sse<S>(
|
||||
| "response.custom_tool_call_input.delta"
|
||||
| "response.custom_tool_call_input.done" // also emitted as response.output_item.done
|
||||
| "response.in_progress"
|
||||
| "response.output_item.added"
|
||||
| "response.output_text.done" => {
|
||||
if event.kind == "response.output_item.added"
|
||||
&& let Some(item) = event.item.as_ref()
|
||||
{
|
||||
| "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"
|
||||
@@ -607,7 +605,7 @@ async fn process_sse<S>(
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("")
|
||||
.to_string();
|
||||
let ev = ResponseEvent::WebSearchCallBegin { call_id, query: None };
|
||||
let ev = ResponseEvent::WebSearchCallBegin { call_id };
|
||||
if tx_event.send(Ok(ev)).await.is_err() {
|
||||
return;
|
||||
}
|
||||
@@ -653,40 +651,6 @@ async fn stream_from_fixture(
|
||||
Ok(ResponseStream { rx_event })
|
||||
}
|
||||
|
||||
fn rate_limit_regex() -> &'static Regex {
|
||||
static RE: OnceLock<Regex> = OnceLock::new();
|
||||
|
||||
#[expect(clippy::unwrap_used)]
|
||||
RE.get_or_init(|| Regex::new(r"Please try again in (\d+(?:\.\d+)?)(s|ms)").unwrap())
|
||||
}
|
||||
|
||||
fn try_parse_retry_after(err: &Error) -> Option<Duration> {
|
||||
if err.code != Some("rate_limit_exceeded".to_string()) {
|
||||
return None;
|
||||
}
|
||||
|
||||
// parse the Please try again in 1.898s format using regex
|
||||
let re = rate_limit_regex();
|
||||
if let Some(message) = &err.message
|
||||
&& let Some(captures) = re.captures(message)
|
||||
{
|
||||
let seconds = captures.get(1);
|
||||
let unit = captures.get(2);
|
||||
|
||||
if let (Some(value), Some(unit)) = (seconds, unit) {
|
||||
let value = value.as_str().parse::<f64>().ok()?;
|
||||
let unit = unit.as_str();
|
||||
|
||||
if unit == "s" {
|
||||
return Some(Duration::from_secs_f64(value));
|
||||
} else if unit == "ms" {
|
||||
return Some(Duration::from_millis(value as u64));
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -907,7 +871,7 @@ mod tests {
|
||||
msg,
|
||||
"Rate limit reached for gpt-5 in organization org-AAA on tokens per min (TPM): Limit 30000, Used 22999, Requested 12528. Please try again in 11.054s. Visit https://platform.openai.com/account/rate-limits to learn more."
|
||||
);
|
||||
assert_eq!(*delay, Some(Duration::from_secs_f64(11.054)));
|
||||
assert_eq!(*delay, None);
|
||||
}
|
||||
other => panic!("unexpected second event: {other:?}"),
|
||||
}
|
||||
@@ -1011,27 +975,4 @@ mod tests {
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_try_parse_retry_after() {
|
||||
let err = Error {
|
||||
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()),
|
||||
};
|
||||
|
||||
let delay = try_parse_retry_after(&err);
|
||||
assert_eq!(delay, Some(Duration::from_millis(28)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_try_parse_retry_after_no_delay() {
|
||||
let err = Error {
|
||||
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()),
|
||||
};
|
||||
let delay = try_parse_retry_after(&err);
|
||||
assert_eq!(delay, Some(Duration::from_secs_f64(1.898)));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -95,7 +95,6 @@ pub enum ResponseEvent {
|
||||
ReasoningSummaryPartAdded,
|
||||
WebSearchCallBegin {
|
||||
call_id: String,
|
||||
query: Option<String>,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@@ -15,6 +15,7 @@ use codex_apply_patch::MaybeApplyPatchVerified;
|
||||
use codex_apply_patch::maybe_parse_apply_patch_verified;
|
||||
use codex_login::AuthManager;
|
||||
use codex_protocol::protocol::ConversationHistoryResponseEvent;
|
||||
use codex_protocol::protocol::TaskStartedEvent;
|
||||
use codex_protocol::protocol::TurnAbortReason;
|
||||
use codex_protocol::protocol::TurnAbortedEvent;
|
||||
use futures::prelude::*;
|
||||
@@ -55,15 +56,17 @@ use crate::exec::StreamOutput;
|
||||
use crate::exec::process_exec_tool_call;
|
||||
use crate::exec_command::EXEC_COMMAND_TOOL_NAME;
|
||||
use crate::exec_command::ExecCommandParams;
|
||||
use crate::exec_command::SESSION_MANAGER;
|
||||
use crate::exec_command::ExecSessionManager;
|
||||
use crate::exec_command::WRITE_STDIN_TOOL_NAME;
|
||||
use crate::exec_command::WriteStdinParams;
|
||||
use crate::exec_env::create_env;
|
||||
use crate::mcp_connection_manager::McpConnectionManager;
|
||||
use crate::mcp_tool_call::handle_mcp_tool_call;
|
||||
use crate::model_family::find_family_for_model;
|
||||
use crate::openai_model_info::get_model_info;
|
||||
use crate::openai_tools::ApplyPatchToolArgs;
|
||||
use crate::openai_tools::ToolsConfig;
|
||||
use crate::openai_tools::ToolsConfigParams;
|
||||
use crate::openai_tools::get_openai_tools;
|
||||
use crate::parse_command::parse_command;
|
||||
use crate::plan_tool::handle_update_plan;
|
||||
@@ -86,6 +89,7 @@ use crate::protocol::ExecCommandBeginEvent;
|
||||
use crate::protocol::ExecCommandEndEvent;
|
||||
use crate::protocol::FileChange;
|
||||
use crate::protocol::InputItem;
|
||||
use crate::protocol::ListCustomPromptsResponseEvent;
|
||||
use crate::protocol::Op;
|
||||
use crate::protocol::PatchApplyBeginEvent;
|
||||
use crate::protocol::PatchApplyEndEvent;
|
||||
@@ -97,6 +101,7 @@ use crate::protocol::Submission;
|
||||
use crate::protocol::TaskCompleteEvent;
|
||||
use crate::protocol::TurnDiffEvent;
|
||||
use crate::protocol::WebSearchBeginEvent;
|
||||
use crate::protocol::WebSearchEndEvent;
|
||||
use crate::rollout::RolloutRecorder;
|
||||
use crate::safety::SafetyCheck;
|
||||
use crate::safety::assess_command_safety;
|
||||
@@ -107,6 +112,7 @@ use crate::user_notification::UserNotification;
|
||||
use crate::util::backoff;
|
||||
use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
|
||||
use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
|
||||
use codex_protocol::custom_prompts::CustomPrompt;
|
||||
use codex_protocol::models::ContentItem;
|
||||
use codex_protocol::models::FunctionCallOutputPayload;
|
||||
use codex_protocol::models::LocalShellAction;
|
||||
@@ -115,6 +121,7 @@ use codex_protocol::models::ReasoningItemReasoningSummary;
|
||||
use codex_protocol::models::ResponseInputItem;
|
||||
use codex_protocol::models::ResponseItem;
|
||||
use codex_protocol::models::ShellToolCallParams;
|
||||
use codex_protocol::models::WebSearchAction;
|
||||
|
||||
// A convenience extension trait for acquiring mutex locks where poisoning is
|
||||
// unrecoverable and should abort the program. This avoids scattered `.unwrap()`
|
||||
@@ -268,6 +275,7 @@ pub(crate) struct Session {
|
||||
|
||||
/// Manager for external MCP servers/tools.
|
||||
mcp_connection_manager: McpConnectionManager,
|
||||
session_manager: ExecSessionManager,
|
||||
|
||||
/// External notifier command (will be passed as args to exec()). When
|
||||
/// `None` this feature is disabled.
|
||||
@@ -506,15 +514,16 @@ impl Session {
|
||||
);
|
||||
let turn_context = TurnContext {
|
||||
client,
|
||||
tools_config: ToolsConfig::new(
|
||||
&config.model_family,
|
||||
tools_config: ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &config.model_family,
|
||||
approval_policy,
|
||||
sandbox_policy.clone(),
|
||||
config.include_plan_tool,
|
||||
config.include_apply_patch_tool,
|
||||
config.tools_web_search_request,
|
||||
config.use_experimental_streamable_shell_tool,
|
||||
),
|
||||
sandbox_policy: sandbox_policy.clone(),
|
||||
include_plan_tool: config.include_plan_tool,
|
||||
include_apply_patch_tool: config.include_apply_patch_tool,
|
||||
include_web_search_request: config.tools_web_search_request,
|
||||
use_streamable_shell_tool: config.use_experimental_streamable_shell_tool,
|
||||
include_view_image_tool: config.include_view_image_tool,
|
||||
}),
|
||||
user_instructions,
|
||||
base_instructions,
|
||||
approval_policy,
|
||||
@@ -527,6 +536,7 @@ impl Session {
|
||||
session_id,
|
||||
tx_event: tx_event.clone(),
|
||||
mcp_connection_manager,
|
||||
session_manager: ExecSessionManager::default(),
|
||||
notify,
|
||||
state: Mutex::new(state),
|
||||
rollout: Mutex::new(rollout_recorder),
|
||||
@@ -1076,6 +1086,9 @@ async fn submission_loop(
|
||||
let mut updated_config = (*config).clone();
|
||||
updated_config.model = effective_model.clone();
|
||||
updated_config.model_family = effective_family.clone();
|
||||
if let Some(model_info) = get_model_info(&effective_family) {
|
||||
updated_config.model_context_window = Some(model_info.context_window);
|
||||
}
|
||||
|
||||
let client = ModelClient::new(
|
||||
Arc::new(updated_config),
|
||||
@@ -1092,15 +1105,16 @@ async fn submission_loop(
|
||||
.unwrap_or(prev.sandbox_policy.clone());
|
||||
let new_cwd = cwd.clone().unwrap_or_else(|| prev.cwd.clone());
|
||||
|
||||
let tools_config = ToolsConfig::new(
|
||||
&effective_family,
|
||||
new_approval_policy,
|
||||
new_sandbox_policy.clone(),
|
||||
config.include_plan_tool,
|
||||
config.include_apply_patch_tool,
|
||||
config.tools_web_search_request,
|
||||
config.use_experimental_streamable_shell_tool,
|
||||
);
|
||||
let tools_config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &effective_family,
|
||||
approval_policy: new_approval_policy,
|
||||
sandbox_policy: new_sandbox_policy.clone(),
|
||||
include_plan_tool: config.include_plan_tool,
|
||||
include_apply_patch_tool: config.include_apply_patch_tool,
|
||||
include_web_search_request: config.tools_web_search_request,
|
||||
use_streamable_shell_tool: config.use_experimental_streamable_shell_tool,
|
||||
include_view_image_tool: config.include_view_image_tool,
|
||||
});
|
||||
|
||||
let new_turn_context = TurnContext {
|
||||
client,
|
||||
@@ -1149,6 +1163,7 @@ async fn submission_loop(
|
||||
if let Err(items) = sess.inject_input(items) {
|
||||
// Derive a fresh TurnContext for this turn using the provided overrides.
|
||||
let provider = turn_context.client.get_provider();
|
||||
let auth_manager = turn_context.client.get_auth_manager();
|
||||
|
||||
// Derive a model family for the requested model; fall back to the session's.
|
||||
let model_family = find_family_for_model(&model)
|
||||
@@ -1158,12 +1173,15 @@ async fn submission_loop(
|
||||
let mut per_turn_config = (*config).clone();
|
||||
per_turn_config.model = model.clone();
|
||||
per_turn_config.model_family = model_family.clone();
|
||||
if let Some(model_info) = get_model_info(&model_family) {
|
||||
per_turn_config.model_context_window = Some(model_info.context_window);
|
||||
}
|
||||
|
||||
// Build a new client with per‑turn reasoning settings.
|
||||
// Reuse the same provider and session id; auth defaults to env/API key.
|
||||
let client = ModelClient::new(
|
||||
Arc::new(per_turn_config),
|
||||
None,
|
||||
auth_manager,
|
||||
provider,
|
||||
effort,
|
||||
summary,
|
||||
@@ -1172,15 +1190,17 @@ async fn submission_loop(
|
||||
|
||||
let fresh_turn_context = TurnContext {
|
||||
client,
|
||||
tools_config: ToolsConfig::new(
|
||||
&model_family,
|
||||
tools_config: ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy,
|
||||
sandbox_policy.clone(),
|
||||
config.include_plan_tool,
|
||||
config.include_apply_patch_tool,
|
||||
config.tools_web_search_request,
|
||||
config.use_experimental_streamable_shell_tool,
|
||||
),
|
||||
sandbox_policy: sandbox_policy.clone(),
|
||||
include_plan_tool: config.include_plan_tool,
|
||||
include_apply_patch_tool: config.include_apply_patch_tool,
|
||||
include_web_search_request: config.tools_web_search_request,
|
||||
use_streamable_shell_tool: config
|
||||
.use_experimental_streamable_shell_tool,
|
||||
include_view_image_tool: config.include_view_image_tool,
|
||||
}),
|
||||
user_instructions: turn_context.user_instructions.clone(),
|
||||
base_instructions: turn_context.base_instructions.clone(),
|
||||
approval_policy,
|
||||
@@ -1270,6 +1290,27 @@ async fn submission_loop(
|
||||
warn!("failed to send McpListToolsResponse event: {e}");
|
||||
}
|
||||
}
|
||||
Op::ListCustomPrompts => {
|
||||
let tx_event = sess.tx_event.clone();
|
||||
let sub_id = sub.id.clone();
|
||||
|
||||
let custom_prompts: Vec<CustomPrompt> =
|
||||
if let Some(dir) = crate::custom_prompts::default_prompts_dir() {
|
||||
crate::custom_prompts::discover_prompts_in(&dir).await
|
||||
} else {
|
||||
Vec::new()
|
||||
};
|
||||
|
||||
let event = Event {
|
||||
id: sub_id,
|
||||
msg: EventMsg::ListCustomPromptsResponse(ListCustomPromptsResponseEvent {
|
||||
custom_prompts,
|
||||
}),
|
||||
};
|
||||
if let Err(e) = tx_event.send(event).await {
|
||||
warn!("failed to send ListCustomPromptsResponse event: {e}");
|
||||
}
|
||||
}
|
||||
Op::Compact => {
|
||||
// Create a summarization request as user input
|
||||
const SUMMARIZATION_PROMPT: &str = include_str!("prompt_for_compact_command.md");
|
||||
@@ -1365,7 +1406,9 @@ async fn run_task(
|
||||
}
|
||||
let event = Event {
|
||||
id: sub_id.clone(),
|
||||
msg: EventMsg::TaskStarted,
|
||||
msg: EventMsg::TaskStarted(TaskStartedEvent {
|
||||
model_context_window: turn_context.client.get_model_context_window(),
|
||||
}),
|
||||
};
|
||||
if sess.tx_event.send(event).await.is_err() {
|
||||
return;
|
||||
@@ -1728,13 +1771,12 @@ async fn try_run_turn(
|
||||
.await?;
|
||||
output.push(ProcessedResponseItem { item, response });
|
||||
}
|
||||
ResponseEvent::WebSearchCallBegin { call_id, query } => {
|
||||
let q = query.unwrap_or_else(|| "Searching Web...".to_string());
|
||||
ResponseEvent::WebSearchCallBegin { call_id } => {
|
||||
let _ = sess
|
||||
.tx_event
|
||||
.send(Event {
|
||||
id: sub_id.to_string(),
|
||||
msg: EventMsg::WebSearchBegin(WebSearchBeginEvent { call_id, query: q }),
|
||||
msg: EventMsg::WebSearchBegin(WebSearchBeginEvent { call_id }),
|
||||
})
|
||||
.await;
|
||||
}
|
||||
@@ -1765,11 +1807,6 @@ async fn try_run_turn(
|
||||
return Ok(output);
|
||||
}
|
||||
ResponseEvent::OutputTextDelta(delta) => {
|
||||
{
|
||||
let mut st = sess.state.lock_unchecked();
|
||||
st.history.append_assistant_text(&delta);
|
||||
}
|
||||
|
||||
let event = Event {
|
||||
id: sub_id.to_string(),
|
||||
msg: EventMsg::AgentMessageDelta(AgentMessageDeltaEvent { delta }),
|
||||
@@ -1812,9 +1849,12 @@ async fn run_compact_task(
|
||||
input: Vec<InputItem>,
|
||||
compact_instructions: String,
|
||||
) {
|
||||
let model_context_window = turn_context.client.get_model_context_window();
|
||||
let start_event = Event {
|
||||
id: sub_id.clone(),
|
||||
msg: EventMsg::TaskStarted,
|
||||
msg: EventMsg::TaskStarted(TaskStartedEvent {
|
||||
model_context_window,
|
||||
}),
|
||||
};
|
||||
if sess.tx_event.send(start_event).await.is_err() {
|
||||
return;
|
||||
@@ -1868,6 +1908,12 @@ async fn run_compact_task(
|
||||
}
|
||||
|
||||
sess.remove_task(&sub_id);
|
||||
|
||||
{
|
||||
let mut state = sess.state.lock_unchecked();
|
||||
state.history.keep_last_messages(1);
|
||||
}
|
||||
|
||||
let event = Event {
|
||||
id: sub_id.clone(),
|
||||
msg: EventMsg::AgentMessage(AgentMessageEvent {
|
||||
@@ -1882,9 +1928,6 @@ async fn run_compact_task(
|
||||
}),
|
||||
};
|
||||
sess.send_event(event).await;
|
||||
|
||||
let mut state = sess.state.lock_unchecked();
|
||||
state.history.keep_last_messages(1);
|
||||
}
|
||||
|
||||
async fn handle_response_item(
|
||||
@@ -2032,6 +2075,17 @@ async fn handle_response_item(
|
||||
debug!("unexpected CustomToolCallOutput from stream");
|
||||
None
|
||||
}
|
||||
ResponseItem::WebSearchCall { id, action, .. } => {
|
||||
if let WebSearchAction::Search { query } = action {
|
||||
let call_id = id.unwrap_or_else(|| "".to_string());
|
||||
let event = Event {
|
||||
id: sub_id.to_string(),
|
||||
msg: EventMsg::WebSearchEnd(WebSearchEndEvent { call_id, query }),
|
||||
};
|
||||
sess.tx_event.send(event).await.ok();
|
||||
}
|
||||
None
|
||||
}
|
||||
ResponseItem::Other => None,
|
||||
};
|
||||
Ok(output)
|
||||
@@ -2064,6 +2118,36 @@ async fn handle_function_call(
|
||||
)
|
||||
.await
|
||||
}
|
||||
"view_image" => {
|
||||
#[derive(serde::Deserialize)]
|
||||
struct SeeImageArgs {
|
||||
path: String,
|
||||
}
|
||||
let args = match serde_json::from_str::<SeeImageArgs>(&arguments) {
|
||||
Ok(a) => a,
|
||||
Err(e) => {
|
||||
return ResponseInputItem::FunctionCallOutput {
|
||||
call_id,
|
||||
output: FunctionCallOutputPayload {
|
||||
content: format!("failed to parse function arguments: {e}"),
|
||||
success: Some(false),
|
||||
},
|
||||
};
|
||||
}
|
||||
};
|
||||
let abs = turn_context.resolve_path(Some(args.path));
|
||||
let output = match sess.inject_input(vec![InputItem::LocalImage { path: abs }]) {
|
||||
Ok(()) => FunctionCallOutputPayload {
|
||||
content: "attached local image path".to_string(),
|
||||
success: Some(true),
|
||||
},
|
||||
Err(_) => FunctionCallOutputPayload {
|
||||
content: "unable to attach image (no active task)".to_string(),
|
||||
success: Some(false),
|
||||
},
|
||||
};
|
||||
ResponseInputItem::FunctionCallOutput { call_id, output }
|
||||
}
|
||||
"apply_patch" => {
|
||||
let args = match serde_json::from_str::<ApplyPatchToolArgs>(&arguments) {
|
||||
Ok(a) => a,
|
||||
@@ -2110,7 +2194,8 @@ async fn handle_function_call(
|
||||
};
|
||||
}
|
||||
};
|
||||
let result = SESSION_MANAGER
|
||||
let result = sess
|
||||
.session_manager
|
||||
.handle_exec_command_request(exec_params)
|
||||
.await;
|
||||
let function_call_output = crate::exec_command::result_into_payload(result);
|
||||
@@ -2132,7 +2217,8 @@ async fn handle_function_call(
|
||||
};
|
||||
}
|
||||
};
|
||||
let result = SESSION_MANAGER
|
||||
let result = sess
|
||||
.session_manager
|
||||
.handle_write_stdin_request(write_stdin_params)
|
||||
.await;
|
||||
let function_call_output: FunctionCallOutputPayload =
|
||||
@@ -2448,11 +2534,15 @@ async fn handle_container_exec_with_params(
|
||||
sandbox_type,
|
||||
sandbox_policy: &turn_context.sandbox_policy,
|
||||
codex_linux_sandbox_exe: &sess.codex_linux_sandbox_exe,
|
||||
stdout_stream: Some(StdoutStream {
|
||||
sub_id: sub_id.clone(),
|
||||
call_id: call_id.clone(),
|
||||
tx_event: sess.tx_event.clone(),
|
||||
}),
|
||||
stdout_stream: if exec_command_context.apply_patch.is_some() {
|
||||
None
|
||||
} else {
|
||||
Some(StdoutStream {
|
||||
sub_id: sub_id.clone(),
|
||||
call_id: call_id.clone(),
|
||||
tx_event: sess.tx_event.clone(),
|
||||
})
|
||||
},
|
||||
},
|
||||
)
|
||||
.await;
|
||||
@@ -2581,11 +2671,15 @@ async fn handle_sandbox_error(
|
||||
sandbox_type: SandboxType::None,
|
||||
sandbox_policy: &turn_context.sandbox_policy,
|
||||
codex_linux_sandbox_exe: &sess.codex_linux_sandbox_exe,
|
||||
stdout_stream: Some(StdoutStream {
|
||||
sub_id: sub_id.clone(),
|
||||
call_id: call_id.clone(),
|
||||
tx_event: sess.tx_event.clone(),
|
||||
}),
|
||||
stdout_stream: if exec_command_context.apply_patch.is_some() {
|
||||
None
|
||||
} else {
|
||||
Some(StdoutStream {
|
||||
sub_id: sub_id.clone(),
|
||||
call_id: call_id.clone(),
|
||||
tx_event: sess.tx_event.clone(),
|
||||
})
|
||||
},
|
||||
},
|
||||
)
|
||||
.await;
|
||||
@@ -2810,15 +2904,9 @@ async fn drain_to_completed(
|
||||
response_id: _,
|
||||
token_usage,
|
||||
}) => {
|
||||
let token_usage = match token_usage {
|
||||
Some(usage) => usage,
|
||||
None => {
|
||||
return Err(CodexErr::Stream(
|
||||
"token_usage was None in ResponseEvent::Completed".into(),
|
||||
None,
|
||||
));
|
||||
}
|
||||
};
|
||||
// some providers don't return token usage, so we default
|
||||
// TODO: consider approximate token usage
|
||||
let token_usage = token_usage.unwrap_or_default();
|
||||
sess.tx_event
|
||||
.send(Event {
|
||||
id: sub_id.to_string(),
|
||||
@@ -2826,6 +2914,7 @@ async fn drain_to_completed(
|
||||
})
|
||||
.await
|
||||
.ok();
|
||||
|
||||
return Ok(());
|
||||
}
|
||||
Ok(_) => continue,
|
||||
|
||||
@@ -178,6 +178,13 @@ pub struct Config {
|
||||
pub preferred_auth_method: AuthMode,
|
||||
|
||||
pub use_experimental_streamable_shell_tool: bool,
|
||||
|
||||
/// Include the `view_image` tool that lets the agent attach a local image path to context.
|
||||
pub include_view_image_tool: bool,
|
||||
/// When true, disables burst-paste detection for typed input entirely.
|
||||
/// All characters are inserted as they are received, and no buffering
|
||||
/// or placeholder replacement will occur for fast keypress bursts.
|
||||
pub disable_paste_burst: bool,
|
||||
}
|
||||
|
||||
impl Config {
|
||||
@@ -485,6 +492,11 @@ pub struct ConfigToml {
|
||||
|
||||
/// Nested tools section for feature toggles
|
||||
pub tools: Option<ToolsToml>,
|
||||
|
||||
/// When true, disables burst-paste detection for typed input entirely.
|
||||
/// All characters are inserted as they are received, and no buffering
|
||||
/// or placeholder replacement will occur for fast keypress bursts.
|
||||
pub disable_paste_burst: Option<bool>,
|
||||
}
|
||||
|
||||
#[derive(Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
@@ -494,9 +506,12 @@ pub struct ProjectConfig {
|
||||
|
||||
#[derive(Deserialize, Debug, Clone, Default)]
|
||||
pub struct ToolsToml {
|
||||
// Renamed from `web_search_request`; keep alias for backwards compatibility.
|
||||
#[serde(default, alias = "web_search_request")]
|
||||
pub web_search: Option<bool>,
|
||||
|
||||
/// Enable the `view_image` tool that lets the agent attach local images.
|
||||
#[serde(default)]
|
||||
pub view_image: Option<bool>,
|
||||
}
|
||||
|
||||
impl ConfigToml {
|
||||
@@ -586,6 +601,7 @@ pub struct ConfigOverrides {
|
||||
pub base_instructions: Option<String>,
|
||||
pub include_plan_tool: Option<bool>,
|
||||
pub include_apply_patch_tool: Option<bool>,
|
||||
pub include_view_image_tool: Option<bool>,
|
||||
pub disable_response_storage: Option<bool>,
|
||||
pub show_raw_agent_reasoning: Option<bool>,
|
||||
pub tools_web_search_request: Option<bool>,
|
||||
@@ -613,6 +629,7 @@ impl Config {
|
||||
base_instructions,
|
||||
include_plan_tool,
|
||||
include_apply_patch_tool,
|
||||
include_view_image_tool,
|
||||
disable_response_storage,
|
||||
show_raw_agent_reasoning,
|
||||
tools_web_search_request: override_tools_web_search_request,
|
||||
@@ -654,7 +671,7 @@ impl Config {
|
||||
})?
|
||||
.clone();
|
||||
|
||||
let shell_environment_policy = cfg.shell_environment_policy.clone().into();
|
||||
let shell_environment_policy = cfg.shell_environment_policy.into();
|
||||
|
||||
let resolved_cwd = {
|
||||
use std::env;
|
||||
@@ -675,12 +692,16 @@ impl Config {
|
||||
}
|
||||
};
|
||||
|
||||
let history = cfg.history.clone().unwrap_or_default();
|
||||
let history = cfg.history.unwrap_or_default();
|
||||
|
||||
let tools_web_search_request = override_tools_web_search_request
|
||||
.or(cfg.tools.as_ref().and_then(|t| t.web_search))
|
||||
.unwrap_or(false);
|
||||
|
||||
let include_view_image_tool = include_view_image_tool
|
||||
.or(cfg.tools.as_ref().and_then(|t| t.view_image))
|
||||
.unwrap_or(true);
|
||||
|
||||
let model = model
|
||||
.or(config_profile.model)
|
||||
.or(cfg.model)
|
||||
@@ -753,7 +774,7 @@ impl Config {
|
||||
codex_home,
|
||||
history,
|
||||
file_opener: cfg.file_opener.unwrap_or(UriBasedFileOpener::VsCode),
|
||||
tui: cfg.tui.clone().unwrap_or_default(),
|
||||
tui: cfg.tui.unwrap_or_default(),
|
||||
codex_linux_sandbox_exe,
|
||||
|
||||
hide_agent_reasoning: cfg.hide_agent_reasoning.unwrap_or(false),
|
||||
@@ -772,7 +793,7 @@ impl Config {
|
||||
model_verbosity: config_profile.model_verbosity.or(cfg.model_verbosity),
|
||||
chatgpt_base_url: config_profile
|
||||
.chatgpt_base_url
|
||||
.or(cfg.chatgpt_base_url.clone())
|
||||
.or(cfg.chatgpt_base_url)
|
||||
.unwrap_or("https://chatgpt.com/backend-api/".to_string()),
|
||||
|
||||
experimental_resume,
|
||||
@@ -784,6 +805,8 @@ impl Config {
|
||||
use_experimental_streamable_shell_tool: cfg
|
||||
.experimental_use_exec_command_tool
|
||||
.unwrap_or(false),
|
||||
include_view_image_tool,
|
||||
disable_paste_burst: cfg.disable_paste_burst.unwrap_or(false),
|
||||
};
|
||||
Ok(config)
|
||||
}
|
||||
@@ -1152,6 +1175,8 @@ disable_response_storage = true
|
||||
responses_originator_header: "codex_cli_rs".to_string(),
|
||||
preferred_auth_method: AuthMode::ChatGPT,
|
||||
use_experimental_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
disable_paste_burst: false,
|
||||
},
|
||||
o3_profile_config
|
||||
);
|
||||
@@ -1208,6 +1233,8 @@ disable_response_storage = true
|
||||
responses_originator_header: "codex_cli_rs".to_string(),
|
||||
preferred_auth_method: AuthMode::ChatGPT,
|
||||
use_experimental_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
disable_paste_burst: false,
|
||||
};
|
||||
|
||||
assert_eq!(expected_gpt3_profile_config, gpt3_profile_config);
|
||||
@@ -1279,6 +1306,8 @@ disable_response_storage = true
|
||||
responses_originator_header: "codex_cli_rs".to_string(),
|
||||
preferred_auth_method: AuthMode::ChatGPT,
|
||||
use_experimental_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
disable_paste_burst: false,
|
||||
};
|
||||
|
||||
assert_eq!(expected_zdr_profile_config, zdr_profile_config);
|
||||
@@ -1300,9 +1329,9 @@ disable_response_storage = true
|
||||
|
||||
let raw_path = project_dir.path().to_string_lossy();
|
||||
let path_str = if raw_path.contains('\\') {
|
||||
format!("'{}'", raw_path)
|
||||
format!("'{raw_path}'")
|
||||
} else {
|
||||
format!("\"{}\"", raw_path)
|
||||
format!("\"{raw_path}\"")
|
||||
};
|
||||
let expected = format!(
|
||||
r#"[projects.{path_str}]
|
||||
@@ -1323,9 +1352,9 @@ trust_level = "trusted"
|
||||
let config_path = codex_home.path().join(CONFIG_TOML_FILE);
|
||||
let raw_path = project_dir.path().to_string_lossy();
|
||||
let path_str = if raw_path.contains('\\') {
|
||||
format!("'{}'", raw_path)
|
||||
format!("'{raw_path}'")
|
||||
} else {
|
||||
format!("\"{}\"", raw_path)
|
||||
format!("\"{raw_path}\"")
|
||||
};
|
||||
// Use a quoted key so backslashes don't require escaping on Windows
|
||||
let initial = format!(
|
||||
|
||||
@@ -28,49 +28,7 @@ impl ConversationHistory {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Merge adjacent assistant messages into a single history entry.
|
||||
// This prevents duplicates when a partial assistant message was
|
||||
// streamed into history earlier in the turn and the final full
|
||||
// message is recorded at turn end.
|
||||
match (&*item, self.items.last_mut()) {
|
||||
(
|
||||
ResponseItem::Message {
|
||||
role: new_role,
|
||||
content: new_content,
|
||||
..
|
||||
},
|
||||
Some(ResponseItem::Message {
|
||||
role: last_role,
|
||||
content: last_content,
|
||||
..
|
||||
}),
|
||||
) if new_role == "assistant" && last_role == "assistant" => {
|
||||
append_text_content(last_content, new_content);
|
||||
}
|
||||
_ => {
|
||||
self.items.push(item.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Append a text `delta` to the latest assistant message, creating a new
|
||||
/// assistant entry if none exists yet (e.g. first delta for this turn).
|
||||
pub(crate) fn append_assistant_text(&mut self, delta: &str) {
|
||||
match self.items.last_mut() {
|
||||
Some(ResponseItem::Message { role, content, .. }) if role == "assistant" => {
|
||||
append_text_delta(content, delta);
|
||||
}
|
||||
_ => {
|
||||
// Start a new assistant message with the delta.
|
||||
self.items.push(ResponseItem::Message {
|
||||
id: None,
|
||||
role: "assistant".to_string(),
|
||||
content: vec![codex_protocol::models::ContentItem::OutputText {
|
||||
text: delta.to_string(),
|
||||
}],
|
||||
});
|
||||
}
|
||||
self.items.push(item.clone());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -114,35 +72,7 @@ fn is_api_message(message: &ResponseItem) -> bool {
|
||||
| ResponseItem::CustomToolCallOutput { .. }
|
||||
| ResponseItem::LocalShellCall { .. }
|
||||
| ResponseItem::Reasoning { .. } => true,
|
||||
ResponseItem::Other => false,
|
||||
}
|
||||
}
|
||||
|
||||
/// Helper to append the textual content from `src` into `dst` in place.
|
||||
fn append_text_content(
|
||||
dst: &mut Vec<codex_protocol::models::ContentItem>,
|
||||
src: &Vec<codex_protocol::models::ContentItem>,
|
||||
) {
|
||||
for c in src {
|
||||
if let codex_protocol::models::ContentItem::OutputText { text } = c {
|
||||
append_text_delta(dst, text);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Append a single text delta to the last OutputText item in `content`, or
|
||||
/// push a new OutputText item if none exists.
|
||||
fn append_text_delta(content: &mut Vec<codex_protocol::models::ContentItem>, delta: &str) {
|
||||
if let Some(codex_protocol::models::ContentItem::OutputText { text }) = content
|
||||
.iter_mut()
|
||||
.rev()
|
||||
.find(|c| matches!(c, codex_protocol::models::ContentItem::OutputText { .. }))
|
||||
{
|
||||
text.push_str(delta);
|
||||
} else {
|
||||
content.push(codex_protocol::models::ContentItem::OutputText {
|
||||
text: delta.to_string(),
|
||||
});
|
||||
ResponseItem::WebSearchCall { .. } | ResponseItem::Other => false,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -171,49 +101,6 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn merges_adjacent_assistant_messages() {
|
||||
let mut h = ConversationHistory::default();
|
||||
let a1 = assistant_msg("Hello");
|
||||
let a2 = assistant_msg(", world!");
|
||||
h.record_items([&a1, &a2]);
|
||||
|
||||
let items = h.contents();
|
||||
assert_eq!(
|
||||
items,
|
||||
vec![ResponseItem::Message {
|
||||
id: None,
|
||||
role: "assistant".to_string(),
|
||||
content: vec![ContentItem::OutputText {
|
||||
text: "Hello, world!".to_string()
|
||||
}]
|
||||
}]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn append_assistant_text_creates_and_appends() {
|
||||
let mut h = ConversationHistory::default();
|
||||
h.append_assistant_text("Hello");
|
||||
h.append_assistant_text(", world");
|
||||
|
||||
// Now record a final full assistant message and verify it merges.
|
||||
let final_msg = assistant_msg("!");
|
||||
h.record_items([&final_msg]);
|
||||
|
||||
let items = h.contents();
|
||||
assert_eq!(
|
||||
items,
|
||||
vec![ResponseItem::Message {
|
||||
id: None,
|
||||
role: "assistant".to_string(),
|
||||
content: vec![ContentItem::OutputText {
|
||||
text: "Hello, world!".to_string()
|
||||
}]
|
||||
}]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn filters_non_api_messages() {
|
||||
let mut h = ConversationHistory::default();
|
||||
|
||||
@@ -110,6 +110,10 @@ impl ConversationManager {
|
||||
.ok_or_else(|| CodexErr::ConversationNotFound(conversation_id))
|
||||
}
|
||||
|
||||
pub async fn remove_conversation(&self, conversation_id: Uuid) {
|
||||
self.conversations.write().await.remove(&conversation_id);
|
||||
}
|
||||
|
||||
/// Fork an existing conversation by dropping the last `drop_last_messages`
|
||||
/// user/assistant messages from its transcript and starting a new
|
||||
/// conversation with identical configuration (unless overridden by the
|
||||
|
||||
127
codex-rs/core/src/custom_prompts.rs
Normal file
127
codex-rs/core/src/custom_prompts.rs
Normal file
@@ -0,0 +1,127 @@
|
||||
use codex_protocol::custom_prompts::CustomPrompt;
|
||||
use std::collections::HashSet;
|
||||
use std::path::Path;
|
||||
use std::path::PathBuf;
|
||||
use tokio::fs;
|
||||
|
||||
/// Return the default prompts directory: `$CODEX_HOME/prompts`.
|
||||
/// If `CODEX_HOME` cannot be resolved, returns `None`.
|
||||
pub fn default_prompts_dir() -> Option<PathBuf> {
|
||||
crate::config::find_codex_home()
|
||||
.ok()
|
||||
.map(|home| home.join("prompts"))
|
||||
}
|
||||
|
||||
/// Discover prompt files in the given directory, returning entries sorted by name.
|
||||
/// Non-files are ignored. If the directory does not exist or cannot be read, returns empty.
|
||||
pub async fn discover_prompts_in(dir: &Path) -> Vec<CustomPrompt> {
|
||||
discover_prompts_in_excluding(dir, &HashSet::new()).await
|
||||
}
|
||||
|
||||
/// Discover prompt files in the given directory, excluding any with names in `exclude`.
|
||||
/// Returns entries sorted by name. Non-files are ignored. Missing/unreadable dir yields empty.
|
||||
pub async fn discover_prompts_in_excluding(
|
||||
dir: &Path,
|
||||
exclude: &HashSet<String>,
|
||||
) -> Vec<CustomPrompt> {
|
||||
let mut out: Vec<CustomPrompt> = Vec::new();
|
||||
let mut entries = match fs::read_dir(dir).await {
|
||||
Ok(entries) => entries,
|
||||
Err(_) => return out,
|
||||
};
|
||||
|
||||
while let Ok(Some(entry)) = entries.next_entry().await {
|
||||
let path = entry.path();
|
||||
let is_file = entry
|
||||
.file_type()
|
||||
.await
|
||||
.map(|ft| ft.is_file())
|
||||
.unwrap_or(false);
|
||||
if !is_file {
|
||||
continue;
|
||||
}
|
||||
// Only include Markdown files with a .md extension.
|
||||
let is_md = path
|
||||
.extension()
|
||||
.and_then(|s| s.to_str())
|
||||
.map(|ext| ext.eq_ignore_ascii_case("md"))
|
||||
.unwrap_or(false);
|
||||
if !is_md {
|
||||
continue;
|
||||
}
|
||||
let Some(name) = path
|
||||
.file_stem()
|
||||
.and_then(|s| s.to_str())
|
||||
.map(|s| s.to_string())
|
||||
else {
|
||||
continue;
|
||||
};
|
||||
if exclude.contains(&name) {
|
||||
continue;
|
||||
}
|
||||
let content = match fs::read_to_string(&path).await {
|
||||
Ok(s) => s,
|
||||
Err(_) => continue,
|
||||
};
|
||||
out.push(CustomPrompt {
|
||||
name,
|
||||
path,
|
||||
content,
|
||||
});
|
||||
}
|
||||
out.sort_by(|a, b| a.name.cmp(&b.name));
|
||||
out
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use std::fs;
|
||||
use tempfile::tempdir;
|
||||
|
||||
#[tokio::test]
|
||||
async fn empty_when_dir_missing() {
|
||||
let tmp = tempdir().expect("create TempDir");
|
||||
let missing = tmp.path().join("nope");
|
||||
let found = discover_prompts_in(&missing).await;
|
||||
assert!(found.is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn discovers_and_sorts_files() {
|
||||
let tmp = tempdir().expect("create TempDir");
|
||||
let dir = tmp.path();
|
||||
fs::write(dir.join("b.md"), b"b").unwrap();
|
||||
fs::write(dir.join("a.md"), b"a").unwrap();
|
||||
fs::create_dir(dir.join("subdir")).unwrap();
|
||||
let found = discover_prompts_in(dir).await;
|
||||
let names: Vec<String> = found.into_iter().map(|e| e.name).collect();
|
||||
assert_eq!(names, vec!["a", "b"]);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn excludes_builtins() {
|
||||
let tmp = tempdir().expect("create TempDir");
|
||||
let dir = tmp.path();
|
||||
fs::write(dir.join("init.md"), b"ignored").unwrap();
|
||||
fs::write(dir.join("foo.md"), b"ok").unwrap();
|
||||
let mut exclude = HashSet::new();
|
||||
exclude.insert("init".to_string());
|
||||
let found = discover_prompts_in_excluding(dir, &exclude).await;
|
||||
let names: Vec<String> = found.into_iter().map(|e| e.name).collect();
|
||||
assert_eq!(names, vec!["foo"]);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn skips_non_utf8_files() {
|
||||
let tmp = tempdir().expect("create TempDir");
|
||||
let dir = tmp.path();
|
||||
// Valid UTF-8 file
|
||||
fs::write(dir.join("good.md"), b"hello").unwrap();
|
||||
// Invalid UTF-8 content in .md file (e.g., lone 0xFF byte)
|
||||
fs::write(dir.join("bad.md"), vec![0xFF, 0xFE, b'\n']).unwrap();
|
||||
let found = discover_prompts_in(dir).await;
|
||||
let names: Vec<String> = found.into_iter().map(|e| e.name).collect();
|
||||
assert_eq!(names, vec!["good"]);
|
||||
}
|
||||
}
|
||||
@@ -85,23 +85,21 @@ impl EnvironmentContext {
|
||||
}
|
||||
if let Some(approval_policy) = self.approval_policy {
|
||||
lines.push(format!(
|
||||
" <approval_policy>{}</approval_policy>",
|
||||
approval_policy
|
||||
" <approval_policy>{approval_policy}</approval_policy>"
|
||||
));
|
||||
}
|
||||
if let Some(sandbox_mode) = self.sandbox_mode {
|
||||
lines.push(format!(" <sandbox_mode>{}</sandbox_mode>", sandbox_mode));
|
||||
lines.push(format!(" <sandbox_mode>{sandbox_mode}</sandbox_mode>"));
|
||||
}
|
||||
if let Some(network_access) = self.network_access {
|
||||
lines.push(format!(
|
||||
" <network_access>{}</network_access>",
|
||||
network_access
|
||||
" <network_access>{network_access}</network_access>"
|
||||
));
|
||||
}
|
||||
if let Some(shell) = self.shell
|
||||
&& let Some(shell_name) = shell.name()
|
||||
{
|
||||
lines.push(format!(" <shell>{}</shell>", shell_name));
|
||||
lines.push(format!(" <shell>{shell_name}</shell>"));
|
||||
}
|
||||
lines.push(ENVIRONMENT_CONTEXT_END.to_string());
|
||||
lines.join("\n")
|
||||
|
||||
@@ -128,27 +128,70 @@ pub enum CodexErr {
|
||||
#[derive(Debug)]
|
||||
pub struct UsageLimitReachedError {
|
||||
pub plan_type: Option<String>,
|
||||
pub resets_in_seconds: Option<u64>,
|
||||
}
|
||||
|
||||
impl std::fmt::Display for UsageLimitReachedError {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
// Base message differs slightly for legacy ChatGPT Plus plan users.
|
||||
if let Some(plan_type) = &self.plan_type
|
||||
&& plan_type == "plus"
|
||||
{
|
||||
write!(
|
||||
f,
|
||||
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), or wait for limits to reset (every 5h and every week.)."
|
||||
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again"
|
||||
)?;
|
||||
if let Some(secs) = self.resets_in_seconds {
|
||||
let reset_duration = format_reset_duration(secs);
|
||||
write!(f, " in {reset_duration}.")?;
|
||||
} else {
|
||||
write!(f, " later.")?;
|
||||
}
|
||||
} else {
|
||||
write!(
|
||||
f,
|
||||
"You've hit your usage limit. Limits reset every 5h and every week."
|
||||
)?;
|
||||
write!(f, "You've hit your usage limit.")?;
|
||||
|
||||
if let Some(secs) = self.resets_in_seconds {
|
||||
let reset_duration = format_reset_duration(secs);
|
||||
write!(f, " Try again in {reset_duration}.")?;
|
||||
} else {
|
||||
write!(f, " Try again later.")?;
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
fn format_reset_duration(total_secs: u64) -> String {
|
||||
let days = total_secs / 86_400;
|
||||
let hours = (total_secs % 86_400) / 3_600;
|
||||
let minutes = (total_secs % 3_600) / 60;
|
||||
|
||||
let mut parts: Vec<String> = Vec::new();
|
||||
if days > 0 {
|
||||
let unit = if days == 1 { "day" } else { "days" };
|
||||
parts.push(format!("{days} {unit}"));
|
||||
}
|
||||
if hours > 0 {
|
||||
let unit = if hours == 1 { "hour" } else { "hours" };
|
||||
parts.push(format!("{hours} {unit}"));
|
||||
}
|
||||
if minutes > 0 {
|
||||
let unit = if minutes == 1 { "minute" } else { "minutes" };
|
||||
parts.push(format!("{minutes} {unit}"));
|
||||
}
|
||||
|
||||
if parts.is_empty() {
|
||||
return "less than a minute".to_string();
|
||||
}
|
||||
|
||||
match parts.len() {
|
||||
1 => parts[0].clone(),
|
||||
2 => format!("{} {}", parts[0], parts[1]),
|
||||
_ => format!("{} {} {}", parts[0], parts[1], parts[2]),
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
pub struct EnvVarError {
|
||||
/// Name of the environment variable that is missing.
|
||||
@@ -181,6 +224,8 @@ impl CodexErr {
|
||||
pub fn get_error_message_ui(e: &CodexErr) -> String {
|
||||
match e {
|
||||
CodexErr::Sandbox(SandboxErr::Denied(_, _, stderr)) => stderr.to_string(),
|
||||
// Timeouts are not sandbox errors from a UX perspective; present them plainly
|
||||
CodexErr::Sandbox(SandboxErr::Timeout) => "error: command timed out".to_string(),
|
||||
_ => e.to_string(),
|
||||
}
|
||||
}
|
||||
@@ -193,19 +238,23 @@ mod tests {
|
||||
fn usage_limit_reached_error_formats_plus_plan() {
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: Some("plus".to_string()),
|
||||
resets_in_seconds: None,
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), or wait for limits to reset (every 5h and every week.)."
|
||||
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again later."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn usage_limit_reached_error_formats_default_when_none() {
|
||||
let err = UsageLimitReachedError { plan_type: None };
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: None,
|
||||
resets_in_seconds: None,
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Limits reset every 5h and every week."
|
||||
"You've hit your usage limit. Try again later."
|
||||
);
|
||||
}
|
||||
|
||||
@@ -213,10 +262,59 @@ mod tests {
|
||||
fn usage_limit_reached_error_formats_default_for_other_plans() {
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: Some("pro".to_string()),
|
||||
resets_in_seconds: None,
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Limits reset every 5h and every week."
|
||||
"You've hit your usage limit. Try again later."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn usage_limit_reached_includes_minutes_when_available() {
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: None,
|
||||
resets_in_seconds: Some(5 * 60),
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Try again in 5 minutes."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn usage_limit_reached_includes_hours_and_minutes() {
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: Some("plus".to_string()),
|
||||
resets_in_seconds: Some(3 * 3600 + 32 * 60),
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again in 3 hours 32 minutes."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn usage_limit_reached_includes_days_hours_minutes() {
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: None,
|
||||
resets_in_seconds: Some(2 * 86_400 + 3 * 3600 + 5 * 60),
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Try again in 2 days 3 hours 5 minutes."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn usage_limit_reached_less_than_minute() {
|
||||
let err = UsageLimitReachedError {
|
||||
plan_type: None,
|
||||
resets_in_seconds: Some(30),
|
||||
};
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"You've hit your usage limit. Try again in less than a minute."
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -40,6 +40,10 @@ const EXIT_CODE_SIGNAL_BASE: i32 = 128; // conventional shell: 128 + signal
|
||||
const READ_CHUNK_SIZE: usize = 8192; // bytes per read
|
||||
const AGGREGATE_BUFFER_INITIAL_CAPACITY: usize = 8 * 1024; // 8 KiB
|
||||
|
||||
/// Limit the number of ExecCommandOutputDelta events emitted per exec call.
|
||||
/// Aggregation still collects full output; only the live event stream is capped.
|
||||
pub(crate) const MAX_EXEC_OUTPUT_DELTAS_PER_CALL: usize = 10_000;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ExecParams {
|
||||
pub command: Vec<String>,
|
||||
@@ -344,6 +348,7 @@ async fn read_capped<R: AsyncRead + Unpin + Send + 'static>(
|
||||
) -> io::Result<StreamOutput<Vec<u8>>> {
|
||||
let mut buf = Vec::with_capacity(AGGREGATE_BUFFER_INITIAL_CAPACITY);
|
||||
let mut tmp = [0u8; READ_CHUNK_SIZE];
|
||||
let mut emitted_deltas: usize = 0;
|
||||
|
||||
// No caps: append all bytes
|
||||
|
||||
@@ -353,7 +358,9 @@ async fn read_capped<R: AsyncRead + Unpin + Send + 'static>(
|
||||
break;
|
||||
}
|
||||
|
||||
if let Some(stream) = &stream {
|
||||
if let Some(stream) = &stream
|
||||
&& emitted_deltas < MAX_EXEC_OUTPUT_DELTAS_PER_CALL
|
||||
{
|
||||
let chunk = tmp[..n].to_vec();
|
||||
let msg = EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
|
||||
call_id: stream.call_id.clone(),
|
||||
@@ -370,6 +377,7 @@ async fn read_capped<R: AsyncRead + Unpin + Send + 'static>(
|
||||
};
|
||||
#[allow(clippy::let_unit_value)]
|
||||
let _ = stream.tx_event.send(event).await;
|
||||
emitted_deltas += 1;
|
||||
}
|
||||
|
||||
if let Some(tx) = &aggregate_tx {
|
||||
|
||||
@@ -10,5 +10,5 @@ pub use responses_api::EXEC_COMMAND_TOOL_NAME;
|
||||
pub use responses_api::WRITE_STDIN_TOOL_NAME;
|
||||
pub use responses_api::create_exec_command_tool_for_responses_api;
|
||||
pub use responses_api::create_write_stdin_tool_for_responses_api;
|
||||
pub use session_manager::SESSION_MANAGER;
|
||||
pub use session_manager::SessionManager as ExecSessionManager;
|
||||
pub use session_manager::result_into_payload;
|
||||
|
||||
@@ -2,7 +2,6 @@ use std::collections::HashMap;
|
||||
use std::io::ErrorKind;
|
||||
use std::io::Read;
|
||||
use std::sync::Arc;
|
||||
use std::sync::LazyLock;
|
||||
use std::sync::Mutex as StdMutex;
|
||||
use std::sync::atomic::AtomicU32;
|
||||
|
||||
@@ -22,8 +21,6 @@ use crate::exec_command::exec_command_session::ExecCommandSession;
|
||||
use crate::exec_command::session_id::SessionId;
|
||||
use codex_protocol::models::FunctionCallOutputPayload;
|
||||
|
||||
pub static SESSION_MANAGER: LazyLock<SessionManager> = LazyLock::new(SessionManager::default);
|
||||
|
||||
#[derive(Debug, Default)]
|
||||
pub struct SessionManager {
|
||||
next_session_id: AtomicU32,
|
||||
@@ -362,10 +359,7 @@ fn truncate_middle(s: &str, max_bytes: usize) -> (String, Option<u64>) {
|
||||
let est_tokens = (s.len() as u64).div_ceil(4);
|
||||
if max_bytes == 0 {
|
||||
// Cannot keep any content; still return a full marker (never truncated).
|
||||
return (
|
||||
format!("…{} tokens truncated…", est_tokens),
|
||||
Some(est_tokens),
|
||||
);
|
||||
return (format!("…{est_tokens} tokens truncated…"), Some(est_tokens));
|
||||
}
|
||||
|
||||
// Helper to truncate a string to a given byte length on a char boundary.
|
||||
@@ -409,16 +403,13 @@ fn truncate_middle(s: &str, max_bytes: usize) -> (String, Option<u64>) {
|
||||
// Refine marker length and budgets until stable. Marker is never truncated.
|
||||
let mut guess_tokens = est_tokens; // worst-case: everything truncated
|
||||
for _ in 0..4 {
|
||||
let marker = format!("…{} tokens truncated…", guess_tokens);
|
||||
let marker = format!("…{guess_tokens} tokens truncated…");
|
||||
let marker_len = marker.len();
|
||||
let keep_budget = max_bytes.saturating_sub(marker_len);
|
||||
if keep_budget == 0 {
|
||||
// No room for any content within the cap; return a full, untruncated marker
|
||||
// that reflects the entire truncated content.
|
||||
return (
|
||||
format!("…{} tokens truncated…", est_tokens),
|
||||
Some(est_tokens),
|
||||
);
|
||||
return (format!("…{est_tokens} tokens truncated…"), Some(est_tokens));
|
||||
}
|
||||
|
||||
let left_budget = keep_budget / 2;
|
||||
@@ -444,14 +435,11 @@ fn truncate_middle(s: &str, max_bytes: usize) -> (String, Option<u64>) {
|
||||
}
|
||||
|
||||
// Fallback: use last guess to build output.
|
||||
let marker = format!("…{} tokens truncated…", guess_tokens);
|
||||
let marker = format!("…{guess_tokens} tokens truncated…");
|
||||
let marker_len = marker.len();
|
||||
let keep_budget = max_bytes.saturating_sub(marker_len);
|
||||
if keep_budget == 0 {
|
||||
return (
|
||||
format!("…{} tokens truncated…", est_tokens),
|
||||
Some(est_tokens),
|
||||
);
|
||||
return (format!("…{est_tokens} tokens truncated…"), Some(est_tokens));
|
||||
}
|
||||
let left_budget = keep_budget / 2;
|
||||
let right_budget = keep_budget - left_budget;
|
||||
|
||||
@@ -385,7 +385,9 @@ async fn find_closest_sha(cwd: &Path, branches: &[String], remotes: &[String]) -
|
||||
}
|
||||
|
||||
async fn diff_against_sha(cwd: &Path, sha: &GitSha) -> Option<String> {
|
||||
let output = run_git_command_with_timeout(&["diff", &sha.0], cwd).await?;
|
||||
let output =
|
||||
run_git_command_with_timeout(&["diff", "--no-textconv", "--no-ext-diff", &sha.0], cwd)
|
||||
.await?;
|
||||
// 0 is success and no diff.
|
||||
// 1 is success but there is a diff.
|
||||
let exit_ok = output.status.code().is_some_and(|c| c == 0 || c == 1);
|
||||
@@ -406,10 +408,21 @@ async fn diff_against_sha(cwd: &Path, sha: &GitSha) -> Option<String> {
|
||||
.collect();
|
||||
|
||||
if !untracked.is_empty() {
|
||||
// Use platform-appropriate null device and guard paths with `--`.
|
||||
let null_device: &str = if cfg!(windows) { "NUL" } else { "/dev/null" };
|
||||
let futures_iter = untracked.into_iter().map(|file| async move {
|
||||
let file_owned = file;
|
||||
let args_vec: Vec<&str> =
|
||||
vec!["diff", "--binary", "--no-index", "/dev/null", &file_owned];
|
||||
let args_vec: Vec<&str> = vec![
|
||||
"diff",
|
||||
"--no-textconv",
|
||||
"--no-ext-diff",
|
||||
"--binary",
|
||||
"--no-index",
|
||||
// -- ensures that filenames that start with - are not treated as options.
|
||||
"--",
|
||||
null_device,
|
||||
&file_owned,
|
||||
];
|
||||
run_git_command_with_timeout(&args_vec, cwd).await
|
||||
});
|
||||
let results = join_all(futures_iter).await;
|
||||
|
||||
@@ -17,6 +17,7 @@ pub mod config;
|
||||
pub mod config_profile;
|
||||
pub mod config_types;
|
||||
mod conversation_history;
|
||||
pub mod custom_prompts;
|
||||
mod environment_context;
|
||||
pub mod error;
|
||||
pub mod exec;
|
||||
|
||||
@@ -17,6 +17,10 @@ use crate::error::EnvVarError;
|
||||
const DEFAULT_STREAM_IDLE_TIMEOUT_MS: u64 = 300_000;
|
||||
const DEFAULT_STREAM_MAX_RETRIES: u64 = 5;
|
||||
const DEFAULT_REQUEST_MAX_RETRIES: u64 = 4;
|
||||
/// Hard cap for user-configured `stream_max_retries`.
|
||||
const MAX_STREAM_MAX_RETRIES: u64 = 100;
|
||||
/// Hard cap for user-configured `request_max_retries`.
|
||||
const MAX_REQUEST_MAX_RETRIES: u64 = 100;
|
||||
|
||||
/// Wire protocol that the provider speaks. Most third-party services only
|
||||
/// implement the classic OpenAI Chat Completions JSON schema, whereas OpenAI
|
||||
@@ -207,12 +211,14 @@ impl ModelProviderInfo {
|
||||
pub fn request_max_retries(&self) -> u64 {
|
||||
self.request_max_retries
|
||||
.unwrap_or(DEFAULT_REQUEST_MAX_RETRIES)
|
||||
.min(MAX_REQUEST_MAX_RETRIES)
|
||||
}
|
||||
|
||||
/// Effective maximum number of stream reconnection attempts for this provider.
|
||||
pub fn stream_max_retries(&self) -> u64 {
|
||||
self.stream_max_retries
|
||||
.unwrap_or(DEFAULT_STREAM_MAX_RETRIES)
|
||||
.min(MAX_STREAM_MAX_RETRIES)
|
||||
}
|
||||
|
||||
/// Effective idle timeout for streaming responses.
|
||||
|
||||
@@ -47,7 +47,9 @@ pub(crate) enum OpenAiTool {
|
||||
Function(ResponsesApiTool),
|
||||
#[serde(rename = "local_shell")]
|
||||
LocalShell {},
|
||||
#[serde(rename = "web_search")]
|
||||
// TODO: Understand why we get an error on web_search although the API docs say it's supported.
|
||||
// https://platform.openai.com/docs/guides/tools-web-search?api-mode=responses#:~:text=%7B%20type%3A%20%22web_search%22%20%7D%2C
|
||||
#[serde(rename = "web_search_preview")]
|
||||
WebSearch {},
|
||||
#[serde(rename = "custom")]
|
||||
Freeform(FreeformTool),
|
||||
@@ -62,24 +64,38 @@ pub enum ConfigShellToolType {
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ToolsConfig {
|
||||
pub(crate) struct ToolsConfig {
|
||||
pub shell_type: ConfigShellToolType,
|
||||
pub plan_tool: bool,
|
||||
pub apply_patch_tool_type: Option<ApplyPatchToolType>,
|
||||
pub web_search_request: bool,
|
||||
pub include_view_image_tool: bool,
|
||||
}
|
||||
|
||||
pub(crate) struct ToolsConfigParams<'a> {
|
||||
pub(crate) model_family: &'a ModelFamily,
|
||||
pub(crate) approval_policy: AskForApproval,
|
||||
pub(crate) sandbox_policy: SandboxPolicy,
|
||||
pub(crate) include_plan_tool: bool,
|
||||
pub(crate) include_apply_patch_tool: bool,
|
||||
pub(crate) include_web_search_request: bool,
|
||||
pub(crate) use_streamable_shell_tool: bool,
|
||||
pub(crate) include_view_image_tool: bool,
|
||||
}
|
||||
|
||||
impl ToolsConfig {
|
||||
pub fn new(
|
||||
model_family: &ModelFamily,
|
||||
approval_policy: AskForApproval,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
include_plan_tool: bool,
|
||||
include_apply_patch_tool: bool,
|
||||
include_web_search_request: bool,
|
||||
use_streamable_shell_tool: bool,
|
||||
) -> Self {
|
||||
let mut shell_type = if use_streamable_shell_tool {
|
||||
pub fn new(params: &ToolsConfigParams) -> Self {
|
||||
let ToolsConfigParams {
|
||||
model_family,
|
||||
approval_policy,
|
||||
sandbox_policy,
|
||||
include_plan_tool,
|
||||
include_apply_patch_tool,
|
||||
include_web_search_request,
|
||||
use_streamable_shell_tool,
|
||||
include_view_image_tool,
|
||||
} = params;
|
||||
let mut shell_type = if *use_streamable_shell_tool {
|
||||
ConfigShellToolType::StreamableShell
|
||||
} else if model_family.uses_local_shell_tool {
|
||||
ConfigShellToolType::LocalShell
|
||||
@@ -96,7 +112,7 @@ impl ToolsConfig {
|
||||
Some(ApplyPatchToolType::Freeform) => Some(ApplyPatchToolType::Freeform),
|
||||
Some(ApplyPatchToolType::Function) => Some(ApplyPatchToolType::Function),
|
||||
None => {
|
||||
if include_apply_patch_tool {
|
||||
if *include_apply_patch_tool {
|
||||
Some(ApplyPatchToolType::Freeform)
|
||||
} else {
|
||||
None
|
||||
@@ -106,9 +122,10 @@ impl ToolsConfig {
|
||||
|
||||
Self {
|
||||
shell_type,
|
||||
plan_tool: include_plan_tool,
|
||||
plan_tool: *include_plan_tool,
|
||||
apply_patch_tool_type,
|
||||
web_search_request: include_web_search_request,
|
||||
web_search_request: *include_web_search_request,
|
||||
include_view_image_tool: *include_view_image_tool,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -281,6 +298,30 @@ The shell tool is used to execute shell commands.
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
fn create_view_image_tool() -> OpenAiTool {
|
||||
// Support only local filesystem path.
|
||||
let mut properties = BTreeMap::new();
|
||||
properties.insert(
|
||||
"path".to_string(),
|
||||
JsonSchema::String {
|
||||
description: Some("Local filesystem path to an image file".to_string()),
|
||||
},
|
||||
);
|
||||
|
||||
OpenAiTool::Function(ResponsesApiTool {
|
||||
name: "view_image".to_string(),
|
||||
description:
|
||||
"Attach a local image (by filesystem path) to the conversation context for this turn."
|
||||
.to_string(),
|
||||
strict: false,
|
||||
parameters: JsonSchema::Object {
|
||||
properties,
|
||||
required: Some(vec!["path".to_string()]),
|
||||
additional_properties: Some(false),
|
||||
},
|
||||
})
|
||||
}
|
||||
/// TODO(dylan): deprecate once we get rid of json tool
|
||||
#[derive(Serialize, Deserialize)]
|
||||
pub(crate) struct ApplyPatchToolArgs {
|
||||
@@ -296,12 +337,12 @@ pub fn create_tools_json_for_responses_api(
|
||||
let mut tools_json = Vec::new();
|
||||
|
||||
for tool in tools {
|
||||
tools_json.push(serde_json::to_value(tool)?);
|
||||
let json = serde_json::to_value(tool)?;
|
||||
tools_json.push(json);
|
||||
}
|
||||
|
||||
Ok(tools_json)
|
||||
}
|
||||
|
||||
/// Returns JSON values that are compatible with Function Calling in the
|
||||
/// Chat Completions API:
|
||||
/// https://platform.openai.com/docs/guides/function-calling?api-mode=chat
|
||||
@@ -530,8 +571,18 @@ pub(crate) fn get_openai_tools(
|
||||
tools.push(OpenAiTool::WebSearch {});
|
||||
}
|
||||
|
||||
// Include the view_image tool so the agent can attach images to context.
|
||||
if config.include_view_image_tool {
|
||||
tools.push(create_view_image_tool());
|
||||
}
|
||||
|
||||
if let Some(mcp_tools) = mcp_tools {
|
||||
for (name, tool) in mcp_tools {
|
||||
// Ensure deterministic ordering to maximize prompt cache hits.
|
||||
// HashMap iteration order is non-deterministic, so sort by fully-qualified tool name.
|
||||
let mut entries: Vec<(String, mcp_types::Tool)> = mcp_tools.into_iter().collect();
|
||||
entries.sort_by(|a, b| a.0.cmp(&b.0));
|
||||
|
||||
for (name, tool) in entries.into_iter() {
|
||||
match mcp_tool_to_openai_tool(name.clone(), tool.clone()) {
|
||||
Ok(converted_tool) => tools.push(OpenAiTool::Function(converted_tool)),
|
||||
Err(e) => {
|
||||
@@ -580,49 +631,58 @@ mod tests {
|
||||
fn test_get_openai_tools() {
|
||||
let model_family = find_family_for_model("codex-mini-latest")
|
||||
.expect("codex-mini-latest should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
true,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: true,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
let tools = get_openai_tools(&config, Some(HashMap::new()));
|
||||
|
||||
assert_eq_tool_names(&tools, &["local_shell", "update_plan", "web_search"]);
|
||||
assert_eq_tool_names(
|
||||
&tools,
|
||||
&["local_shell", "update_plan", "web_search", "view_image"],
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_get_openai_tools_default_shell() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
true,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: true,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
let tools = get_openai_tools(&config, Some(HashMap::new()));
|
||||
|
||||
assert_eq_tool_names(&tools, &["shell", "update_plan", "web_search"]);
|
||||
assert_eq_tool_names(
|
||||
&tools,
|
||||
&["shell", "update_plan", "web_search", "view_image"],
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_get_openai_tools_mcp_tools() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
false,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: false,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
let tools = get_openai_tools(
|
||||
&config,
|
||||
Some(HashMap::from([(
|
||||
@@ -644,8 +704,8 @@ mod tests {
|
||||
"number_property": { "type": "number" },
|
||||
},
|
||||
"required": [
|
||||
"string_property".to_string(),
|
||||
"number_property".to_string()
|
||||
"string_property",
|
||||
"number_property",
|
||||
],
|
||||
"additionalProperties": Some(false),
|
||||
},
|
||||
@@ -663,11 +723,16 @@ mod tests {
|
||||
|
||||
assert_eq_tool_names(
|
||||
&tools,
|
||||
&["shell", "web_search", "test_server/do_something_cool"],
|
||||
&[
|
||||
"shell",
|
||||
"web_search",
|
||||
"view_image",
|
||||
"test_server/do_something_cool",
|
||||
],
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
tools[2],
|
||||
tools[3],
|
||||
OpenAiTool::Function(ResponsesApiTool {
|
||||
name: "test_server/do_something_cool".to_string(),
|
||||
parameters: JsonSchema::Object {
|
||||
@@ -710,18 +775,96 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_get_openai_tools_mcp_tools_sorted_by_name() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: false,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: false,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
|
||||
// Intentionally construct a map with keys that would sort alphabetically.
|
||||
let tools_map: HashMap<String, mcp_types::Tool> = HashMap::from([
|
||||
(
|
||||
"test_server/do".to_string(),
|
||||
mcp_types::Tool {
|
||||
name: "a".to_string(),
|
||||
input_schema: ToolInputSchema {
|
||||
properties: Some(serde_json::json!({})),
|
||||
required: None,
|
||||
r#type: "object".to_string(),
|
||||
},
|
||||
output_schema: None,
|
||||
title: None,
|
||||
annotations: None,
|
||||
description: Some("a".to_string()),
|
||||
},
|
||||
),
|
||||
(
|
||||
"test_server/something".to_string(),
|
||||
mcp_types::Tool {
|
||||
name: "b".to_string(),
|
||||
input_schema: ToolInputSchema {
|
||||
properties: Some(serde_json::json!({})),
|
||||
required: None,
|
||||
r#type: "object".to_string(),
|
||||
},
|
||||
output_schema: None,
|
||||
title: None,
|
||||
annotations: None,
|
||||
description: Some("b".to_string()),
|
||||
},
|
||||
),
|
||||
(
|
||||
"test_server/cool".to_string(),
|
||||
mcp_types::Tool {
|
||||
name: "c".to_string(),
|
||||
input_schema: ToolInputSchema {
|
||||
properties: Some(serde_json::json!({})),
|
||||
required: None,
|
||||
r#type: "object".to_string(),
|
||||
},
|
||||
output_schema: None,
|
||||
title: None,
|
||||
annotations: None,
|
||||
description: Some("c".to_string()),
|
||||
},
|
||||
),
|
||||
]);
|
||||
|
||||
let tools = get_openai_tools(&config, Some(tools_map));
|
||||
// Expect shell first, followed by MCP tools sorted by fully-qualified name.
|
||||
assert_eq_tool_names(
|
||||
&tools,
|
||||
&[
|
||||
"shell",
|
||||
"view_image",
|
||||
"test_server/cool",
|
||||
"test_server/do",
|
||||
"test_server/something",
|
||||
],
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_mcp_tool_property_missing_type_defaults_to_string() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
false,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: false,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
|
||||
let tools = get_openai_tools(
|
||||
&config,
|
||||
@@ -746,10 +889,13 @@ mod tests {
|
||||
)])),
|
||||
);
|
||||
|
||||
assert_eq_tool_names(&tools, &["shell", "web_search", "dash/search"]);
|
||||
assert_eq_tool_names(
|
||||
&tools,
|
||||
&["shell", "web_search", "view_image", "dash/search"],
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
tools[2],
|
||||
tools[3],
|
||||
OpenAiTool::Function(ResponsesApiTool {
|
||||
name: "dash/search".to_string(),
|
||||
parameters: JsonSchema::Object {
|
||||
@@ -771,15 +917,16 @@ mod tests {
|
||||
#[test]
|
||||
fn test_mcp_tool_integer_normalized_to_number() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
false,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: false,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
|
||||
let tools = get_openai_tools(
|
||||
&config,
|
||||
@@ -802,9 +949,12 @@ mod tests {
|
||||
)])),
|
||||
);
|
||||
|
||||
assert_eq_tool_names(&tools, &["shell", "web_search", "dash/paginate"]);
|
||||
assert_eq_tool_names(
|
||||
&tools,
|
||||
&["shell", "web_search", "view_image", "dash/paginate"],
|
||||
);
|
||||
assert_eq!(
|
||||
tools[2],
|
||||
tools[3],
|
||||
OpenAiTool::Function(ResponsesApiTool {
|
||||
name: "dash/paginate".to_string(),
|
||||
parameters: JsonSchema::Object {
|
||||
@@ -824,15 +974,16 @@ mod tests {
|
||||
#[test]
|
||||
fn test_mcp_tool_array_without_items_gets_default_string_items() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
false,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: false,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
|
||||
let tools = get_openai_tools(
|
||||
&config,
|
||||
@@ -855,9 +1006,9 @@ mod tests {
|
||||
)])),
|
||||
);
|
||||
|
||||
assert_eq_tool_names(&tools, &["shell", "web_search", "dash/tags"]);
|
||||
assert_eq_tool_names(&tools, &["shell", "web_search", "view_image", "dash/tags"]);
|
||||
assert_eq!(
|
||||
tools[2],
|
||||
tools[3],
|
||||
OpenAiTool::Function(ResponsesApiTool {
|
||||
name: "dash/tags".to_string(),
|
||||
parameters: JsonSchema::Object {
|
||||
@@ -880,15 +1031,16 @@ mod tests {
|
||||
#[test]
|
||||
fn test_mcp_tool_anyof_defaults_to_string() {
|
||||
let model_family = find_family_for_model("o3").expect("o3 should be a valid model family");
|
||||
let config = ToolsConfig::new(
|
||||
&model_family,
|
||||
AskForApproval::Never,
|
||||
SandboxPolicy::ReadOnly,
|
||||
false,
|
||||
false,
|
||||
true,
|
||||
/*use_experimental_streamable_shell_tool*/ false,
|
||||
);
|
||||
let config = ToolsConfig::new(&ToolsConfigParams {
|
||||
model_family: &model_family,
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::ReadOnly,
|
||||
include_plan_tool: false,
|
||||
include_apply_patch_tool: false,
|
||||
include_web_search_request: true,
|
||||
use_streamable_shell_tool: false,
|
||||
include_view_image_tool: true,
|
||||
});
|
||||
|
||||
let tools = get_openai_tools(
|
||||
&config,
|
||||
@@ -911,9 +1063,9 @@ mod tests {
|
||||
)])),
|
||||
);
|
||||
|
||||
assert_eq_tool_names(&tools, &["shell", "web_search", "dash/value"]);
|
||||
assert_eq_tool_names(&tools, &["shell", "web_search", "view_image", "dash/value"]);
|
||||
assert_eq!(
|
||||
tools[2],
|
||||
tools[3],
|
||||
OpenAiTool::Function(ResponsesApiTool {
|
||||
name: "dash/value".to_string(),
|
||||
parameters: JsonSchema::Object {
|
||||
|
||||
@@ -135,7 +135,7 @@ impl RolloutRecorder {
|
||||
| ResponseItem::CustomToolCall { .. }
|
||||
| ResponseItem::CustomToolCallOutput { .. }
|
||||
| ResponseItem::Reasoning { .. } => filtered.push(item.clone()),
|
||||
ResponseItem::Other => {
|
||||
ResponseItem::WebSearchCall { .. } | ResponseItem::Other => {
|
||||
// These should never be serialized.
|
||||
continue;
|
||||
}
|
||||
@@ -199,7 +199,7 @@ impl RolloutRecorder {
|
||||
| ResponseItem::CustomToolCall { .. }
|
||||
| ResponseItem::CustomToolCallOutput { .. }
|
||||
| ResponseItem::Reasoning { .. } => items.push(item),
|
||||
ResponseItem::Other => {}
|
||||
ResponseItem::WebSearchCall { .. } | ResponseItem::Other => {}
|
||||
},
|
||||
Err(e) => {
|
||||
warn!("failed to parse item: {v:?}, error: {e}");
|
||||
@@ -326,7 +326,7 @@ async fn rollout_writer(
|
||||
| ResponseItem::Reasoning { .. } => {
|
||||
writer.write_line(&item).await?;
|
||||
}
|
||||
ResponseItem::Other => {}
|
||||
ResponseItem::WebSearchCall { .. } | ResponseItem::Other => {}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -12,6 +12,7 @@ use codex_login::CodexAuth;
|
||||
use core_test_support::load_default_config_for_test;
|
||||
use core_test_support::load_sse_fixture_with_id;
|
||||
use core_test_support::wait_for_event;
|
||||
use serde_json::json;
|
||||
use tempfile::TempDir;
|
||||
use wiremock::Mock;
|
||||
use wiremock::MockServer;
|
||||
@@ -66,7 +67,6 @@ fn write_auth_json(
|
||||
account_id: Option<&str>,
|
||||
) -> String {
|
||||
use base64::Engine as _;
|
||||
use serde_json::json;
|
||||
|
||||
let header = json!({ "alg": "none", "typ": "JWT" });
|
||||
let payload = json!({
|
||||
@@ -418,7 +418,7 @@ async fn prefers_chatgpt_token_when_config_prefers_chatgpt() {
|
||||
match CodexAuth::from_codex_home(codex_home.path(), config.preferred_auth_method) {
|
||||
Ok(Some(auth)) => codex_login::AuthManager::from_auth_for_testing(auth),
|
||||
Ok(None) => panic!("No CodexAuth found in codex_home"),
|
||||
Err(e) => panic!("Failed to load CodexAuth: {}", e),
|
||||
Err(e) => panic!("Failed to load CodexAuth: {e}"),
|
||||
};
|
||||
let conversation_manager = ConversationManager::new(auth_manager);
|
||||
let NewConversation {
|
||||
@@ -499,7 +499,7 @@ async fn prefers_apikey_when_config_prefers_apikey_even_with_chatgpt_tokens() {
|
||||
match CodexAuth::from_codex_home(codex_home.path(), config.preferred_auth_method) {
|
||||
Ok(Some(auth)) => codex_login::AuthManager::from_auth_for_testing(auth),
|
||||
Ok(None) => panic!("No CodexAuth found in codex_home"),
|
||||
Err(e) => panic!("Failed to load CodexAuth: {}", e),
|
||||
Err(e) => panic!("Failed to load CodexAuth: {e}"),
|
||||
};
|
||||
let conversation_manager = ConversationManager::new(auth_manager);
|
||||
let NewConversation {
|
||||
@@ -746,3 +746,151 @@ async fn env_var_overrides_loaded_auth() {
|
||||
fn create_dummy_codex_auth() -> CodexAuth {
|
||||
CodexAuth::create_dummy_chatgpt_auth_for_testing()
|
||||
}
|
||||
|
||||
/// Scenario:
|
||||
/// - Turn 1: user sends U1; model streams deltas then a final assistant message A.
|
||||
/// - Turn 2: user sends U2; model streams a delta then the same final assistant message A.
|
||||
/// - Turn 3: user sends U3; model responds (same SSE again, not important).
|
||||
///
|
||||
/// We assert that the `input` sent on each turn contains the expected conversation history
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
async fn history_dedupes_streamed_and_final_messages_across_turns() {
|
||||
// Skip under Codex sandbox network restrictions (mirrors other tests).
|
||||
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
|
||||
println!(
|
||||
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
// Mock server that will receive three sequential requests and return the same SSE stream
|
||||
// each time: a few deltas, then a final assistant message, then completed.
|
||||
let server = MockServer::start().await;
|
||||
|
||||
// Build a small SSE stream with deltas and a final assistant message.
|
||||
// We emit the same body for all 3 turns; ids vary but are unused by assertions.
|
||||
let sse_raw = r##"[
|
||||
{"type":"response.output_text.delta", "delta":"Hey "},
|
||||
{"type":"response.output_text.delta", "delta":"there"},
|
||||
{"type":"response.output_text.delta", "delta":"!\n"},
|
||||
{"type":"response.output_item.done", "item":{
|
||||
"type":"message", "role":"assistant",
|
||||
"content":[{"type":"output_text","text":"Hey there!\n"}]
|
||||
}},
|
||||
{"type":"response.completed", "response": {"id": "__ID__"}}
|
||||
]"##;
|
||||
let sse1 = core_test_support::load_sse_fixture_with_id_from_str(sse_raw, "resp1");
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(
|
||||
ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(sse1.clone(), "text/event-stream"),
|
||||
)
|
||||
.expect(3) // respond identically to the three sequential turns
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
// Configure provider to point to mock server (Responses API) and use API key auth.
|
||||
let model_provider = ModelProviderInfo {
|
||||
base_url: Some(format!("{}/v1", server.uri())),
|
||||
..built_in_model_providers()["openai"].clone()
|
||||
};
|
||||
|
||||
// Init session with isolated codex home.
|
||||
let codex_home = TempDir::new().unwrap();
|
||||
let mut config = load_default_config_for_test(&codex_home);
|
||||
config.model_provider = model_provider;
|
||||
|
||||
let conversation_manager =
|
||||
ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
|
||||
let NewConversation {
|
||||
conversation: codex,
|
||||
..
|
||||
} = conversation_manager
|
||||
.new_conversation(config)
|
||||
.await
|
||||
.expect("create new conversation");
|
||||
|
||||
// Turn 1: user sends U1; wait for completion.
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text { text: "U1".into() }],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
// Turn 2: user sends U2; wait for completion.
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text { text: "U2".into() }],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
// Turn 3: user sends U3; wait for completion.
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text { text: "U3".into() }],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
// Inspect the three captured requests.
|
||||
let requests = server.received_requests().await.unwrap();
|
||||
assert_eq!(requests.len(), 3, "expected 3 requests (one per turn)");
|
||||
|
||||
// Replace full-array compare with tail-only raw JSON compare using a single hard-coded value.
|
||||
let r3_tail_expected = serde_json::json!([
|
||||
{
|
||||
"type": "message",
|
||||
"id": null,
|
||||
"role": "user",
|
||||
"content": [{"type":"input_text","text":"U1"}]
|
||||
},
|
||||
{
|
||||
"type": "message",
|
||||
"id": null,
|
||||
"role": "assistant",
|
||||
"content": [{"type":"output_text","text":"Hey there!\n"}]
|
||||
},
|
||||
{
|
||||
"type": "message",
|
||||
"id": null,
|
||||
"role": "user",
|
||||
"content": [{"type":"input_text","text":"U2"}]
|
||||
},
|
||||
{
|
||||
"type": "message",
|
||||
"id": null,
|
||||
"role": "assistant",
|
||||
"content": [{"type":"output_text","text":"Hey there!\n"}]
|
||||
},
|
||||
{
|
||||
"type": "message",
|
||||
"id": null,
|
||||
"role": "user",
|
||||
"content": [{"type":"input_text","text":"U3"}]
|
||||
}
|
||||
]);
|
||||
|
||||
let r3_input_array = requests[2]
|
||||
.body_json::<serde_json::Value>()
|
||||
.unwrap()
|
||||
.get("input")
|
||||
.and_then(|v| v.as_array())
|
||||
.cloned()
|
||||
.expect("r3 missing input array");
|
||||
// skipping earlier context and developer messages
|
||||
let tail_len = r3_tail_expected.as_array().unwrap().len();
|
||||
let actual_tail = &r3_input_array[r3_input_array.len() - tail_len..];
|
||||
assert_eq!(
|
||||
serde_json::Value::Array(actual_tail.to_vec()),
|
||||
r3_tail_expected,
|
||||
"request 3 tail mismatch",
|
||||
);
|
||||
}
|
||||
|
||||
@@ -191,7 +191,7 @@ async fn prompt_tools_are_consistent_across_requests() {
|
||||
let expected_instructions: &str = include_str!("../../prompt.md");
|
||||
// our internal implementation is responsible for keeping tools in sync
|
||||
// with the OpenAI schema, so we just verify the tool presence here
|
||||
let expected_tools_names: &[&str] = &["shell", "update_plan", "apply_patch"];
|
||||
let expected_tools_names: &[&str] = &["shell", "update_plan", "apply_patch", "view_image"];
|
||||
let body0 = requests[0].body_json::<serde_json::Value>().unwrap();
|
||||
assert_eq!(
|
||||
body0["instructions"],
|
||||
@@ -280,7 +280,7 @@ async fn prefixes_context_and_instructions_once_and_consistently_across_requests
|
||||
{}</environment_context>"#,
|
||||
cwd.path().to_string_lossy(),
|
||||
match shell.name() {
|
||||
Some(name) => format!(" <shell>{}</shell>\n", name),
|
||||
Some(name) => format!(" <shell>{name}</shell>\n"),
|
||||
None => String::new(),
|
||||
}
|
||||
);
|
||||
|
||||
@@ -25,6 +25,7 @@ use codex_core::protocol::TaskCompleteEvent;
|
||||
use codex_core::protocol::TurnAbortReason;
|
||||
use codex_core::protocol::TurnDiffEvent;
|
||||
use codex_core::protocol::WebSearchBeginEvent;
|
||||
use codex_core::protocol::WebSearchEndEvent;
|
||||
use owo_colors::OwoColorize;
|
||||
use owo_colors::Style;
|
||||
use shlex::try_join;
|
||||
@@ -179,7 +180,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
|
||||
EventMsg::StreamError(StreamErrorEvent { message }) => {
|
||||
ts_println!(self, "{}", message.style(self.dimmed));
|
||||
}
|
||||
EventMsg::TaskStarted => {
|
||||
EventMsg::TaskStarted(_) => {
|
||||
// Ignore.
|
||||
}
|
||||
EventMsg::TaskComplete(TaskCompleteEvent { last_agent_message }) => {
|
||||
@@ -362,8 +363,9 @@ impl EventProcessor for EventProcessorWithHumanOutput {
|
||||
}
|
||||
}
|
||||
}
|
||||
EventMsg::WebSearchBegin(WebSearchBeginEvent { call_id: _, query }) => {
|
||||
ts_println!(self, "🌐 {query}");
|
||||
EventMsg::WebSearchBegin(WebSearchBeginEvent { call_id: _ }) => {}
|
||||
EventMsg::WebSearchEnd(WebSearchEndEvent { call_id: _, query }) => {
|
||||
ts_println!(self, "🌐 Searched: {query}");
|
||||
}
|
||||
EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
|
||||
call_id,
|
||||
@@ -533,6 +535,9 @@ impl EventProcessor for EventProcessorWithHumanOutput {
|
||||
EventMsg::McpListToolsResponse(_) => {
|
||||
// Currently ignored in exec output.
|
||||
}
|
||||
EventMsg::ListCustomPromptsResponse(_) => {
|
||||
// Currently ignored in exec output.
|
||||
}
|
||||
EventMsg::TurnAborted(abort_reason) => match abort_reason.reason {
|
||||
TurnAbortReason::Interrupted => {
|
||||
ts_println!(self, "task interrupted");
|
||||
|
||||
@@ -148,6 +148,7 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
|
||||
base_instructions: None,
|
||||
include_plan_tool: None,
|
||||
include_apply_patch_tool: None,
|
||||
include_view_image_tool: None,
|
||||
disable_response_storage: oss.then_some(true),
|
||||
show_raw_agent_reasoning: oss.then_some(true),
|
||||
tools_web_search_request: None,
|
||||
|
||||
4
codex-rs/exec/tests/fixtures/apply_patch_freeform_final.txt
vendored
Normal file
4
codex-rs/exec/tests/fixtures/apply_patch_freeform_final.txt
vendored
Normal file
@@ -0,0 +1,4 @@
|
||||
class BaseClass:
|
||||
def method():
|
||||
|
||||
return True
|
||||
25
codex-rs/exec/tests/fixtures/sse_apply_patch_add.json
vendored
Normal file
25
codex-rs/exec/tests/fixtures/sse_apply_patch_add.json
vendored
Normal file
@@ -0,0 +1,25 @@
|
||||
[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "custom_tool_call",
|
||||
"name": "apply_patch",
|
||||
"input": "*** Begin Patch\n*** Add File: test.md\n+Hello world\n*** End Patch",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]
|
||||
25
codex-rs/exec/tests/fixtures/sse_apply_patch_freeform_add.json
vendored
Normal file
25
codex-rs/exec/tests/fixtures/sse_apply_patch_freeform_add.json
vendored
Normal file
@@ -0,0 +1,25 @@
|
||||
[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "custom_tool_call",
|
||||
"name": "apply_patch",
|
||||
"input": "*** Begin Patch\n*** Add File: app.py\n+class BaseClass:\n+ def method():\n+ return False\n*** End Patch",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]
|
||||
25
codex-rs/exec/tests/fixtures/sse_apply_patch_freeform_update.json
vendored
Normal file
25
codex-rs/exec/tests/fixtures/sse_apply_patch_freeform_update.json
vendored
Normal file
@@ -0,0 +1,25 @@
|
||||
[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "custom_tool_call",
|
||||
"name": "apply_patch",
|
||||
"input": "*** Begin Patch\n*** Update File: app.py\n@@ def method():\n- return False\n+\n+ return True\n*** End Patch",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]
|
||||
25
codex-rs/exec/tests/fixtures/sse_apply_patch_update.json
vendored
Normal file
25
codex-rs/exec/tests/fixtures/sse_apply_patch_update.json
vendored
Normal file
@@ -0,0 +1,25 @@
|
||||
[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "function_call",
|
||||
"name": "apply_patch",
|
||||
"arguments": "{\n \"input\": \"*** Begin Patch\\n*** Update File: test.md\\n@@\\n-Hello world\\n+Final text\\n*** End Patch\"\n}",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]
|
||||
16
codex-rs/exec/tests/fixtures/sse_response_completed.json
vendored
Normal file
16
codex-rs/exec/tests/fixtures/sse_response_completed.json
vendored
Normal file
@@ -0,0 +1,16 @@
|
||||
[
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -41,148 +41,31 @@ fn test_standalone_exec_cli_can_use_apply_patch() -> anyhow::Result<()> {
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
#[tokio::test]
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
|
||||
async fn test_apply_patch_tool() -> anyhow::Result<()> {
|
||||
use core_test_support::load_sse_fixture_with_id_from_str;
|
||||
use tempfile::TempDir;
|
||||
use wiremock::Mock;
|
||||
use wiremock::MockServer;
|
||||
use wiremock::ResponseTemplate;
|
||||
use wiremock::matchers::method;
|
||||
use wiremock::matchers::path;
|
||||
use crate::suite::common::run_e2e_exec_test;
|
||||
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
|
||||
|
||||
const SSE_TOOL_CALL_ADD: &str = r#"[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "function_call",
|
||||
"name": "apply_patch",
|
||||
"arguments": "{\n \"input\": \"*** Begin Patch\\n*** Add File: test.md\\n+Hello world\\n*** End Patch\"\n}",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]"#;
|
||||
|
||||
const SSE_TOOL_CALL_UPDATE: &str = r#"[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "function_call",
|
||||
"name": "apply_patch",
|
||||
"arguments": "{\n \"input\": \"*** Begin Patch\\n*** Update File: test.md\\n@@\\n-Hello world\\n+Final text\\n*** End Patch\"\n}",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]"#;
|
||||
|
||||
const SSE_TOOL_CALL_COMPLETED: &str = r#"[
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]"#;
|
||||
|
||||
// Start a mock model server
|
||||
let server = MockServer::start().await;
|
||||
|
||||
// First response: model calls apply_patch to create test.md
|
||||
let first = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_ADD, "call1"),
|
||||
"text/event-stream",
|
||||
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
|
||||
println!(
|
||||
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
|
||||
);
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
Mock::given(method("POST"))
|
||||
// .and(path("/v1/responses"))
|
||||
.respond_with(first)
|
||||
.up_to_n_times(1)
|
||||
.mount(&server)
|
||||
.await;
|
||||
let tmp_cwd = tempdir().expect("failed to create temp dir");
|
||||
let tmp_path = tmp_cwd.path().to_path_buf();
|
||||
run_e2e_exec_test(
|
||||
tmp_cwd.path(),
|
||||
vec![
|
||||
include_str!("../fixtures/sse_apply_patch_add.json").to_string(),
|
||||
include_str!("../fixtures/sse_apply_patch_update.json").to_string(),
|
||||
include_str!("../fixtures/sse_response_completed.json").to_string(),
|
||||
],
|
||||
)
|
||||
.await;
|
||||
|
||||
// Second response: model calls apply_patch to update test.md
|
||||
let second = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_UPDATE, "call2"),
|
||||
"text/event-stream",
|
||||
);
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(second)
|
||||
.up_to_n_times(1)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let final_completed = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_COMPLETED, "resp3"),
|
||||
"text/event-stream",
|
||||
);
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(final_completed)
|
||||
.expect(1)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let tmp_cwd = TempDir::new().unwrap();
|
||||
Command::cargo_bin("codex-exec")
|
||||
.context("should find binary for codex-exec")?
|
||||
.current_dir(tmp_cwd.path())
|
||||
.env("CODEX_HOME", tmp_cwd.path())
|
||||
.env("OPENAI_API_KEY", "dummy")
|
||||
.env("OPENAI_BASE_URL", format!("{}/v1", server.uri()))
|
||||
.arg("--skip-git-repo-check")
|
||||
.arg("-s")
|
||||
.arg("workspace-write")
|
||||
.arg("foo")
|
||||
.assert()
|
||||
.success();
|
||||
|
||||
// Verify final file contents
|
||||
let final_path = tmp_cwd.path().join("test.md");
|
||||
let final_path = tmp_path.join("test.md");
|
||||
let contents = std::fs::read_to_string(&final_path)
|
||||
.unwrap_or_else(|e| panic!("failed reading {}: {e}", final_path.display()));
|
||||
assert_eq!(contents, "Final text\n");
|
||||
@@ -190,150 +73,36 @@ async fn test_apply_patch_tool() -> anyhow::Result<()> {
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
#[tokio::test]
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
|
||||
async fn test_apply_patch_freeform_tool() -> anyhow::Result<()> {
|
||||
use core_test_support::load_sse_fixture_with_id_from_str;
|
||||
use tempfile::TempDir;
|
||||
use wiremock::Mock;
|
||||
use wiremock::MockServer;
|
||||
use wiremock::ResponseTemplate;
|
||||
use wiremock::matchers::method;
|
||||
use wiremock::matchers::path;
|
||||
use crate::suite::common::run_e2e_exec_test;
|
||||
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
|
||||
|
||||
const SSE_TOOL_CALL_ADD: &str = r#"[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "custom_tool_call",
|
||||
"name": "apply_patch",
|
||||
"input": "*** Begin Patch\n*** Add File: test.md\n+Hello world\n*** End Patch",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]"#;
|
||||
|
||||
const SSE_TOOL_CALL_UPDATE: &str = r#"[
|
||||
{
|
||||
"type": "response.output_item.done",
|
||||
"item": {
|
||||
"type": "custom_tool_call",
|
||||
"name": "apply_patch",
|
||||
"input": "*** Begin Patch\n*** Update File: test.md\n@@\n-Hello world\n+Final text\n*** End Patch",
|
||||
"call_id": "__ID__"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]"#;
|
||||
|
||||
const SSE_TOOL_CALL_COMPLETED: &str = r#"[
|
||||
{
|
||||
"type": "response.completed",
|
||||
"response": {
|
||||
"id": "__ID__",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"input_tokens_details": null,
|
||||
"output_tokens": 0,
|
||||
"output_tokens_details": null,
|
||||
"total_tokens": 0
|
||||
},
|
||||
"output": []
|
||||
}
|
||||
}
|
||||
]"#;
|
||||
|
||||
// Start a mock model server
|
||||
let server = MockServer::start().await;
|
||||
|
||||
// First response: model calls apply_patch to create test.md
|
||||
let first = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_ADD, "call1"),
|
||||
"text/event-stream",
|
||||
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
|
||||
println!(
|
||||
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
|
||||
);
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
Mock::given(method("POST"))
|
||||
// .and(path("/v1/responses"))
|
||||
.respond_with(first)
|
||||
.up_to_n_times(1)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
// Second response: model calls apply_patch to update test.md
|
||||
let second = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_UPDATE, "call2"),
|
||||
"text/event-stream",
|
||||
);
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(second)
|
||||
.up_to_n_times(1)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let final_completed = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_COMPLETED, "resp3"),
|
||||
"text/event-stream",
|
||||
);
|
||||
|
||||
Mock::given(method("POST"))
|
||||
// .and(path("/v1/responses"))
|
||||
.respond_with(final_completed)
|
||||
.expect(1)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let tmp_cwd = TempDir::new().unwrap();
|
||||
Command::cargo_bin("codex-exec")
|
||||
.context("should find binary for codex-exec")?
|
||||
.current_dir(tmp_cwd.path())
|
||||
.env("CODEX_HOME", tmp_cwd.path())
|
||||
.env("OPENAI_API_KEY", "dummy")
|
||||
.env("OPENAI_BASE_URL", format!("{}/v1", server.uri()))
|
||||
.arg("--skip-git-repo-check")
|
||||
.arg("-s")
|
||||
.arg("workspace-write")
|
||||
.arg("foo")
|
||||
.assert()
|
||||
.success();
|
||||
let tmp_cwd = tempdir().expect("failed to create temp dir");
|
||||
run_e2e_exec_test(
|
||||
tmp_cwd.path(),
|
||||
vec![
|
||||
include_str!("../fixtures/sse_apply_patch_freeform_add.json").to_string(),
|
||||
include_str!("../fixtures/sse_apply_patch_freeform_update.json").to_string(),
|
||||
include_str!("../fixtures/sse_response_completed.json").to_string(),
|
||||
],
|
||||
)
|
||||
.await;
|
||||
|
||||
// Verify final file contents
|
||||
let final_path = tmp_cwd.path().join("test.md");
|
||||
let final_path = tmp_cwd.path().join("app.py");
|
||||
let contents = std::fs::read_to_string(&final_path)
|
||||
.unwrap_or_else(|e| panic!("failed reading {}: {e}", final_path.display()));
|
||||
assert_eq!(contents, "Final text\n");
|
||||
assert_eq!(
|
||||
contents,
|
||||
include_str!("../fixtures/apply_patch_freeform_final.txt")
|
||||
);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
73
codex-rs/exec/tests/suite/common.rs
Normal file
73
codex-rs/exec/tests/suite/common.rs
Normal file
@@ -0,0 +1,73 @@
|
||||
// this file is only used for e2e tests which are currently disabled on windows
|
||||
#![cfg(not(target_os = "windows"))]
|
||||
#![allow(clippy::expect_used)]
|
||||
|
||||
use anyhow::Context;
|
||||
use assert_cmd::prelude::*;
|
||||
use core_test_support::load_sse_fixture_with_id_from_str;
|
||||
use std::path::Path;
|
||||
use std::process::Command;
|
||||
use std::sync::atomic::AtomicUsize;
|
||||
use std::sync::atomic::Ordering;
|
||||
use wiremock::Mock;
|
||||
use wiremock::MockServer;
|
||||
use wiremock::matchers::method;
|
||||
use wiremock::matchers::path;
|
||||
|
||||
use wiremock::Respond;
|
||||
|
||||
struct SeqResponder {
|
||||
num_calls: AtomicUsize,
|
||||
responses: Vec<String>,
|
||||
}
|
||||
|
||||
impl Respond for SeqResponder {
|
||||
fn respond(&self, _: &wiremock::Request) -> wiremock::ResponseTemplate {
|
||||
let call_num = self.num_calls.fetch_add(1, Ordering::SeqCst);
|
||||
match self.responses.get(call_num) {
|
||||
Some(body) => wiremock::ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(
|
||||
load_sse_fixture_with_id_from_str(body, &format!("request_{call_num}")),
|
||||
"text/event-stream",
|
||||
),
|
||||
None => panic!("no response for {call_num}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Helper function to run an E2E test of a codex-exec call. Starts a wiremock
|
||||
/// server, and returns the response_streams in order for each api call. Runs
|
||||
/// the codex-exec command with the wiremock server as the model server.
|
||||
pub(crate) async fn run_e2e_exec_test(cwd: &Path, response_streams: Vec<String>) {
|
||||
let server = MockServer::start().await;
|
||||
|
||||
let num_calls = response_streams.len();
|
||||
let seq_responder = SeqResponder {
|
||||
num_calls: AtomicUsize::new(0),
|
||||
responses: response_streams,
|
||||
};
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(seq_responder)
|
||||
.expect(num_calls as u64)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let cwd = cwd.to_path_buf();
|
||||
let uri = server.uri();
|
||||
Command::cargo_bin("codex-exec")
|
||||
.context("should find binary for codex-exec")
|
||||
.expect("should find binary for codex-exec")
|
||||
.current_dir(cwd.clone())
|
||||
.env("CODEX_HOME", cwd.clone())
|
||||
.env("OPENAI_API_KEY", "dummy")
|
||||
.env("OPENAI_BASE_URL", format!("{uri}/v1"))
|
||||
.arg("--skip-git-repo-check")
|
||||
.arg("-s")
|
||||
.arg("danger-full-access")
|
||||
.arg("foo")
|
||||
.assert()
|
||||
.success();
|
||||
}
|
||||
@@ -1,3 +1,4 @@
|
||||
// Aggregates all former standalone integration tests as modules.
|
||||
mod apply_patch;
|
||||
mod common;
|
||||
mod sandbox;
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<title>Sign into Codex CLI</title>
|
||||
<title>Sign into Codex</title>
|
||||
<link rel="icon" href='data:image/svg+xml,%3Csvg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none" viewBox="0 0 32 32"%3E%3Cpath stroke="%23000" stroke-linecap="round" stroke-width="2.484" d="M22.356 19.797H17.17M9.662 12.29l1.979 3.576a.511.511 0 0 1-.005.504l-1.974 3.409M30.758 16c0 8.15-6.607 14.758-14.758 14.758-8.15 0-14.758-6.607-14.758-14.758C1.242 7.85 7.85 1.242 16 1.242c8.15 0 14.758 6.608 14.758 14.758Z"/%3E%3C/svg%3E' type="image/svg+xml">
|
||||
<style>
|
||||
.container {
|
||||
@@ -135,7 +135,7 @@
|
||||
<div class="logo">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none" viewBox="0 0 32 32"><path stroke="#000" stroke-linecap="round" stroke-width="2.484" d="M22.356 19.797H17.17M9.662 12.29l1.979 3.576a.511.511 0 0 1-.005.504l-1.974 3.409M30.758 16c0 8.15-6.607 14.758-14.758 14.758-8.15 0-14.758-6.607-14.758-14.758C1.242 7.85 7.85 1.242 16 1.242c8.15 0 14.758 6.608 14.758 14.758Z"></path></svg>
|
||||
</div>
|
||||
<div class="title">Signed in to Codex CLI</div>
|
||||
<div class="title">Signed in to Codex</div>
|
||||
</div>
|
||||
<div class="close-box" style="display: none;">
|
||||
<div class="setup-description">You may now close this page</div>
|
||||
|
||||
@@ -8,6 +8,8 @@ use codex_core::ConversationManager;
|
||||
use codex_core::NewConversation;
|
||||
use codex_core::config::Config;
|
||||
use codex_core::config::ConfigOverrides;
|
||||
use codex_core::config::ConfigToml;
|
||||
use codex_core::config::load_config_as_toml;
|
||||
use codex_core::git_info::git_diff_to_remote;
|
||||
use codex_core::protocol::ApplyPatchApprovalRequestEvent;
|
||||
use codex_core::protocol::Event;
|
||||
@@ -46,6 +48,7 @@ use codex_protocol::mcp_protocol::ConversationId;
|
||||
use codex_protocol::mcp_protocol::EXEC_COMMAND_APPROVAL_METHOD;
|
||||
use codex_protocol::mcp_protocol::ExecCommandApprovalParams;
|
||||
use codex_protocol::mcp_protocol::ExecCommandApprovalResponse;
|
||||
use codex_protocol::mcp_protocol::GetConfigTomlResponse;
|
||||
use codex_protocol::mcp_protocol::InputItem as WireInputItem;
|
||||
use codex_protocol::mcp_protocol::InterruptConversationParams;
|
||||
use codex_protocol::mcp_protocol::InterruptConversationResponse;
|
||||
@@ -146,6 +149,9 @@ impl CodexMessageProcessor {
|
||||
ClientRequest::GetAuthStatus { request_id, params } => {
|
||||
self.get_auth_status(request_id, params).await;
|
||||
}
|
||||
ClientRequest::GetConfigToml { request_id } => {
|
||||
self.get_config_toml(request_id).await;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -354,6 +360,62 @@ impl CodexMessageProcessor {
|
||||
self.outgoing.send_response(request_id, response).await;
|
||||
}
|
||||
|
||||
async fn get_config_toml(&self, request_id: RequestId) {
|
||||
let toml_value = match load_config_as_toml(&self.config.codex_home) {
|
||||
Ok(val) => val,
|
||||
Err(err) => {
|
||||
let error = JSONRPCErrorError {
|
||||
code: INTERNAL_ERROR_CODE,
|
||||
message: format!("failed to load config.toml: {err}"),
|
||||
data: None,
|
||||
};
|
||||
self.outgoing.send_error(request_id, error).await;
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
let cfg: ConfigToml = match toml_value.try_into() {
|
||||
Ok(cfg) => cfg,
|
||||
Err(err) => {
|
||||
let error = JSONRPCErrorError {
|
||||
code: INTERNAL_ERROR_CODE,
|
||||
message: format!("failed to parse config.toml: {err}"),
|
||||
data: None,
|
||||
};
|
||||
self.outgoing.send_error(request_id, error).await;
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
let profiles: HashMap<String, codex_protocol::config_types::ConfigProfile> = cfg
|
||||
.profiles
|
||||
.into_iter()
|
||||
.map(|(k, v)| {
|
||||
(
|
||||
k,
|
||||
// Define this explicitly here to avoid the need to
|
||||
// implement `From<codex_core::config_profile::ConfigProfile>`
|
||||
// for the `ConfigProfile` type and introduce a dependency on codex_core
|
||||
codex_protocol::config_types::ConfigProfile {
|
||||
model: v.model,
|
||||
approval_policy: v.approval_policy,
|
||||
model_reasoning_effort: v.model_reasoning_effort,
|
||||
},
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
|
||||
let response = GetConfigTomlResponse {
|
||||
approval_policy: cfg.approval_policy,
|
||||
sandbox_mode: cfg.sandbox_mode,
|
||||
model_reasoning_effort: cfg.model_reasoning_effort,
|
||||
profile: cfg.profile,
|
||||
profiles: Some(profiles),
|
||||
};
|
||||
|
||||
self.outgoing.send_response(request_id, response).await;
|
||||
}
|
||||
|
||||
async fn process_new_conversation(&self, request_id: RequestId, params: NewConversationParams) {
|
||||
let config = match derive_config_from_params(params, self.codex_linux_sandbox_exe.clone()) {
|
||||
Ok(config) => config,
|
||||
@@ -736,6 +798,7 @@ fn derive_config_from_params(
|
||||
base_instructions,
|
||||
include_plan_tool,
|
||||
include_apply_patch_tool,
|
||||
include_view_image_tool: None,
|
||||
disable_response_storage: None,
|
||||
show_raw_agent_reasoning: None,
|
||||
tools_web_search_request: None,
|
||||
|
||||
@@ -161,6 +161,7 @@ impl CodexToolCallParam {
|
||||
base_instructions,
|
||||
include_plan_tool,
|
||||
include_apply_patch_tool: None,
|
||||
include_view_image_tool: None,
|
||||
disable_response_storage: None,
|
||||
show_raw_agent_reasoning: None,
|
||||
tools_web_search_request: None,
|
||||
|
||||
@@ -257,13 +257,14 @@ async fn run_codex_tool_session_inner(
|
||||
}
|
||||
EventMsg::AgentReasoningRawContent(_)
|
||||
| EventMsg::AgentReasoningRawContentDelta(_)
|
||||
| EventMsg::TaskStarted
|
||||
| EventMsg::TaskStarted(_)
|
||||
| EventMsg::TokenCount(_)
|
||||
| EventMsg::AgentReasoning(_)
|
||||
| EventMsg::AgentReasoningSectionBreak(_)
|
||||
| EventMsg::McpToolCallBegin(_)
|
||||
| EventMsg::McpToolCallEnd(_)
|
||||
| EventMsg::McpListToolsResponse(_)
|
||||
| EventMsg::ListCustomPromptsResponse(_)
|
||||
| EventMsg::ExecCommandBegin(_)
|
||||
| EventMsg::ExecCommandOutputDelta(_)
|
||||
| EventMsg::ExecCommandEnd(_)
|
||||
@@ -273,6 +274,7 @@ async fn run_codex_tool_session_inner(
|
||||
| EventMsg::PatchApplyEnd(_)
|
||||
| EventMsg::TurnDiff(_)
|
||||
| EventMsg::WebSearchBegin(_)
|
||||
| EventMsg::WebSearchEnd(_)
|
||||
| EventMsg::GetHistoryEntryResponse(_)
|
||||
| EventMsg::PlanUpdate(_)
|
||||
| EventMsg::TurnAborted(_)
|
||||
|
||||
@@ -63,7 +63,6 @@ pub async fn run_main(
|
||||
|
||||
// Task: read from stdin, push to `incoming_tx`.
|
||||
let stdin_reader_handle = tokio::spawn({
|
||||
let incoming_tx = incoming_tx.clone();
|
||||
async move {
|
||||
let stdin = io::stdin();
|
||||
let reader = BufReader::new(stdin);
|
||||
|
||||
@@ -123,7 +123,7 @@ impl OutgoingMessageSender {
|
||||
}
|
||||
|
||||
pub(crate) async fn send_server_notification(&self, notification: ServerNotification) {
|
||||
let method = format!("codex/event/{}", notification);
|
||||
let method = format!("codex/event/{notification}");
|
||||
let params = match serde_json::to_value(¬ification) {
|
||||
Ok(serde_json::Value::Object(mut map)) => map.remove("data"),
|
||||
_ => None,
|
||||
|
||||
@@ -61,6 +61,7 @@ impl McpProcess {
|
||||
|
||||
cmd.stdin(Stdio::piped());
|
||||
cmd.stdout(Stdio::piped());
|
||||
cmd.stderr(Stdio::piped());
|
||||
cmd.env("CODEX_HOME", codex_home);
|
||||
cmd.env("RUST_LOG", "debug");
|
||||
|
||||
@@ -77,6 +78,17 @@ impl McpProcess {
|
||||
.take()
|
||||
.ok_or_else(|| anyhow::format_err!("mcp should have stdout fd"))?;
|
||||
let stdout = BufReader::new(stdout);
|
||||
|
||||
// Forward child's stderr to our stderr so failures are visible even
|
||||
// when stdout/stderr are captured by the test harness.
|
||||
if let Some(stderr) = process.stderr.take() {
|
||||
let mut stderr_reader = BufReader::new(stderr).lines();
|
||||
tokio::spawn(async move {
|
||||
while let Ok(Some(line)) = stderr_reader.next_line().await {
|
||||
eprintln!("[mcp stderr] {line}");
|
||||
}
|
||||
});
|
||||
}
|
||||
Ok(Self {
|
||||
next_request_id: AtomicI64::new(0),
|
||||
process,
|
||||
@@ -228,6 +240,11 @@ impl McpProcess {
|
||||
self.send_request("getAuthStatus", params).await
|
||||
}
|
||||
|
||||
/// Send a `getConfigToml` JSON-RPC request.
|
||||
pub async fn send_get_config_toml_request(&mut self) -> anyhow::Result<i64> {
|
||||
self.send_request("getConfigToml", None).await
|
||||
}
|
||||
|
||||
/// Send a `loginChatGpt` JSON-RPC request.
|
||||
pub async fn send_login_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
|
||||
self.send_request("loginChatGpt", None).await
|
||||
@@ -278,6 +295,7 @@ impl McpProcess {
|
||||
}
|
||||
|
||||
async fn send_jsonrpc_message(&mut self, message: JSONRPCMessage) -> anyhow::Result<()> {
|
||||
eprintln!("writing message to stdin: {message:?}");
|
||||
let payload = serde_json::to_string(&message)?;
|
||||
self.stdin.write_all(payload.as_bytes()).await?;
|
||||
self.stdin.write_all(b"\n").await?;
|
||||
@@ -289,13 +307,15 @@ impl McpProcess {
|
||||
let mut line = String::new();
|
||||
self.stdout.read_line(&mut line).await?;
|
||||
let message = serde_json::from_str::<JSONRPCMessage>(&line)?;
|
||||
eprintln!("read message from stdout: {message:?}");
|
||||
Ok(message)
|
||||
}
|
||||
|
||||
pub async fn read_stream_until_request_message(&mut self) -> anyhow::Result<JSONRPCRequest> {
|
||||
eprintln!("in read_stream_until_request_message()");
|
||||
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
eprint!("message: {message:?}");
|
||||
|
||||
match message {
|
||||
JSONRPCMessage::Notification(_) => {
|
||||
@@ -318,10 +338,10 @@ impl McpProcess {
|
||||
&mut self,
|
||||
request_id: RequestId,
|
||||
) -> anyhow::Result<JSONRPCResponse> {
|
||||
eprintln!("in read_stream_until_response_message({request_id:?})");
|
||||
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
eprint!("message: {message:?}");
|
||||
|
||||
match message {
|
||||
JSONRPCMessage::Notification(_) => {
|
||||
eprintln!("notification: {message:?}");
|
||||
@@ -347,8 +367,6 @@ impl McpProcess {
|
||||
) -> anyhow::Result<mcp_types::JSONRPCError> {
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
eprint!("message: {message:?}");
|
||||
|
||||
match message {
|
||||
JSONRPCMessage::Notification(_) => {
|
||||
eprintln!("notification: {message:?}");
|
||||
@@ -372,10 +390,10 @@ impl McpProcess {
|
||||
&mut self,
|
||||
method: &str,
|
||||
) -> anyhow::Result<JSONRPCNotification> {
|
||||
eprintln!("in read_stream_until_notification_message({method})");
|
||||
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
eprint!("message: {message:?}");
|
||||
|
||||
match message {
|
||||
JSONRPCMessage::Notification(notification) => {
|
||||
if notification.method == method {
|
||||
@@ -400,10 +418,10 @@ impl McpProcess {
|
||||
pub async fn read_stream_until_legacy_task_complete_notification(
|
||||
&mut self,
|
||||
) -> anyhow::Result<JSONRPCNotification> {
|
||||
eprintln!("in read_stream_until_legacy_task_complete_notification()");
|
||||
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
eprint!("message: {message:?}");
|
||||
|
||||
match message {
|
||||
JSONRPCMessage::Notification(notification) => {
|
||||
let is_match = if notification.method == "codex/event" {
|
||||
@@ -422,6 +440,8 @@ impl McpProcess {
|
||||
|
||||
if is_match {
|
||||
return Ok(notification);
|
||||
} else {
|
||||
eprintln!("ignoring notification: {notification:?}");
|
||||
}
|
||||
}
|
||||
JSONRPCMessage::Request(_) => {
|
||||
|
||||
@@ -30,7 +30,8 @@ use mcp_test_support::create_final_assistant_message_sse_response;
|
||||
use mcp_test_support::create_mock_chat_completions_server;
|
||||
use mcp_test_support::create_shell_sse_response;
|
||||
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
// Allow ample time on slower CI or under load to avoid flakes.
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(20);
|
||||
|
||||
/// Test that a shell command that is not on the "trusted" list triggers an
|
||||
/// elicitation request to the MCP and that sending the approval runs the
|
||||
@@ -52,9 +53,22 @@ async fn test_shell_command_approval_triggers_elicitation() {
|
||||
}
|
||||
|
||||
async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
|
||||
// We use `git init` because it will not be on the "trusted" list.
|
||||
let shell_command = vec!["git".to_string(), "init".to_string()];
|
||||
// Use a simple, untrusted command that creates a file so we can
|
||||
// observe a side-effect.
|
||||
//
|
||||
// Cross‑platform approach: run a tiny Python snippet to touch the file
|
||||
// using `python3 -c ...` on all platforms.
|
||||
let workdir_for_shell_function_call = TempDir::new()?;
|
||||
let created_filename = "created_by_shell_tool.txt";
|
||||
let created_file = workdir_for_shell_function_call
|
||||
.path()
|
||||
.join(created_filename);
|
||||
|
||||
let shell_command = vec![
|
||||
"python3".to_string(),
|
||||
"-c".to_string(),
|
||||
format!("import pathlib; pathlib.Path('{created_filename}').touch()"),
|
||||
];
|
||||
|
||||
let McpHandle {
|
||||
process: mut mcp_process,
|
||||
@@ -67,7 +81,7 @@ async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
|
||||
Some(5_000),
|
||||
"call1234",
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("Enjoy your new git repo!")?,
|
||||
create_final_assistant_message_sse_response("File created!")?,
|
||||
])
|
||||
.await?;
|
||||
|
||||
@@ -122,8 +136,7 @@ async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
|
||||
.expect("task_complete_notification timeout")
|
||||
.expect("task_complete_notification resp");
|
||||
|
||||
// Verify the original `codex` tool call completes and that `git init` ran
|
||||
// successfully.
|
||||
// Verify the original `codex` tool call completes and that the file was created.
|
||||
let codex_response = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
|
||||
@@ -136,7 +149,7 @@ async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
|
||||
result: json!({
|
||||
"content": [
|
||||
{
|
||||
"text": "Enjoy your new git repo!",
|
||||
"text": "File created!",
|
||||
"type": "text"
|
||||
}
|
||||
]
|
||||
@@ -145,10 +158,7 @@ async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
|
||||
codex_response
|
||||
);
|
||||
|
||||
assert!(
|
||||
workdir_for_shell_function_call.path().join(".git").is_dir(),
|
||||
".git folder should have been created"
|
||||
);
|
||||
assert!(created_file.is_file(), "created file should exist");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
80
codex-rs/mcp-server/tests/suite/config.rs
Normal file
80
codex-rs/mcp-server/tests/suite/config.rs
Normal file
@@ -0,0 +1,80 @@
|
||||
use std::collections::HashMap;
|
||||
use std::path::Path;
|
||||
|
||||
use codex_core::protocol::AskForApproval;
|
||||
use codex_protocol::config_types::ConfigProfile;
|
||||
use codex_protocol::config_types::ReasoningEffort;
|
||||
use codex_protocol::config_types::SandboxMode;
|
||||
use codex_protocol::mcp_protocol::GetConfigTomlResponse;
|
||||
use mcp_test_support::McpProcess;
|
||||
use mcp_test_support::to_response;
|
||||
use mcp_types::JSONRPCResponse;
|
||||
use mcp_types::RequestId;
|
||||
use pretty_assertions::assert_eq;
|
||||
use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
|
||||
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
|
||||
let config_toml = codex_home.join("config.toml");
|
||||
std::fs::write(
|
||||
config_toml,
|
||||
r#"
|
||||
approval_policy = "on-request"
|
||||
sandbox_mode = "workspace-write"
|
||||
model_reasoning_effort = "high"
|
||||
profile = "test"
|
||||
|
||||
[profiles.test]
|
||||
model = "gpt-4o"
|
||||
approval_policy = "on-request"
|
||||
model_reasoning_effort = "high"
|
||||
model_reasoning_summary = "detailed"
|
||||
"#,
|
||||
)
|
||||
}
|
||||
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
async fn get_config_toml_returns_subset() {
|
||||
let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
|
||||
create_config_toml(codex_home.path()).expect("write config.toml");
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.path())
|
||||
.await
|
||||
.expect("spawn mcp process");
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
|
||||
.await
|
||||
.expect("init timeout")
|
||||
.expect("init failed");
|
||||
|
||||
let request_id = mcp
|
||||
.send_get_config_toml_request()
|
||||
.await
|
||||
.expect("send getConfigToml");
|
||||
let resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
|
||||
)
|
||||
.await
|
||||
.expect("getConfigToml timeout")
|
||||
.expect("getConfigToml response");
|
||||
|
||||
let config: GetConfigTomlResponse = to_response(resp).expect("deserialize config");
|
||||
let expected = GetConfigTomlResponse {
|
||||
approval_policy: Some(AskForApproval::OnRequest),
|
||||
sandbox_mode: Some(SandboxMode::WorkspaceWrite),
|
||||
model_reasoning_effort: Some(ReasoningEffort::High),
|
||||
profile: Some("test".to_string()),
|
||||
profiles: Some(HashMap::from([(
|
||||
"test".into(),
|
||||
ConfigProfile {
|
||||
model: Some("gpt-4o".into()),
|
||||
approval_policy: Some(AskForApproval::OnRequest),
|
||||
model_reasoning_effort: Some(ReasoningEffort::High),
|
||||
},
|
||||
)])),
|
||||
};
|
||||
|
||||
assert_eq!(expected, config);
|
||||
}
|
||||
@@ -2,6 +2,7 @@
|
||||
mod auth;
|
||||
mod codex_message_processor_flow;
|
||||
mod codex_tool;
|
||||
mod config;
|
||||
mod create_conversation;
|
||||
mod interrupt;
|
||||
mod login;
|
||||
|
||||
@@ -48,6 +48,8 @@ pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
|
||||
codex_protocol::mcp_protocol::ExecCommandApprovalResponse::export_all_to(out_dir)?;
|
||||
codex_protocol::mcp_protocol::ServerNotification::export_all_to(out_dir)?;
|
||||
|
||||
generate_index_ts(out_dir)?;
|
||||
|
||||
// Prepend header to each generated .ts file
|
||||
let ts_files = ts_files_in(out_dir)?;
|
||||
for file in &ts_files {
|
||||
@@ -109,5 +111,39 @@ fn ts_files_in(dir: &Path) -> Result<Vec<PathBuf>> {
|
||||
files.push(path);
|
||||
}
|
||||
}
|
||||
files.sort();
|
||||
Ok(files)
|
||||
}
|
||||
|
||||
/// Generate an index.ts file that re-exports all generated types.
|
||||
/// This allows consumers to import all types from a single file.
|
||||
fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
|
||||
let mut entries: Vec<String> = Vec::new();
|
||||
let mut stems: Vec<String> = ts_files_in(out_dir)?
|
||||
.into_iter()
|
||||
.filter_map(|p| {
|
||||
let stem = p.file_stem()?.to_string_lossy().into_owned();
|
||||
if stem == "index" { None } else { Some(stem) }
|
||||
})
|
||||
.collect();
|
||||
stems.sort();
|
||||
stems.dedup();
|
||||
|
||||
for name in stems {
|
||||
entries.push(format!("export type {{ {name} }} from \"./{name}\";\n"));
|
||||
}
|
||||
|
||||
let mut content =
|
||||
String::with_capacity(HEADER.len() + entries.iter().map(|s| s.len()).sum::<usize>());
|
||||
content.push_str(HEADER);
|
||||
for line in &entries {
|
||||
content.push_str(line);
|
||||
}
|
||||
|
||||
let index_path = out_dir.join("index.ts");
|
||||
let mut f = fs::File::create(&index_path)
|
||||
.with_context(|| format!("Failed to create {}", index_path.display()))?;
|
||||
f.write_all(content.as_bytes())
|
||||
.with_context(|| format!("Failed to write {}", index_path.display()))?;
|
||||
Ok(index_path)
|
||||
}
|
||||
|
||||
@@ -4,6 +4,8 @@ use strum_macros::Display;
|
||||
use strum_macros::EnumIter;
|
||||
use ts_rs::TS;
|
||||
|
||||
use crate::protocol::AskForApproval;
|
||||
|
||||
/// See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning
|
||||
#[derive(
|
||||
Debug, Serialize, Deserialize, Default, Clone, Copy, PartialEq, Eq, Display, TS, EnumIter,
|
||||
@@ -47,3 +49,13 @@ pub enum SandboxMode {
|
||||
#[serde(rename = "danger-full-access")]
|
||||
DangerFullAccess,
|
||||
}
|
||||
|
||||
/// Collection of common configuration options that a user can define as a unit
|
||||
/// in `config.toml`. Currently only a subset of the fields are supported.
|
||||
#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ConfigProfile {
|
||||
pub model: Option<String>,
|
||||
pub approval_policy: Option<AskForApproval>,
|
||||
pub model_reasoning_effort: Option<ReasoningEffort>,
|
||||
}
|
||||
|
||||
10
codex-rs/protocol/src/custom_prompts.rs
Normal file
10
codex-rs/protocol/src/custom_prompts.rs
Normal file
@@ -0,0 +1,10 @@
|
||||
use serde::Deserialize;
|
||||
use serde::Serialize;
|
||||
use std::path::PathBuf;
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone)]
|
||||
pub struct CustomPrompt {
|
||||
pub name: String,
|
||||
pub path: PathBuf,
|
||||
pub content: String,
|
||||
}
|
||||
@@ -1,4 +1,5 @@
|
||||
pub mod config_types;
|
||||
pub mod custom_prompts;
|
||||
pub mod mcp_protocol;
|
||||
pub mod message_history;
|
||||
pub mod models;
|
||||
|
||||
@@ -2,6 +2,7 @@ use std::collections::HashMap;
|
||||
use std::fmt::Display;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::config_types::ConfigProfile;
|
||||
use crate::config_types::ReasoningEffort;
|
||||
use crate::config_types::ReasoningSummary;
|
||||
use crate::config_types::SandboxMode;
|
||||
@@ -101,6 +102,10 @@ pub enum ClientRequest {
|
||||
request_id: RequestId,
|
||||
params: GetAuthStatusParams,
|
||||
},
|
||||
GetConfigToml {
|
||||
#[serde(rename = "id")]
|
||||
request_id: RequestId,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
|
||||
@@ -223,6 +228,26 @@ pub struct GetAuthStatusResponse {
|
||||
pub auth_token: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct GetConfigTomlResponse {
|
||||
/// Approvals
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub approval_policy: Option<AskForApproval>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub sandbox_mode: Option<SandboxMode>,
|
||||
|
||||
/// Relevant model configuration
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub model_reasoning_effort: Option<ReasoningEffort>,
|
||||
|
||||
/// Profiles
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub profile: Option<String>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub profiles: Option<HashMap<String, ConfigProfile>>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct SendUserMessageParams {
|
||||
|
||||
@@ -95,6 +95,22 @@ pub enum ResponseItem {
|
||||
call_id: String,
|
||||
output: String,
|
||||
},
|
||||
// Emitted by the Responses API when the agent triggers a web search.
|
||||
// Example payload (from SSE `response.output_item.done`):
|
||||
// {
|
||||
// "id":"ws_...",
|
||||
// "type":"web_search_call",
|
||||
// "status":"completed",
|
||||
// "action": {"type":"search","query":"weather: San Francisco, CA"}
|
||||
// }
|
||||
WebSearchCall {
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
id: Option<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
status: Option<String>,
|
||||
action: WebSearchAction,
|
||||
},
|
||||
|
||||
#[serde(other)]
|
||||
Other,
|
||||
}
|
||||
@@ -162,6 +178,16 @@ pub struct LocalShellExecAction {
|
||||
pub user: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
|
||||
#[serde(tag = "type", rename_all = "snake_case")]
|
||||
pub enum WebSearchAction {
|
||||
Search {
|
||||
query: String,
|
||||
},
|
||||
#[serde(other)]
|
||||
Other,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
|
||||
#[serde(tag = "type", rename_all = "snake_case")]
|
||||
pub enum ReasoningItemReasoningSummary {
|
||||
|
||||
@@ -10,6 +10,7 @@ use std::path::PathBuf;
|
||||
use std::str::FromStr;
|
||||
use std::time::Duration;
|
||||
|
||||
use crate::custom_prompts::CustomPrompt;
|
||||
use mcp_types::CallToolResult;
|
||||
use mcp_types::Tool as McpTool;
|
||||
use serde::Deserialize;
|
||||
@@ -146,6 +147,9 @@ pub enum Op {
|
||||
/// Reply is delivered via `EventMsg::McpListToolsResponse`.
|
||||
ListMcpTools,
|
||||
|
||||
/// Request the list of available custom prompts.
|
||||
ListCustomPrompts,
|
||||
|
||||
/// Request the agent to summarize the current conversation context.
|
||||
/// The agent will use its existing context (either conversation history or previous response id)
|
||||
/// to generate a summary which will be returned as an AgentMessage event.
|
||||
@@ -401,7 +405,7 @@ pub enum EventMsg {
|
||||
Error(ErrorEvent),
|
||||
|
||||
/// Agent has started a task
|
||||
TaskStarted,
|
||||
TaskStarted(TaskStartedEvent),
|
||||
|
||||
/// Agent has completed all actions
|
||||
TaskComplete(TaskCompleteEvent),
|
||||
@@ -439,6 +443,8 @@ pub enum EventMsg {
|
||||
|
||||
WebSearchBegin(WebSearchBeginEvent),
|
||||
|
||||
WebSearchEnd(WebSearchEndEvent),
|
||||
|
||||
/// Notification that the server is about to execute a command.
|
||||
ExecCommandBegin(ExecCommandBeginEvent),
|
||||
|
||||
@@ -472,6 +478,9 @@ pub enum EventMsg {
|
||||
/// List of MCP tools available to the agent.
|
||||
McpListToolsResponse(McpListToolsResponseEvent),
|
||||
|
||||
/// List of custom prompts available to the agent.
|
||||
ListCustomPromptsResponse(ListCustomPromptsResponseEvent),
|
||||
|
||||
PlanUpdate(UpdatePlanArgs),
|
||||
|
||||
TurnAborted(TurnAbortedEvent),
|
||||
@@ -494,6 +503,11 @@ pub struct TaskCompleteEvent {
|
||||
pub last_agent_message: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Deserialize, Serialize)]
|
||||
pub struct TaskStartedEvent {
|
||||
pub model_context_window: Option<u64>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Deserialize, Serialize, Default)]
|
||||
pub struct TokenUsage {
|
||||
pub input_tokens: u64,
|
||||
@@ -663,6 +677,11 @@ impl McpToolCallEndEvent {
|
||||
#[derive(Debug, Clone, Deserialize, Serialize)]
|
||||
pub struct WebSearchBeginEvent {
|
||||
pub call_id: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Deserialize, Serialize)]
|
||||
pub struct WebSearchEndEvent {
|
||||
pub call_id: String,
|
||||
pub query: String,
|
||||
}
|
||||
|
||||
@@ -801,6 +820,12 @@ pub struct McpListToolsResponseEvent {
|
||||
pub tools: std::collections::HashMap<String, McpTool>,
|
||||
}
|
||||
|
||||
/// Response payload for `Op::ListCustomPrompts`.
|
||||
#[derive(Debug, Clone, Deserialize, Serialize)]
|
||||
pub struct ListCustomPromptsResponseEvent {
|
||||
pub custom_prompts: Vec<CustomPrompt>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Default, Clone, Deserialize, Serialize)]
|
||||
pub struct SessionConfiguredEvent {
|
||||
/// Unique id for this session.
|
||||
|
||||
@@ -40,7 +40,10 @@ codex-login = { path = "../login" }
|
||||
codex-ollama = { path = "../ollama" }
|
||||
codex-protocol = { path = "../protocol" }
|
||||
color-eyre = "0.6.3"
|
||||
crossterm = { version = "0.28.1", features = ["bracketed-paste", "event-stream"] }
|
||||
crossterm = { version = "0.28.1", features = [
|
||||
"bracketed-paste",
|
||||
"event-stream",
|
||||
] }
|
||||
diffy = "0.4.2"
|
||||
image = { version = "^0.25.6", default-features = false, features = [
|
||||
"jpeg",
|
||||
@@ -82,6 +85,7 @@ tui-input = "0.14.0"
|
||||
tui-markdown = "0.3.3"
|
||||
unicode-segmentation = "1.12.0"
|
||||
unicode-width = "0.1"
|
||||
url = "2"
|
||||
uuid = "1"
|
||||
|
||||
[target.'cfg(unix)'.dependencies]
|
||||
|
||||
@@ -3,7 +3,7 @@ use crate::app_event::AppEvent;
|
||||
use crate::app_event_sender::AppEventSender;
|
||||
use crate::chatwidget::ChatWidget;
|
||||
use crate::file_search::FileSearchManager;
|
||||
use crate::transcript_app::TranscriptApp;
|
||||
use crate::pager_overlay::Overlay;
|
||||
use crate::tui;
|
||||
use crate::tui::TuiEvent;
|
||||
use codex_ansi_escape::ansi_escape_line;
|
||||
@@ -40,8 +40,8 @@ pub(crate) struct App {
|
||||
|
||||
pub(crate) transcript_lines: Vec<Line<'static>>,
|
||||
|
||||
// Transcript overlay state
|
||||
pub(crate) transcript_overlay: Option<TranscriptApp>,
|
||||
// Pager overlay state (Transcript or Static like Diff)
|
||||
pub(crate) overlay: Option<Overlay>,
|
||||
pub(crate) deferred_history_lines: Vec<Line<'static>>,
|
||||
|
||||
pub(crate) enhanced_keys_supported: bool,
|
||||
@@ -89,7 +89,7 @@ impl App {
|
||||
file_search,
|
||||
enhanced_keys_supported,
|
||||
transcript_lines: Vec::new(),
|
||||
transcript_overlay: None,
|
||||
overlay: None,
|
||||
deferred_history_lines: Vec::new(),
|
||||
commit_anim_running: Arc::new(AtomicBool::new(false)),
|
||||
backtrack: BacktrackState::default(),
|
||||
@@ -117,7 +117,7 @@ impl App {
|
||||
tui: &mut tui::Tui,
|
||||
event: TuiEvent,
|
||||
) -> Result<bool> {
|
||||
if self.transcript_overlay.is_some() {
|
||||
if self.overlay.is_some() {
|
||||
let _ = self.handle_backtrack_overlay_event(tui, event).await?;
|
||||
} else {
|
||||
match event {
|
||||
@@ -133,6 +133,12 @@ impl App {
|
||||
self.chat_widget.handle_paste(pasted);
|
||||
}
|
||||
TuiEvent::Draw => {
|
||||
if self
|
||||
.chat_widget
|
||||
.handle_paste_burst_tick(tui.frame_requester())
|
||||
{
|
||||
return Ok(true);
|
||||
}
|
||||
tui.draw(
|
||||
self.chat_widget.desired_height(tui.terminal.size()?.width),
|
||||
|frame| {
|
||||
@@ -172,26 +178,27 @@ impl App {
|
||||
tui.frame_requester().schedule_frame();
|
||||
}
|
||||
AppEvent::InsertHistoryLines(lines) => {
|
||||
if let Some(overlay) = &mut self.transcript_overlay {
|
||||
overlay.insert_lines(lines.clone());
|
||||
if let Some(Overlay::Transcript(t)) = &mut self.overlay {
|
||||
t.insert_lines(lines.clone());
|
||||
tui.frame_requester().schedule_frame();
|
||||
}
|
||||
self.transcript_lines.extend(lines.clone());
|
||||
if self.transcript_overlay.is_some() {
|
||||
if self.overlay.is_some() {
|
||||
self.deferred_history_lines.extend(lines);
|
||||
} else {
|
||||
tui.insert_history_lines(lines);
|
||||
}
|
||||
}
|
||||
AppEvent::InsertHistoryCell(cell) => {
|
||||
if let Some(overlay) = &mut self.transcript_overlay {
|
||||
overlay.insert_lines(cell.transcript_lines());
|
||||
let cell_transcript = cell.transcript_lines();
|
||||
if let Some(Overlay::Transcript(t)) = &mut self.overlay {
|
||||
t.insert_lines(cell_transcript.clone());
|
||||
tui.frame_requester().schedule_frame();
|
||||
}
|
||||
self.transcript_lines.extend(cell.transcript_lines());
|
||||
self.transcript_lines.extend(cell_transcript.clone());
|
||||
let display = cell.display_lines();
|
||||
if !display.is_empty() {
|
||||
if self.transcript_overlay.is_some() {
|
||||
if self.overlay.is_some() {
|
||||
self.deferred_history_lines.extend(display);
|
||||
} else {
|
||||
tui.insert_history_lines(display);
|
||||
@@ -240,7 +247,7 @@ impl App {
|
||||
} else {
|
||||
text.lines().map(ansi_escape_line).collect()
|
||||
};
|
||||
self.transcript_overlay = Some(TranscriptApp::with_title(
|
||||
self.overlay = Some(Overlay::new_static_with_title(
|
||||
pager_lines,
|
||||
"D I F F".to_string(),
|
||||
));
|
||||
@@ -276,22 +283,6 @@ impl App {
|
||||
|
||||
async fn handle_key_event(&mut self, tui: &mut tui::Tui, key_event: KeyEvent) {
|
||||
match key_event {
|
||||
KeyEvent {
|
||||
code: KeyCode::Char('c'),
|
||||
modifiers: crossterm::event::KeyModifiers::CONTROL,
|
||||
kind: KeyEventKind::Press,
|
||||
..
|
||||
} => {
|
||||
self.chat_widget.on_ctrl_c();
|
||||
}
|
||||
KeyEvent {
|
||||
code: KeyCode::Char('d'),
|
||||
modifiers: crossterm::event::KeyModifiers::CONTROL,
|
||||
kind: KeyEventKind::Press,
|
||||
..
|
||||
} if self.chat_widget.composer_is_empty() => {
|
||||
self.app_event_tx.send(AppEvent::ExitRequest);
|
||||
}
|
||||
KeyEvent {
|
||||
code: KeyCode::Char('t'),
|
||||
modifiers: crossterm::event::KeyModifiers::CONTROL,
|
||||
@@ -300,16 +291,24 @@ impl App {
|
||||
} => {
|
||||
// Enter alternate screen and set viewport to full size.
|
||||
let _ = tui.enter_alt_screen();
|
||||
self.transcript_overlay = Some(TranscriptApp::new(self.transcript_lines.clone()));
|
||||
self.overlay = Some(Overlay::new_transcript(self.transcript_lines.clone()));
|
||||
tui.frame_requester().schedule_frame();
|
||||
}
|
||||
// Esc primes/advances backtracking when composer is empty.
|
||||
// Esc primes/advances backtracking only in normal (not working) mode
|
||||
// with an empty composer. In any other state, forward Esc so the
|
||||
// active UI (e.g. status indicator, modals, popups) handles it.
|
||||
KeyEvent {
|
||||
code: KeyCode::Esc,
|
||||
kind: KeyEventKind::Press | KeyEventKind::Repeat,
|
||||
..
|
||||
} => {
|
||||
self.handle_backtrack_esc_key(tui);
|
||||
if self.chat_widget.is_normal_backtrack_mode()
|
||||
&& self.chat_widget.composer_is_empty()
|
||||
{
|
||||
self.handle_backtrack_esc_key(tui);
|
||||
} else {
|
||||
self.chat_widget.handle_key_event(key_event);
|
||||
}
|
||||
}
|
||||
// Enter confirms backtrack when primed + count > 0. Otherwise pass to widget.
|
||||
KeyEvent {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use crate::app::App;
|
||||
use crate::backtrack_helpers;
|
||||
use crate::transcript_app::TranscriptApp;
|
||||
use crate::pager_overlay::Overlay;
|
||||
use crate::tui;
|
||||
use crate::tui::TuiEvent;
|
||||
use codex_core::protocol::ConversationHistoryResponseEvent;
|
||||
@@ -79,7 +79,7 @@ impl App {
|
||||
if self.chat_widget.composer_is_empty() {
|
||||
if !self.backtrack.primed {
|
||||
self.prime_backtrack();
|
||||
} else if self.transcript_overlay.is_none() {
|
||||
} else if self.overlay.is_none() {
|
||||
self.open_backtrack_preview(tui);
|
||||
} else if self.backtrack.overlay_preview_active {
|
||||
self.step_backtrack_and_highlight(tui);
|
||||
@@ -103,7 +103,7 @@ impl App {
|
||||
/// Open transcript overlay (enters alternate screen and shows full transcript).
|
||||
pub(crate) fn open_transcript_overlay(&mut self, tui: &mut tui::Tui) {
|
||||
let _ = tui.enter_alt_screen();
|
||||
self.transcript_overlay = Some(TranscriptApp::new(self.transcript_lines.clone()));
|
||||
self.overlay = Some(Overlay::new_transcript(self.transcript_lines.clone()));
|
||||
tui.frame_requester().schedule_frame();
|
||||
}
|
||||
|
||||
@@ -115,7 +115,7 @@ impl App {
|
||||
let lines = std::mem::take(&mut self.deferred_history_lines);
|
||||
tui.insert_history_lines(lines);
|
||||
}
|
||||
self.transcript_overlay = None;
|
||||
self.overlay = None;
|
||||
self.backtrack.overlay_preview_active = false;
|
||||
if was_backtrack {
|
||||
// Ensure backtrack state is fully reset when overlay closes (e.g. via 'q').
|
||||
@@ -193,23 +193,23 @@ impl App {
|
||||
) {
|
||||
let (nth, offset, hl) = selection;
|
||||
self.backtrack.count = nth;
|
||||
if let Some(overlay) = &mut self.transcript_overlay {
|
||||
if let Some(Overlay::Transcript(t)) = &mut self.overlay {
|
||||
if let Some(off) = offset {
|
||||
overlay.scroll_offset = off;
|
||||
t.set_scroll_offset(off);
|
||||
}
|
||||
overlay.set_highlight_range(hl);
|
||||
t.set_highlight_range(hl);
|
||||
}
|
||||
}
|
||||
|
||||
/// Forward any event to the overlay and close it if done.
|
||||
fn overlay_forward_event(&mut self, tui: &mut tui::Tui, event: TuiEvent) -> Result<()> {
|
||||
if let Some(overlay) = &mut self.transcript_overlay {
|
||||
if let Some(overlay) = &mut self.overlay {
|
||||
overlay.handle_event(tui, event)?;
|
||||
if overlay.is_done {
|
||||
if overlay.is_done() {
|
||||
self.close_transcript_overlay(tui);
|
||||
tui.frame_requester().schedule_frame();
|
||||
}
|
||||
}
|
||||
tui.frame_requester().schedule_frame();
|
||||
Ok(())
|
||||
}
|
||||
|
||||
|
||||
@@ -100,6 +100,7 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
assert_eq!(CancellationEvent::Handled, view.on_ctrl_c(&mut pane));
|
||||
assert!(view.queue.is_empty());
|
||||
|
||||
@@ -28,16 +28,6 @@ pub(crate) trait BottomPaneView {
|
||||
/// Render the view: this will be displayed in place of the composer.
|
||||
fn render(&self, area: Rect, buf: &mut Buffer);
|
||||
|
||||
/// Update the status indicator animated header. Default no-op.
|
||||
fn update_status_header(&mut self, _header: String) {
|
||||
// no-op
|
||||
}
|
||||
|
||||
/// Called when task completes to check if the view should be hidden.
|
||||
fn should_hide_when_task_is_done(&mut self) -> bool {
|
||||
false
|
||||
}
|
||||
|
||||
/// Try to handle approval request; return the original value if not
|
||||
/// consumed.
|
||||
fn try_consume_approval_request(
|
||||
@@ -46,8 +36,4 @@ pub(crate) trait BottomPaneView {
|
||||
) -> Option<ApprovalRequest> {
|
||||
Some(request)
|
||||
}
|
||||
|
||||
/// Optional hook for views that expose a live status line. Views that do not
|
||||
/// support this can ignore the call.
|
||||
fn update_status_text(&mut self, _text: String) {}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -9,22 +9,58 @@ use super::selection_popup_common::render_rows;
|
||||
use crate::slash_command::SlashCommand;
|
||||
use crate::slash_command::built_in_slash_commands;
|
||||
use codex_common::fuzzy_match::fuzzy_match;
|
||||
use codex_protocol::custom_prompts::CustomPrompt;
|
||||
use std::collections::HashSet;
|
||||
|
||||
/// A selectable item in the popup: either a built-in command or a user prompt.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
pub(crate) enum CommandItem {
|
||||
Builtin(SlashCommand),
|
||||
// Index into `prompts`
|
||||
UserPrompt(usize),
|
||||
}
|
||||
|
||||
pub(crate) struct CommandPopup {
|
||||
command_filter: String,
|
||||
all_commands: Vec<(&'static str, SlashCommand)>,
|
||||
builtins: Vec<(&'static str, SlashCommand)>,
|
||||
prompts: Vec<CustomPrompt>,
|
||||
state: ScrollState,
|
||||
}
|
||||
|
||||
impl CommandPopup {
|
||||
pub(crate) fn new() -> Self {
|
||||
pub(crate) fn new(mut prompts: Vec<CustomPrompt>) -> Self {
|
||||
let builtins = built_in_slash_commands();
|
||||
// Exclude prompts that collide with builtin command names and sort by name.
|
||||
let exclude: HashSet<String> = builtins.iter().map(|(n, _)| (*n).to_string()).collect();
|
||||
prompts.retain(|p| !exclude.contains(&p.name));
|
||||
prompts.sort_by(|a, b| a.name.cmp(&b.name));
|
||||
Self {
|
||||
command_filter: String::new(),
|
||||
all_commands: built_in_slash_commands(),
|
||||
builtins,
|
||||
prompts,
|
||||
state: ScrollState::new(),
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn set_prompts(&mut self, mut prompts: Vec<CustomPrompt>) {
|
||||
let exclude: HashSet<String> = self
|
||||
.builtins
|
||||
.iter()
|
||||
.map(|(n, _)| (*n).to_string())
|
||||
.collect();
|
||||
prompts.retain(|p| !exclude.contains(&p.name));
|
||||
prompts.sort_by(|a, b| a.name.cmp(&b.name));
|
||||
self.prompts = prompts;
|
||||
}
|
||||
|
||||
pub(crate) fn prompt_name(&self, idx: usize) -> Option<&str> {
|
||||
self.prompts.get(idx).map(|p| p.name.as_str())
|
||||
}
|
||||
|
||||
pub(crate) fn prompt_content(&self, idx: usize) -> Option<&str> {
|
||||
self.prompts.get(idx).map(|p| p.content.as_str())
|
||||
}
|
||||
|
||||
/// Update the filter string based on the current composer text. The text
|
||||
/// passed in is expected to start with a leading '/'. Everything after the
|
||||
/// *first* '/" on the *first* line becomes the active filter that is used
|
||||
@@ -50,7 +86,7 @@ impl CommandPopup {
|
||||
}
|
||||
|
||||
// Reset or clamp selected index based on new filtered list.
|
||||
let matches_len = self.filtered_commands().len();
|
||||
let matches_len = self.filtered_items().len();
|
||||
self.state.clamp_selection(matches_len);
|
||||
self.state
|
||||
.ensure_visible(matches_len, MAX_POPUP_ROWS.min(matches_len));
|
||||
@@ -59,56 +95,76 @@ impl CommandPopup {
|
||||
/// Determine the preferred height of the popup. This is the number of
|
||||
/// rows required to show at most MAX_POPUP_ROWS commands.
|
||||
pub(crate) fn calculate_required_height(&self) -> u16 {
|
||||
self.filtered_commands().len().clamp(1, MAX_POPUP_ROWS) as u16
|
||||
self.filtered_items().len().clamp(1, MAX_POPUP_ROWS) as u16
|
||||
}
|
||||
|
||||
/// Compute fuzzy-filtered matches paired with optional highlight indices and score.
|
||||
/// Sorted by ascending score, then by command name for stability.
|
||||
fn filtered(&self) -> Vec<(&SlashCommand, Option<Vec<usize>>, i32)> {
|
||||
/// Compute fuzzy-filtered matches over built-in commands and user prompts,
|
||||
/// paired with optional highlight indices and score. Sorted by ascending
|
||||
/// score, then by name for stability.
|
||||
fn filtered(&self) -> Vec<(CommandItem, Option<Vec<usize>>, i32)> {
|
||||
let filter = self.command_filter.trim();
|
||||
let mut out: Vec<(&SlashCommand, Option<Vec<usize>>, i32)> = Vec::new();
|
||||
let mut out: Vec<(CommandItem, Option<Vec<usize>>, i32)> = Vec::new();
|
||||
if filter.is_empty() {
|
||||
for (_, cmd) in self.all_commands.iter() {
|
||||
out.push((cmd, None, 0));
|
||||
// Built-ins first, in presentation order.
|
||||
for (_, cmd) in self.builtins.iter() {
|
||||
out.push((CommandItem::Builtin(*cmd), None, 0));
|
||||
}
|
||||
// Then prompts, already sorted by name.
|
||||
for idx in 0..self.prompts.len() {
|
||||
out.push((CommandItem::UserPrompt(idx), None, 0));
|
||||
}
|
||||
// Keep the original presentation order when no filter is applied.
|
||||
return out;
|
||||
} else {
|
||||
for (_, cmd) in self.all_commands.iter() {
|
||||
if let Some((indices, score)) = fuzzy_match(cmd.command(), filter) {
|
||||
out.push((cmd, Some(indices), score));
|
||||
}
|
||||
}
|
||||
|
||||
for (_, cmd) in self.builtins.iter() {
|
||||
if let Some((indices, score)) = fuzzy_match(cmd.command(), filter) {
|
||||
out.push((CommandItem::Builtin(*cmd), Some(indices), score));
|
||||
}
|
||||
}
|
||||
// When filtering, sort by ascending score and then by command for stability.
|
||||
out.sort_by(|a, b| a.2.cmp(&b.2).then_with(|| a.0.command().cmp(b.0.command())));
|
||||
for (idx, p) in self.prompts.iter().enumerate() {
|
||||
if let Some((indices, score)) = fuzzy_match(&p.name, filter) {
|
||||
out.push((CommandItem::UserPrompt(idx), Some(indices), score));
|
||||
}
|
||||
}
|
||||
// When filtering, sort by ascending score and then by name for stability.
|
||||
out.sort_by(|a, b| {
|
||||
a.2.cmp(&b.2).then_with(|| {
|
||||
let an = match a.0 {
|
||||
CommandItem::Builtin(c) => c.command(),
|
||||
CommandItem::UserPrompt(i) => &self.prompts[i].name,
|
||||
};
|
||||
let bn = match b.0 {
|
||||
CommandItem::Builtin(c) => c.command(),
|
||||
CommandItem::UserPrompt(i) => &self.prompts[i].name,
|
||||
};
|
||||
an.cmp(bn)
|
||||
})
|
||||
});
|
||||
out
|
||||
}
|
||||
|
||||
fn filtered_commands(&self) -> Vec<&SlashCommand> {
|
||||
fn filtered_items(&self) -> Vec<CommandItem> {
|
||||
self.filtered().into_iter().map(|(c, _, _)| c).collect()
|
||||
}
|
||||
|
||||
/// Move the selection cursor one step up.
|
||||
pub(crate) fn move_up(&mut self) {
|
||||
let matches = self.filtered_commands();
|
||||
let len = matches.len();
|
||||
let len = self.filtered_items().len();
|
||||
self.state.move_up_wrap(len);
|
||||
self.state.ensure_visible(len, MAX_POPUP_ROWS.min(len));
|
||||
}
|
||||
|
||||
/// Move the selection cursor one step down.
|
||||
pub(crate) fn move_down(&mut self) {
|
||||
let matches = self.filtered_commands();
|
||||
let matches_len = matches.len();
|
||||
let matches_len = self.filtered_items().len();
|
||||
self.state.move_down_wrap(matches_len);
|
||||
self.state
|
||||
.ensure_visible(matches_len, MAX_POPUP_ROWS.min(matches_len));
|
||||
}
|
||||
|
||||
/// Return currently selected command, if any.
|
||||
pub(crate) fn selected_command(&self) -> Option<&SlashCommand> {
|
||||
let matches = self.filtered_commands();
|
||||
pub(crate) fn selected_item(&self) -> Option<CommandItem> {
|
||||
let matches = self.filtered_items();
|
||||
self.state
|
||||
.selected_idx
|
||||
.and_then(|idx| matches.get(idx).copied())
|
||||
@@ -123,11 +179,19 @@ impl WidgetRef for CommandPopup {
|
||||
} else {
|
||||
matches
|
||||
.into_iter()
|
||||
.map(|(cmd, indices, _)| GenericDisplayRow {
|
||||
name: format!("/{}", cmd.command()),
|
||||
match_indices: indices.map(|v| v.into_iter().map(|i| i + 1).collect()),
|
||||
is_current: false,
|
||||
description: Some(cmd.description().to_string()),
|
||||
.map(|(item, indices, _)| match item {
|
||||
CommandItem::Builtin(cmd) => GenericDisplayRow {
|
||||
name: format!("/{}", cmd.command()),
|
||||
match_indices: indices.map(|v| v.into_iter().map(|i| i + 1).collect()),
|
||||
is_current: false,
|
||||
description: Some(cmd.description().to_string()),
|
||||
},
|
||||
CommandItem::UserPrompt(i) => GenericDisplayRow {
|
||||
name: format!("/{}", self.prompts[i].name),
|
||||
match_indices: indices.map(|v| v.into_iter().map(|i| i + 1).collect()),
|
||||
is_current: false,
|
||||
description: Some("send saved prompt".to_string()),
|
||||
},
|
||||
})
|
||||
.collect()
|
||||
};
|
||||
@@ -141,31 +205,82 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn filter_includes_init_when_typing_prefix() {
|
||||
let mut popup = CommandPopup::new();
|
||||
let mut popup = CommandPopup::new(Vec::new());
|
||||
// Simulate the composer line starting with '/in' so the popup filters
|
||||
// matching commands by prefix.
|
||||
popup.on_composer_text_change("/in".to_string());
|
||||
|
||||
// Access the filtered list via the selected command and ensure that
|
||||
// one of the matches is the new "init" command.
|
||||
let matches = popup.filtered_commands();
|
||||
let matches = popup.filtered_items();
|
||||
let has_init = matches.iter().any(|item| match item {
|
||||
CommandItem::Builtin(cmd) => cmd.command() == "init",
|
||||
CommandItem::UserPrompt(_) => false,
|
||||
});
|
||||
assert!(
|
||||
matches.iter().any(|cmd| cmd.command() == "init"),
|
||||
has_init,
|
||||
"expected '/init' to appear among filtered commands"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn selecting_init_by_exact_match() {
|
||||
let mut popup = CommandPopup::new();
|
||||
let mut popup = CommandPopup::new(Vec::new());
|
||||
popup.on_composer_text_change("/init".to_string());
|
||||
|
||||
// When an exact match exists, the selected command should be that
|
||||
// command by default.
|
||||
let selected = popup.selected_command();
|
||||
let selected = popup.selected_item();
|
||||
match selected {
|
||||
Some(cmd) => assert_eq!(cmd.command(), "init"),
|
||||
Some(CommandItem::Builtin(cmd)) => assert_eq!(cmd.command(), "init"),
|
||||
Some(CommandItem::UserPrompt(_)) => panic!("unexpected prompt selected for '/init'"),
|
||||
None => panic!("expected a selected command for exact match"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prompt_discovery_lists_custom_prompts() {
|
||||
let prompts = vec![
|
||||
CustomPrompt {
|
||||
name: "foo".to_string(),
|
||||
path: "/tmp/foo.md".to_string().into(),
|
||||
content: "hello from foo".to_string(),
|
||||
},
|
||||
CustomPrompt {
|
||||
name: "bar".to_string(),
|
||||
path: "/tmp/bar.md".to_string().into(),
|
||||
content: "hello from bar".to_string(),
|
||||
},
|
||||
];
|
||||
let popup = CommandPopup::new(prompts);
|
||||
let items = popup.filtered_items();
|
||||
let mut prompt_names: Vec<String> = items
|
||||
.into_iter()
|
||||
.filter_map(|it| match it {
|
||||
CommandItem::UserPrompt(i) => popup.prompt_name(i).map(|s| s.to_string()),
|
||||
_ => None,
|
||||
})
|
||||
.collect();
|
||||
prompt_names.sort();
|
||||
assert_eq!(prompt_names, vec!["bar".to_string(), "foo".to_string()]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prompt_name_collision_with_builtin_is_ignored() {
|
||||
// Create a prompt named like a builtin (e.g. "init").
|
||||
let popup = CommandPopup::new(vec![CustomPrompt {
|
||||
name: "init".to_string(),
|
||||
path: "/tmp/init.md".to_string().into(),
|
||||
content: "should be ignored".to_string(),
|
||||
}]);
|
||||
let items = popup.filtered_items();
|
||||
let has_collision_prompt = items.into_iter().any(|it| match it {
|
||||
CommandItem::UserPrompt(i) => popup.prompt_name(i) == Some("init"),
|
||||
_ => false,
|
||||
});
|
||||
assert!(
|
||||
!has_collision_prompt,
|
||||
"prompt with builtin name should be ignored"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,6 +13,7 @@ use ratatui::layout::Constraint;
|
||||
use ratatui::layout::Layout;
|
||||
use ratatui::layout::Rect;
|
||||
use ratatui::widgets::WidgetRef;
|
||||
use std::time::Duration;
|
||||
|
||||
mod approval_modal_view;
|
||||
mod bottom_pane_view;
|
||||
@@ -21,10 +22,10 @@ mod chat_composer_history;
|
||||
mod command_popup;
|
||||
mod file_search_popup;
|
||||
mod list_selection_view;
|
||||
mod paste_burst;
|
||||
mod popup_consts;
|
||||
mod scroll_state;
|
||||
mod selection_popup_common;
|
||||
mod status_indicator_view;
|
||||
mod textarea;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
@@ -35,11 +36,12 @@ pub(crate) enum CancellationEvent {
|
||||
|
||||
pub(crate) use chat_composer::ChatComposer;
|
||||
pub(crate) use chat_composer::InputResult;
|
||||
use codex_protocol::custom_prompts::CustomPrompt;
|
||||
|
||||
use crate::status_indicator_widget::StatusIndicatorWidget;
|
||||
use approval_modal_view::ApprovalModalView;
|
||||
pub(crate) use list_selection_view::SelectionAction;
|
||||
pub(crate) use list_selection_view::SelectionItem;
|
||||
use status_indicator_view::StatusIndicatorView;
|
||||
|
||||
/// Pane displayed in the lower half of the chat UI.
|
||||
pub(crate) struct BottomPane {
|
||||
@@ -47,7 +49,7 @@ pub(crate) struct BottomPane {
|
||||
/// input state is retained when the view is closed.
|
||||
composer: ChatComposer,
|
||||
|
||||
/// If present, this is displayed instead of the `composer`.
|
||||
/// If present, this is displayed instead of the `composer` (e.g. modals).
|
||||
active_view: Option<Box<dyn BottomPaneView>>,
|
||||
|
||||
app_event_tx: AppEventSender,
|
||||
@@ -58,9 +60,10 @@ pub(crate) struct BottomPane {
|
||||
ctrl_c_quit_hint: bool,
|
||||
esc_backtrack_hint: bool,
|
||||
|
||||
/// True if the active view is the StatusIndicatorView that replaces the
|
||||
/// composer during a running task.
|
||||
status_view_active: bool,
|
||||
/// Inline status indicator shown above the composer while a task is running.
|
||||
status: Option<StatusIndicatorWidget>,
|
||||
/// Queued user messages to show under the status indicator.
|
||||
queued_user_messages: Vec<String>,
|
||||
}
|
||||
|
||||
pub(crate) struct BottomPaneParams {
|
||||
@@ -69,10 +72,11 @@ pub(crate) struct BottomPaneParams {
|
||||
pub(crate) has_input_focus: bool,
|
||||
pub(crate) enhanced_keys_supported: bool,
|
||||
pub(crate) placeholder_text: String,
|
||||
pub(crate) disable_paste_burst: bool,
|
||||
}
|
||||
|
||||
impl BottomPane {
|
||||
const BOTTOM_PAD_LINES: u16 = 2;
|
||||
const BOTTOM_PAD_LINES: u16 = 1;
|
||||
pub fn new(params: BottomPaneParams) -> Self {
|
||||
let enhanced_keys_supported = params.enhanced_keys_supported;
|
||||
Self {
|
||||
@@ -81,6 +85,7 @@ impl BottomPane {
|
||||
params.app_event_tx.clone(),
|
||||
enhanced_keys_supported,
|
||||
params.placeholder_text,
|
||||
params.disable_paste_burst,
|
||||
),
|
||||
active_view: None,
|
||||
app_event_tx: params.app_event_tx,
|
||||
@@ -88,42 +93,60 @@ impl BottomPane {
|
||||
has_input_focus: params.has_input_focus,
|
||||
is_task_running: false,
|
||||
ctrl_c_quit_hint: false,
|
||||
status: None,
|
||||
queued_user_messages: Vec::new(),
|
||||
esc_backtrack_hint: false,
|
||||
status_view_active: false,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn desired_height(&self, width: u16) -> u16 {
|
||||
let view_height = if let Some(view) = self.active_view.as_ref() {
|
||||
let top_margin = if self.active_view.is_some() { 0 } else { 1 };
|
||||
|
||||
// Base height depends on whether a modal/overlay is active.
|
||||
let mut base = if let Some(view) = self.active_view.as_ref() {
|
||||
view.desired_height(width)
|
||||
} else {
|
||||
self.composer.desired_height(width)
|
||||
};
|
||||
let top_pad = if self.active_view.is_none() || self.status_view_active {
|
||||
1
|
||||
} else {
|
||||
0
|
||||
};
|
||||
view_height
|
||||
.saturating_add(Self::BOTTOM_PAD_LINES)
|
||||
.saturating_add(top_pad)
|
||||
// If a status indicator is active and no modal is covering the composer,
|
||||
// include its height above the composer.
|
||||
if self.active_view.is_none()
|
||||
&& let Some(status) = self.status.as_ref()
|
||||
{
|
||||
base = base.saturating_add(status.desired_height(width));
|
||||
}
|
||||
// Account for bottom padding rows. Top spacing is handled in layout().
|
||||
base.saturating_add(Self::BOTTOM_PAD_LINES)
|
||||
.saturating_add(top_margin)
|
||||
}
|
||||
|
||||
fn layout(&self, area: Rect) -> Rect {
|
||||
let top = if self.active_view.is_none() || self.status_view_active {
|
||||
1
|
||||
fn layout(&self, area: Rect) -> [Rect; 2] {
|
||||
// Prefer showing the status header when space is extremely tight.
|
||||
// Drop the top spacer if there is only one row available.
|
||||
let mut top_margin = if self.active_view.is_some() { 0 } else { 1 };
|
||||
if area.height <= 1 {
|
||||
top_margin = 0;
|
||||
}
|
||||
|
||||
let status_height = if self.active_view.is_none() {
|
||||
if let Some(status) = self.status.as_ref() {
|
||||
status.desired_height(area.width)
|
||||
} else {
|
||||
0
|
||||
}
|
||||
} else {
|
||||
0
|
||||
};
|
||||
|
||||
let [_, content, _] = Layout::vertical([
|
||||
Constraint::Max(top),
|
||||
let [_, status, content, _] = Layout::vertical([
|
||||
Constraint::Max(top_margin),
|
||||
Constraint::Max(status_height),
|
||||
Constraint::Min(1),
|
||||
Constraint::Max(BottomPane::BOTTOM_PAD_LINES),
|
||||
])
|
||||
.areas(area);
|
||||
|
||||
content
|
||||
[status, content]
|
||||
}
|
||||
|
||||
pub fn cursor_pos(&self, area: Rect) -> Option<(u16, u16)> {
|
||||
@@ -131,10 +154,10 @@ impl BottomPane {
|
||||
// status indicator shown while a task is running, or approval modal).
|
||||
// In these states the textarea is not interactable, so we should not
|
||||
// show its caret.
|
||||
if self.active_view.is_some() || self.status_view_active {
|
||||
if self.active_view.is_some() {
|
||||
None
|
||||
} else {
|
||||
let content = self.layout(area);
|
||||
let [_, content] = self.layout(area);
|
||||
self.composer.cursor_pos(content)
|
||||
}
|
||||
}
|
||||
@@ -145,22 +168,28 @@ impl BottomPane {
|
||||
view.handle_key_event(self, key_event);
|
||||
if !view.is_complete() {
|
||||
self.active_view = Some(view);
|
||||
} else if self.is_task_running {
|
||||
let mut v = StatusIndicatorView::new(
|
||||
self.app_event_tx.clone(),
|
||||
self.frame_requester.clone(),
|
||||
);
|
||||
v.update_text("waiting for model".to_string());
|
||||
self.active_view = Some(Box::new(v));
|
||||
self.status_view_active = true;
|
||||
}
|
||||
self.request_redraw();
|
||||
InputResult::None
|
||||
} else {
|
||||
// If a task is running and a status line is visible, allow Esc to
|
||||
// send an interrupt even while the composer has focus.
|
||||
if matches!(key_event.code, crossterm::event::KeyCode::Esc)
|
||||
&& self.is_task_running
|
||||
&& let Some(status) = &self.status
|
||||
{
|
||||
// Send Op::Interrupt
|
||||
status.interrupt();
|
||||
self.request_redraw();
|
||||
return InputResult::None;
|
||||
}
|
||||
let (input_result, needs_redraw) = self.composer.handle_key_event(key_event);
|
||||
if needs_redraw {
|
||||
self.request_redraw();
|
||||
}
|
||||
if self.composer.is_in_paste_burst() {
|
||||
self.request_redraw_in(ChatComposer::recommended_paste_flush_delay());
|
||||
}
|
||||
input_result
|
||||
}
|
||||
}
|
||||
@@ -178,15 +207,6 @@ impl BottomPane {
|
||||
CancellationEvent::Handled => {
|
||||
if !view.is_complete() {
|
||||
self.active_view = Some(view);
|
||||
} else if self.is_task_running {
|
||||
// Modal aborted but task still running – restore status indicator.
|
||||
let mut v = StatusIndicatorView::new(
|
||||
self.app_event_tx.clone(),
|
||||
self.frame_requester.clone(),
|
||||
);
|
||||
v.update_text("waiting for model".to_string());
|
||||
self.active_view = Some(Box::new(v));
|
||||
self.status_view_active = true;
|
||||
}
|
||||
self.show_ctrl_c_quit_hint();
|
||||
}
|
||||
@@ -211,13 +231,24 @@ impl BottomPane {
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
/// Replace the composer text with `text`.
|
||||
pub(crate) fn set_composer_text(&mut self, text: String) {
|
||||
self.composer.set_text_content(text);
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
/// Get the current composer text (for tests and programmatic checks).
|
||||
#[cfg(test)]
|
||||
pub(crate) fn composer_text(&self) -> String {
|
||||
self.composer.current_text()
|
||||
}
|
||||
|
||||
/// Update the animated header shown to the left of the brackets in the
|
||||
/// status indicator (defaults to "Working"). This will update the active
|
||||
/// StatusIndicatorView if present; otherwise, if a live overlay is active,
|
||||
/// it will update that. If neither is present, this call is a no-op.
|
||||
/// status indicator (defaults to "Working"). No-ops if the status
|
||||
/// indicator is not active.
|
||||
pub(crate) fn update_status_header(&mut self, header: String) {
|
||||
if let Some(view) = self.active_view.as_mut() {
|
||||
view.update_status_header(header.clone());
|
||||
if let Some(status) = self.status.as_mut() {
|
||||
status.update_header(header);
|
||||
self.request_redraw();
|
||||
}
|
||||
}
|
||||
@@ -262,23 +293,19 @@ impl BottomPane {
|
||||
self.is_task_running = running;
|
||||
|
||||
if running {
|
||||
if self.active_view.is_none() {
|
||||
self.active_view = Some(Box::new(StatusIndicatorView::new(
|
||||
if self.status.is_none() {
|
||||
self.status = Some(StatusIndicatorWidget::new(
|
||||
self.app_event_tx.clone(),
|
||||
self.frame_requester.clone(),
|
||||
)));
|
||||
self.status_view_active = true;
|
||||
));
|
||||
}
|
||||
if let Some(status) = self.status.as_mut() {
|
||||
status.set_queued_messages(self.queued_user_messages.clone());
|
||||
}
|
||||
self.request_redraw();
|
||||
} else {
|
||||
// Drop the status view when a task completes, but keep other
|
||||
// modal views (e.g. approval dialogs).
|
||||
if let Some(mut view) = self.active_view.take() {
|
||||
if !view.should_hide_when_task_is_done() {
|
||||
self.active_view = Some(view);
|
||||
}
|
||||
self.status_view_active = false;
|
||||
}
|
||||
// Hide the status indicator when a task completes, but keep other modal views.
|
||||
self.status = None;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -298,21 +325,22 @@ impl BottomPane {
|
||||
self.app_event_tx.clone(),
|
||||
);
|
||||
self.active_view = Some(Box::new(view));
|
||||
self.status_view_active = false;
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
/// Update the live status text shown while a task is running.
|
||||
/// If a modal view is active (i.e., not the status indicator), this is a no‑op.
|
||||
pub(crate) fn update_status_text(&mut self, text: String) {
|
||||
if !self.is_task_running || !self.status_view_active {
|
||||
return;
|
||||
}
|
||||
if let Some(mut view) = self.active_view.take() {
|
||||
view.update_status_text(text);
|
||||
self.active_view = Some(view);
|
||||
self.request_redraw();
|
||||
/// Update the queued messages shown under the status header.
|
||||
pub(crate) fn set_queued_user_messages(&mut self, queued: Vec<String>) {
|
||||
self.queued_user_messages = queued.clone();
|
||||
if let Some(status) = self.status.as_mut() {
|
||||
status.set_queued_messages(queued);
|
||||
}
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
/// Update custom prompts available for the slash popup.
|
||||
pub(crate) fn set_custom_prompts(&mut self, prompts: Vec<CustomPrompt>) {
|
||||
self.composer.set_custom_prompts(prompts);
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn composer_is_empty(&self) -> bool {
|
||||
@@ -323,6 +351,13 @@ impl BottomPane {
|
||||
self.is_task_running
|
||||
}
|
||||
|
||||
/// Return true when the pane is in the regular composer state without any
|
||||
/// overlays or popups and not running a task. This is the safe context to
|
||||
/// use Esc-Esc for backtracking from the main view.
|
||||
pub(crate) fn is_normal_backtrack_mode(&self) -> bool {
|
||||
!self.is_task_running && self.active_view.is_none() && !self.composer.popup_active()
|
||||
}
|
||||
|
||||
/// Update the *context-window remaining* indicator in the composer. This
|
||||
/// is forwarded directly to the underlying `ChatComposer`.
|
||||
pub(crate) fn set_token_usage(
|
||||
@@ -353,7 +388,6 @@ impl BottomPane {
|
||||
// Otherwise create a new approval modal overlay.
|
||||
let modal = ApprovalModalView::new(request, self.app_event_tx.clone());
|
||||
self.active_view = Some(Box::new(modal));
|
||||
self.status_view_active = false;
|
||||
self.request_redraw()
|
||||
}
|
||||
|
||||
@@ -362,12 +396,24 @@ impl BottomPane {
|
||||
self.frame_requester.schedule_frame();
|
||||
}
|
||||
|
||||
pub(crate) fn request_redraw_in(&self, dur: Duration) {
|
||||
self.frame_requester.schedule_frame_in(dur);
|
||||
}
|
||||
|
||||
// --- History helpers ---
|
||||
|
||||
pub(crate) fn set_history_metadata(&mut self, log_id: u64, entry_count: usize) {
|
||||
self.composer.set_history_metadata(log_id, entry_count);
|
||||
}
|
||||
|
||||
pub(crate) fn flush_paste_burst_if_due(&mut self) -> bool {
|
||||
self.composer.flush_paste_burst_if_due()
|
||||
}
|
||||
|
||||
pub(crate) fn is_in_paste_burst(&self) -> bool {
|
||||
self.composer.is_in_paste_burst()
|
||||
}
|
||||
|
||||
pub(crate) fn on_history_entry_response(
|
||||
&mut self,
|
||||
log_id: u64,
|
||||
@@ -409,12 +455,20 @@ impl BottomPane {
|
||||
|
||||
impl WidgetRef for &BottomPane {
|
||||
fn render_ref(&self, area: Rect, buf: &mut Buffer) {
|
||||
let content = self.layout(area);
|
||||
let [status_area, content] = self.layout(area);
|
||||
|
||||
// When a modal view is active, it owns the whole content area.
|
||||
if let Some(view) = &self.active_view {
|
||||
view.render(content, buf);
|
||||
} else {
|
||||
(&self.composer).render_ref(content, buf);
|
||||
// No active modal:
|
||||
// If a status indicator is active, render it above the composer.
|
||||
if let Some(status) = &self.status {
|
||||
status.render_ref(status_area, buf);
|
||||
}
|
||||
|
||||
// Render the composer in the remaining area.
|
||||
self.composer.render_ref(content, buf);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -445,6 +499,7 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
pane.push_approval_request(exec_request());
|
||||
assert_eq!(CancellationEvent::Handled, pane.on_ctrl_c());
|
||||
@@ -464,6 +519,7 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
|
||||
// Create an approval modal (active view).
|
||||
@@ -485,7 +541,7 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn composer_not_shown_after_denied_if_task_running() {
|
||||
fn composer_shown_after_denied_while_task_running() {
|
||||
let (tx_raw, rx) = unbounded_channel::<AppEvent>();
|
||||
let tx = AppEventSender::new(tx_raw);
|
||||
let mut pane = BottomPane::new(BottomPaneParams {
|
||||
@@ -494,30 +550,32 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
|
||||
// Start a running task so the status indicator replaces the composer.
|
||||
// Start a running task so the status indicator is active above the composer.
|
||||
pane.set_task_running(true);
|
||||
|
||||
// Push an approval modal (e.g., command approval) which should hide the status view.
|
||||
pane.push_approval_request(exec_request());
|
||||
|
||||
// Simulate pressing 'n' (deny) on the modal.
|
||||
// Simulate pressing 'n' (No) on the modal.
|
||||
use crossterm::event::KeyCode;
|
||||
use crossterm::event::KeyEvent;
|
||||
use crossterm::event::KeyModifiers;
|
||||
pane.handle_key_event(KeyEvent::new(KeyCode::Char('n'), KeyModifiers::NONE));
|
||||
|
||||
// After denial, since the task is still running, the status indicator
|
||||
// should be restored as the active view; the composer should NOT be visible.
|
||||
// After denial, since the task is still running, the status indicator should be
|
||||
// visible above the composer. The modal should be gone.
|
||||
assert!(
|
||||
pane.status_view_active,
|
||||
"status view should be active after denial"
|
||||
pane.active_view.is_none(),
|
||||
"no active modal view after denial"
|
||||
);
|
||||
assert!(pane.active_view.is_some(), "active view should be present");
|
||||
|
||||
// Render and ensure the top row includes the Working header instead of the composer.
|
||||
let area = Rect::new(0, 0, 40, 3);
|
||||
// Render and ensure the top row includes the Working header and a composer line below.
|
||||
// Give the animation thread a moment to tick.
|
||||
std::thread::sleep(std::time::Duration::from_millis(120));
|
||||
let area = Rect::new(0, 0, 40, 6);
|
||||
let mut buf = Buffer::empty(area);
|
||||
(&pane).render_ref(area, &mut buf);
|
||||
let mut row1 = String::new();
|
||||
@@ -529,6 +587,23 @@ mod tests {
|
||||
"expected Working header after denial on row 1: {row1:?}"
|
||||
);
|
||||
|
||||
// Composer placeholder should be visible somewhere below.
|
||||
let mut found_composer = false;
|
||||
for y in 1..area.height.saturating_sub(2) {
|
||||
let mut row = String::new();
|
||||
for x in 0..area.width {
|
||||
row.push(buf[(x, y)].symbol().chars().next().unwrap_or(' '));
|
||||
}
|
||||
if row.contains("Ask Codex") {
|
||||
found_composer = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
assert!(
|
||||
found_composer,
|
||||
"expected composer visible under status line"
|
||||
);
|
||||
|
||||
// Drain the channel to avoid unused warnings.
|
||||
drop(rx);
|
||||
}
|
||||
@@ -543,12 +618,14 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
|
||||
// Begin a task: show initial status.
|
||||
pane.set_task_running(true);
|
||||
|
||||
let area = Rect::new(0, 0, 40, 3);
|
||||
// Use a height that allows the status line to be visible above the composer.
|
||||
let area = Rect::new(0, 0, 40, 6);
|
||||
let mut buf = Buffer::empty(area);
|
||||
(&pane).render_ref(area, &mut buf);
|
||||
|
||||
@@ -563,7 +640,7 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bottom_padding_present_for_status_view() {
|
||||
fn bottom_padding_present_with_status_above_composer() {
|
||||
let (tx_raw, _rx) = unbounded_channel::<AppEvent>();
|
||||
let tx = AppEventSender::new(tx_raw);
|
||||
let mut pane = BottomPane::new(BottomPaneParams {
|
||||
@@ -572,6 +649,7 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
|
||||
// Activate spinner (status view replaces composer) with no live ring.
|
||||
@@ -592,27 +670,24 @@ mod tests {
|
||||
for x in 0..area.width {
|
||||
top.push(buf[(x, 1)].symbol().chars().next().unwrap_or(' '));
|
||||
}
|
||||
assert_eq!(buf[(0, 1)].symbol().chars().next().unwrap_or(' '), '▌');
|
||||
assert!(
|
||||
top.trim_start().starts_with("Working"),
|
||||
"expected top row to start with 'Working': {top:?}"
|
||||
);
|
||||
assert!(
|
||||
top.contains("Working"),
|
||||
"expected Working header on top row: {top:?}"
|
||||
);
|
||||
|
||||
// Bottom two rows are blank padding
|
||||
// Last row should be blank padding; the row above should generally contain composer content.
|
||||
let mut r_last = String::new();
|
||||
let mut r_last2 = String::new();
|
||||
for x in 0..area.width {
|
||||
r_last.push(buf[(x, height - 1)].symbol().chars().next().unwrap_or(' '));
|
||||
r_last2.push(buf[(x, height - 2)].symbol().chars().next().unwrap_or(' '));
|
||||
}
|
||||
assert!(
|
||||
r_last.trim().is_empty(),
|
||||
"expected last row blank: {r_last:?}"
|
||||
);
|
||||
assert!(
|
||||
r_last2.trim().is_empty(),
|
||||
"expected second-to-last row blank: {r_last2:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -625,11 +700,12 @@ mod tests {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported: false,
|
||||
placeholder_text: "Ask Codex to do anything".to_string(),
|
||||
disable_paste_burst: false,
|
||||
});
|
||||
|
||||
pane.set_task_running(true);
|
||||
|
||||
// Height=2 → with spacer, spinner on row 1; no bottom padding.
|
||||
// Height=2 → composer visible; status is hidden to preserve composer. Spacer may collapse.
|
||||
let area2 = Rect::new(0, 0, 20, 2);
|
||||
let mut buf2 = Buffer::empty(area2);
|
||||
(&pane).render_ref(area2, &mut buf2);
|
||||
@@ -639,13 +715,17 @@ mod tests {
|
||||
row0.push(buf2[(x, 0)].symbol().chars().next().unwrap_or(' '));
|
||||
row1.push(buf2[(x, 1)].symbol().chars().next().unwrap_or(' '));
|
||||
}
|
||||
assert!(row0.trim().is_empty(), "expected spacer on row 0: {row0:?}");
|
||||
let has_composer = row0.contains("Ask Codex") || row1.contains("Ask Codex");
|
||||
assert!(
|
||||
row1.contains("Working"),
|
||||
"expected Working on row 1: {row1:?}"
|
||||
has_composer,
|
||||
"expected composer to be visible on one of the rows: row0={row0:?}, row1={row1:?}"
|
||||
);
|
||||
assert!(
|
||||
!row0.contains("Working") && !row1.contains("Working"),
|
||||
"status header should be hidden when height=2"
|
||||
);
|
||||
|
||||
// Height=1 → no padding; single row is the spinner.
|
||||
// Height=1 → no padding; single row is the composer (status hidden).
|
||||
let area1 = Rect::new(0, 0, 20, 1);
|
||||
let mut buf1 = Buffer::empty(area1);
|
||||
(&pane).render_ref(area1, &mut buf1);
|
||||
@@ -654,8 +734,8 @@ mod tests {
|
||||
only.push(buf1[(x, 0)].symbol().chars().next().unwrap_or(' '));
|
||||
}
|
||||
assert!(
|
||||
only.contains("Working"),
|
||||
"expected Working header with no padding: {only:?}"
|
||||
only.contains("Ask Codex"),
|
||||
"expected composer with no padding: {only:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
246
codex-rs/tui/src/bottom_pane/paste_burst.rs
Normal file
246
codex-rs/tui/src/bottom_pane/paste_burst.rs
Normal file
@@ -0,0 +1,246 @@
|
||||
use std::time::Duration;
|
||||
use std::time::Instant;
|
||||
|
||||
// Heuristic thresholds for detecting paste-like input bursts.
|
||||
// Detect quickly to avoid showing typed prefix before paste is recognized
|
||||
const PASTE_BURST_MIN_CHARS: u16 = 3;
|
||||
const PASTE_BURST_CHAR_INTERVAL: Duration = Duration::from_millis(8);
|
||||
const PASTE_ENTER_SUPPRESS_WINDOW: Duration = Duration::from_millis(120);
|
||||
|
||||
#[derive(Default)]
|
||||
pub(crate) struct PasteBurst {
|
||||
last_plain_char_time: Option<Instant>,
|
||||
consecutive_plain_char_burst: u16,
|
||||
burst_window_until: Option<Instant>,
|
||||
buffer: String,
|
||||
active: bool,
|
||||
// Hold first fast char briefly to avoid rendering flicker
|
||||
pending_first_char: Option<(char, Instant)>,
|
||||
}
|
||||
|
||||
pub(crate) enum CharDecision {
|
||||
/// Start buffering and retroactively capture some already-inserted chars.
|
||||
BeginBuffer { retro_chars: u16 },
|
||||
/// We are currently buffering; append the current char into the buffer.
|
||||
BufferAppend,
|
||||
/// Do not insert/render this char yet; temporarily save the first fast
|
||||
/// char while we wait to see if a paste-like burst follows.
|
||||
RetainFirstChar,
|
||||
/// Begin buffering using the previously saved first char (no retro grab needed).
|
||||
BeginBufferFromPending,
|
||||
}
|
||||
|
||||
pub(crate) struct RetroGrab {
|
||||
pub start_byte: usize,
|
||||
pub grabbed: String,
|
||||
}
|
||||
|
||||
impl PasteBurst {
|
||||
/// Recommended delay to wait between simulated keypresses (or before
|
||||
/// scheduling a UI tick) so that a pending fast keystroke is flushed
|
||||
/// out of the burst detector as normal typed input.
|
||||
///
|
||||
/// Primarily used by tests and by the TUI to reliably cross the
|
||||
/// paste-burst timing threshold.
|
||||
pub fn recommended_flush_delay() -> Duration {
|
||||
PASTE_BURST_CHAR_INTERVAL + Duration::from_millis(1)
|
||||
}
|
||||
|
||||
/// Entry point: decide how to treat a plain char with current timing.
|
||||
pub fn on_plain_char(&mut self, ch: char, now: Instant) -> CharDecision {
|
||||
match self.last_plain_char_time {
|
||||
Some(prev) if now.duration_since(prev) <= PASTE_BURST_CHAR_INTERVAL => {
|
||||
self.consecutive_plain_char_burst =
|
||||
self.consecutive_plain_char_burst.saturating_add(1)
|
||||
}
|
||||
_ => self.consecutive_plain_char_burst = 1,
|
||||
}
|
||||
self.last_plain_char_time = Some(now);
|
||||
|
||||
if self.active {
|
||||
self.burst_window_until = Some(now + PASTE_ENTER_SUPPRESS_WINDOW);
|
||||
return CharDecision::BufferAppend;
|
||||
}
|
||||
|
||||
// If we already held a first char and receive a second fast char,
|
||||
// start buffering without retro-grabbing (we never rendered the first).
|
||||
if let Some((held, held_at)) = self.pending_first_char
|
||||
&& now.duration_since(held_at) <= PASTE_BURST_CHAR_INTERVAL
|
||||
{
|
||||
self.active = true;
|
||||
// take() to clear pending; we already captured the held char above
|
||||
let _ = self.pending_first_char.take();
|
||||
self.buffer.push(held);
|
||||
self.burst_window_until = Some(now + PASTE_ENTER_SUPPRESS_WINDOW);
|
||||
return CharDecision::BeginBufferFromPending;
|
||||
}
|
||||
|
||||
if self.consecutive_plain_char_burst >= PASTE_BURST_MIN_CHARS {
|
||||
return CharDecision::BeginBuffer {
|
||||
retro_chars: self.consecutive_plain_char_burst.saturating_sub(1),
|
||||
};
|
||||
}
|
||||
|
||||
// Save the first fast char very briefly to see if a burst follows.
|
||||
self.pending_first_char = Some((ch, now));
|
||||
CharDecision::RetainFirstChar
|
||||
}
|
||||
|
||||
/// Flush the buffered burst if the inter-key timeout has elapsed.
|
||||
///
|
||||
/// Returns Some(String) when either:
|
||||
/// - We were actively buffering paste-like input and the buffer is now
|
||||
/// emitted as a single pasted string; or
|
||||
/// - We had saved a single fast first-char with no subsequent burst and we
|
||||
/// now emit that char as normal typed input.
|
||||
///
|
||||
/// Returns None if the timeout has not elapsed or there is nothing to flush.
|
||||
pub fn flush_if_due(&mut self, now: Instant) -> Option<String> {
|
||||
let timed_out = self
|
||||
.last_plain_char_time
|
||||
.is_some_and(|t| now.duration_since(t) > PASTE_BURST_CHAR_INTERVAL);
|
||||
if timed_out && self.is_active_internal() {
|
||||
self.active = false;
|
||||
let out = std::mem::take(&mut self.buffer);
|
||||
Some(out)
|
||||
} else if timed_out {
|
||||
// If we were saving a single fast char and no burst followed,
|
||||
// flush it as normal typed input.
|
||||
if let Some((ch, _at)) = self.pending_first_char.take() {
|
||||
Some(ch.to_string())
|
||||
} else {
|
||||
None
|
||||
}
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
/// While bursting: accumulate a newline into the buffer instead of
|
||||
/// submitting the textarea.
|
||||
///
|
||||
/// Returns true if a newline was appended (we are in a burst context),
|
||||
/// false otherwise.
|
||||
pub fn append_newline_if_active(&mut self, now: Instant) -> bool {
|
||||
if self.is_active() {
|
||||
self.buffer.push('\n');
|
||||
self.burst_window_until = Some(now + PASTE_ENTER_SUPPRESS_WINDOW);
|
||||
true
|
||||
} else {
|
||||
false
|
||||
}
|
||||
}
|
||||
|
||||
/// Decide if Enter should insert a newline (burst context) vs submit.
|
||||
pub fn newline_should_insert_instead_of_submit(&self, now: Instant) -> bool {
|
||||
let in_burst_window = self.burst_window_until.is_some_and(|until| now <= until);
|
||||
self.is_active() || in_burst_window
|
||||
}
|
||||
|
||||
/// Keep the burst window alive.
|
||||
pub fn extend_window(&mut self, now: Instant) {
|
||||
self.burst_window_until = Some(now + PASTE_ENTER_SUPPRESS_WINDOW);
|
||||
}
|
||||
|
||||
/// Begin buffering with retroactively grabbed text.
|
||||
pub fn begin_with_retro_grabbed(&mut self, grabbed: String, now: Instant) {
|
||||
if !grabbed.is_empty() {
|
||||
self.buffer.push_str(&grabbed);
|
||||
}
|
||||
self.active = true;
|
||||
self.burst_window_until = Some(now + PASTE_ENTER_SUPPRESS_WINDOW);
|
||||
}
|
||||
|
||||
/// Append a char into the burst buffer.
|
||||
pub fn append_char_to_buffer(&mut self, ch: char, now: Instant) {
|
||||
self.buffer.push(ch);
|
||||
self.burst_window_until = Some(now + PASTE_ENTER_SUPPRESS_WINDOW);
|
||||
}
|
||||
|
||||
/// Decide whether to begin buffering by retroactively capturing recent
|
||||
/// chars from the slice before the cursor.
|
||||
///
|
||||
/// Heuristic: if the retro-grabbed slice contains any whitespace or is
|
||||
/// sufficiently long (>= 16 characters), treat it as paste-like to avoid
|
||||
/// rendering the typed prefix momentarily before the paste is recognized.
|
||||
/// This favors responsiveness and prevents flicker for typical pastes
|
||||
/// (URLs, file paths, multiline text) while not triggering on short words.
|
||||
///
|
||||
/// Returns Some(RetroGrab) with the start byte and grabbed text when we
|
||||
/// decide to buffer retroactively; otherwise None.
|
||||
pub fn decide_begin_buffer(
|
||||
&mut self,
|
||||
now: Instant,
|
||||
before: &str,
|
||||
retro_chars: usize,
|
||||
) -> Option<RetroGrab> {
|
||||
let start_byte = retro_start_index(before, retro_chars);
|
||||
let grabbed = before[start_byte..].to_string();
|
||||
let looks_pastey =
|
||||
grabbed.chars().any(|c| c.is_whitespace()) || grabbed.chars().count() >= 16;
|
||||
if looks_pastey {
|
||||
// Note: caller is responsible for removing this slice from UI text.
|
||||
self.begin_with_retro_grabbed(grabbed.clone(), now);
|
||||
Some(RetroGrab {
|
||||
start_byte,
|
||||
grabbed,
|
||||
})
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
/// Before applying modified/non-char input: flush buffered burst immediately.
|
||||
pub fn flush_before_modified_input(&mut self) -> Option<String> {
|
||||
if self.is_active() {
|
||||
self.active = false;
|
||||
Some(std::mem::take(&mut self.buffer))
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
/// Clear only the timing window and any pending first-char.
|
||||
///
|
||||
/// Does not emit or clear the buffered text itself; callers should have
|
||||
/// already flushed (if needed) via one of the flush methods above.
|
||||
pub fn clear_window_after_non_char(&mut self) {
|
||||
self.consecutive_plain_char_burst = 0;
|
||||
self.last_plain_char_time = None;
|
||||
self.burst_window_until = None;
|
||||
self.active = false;
|
||||
self.pending_first_char = None;
|
||||
}
|
||||
|
||||
/// Returns true if we are in any paste-burst related transient state
|
||||
/// (actively buffering, have a non-empty buffer, or have saved the first
|
||||
/// fast char while waiting for a potential burst).
|
||||
pub fn is_active(&self) -> bool {
|
||||
self.is_active_internal() || self.pending_first_char.is_some()
|
||||
}
|
||||
|
||||
fn is_active_internal(&self) -> bool {
|
||||
self.active || !self.buffer.is_empty()
|
||||
}
|
||||
|
||||
pub fn clear_after_explicit_paste(&mut self) {
|
||||
self.last_plain_char_time = None;
|
||||
self.consecutive_plain_char_burst = 0;
|
||||
self.burst_window_until = None;
|
||||
self.active = false;
|
||||
self.buffer.clear();
|
||||
self.pending_first_char = None;
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn retro_start_index(before: &str, retro_chars: usize) -> usize {
|
||||
if retro_chars == 0 {
|
||||
return before.len();
|
||||
}
|
||||
before
|
||||
.char_indices()
|
||||
.rev()
|
||||
.nth(retro_chars.saturating_sub(1))
|
||||
.map(|(idx, _)| idx)
|
||||
.unwrap_or(0)
|
||||
}
|
||||
@@ -1,59 +0,0 @@
|
||||
use crossterm::event::KeyCode;
|
||||
use crossterm::event::KeyEvent;
|
||||
use ratatui::buffer::Buffer;
|
||||
use ratatui::widgets::WidgetRef;
|
||||
|
||||
use crate::app_event_sender::AppEventSender;
|
||||
use crate::bottom_pane::BottomPane;
|
||||
use crate::status_indicator_widget::StatusIndicatorWidget;
|
||||
use crate::tui::FrameRequester;
|
||||
|
||||
use super::BottomPaneView;
|
||||
|
||||
pub(crate) struct StatusIndicatorView {
|
||||
view: StatusIndicatorWidget,
|
||||
}
|
||||
|
||||
impl StatusIndicatorView {
|
||||
pub fn new(app_event_tx: AppEventSender, frame_requester: FrameRequester) -> Self {
|
||||
Self {
|
||||
view: StatusIndicatorWidget::new(app_event_tx, frame_requester),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn update_text(&mut self, text: String) {
|
||||
self.view.update_text(text);
|
||||
}
|
||||
|
||||
pub fn update_header(&mut self, header: String) {
|
||||
self.view.update_header(header);
|
||||
}
|
||||
}
|
||||
|
||||
impl BottomPaneView for StatusIndicatorView {
|
||||
fn update_status_header(&mut self, header: String) {
|
||||
self.update_header(header);
|
||||
}
|
||||
|
||||
fn should_hide_when_task_is_done(&mut self) -> bool {
|
||||
true
|
||||
}
|
||||
|
||||
fn desired_height(&self, width: u16) -> u16 {
|
||||
self.view.desired_height(width)
|
||||
}
|
||||
|
||||
fn render(&self, area: ratatui::layout::Rect, buf: &mut Buffer) {
|
||||
self.view.render_ref(area, buf);
|
||||
}
|
||||
|
||||
fn handle_key_event(&mut self, _pane: &mut BottomPane, key_event: KeyEvent) {
|
||||
if key_event.code == KeyCode::Esc {
|
||||
self.view.interrupt();
|
||||
}
|
||||
}
|
||||
|
||||
fn update_status_text(&mut self, text: String) {
|
||||
self.update_text(text);
|
||||
}
|
||||
}
|
||||
@@ -231,6 +231,13 @@ impl TextArea {
|
||||
code: KeyCode::Enter,
|
||||
..
|
||||
} => self.insert_str("\n"),
|
||||
KeyEvent {
|
||||
code: KeyCode::Char('h'),
|
||||
modifiers,
|
||||
..
|
||||
} if modifiers == (KeyModifiers::CONTROL | KeyModifiers::ALT) => {
|
||||
self.delete_backward_word()
|
||||
},
|
||||
KeyEvent {
|
||||
code: KeyCode::Backspace,
|
||||
modifiers: KeyModifiers::ALT,
|
||||
@@ -1138,10 +1145,6 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn control_b_and_f_move_cursor() {
|
||||
use crossterm::event::KeyCode;
|
||||
use crossterm::event::KeyEvent;
|
||||
use crossterm::event::KeyModifiers;
|
||||
|
||||
let mut t = ta_with("abcd");
|
||||
t.set_cursor(1);
|
||||
|
||||
@@ -1154,10 +1157,6 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn control_b_f_fallback_control_chars_move_cursor() {
|
||||
use crossterm::event::KeyCode;
|
||||
use crossterm::event::KeyEvent;
|
||||
use crossterm::event::KeyModifiers;
|
||||
|
||||
let mut t = ta_with("abcd");
|
||||
t.set_cursor(2);
|
||||
|
||||
@@ -1171,6 +1170,48 @@ mod tests {
|
||||
assert_eq!(t.cursor(), 2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn delete_backward_word_alt_keys() {
|
||||
// Test the custom Alt+Ctrl+h binding
|
||||
let mut t = ta_with("hello world");
|
||||
t.set_cursor(t.text().len()); // cursor at the end
|
||||
t.input(KeyEvent::new(
|
||||
KeyCode::Char('h'),
|
||||
KeyModifiers::CONTROL | KeyModifiers::ALT,
|
||||
));
|
||||
assert_eq!(t.text(), "hello ");
|
||||
assert_eq!(t.cursor(), 6);
|
||||
|
||||
// Test the standard Alt+Backspace binding
|
||||
let mut t = ta_with("hello world");
|
||||
t.set_cursor(t.text().len()); // cursor at the end
|
||||
t.input(KeyEvent::new(KeyCode::Backspace, KeyModifiers::ALT));
|
||||
assert_eq!(t.text(), "hello ");
|
||||
assert_eq!(t.cursor(), 6);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn control_h_backspace() {
|
||||
// Test Ctrl+H as backspace
|
||||
let mut t = ta_with("12345");
|
||||
t.set_cursor(3); // cursor after '3'
|
||||
t.input(KeyEvent::new(KeyCode::Char('h'), KeyModifiers::CONTROL));
|
||||
assert_eq!(t.text(), "1245");
|
||||
assert_eq!(t.cursor(), 2);
|
||||
|
||||
// Test Ctrl+H at beginning (should be no-op)
|
||||
t.set_cursor(0);
|
||||
t.input(KeyEvent::new(KeyCode::Char('h'), KeyModifiers::CONTROL));
|
||||
assert_eq!(t.text(), "1245");
|
||||
assert_eq!(t.cursor(), 0);
|
||||
|
||||
// Test Ctrl+H at end
|
||||
t.set_cursor(t.text().len());
|
||||
t.input(KeyEvent::new(KeyCode::Char('h'), KeyModifiers::CONTROL));
|
||||
assert_eq!(t.text(), "124");
|
||||
assert_eq!(t.cursor(), 3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cursor_vertical_movement_across_lines_and_bounds() {
|
||||
let mut t = ta_with("short\nloooooooooong\nmid");
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
use std::collections::HashMap;
|
||||
use std::collections::VecDeque;
|
||||
use std::path::PathBuf;
|
||||
use std::sync::Arc;
|
||||
|
||||
@@ -18,6 +19,7 @@ use codex_core::protocol::ExecApprovalRequestEvent;
|
||||
use codex_core::protocol::ExecCommandBeginEvent;
|
||||
use codex_core::protocol::ExecCommandEndEvent;
|
||||
use codex_core::protocol::InputItem;
|
||||
use codex_core::protocol::ListCustomPromptsResponseEvent;
|
||||
use codex_core::protocol::McpListToolsResponseEvent;
|
||||
use codex_core::protocol::McpToolCallBeginEvent;
|
||||
use codex_core::protocol::McpToolCallEndEvent;
|
||||
@@ -29,9 +31,12 @@ use codex_core::protocol::TokenUsage;
|
||||
use codex_core::protocol::TurnAbortReason;
|
||||
use codex_core::protocol::TurnDiffEvent;
|
||||
use codex_core::protocol::WebSearchBeginEvent;
|
||||
use codex_core::protocol::WebSearchEndEvent;
|
||||
use codex_protocol::parse_command::ParsedCommand;
|
||||
use crossterm::event::KeyCode;
|
||||
use crossterm::event::KeyEvent;
|
||||
use crossterm::event::KeyEventKind;
|
||||
use crossterm::event::KeyModifiers;
|
||||
use rand::Rng;
|
||||
use ratatui::buffer::Buffer;
|
||||
use ratatui::layout::Constraint;
|
||||
@@ -100,8 +105,6 @@ pub(crate) struct ChatWidget {
|
||||
task_complete_pending: bool,
|
||||
// Queue of interruptive UI events deferred during an active write cycle
|
||||
interrupts: InterruptManager,
|
||||
// Whether a redraw is needed after handling the current event
|
||||
needs_redraw: bool,
|
||||
// Accumulates the current reasoning block text to extract a header
|
||||
reasoning_buffer: String,
|
||||
// Accumulates full reasoning content for transcript-only recording
|
||||
@@ -111,6 +114,8 @@ pub(crate) struct ChatWidget {
|
||||
// Whether to include the initial welcome banner on session configured
|
||||
show_welcome_banner: bool,
|
||||
last_history_was_exec: bool,
|
||||
// User messages queued while a turn is in progress
|
||||
queued_user_messages: VecDeque<UserMessage>,
|
||||
}
|
||||
|
||||
struct UserMessage {
|
||||
@@ -136,10 +141,6 @@ fn create_initial_user_message(text: String, image_paths: Vec<PathBuf>) -> Optio
|
||||
}
|
||||
|
||||
impl ChatWidget {
|
||||
#[inline]
|
||||
fn mark_needs_redraw(&mut self) {
|
||||
self.needs_redraw = true;
|
||||
}
|
||||
fn flush_answer_stream_with_separator(&mut self) {
|
||||
let sink = AppEventHistorySink(self.app_event_tx.clone());
|
||||
let _ = self.stream.finalize(true, &sink);
|
||||
@@ -154,17 +155,19 @@ impl ChatWidget {
|
||||
event,
|
||||
self.show_welcome_banner,
|
||||
));
|
||||
// Ask codex-core to enumerate custom prompts for this session.
|
||||
self.submit_op(Op::ListCustomPrompts);
|
||||
if let Some(user_message) = self.initial_user_message.take() {
|
||||
self.submit_user_message(user_message);
|
||||
}
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
fn on_agent_message(&mut self, message: String) {
|
||||
let sink = AppEventHistorySink(self.app_event_tx.clone());
|
||||
let finished = self.stream.apply_final_answer(&message, &sink);
|
||||
self.handle_if_stream_finished(finished);
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
fn on_agent_message_delta(&mut self, delta: String) {
|
||||
@@ -183,7 +186,7 @@ impl ChatWidget {
|
||||
} else {
|
||||
// Fallback while we don't yet have a bold header: leave existing header as-is.
|
||||
}
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
fn on_agent_reasoning_final(&mut self) {
|
||||
@@ -197,7 +200,7 @@ impl ChatWidget {
|
||||
}
|
||||
self.reasoning_buffer.clear();
|
||||
self.full_reasoning_buffer.clear();
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
fn on_reasoning_section_break(&mut self) {
|
||||
@@ -215,7 +218,7 @@ impl ChatWidget {
|
||||
self.stream.reset_headers_for_new_turn();
|
||||
self.full_reasoning_buffer.clear();
|
||||
self.reasoning_buffer.clear();
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
fn on_task_complete(&mut self) {
|
||||
@@ -228,7 +231,10 @@ impl ChatWidget {
|
||||
// Mark task stopped and request redraw now that all content is in history.
|
||||
self.bottom_pane.set_task_running(false);
|
||||
self.running_commands.clear();
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
|
||||
// If there is a queued user message, send exactly one now to begin the next turn.
|
||||
self.maybe_send_next_queued_input();
|
||||
}
|
||||
|
||||
fn on_token_count(&mut self, token_usage: TokenUsage) {
|
||||
@@ -241,12 +247,49 @@ impl ChatWidget {
|
||||
);
|
||||
}
|
||||
|
||||
fn on_error(&mut self, message: String) {
|
||||
/// Finalize any active exec as failed, push an error message into history,
|
||||
/// and stop/clear running UI state.
|
||||
fn finalize_turn_with_error_message(&mut self, message: String) {
|
||||
// Ensure any spinner is replaced by a red ✗ and flushed into history.
|
||||
self.finalize_active_exec_cell_as_failed();
|
||||
// Emit the provided error message/history cell.
|
||||
self.add_to_history(history_cell::new_error_event(message));
|
||||
// Reset running state and clear streaming buffers.
|
||||
self.bottom_pane.set_task_running(false);
|
||||
self.running_commands.clear();
|
||||
self.stream.clear_all();
|
||||
self.mark_needs_redraw();
|
||||
}
|
||||
|
||||
fn on_error(&mut self, message: String) {
|
||||
self.finalize_turn_with_error_message(message);
|
||||
self.request_redraw();
|
||||
|
||||
// After an error ends the turn, try sending the next queued input.
|
||||
self.maybe_send_next_queued_input();
|
||||
}
|
||||
|
||||
/// Handle a turn aborted due to user interrupt (Esc).
|
||||
/// When there are queued user messages, restore them into the composer
|
||||
/// separated by newlines rather than auto‑submitting the next one.
|
||||
fn on_interrupted_turn(&mut self) {
|
||||
// Finalize, log a gentle prompt, and clear running state.
|
||||
self.finalize_turn_with_error_message("Tell the model what to do differently".to_owned());
|
||||
|
||||
// If any messages were queued during the task, restore them into the composer.
|
||||
if !self.queued_user_messages.is_empty() {
|
||||
let combined = self
|
||||
.queued_user_messages
|
||||
.iter()
|
||||
.map(|m| m.text.clone())
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n");
|
||||
self.bottom_pane.set_composer_text(combined);
|
||||
// Clear the queue and update the status indicator list.
|
||||
self.queued_user_messages.clear();
|
||||
self.refresh_queued_user_messages();
|
||||
}
|
||||
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
fn on_plan_update(&mut self, update: codex_core::plan_tool::UpdatePlanArgs) {
|
||||
@@ -316,9 +359,16 @@ impl ChatWidget {
|
||||
self.defer_or_handle(|q| q.push_mcp_end(ev), |s| s.handle_mcp_end_now(ev2));
|
||||
}
|
||||
|
||||
fn on_web_search_begin(&mut self, ev: WebSearchBeginEvent) {
|
||||
fn on_web_search_begin(&mut self, _ev: WebSearchBeginEvent) {
|
||||
self.flush_answer_stream_with_separator();
|
||||
self.add_to_history(history_cell::new_web_search_call(ev.query));
|
||||
}
|
||||
|
||||
fn on_web_search_end(&mut self, ev: WebSearchEndEvent) {
|
||||
self.flush_answer_stream_with_separator();
|
||||
self.add_to_history(history_cell::new_web_search_call(format!(
|
||||
"Searched: {}",
|
||||
ev.query
|
||||
)));
|
||||
}
|
||||
|
||||
fn on_get_history_entry_response(
|
||||
@@ -349,7 +399,7 @@ impl ChatWidget {
|
||||
fn on_stream_error(&mut self, message: String) {
|
||||
// Show stream errors in the transcript so users see retry/backoff info.
|
||||
self.add_to_history(history_cell::new_stream_error_event(message));
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
/// Periodic tick to commit at most one queued line to history with a small delay,
|
||||
/// animating the output.
|
||||
@@ -403,7 +453,7 @@ impl ChatWidget {
|
||||
let sink = AppEventHistorySink(self.app_event_tx.clone());
|
||||
self.stream.begin(&sink);
|
||||
self.stream.push_and_maybe_commit(&delta, &sink);
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn handle_exec_end_now(&mut self, ev: ExecCommandEndEvent) {
|
||||
@@ -461,7 +511,7 @@ impl ChatWidget {
|
||||
reason: ev.reason,
|
||||
};
|
||||
self.bottom_pane.push_approval_request(request);
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn handle_apply_patch_approval_now(
|
||||
@@ -481,7 +531,7 @@ impl ChatWidget {
|
||||
grant_root: ev.grant_root,
|
||||
};
|
||||
self.bottom_pane.push_approval_request(request);
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn handle_exec_begin_now(&mut self, ev: ExecCommandBeginEvent) {
|
||||
@@ -509,7 +559,7 @@ impl ChatWidget {
|
||||
}
|
||||
|
||||
// Request a redraw so the working header and command list are visible immediately.
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn handle_mcp_begin_now(&mut self, ev: McpToolCallBeginEvent) {
|
||||
@@ -529,17 +579,7 @@ impl ChatWidget {
|
||||
ev.result,
|
||||
));
|
||||
}
|
||||
fn interrupt_running_task(&mut self) {
|
||||
if self.bottom_pane.is_task_running() {
|
||||
self.active_exec_cell = None;
|
||||
self.running_commands.clear();
|
||||
self.bottom_pane.clear_ctrl_c_quit_hint();
|
||||
self.submit_op(Op::Interrupt);
|
||||
self.bottom_pane.set_task_running(false);
|
||||
self.stream.clear_all();
|
||||
self.request_redraw();
|
||||
}
|
||||
}
|
||||
|
||||
fn layout_areas(&self, area: Rect) -> [Rect; 2] {
|
||||
Layout::vertical([
|
||||
Constraint::Max(
|
||||
@@ -575,6 +615,7 @@ impl ChatWidget {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported,
|
||||
placeholder_text: placeholder,
|
||||
disable_paste_burst: config.disable_paste_burst,
|
||||
}),
|
||||
active_exec_cell: None,
|
||||
config: config.clone(),
|
||||
@@ -589,11 +630,11 @@ impl ChatWidget {
|
||||
pending_exec_completions: Vec::new(),
|
||||
task_complete_pending: false,
|
||||
interrupts: InterruptManager::new(),
|
||||
needs_redraw: false,
|
||||
reasoning_buffer: String::new(),
|
||||
full_reasoning_buffer: String::new(),
|
||||
session_id: None,
|
||||
last_history_was_exec: false,
|
||||
queued_user_messages: VecDeque::new(),
|
||||
show_welcome_banner: true,
|
||||
}
|
||||
}
|
||||
@@ -623,6 +664,7 @@ impl ChatWidget {
|
||||
has_input_focus: true,
|
||||
enhanced_keys_supported,
|
||||
placeholder_text: placeholder,
|
||||
disable_paste_burst: config.disable_paste_burst,
|
||||
}),
|
||||
active_exec_cell: None,
|
||||
config: config.clone(),
|
||||
@@ -634,11 +676,11 @@ impl ChatWidget {
|
||||
pending_exec_completions: Vec::new(),
|
||||
task_complete_pending: false,
|
||||
interrupts: InterruptManager::new(),
|
||||
needs_redraw: false,
|
||||
reasoning_buffer: String::new(),
|
||||
full_reasoning_buffer: String::new(),
|
||||
session_id: None,
|
||||
last_history_was_exec: false,
|
||||
queued_user_messages: VecDeque::new(),
|
||||
show_welcome_banner: false,
|
||||
}
|
||||
}
|
||||
@@ -652,22 +694,57 @@ impl ChatWidget {
|
||||
}
|
||||
|
||||
pub(crate) fn handle_key_event(&mut self, key_event: KeyEvent) {
|
||||
if key_event.kind == KeyEventKind::Press {
|
||||
self.bottom_pane.clear_ctrl_c_quit_hint();
|
||||
match key_event {
|
||||
KeyEvent {
|
||||
code: KeyCode::Char('c'),
|
||||
modifiers: crossterm::event::KeyModifiers::CONTROL,
|
||||
kind: KeyEventKind::Press,
|
||||
..
|
||||
} => {
|
||||
self.on_ctrl_c();
|
||||
return;
|
||||
}
|
||||
other if other.kind == KeyEventKind::Press => {
|
||||
self.bottom_pane.clear_ctrl_c_quit_hint();
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
|
||||
match self.bottom_pane.handle_key_event(key_event) {
|
||||
InputResult::Submitted(text) => {
|
||||
let images = self.bottom_pane.take_recent_submission_images();
|
||||
self.submit_user_message(UserMessage {
|
||||
text,
|
||||
image_paths: images,
|
||||
});
|
||||
match key_event {
|
||||
KeyEvent {
|
||||
code: KeyCode::Up,
|
||||
modifiers: KeyModifiers::ALT,
|
||||
kind: KeyEventKind::Press,
|
||||
..
|
||||
} if !self.queued_user_messages.is_empty() => {
|
||||
// Prefer the most recently queued item.
|
||||
if let Some(user_message) = self.queued_user_messages.pop_back() {
|
||||
self.bottom_pane.set_composer_text(user_message.text);
|
||||
self.refresh_queued_user_messages();
|
||||
self.request_redraw();
|
||||
}
|
||||
}
|
||||
InputResult::Command(cmd) => {
|
||||
self.dispatch_command(cmd);
|
||||
_ => {
|
||||
match self.bottom_pane.handle_key_event(key_event) {
|
||||
InputResult::Submitted(text) => {
|
||||
// If a task is running, queue the user input to be sent after the turn completes.
|
||||
let user_message = UserMessage {
|
||||
text,
|
||||
image_paths: self.bottom_pane.take_recent_submission_images(),
|
||||
};
|
||||
if self.bottom_pane.is_task_running() {
|
||||
self.queued_user_messages.push_back(user_message);
|
||||
self.refresh_queued_user_messages();
|
||||
} else {
|
||||
self.submit_user_message(user_message);
|
||||
}
|
||||
}
|
||||
InputResult::Command(cmd) => {
|
||||
self.dispatch_command(cmd);
|
||||
}
|
||||
InputResult::None => {}
|
||||
}
|
||||
}
|
||||
InputResult::None => {}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -687,12 +764,20 @@ impl ChatWidget {
|
||||
}
|
||||
|
||||
fn dispatch_command(&mut self, cmd: SlashCommand) {
|
||||
if !cmd.available_during_task() && self.bottom_pane.is_task_running() {
|
||||
let message = format!(
|
||||
"'/'{}' is disabled while a task is in progress.",
|
||||
cmd.command()
|
||||
);
|
||||
self.add_to_history(history_cell::new_error_event(message));
|
||||
self.request_redraw();
|
||||
return;
|
||||
}
|
||||
match cmd {
|
||||
SlashCommand::New => {
|
||||
self.app_event_tx.send(AppEvent::NewSession);
|
||||
}
|
||||
SlashCommand::Init => {
|
||||
// Guard: do not run if a task is active.
|
||||
const INIT_PROMPT: &str = include_str!("../prompt_for_init_command.md");
|
||||
self.submit_text_message(INIT_PROMPT.to_string());
|
||||
}
|
||||
@@ -786,6 +871,24 @@ impl ChatWidget {
|
||||
self.bottom_pane.handle_paste(text);
|
||||
}
|
||||
|
||||
// Returns true if caller should skip rendering this frame (a future frame is scheduled).
|
||||
pub(crate) fn handle_paste_burst_tick(&mut self, frame_requester: FrameRequester) -> bool {
|
||||
if self.bottom_pane.flush_paste_burst_if_due() {
|
||||
// A paste just flushed; request an immediate redraw and skip this frame.
|
||||
self.request_redraw();
|
||||
true
|
||||
} else if self.bottom_pane.is_in_paste_burst() {
|
||||
// While capturing a burst, schedule a follow-up tick and skip this frame
|
||||
// to avoid redundant renders between ticks.
|
||||
frame_requester.schedule_frame_in(
|
||||
crate::bottom_pane::ChatComposer::recommended_paste_flush_delay(),
|
||||
);
|
||||
true
|
||||
} else {
|
||||
false
|
||||
}
|
||||
}
|
||||
|
||||
fn flush_active_exec_cell(&mut self) {
|
||||
if let Some(active) = self.active_exec_cell.take() {
|
||||
self.last_history_was_exec = true;
|
||||
@@ -848,8 +951,6 @@ impl ChatWidget {
|
||||
}
|
||||
|
||||
pub(crate) fn handle_codex_event(&mut self, event: Event) {
|
||||
// Reset redraw flag for this dispatch
|
||||
self.needs_redraw = false;
|
||||
let Event { id, msg } = event;
|
||||
|
||||
match msg {
|
||||
@@ -876,13 +977,13 @@ impl ChatWidget {
|
||||
self.on_agent_reasoning_final()
|
||||
}
|
||||
EventMsg::AgentReasoningSectionBreak(_) => self.on_reasoning_section_break(),
|
||||
EventMsg::TaskStarted => self.on_task_started(),
|
||||
EventMsg::TaskStarted(_) => self.on_task_started(),
|
||||
EventMsg::TaskComplete(TaskCompleteEvent { .. }) => self.on_task_complete(),
|
||||
EventMsg::TokenCount(token_usage) => self.on_token_count(token_usage),
|
||||
EventMsg::Error(ErrorEvent { message }) => self.on_error(message),
|
||||
EventMsg::TurnAborted(ev) => match ev.reason {
|
||||
TurnAbortReason::Interrupted => {
|
||||
self.on_error("Tell the model what to do differently".to_owned())
|
||||
self.on_interrupted_turn();
|
||||
}
|
||||
TurnAbortReason::Replaced => {
|
||||
self.on_error("Turn aborted: replaced by a new task".to_owned())
|
||||
@@ -899,8 +1000,10 @@ impl ChatWidget {
|
||||
EventMsg::McpToolCallBegin(ev) => self.on_mcp_tool_call_begin(ev),
|
||||
EventMsg::McpToolCallEnd(ev) => self.on_mcp_tool_call_end(ev),
|
||||
EventMsg::WebSearchBegin(ev) => self.on_web_search_begin(ev),
|
||||
EventMsg::WebSearchEnd(ev) => self.on_web_search_end(ev),
|
||||
EventMsg::GetHistoryEntryResponse(ev) => self.on_get_history_entry_response(ev),
|
||||
EventMsg::McpListToolsResponse(ev) => self.on_list_mcp_tools(ev),
|
||||
EventMsg::ListCustomPromptsResponse(ev) => self.on_list_custom_prompts(ev),
|
||||
EventMsg::ShutdownComplete => self.on_shutdown_complete(),
|
||||
EventMsg::TurnDiff(TurnDiffEvent { unified_diff }) => self.on_turn_diff(unified_diff),
|
||||
EventMsg::BackgroundEvent(BackgroundEventEvent { message }) => {
|
||||
@@ -913,27 +1016,50 @@ impl ChatWidget {
|
||||
.send(crate::app_event::AppEvent::ConversationHistory(ev));
|
||||
}
|
||||
}
|
||||
// Coalesce redraws: issue at most one after handling the event
|
||||
if self.needs_redraw {
|
||||
self.request_redraw();
|
||||
self.needs_redraw = false;
|
||||
}
|
||||
}
|
||||
|
||||
fn request_redraw(&mut self) {
|
||||
self.frame_requester.schedule_frame();
|
||||
}
|
||||
|
||||
/// Mark the active exec cell as failed (✗) and flush it into history.
|
||||
fn finalize_active_exec_cell_as_failed(&mut self) {
|
||||
if let Some(cell) = self.active_exec_cell.take() {
|
||||
let cell = cell.into_failed();
|
||||
// Insert finalized exec into history and keep grouping consistent.
|
||||
self.add_to_history(cell);
|
||||
self.last_history_was_exec = true;
|
||||
}
|
||||
}
|
||||
|
||||
// If idle and there are queued inputs, submit exactly one to start the next turn.
|
||||
fn maybe_send_next_queued_input(&mut self) {
|
||||
if self.bottom_pane.is_task_running() {
|
||||
return;
|
||||
}
|
||||
if let Some(user_message) = self.queued_user_messages.pop_front() {
|
||||
self.submit_user_message(user_message);
|
||||
}
|
||||
// Update the list to reflect the remaining queued messages (if any).
|
||||
self.refresh_queued_user_messages();
|
||||
}
|
||||
|
||||
/// Rebuild and update the queued user messages from the current queue.
|
||||
fn refresh_queued_user_messages(&mut self) {
|
||||
let messages: Vec<String> = self
|
||||
.queued_user_messages
|
||||
.iter()
|
||||
.map(|m| m.text.clone())
|
||||
.collect();
|
||||
self.bottom_pane.set_queued_user_messages(messages);
|
||||
}
|
||||
|
||||
pub(crate) fn add_diff_in_progress(&mut self) {
|
||||
self.bottom_pane.set_task_running(true);
|
||||
self.bottom_pane
|
||||
.update_status_text("computing diff".to_string());
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn on_diff_complete(&mut self) {
|
||||
self.bottom_pane.set_task_running(false);
|
||||
self.mark_needs_redraw();
|
||||
self.request_redraw();
|
||||
}
|
||||
|
||||
pub(crate) fn add_status_output(&mut self) {
|
||||
@@ -1060,22 +1186,15 @@ impl ChatWidget {
|
||||
}
|
||||
|
||||
/// Handle Ctrl-C key press.
|
||||
/// Returns CancellationEvent::Handled if the event was consumed by the UI, or
|
||||
/// CancellationEvent::Ignored if the caller should handle it (e.g. exit).
|
||||
pub(crate) fn on_ctrl_c(&mut self) -> CancellationEvent {
|
||||
match self.bottom_pane.on_ctrl_c() {
|
||||
CancellationEvent::Handled => return CancellationEvent::Handled,
|
||||
CancellationEvent::Ignored => {}
|
||||
}
|
||||
if self.bottom_pane.is_task_running() {
|
||||
self.interrupt_running_task();
|
||||
CancellationEvent::Ignored
|
||||
} else if self.bottom_pane.ctrl_c_quit_hint_visible() {
|
||||
self.submit_op(Op::Shutdown);
|
||||
CancellationEvent::Handled
|
||||
} else {
|
||||
self.bottom_pane.show_ctrl_c_quit_hint();
|
||||
CancellationEvent::Ignored
|
||||
fn on_ctrl_c(&mut self) {
|
||||
if self.bottom_pane.on_ctrl_c() == CancellationEvent::Ignored {
|
||||
if self.bottom_pane.is_task_running() {
|
||||
self.submit_op(Op::Interrupt);
|
||||
} else if self.bottom_pane.ctrl_c_quit_hint_visible() {
|
||||
self.submit_op(Op::Shutdown);
|
||||
} else {
|
||||
self.bottom_pane.show_ctrl_c_quit_hint();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1083,6 +1202,13 @@ impl ChatWidget {
|
||||
self.bottom_pane.composer_is_empty()
|
||||
}
|
||||
|
||||
/// True when the UI is in the regular composer state with no running task,
|
||||
/// no modal overlay (e.g. approvals or status indicator), and no composer popups.
|
||||
/// In this state Esc-Esc backtracking is enabled.
|
||||
pub(crate) fn is_normal_backtrack_mode(&self) -> bool {
|
||||
self.bottom_pane.is_normal_backtrack_mode()
|
||||
}
|
||||
|
||||
pub(crate) fn insert_str(&mut self, text: &str) {
|
||||
self.bottom_pane.insert_str(text);
|
||||
}
|
||||
@@ -1107,6 +1233,13 @@ impl ChatWidget {
|
||||
self.add_to_history(history_cell::new_mcp_tools_output(&self.config, ev.tools));
|
||||
}
|
||||
|
||||
fn on_list_custom_prompts(&mut self, ev: ListCustomPromptsResponseEvent) {
|
||||
let len = ev.custom_prompts.len();
|
||||
debug!("received {len} custom prompts");
|
||||
// Forward to bottom pane so the slash popup can show them now.
|
||||
self.bottom_pane.set_custom_prompts(ev.custom_prompts);
|
||||
}
|
||||
|
||||
/// Programmatically submit a user text message as if typed in the
|
||||
/// composer. The text will be added to conversation history and sent to
|
||||
/// the agent.
|
||||
|
||||
@@ -0,0 +1,13 @@
|
||||
---
|
||||
source: tui/src/chatwidget/tests.rs
|
||||
assertion_line: 728
|
||||
expression: terminal.backend()
|
||||
---
|
||||
"? Codex wants to run echo hello world "
|
||||
" "
|
||||
"Model wants to run a command "
|
||||
" "
|
||||
"▌Allow command? "
|
||||
"▌ Yes Always No, provide feedback "
|
||||
"▌ Approve and run the command "
|
||||
" "
|
||||
@@ -0,0 +1,13 @@
|
||||
---
|
||||
source: tui/src/chatwidget/tests.rs
|
||||
assertion_line: 763
|
||||
expression: terminal.backend()
|
||||
---
|
||||
"The model wants to apply changes "
|
||||
" "
|
||||
"This will grant write access to /tmp for the remainder of this session. "
|
||||
" "
|
||||
"▌Apply changes? "
|
||||
"▌ Yes No, provide feedback "
|
||||
"▌ Approve and apply the changes "
|
||||
" "
|
||||
@@ -0,0 +1,5 @@
|
||||
---
|
||||
source: tui/src/chatwidget/tests.rs
|
||||
expression: terminal.backend()
|
||||
---
|
||||
"▌ Ask Codex to do anything "
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user