Compare commits

..

1 Commits

Author SHA1 Message Date
Abhishek Bhardwaj
9518387ddb feature: Add "!cmd" user shell execution
- protocol: add Op::RunUserShellCommand to model a user-initiated one-off command
- core: handle new Op by spawning a cancellable task that runs the command using the user’s default shell; stream output via ExecCommand* events; send TaskStarted/TaskComplete; track as current_task so Interrupt works
- tui: detect leading '!' in composer submission and dispatch Op::RunUserShellCommand instead of sending a user message

No changes to sandbox env var behavior; uses existing exec pipeline and event types.
2025-09-13 17:24:18 -07:00
823 changed files with 8695 additions and 51801 deletions

View File

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

View File

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

View File

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

View File

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

View File

@@ -57,7 +57,7 @@ jobs:
working-directory: codex-rs
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
with:
components: rustfmt
- name: cargo fmt
@@ -75,7 +75,7 @@ jobs:
working-directory: codex-rs
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
- uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: cargo-shear
@@ -143,7 +143,7 @@ jobs:
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
with:
targets: ${{ matrix.target }}
components: clippy

View File

@@ -77,7 +77,7 @@ jobs:
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: dtolnay/rust-toolchain@1.89
with:
targets: ${{ matrix.target }}
@@ -97,7 +97,7 @@ jobs:
sudo apt install -y musl-tools pkg-config
- name: Cargo build
run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
run: cargo build --target ${{ matrix.target }} --release --bin codex
- name: Stage artifacts
shell: bash
@@ -107,10 +107,8 @@ jobs:
if [[ "${{ matrix.runner }}" == windows* ]]; then
cp target/${{ matrix.target }}/release/codex.exe "$dest/codex-${{ matrix.target }}.exe"
cp target/${{ matrix.target }}/release/codex-responses-api-proxy.exe "$dest/codex-responses-api-proxy-${{ matrix.target }}.exe"
else
cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
cp target/${{ matrix.target }}/release/codex-responses-api-proxy "$dest/codex-responses-api-proxy-${{ matrix.target }}"
fi
- if: ${{ matrix.runner == 'windows-11-arm' }}
@@ -169,14 +167,6 @@ jobs:
needs: build
name: release
runs-on: ubuntu-latest
permissions:
contents: write
actions: read
outputs:
version: ${{ steps.release_name.outputs.name }}
tag: ${{ github.ref_name }}
should_publish_npm: ${{ steps.npm_publish_settings.outputs.should_publish }}
npm_tag: ${{ steps.npm_publish_settings.outputs.npm_tag }}
steps:
- name: Checkout repository
@@ -197,50 +187,21 @@ jobs:
version="${GITHUB_REF_NAME#rust-v}"
echo "name=${version}" >> $GITHUB_OUTPUT
- name: Determine npm publish settings
id: npm_publish_settings
env:
VERSION: ${{ steps.release_name.outputs.name }}
run: |
set -euo pipefail
version="${VERSION}"
if [[ "${version}" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
echo "should_publish=true" >> "$GITHUB_OUTPUT"
echo "npm_tag=" >> "$GITHUB_OUTPUT"
elif [[ "${version}" =~ ^[0-9]+\.[0-9]+\.[0-9]+-alpha\.[0-9]+$ ]]; then
echo "should_publish=true" >> "$GITHUB_OUTPUT"
echo "npm_tag=alpha" >> "$GITHUB_OUTPUT"
else
echo "should_publish=false" >> "$GITHUB_OUTPUT"
echo "npm_tag=" >> "$GITHUB_OUTPUT"
fi
# build_npm_package.py requires DotSlash when staging releases.
- uses: facebook/install-dotslash@v2
- name: Stage codex CLI npm package
- name: Stage npm package
env:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
TMP_DIR="${RUNNER_TEMP}/npm-stage"
./codex-cli/scripts/build_npm_package.py \
--package codex \
python3 codex-cli/scripts/stage_rust_release.py \
--release-version "${{ steps.release_name.outputs.name }}" \
--staging-dir "${TMP_DIR}" \
--pack-output "${GITHUB_WORKSPACE}/dist/npm/codex-npm-${{ steps.release_name.outputs.name }}.tgz"
- name: Stage responses API proxy npm package
env:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
TMP_DIR="${RUNNER_TEMP}/npm-stage-responses"
./codex-cli/scripts/build_npm_package.py \
--package codex-responses-api-proxy \
--release-version "${{ steps.release_name.outputs.name }}" \
--staging-dir "${TMP_DIR}" \
--pack-output "${GITHUB_WORKSPACE}/dist/npm/codex-responses-api-proxy-npm-${{ steps.release_name.outputs.name }}.tgz"
--tmp "${TMP_DIR}"
mkdir -p dist/npm
# Produce an npm-ready tarball using `npm pack` and store it in dist/npm.
# We then rename it to a stable name used by our publishing script.
(cd "$TMP_DIR" && npm pack --pack-destination "${GITHUB_WORKSPACE}/dist/npm")
mv "${GITHUB_WORKSPACE}"/dist/npm/*.tgz \
"${GITHUB_WORKSPACE}/dist/npm/codex-npm-${{ steps.release_name.outputs.name }}.tgz"
- name: Create GitHub Release
uses: softprops/action-gh-release@v2
@@ -259,69 +220,6 @@ jobs:
tag: ${{ github.ref_name }}
config: .github/dotslash-config.json
# Publish to npm using OIDC authentication.
# July 31, 2025: https://github.blog/changelog/2025-07-31-npm-trusted-publishing-with-oidc-is-generally-available/
# npm docs: https://docs.npmjs.com/trusted-publishers
publish-npm:
# Publish to npm for stable releases and alpha pre-releases with numeric suffixes.
if: ${{ needs.release.outputs.should_publish_npm == 'true' }}
name: publish-npm
needs: release
runs-on: ubuntu-latest
permissions:
id-token: write # Required for OIDC
contents: read
steps:
- name: Setup Node.js
uses: actions/setup-node@v5
with:
node-version: 22
registry-url: "https://registry.npmjs.org"
scope: "@openai"
# Trusted publishing requires npm CLI version 11.5.1 or later.
- name: Update npm
run: npm install -g npm@latest
- name: Download npm tarballs from release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
set -euo pipefail
version="${{ needs.release.outputs.version }}"
tag="${{ needs.release.outputs.tag }}"
mkdir -p dist/npm
gh release download "$tag" \
--repo "${GITHUB_REPOSITORY}" \
--pattern "codex-npm-${version}.tgz" \
--dir dist/npm
gh release download "$tag" \
--repo "${GITHUB_REPOSITORY}" \
--pattern "codex-responses-api-proxy-npm-${version}.tgz" \
--dir dist/npm
# No NODE_AUTH_TOKEN needed because we use OIDC.
- name: Publish to npm
env:
VERSION: ${{ needs.release.outputs.version }}
NPM_TAG: ${{ needs.release.outputs.npm_tag }}
run: |
set -euo pipefail
tag_args=()
if [[ -n "${NPM_TAG}" ]]; then
tag_args+=(--tag "${NPM_TAG}")
fi
tarballs=(
"codex-npm-${VERSION}.tgz"
"codex-responses-api-proxy-npm-${VERSION}.tgz"
)
for tarball in "${tarballs[@]}"; do
npm publish "${GITHUB_WORKSPACE}/dist/npm/${tarball}" "${tag_args[@]}"
done
update-branch:
name: Update latest-alpha-cli branch
permissions:

View File

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

View File

@@ -4,7 +4,6 @@ In the codex-rs folder where the rust code lives:
- Crate names are prefixed with `codex-`. For example, the `core` folder's crate is named `codex-core`
- When using format! and you can inline variables into {}, always do that.
- Install any commands the repo relies on (for example `just`, `rg`, or `cargo-insta`) if they aren't already available before running instructions here.
- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` or `CODEX_SANDBOX_ENV_VAR`.
- You operate in a sandbox where `CODEX_SANDBOX_NETWORK_DISABLED=1` will be set whenever you use the `shell` tool. Any existing code that uses `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` was authored with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations.
- Similarly, when you spawn a process using Seatbelt (`/usr/bin/sandbox-exec`), `CODEX_SANDBOX=seatbelt` will be set on the child process. Integration tests that want to run Seatbelt themselves cannot be run under Seatbelt, so checks for `CODEX_SANDBOX=seatbelt` are also often used to early exit out of tests, as appropriate.

View File

@@ -1,3 +1,4 @@
<h1 align="center">OpenAI Codex CLI</h1>
<p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>
@@ -101,3 +102,4 @@ Codex CLI supports a rich set of configuration options, with preferences stored
## License
This repository is licensed under the [Apache-2.0 License](LICENSE).

View File

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

View File

@@ -208,7 +208,7 @@ The hardening mechanism Codex uses depends on your OS:
| Requirement | Details |
| --------------------------- | --------------------------------------------------------------- |
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 **via WSL2** |
| Node.js | **16 or newer** (Node 20 LTS recommended) |
| Node.js | **22 or newer** (LTS recommended) |
| Git (optional, recommended) | 2.23+ for built-in PR helpers |
| RAM | 4-GB minimum (8-GB recommended) |
@@ -513,7 +513,7 @@ Codex runs model-generated commands in a sandbox. If a proposed command or file
<details>
<summary>Does it work on Windows?</summary>
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex is regularly tested on macOS and Linux with Node 20+, and also supports Node 16.
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex has been tested on macOS and Linux with Node 22.
</details>

View File

@@ -1,8 +1,6 @@
#!/usr/bin/env node
// Unified entry point for the Codex CLI.
import { spawn } from "node:child_process";
import { existsSync } from "fs";
import path from "path";
import { fileURLToPath } from "url";
@@ -42,10 +40,10 @@ switch (platform) {
case "win32":
switch (arch) {
case "x64":
targetTriple = "x86_64-pc-windows-msvc";
targetTriple = "x86_64-pc-windows-msvc.exe";
break;
case "arm64":
targetTriple = "aarch64-pc-windows-msvc";
targetTriple = "aarch64-pc-windows-msvc.exe";
break;
default:
break;
@@ -59,16 +57,31 @@ if (!targetTriple) {
throw new Error(`Unsupported platform: ${platform} (${arch})`);
}
const vendorRoot = path.join(__dirname, "..", "vendor");
const archRoot = path.join(vendorRoot, targetTriple);
const codexBinaryName = process.platform === "win32" ? "codex.exe" : "codex";
const binaryPath = path.join(archRoot, "codex", codexBinaryName);
const binaryPath = path.join(__dirname, "..", "bin", `codex-${targetTriple}`);
// Use an asynchronous spawn instead of spawnSync so that Node is able to
// respond to signals (e.g. Ctrl-C / SIGINT) while the native binary is
// executing. This allows us to forward those signals to the child process
// and guarantees that when either the child terminates or the parent
// receives a fatal signal, both processes exit in a predictable manner.
const { spawn } = await import("child_process");
async function tryImport(moduleName) {
try {
// eslint-disable-next-line node/no-unsupported-features/es-syntax
return await import(moduleName);
} catch (err) {
return null;
}
}
async function resolveRgDir() {
const ripgrep = await tryImport("@vscode/ripgrep");
if (!ripgrep?.rgPath) {
return null;
}
return path.dirname(ripgrep.rgPath);
}
function getUpdatedPath(newDirs) {
const pathSep = process.platform === "win32" ? ";" : ":";
@@ -81,9 +94,9 @@ function getUpdatedPath(newDirs) {
}
const additionalDirs = [];
const pathDir = path.join(archRoot, "path");
if (existsSync(pathDir)) {
additionalDirs.push(pathDir);
const rgDir = await resolveRgDir();
if (rgDir) {
additionalDirs.push(rgDir);
}
const updatedPath = getUpdatedPath(additionalDirs);

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,307 +0,0 @@
#!/usr/bin/env python3
"""Stage and optionally package the @openai/codex npm module."""
import argparse
import json
import re
import shutil
import subprocess
import sys
import tempfile
from pathlib import Path
SCRIPT_DIR = Path(__file__).resolve().parent
CODEX_CLI_ROOT = SCRIPT_DIR.parent
REPO_ROOT = CODEX_CLI_ROOT.parent
RESPONSES_API_PROXY_NPM_ROOT = REPO_ROOT / "codex-rs" / "responses-api-proxy" / "npm"
GITHUB_REPO = "openai/codex"
# The docs are not clear on what the expected value/format of
# workflow/workflowName is:
# https://cli.github.com/manual/gh_run_list
WORKFLOW_NAME = ".github/workflows/rust-release.yml"
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Build or stage the Codex CLI npm package.")
parser.add_argument(
"--package",
choices=("codex", "codex-responses-api-proxy"),
default="codex",
help="Which npm package to stage (default: codex).",
)
parser.add_argument(
"--version",
help="Version number to write to package.json inside the staged package.",
)
parser.add_argument(
"--release-version",
help=(
"Version to stage for npm release. When provided, the script also resolves the "
"matching rust-release workflow unless --workflow-url is supplied."
),
)
parser.add_argument(
"--workflow-url",
help="Optional GitHub Actions workflow run URL used to download native binaries.",
)
parser.add_argument(
"--staging-dir",
type=Path,
help=(
"Directory to stage the package contents. Defaults to a new temporary directory "
"if omitted. The directory must be empty when provided."
),
)
parser.add_argument(
"--tmp",
dest="staging_dir",
type=Path,
help=argparse.SUPPRESS,
)
parser.add_argument(
"--pack-output",
type=Path,
help="Path where the generated npm tarball should be written.",
)
return parser.parse_args()
def main() -> int:
args = parse_args()
package = args.package
version = args.version
release_version = args.release_version
if release_version:
if version and version != release_version:
raise RuntimeError("--version and --release-version must match when both are provided.")
version = release_version
if not version:
raise RuntimeError("Must specify --version or --release-version.")
staging_dir, created_temp = prepare_staging_dir(args.staging_dir)
try:
stage_sources(staging_dir, version, package)
workflow_url = args.workflow_url
resolved_head_sha: str | None = None
if not workflow_url:
if release_version:
workflow = resolve_release_workflow(version)
workflow_url = workflow["url"]
resolved_head_sha = workflow.get("headSha")
else:
workflow_url = resolve_latest_alpha_workflow_url()
elif release_version:
try:
workflow = resolve_release_workflow(version)
resolved_head_sha = workflow.get("headSha")
except Exception:
resolved_head_sha = None
if release_version and resolved_head_sha:
print(f"should `git checkout {resolved_head_sha}`")
if not workflow_url:
raise RuntimeError("Unable to determine workflow URL for native binaries.")
install_native_binaries(staging_dir, workflow_url, package)
if release_version:
staging_dir_str = str(staging_dir)
if package == "codex":
print(
f"Staged version {version} for release in {staging_dir_str}\n\n"
"Verify the CLI:\n"
f" node {staging_dir_str}/bin/codex.js --version\n"
f" node {staging_dir_str}/bin/codex.js --help\n\n"
)
else:
print(
f"Staged version {version} for release in {staging_dir_str}\n\n"
"Verify the responses API proxy:\n"
f" node {staging_dir_str}/bin/codex-responses-api-proxy.js --help\n\n"
)
else:
print(f"Staged package in {staging_dir}")
if args.pack_output is not None:
output_path = run_npm_pack(staging_dir, args.pack_output)
print(f"npm pack output written to {output_path}")
finally:
if created_temp:
# Preserve the staging directory for further inspection.
pass
return 0
def prepare_staging_dir(staging_dir: Path | None) -> tuple[Path, bool]:
if staging_dir is not None:
staging_dir = staging_dir.resolve()
staging_dir.mkdir(parents=True, exist_ok=True)
if any(staging_dir.iterdir()):
raise RuntimeError(f"Staging directory {staging_dir} is not empty.")
return staging_dir, False
temp_dir = Path(tempfile.mkdtemp(prefix="codex-npm-stage-"))
return temp_dir, True
def stage_sources(staging_dir: Path, version: str, package: str) -> None:
bin_dir = staging_dir / "bin"
bin_dir.mkdir(parents=True, exist_ok=True)
if package == "codex":
shutil.copy2(CODEX_CLI_ROOT / "bin" / "codex.js", bin_dir / "codex.js")
rg_manifest = CODEX_CLI_ROOT / "bin" / "rg"
if rg_manifest.exists():
shutil.copy2(rg_manifest, bin_dir / "rg")
readme_src = REPO_ROOT / "README.md"
if readme_src.exists():
shutil.copy2(readme_src, staging_dir / "README.md")
package_json_path = CODEX_CLI_ROOT / "package.json"
elif package == "codex-responses-api-proxy":
launcher_src = RESPONSES_API_PROXY_NPM_ROOT / "bin" / "codex-responses-api-proxy.js"
shutil.copy2(launcher_src, bin_dir / "codex-responses-api-proxy.js")
readme_src = RESPONSES_API_PROXY_NPM_ROOT / "README.md"
if readme_src.exists():
shutil.copy2(readme_src, staging_dir / "README.md")
package_json_path = RESPONSES_API_PROXY_NPM_ROOT / "package.json"
else:
raise RuntimeError(f"Unknown package '{package}'.")
with open(package_json_path, "r", encoding="utf-8") as fh:
package_json = json.load(fh)
package_json["version"] = version
with open(staging_dir / "package.json", "w", encoding="utf-8") as out:
json.dump(package_json, out, indent=2)
out.write("\n")
def install_native_binaries(staging_dir: Path, workflow_url: str, package: str) -> None:
package_components = {
"codex": ["codex", "rg"],
"codex-responses-api-proxy": ["codex-responses-api-proxy"],
}
components = package_components.get(package)
if components is None:
raise RuntimeError(f"Unknown package '{package}'.")
cmd = ["./scripts/install_native_deps.py", "--workflow-url", workflow_url]
for component in components:
cmd.extend(["--component", component])
cmd.append(str(staging_dir))
subprocess.check_call(cmd, cwd=CODEX_CLI_ROOT)
def resolve_latest_alpha_workflow_url() -> str:
version = determine_latest_alpha_version()
workflow = resolve_release_workflow(version)
return workflow["url"]
def determine_latest_alpha_version() -> str:
releases = list_releases()
best_key: tuple[int, int, int, int] | None = None
best_version: str | None = None
pattern = re.compile(r"^rust-v(\d+)\.(\d+)\.(\d+)-alpha\.(\d+)$")
for release in releases:
tag = release.get("tag_name", "")
match = pattern.match(tag)
if not match:
continue
key = tuple(int(match.group(i)) for i in range(1, 5))
if best_key is None or key > best_key:
best_key = key
best_version = (
f"{match.group(1)}.{match.group(2)}.{match.group(3)}-alpha.{match.group(4)}"
)
if best_version is None:
raise RuntimeError("No alpha releases found when resolving workflow URL.")
return best_version
def list_releases() -> list[dict]:
stdout = subprocess.check_output(
["gh", "api", f"/repos/{GITHUB_REPO}/releases?per_page=100"],
text=True,
)
try:
releases = json.loads(stdout or "[]")
except json.JSONDecodeError as exc:
raise RuntimeError("Unable to parse releases JSON.") from exc
if not isinstance(releases, list):
raise RuntimeError("Unexpected response when listing releases.")
return releases
def resolve_release_workflow(version: str) -> dict:
stdout = subprocess.check_output(
[
"gh",
"run",
"list",
"--branch",
f"rust-v{version}",
"--json",
"workflowName,url,headSha",
"--workflow",
WORKFLOW_NAME,
"--jq",
"first(.[])",
],
text=True,
)
workflow = json.loads(stdout or "[]")
if not workflow:
raise RuntimeError(f"Unable to find rust-release workflow for version {version}.")
return workflow
def run_npm_pack(staging_dir: Path, output_path: Path) -> Path:
output_path = output_path.resolve()
output_path.parent.mkdir(parents=True, exist_ok=True)
with tempfile.TemporaryDirectory(prefix="codex-npm-pack-") as pack_dir_str:
pack_dir = Path(pack_dir_str)
stdout = subprocess.check_output(
["npm", "pack", "--json", "--pack-destination", str(pack_dir)],
cwd=staging_dir,
text=True,
)
try:
pack_output = json.loads(stdout)
except json.JSONDecodeError as exc:
raise RuntimeError("Failed to parse npm pack output.") from exc
if not pack_output:
raise RuntimeError("npm pack did not produce an output tarball.")
tarball_name = pack_output[0].get("filename") or pack_output[0].get("name")
if not tarball_name:
raise RuntimeError("Unable to determine npm pack output filename.")
tarball_path = pack_dir / tarball_name
if not tarball_path.exists():
raise RuntimeError(f"Expected npm pack output not found: {tarball_path}")
shutil.move(str(tarball_path), output_path)
return output_path
if __name__ == "__main__":
import sys
sys.exit(main())

View File

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

View File

@@ -0,0 +1,94 @@
#!/usr/bin/env bash
# Install native runtime dependencies for codex-cli.
#
# Usage
# install_native_deps.sh [--workflow-url URL] [CODEX_CLI_ROOT]
#
# The optional RELEASE_ROOT is the path that contains package.json. Omitting
# it installs the binaries into the repository's own bin/ folder to support
# local development.
set -euo pipefail
# ------------------
# Parse arguments
# ------------------
CODEX_CLI_ROOT=""
# Until we start publishing stable GitHub releases, we have to grab the binaries
# from the GitHub Action that created them. Update the URL below to point to the
# appropriate workflow run:
WORKFLOW_URL="https://github.com/openai/codex/actions/runs/17417194663" # rust-v0.28.0
while [[ $# -gt 0 ]]; do
case "$1" in
--workflow-url)
shift || { echo "--workflow-url requires an argument"; exit 1; }
if [ -n "$1" ]; then
WORKFLOW_URL="$1"
fi
;;
*)
if [[ -z "$CODEX_CLI_ROOT" ]]; then
CODEX_CLI_ROOT="$1"
else
echo "Unexpected argument: $1" >&2
exit 1
fi
;;
esac
shift
done
# ----------------------------------------------------------------------------
# Determine where the binaries should be installed.
# ----------------------------------------------------------------------------
if [ -n "$CODEX_CLI_ROOT" ]; then
# The caller supplied a release root directory.
BIN_DIR="$CODEX_CLI_ROOT/bin"
else
# No argument; fall back to the repos own bin directory.
# Resolve the path of this script, then walk up to the repo root.
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
CODEX_CLI_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
BIN_DIR="$CODEX_CLI_ROOT/bin"
fi
# Make sure the destination directory exists.
mkdir -p "$BIN_DIR"
# ----------------------------------------------------------------------------
# Download and decompress the artifacts from the GitHub Actions workflow.
# ----------------------------------------------------------------------------
WORKFLOW_ID="${WORKFLOW_URL##*/}"
ARTIFACTS_DIR="$(mktemp -d)"
trap 'rm -rf "$ARTIFACTS_DIR"' EXIT
# NB: The GitHub CLI `gh` must be installed and authenticated.
gh run download --dir "$ARTIFACTS_DIR" --repo openai/codex "$WORKFLOW_ID"
# x64 Linux
zstd -d "$ARTIFACTS_DIR/x86_64-unknown-linux-musl/codex-x86_64-unknown-linux-musl.zst" \
-o "$BIN_DIR/codex-x86_64-unknown-linux-musl"
# ARM64 Linux
zstd -d "$ARTIFACTS_DIR/aarch64-unknown-linux-musl/codex-aarch64-unknown-linux-musl.zst" \
-o "$BIN_DIR/codex-aarch64-unknown-linux-musl"
# x64 macOS
zstd -d "$ARTIFACTS_DIR/x86_64-apple-darwin/codex-x86_64-apple-darwin.zst" \
-o "$BIN_DIR/codex-x86_64-apple-darwin"
# ARM64 macOS
zstd -d "$ARTIFACTS_DIR/aarch64-apple-darwin/codex-aarch64-apple-darwin.zst" \
-o "$BIN_DIR/codex-aarch64-apple-darwin"
# x64 Windows
zstd -d "$ARTIFACTS_DIR/x86_64-pc-windows-msvc/codex-x86_64-pc-windows-msvc.exe.zst" \
-o "$BIN_DIR/codex-x86_64-pc-windows-msvc.exe"
# ARM64 Windows
zstd -d "$ARTIFACTS_DIR/aarch64-pc-windows-msvc/codex-aarch64-pc-windows-msvc.exe.zst" \
-o "$BIN_DIR/codex-aarch64-pc-windows-msvc.exe"
echo "Installed native dependencies into $BIN_DIR"

View File

@@ -0,0 +1,120 @@
#!/usr/bin/env bash
# -----------------------------------------------------------------------------
# stage_release.sh
# -----------------------------------------------------------------------------
# Stages an npm release for @openai/codex.
#
# Usage:
#
# --tmp <dir> : Use <dir> instead of a freshly created temp directory.
# -h|--help : Print usage.
#
# -----------------------------------------------------------------------------
set -euo pipefail
# Helper - usage / flag parsing
usage() {
cat <<EOF
Usage: $(basename "$0") [--tmp DIR] [--version VERSION]
Options
--tmp DIR Use DIR to stage the release (defaults to a fresh mktemp dir)
--version Specify the version to release (defaults to a timestamp-based version)
-h, --help Show this help
Legacy positional argument: the first non-flag argument is still interpreted
as the temporary directory (for backwards compatibility) but is deprecated.
EOF
exit "${1:-0}"
}
TMPDIR=""
# Default to a timestamp-based version (keep same scheme as before)
VERSION="$(printf '0.1.%d' "$(date +%y%m%d%H%M)")"
WORKFLOW_URL=""
# Manual flag parser - Bash getopts does not handle GNU long options well.
while [[ $# -gt 0 ]]; do
case "$1" in
--tmp)
shift || { echo "--tmp requires an argument"; usage 1; }
TMPDIR="$1"
;;
--tmp=*)
TMPDIR="${1#*=}"
;;
--version)
shift || { echo "--version requires an argument"; usage 1; }
VERSION="$1"
;;
--workflow-url)
shift || { echo "--workflow-url requires an argument"; exit 1; }
WORKFLOW_URL="$1"
;;
-h|--help)
usage 0
;;
--*)
echo "Unknown option: $1" >&2
usage 1
;;
*)
echo "Unexpected extra argument: $1" >&2
usage 1
;;
esac
shift
done
# Fallback when the caller did not specify a directory.
# If no directory was specified create a fresh temporary one.
if [[ -z "$TMPDIR" ]]; then
TMPDIR="$(mktemp -d)"
fi
# Ensure the directory exists, then resolve to an absolute path.
mkdir -p "$TMPDIR"
TMPDIR="$(cd "$TMPDIR" && pwd)"
# Main build logic
echo "Staging release in $TMPDIR"
# The script lives in codex-cli/scripts/ - change into codex-cli root so that
# relative paths keep working.
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
CODEX_CLI_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
pushd "$CODEX_CLI_ROOT" >/dev/null
# 1. Build the JS artifacts ---------------------------------------------------
# Paths inside the staged package
mkdir -p "$TMPDIR/bin"
cp -r bin/codex.js "$TMPDIR/bin/codex.js"
cp ../README.md "$TMPDIR" || true # README is one level up - ignore if missing
# Modify package.json - bump version and optionally add the native directory to
# the files array so that the binaries are published to npm.
jq --arg version "$VERSION" \
'.version = $version' \
package.json > "$TMPDIR/package.json"
# 2. Native runtime deps (sandbox plus optional Rust binaries)
./scripts/install_native_deps.sh --workflow-url "$WORKFLOW_URL" "$TMPDIR"
popd >/dev/null
echo "Staged version $VERSION for release in $TMPDIR"
echo "Verify the CLI:"
echo " node ${TMPDIR}/bin/codex.js --version"
echo " node ${TMPDIR}/bin/codex.js --help"
# Print final hint for convenience
echo "Next: cd \"$TMPDIR\" && npm publish"

View File

@@ -0,0 +1,70 @@
#!/usr/bin/env python3
import json
import subprocess
import sys
import argparse
from pathlib import Path
def main() -> int:
parser = argparse.ArgumentParser(
description="""Stage a release for the npm module.
Run this after the GitHub Release has been created and use
`--release-version` to specify the version to release.
Optionally pass `--tmp` to control the temporary staging directory that will be
forwarded to stage_release.sh.
"""
)
parser.add_argument(
"--release-version", required=True, help="Version to release, e.g., 0.3.0"
)
parser.add_argument(
"--tmp",
help="Optional path to stage the npm package; forwarded to stage_release.sh",
)
args = parser.parse_args()
version = args.release_version
gh_run = subprocess.run(
[
"gh",
"run",
"list",
"--branch",
f"rust-v{version}",
"--json",
"workflowName,url,headSha",
"--jq",
'first(.[] | select(.workflowName == "rust-release"))',
],
stdout=subprocess.PIPE,
check=True,
)
gh_run.check_returncode()
workflow = json.loads(gh_run.stdout)
sha = workflow["headSha"]
print(f"should `git checkout {sha}`")
current_dir = Path(__file__).parent.resolve()
cmd = [
str(current_dir / "stage_release.sh"),
"--version",
version,
"--workflow-url",
workflow["url"],
]
if args.tmp:
cmd.extend(["--tmp", args.tmp])
stage_release = subprocess.run(cmd)
stage_release.check_returncode()
return 0
if __name__ == "__main__":
sys.exit(main())

1777
codex-rs/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,36 +1,23 @@
[workspace]
members = [
"backend-client",
"ansi-escape",
"app-server",
"apply-patch",
"arg0",
"codex-backend-openapi-models",
"cloud-tasks",
"cloud-tasks-client",
"cli",
"common",
"core",
"exec",
"execpolicy",
"file-search",
"git-tooling",
"linux-sandbox",
"login",
"mcp-client",
"mcp-server",
"mcp-types",
"ollama",
"process-hardening",
"protocol",
"protocol-ts",
"rmcp-client",
"responses-api-proxy",
"otel",
"tui",
"git-apply",
"utils/json-to-toml",
"utils/readiness",
]
resolver = "2"
@@ -42,187 +29,15 @@ version = "0.0.0"
# edition.
edition = "2024"
[workspace.dependencies]
# Internal
app_test_support = { path = "app-server/tests/common" }
codex-ansi-escape = { path = "ansi-escape" }
codex-app-server = { path = "app-server" }
codex-apply-patch = { path = "apply-patch" }
codex-arg0 = { path = "arg0" }
codex-chatgpt = { path = "chatgpt" }
codex-common = { path = "common" }
codex-core = { path = "core" }
codex-exec = { path = "exec" }
codex-file-search = { path = "file-search" }
codex-git-tooling = { path = "git-tooling" }
codex-linux-sandbox = { path = "linux-sandbox" }
codex-login = { path = "login" }
codex-mcp-client = { path = "mcp-client" }
codex-mcp-server = { path = "mcp-server" }
codex-ollama = { path = "ollama" }
codex-otel = { path = "otel" }
codex-process-hardening = { path = "process-hardening" }
codex-protocol = { path = "protocol" }
codex-protocol-ts = { path = "protocol-ts" }
codex-responses-api-proxy = { path = "responses-api-proxy" }
codex-rmcp-client = { path = "rmcp-client" }
codex-tui = { path = "tui" }
codex-utils-json-to-toml = { path = "utils/json-to-toml" }
codex-utils-readiness = { path = "utils/readiness" }
core_test_support = { path = "core/tests/common" }
mcp-types = { path = "mcp-types" }
mcp_test_support = { path = "mcp-server/tests/common" }
# External
allocative = "0.3.3"
ansi-to-tui = "7.0.0"
anyhow = "1"
arboard = "3"
askama = "0.12"
assert_cmd = "2"
async-channel = "2.3.1"
async-stream = "0.3.6"
async-trait = "0.1.89"
base64 = "0.22.1"
bytes = "1.10.1"
chrono = "0.4.42"
clap = "4"
clap_complete = "4"
color-eyre = "0.6.3"
crossterm = "0.28.1"
ctor = "0.5.0"
derive_more = "2"
diffy = "0.4.2"
dirs = "6"
dotenvy = "0.15.7"
env-flags = "0.1.1"
env_logger = "0.11.5"
escargot = "0.5"
eventsource-stream = "0.2.3"
futures = "0.3"
icu_decimal = "2.0.0"
icu_locale_core = "2.0.0"
ignore = "0.4.23"
image = { version = "^0.25.8", default-features = false }
indexmap = "2.6.0"
insta = "1.43.2"
itertools = "0.14.0"
landlock = "0.4.1"
lazy_static = "1"
libc = "0.2.175"
log = "0.4"
maplit = "1.0.2"
mime_guess = "2.0.5"
multimap = "0.10.0"
nucleo-matcher = "0.3.1"
openssl-sys = "*"
opentelemetry = "0.30.0"
opentelemetry-appender-tracing = "0.30.0"
opentelemetry-otlp = "0.30.0"
opentelemetry-semantic-conventions = "0.30.0"
opentelemetry_sdk = "0.30.0"
os_info = "3.12.0"
owo-colors = "4.2.0"
path-absolutize = "3.1.1"
path-clean = "1.0.1"
pathdiff = "0.2"
portable-pty = "0.9.0"
predicates = "3"
pretty_assertions = "1.4.1"
pulldown-cmark = "0.10"
rand = "0.9"
ratatui = "0.29.0"
regex-lite = "0.1.7"
reqwest = "0.12"
schemars = "0.8.22"
seccompiler = "0.5.0"
serde = "1"
serde_json = "1"
serde_with = "3.14"
sha1 = "0.10.6"
sha2 = "0.10"
shlex = "1.3.0"
similar = "2.7.0"
starlark = "0.13.0"
strum = "0.27.2"
strum_macros = "0.27.2"
supports-color = "3.0.2"
sys-locale = "0.3.2"
tempfile = "3.23.0"
textwrap = "0.16.2"
thiserror = "2.0.16"
time = "0.3"
tiny_http = "0.12"
tokio = "1"
tokio-stream = "0.1.17"
tokio-test = "0.4"
tokio-util = "0.7.16"
toml = "0.9.5"
toml_edit = "0.23.4"
tonic = "0.13.1"
tracing = "0.1.41"
tracing-appender = "0.2.3"
tracing-subscriber = "0.3.20"
tracing-test = "0.2.5"
tree-sitter = "0.25.9"
tree-sitter-bash = "0.25.0"
ts-rs = "11"
unicode-segmentation = "1.12.0"
unicode-width = "0.2"
url = "2"
urlencoding = "2.1"
uuid = "1"
vt100 = "0.16.2"
walkdir = "2.5.0"
webbrowser = "1.0"
which = "6"
wildmatch = "2.5.0"
wiremock = "0.6"
zeroize = "1.8.1"
[workspace.lints]
rust = {}
[workspace.lints.clippy]
expect_used = "deny"
identity_op = "deny"
manual_clamp = "deny"
manual_filter = "deny"
manual_find = "deny"
manual_flatten = "deny"
manual_map = "deny"
manual_memcpy = "deny"
manual_non_exhaustive = "deny"
manual_ok_or = "deny"
manual_range_contains = "deny"
manual_retain = "deny"
manual_strip = "deny"
manual_try_fold = "deny"
manual_unwrap_or = "deny"
needless_borrow = "deny"
needless_borrowed_reference = "deny"
needless_collect = "deny"
needless_late_init = "deny"
needless_option_as_deref = "deny"
needless_question_mark = "deny"
needless_update = "deny"
redundant_clone = "deny"
redundant_closure = "deny"
redundant_closure_for_method_calls = "deny"
redundant_static_lifetimes = "deny"
trivially_copy_pass_by_ref = "deny"
uninlined_format_args = "deny"
unnecessary_filter_map = "deny"
unnecessary_lazy_evaluations = "deny"
unnecessary_sort_by = "deny"
unnecessary_to_owned = "deny"
unwrap_used = "deny"
# cargo-shear cannot see the platform-specific openssl-sys usage, so we
# silence the false positive here instead of deleting a real dependency.
[workspace.metadata.cargo-shear]
ignored = ["openssl-sys", "codex-utils-readiness"]
[profile.release]
lto = "fat"
# Because we bundle some of these executables with the TypeScript CLI, we

View File

@@ -4,18 +4,18 @@ We provide Codex CLI as a standalone, native executable to ensure a zero-depende
## Installing Codex
Today, the easiest way to install Codex is via `npm`:
Today, the easiest way to install Codex is via `npm`, though we plan to publish Codex to other package managers soon.
```shell
npm i -g @openai/codex
npm i -g @openai/codex@native
codex
```
You can also install via Homebrew (`brew install codex`) or download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
You can also download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
## What's new in the Rust CLI
The Rust implementation is now the maintained Codex CLI and serves as the default experience. It includes a number of features that the legacy TypeScript CLI never supported.
While we are [working to close the gap between the TypeScript and Rust implementations of Codex CLI](https://github.com/openai/codex/issues/1262), note that the Rust CLI has a number of features that the TypeScript CLI does not!
### Config
@@ -25,14 +25,12 @@ Codex supports a rich set of configuration options. Note that the Rust CLI uses
Codex CLI functions as an MCP client that can connect to MCP servers on startup. See the [`mcp_servers`](../docs/config.md#mcp_servers) section in the configuration documentation for details.
It is still experimental, but you can also launch Codex as an MCP _server_ by running `codex mcp-server`. Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
It is still experimental, but you can also launch Codex as an MCP _server_ by running `codex mcp`. Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
```shell
npx @modelcontextprotocol/inspector codex mcp-server
npx @modelcontextprotocol/inspector codex mcp
```
Use `codex mcp` to add/list/get/remove MCP server launchers defined in `config.toml`, and `codex mcp-server` to run the MCP server directly.
### Notifications
You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS.
@@ -55,14 +53,6 @@ In the transcript preview, the footer shows an `Esc edit prev` hint while editin
Sometimes it is not convenient to `cd` to the directory you want Codex to use as the "working root" before running Codex. Fortunately, `codex` supports a `--cd` option so you can specify whatever folder you want. You can confirm that Codex is honoring `--cd` by double-checking the **workdir** it reports in the TUI at the start of a new session.
### Resuming sessions
When you use `codex resume`, provide any follow-up prompt *before* an optional session id. This keeps combinations like `codex resume --last "fix the tests"` working while still letting you resume a specific session when needed:
- `codex resume --last "kick off linting"` — resume the most recent session and immediately send a new prompt.
- `codex resume "draft release notes" d9b7b8b8-3a1f-4a4d-b0a2-4f04bb8d58df` — resume a specific session and send a follow-up prompt.
- `codex resume d9b7b8b8-3a1f-4a4d-b0a2-4f04bb8d58df` — resume a session without sending a prompt (the CLI treats lone UUIDs as session ids).
### Shell completions
Generate shell completion scripts via:

View File

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

View File

@@ -1,51 +0,0 @@
[package]
edition = "2024"
name = "codex-app-server"
version = { workspace = true }
[[bin]]
name = "codex-app-server"
path = "src/main.rs"
[lib]
name = "codex_app_server"
path = "src/lib.rs"
[lints]
workspace = true
[dependencies]
anyhow = { workspace = true }
codex-arg0 = { workspace = true }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
codex-file-search = { workspace = true }
codex-login = { workspace = true }
codex-protocol = { workspace = true }
codex-utils-json-to-toml = { workspace = true }
# We should only be using mcp-types for JSON-RPC types: it would be nice to
# split this out into a separate crate at some point.
mcp-types = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
tokio = { workspace = true, features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tracing = { workspace = true, features = ["log"] }
tracing-subscriber = { workspace = true, features = ["env-filter", "fmt"] }
uuid = { workspace = true, features = ["serde", "v7"] }
[dev-dependencies]
app_test_support = { workspace = true }
assert_cmd = { workspace = true }
base64 = { workspace = true }
core_test_support = { workspace = true }
os_info = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
toml = { workspace = true }
wiremock = { workspace = true }

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,239 +0,0 @@
use std::collections::HashMap;
use std::sync::atomic::AtomicI64;
use std::sync::atomic::Ordering;
use codex_protocol::mcp_protocol::ServerNotification;
use mcp_types::JSONRPC_VERSION;
use mcp_types::JSONRPCError;
use mcp_types::JSONRPCErrorError;
use mcp_types::JSONRPCMessage;
use mcp_types::JSONRPCNotification;
use mcp_types::JSONRPCRequest;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use mcp_types::Result;
use serde::Serialize;
use tokio::sync::Mutex;
use tokio::sync::mpsc;
use tokio::sync::oneshot;
use tracing::warn;
use crate::error_code::INTERNAL_ERROR_CODE;
/// Sends messages to the client and manages request callbacks.
pub(crate) struct OutgoingMessageSender {
next_request_id: AtomicI64,
sender: mpsc::UnboundedSender<OutgoingMessage>,
request_id_to_callback: Mutex<HashMap<RequestId, oneshot::Sender<Result>>>,
}
impl OutgoingMessageSender {
pub(crate) fn new(sender: mpsc::UnboundedSender<OutgoingMessage>) -> Self {
Self {
next_request_id: AtomicI64::new(0),
sender,
request_id_to_callback: Mutex::new(HashMap::new()),
}
}
pub(crate) async fn send_request(
&self,
method: &str,
params: Option<serde_json::Value>,
) -> oneshot::Receiver<Result> {
let id = RequestId::Integer(self.next_request_id.fetch_add(1, Ordering::Relaxed));
let outgoing_message_id = id.clone();
let (tx_approve, rx_approve) = oneshot::channel();
{
let mut request_id_to_callback = self.request_id_to_callback.lock().await;
request_id_to_callback.insert(id, tx_approve);
}
let outgoing_message = OutgoingMessage::Request(OutgoingRequest {
id: outgoing_message_id,
method: method.to_string(),
params,
});
let _ = self.sender.send(outgoing_message);
rx_approve
}
pub(crate) async fn notify_client_response(&self, id: RequestId, result: Result) {
let entry = {
let mut request_id_to_callback = self.request_id_to_callback.lock().await;
request_id_to_callback.remove_entry(&id)
};
match entry {
Some((id, sender)) => {
if let Err(err) = sender.send(result) {
warn!("could not notify callback for {id:?} due to: {err:?}");
}
}
None => {
warn!("could not find callback for {id:?}");
}
}
}
pub(crate) async fn send_response<T: Serialize>(&self, id: RequestId, response: T) {
match serde_json::to_value(response) {
Ok(result) => {
let outgoing_message = OutgoingMessage::Response(OutgoingResponse { id, result });
let _ = self.sender.send(outgoing_message);
}
Err(err) => {
self.send_error(
id,
JSONRPCErrorError {
code: INTERNAL_ERROR_CODE,
message: format!("failed to serialize response: {err}"),
data: None,
},
)
.await;
}
}
}
pub(crate) async fn send_server_notification(&self, notification: ServerNotification) {
let _ = self
.sender
.send(OutgoingMessage::AppServerNotification(notification));
}
/// All notifications should be migrated to [`ServerNotification`] and
/// [`OutgoingMessage::Notification`] should be removed.
pub(crate) async fn send_notification(&self, notification: OutgoingNotification) {
let outgoing_message = OutgoingMessage::Notification(notification);
let _ = self.sender.send(outgoing_message);
}
pub(crate) async fn send_error(&self, id: RequestId, error: JSONRPCErrorError) {
let outgoing_message = OutgoingMessage::Error(OutgoingError { id, error });
let _ = self.sender.send(outgoing_message);
}
}
/// Outgoing message from the server to the client.
pub(crate) enum OutgoingMessage {
Request(OutgoingRequest),
Notification(OutgoingNotification),
/// AppServerNotification is specific to the case where this is run as an
/// "app server" as opposed to an MCP server.
AppServerNotification(ServerNotification),
Response(OutgoingResponse),
Error(OutgoingError),
}
impl From<OutgoingMessage> for JSONRPCMessage {
fn from(val: OutgoingMessage) -> Self {
use OutgoingMessage::*;
match val {
Request(OutgoingRequest { id, method, params }) => {
JSONRPCMessage::Request(JSONRPCRequest {
jsonrpc: JSONRPC_VERSION.into(),
id,
method,
params,
})
}
Notification(OutgoingNotification { method, params }) => {
JSONRPCMessage::Notification(JSONRPCNotification {
jsonrpc: JSONRPC_VERSION.into(),
method,
params,
})
}
AppServerNotification(notification) => {
let method = notification.to_string();
let params = match notification.to_params() {
Ok(params) => Some(params),
Err(err) => {
warn!("failed to serialize notification params: {err}");
None
}
};
JSONRPCMessage::Notification(JSONRPCNotification {
jsonrpc: JSONRPC_VERSION.into(),
method,
params,
})
}
Response(OutgoingResponse { id, result }) => {
JSONRPCMessage::Response(JSONRPCResponse {
jsonrpc: JSONRPC_VERSION.into(),
id,
result,
})
}
Error(OutgoingError { id, error }) => JSONRPCMessage::Error(JSONRPCError {
jsonrpc: JSONRPC_VERSION.into(),
id,
error,
}),
}
}
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingRequest {
pub id: RequestId,
pub method: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub params: Option<serde_json::Value>,
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingNotification {
pub method: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub params: Option<serde_json::Value>,
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingResponse {
pub id: RequestId,
pub result: Result,
}
#[derive(Debug, Clone, PartialEq, Serialize)]
pub(crate) struct OutgoingError {
pub error: JSONRPCErrorError,
pub id: RequestId,
}
#[cfg(test)]
mod tests {
use codex_protocol::mcp_protocol::LoginChatGptCompleteNotification;
use pretty_assertions::assert_eq;
use serde_json::json;
use uuid::Uuid;
use super::*;
#[test]
fn verify_server_notification_serialization() {
let notification =
ServerNotification::LoginChatGptComplete(LoginChatGptCompleteNotification {
login_id: Uuid::nil(),
success: true,
error: None,
});
let jsonrpc_notification: JSONRPCMessage =
OutgoingMessage::AppServerNotification(notification).into();
assert_eq!(
JSONRPCMessage::Notification(JSONRPCNotification {
jsonrpc: "2.0".into(),
method: "loginChatGptComplete".into(),
params: Some(json!({
"loginId": Uuid::nil(),
"success": true,
})),
}),
jsonrpc_notification,
"ensure the strum macros serialize the method field correctly"
);
}
}

View File

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

View File

@@ -1,22 +0,0 @@
[package]
edition = "2024"
name = "app_test_support"
version = { workspace = true }
[lib]
path = "lib.rs"
[dependencies]
anyhow = { workspace = true }
assert_cmd = { workspace = true }
codex-protocol = { workspace = true }
mcp-types = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true, features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
] }
wiremock = { workspace = true }

View File

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

View File

@@ -1,477 +0,0 @@
use std::path::Path;
use std::process::Stdio;
use std::sync::atomic::AtomicI64;
use std::sync::atomic::Ordering;
use tokio::io::AsyncBufReadExt;
use tokio::io::AsyncWriteExt;
use tokio::io::BufReader;
use tokio::process::Child;
use tokio::process::ChildStdin;
use tokio::process::ChildStdout;
use anyhow::Context;
use assert_cmd::prelude::*;
use codex_protocol::mcp_protocol::AddConversationListenerParams;
use codex_protocol::mcp_protocol::ArchiveConversationParams;
use codex_protocol::mcp_protocol::CancelLoginChatGptParams;
use codex_protocol::mcp_protocol::ClientInfo;
use codex_protocol::mcp_protocol::ClientNotification;
use codex_protocol::mcp_protocol::GetAuthStatusParams;
use codex_protocol::mcp_protocol::InitializeParams;
use codex_protocol::mcp_protocol::InterruptConversationParams;
use codex_protocol::mcp_protocol::ListConversationsParams;
use codex_protocol::mcp_protocol::LoginApiKeyParams;
use codex_protocol::mcp_protocol::NewConversationParams;
use codex_protocol::mcp_protocol::RemoveConversationListenerParams;
use codex_protocol::mcp_protocol::ResumeConversationParams;
use codex_protocol::mcp_protocol::SendUserMessageParams;
use codex_protocol::mcp_protocol::SendUserTurnParams;
use codex_protocol::mcp_protocol::SetDefaultModelParams;
use mcp_types::JSONRPC_VERSION;
use mcp_types::JSONRPCMessage;
use mcp_types::JSONRPCNotification;
use mcp_types::JSONRPCRequest;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use std::process::Command as StdCommand;
use tokio::process::Command;
pub struct McpProcess {
next_request_id: AtomicI64,
/// Retain this child process until the client is dropped. The Tokio runtime
/// will make a "best effort" to reap the process after it exits, but it is
/// not a guarantee. See the `kill_on_drop` documentation for details.
#[allow(dead_code)]
process: Child,
stdin: ChildStdin,
stdout: BufReader<ChildStdout>,
}
impl McpProcess {
pub async fn new(codex_home: &Path) -> anyhow::Result<Self> {
Self::new_with_env(codex_home, &[]).await
}
/// Creates a new MCP process, allowing tests to override or remove
/// specific environment variables for the child process only.
///
/// Pass a tuple of (key, Some(value)) to set/override, or (key, None) to
/// remove a variable from the child's environment.
pub async fn new_with_env(
codex_home: &Path,
env_overrides: &[(&str, Option<&str>)],
) -> anyhow::Result<Self> {
// Use assert_cmd to locate the binary path and then switch to tokio::process::Command
let std_cmd = StdCommand::cargo_bin("codex-app-server")
.context("should find binary for codex-mcp-server")?;
let program = std_cmd.get_program().to_owned();
let mut cmd = Command::new(program);
cmd.stdin(Stdio::piped());
cmd.stdout(Stdio::piped());
cmd.stderr(Stdio::piped());
cmd.env("CODEX_HOME", codex_home);
cmd.env("RUST_LOG", "debug");
for (k, v) in env_overrides {
match v {
Some(val) => {
cmd.env(k, val);
}
None => {
cmd.env_remove(k);
}
}
}
let mut process = cmd
.kill_on_drop(true)
.spawn()
.context("codex-mcp-server proc should start")?;
let stdin = process
.stdin
.take()
.ok_or_else(|| anyhow::format_err!("mcp should have stdin fd"))?;
let stdout = process
.stdout
.take()
.ok_or_else(|| anyhow::format_err!("mcp should have stdout fd"))?;
let stdout = BufReader::new(stdout);
// Forward child's stderr to our stderr so failures are visible even
// when stdout/stderr are captured by the test harness.
if let Some(stderr) = process.stderr.take() {
let mut stderr_reader = BufReader::new(stderr).lines();
tokio::spawn(async move {
while let Ok(Some(line)) = stderr_reader.next_line().await {
eprintln!("[mcp stderr] {line}");
}
});
}
Ok(Self {
next_request_id: AtomicI64::new(0),
process,
stdin,
stdout,
})
}
/// Performs the initialization handshake with the MCP server.
pub async fn initialize(&mut self) -> anyhow::Result<()> {
let params = Some(serde_json::to_value(InitializeParams {
client_info: ClientInfo {
name: "codex-app-server-tests".to_string(),
title: None,
version: "0.1.0".to_string(),
},
})?);
let req_id = self.send_request("initialize", params).await?;
let initialized = self.read_jsonrpc_message().await?;
let JSONRPCMessage::Response(response) = initialized else {
unreachable!("expected JSONRPCMessage::Response for initialize, got {initialized:?}");
};
if response.id != RequestId::Integer(req_id) {
anyhow::bail!(
"initialize response id mismatch: expected {}, got {:?}",
req_id,
response.id
);
}
// Send notifications/initialized to ack the response.
self.send_notification(ClientNotification::Initialized)
.await?;
Ok(())
}
/// Send a `newConversation` JSON-RPC request.
pub async fn send_new_conversation_request(
&mut self,
params: NewConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("newConversation", params).await
}
/// Send an `archiveConversation` JSON-RPC request.
pub async fn send_archive_conversation_request(
&mut self,
params: ArchiveConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("archiveConversation", params).await
}
/// Send an `addConversationListener` JSON-RPC request.
pub async fn send_add_conversation_listener_request(
&mut self,
params: AddConversationListenerParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("addConversationListener", params).await
}
/// Send a `sendUserMessage` JSON-RPC request with a single text item.
pub async fn send_send_user_message_request(
&mut self,
params: SendUserMessageParams,
) -> anyhow::Result<i64> {
// Wire format expects variants in camelCase; text item uses external tagging.
let params = Some(serde_json::to_value(params)?);
self.send_request("sendUserMessage", params).await
}
/// Send a `removeConversationListener` JSON-RPC request.
pub async fn send_remove_conversation_listener_request(
&mut self,
params: RemoveConversationListenerParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("removeConversationListener", params)
.await
}
/// Send a `sendUserTurn` JSON-RPC request.
pub async fn send_send_user_turn_request(
&mut self,
params: SendUserTurnParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("sendUserTurn", params).await
}
/// Send a `interruptConversation` JSON-RPC request.
pub async fn send_interrupt_conversation_request(
&mut self,
params: InterruptConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("interruptConversation", params).await
}
/// Send a `getAuthStatus` JSON-RPC request.
pub async fn send_get_auth_status_request(
&mut self,
params: GetAuthStatusParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("getAuthStatus", params).await
}
/// Send a `getUserSavedConfig` JSON-RPC request.
pub async fn send_get_user_saved_config_request(&mut self) -> anyhow::Result<i64> {
self.send_request("getUserSavedConfig", None).await
}
/// Send a `getUserAgent` JSON-RPC request.
pub async fn send_get_user_agent_request(&mut self) -> anyhow::Result<i64> {
self.send_request("getUserAgent", None).await
}
/// Send a `userInfo` JSON-RPC request.
pub async fn send_user_info_request(&mut self) -> anyhow::Result<i64> {
self.send_request("userInfo", None).await
}
/// Send a `setDefaultModel` JSON-RPC request.
pub async fn send_set_default_model_request(
&mut self,
params: SetDefaultModelParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("setDefaultModel", params).await
}
/// Send a `listConversations` JSON-RPC request.
pub async fn send_list_conversations_request(
&mut self,
params: ListConversationsParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("listConversations", params).await
}
/// Send a `resumeConversation` JSON-RPC request.
pub async fn send_resume_conversation_request(
&mut self,
params: ResumeConversationParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("resumeConversation", params).await
}
/// Send a `loginApiKey` JSON-RPC request.
pub async fn send_login_api_key_request(
&mut self,
params: LoginApiKeyParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("loginApiKey", params).await
}
/// Send a `loginChatGpt` JSON-RPC request.
pub async fn send_login_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
self.send_request("loginChatGpt", None).await
}
/// Send a `cancelLoginChatGpt` JSON-RPC request.
pub async fn send_cancel_login_chat_gpt_request(
&mut self,
params: CancelLoginChatGptParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("cancelLoginChatGpt", params).await
}
/// Send a `logoutChatGpt` JSON-RPC request.
pub async fn send_logout_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
self.send_request("logoutChatGpt", None).await
}
/// Send a `fuzzyFileSearch` JSON-RPC request.
pub async fn send_fuzzy_file_search_request(
&mut self,
query: &str,
roots: Vec<String>,
cancellation_token: Option<String>,
) -> anyhow::Result<i64> {
let mut params = serde_json::json!({
"query": query,
"roots": roots,
});
if let Some(token) = cancellation_token {
params["cancellationToken"] = serde_json::json!(token);
}
self.send_request("fuzzyFileSearch", Some(params)).await
}
async fn send_request(
&mut self,
method: &str,
params: Option<serde_json::Value>,
) -> anyhow::Result<i64> {
let request_id = self.next_request_id.fetch_add(1, Ordering::Relaxed);
let message = JSONRPCMessage::Request(JSONRPCRequest {
jsonrpc: JSONRPC_VERSION.into(),
id: RequestId::Integer(request_id),
method: method.to_string(),
params,
});
self.send_jsonrpc_message(message).await?;
Ok(request_id)
}
pub async fn send_response(
&mut self,
id: RequestId,
result: serde_json::Value,
) -> anyhow::Result<()> {
self.send_jsonrpc_message(JSONRPCMessage::Response(JSONRPCResponse {
jsonrpc: JSONRPC_VERSION.into(),
id,
result,
}))
.await
}
pub async fn send_notification(
&mut self,
notification: ClientNotification,
) -> anyhow::Result<()> {
let value = serde_json::to_value(notification)?;
self.send_jsonrpc_message(JSONRPCMessage::Notification(JSONRPCNotification {
jsonrpc: JSONRPC_VERSION.into(),
method: value
.get("method")
.and_then(|m| m.as_str())
.ok_or_else(|| anyhow::format_err!("notification missing method field"))?
.to_string(),
params: value.get("params").cloned(),
}))
.await
}
async fn send_jsonrpc_message(&mut self, message: JSONRPCMessage) -> anyhow::Result<()> {
eprintln!("writing message to stdin: {message:?}");
let payload = serde_json::to_string(&message)?;
self.stdin.write_all(payload.as_bytes()).await?;
self.stdin.write_all(b"\n").await?;
self.stdin.flush().await?;
Ok(())
}
async fn read_jsonrpc_message(&mut self) -> anyhow::Result<JSONRPCMessage> {
let mut line = String::new();
self.stdout.read_line(&mut line).await?;
let message = serde_json::from_str::<JSONRPCMessage>(&line)?;
eprintln!("read message from stdout: {message:?}");
Ok(message)
}
pub async fn read_stream_until_request_message(&mut self) -> anyhow::Result<JSONRPCRequest> {
eprintln!("in read_stream_until_request_message()");
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(_) => {
eprintln!("notification: {message:?}");
}
JSONRPCMessage::Request(jsonrpc_request) => {
return Ok(jsonrpc_request);
}
JSONRPCMessage::Error(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
}
JSONRPCMessage::Response(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
}
}
}
}
pub async fn read_stream_until_response_message(
&mut self,
request_id: RequestId,
) -> anyhow::Result<JSONRPCResponse> {
eprintln!("in read_stream_until_response_message({request_id:?})");
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(_) => {
eprintln!("notification: {message:?}");
}
JSONRPCMessage::Request(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
}
JSONRPCMessage::Error(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
}
JSONRPCMessage::Response(jsonrpc_response) => {
if jsonrpc_response.id == request_id {
return Ok(jsonrpc_response);
}
}
}
}
}
pub async fn read_stream_until_error_message(
&mut self,
request_id: RequestId,
) -> anyhow::Result<mcp_types::JSONRPCError> {
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(_) => {
eprintln!("notification: {message:?}");
}
JSONRPCMessage::Request(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
}
JSONRPCMessage::Response(_) => {
// Keep scanning; we're waiting for an error with matching id.
}
JSONRPCMessage::Error(err) => {
if err.id == request_id {
return Ok(err);
}
}
}
}
}
pub async fn read_stream_until_notification_message(
&mut self,
method: &str,
) -> anyhow::Result<JSONRPCNotification> {
eprintln!("in read_stream_until_notification_message({method})");
loop {
let message = self.read_jsonrpc_message().await?;
match message {
JSONRPCMessage::Notification(notification) => {
if notification.method == method {
return Ok(notification);
}
}
JSONRPCMessage::Request(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
}
JSONRPCMessage::Error(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
}
JSONRPCMessage::Response(_) => {
anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
}
}
}
}
}

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -6,10 +6,10 @@ use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
use std::str::Utf8Error;
use std::sync::LazyLock;
use anyhow::Context;
use anyhow::Result;
use once_cell::sync::Lazy;
pub use parser::Hunk;
pub use parser::ParseError;
use parser::ParseError::*;
@@ -351,7 +351,7 @@ fn extract_apply_patch_from_bash(
// also run an arbitrary query against the AST. This is useful for understanding
// how tree-sitter parses the script and whether the query syntax is correct. Be sure
// to test both positive and negative cases.
static APPLY_PATCH_QUERY: LazyLock<Query> = LazyLock::new(|| {
static APPLY_PATCH_QUERY: Lazy<Query> = Lazy::new(|| {
let language = BASH.into();
#[expect(clippy::expect_used)]
Query::new(
@@ -648,18 +648,21 @@ fn derive_new_contents_from_chunks(
}
};
let mut original_lines: Vec<String> = original_contents.split('\n').map(String::from).collect();
let mut original_lines: Vec<String> = original_contents
.split('\n')
.map(|s| s.to_string())
.collect();
// Drop the trailing empty element that results from the final newline so
// that line counts match the behaviour of standard `diff`.
if original_lines.last().is_some_and(String::is_empty) {
if original_lines.last().is_some_and(|s| s.is_empty()) {
original_lines.pop();
}
let replacements = compute_replacements(&original_lines, path, chunks)?;
let new_lines = apply_replacements(original_lines, &replacements);
let mut new_lines = new_lines;
if !new_lines.last().is_some_and(String::is_empty) {
if !new_lines.last().is_some_and(|s| s.is_empty()) {
new_lines.push(String::new());
}
let new_contents = new_lines.join("\n");
@@ -703,7 +706,7 @@ fn compute_replacements(
if chunk.old_lines.is_empty() {
// Pure addition (no old lines). We'll add them at the end or just
// before the final empty line if one exists.
let insertion_idx = if original_lines.last().is_some_and(String::is_empty) {
let insertion_idx = if original_lines.last().is_some_and(|s| s.is_empty()) {
original_lines.len() - 1
} else {
original_lines.len()
@@ -729,11 +732,11 @@ fn compute_replacements(
let mut new_slice: &[String] = &chunk.new_lines;
if found.is_none() && pattern.last().is_some_and(String::is_empty) {
if found.is_none() && pattern.last().is_some_and(|s| s.is_empty()) {
// Retry without the trailing empty line which represents the final
// newline in the file.
pattern = &pattern[..pattern.len() - 1];
if new_slice.last().is_some_and(String::is_empty) {
if new_slice.last().is_some_and(|s| s.is_empty()) {
new_slice = &new_slice[..new_slice.len() - 1];
}
@@ -845,7 +848,6 @@ mod tests {
use super::*;
use pretty_assertions::assert_eq;
use std::fs;
use std::string::ToString;
use tempfile::tempdir;
/// Helper to construct a patch with the given body.
@@ -854,7 +856,7 @@ mod tests {
}
fn strs_to_strings(strs: &[&str]) -> Vec<String> {
strs.iter().map(ToString::to_string).collect()
strs.iter().map(|s| s.to_string()).collect()
}
// Test helpers to reduce repetition when building bash -lc heredoc scripts

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -7,14 +7,13 @@ version = { workspace = true }
workspace = true
[dependencies]
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive"] }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
tokio = { workspace = true, features = ["full"] }
codex-git-apply = { path = "../git-apply" }
anyhow = "1"
clap = { version = "4", features = ["derive"] }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tokio = { version = "1", features = ["full"] }
[dev-dependencies]
tempfile = { workspace = true }
tempfile = "3"

View File

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

View File

@@ -44,6 +44,6 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
} else {
let status = response.status();
let body = response.text().await.unwrap_or_default();
anyhow::bail!("Request failed with status {status}: {body}")
anyhow::bail!("Request failed with status {}: {}", status, body)
}
}

View File

@@ -15,40 +15,26 @@ path = "src/lib.rs"
workspace = true
[dependencies]
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive"] }
clap_complete = { workspace = true }
codex-app-server = { workspace = true }
codex-arg0 = { workspace = true }
codex-chatgpt = { workspace = true }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
codex-exec = { workspace = true }
codex-login = { workspace = true }
codex-mcp-server = { workspace = true }
codex-process-hardening = { workspace = true }
codex-protocol = { workspace = true }
codex-protocol-ts = { workspace = true }
codex-responses-api-proxy = { workspace = true }
codex-tui = { workspace = true }
codex-cloud-tasks = { path = "../cloud-tasks" }
ctor = { workspace = true }
owo-colors = { workspace = true }
serde_json = { workspace = true }
supports-color = { workspace = true }
uuid = { workspace = true }
tokio = { workspace = true, features = [
anyhow = "1"
clap = { version = "4", features = ["derive"] }
clap_complete = "4"
codex-arg0 = { path = "../arg0" }
codex-chatgpt = { path = "../chatgpt" }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
codex-exec = { path = "../exec" }
codex-login = { path = "../login" }
codex-mcp-server = { path = "../mcp-server" }
codex-protocol = { path = "../protocol" }
codex-tui = { path = "../tui" }
serde_json = "1"
tokio = { version = "1", features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tracing = { workspace = true }
tracing-subscriber = { workspace = true }
[dev-dependencies]
assert_cmd = { workspace = true }
predicates = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
tracing = "0.1.41"
tracing-subscriber = "0.3.19"
codex-protocol-ts = { path = "../protocol-ts" }

View File

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

View File

@@ -6,7 +6,6 @@ use codex_core::auth::logout;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_login::ServerOptions;
use codex_login::run_device_code_login;
use codex_login::run_login_server;
use codex_protocol::mcp_protocol::AuthMode;
use std::path::PathBuf;
@@ -56,32 +55,6 @@ pub async fn run_login_with_api_key(
}
}
/// Login using the OAuth device code flow.
pub async fn run_login_with_device_code(
cli_config_overrides: CliConfigOverrides,
issuer_base_url: Option<String>,
client_id: Option<String>,
) -> ! {
let config = load_config_or_exit(cli_config_overrides);
let mut opts = ServerOptions::new(
config.codex_home,
client_id.unwrap_or(CLIENT_ID.to_string()),
);
if let Some(iss) = issuer_base_url {
opts.issuer = iss;
}
match run_device_code_login(opts).await {
Ok(()) => {
eprintln!("Successfully logged in");
std::process::exit(0);
}
Err(e) => {
eprintln!("Error logging in with device code: {e}");
std::process::exit(1);
}
}
}
pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
let config = load_config_or_exit(cli_config_overrides);

View File

@@ -1,7 +1,5 @@
use clap::CommandFactory;
use clap::Parser;
use clap::error::Error as ClapError;
use clap::error::ErrorKind as ClapErrorKind;
use clap_complete::Shell;
use clap_complete::generate;
use codex_arg0::arg0_dispatch_or_else;
@@ -12,23 +10,13 @@ use codex_cli::SeatbeltCommand;
use codex_cli::login::run_login_status;
use codex_cli::login::run_login_with_api_key;
use codex_cli::login::run_login_with_chatgpt;
use codex_cli::login::run_login_with_device_code;
use codex_cli::login::run_logout;
use codex_cli::proto;
use codex_cloud_tasks::Cli as CloudTasksCli;
use codex_common::CliConfigOverrides;
use codex_exec::Cli as ExecCli;
use codex_responses_api_proxy::Args as ResponsesApiProxyArgs;
use codex_tui::AppExitInfo;
use codex_tui::Cli as TuiCli;
use owo_colors::OwoColorize;
use std::path::PathBuf;
use supports_color::Stream;
use uuid::Uuid;
mod mcp_cmd;
use crate::mcp_cmd::McpCli;
use crate::proto::ProtoCli;
/// Codex CLI
@@ -68,14 +56,8 @@ enum Subcommand {
/// Remove stored authentication credentials.
Logout(LogoutCommand),
/// [experimental] Run Codex as an MCP server and manage MCP servers.
Mcp(McpCli),
/// [experimental] Run the Codex MCP server (stdio transport).
McpServer,
/// [experimental] Run the app server.
AppServer,
/// Experimental: run Codex as an MCP server.
Mcp,
/// Run the Protocol stream via stdin/stdout
#[clap(visible_alias = "p")]
@@ -91,19 +73,9 @@ enum Subcommand {
#[clap(visible_alias = "a")]
Apply(ApplyCommand),
/// Resume a previous interactive session (picker by default; use --last to continue the most recent).
Resume(ResumeCommand),
/// Internal: generate TypeScript protocol bindings.
#[clap(hide = true)]
GenerateTs(GenerateTsCommand),
/// [EXPERIMENTAL] Browse tasks from Codex Cloud and apply changes locally.
#[clap(name = "cloud", alias = "cloud-tasks")]
Cloud(CloudTasksCli),
/// Internal: run the responses API proxy.
#[clap(hide = true)]
ResponsesApiProxy(ResponsesApiProxyArgs),
}
#[derive(Debug, Parser)]
@@ -113,21 +85,6 @@ struct CompletionCommand {
shell: Shell,
}
#[derive(Debug, Parser)]
struct ResumeCommand {
#[clap(flatten)]
config_overrides: TuiCli,
/// Continue the most recent session without showing the picker.
#[arg(long = "last", default_value_t = false)]
last: bool,
/// Conversation/session id (UUID). When provided, resumes this session.
/// If omitted, use --last to pick the most recent recorded session.
#[arg(value_name = "SESSION_ID", index = 2)]
session_id: Option<String>,
}
#[derive(Debug, Parser)]
struct DebugArgs {
#[command(subcommand)]
@@ -151,20 +108,6 @@ struct LoginCommand {
#[arg(long = "api-key", value_name = "API_KEY")]
api_key: Option<String>,
/// EXPERIMENTAL: Use device code flow (not yet supported)
/// This feature is experimental and may changed in future releases.
#[arg(long = "experimental_use-device-code", hide = true)]
use_device_code: bool,
/// EXPERIMENTAL: Use custom OAuth issuer base URL (advanced)
/// Override the OAuth issuer base URL (advanced)
#[arg(long = "experimental_issuer", value_name = "URL", hide = true)]
issuer_base_url: Option<String>,
/// EXPERIMENTAL: Use custom OAuth client ID (advanced)
#[arg(long = "experimental_client-id", value_name = "CLIENT_ID", hide = true)]
client_id: Option<String>,
#[command(subcommand)]
action: Option<LoginSubcommand>,
}
@@ -192,62 +135,6 @@ struct GenerateTsCommand {
prettier: Option<PathBuf>,
}
fn format_exit_messages(exit_info: AppExitInfo, color_enabled: bool) -> Vec<String> {
let AppExitInfo {
token_usage,
conversation_id,
} = exit_info;
if token_usage.is_zero() {
return Vec::new();
}
let mut lines = vec![format!(
"{}",
codex_core::protocol::FinalOutput::from(token_usage)
)];
if let Some(session_id) = conversation_id {
let resume_cmd = format!("codex resume {session_id}");
let command = if color_enabled {
resume_cmd.cyan().to_string()
} else {
resume_cmd
};
lines.push(format!("To continue this session, run {command}"));
}
lines
}
fn print_exit_messages(exit_info: AppExitInfo) {
let color_enabled = supports_color::on(Stream::Stdout).is_some();
for line in format_exit_messages(exit_info, color_enabled) {
println!("{line}");
}
}
pub(crate) const CODEX_SECURE_MODE_ENV_VAR: &str = "CODEX_SECURE_MODE";
/// As early as possible in the process lifecycle, apply hardening measures
/// if the CODEX_SECURE_MODE environment variable is set to "1".
#[ctor::ctor]
fn pre_main_hardening() {
let secure_mode = match std::env::var(CODEX_SECURE_MODE_ENV_VAR) {
Ok(value) => value,
Err(_) => return,
};
if secure_mode == "1" {
codex_process_hardening::pre_main_hardening();
}
// Always clear this env var so child processes don't inherit it.
unsafe {
std::env::remove_var(CODEX_SECURE_MODE_ENV_VAR);
}
}
fn main() -> anyhow::Result<()> {
arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
cli_main(codex_linux_sandbox_exe).await?;
@@ -256,75 +143,32 @@ fn main() -> anyhow::Result<()> {
}
async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()> {
let MultitoolCli {
config_overrides: root_config_overrides,
mut interactive,
subcommand,
} = MultitoolCli::parse();
let cli = MultitoolCli::parse();
match subcommand {
match cli.subcommand {
None => {
prepend_config_flags(
&mut interactive.config_overrides,
root_config_overrides.clone(),
);
let exit_info = codex_tui::run_main(interactive, codex_linux_sandbox_exe).await?;
print_exit_messages(exit_info);
let mut tui_cli = cli.interactive;
prepend_config_flags(&mut tui_cli.config_overrides, cli.config_overrides);
let usage = codex_tui::run_main(tui_cli, codex_linux_sandbox_exe).await?;
if !usage.is_zero() {
println!("{}", codex_core::protocol::FinalOutput::from(usage));
}
}
Some(Subcommand::Exec(mut exec_cli)) => {
prepend_config_flags(
&mut exec_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut exec_cli.config_overrides, cli.config_overrides);
codex_exec::run_main(exec_cli, codex_linux_sandbox_exe).await?;
}
Some(Subcommand::McpServer) => {
codex_mcp_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
}
Some(Subcommand::Mcp(mut mcp_cli)) => {
// Propagate any root-level config overrides (e.g. `-c key=value`).
prepend_config_flags(&mut mcp_cli.config_overrides, root_config_overrides.clone());
mcp_cli.run().await?;
}
Some(Subcommand::AppServer) => {
codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
}
Some(Subcommand::Resume(mut resume_cmd)) => {
if let Err(err) = resume_cmd.normalize() {
err.exit();
}
let ResumeCommand {
config_overrides,
last,
session_id,
} = resume_cmd;
interactive = finalize_resume_interactive(
interactive,
root_config_overrides.clone(),
session_id,
last,
config_overrides,
);
codex_tui::run_main(interactive, codex_linux_sandbox_exe).await?;
Some(Subcommand::Mcp) => {
codex_mcp_server::run_main(codex_linux_sandbox_exe, cli.config_overrides).await?;
}
Some(Subcommand::Login(mut login_cli)) => {
prepend_config_flags(
&mut login_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut login_cli.config_overrides, cli.config_overrides);
match login_cli.action {
Some(LoginSubcommand::Status) => {
run_login_status(login_cli.config_overrides).await;
}
None => {
if login_cli.use_device_code {
run_login_with_device_code(
login_cli.config_overrides,
login_cli.issuer_base_url,
login_cli.client_id,
)
.await;
} else if let Some(api_key) = login_cli.api_key {
if let Some(api_key) = login_cli.api_key {
run_login_with_api_key(login_cli.config_overrides, api_key).await;
} else {
run_login_with_chatgpt(login_cli.config_overrides).await;
@@ -333,35 +177,19 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
}
}
Some(Subcommand::Logout(mut logout_cli)) => {
prepend_config_flags(
&mut logout_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut logout_cli.config_overrides, cli.config_overrides);
run_logout(logout_cli.config_overrides).await;
}
Some(Subcommand::Proto(mut proto_cli)) => {
prepend_config_flags(
&mut proto_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut proto_cli.config_overrides, cli.config_overrides);
proto::run_main(proto_cli).await?;
}
Some(Subcommand::Completion(completion_cli)) => {
print_completion(completion_cli);
}
Some(Subcommand::Cloud(mut cloud_cli)) => {
prepend_config_flags(
&mut cloud_cli.config_overrides,
root_config_overrides.clone(),
);
codex_cloud_tasks::run_main(cloud_cli, codex_linux_sandbox_exe).await?;
}
Some(Subcommand::Debug(debug_args)) => match debug_args.cmd {
DebugCommand::Seatbelt(mut seatbelt_cli) => {
prepend_config_flags(
&mut seatbelt_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut seatbelt_cli.config_overrides, cli.config_overrides);
codex_cli::debug_sandbox::run_command_under_seatbelt(
seatbelt_cli,
codex_linux_sandbox_exe,
@@ -369,10 +197,7 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
.await?;
}
DebugCommand::Landlock(mut landlock_cli) => {
prepend_config_flags(
&mut landlock_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut landlock_cli.config_overrides, cli.config_overrides);
codex_cli::debug_sandbox::run_command_under_landlock(
landlock_cli,
codex_linux_sandbox_exe,
@@ -381,16 +206,9 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
}
},
Some(Subcommand::Apply(mut apply_cli)) => {
prepend_config_flags(
&mut apply_cli.config_overrides,
root_config_overrides.clone(),
);
prepend_config_flags(&mut apply_cli.config_overrides, cli.config_overrides);
run_apply_command(apply_cli, None).await?;
}
Some(Subcommand::ResponsesApiProxy(args)) => {
tokio::task::spawn_blocking(move || codex_responses_api_proxy::run_main(args))
.await??;
}
Some(Subcommand::GenerateTs(gen_cli)) => {
codex_protocol_ts::generate_ts(&gen_cli.out_dir, gen_cli.prettier.as_deref())?;
}
@@ -410,336 +228,8 @@ fn prepend_config_flags(
.splice(0..0, cli_config_overrides.raw_overrides);
}
/// Build the final `TuiCli` for a `codex resume` invocation.
fn finalize_resume_interactive(
mut interactive: TuiCli,
root_config_overrides: CliConfigOverrides,
session_id: Option<String>,
last: bool,
resume_cli: TuiCli,
) -> TuiCli {
// Start with the parsed interactive CLI so resume shares the same
// configuration surface area as `codex` without additional flags.
let resume_session_id = session_id;
interactive.resume_picker = resume_session_id.is_none() && !last;
interactive.resume_last = last;
interactive.resume_session_id = resume_session_id;
// Merge resume-scoped flags and overrides with highest precedence.
merge_resume_cli_flags(&mut interactive, resume_cli);
// Propagate any root-level config overrides (e.g. `-c key=value`).
prepend_config_flags(&mut interactive.config_overrides, root_config_overrides);
interactive
}
/// Merge flags provided to `codex resume` so they take precedence over any
/// root-level flags. Only overrides fields explicitly set on the resume-scoped
/// CLI. Also appends `-c key=value` overrides with highest precedence.
fn merge_resume_cli_flags(interactive: &mut TuiCli, resume_cli: TuiCli) {
if let Some(model) = resume_cli.model {
interactive.model = Some(model);
}
if resume_cli.oss {
interactive.oss = true;
}
if let Some(profile) = resume_cli.config_profile {
interactive.config_profile = Some(profile);
}
if let Some(sandbox) = resume_cli.sandbox_mode {
interactive.sandbox_mode = Some(sandbox);
}
if let Some(approval) = resume_cli.approval_policy {
interactive.approval_policy = Some(approval);
}
if resume_cli.full_auto {
interactive.full_auto = true;
}
if resume_cli.dangerously_bypass_approvals_and_sandbox {
interactive.dangerously_bypass_approvals_and_sandbox = true;
}
if let Some(cwd) = resume_cli.cwd {
interactive.cwd = Some(cwd);
}
if resume_cli.web_search {
interactive.web_search = true;
}
if !resume_cli.images.is_empty() {
interactive.images = resume_cli.images;
}
if let Some(prompt) = resume_cli.prompt {
interactive.prompt = Some(prompt);
}
interactive
.config_overrides
.raw_overrides
.extend(resume_cli.config_overrides.raw_overrides);
}
fn print_completion(cmd: CompletionCommand) {
let mut app = MultitoolCli::command();
let name = "codex";
generate(cmd.shell, &mut app, name, &mut std::io::stdout());
}
#[cfg(test)]
mod tests {
use super::*;
use codex_core::protocol::TokenUsage;
use codex_protocol::mcp_protocol::ConversationId;
fn finalize_from_args(args: &[&str]) -> TuiCli {
let cli = MultitoolCli::try_parse_from(args).expect("parse");
let MultitoolCli {
interactive,
config_overrides: root_overrides,
subcommand,
} = cli;
let mut resume_cmd = match subcommand.expect("resume present") {
Subcommand::Resume(cmd) => cmd,
_ => unreachable!(),
};
resume_cmd.normalize().expect("normalize resume args");
let ResumeCommand {
config_overrides: resume_cli,
last,
session_id,
} = resume_cmd;
finalize_resume_interactive(interactive, root_overrides, session_id, last, resume_cli)
}
fn sample_exit_info(conversation: Option<&str>) -> AppExitInfo {
let token_usage = TokenUsage {
output_tokens: 2,
total_tokens: 2,
..Default::default()
};
AppExitInfo {
token_usage,
conversation_id: conversation
.map(ConversationId::from_string)
.map(Result::unwrap),
}
}
#[test]
fn format_exit_messages_skips_zero_usage() {
let exit_info = AppExitInfo {
token_usage: TokenUsage::default(),
conversation_id: None,
};
let lines = format_exit_messages(exit_info, false);
assert!(lines.is_empty());
}
#[test]
fn format_exit_messages_includes_resume_hint_without_color() {
let exit_info = sample_exit_info(Some("123e4567-e89b-12d3-a456-426614174000"));
let lines = format_exit_messages(exit_info, false);
assert_eq!(
lines,
vec![
"Token usage: total=2 input=0 output=2".to_string(),
"To continue this session, run codex resume 123e4567-e89b-12d3-a456-426614174000"
.to_string(),
]
);
}
#[test]
fn format_exit_messages_applies_color_when_enabled() {
let exit_info = sample_exit_info(Some("123e4567-e89b-12d3-a456-426614174000"));
let lines = format_exit_messages(exit_info, true);
assert_eq!(lines.len(), 2);
assert!(lines[1].contains("\u{1b}[36m"));
}
#[test]
fn resume_model_flag_applies_when_no_root_flags() {
let interactive = finalize_from_args(["codex", "resume", "-m", "gpt-5-test"].as_ref());
assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_picker_logic_none_and_not_last() {
let interactive = finalize_from_args(["codex", "resume"].as_ref());
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_picker_logic_last() {
let interactive = finalize_from_args(["codex", "resume", "--last"].as_ref());
assert!(!interactive.resume_picker);
assert!(interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_last_accepts_follow_up_prompt() {
let interactive = finalize_from_args(["codex", "resume", "--last", "hi there"].as_ref());
assert!(interactive.resume_last);
assert_eq!(interactive.prompt.as_deref(), Some("hi there"));
assert_eq!(interactive.resume_session_id, None);
}
#[test]
fn resume_prompt_before_session_id() {
let interactive = finalize_from_args(
[
"codex",
"resume",
"summarize progress",
"123e4567-e89b-12d3-a456-426614174000",
]
.as_ref(),
);
assert_eq!(interactive.prompt.as_deref(), Some("summarize progress"));
assert_eq!(
interactive.resume_session_id.as_deref(),
Some("123e4567-e89b-12d3-a456-426614174000"),
);
assert!(!interactive.resume_last);
assert!(!interactive.resume_picker);
}
#[test]
fn resume_picker_logic_with_session_id() {
let interactive = finalize_from_args(
["codex", "resume", "123e4567-e89b-12d3-a456-426614174000"].as_ref(),
);
assert!(!interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(
interactive.resume_session_id.as_deref(),
Some("123e4567-e89b-12d3-a456-426614174000")
);
}
#[test]
fn resume_merges_option_flags_and_full_auto() {
let interactive = finalize_from_args(
[
"codex",
"resume",
"123e4567-e89b-12d3-a456-426614174000",
"--oss",
"--full-auto",
"--search",
"--sandbox",
"workspace-write",
"--ask-for-approval",
"on-request",
"-m",
"gpt-5-test",
"-p",
"my-profile",
"-C",
"/tmp",
"-i",
"/tmp/a.png,/tmp/b.png",
]
.as_ref(),
);
assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
assert!(interactive.oss);
assert_eq!(interactive.config_profile.as_deref(), Some("my-profile"));
assert!(matches!(
interactive.sandbox_mode,
Some(codex_common::SandboxModeCliArg::WorkspaceWrite)
));
assert!(matches!(
interactive.approval_policy,
Some(codex_common::ApprovalModeCliArg::OnRequest)
));
assert!(interactive.full_auto);
assert_eq!(
interactive.cwd.as_deref(),
Some(std::path::Path::new("/tmp"))
);
assert!(interactive.web_search);
let has_a = interactive
.images
.iter()
.any(|p| p == std::path::Path::new("/tmp/a.png"));
let has_b = interactive
.images
.iter()
.any(|p| p == std::path::Path::new("/tmp/b.png"));
assert!(has_a && has_b);
assert!(!interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(
interactive.resume_session_id.as_deref(),
Some("123e4567-e89b-12d3-a456-426614174000")
);
}
#[test]
fn resume_merges_dangerously_bypass_flag() {
let interactive = finalize_from_args(
[
"codex",
"resume",
"--dangerously-bypass-approvals-and-sandbox",
]
.as_ref(),
);
assert!(interactive.dangerously_bypass_approvals_and_sandbox);
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
}
}
impl ResumeCommand {
fn normalize(&mut self) -> Result<(), ClapError> {
if self.last {
if let Some(value) = self.session_id.take() {
if Self::looks_like_session_id(&value) {
return Err(ClapError::raw(
ClapErrorKind::ArgumentConflict,
"The argument '--last' cannot be used with '[SESSION_ID]'",
));
}
if let Some(existing) = &mut self.config_overrides.prompt {
if !existing.is_empty() {
existing.push(' ');
}
existing.push_str(&value);
} else {
self.config_overrides.prompt = Some(value);
}
}
return Ok(());
}
if self.session_id.is_some() {
return Ok(());
}
if let Some(prompt) = self.config_overrides.prompt.take() {
if Self::looks_like_session_id(&prompt) {
self.session_id = Some(prompt);
} else {
self.config_overrides.prompt = Some(prompt);
}
}
Ok(())
}
fn looks_like_session_id(value: &str) -> bool {
Uuid::parse_str(value).is_ok()
}
}

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

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

View File

View File

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

View File

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

View File

@@ -1,42 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use crate::models;
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct CodeTaskDetailsResponse {
#[serde(rename = "task")]
pub task: Box<models::TaskResponse>,
#[serde(rename = "current_user_turn", skip_serializing_if = "Option::is_none")]
pub current_user_turn: Option<std::collections::HashMap<String, serde_json::Value>>,
#[serde(
rename = "current_assistant_turn",
skip_serializing_if = "Option::is_none"
)]
pub current_assistant_turn: Option<std::collections::HashMap<String, serde_json::Value>>,
#[serde(
rename = "current_diff_task_turn",
skip_serializing_if = "Option::is_none"
)]
pub current_diff_task_turn: Option<std::collections::HashMap<String, serde_json::Value>>,
}
impl CodeTaskDetailsResponse {
pub fn new(task: models::TaskResponse) -> CodeTaskDetailsResponse {
CodeTaskDetailsResponse {
task: Box::new(task),
current_user_turn: None,
current_assistant_turn: None,
current_diff_task_turn: None,
}
}
}

View File

@@ -1,40 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use crate::models;
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct ExternalPullRequestResponse {
#[serde(rename = "id")]
pub id: String,
#[serde(rename = "assistant_turn_id")]
pub assistant_turn_id: String,
#[serde(rename = "pull_request")]
pub pull_request: Box<models::GitPullRequest>,
#[serde(rename = "codex_updated_sha", skip_serializing_if = "Option::is_none")]
pub codex_updated_sha: Option<String>,
}
impl ExternalPullRequestResponse {
pub fn new(
id: String,
assistant_turn_id: String,
pull_request: models::GitPullRequest,
) -> ExternalPullRequestResponse {
ExternalPullRequestResponse {
id,
assistant_turn_id,
pull_request: Box::new(pull_request),
codex_updated_sha: None,
}
}
}

View File

@@ -1,77 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct GitPullRequest {
#[serde(rename = "number")]
pub number: i32,
#[serde(rename = "url")]
pub url: String,
#[serde(rename = "state")]
pub state: String,
#[serde(rename = "merged")]
pub merged: bool,
#[serde(rename = "mergeable")]
pub mergeable: bool,
#[serde(rename = "draft", skip_serializing_if = "Option::is_none")]
pub draft: Option<bool>,
#[serde(rename = "title", skip_serializing_if = "Option::is_none")]
pub title: Option<String>,
#[serde(rename = "body", skip_serializing_if = "Option::is_none")]
pub body: Option<String>,
#[serde(rename = "base", skip_serializing_if = "Option::is_none")]
pub base: Option<String>,
#[serde(rename = "head", skip_serializing_if = "Option::is_none")]
pub head: Option<String>,
#[serde(rename = "base_sha", skip_serializing_if = "Option::is_none")]
pub base_sha: Option<String>,
#[serde(rename = "head_sha", skip_serializing_if = "Option::is_none")]
pub head_sha: Option<String>,
#[serde(rename = "merge_commit_sha", skip_serializing_if = "Option::is_none")]
pub merge_commit_sha: Option<String>,
#[serde(rename = "comments", skip_serializing_if = "Option::is_none")]
pub comments: Option<serde_json::Value>,
#[serde(rename = "diff", skip_serializing_if = "Option::is_none")]
pub diff: Option<serde_json::Value>,
#[serde(rename = "user", skip_serializing_if = "Option::is_none")]
pub user: Option<serde_json::Value>,
}
impl GitPullRequest {
pub fn new(
number: i32,
url: String,
state: String,
merged: bool,
mergeable: bool,
) -> GitPullRequest {
GitPullRequest {
number,
url,
state,
merged,
mergeable,
draft: None,
title: None,
body: None,
base: None,
head: None,
base_sha: None,
head_sha: None,
merge_commit_sha: None,
comments: None,
diff: None,
user: None,
}
}
}

View File

@@ -1,22 +0,0 @@
// Curated minimal export list for current workspace usage.
// NOTE: This file was previously auto-generated by the OpenAPI generator.
// Currently export only the types referenced by the workspace
// The process for this will change
pub mod code_task_details_response;
pub use self::code_task_details_response::CodeTaskDetailsResponse;
pub mod task_response;
pub use self::task_response::TaskResponse;
pub mod external_pull_request_response;
pub use self::external_pull_request_response::ExternalPullRequestResponse;
pub mod git_pull_request;
pub use self::git_pull_request::GitPullRequest;
pub mod task_list_item;
pub use self::task_list_item::TaskListItem;
pub mod paginated_list_task_list_item_;
pub use self::paginated_list_task_list_item_::PaginatedListTaskListItem;

View File

@@ -1,30 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use crate::models;
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct PaginatedListTaskListItem {
#[serde(rename = "items")]
pub items: Vec<models::TaskListItem>,
#[serde(rename = "cursor", skip_serializing_if = "Option::is_none")]
pub cursor: Option<String>,
}
impl PaginatedListTaskListItem {
pub fn new(items: Vec<models::TaskListItem>) -> PaginatedListTaskListItem {
PaginatedListTaskListItem {
items,
cursor: None,
}
}
}

View File

@@ -1,63 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use crate::models;
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct TaskListItem {
#[serde(rename = "id")]
pub id: String,
#[serde(rename = "title")]
pub title: String,
#[serde(
rename = "has_generated_title",
skip_serializing_if = "Option::is_none"
)]
pub has_generated_title: Option<bool>,
#[serde(rename = "updated_at", skip_serializing_if = "Option::is_none")]
pub updated_at: Option<f64>,
#[serde(rename = "created_at", skip_serializing_if = "Option::is_none")]
pub created_at: Option<f64>,
#[serde(
rename = "task_status_display",
skip_serializing_if = "Option::is_none"
)]
pub task_status_display: Option<std::collections::HashMap<String, serde_json::Value>>,
#[serde(rename = "archived")]
pub archived: bool,
#[serde(rename = "has_unread_turn")]
pub has_unread_turn: bool,
#[serde(rename = "pull_requests", skip_serializing_if = "Option::is_none")]
pub pull_requests: Option<Vec<models::ExternalPullRequestResponse>>,
}
impl TaskListItem {
pub fn new(
id: String,
title: String,
has_generated_title: Option<bool>,
archived: bool,
has_unread_turn: bool,
) -> TaskListItem {
TaskListItem {
id,
title,
has_generated_title,
updated_at: None,
created_at: None,
task_status_display: None,
archived,
has_unread_turn,
pull_requests: None,
}
}
}

View File

@@ -1,62 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use crate::models;
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct TaskResponse {
#[serde(rename = "id")]
pub id: String,
#[serde(rename = "created_at", skip_serializing_if = "Option::is_none")]
pub created_at: Option<f64>,
#[serde(rename = "title")]
pub title: String,
#[serde(
rename = "has_generated_title",
skip_serializing_if = "Option::is_none"
)]
pub has_generated_title: Option<bool>,
#[serde(rename = "current_turn_id", skip_serializing_if = "Option::is_none")]
pub current_turn_id: Option<String>,
#[serde(rename = "has_unread_turn", skip_serializing_if = "Option::is_none")]
pub has_unread_turn: Option<bool>,
#[serde(
rename = "denormalized_metadata",
skip_serializing_if = "Option::is_none"
)]
pub denormalized_metadata: Option<std::collections::HashMap<String, serde_json::Value>>,
#[serde(rename = "archived")]
pub archived: bool,
#[serde(rename = "external_pull_requests")]
pub external_pull_requests: Vec<models::ExternalPullRequestResponse>,
}
impl TaskResponse {
pub fn new(
id: String,
title: String,
archived: bool,
external_pull_requests: Vec<models::ExternalPullRequestResponse>,
) -> TaskResponse {
TaskResponse {
id,
created_at: None,
title,
has_generated_title: None,
current_turn_id: None,
has_unread_turn: None,
denormalized_metadata: None,
archived,
external_pull_requests,
}
}
}

View File

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

View File

@@ -1,5 +1,4 @@
use codex_core::protocol_config_types::ReasoningEffort;
use codex_protocol::mcp_protocol::AuthMode;
/// A simple preset pairing a model slug with a reasoning effort.
#[derive(Debug, Clone, Copy)]
@@ -16,58 +15,47 @@ pub struct ModelPreset {
pub effort: Option<ReasoningEffort>,
}
const PRESETS: &[ModelPreset] = &[
ModelPreset {
id: "gpt-5-codex-low",
label: "gpt-5-codex low",
description: "",
model: "gpt-5-codex",
effort: Some(ReasoningEffort::Low),
},
ModelPreset {
id: "gpt-5-codex-medium",
label: "gpt-5-codex medium",
description: "",
model: "gpt-5-codex",
effort: Some(ReasoningEffort::Medium),
},
ModelPreset {
id: "gpt-5-codex-high",
label: "gpt-5-codex high",
description: "",
model: "gpt-5-codex",
effort: Some(ReasoningEffort::High),
},
ModelPreset {
id: "gpt-5-minimal",
label: "gpt-5 minimal",
description: "— fastest responses with limited reasoning; ideal for coding, instructions, or lightweight tasks",
model: "gpt-5",
effort: Some(ReasoningEffort::Minimal),
},
ModelPreset {
id: "gpt-5-low",
label: "gpt-5 low",
description: "— balances speed with some reasoning; useful for straightforward queries and short explanations",
model: "gpt-5",
effort: Some(ReasoningEffort::Low),
},
ModelPreset {
id: "gpt-5-medium",
label: "gpt-5 medium",
description: "— default setting; provides a solid balance of reasoning depth and latency for general-purpose tasks",
model: "gpt-5",
effort: Some(ReasoningEffort::Medium),
},
ModelPreset {
id: "gpt-5-high",
label: "gpt-5 high",
description: "— maximizes reasoning depth for complex or ambiguous problems",
model: "gpt-5",
effort: Some(ReasoningEffort::High),
},
];
pub fn builtin_model_presets(_auth_mode: Option<AuthMode>) -> Vec<ModelPreset> {
PRESETS.to_vec()
/// Built-in list of model presets that pair a model with a reasoning effort.
///
/// Keep this UI-agnostic so it can be reused by both TUI and MCP server.
pub fn builtin_model_presets() -> &'static [ModelPreset] {
// Order reflects effort from minimal to high.
const PRESETS: &[ModelPreset] = &[
ModelPreset {
id: "gpt-5-minimal",
label: "gpt-5 minimal",
description: "— fastest responses with limited reasoning; ideal for coding, instructions, or lightweight tasks",
model: "gpt-5",
effort: Some(ReasoningEffort::Minimal),
},
ModelPreset {
id: "gpt-5-low",
label: "gpt-5 low",
description: "— balances speed with some reasoning; useful for straightforward queries and short explanations",
model: "gpt-5",
effort: Some(ReasoningEffort::Low),
},
ModelPreset {
id: "gpt-5-medium",
label: "gpt-5 medium",
description: "— default setting; provides a solid balance of reasoning depth and latency for general-purpose tasks",
model: "gpt-5",
effort: Some(ReasoningEffort::Medium),
},
ModelPreset {
id: "gpt-5-high",
label: "gpt-5 high",
description: "— maximizes reasoning depth for complex or ambiguous problems",
model: "gpt-5",
effort: Some(ReasoningEffort::High),
},
ModelPreset {
id: "gpt-5-high-new",
label: "gpt-5 high new",
description: "— our latest release tuned to rely on the model's built-in reasoning defaults",
model: "gpt-5-high-new",
effort: None,
},
];
PRESETS
}

View File

@@ -4,95 +4,83 @@ name = "codex-core"
version = { workspace = true }
[lib]
doctest = false
name = "codex_core"
path = "src/lib.rs"
doctest = false
[lints]
workspace = true
[dependencies]
anyhow = { workspace = true }
askama = { workspace = true }
async-channel = { workspace = true }
async-trait = { workspace = true }
base64 = { workspace = true }
bytes = { workspace = true }
chrono = { workspace = true, features = ["serde"] }
codex-apply-patch = { workspace = true }
codex-file-search = { workspace = true }
codex-mcp-client = { workspace = true }
codex-rmcp-client = { workspace = true }
codex-protocol = { workspace = true }
codex-otel = { workspace = true, features = ["otel"] }
dirs = { workspace = true }
env-flags = { workspace = true }
eventsource-stream = { workspace = true }
futures = { workspace = true }
indexmap = { workspace = true }
libc = { workspace = true }
mcp-types = { workspace = true }
os_info = { workspace = true }
portable-pty = { workspace = true }
rand = { workspace = true }
regex-lite = { workspace = true }
reqwest = { workspace = true, features = ["json", "stream"] }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
sha1 = { workspace = true }
shlex = { workspace = true }
similar = { workspace = true }
strum_macros = { workspace = true }
tempfile = { workspace = true }
thiserror = { workspace = true }
time = { workspace = true, features = [
"formatting",
"parsing",
"local-offset",
"macros",
] }
tokio = { workspace = true, features = [
anyhow = "1"
askama = "0.12"
async-channel = "2.3.1"
base64 = "0.22"
bytes = "1.10.1"
chrono = { version = "0.4", features = ["serde"] }
codex-apply-patch = { path = "../apply-patch" }
codex-mcp-client = { path = "../mcp-client" }
codex-protocol = { path = "../protocol" }
dirs = "6"
env-flags = "0.1.1"
eventsource-stream = "0.2.3"
futures = "0.3"
libc = "0.2.175"
mcp-types = { path = "../mcp-types" }
os_info = "3.12.0"
portable-pty = "0.9.0"
rand = "0.9"
regex-lite = "0.1.7"
reqwest = { version = "0.12", features = ["json", "stream"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
sha1 = "0.10.6"
shlex = "1.3.0"
similar = "2.7.0"
strum_macros = "0.27.2"
tempfile = "3"
thiserror = "2.0.16"
time = { version = "0.3", features = ["formatting", "parsing", "local-offset", "macros"] }
tokio = { version = "1", features = [
"io-std",
"macros",
"process",
"rt-multi-thread",
"signal",
] }
tokio-util = { workspace = true }
toml = { workspace = true }
toml_edit = { workspace = true }
tracing = { workspace = true, features = ["log"] }
tree-sitter = { workspace = true }
tree-sitter-bash = { workspace = true }
uuid = { workspace = true, features = ["serde", "v4"] }
which = { workspace = true }
wildmatch = { workspace = true }
tokio-util = "0.7.16"
toml = "0.9.5"
toml_edit = "0.23.4"
tracing = { version = "0.1.41", features = ["log"] }
tree-sitter = "0.25.9"
tree-sitter-bash = "0.25.0"
uuid = { version = "1", features = ["serde", "v4"] }
which = "6"
wildmatch = "2.4.0"
[target.'cfg(target_os = "linux")'.dependencies]
landlock = { workspace = true }
seccompiler = { workspace = true }
landlock = "0.4.1"
seccompiler = "0.5.0"
# Build OpenSSL from source for musl builds.
[target.x86_64-unknown-linux-musl.dependencies]
openssl-sys = { workspace = true, features = ["vendored"] }
openssl-sys = { version = "*", features = ["vendored"] }
# Build OpenSSL from source for musl builds.
[target.aarch64-unknown-linux-musl.dependencies]
openssl-sys = { workspace = true, features = ["vendored"] }
openssl-sys = { version = "*", features = ["vendored"] }
[dev-dependencies]
assert_cmd = { workspace = true }
core_test_support = { workspace = true }
escargot = { workspace = true }
maplit = { workspace = true }
predicates = { workspace = true }
pretty_assertions = { workspace = true }
tempfile = { workspace = true }
tokio-test = { workspace = true }
walkdir = { workspace = true }
wiremock = { workspace = true }
tracing-test = { workspace = true, features = ["no-env-filter"] }
assert_cmd = "2"
core_test_support = { path = "tests/common" }
maplit = "1.0.2"
predicates = "3"
pretty_assertions = "1.4.1"
tempfile = "3"
tokio-test = "0.4"
walkdir = "2.5.0"
wiremock = "0.6"
[package.metadata.cargo-shear]
ignored = ["openssl-sys"]

View File

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

View File

@@ -251,16 +251,6 @@ You are producing plain text that will later be styled by the CLI. Follow these
- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.
- Never mix monospace and bold markers; choose one based on whether its a keyword (`**`) or inline code/path (`` ` ``).
**File References**
When referencing files in your response, make sure to include the relevant start line and always follow the below rules:
* Use inline code to make file paths clickable.
* Each reference should have a stand alone path. Even if it's the same file.
* Accepted: absolute, workspacerelative, a/ or b/ diff prefixes, or bare filename/suffix.
* Line/column (1based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
* Do not use URIs like file://, vscode://, or https://.
* Do not provide range of lines
* Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5
**Structure**
- Place related bullets together; dont mix unrelated concepts in the same section.

View File

@@ -1,12 +1,13 @@
use crate::codex::Session;
use crate::codex::TurnContext;
use crate::function_tool::FunctionCallError;
use crate::protocol::FileChange;
use crate::protocol::ReviewDecision;
use crate::safety::SafetyCheck;
use crate::safety::assess_patch_safety;
use codex_apply_patch::ApplyPatchAction;
use codex_apply_patch::ApplyPatchFileChange;
use codex_protocol::models::FunctionCallOutputPayload;
use codex_protocol::models::ResponseInputItem;
use std::collections::HashMap;
use std::path::PathBuf;
@@ -16,7 +17,7 @@ pub(crate) enum InternalApplyPatchInvocation {
/// The `apply_patch` call was handled programmatically, without any sort
/// of sandbox, because the user explicitly approved it. This is the
/// result to use with the `shell` function call that contained `apply_patch`.
Output(Result<String, FunctionCallError>),
Output(ResponseInputItem),
/// The `apply_patch` call was approved, either automatically because it
/// appears that it should be allowed based on the user's sandbox policy
@@ -32,6 +33,12 @@ pub(crate) struct ApplyPatchExec {
pub(crate) user_explicitly_approved_this_action: bool,
}
impl From<ResponseInputItem> for InternalApplyPatchInvocation {
fn from(item: ResponseInputItem) -> Self {
InternalApplyPatchInvocation::Output(item)
}
}
pub(crate) async fn apply_patch(
sess: &Session,
turn_context: &TurnContext,
@@ -45,13 +52,12 @@ pub(crate) async fn apply_patch(
&turn_context.sandbox_policy,
&turn_context.cwd,
) {
SafetyCheck::AutoApprove {
user_explicitly_approved,
..
} => InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
action,
user_explicitly_approved_this_action: user_explicitly_approved,
}),
SafetyCheck::AutoApprove { .. } => {
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
action,
user_explicitly_approved_this_action: false,
})
}
SafetyCheck::AskUser => {
// Compute a readable summary of path changes to include in the
// approval request so the user can make an informed decision.
@@ -71,15 +77,25 @@ pub(crate) async fn apply_patch(
})
}
ReviewDecision::Denied | ReviewDecision::Abort => {
InternalApplyPatchInvocation::Output(Err(FunctionCallError::RespondToModel(
"patch rejected by user".to_string(),
)))
ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: "patch rejected by user".to_string(),
success: Some(false),
},
}
.into()
}
}
}
SafetyCheck::Reject { reason } => InternalApplyPatchInvocation::Output(Err(
FunctionCallError::RespondToModel(format!("patch rejected: {reason}")),
)),
SafetyCheck::Reject { reason } => ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: format!("patch rejected: {reason}"),
success: Some(false),
},
}
.into(),
}
}

View File

@@ -267,9 +267,6 @@ pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
}
pub fn write_auth_json(auth_file: &Path, auth_dot_json: &AuthDotJson) -> std::io::Result<()> {
if let Some(parent) = auth_file.parent() {
std::fs::create_dir_all(parent)?;
}
let json_data = serde_json::to_string_pretty(auth_dot_json)?;
let mut options = OpenOptions::new();
options.truncate(true).write(true).create(true);
@@ -411,32 +408,6 @@ mod tests {
assert_eq!(auth_dot_json, same_auth_dot_json);
}
#[test]
fn login_with_api_key_overwrites_existing_auth_json() {
let dir = tempdir().unwrap();
let auth_path = dir.path().join("auth.json");
let stale_auth = json!({
"OPENAI_API_KEY": "sk-old",
"tokens": {
"id_token": "stale.header.payload",
"access_token": "stale-access",
"refresh_token": "stale-refresh",
"account_id": "stale-acc"
}
});
std::fs::write(
&auth_path,
serde_json::to_string_pretty(&stale_auth).unwrap(),
)
.unwrap();
super::login_with_api_key(dir.path(), "sk-new").expect("login_with_api_key should succeed");
let auth = super::try_read_auth_json(&auth_path).expect("auth.json should parse");
assert_eq!(auth.openai_api_key.as_deref(), Some("sk-new"));
assert!(auth.tokens.is_none(), "tokens should be cleared");
}
#[tokio::test]
async fn pro_account_with_no_api_key_uses_chatgpt_auth() {
let codex_home = tempdir().unwrap();

View File

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

View File

@@ -1,19 +1,6 @@
use std::time::Duration;
use crate::ModelProviderInfo;
use crate::client_common::Prompt;
use crate::client_common::ResponseEvent;
use crate::client_common::ResponseStream;
use crate::error::CodexErr;
use crate::error::Result;
use crate::model_family::ModelFamily;
use crate::openai_tools::create_tools_json_for_chat_completions_api;
use crate::util::backoff;
use bytes::Bytes;
use codex_otel::otel_event_manager::OtelEventManager;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ReasoningItemContent;
use codex_protocol::models::ResponseItem;
use eventsource_stream::Eventsource;
use futures::Stream;
use futures::StreamExt;
@@ -28,20 +15,26 @@ use tokio::time::timeout;
use tracing::debug;
use tracing::trace;
use crate::ModelProviderInfo;
use crate::client_common::Prompt;
use crate::client_common::ResponseEvent;
use crate::client_common::ResponseStream;
use crate::error::CodexErr;
use crate::error::Result;
use crate::model_family::ModelFamily;
use crate::openai_tools::create_tools_json_for_chat_completions_api;
use crate::util::backoff;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ReasoningItemContent;
use codex_protocol::models::ResponseItem;
/// Implementation for the classic Chat Completions API.
pub(crate) async fn stream_chat_completions(
prompt: &Prompt,
model_family: &ModelFamily,
client: &reqwest::Client,
provider: &ModelProviderInfo,
otel_event_manager: &OtelEventManager,
) -> Result<ResponseStream> {
if prompt.output_schema.is_some() {
return Err(CodexErr::UnsupportedOperation(
"output_schema is not supported for Chat Completions API".to_string(),
));
}
// Build messages array
let mut messages = Vec::<serde_json::Value>::new();
@@ -295,13 +288,10 @@ pub(crate) async fn stream_chat_completions(
let req_builder = provider.create_request_builder(client, &None).await?;
let res = otel_event_manager
.log_request(attempt, || {
req_builder
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload)
.send()
})
let res = req_builder
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload)
.send()
.await;
match res {
@@ -312,7 +302,6 @@ pub(crate) async fn stream_chat_completions(
stream,
tx_event,
provider.stream_idle_timeout(),
otel_event_manager.clone(),
));
return Ok(ResponseStream { rx_event });
}
@@ -356,7 +345,6 @@ async fn process_chat_sse<S>(
stream: S,
tx_event: mpsc::Sender<Result<ResponseEvent>>,
idle_timeout: Duration,
otel_event_manager: OtelEventManager,
) where
S: Stream<Item = Result<Bytes>> + Unpin,
{
@@ -380,10 +368,7 @@ async fn process_chat_sse<S>(
let mut reasoning_text = String::new();
loop {
let sse = match otel_event_manager
.log_sse_event(|| timeout(idle_timeout, stream.next()))
.await
{
let sse = match timeout(idle_timeout, stream.next()).await {
Ok(Some(Ok(ev))) => ev,
Ok(Some(Err(e))) => {
let _ = tx_event
@@ -477,7 +462,7 @@ async fn process_chat_sse<S>(
if let Some(reasoning_val) = choice.get("delta").and_then(|d| d.get("reasoning")) {
let mut maybe_text = reasoning_val
.as_str()
.map(str::to_string)
.map(|s| s.to_string())
.filter(|s| !s.is_empty());
if maybe_text.is_none() && reasoning_val.is_object() {
@@ -731,9 +716,6 @@ where
// Not an assistant message forward immediately.
return Poll::Ready(Some(Ok(ResponseEvent::OutputItemDone(item))));
}
Poll::Ready(Some(Ok(ResponseEvent::RateLimits(snapshot)))) => {
return Poll::Ready(Some(Ok(ResponseEvent::RateLimits(snapshot))));
}
Poll::Ready(Some(Ok(ResponseEvent::Completed {
response_id,
token_usage,

View File

@@ -4,7 +4,6 @@ use std::sync::OnceLock;
use std::time::Duration;
use crate::AuthManager;
use crate::auth::CodexAuth;
use bytes::Bytes;
use codex_protocol::mcp_protocol::AuthMode;
use codex_protocol::mcp_protocol::ConversationId;
@@ -12,7 +11,6 @@ use eventsource_stream::Eventsource;
use futures::prelude::*;
use regex_lite::Regex;
use reqwest::StatusCode;
use reqwest::header::HeaderMap;
use serde::Deserialize;
use serde::Serialize;
use serde_json::Value;
@@ -42,12 +40,9 @@ 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::RateLimitSnapshot;
use crate::protocol::RateLimitWindow;
use crate::protocol::TokenUsage;
use crate::token_data::PlanType;
use crate::util::backoff;
use codex_otel::otel_event_manager::OtelEventManager;
use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
use codex_protocol::models::ResponseItem;
@@ -74,7 +69,6 @@ struct Error {
pub struct ModelClient {
config: Arc<Config>,
auth_manager: Option<Arc<AuthManager>>,
otel_event_manager: OtelEventManager,
client: reqwest::Client,
provider: ModelProviderInfo,
conversation_id: ConversationId,
@@ -86,7 +80,6 @@ impl ModelClient {
pub fn new(
config: Arc<Config>,
auth_manager: Option<Arc<AuthManager>>,
otel_event_manager: OtelEventManager,
provider: ModelProviderInfo,
effort: Option<ReasoningEffortConfig>,
summary: ReasoningSummaryConfig,
@@ -97,7 +90,6 @@ impl ModelClient {
Self {
config,
auth_manager,
otel_event_manager,
client,
provider,
conversation_id,
@@ -131,7 +123,6 @@ impl ModelClient {
&self.config.model_family,
&self.client,
&self.provider,
&self.otel_event_manager,
)
.await?;
@@ -168,12 +159,7 @@ impl ModelClient {
if let Some(path) = &*CODEX_RS_SSE_FIXTURE {
// short circuit for tests
warn!(path, "Streaming from fixture");
return stream_from_fixture(
path,
self.provider.clone(),
self.otel_event_manager.clone(),
)
.await;
return stream_from_fixture(path, self.provider.clone()).await;
}
let auth_manager = self.auth_manager.clone();
@@ -194,22 +180,18 @@ impl ModelClient {
let input_with_instructions = prompt.get_formatted_input();
let verbosity = match &self.config.model_family.family {
family if family == "gpt-5" => self.config.model_verbosity,
_ => {
if self.config.model_verbosity.is_some() {
warn!(
"model_verbosity is set but ignored for non-gpt-5 model family: {}",
self.config.model_family.family
);
}
None
}
};
// Only include `text.verbosity` for GPT-5 family models
let text = create_text_param_for_request(verbosity, &prompt.output_schema);
let text = if self.config.model_family.family == "gpt-5" {
create_text_param_for_request(self.config.model_verbosity)
} else {
if self.config.model_verbosity.is_some() {
warn!(
"model_verbosity is set but ignored for non-gpt-5 model family: {}",
self.config.model_family.family
);
}
None
};
// In general, we want to explicitly send `store: false` when using the Responses API,
// but in practice, the Azure Responses API rejects `store: false`:
@@ -239,175 +221,144 @@ impl ModelClient {
if azure_workaround {
attach_item_ids(&mut payload_json, &input_with_instructions);
}
let payload_body = serde_json::to_string(&payload_json)?;
let max_attempts = self.provider.request_max_retries();
for attempt in 0..=max_attempts {
match self
.attempt_stream_responses(attempt, &payload_json, &auth_manager)
.await
let mut attempt = 0;
let max_retries = self.provider.request_max_retries();
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),
payload_body.as_str()
);
let mut req_builder = self
.provider
.create_request_builder(&self.client, &auth)
.await?;
req_builder = req_builder
.header("OpenAI-Beta", "responses=experimental")
// Send session_id for compatibility.
.header("conversation_id", self.conversation_id.to_string())
.header("session_id", self.conversation_id.to_string())
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload_json);
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Some(account_id) = auth.get_account_id()
{
Ok(stream) => {
return Ok(stream);
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
let res = req_builder.send().await;
if let Ok(resp) = &res {
trace!(
"Response status: {}, cf-ray: {}",
resp.status(),
resp.headers()
.get("cf-ray")
.map(|v| v.to_str().unwrap_or_default())
.unwrap_or_default()
);
}
match res {
Ok(resp) if resp.status().is_success() => {
let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
// spawn task to process SSE
let stream = resp.bytes_stream().map_err(CodexErr::Reqwest);
tokio::spawn(process_sse(
stream,
tx_event,
self.provider.stream_idle_timeout(),
));
return Ok(ResponseStream { rx_event });
}
Err(StreamAttemptError::Fatal(e)) => {
return Err(e);
}
Err(retryable_attempt_error) => {
if attempt == max_attempts {
return Err(retryable_attempt_error.into_error());
Ok(res) => {
let status = res.status();
// Pull out RetryAfter header if present.
let retry_after_secs = res
.headers()
.get(reqwest::header::RETRY_AFTER)
.and_then(|v| v.to_str().ok())
.and_then(|s| s.parse::<u64>().ok());
if status == StatusCode::UNAUTHORIZED
&& let Some(manager) = auth_manager.as_ref()
&& manager.auth().is_some()
{
let _ = manager.refresh_token().await;
}
tokio::time::sleep(retryable_attempt_error.delay(attempt)).await;
}
}
}
// The OpenAI Responses endpoint returns structured JSON bodies even for 4xx/5xx
// errors. When we bubble early with only the HTTP status the caller sees an opaque
// "unexpected status 400 Bad Request" which makes debugging nearly impossible.
// Instead, read (and include) the response text so higher layers and users see the
// exact error message (e.g. "Unknown parameter: 'input[0].metadata'"). The body is
// small and this branch only runs on error paths so the extra allocation is
// negligible.
if !(status == StatusCode::TOO_MANY_REQUESTS
|| status == StatusCode::UNAUTHORIZED
|| status.is_server_error())
{
// Surface the error body to callers. Use `unwrap_or_default` per Clippy.
let body = res.text().await.unwrap_or_default();
return Err(CodexErr::UnexpectedStatus(status, body));
}
unreachable!("stream_responses_attempt should always return");
}
/// Single attempt to start a streaming Responses API call.
async fn attempt_stream_responses(
&self,
attempt: u64,
payload_json: &Value,
auth_manager: &Option<Arc<AuthManager>>,
) -> std::result::Result<ResponseStream, StreamAttemptError> {
// Always fetch the latest auth in case a prior attempt refreshed the token.
let auth = auth_manager.as_ref().and_then(|m| m.auth());
trace!(
"POST to {}: {:?}",
self.provider.get_full_url(&auth),
serde_json::to_string(payload_json)
);
let mut req_builder = self
.provider
.create_request_builder(&self.client, &auth)
.await
.map_err(StreamAttemptError::Fatal)?;
req_builder = req_builder
.header("OpenAI-Beta", "responses=experimental")
// Send session_id for compatibility.
.header("conversation_id", self.conversation_id.to_string())
.header("session_id", self.conversation_id.to_string())
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(payload_json);
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Some(account_id) = auth.get_account_id()
{
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
let res = self
.otel_event_manager
.log_request(attempt, || req_builder.send())
.await;
if let Ok(resp) = &res {
trace!(
"Response status: {}, cf-ray: {}",
resp.status(),
resp.headers()
.get("cf-ray")
.map(|v| v.to_str().unwrap_or_default())
.unwrap_or_default()
);
}
match res {
Ok(resp) if resp.status().is_success() => {
let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
if let Some(snapshot) = parse_rate_limit_snapshot(resp.headers())
&& tx_event
.send(Ok(ResponseEvent::RateLimits(snapshot)))
.await
.is_err()
{
debug!("receiver dropped rate limit snapshot event");
}
// spawn task to process SSE
let stream = resp.bytes_stream().map_err(CodexErr::Reqwest);
tokio::spawn(process_sse(
stream,
tx_event,
self.provider.stream_idle_timeout(),
self.otel_event_manager.clone(),
));
Ok(ResponseStream { rx_event })
}
Ok(res) => {
let status = res.status();
// Pull out RetryAfter header if present.
let retry_after_secs = res
.headers()
.get(reqwest::header::RETRY_AFTER)
.and_then(|v| v.to_str().ok())
.and_then(|s| s.parse::<u64>().ok());
let retry_after = retry_after_secs.map(|s| Duration::from_millis(s * 1_000));
if status == StatusCode::UNAUTHORIZED
&& let Some(manager) = auth_manager.as_ref()
&& manager.auth().is_some()
{
let _ = manager.refresh_token().await;
}
// The OpenAI Responses endpoint returns structured JSON bodies even for 4xx/5xx
// errors. When we bubble early with only the HTTP status the caller sees an opaque
// "unexpected status 400 Bad Request" which makes debugging nearly impossible.
// Instead, read (and include) the response text so higher layers and users see the
// exact error message (e.g. "Unknown parameter: 'input[0].metadata'"). The body is
// small and this branch only runs on error paths so the extra allocation is
// negligible.
if !(status == StatusCode::TOO_MANY_REQUESTS
|| status == StatusCode::UNAUTHORIZED
|| status.is_server_error())
{
// Surface the error body to callers. Use `unwrap_or_default` per Clippy.
let body = res.text().await.unwrap_or_default();
return Err(StreamAttemptError::Fatal(CodexErr::UnexpectedStatus(
status, body,
)));
}
if status == StatusCode::TOO_MANY_REQUESTS {
let rate_limit_snapshot = parse_rate_limit_snapshot(res.headers());
let body = res.json::<ErrorResponse>().await.ok();
if let Some(ErrorResponse { error }) = body {
if error.r#type.as_deref() == Some("usage_limit_reached") {
// Prefer the plan_type provided in the error message if present
// because it's more up to date than the one encoded in the auth
// token.
let plan_type = error
.plan_type
.or_else(|| auth.as_ref().and_then(CodexAuth::get_plan_type));
let resets_in_seconds = error.resets_in_seconds;
let codex_err = CodexErr::UsageLimitReached(UsageLimitReachedError {
plan_type,
resets_in_seconds,
rate_limits: rate_limit_snapshot,
});
return Err(StreamAttemptError::Fatal(codex_err));
} else if error.r#type.as_deref() == Some("usage_not_included") {
return Err(StreamAttemptError::Fatal(CodexErr::UsageNotIncluded));
if status == StatusCode::TOO_MANY_REQUESTS {
let body = res.json::<ErrorResponse>().await.ok();
if let Some(ErrorResponse { error }) = body {
if error.r#type.as_deref() == Some("usage_limit_reached") {
// Prefer the plan_type provided in the error message if present
// because it's more up to date than the one encoded in the auth
// token.
let plan_type = error
.plan_type
.or_else(|| auth.as_ref().and_then(|a| a.get_plan_type()));
let resets_in_seconds = error.resets_in_seconds;
return Err(CodexErr::UsageLimitReached(UsageLimitReachedError {
plan_type,
resets_in_seconds,
}));
} else if error.r#type.as_deref() == Some("usage_not_included") {
return Err(CodexErr::UsageNotIncluded);
}
}
}
}
Err(StreamAttemptError::RetryableHttpError {
status,
retry_after,
})
if attempt > max_retries {
if status == StatusCode::INTERNAL_SERVER_ERROR {
return Err(CodexErr::InternalServerError);
}
return Err(CodexErr::RetryLimit(status));
}
let delay = retry_after_secs
.map(|s| Duration::from_millis(s * 1_000))
.unwrap_or_else(|| backoff(attempt));
tokio::time::sleep(delay).await;
}
Err(e) => {
if attempt > max_retries {
return Err(e.into());
}
let delay = backoff(attempt);
tokio::time::sleep(delay).await;
}
}
Err(e) => Err(StreamAttemptError::RetryableTransportError(e.into())),
}
}
@@ -415,10 +366,6 @@ impl ModelClient {
self.provider.clone()
}
pub fn get_otel_event_manager(&self) -> OtelEventManager {
self.otel_event_manager.clone()
}
/// Returns the currently configured model slug.
pub fn get_model(&self) -> String {
self.config.model.clone()
@@ -444,47 +391,6 @@ impl ModelClient {
}
}
enum StreamAttemptError {
RetryableHttpError {
status: StatusCode,
retry_after: Option<Duration>,
},
RetryableTransportError(CodexErr),
Fatal(CodexErr),
}
impl StreamAttemptError {
/// attempt is 0-based.
fn delay(&self, attempt: u64) -> Duration {
// backoff() uses 1-based attempts.
let backoff_attempt = attempt + 1;
match self {
Self::RetryableHttpError { retry_after, .. } => {
retry_after.unwrap_or_else(|| backoff(backoff_attempt))
}
Self::RetryableTransportError { .. } => backoff(backoff_attempt),
Self::Fatal(_) => {
// Should not be called on Fatal errors.
Duration::from_secs(0)
}
}
}
fn into_error(self) -> CodexErr {
match self {
Self::RetryableHttpError { status, .. } => {
if status == StatusCode::INTERNAL_SERVER_ERROR {
CodexErr::InternalServerError
} else {
CodexErr::RetryLimit(status)
}
}
Self::RetryableTransportError(error) => error,
Self::Fatal(error) => error,
}
}
}
#[derive(Debug, Deserialize, Serialize)]
struct SseEvent {
#[serde(rename = "type")]
@@ -494,6 +400,9 @@ struct SseEvent {
delta: Option<String>,
}
#[derive(Debug, Deserialize)]
struct ResponseCreated {}
#[derive(Debug, Deserialize)]
struct ResponseCompleted {
id: String,
@@ -564,68 +473,10 @@ fn attach_item_ids(payload_json: &mut Value, original_items: &[ResponseItem]) {
}
}
fn parse_rate_limit_snapshot(headers: &HeaderMap) -> Option<RateLimitSnapshot> {
let primary = parse_rate_limit_window(
headers,
"x-codex-primary-used-percent",
"x-codex-primary-window-minutes",
"x-codex-primary-reset-after-seconds",
);
let secondary = parse_rate_limit_window(
headers,
"x-codex-secondary-used-percent",
"x-codex-secondary-window-minutes",
"x-codex-secondary-reset-after-seconds",
);
Some(RateLimitSnapshot { primary, secondary })
}
fn parse_rate_limit_window(
headers: &HeaderMap,
used_percent_header: &str,
window_minutes_header: &str,
resets_header: &str,
) -> Option<RateLimitWindow> {
let used_percent: Option<f64> = parse_header_f64(headers, used_percent_header);
used_percent.and_then(|used_percent| {
let window_minutes = parse_header_u64(headers, window_minutes_header);
let resets_in_seconds = parse_header_u64(headers, resets_header);
let has_data = used_percent != 0.0
|| window_minutes.is_some_and(|minutes| minutes != 0)
|| resets_in_seconds.is_some_and(|seconds| seconds != 0);
has_data.then_some(RateLimitWindow {
used_percent,
window_minutes,
resets_in_seconds,
})
})
}
fn parse_header_f64(headers: &HeaderMap, name: &str) -> Option<f64> {
parse_header_str(headers, name)?
.parse::<f64>()
.ok()
.filter(|v| v.is_finite())
}
fn parse_header_u64(headers: &HeaderMap, name: &str) -> Option<u64> {
parse_header_str(headers, name)?.parse::<u64>().ok()
}
fn parse_header_str<'a>(headers: &'a HeaderMap, name: &str) -> Option<&'a str> {
headers.get(name)?.to_str().ok()
}
async fn process_sse<S>(
stream: S,
tx_event: mpsc::Sender<Result<ResponseEvent>>,
idle_timeout: Duration,
otel_event_manager: OtelEventManager,
) where
S: Stream<Item = Result<Bytes>> + Unpin,
{
@@ -637,10 +488,7 @@ async fn process_sse<S>(
let mut response_error: Option<CodexErr> = None;
loop {
let sse = match otel_event_manager
.log_sse_event(|| timeout(idle_timeout, stream.next()))
.await
{
let sse = match timeout(idle_timeout, stream.next()).await {
Ok(Some(Ok(sse))) => sse,
Ok(Some(Err(e))) => {
debug!("SSE Error: {e:#}");
@@ -654,21 +502,6 @@ async fn process_sse<S>(
id: response_id,
usage,
}) => {
if let Some(token_usage) = &usage {
otel_event_manager.sse_event_completed(
token_usage.input_tokens,
token_usage.output_tokens,
token_usage
.input_tokens_details
.as_ref()
.map(|d| d.cached_tokens),
token_usage
.output_tokens_details
.as_ref()
.map(|d| d.reasoning_tokens),
token_usage.total_tokens,
);
}
let event = ResponseEvent::Completed {
response_id,
token_usage: usage.map(Into::into),
@@ -676,13 +509,12 @@ async fn process_sse<S>(
let _ = tx_event.send(Ok(event)).await;
}
None => {
let error = response_error.unwrap_or(CodexErr::Stream(
"stream closed before response.completed".into(),
None,
));
otel_event_manager.see_event_completed_failed(&error);
let _ = tx_event.send(Err(error)).await;
let _ = tx_event
.send(Err(response_error.unwrap_or(CodexErr::Stream(
"stream closed before response.completed".into(),
None,
))))
.await;
}
}
return;
@@ -786,9 +618,7 @@ async fn process_sse<S>(
response_error = Some(CodexErr::Stream(message, delay));
}
Err(e) => {
let error = format!("failed to parse ErrorResponse: {e}");
debug!(error);
response_error = Some(CodexErr::Stream(error, None))
debug!("failed to parse ErrorResponse: {e}");
}
}
}
@@ -802,9 +632,7 @@ async fn process_sse<S>(
response_completed = Some(r);
}
Err(e) => {
let error = format!("failed to parse ResponseCompleted: {e}");
debug!(error);
response_error = Some(CodexErr::Stream(error, None));
debug!("failed to parse ResponseCompleted: {e}");
continue;
}
};
@@ -851,7 +679,6 @@ async fn process_sse<S>(
async fn stream_from_fixture(
path: impl AsRef<Path>,
provider: ModelProviderInfo,
otel_event_manager: OtelEventManager,
) -> Result<ResponseStream> {
let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
let f = std::fs::File::open(path.as_ref())?;
@@ -870,7 +697,6 @@ async fn stream_from_fixture(
stream,
tx_event,
provider.stream_idle_timeout(),
otel_event_manager,
));
Ok(ResponseStream { rx_event })
}
@@ -926,7 +752,6 @@ mod tests {
async fn collect_events(
chunks: &[&[u8]],
provider: ModelProviderInfo,
otel_event_manager: OtelEventManager,
) -> Vec<Result<ResponseEvent>> {
let mut builder = IoBuilder::new();
for chunk in chunks {
@@ -936,12 +761,7 @@ mod tests {
let reader = builder.build();
let stream = ReaderStream::new(reader).map_err(CodexErr::Io);
let (tx, mut rx) = mpsc::channel::<Result<ResponseEvent>>(16);
tokio::spawn(process_sse(
stream,
tx,
provider.stream_idle_timeout(),
otel_event_manager,
));
tokio::spawn(process_sse(stream, tx, provider.stream_idle_timeout()));
let mut events = Vec::new();
while let Some(ev) = rx.recv().await {
@@ -955,7 +775,6 @@ mod tests {
async fn run_sse(
events: Vec<serde_json::Value>,
provider: ModelProviderInfo,
otel_event_manager: OtelEventManager,
) -> Vec<ResponseEvent> {
let mut body = String::new();
for e in events {
@@ -972,12 +791,7 @@ mod tests {
let (tx, mut rx) = mpsc::channel::<Result<ResponseEvent>>(8);
let stream = ReaderStream::new(std::io::Cursor::new(body)).map_err(CodexErr::Io);
tokio::spawn(process_sse(
stream,
tx,
provider.stream_idle_timeout(),
otel_event_manager,
));
tokio::spawn(process_sse(stream, tx, provider.stream_idle_timeout()));
let mut out = Vec::new();
while let Some(ev) = rx.recv().await {
@@ -986,18 +800,6 @@ mod tests {
out
}
fn otel_event_manager() -> OtelEventManager {
OtelEventManager::new(
ConversationId::new(),
"test",
"test",
None,
Some(AuthMode::ChatGPT),
false,
"test".to_string(),
)
}
// ────────────────────────────
// Tests from `implement-test-for-responses-api-sse-parser`
// ────────────────────────────
@@ -1049,12 +851,9 @@ mod tests {
requires_openai_auth: false,
};
let otel_event_manager = otel_event_manager();
let events = collect_events(
&[sse1.as_bytes(), sse2.as_bytes(), sse3.as_bytes()],
provider,
otel_event_manager,
)
.await;
@@ -1112,9 +911,7 @@ mod tests {
requires_openai_auth: false,
};
let otel_event_manager = otel_event_manager();
let events = collect_events(&[sse1.as_bytes()], provider, otel_event_manager).await;
let events = collect_events(&[sse1.as_bytes()], provider).await;
assert_eq!(events.len(), 2);
@@ -1148,9 +945,7 @@ mod tests {
requires_openai_auth: false,
};
let otel_event_manager = otel_event_manager();
let events = collect_events(&[sse1.as_bytes()], provider, otel_event_manager).await;
let events = collect_events(&[sse1.as_bytes()], provider).await;
assert_eq!(events.len(), 1);
@@ -1255,9 +1050,7 @@ mod tests {
requires_openai_auth: false,
};
let otel_event_manager = otel_event_manager();
let out = run_sse(evs, provider, otel_event_manager).await;
let out = run_sse(evs, provider).await;
assert_eq!(out.len(), case.expected_len, "case {}", case.name);
assert!(
(case.expect_first)(&out[0]),

View File

@@ -1,7 +1,6 @@
use crate::error::Result;
use crate::model_family::ModelFamily;
use crate::openai_tools::OpenAiTool;
use crate::protocol::RateLimitSnapshot;
use crate::protocol::TokenUsage;
use codex_apply_patch::APPLY_PATCH_TOOL_INSTRUCTIONS;
use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
@@ -10,14 +9,16 @@ use codex_protocol::config_types::Verbosity as VerbosityConfig;
use codex_protocol::models::ResponseItem;
use futures::Stream;
use serde::Serialize;
use serde_json::Value;
use std::borrow::Cow;
use std::ops::Deref;
use std::pin::Pin;
use std::task::Context;
use std::task::Poll;
use tokio::sync::mpsc;
/// The `instructions` field in the payload sent to a model should always start
/// with this content.
const BASE_INSTRUCTIONS: &str = include_str!("../prompt.md");
/// Review thread system prompt. Edit `core/src/review_prompt.md` to customize.
pub const REVIEW_PROMPT: &str = include_str!("../review_prompt.md");
@@ -33,20 +34,18 @@ pub struct Prompt {
/// Optional override for the built-in BASE_INSTRUCTIONS.
pub base_instructions_override: Option<String>,
/// Optional the output schema for the model's response.
pub output_schema: Option<Value>,
}
impl Prompt {
pub(crate) fn get_full_instructions<'a>(&'a self, model: &'a ModelFamily) -> Cow<'a, str> {
pub(crate) fn get_full_instructions(&self, model: &ModelFamily) -> Cow<'_, str> {
let base = self
.base_instructions_override
.as_deref()
.unwrap_or(model.base_instructions.deref());
// When there are no custom instructions, add apply_patch_tool_instructions if:
// - the model needs special instructions (4.1)
// AND
.unwrap_or(BASE_INSTRUCTIONS);
let mut sections: Vec<&str> = vec![base];
// When there are no custom instructions, add apply_patch_tool_instructions if either:
// - the model needs special instructions (4.1), or
// - there is no apply_patch tool present
let is_apply_patch_tool_present = self.tools.iter().any(|tool| match tool {
OpenAiTool::Function(f) => f.name == "apply_patch",
@@ -54,13 +53,11 @@ impl Prompt {
_ => false,
});
if self.base_instructions_override.is_none()
&& model.needs_special_apply_patch_instructions
&& !is_apply_patch_tool_present
&& (model.needs_special_apply_patch_instructions || !is_apply_patch_tool_present)
{
Cow::Owned(format!("{base}\n{APPLY_PATCH_TOOL_INSTRUCTIONS}"))
} else {
Cow::Borrowed(base)
sections.push(APPLY_PATCH_TOOL_INSTRUCTIONS);
}
Cow::Owned(sections.join("\n"))
}
pub(crate) fn get_formatted_input(&self) -> Vec<ResponseItem> {
@@ -83,7 +80,6 @@ pub enum ResponseEvent {
WebSearchCallBegin {
call_id: String,
},
RateLimits(RateLimitSnapshot),
}
#[derive(Debug, Serialize)]
@@ -94,31 +90,14 @@ pub(crate) struct Reasoning {
pub(crate) summary: Option<ReasoningSummaryConfig>,
}
#[derive(Debug, Serialize, Default, Clone)]
#[serde(rename_all = "snake_case")]
pub(crate) enum TextFormatType {
#[default]
JsonSchema,
}
#[derive(Debug, Serialize, Default, Clone)]
pub(crate) struct TextFormat {
pub(crate) r#type: TextFormatType,
pub(crate) strict: bool,
pub(crate) schema: Value,
pub(crate) name: String,
}
/// Controls under the `text` field in the Responses API for GPT-5.
#[derive(Debug, Serialize, Default, Clone)]
#[derive(Debug, Serialize, Default, Clone, Copy)]
pub(crate) struct TextControls {
#[serde(skip_serializing_if = "Option::is_none")]
pub(crate) verbosity: Option<OpenAiVerbosity>,
#[serde(skip_serializing_if = "Option::is_none")]
pub(crate) format: Option<TextFormat>,
}
#[derive(Debug, Serialize, Default, Clone)]
#[derive(Debug, Serialize, Default, Clone, Copy)]
#[serde(rename_all = "lowercase")]
pub(crate) enum OpenAiVerbosity {
Low,
@@ -177,20 +156,9 @@ pub(crate) fn create_reasoning_param_for_request(
pub(crate) fn create_text_param_for_request(
verbosity: Option<VerbosityConfig>,
output_schema: &Option<Value>,
) -> Option<TextControls> {
if verbosity.is_none() && output_schema.is_none() {
return None;
}
Some(TextControls {
verbosity: verbosity.map(std::convert::Into::into),
format: output_schema.as_ref().map(|schema| TextFormat {
r#type: TextFormatType::JsonSchema,
strict: true,
schema: schema.clone(),
name: "codex_output_schema".to_string(),
}),
verbosity.map(|v| TextControls {
verbosity: Some(v.into()),
})
}
@@ -209,64 +177,18 @@ impl Stream for ResponseStream {
#[cfg(test)]
mod tests {
use crate::model_family::find_family_for_model;
use pretty_assertions::assert_eq;
use super::*;
struct InstructionsTestCase {
pub slug: &'static str,
pub expects_apply_patch_instructions: bool,
}
#[test]
fn get_full_instructions_no_user_content() {
let prompt = Prompt {
..Default::default()
};
let test_cases = vec![
InstructionsTestCase {
slug: "gpt-3.5",
expects_apply_patch_instructions: true,
},
InstructionsTestCase {
slug: "gpt-4.1",
expects_apply_patch_instructions: true,
},
InstructionsTestCase {
slug: "gpt-4o",
expects_apply_patch_instructions: true,
},
InstructionsTestCase {
slug: "gpt-5",
expects_apply_patch_instructions: true,
},
InstructionsTestCase {
slug: "codex-mini-latest",
expects_apply_patch_instructions: true,
},
InstructionsTestCase {
slug: "gpt-oss:120b",
expects_apply_patch_instructions: false,
},
InstructionsTestCase {
slug: "gpt-5-codex",
expects_apply_patch_instructions: false,
},
];
for test_case in test_cases {
let model_family = find_family_for_model(test_case.slug).expect("known model slug");
let expected = if test_case.expects_apply_patch_instructions {
format!(
"{}\n{}",
model_family.clone().base_instructions,
APPLY_PATCH_TOOL_INSTRUCTIONS
)
} else {
model_family.clone().base_instructions
};
let full = prompt.get_full_instructions(&model_family);
assert_eq!(full, expected);
}
let expected = format!("{BASE_INSTRUCTIONS}\n{APPLY_PATCH_TOOL_INSTRUCTIONS}");
let model_family = find_family_for_model("gpt-4.1").expect("known model slug");
let full = prompt.get_full_instructions(&model_family);
assert_eq!(full, expected);
}
#[test]
@@ -287,7 +209,6 @@ mod tests {
prompt_cache_key: None,
text: Some(TextControls {
verbosity: Some(OpenAiVerbosity::Low),
format: None,
}),
};
@@ -300,52 +221,6 @@ mod tests {
);
}
#[test]
fn serializes_text_schema_with_strict_format() {
let input: Vec<ResponseItem> = vec![];
let tools: Vec<serde_json::Value> = vec![];
let schema = serde_json::json!({
"type": "object",
"properties": {
"answer": {"type": "string"}
},
"required": ["answer"],
});
let text_controls =
create_text_param_for_request(None, &Some(schema.clone())).expect("text controls");
let req = ResponsesApiRequest {
model: "gpt-5",
instructions: "i",
input: &input,
tools: &tools,
tool_choice: "auto",
parallel_tool_calls: false,
reasoning: None,
store: false,
stream: true,
include: vec![],
prompt_cache_key: None,
text: Some(text_controls),
};
let v = serde_json::to_value(&req).expect("json");
let text = v.get("text").expect("text field");
assert!(text.get("verbosity").is_none());
let format = text.get("format").expect("format field");
assert_eq!(
format.get("name"),
Some(&serde_json::Value::String("codex_output_schema".into()))
);
assert_eq!(
format.get("type"),
Some(&serde_json::Value::String("json_schema".into()))
);
assert_eq!(format.get("strict"), Some(&serde_json::Value::Bool(true)));
assert_eq!(format.get("schema"), Some(&schema));
}
#[test]
fn omits_text_when_not_set() {
let input: Vec<ResponseItem> = vec![];

File diff suppressed because it is too large Load Diff

View File

@@ -1,5 +1,7 @@
use std::sync::Arc;
use super::AgentTask;
use super::MutexExt;
use super::Session;
use super::TurnContext;
use super::get_last_assistant_message_from_turn;
@@ -14,9 +16,9 @@ use crate::protocol::Event;
use crate::protocol::EventMsg;
use crate::protocol::InputItem;
use crate::protocol::InputMessageKind;
use crate::protocol::TaskCompleteEvent;
use crate::protocol::TaskStartedEvent;
use crate::protocol::TurnContextItem;
use crate::truncate::truncate_middle;
use crate::util::backoff;
use askama::Template;
use codex_protocol::models::ContentItem;
@@ -25,8 +27,8 @@ use codex_protocol::models::ResponseItem;
use codex_protocol::protocol::RolloutItem;
use futures::prelude::*;
pub const SUMMARIZATION_PROMPT: &str = include_str!("../../templates/compact/prompt.md");
const COMPACT_USER_MESSAGE_MAX_TOKENS: usize = 20_000;
pub(super) const COMPACT_TRIGGER_TEXT: &str = "Start Summarization";
const SUMMARIZATION_PROMPT: &str = include_str!("../../templates/compact/prompt.md");
#[derive(Template)]
#[template(path = "compact/history_bridge.md", escape = "none")]
@@ -35,32 +37,57 @@ struct HistoryBridgeTemplate<'a> {
summary_text: &'a str,
}
pub(crate) async fn run_inline_auto_compact_task(
pub(super) fn spawn_compact_task(
sess: Arc<Session>,
turn_context: Arc<TurnContext>,
sub_id: String,
input: Vec<InputItem>,
) {
let task = AgentTask::compact(
sess.clone(),
turn_context,
sub_id,
input,
SUMMARIZATION_PROMPT.to_string(),
);
sess.set_task(task);
}
pub(super) async fn run_inline_auto_compact_task(
sess: Arc<Session>,
turn_context: Arc<TurnContext>,
) {
let sub_id = sess.next_internal_sub_id();
let input = vec![InputItem::Text {
text: SUMMARIZATION_PROMPT.to_string(),
text: COMPACT_TRIGGER_TEXT.to_string(),
}];
run_compact_task_inner(sess, turn_context, sub_id, input).await;
run_compact_task_inner(
sess,
turn_context,
sub_id,
input,
SUMMARIZATION_PROMPT.to_string(),
false,
)
.await;
}
pub(crate) async fn run_compact_task(
pub(super) async fn run_compact_task(
sess: Arc<Session>,
turn_context: Arc<TurnContext>,
sub_id: String,
input: Vec<InputItem>,
) -> Option<String> {
let start_event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskStarted(TaskStartedEvent {
model_context_window: turn_context.client.get_model_context_window(),
}),
};
sess.send_event(start_event).await;
run_compact_task_inner(sess.clone(), turn_context, sub_id.clone(), input).await;
None
compact_instructions: String,
) {
run_compact_task_inner(
sess,
turn_context,
sub_id,
input,
compact_instructions,
true,
)
.await;
}
async fn run_compact_task_inner(
@@ -68,15 +95,26 @@ async fn run_compact_task_inner(
turn_context: Arc<TurnContext>,
sub_id: String,
input: Vec<InputItem>,
compact_instructions: String,
remove_task_on_completion: bool,
) {
let model_context_window = turn_context.client.get_model_context_window();
let start_event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskStarted(TaskStartedEvent {
model_context_window,
}),
};
sess.send_event(start_event).await;
let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
let turn_input = sess
.turn_input_with_history(vec![initial_input_for_turn.clone().into()])
.await;
let instructions_override = compact_instructions;
let turn_input = sess.turn_input_with_history(vec![initial_input_for_turn.clone().into()]);
let prompt = Prompt {
input: turn_input,
..Default::default()
tools: Vec::new(),
base_instructions_override: Some(instructions_override),
};
let max_retries = turn_context.client.get_provider().stream_max_retries();
@@ -93,8 +131,7 @@ async fn run_compact_task_inner(
sess.persist_rollout_items(&[rollout_item]).await;
loop {
let attempt_result =
drain_to_completed(&sess, turn_context.as_ref(), &sub_id, &prompt).await;
let attempt_result = drain_to_completed(&sess, turn_context.as_ref(), &prompt).await;
match attempt_result {
Ok(()) => {
@@ -130,12 +167,21 @@ async fn run_compact_task_inner(
}
}
let history_snapshot = sess.history_snapshot().await;
if remove_task_on_completion {
sess.remove_task(&sub_id);
}
let history_snapshot = {
let state = sess.state.lock_unchecked();
state.history.contents()
};
let summary_text = get_last_assistant_message_from_turn(&history_snapshot).unwrap_or_default();
let user_messages = collect_user_messages(&history_snapshot);
let initial_context = sess.build_initial_context(turn_context.as_ref());
let new_history = build_compacted_history(initial_context, &user_messages, &summary_text);
sess.replace_history(new_history).await;
let new_history =
build_compacted_history(&sess, turn_context.as_ref(), &user_messages, &summary_text);
{
let mut state = sess.state.lock_unchecked();
state.history.replace(new_history);
}
let rollout_item = RolloutItem::Compacted(CompactedItem {
message: summary_text.clone(),
@@ -149,9 +195,16 @@ async fn run_compact_task_inner(
}),
};
sess.send_event(event).await;
let event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskComplete(TaskCompleteEvent {
last_agent_message: None,
}),
};
sess.send_event(event).await;
}
pub fn content_items_to_text(content: &[ContentItem]) -> Option<String> {
fn content_items_to_text(content: &[ContentItem]) -> Option<String> {
let mut pieces = Vec::new();
for item in content {
match item {
@@ -170,7 +223,7 @@ pub fn content_items_to_text(content: &[ContentItem]) -> Option<String> {
}
}
pub(crate) fn collect_user_messages(items: &[ResponseItem]) -> Vec<String> {
fn collect_user_messages(items: &[ResponseItem]) -> Vec<String> {
items
.iter()
.filter_map(|item| match item {
@@ -183,30 +236,25 @@ pub(crate) fn collect_user_messages(items: &[ResponseItem]) -> Vec<String> {
.collect()
}
pub fn is_session_prefix_message(text: &str) -> bool {
fn is_session_prefix_message(text: &str) -> bool {
matches!(
InputMessageKind::from(("user", text)),
InputMessageKind::UserInstructions | InputMessageKind::EnvironmentContext
)
}
pub(crate) fn build_compacted_history(
initial_context: Vec<ResponseItem>,
fn build_compacted_history(
sess: &Session,
turn_context: &TurnContext,
user_messages: &[String],
summary_text: &str,
) -> Vec<ResponseItem> {
let mut history = initial_context;
let mut user_messages_text = if user_messages.is_empty() {
let mut history = sess.build_initial_context(turn_context);
let user_messages_text = if user_messages.is_empty() {
"(none)".to_string()
} else {
user_messages.join("\n\n")
};
// Truncate the concatenated prior user messages so the bridge message
// stays well under the context window (approx. 4 bytes/token).
let max_bytes = COMPACT_USER_MESSAGE_MAX_TOKENS * 4;
if user_messages_text.len() > max_bytes {
user_messages_text = truncate_middle(&user_messages_text, max_bytes).0;
}
let summary_text = if summary_text.is_empty() {
"(no summary available)".to_string()
} else {
@@ -230,7 +278,6 @@ pub(crate) fn build_compacted_history(
async fn drain_to_completed(
sess: &Session,
turn_context: &TurnContext,
sub_id: &str,
prompt: &Prompt,
) -> CodexResult<()> {
let mut stream = turn_context.client.clone().stream(prompt).await?;
@@ -244,14 +291,10 @@ async fn drain_to_completed(
};
match event {
Ok(ResponseEvent::OutputItemDone(item)) => {
sess.record_into_history(std::slice::from_ref(&item)).await;
let mut state = sess.state.lock_unchecked();
state.history.record_items(std::slice::from_ref(&item));
}
Ok(ResponseEvent::RateLimits(snapshot)) => {
sess.update_rate_limits(sub_id, snapshot).await;
}
Ok(ResponseEvent::Completed { token_usage, .. }) => {
sess.update_token_usage_info(sub_id, turn_context, token_usage.as_ref())
.await;
Ok(ResponseEvent::Completed { .. }) => {
return Ok(());
}
Ok(_) => continue,
@@ -355,38 +398,4 @@ mod tests {
assert_eq!(vec!["real user message".to_string()], collected);
}
#[test]
fn build_compacted_history_truncates_overlong_user_messages() {
// Prepare a very large prior user message so the aggregated
// `user_messages_text` exceeds the truncation threshold used by
// `build_compacted_history` (80k bytes).
let big = "X".repeat(200_000);
let history = build_compacted_history(Vec::new(), std::slice::from_ref(&big), "SUMMARY");
// Expect exactly one bridge message added to history (plus any initial context we provided, which is none).
assert_eq!(history.len(), 1);
// Extract the text content of the bridge message.
let bridge_text = match &history[0] {
ResponseItem::Message { role, content, .. } if role == "user" => {
content_items_to_text(content).unwrap_or_default()
}
other => panic!("unexpected item in history: {other:?}"),
};
// The bridge should contain the truncation marker and not the full original payload.
assert!(
bridge_text.contains("tokens truncated"),
"expected truncation marker in bridge message"
);
assert!(
!bridge_text.contains(&big),
"bridge should not include the full oversized user text"
);
assert!(
bridge_text.contains("SUMMARY"),
"bridge should include the provided summary text"
);
}
}

View File

@@ -1,99 +0,0 @@
use crate::bash::parse_bash_lc_plain_commands;
pub fn command_might_be_dangerous(command: &[String]) -> bool {
if is_dangerous_to_call_with_exec(command) {
return true;
}
// Support `bash -lc "<script>"` where the any part of the script might contain a dangerous command.
if let Some(all_commands) = parse_bash_lc_plain_commands(command)
&& all_commands
.iter()
.any(|cmd| is_dangerous_to_call_with_exec(cmd))
{
return true;
}
false
}
fn is_dangerous_to_call_with_exec(command: &[String]) -> bool {
let cmd0 = command.first().map(String::as_str);
match cmd0 {
Some(cmd) if cmd.ends_with("git") || cmd.ends_with("/git") => {
matches!(command.get(1).map(String::as_str), Some("reset" | "rm"))
}
Some("rm") => matches!(command.get(1).map(String::as_str), Some("-f" | "-rf")),
// for sudo <cmd> simply do the check for <cmd>
Some("sudo") => is_dangerous_to_call_with_exec(&command[1..]),
// ── anything else ─────────────────────────────────────────────────
_ => false,
}
}
#[cfg(test)]
mod tests {
use super::*;
fn vec_str(items: &[&str]) -> Vec<String> {
items.iter().map(std::string::ToString::to_string).collect()
}
#[test]
fn git_reset_is_dangerous() {
assert!(command_might_be_dangerous(&vec_str(&["git", "reset"])));
}
#[test]
fn bash_git_reset_is_dangerous() {
assert!(command_might_be_dangerous(&vec_str(&[
"bash",
"-lc",
"git reset --hard"
])));
}
#[test]
fn git_status_is_not_dangerous() {
assert!(!command_might_be_dangerous(&vec_str(&["git", "status"])));
}
#[test]
fn bash_git_status_is_not_dangerous() {
assert!(!command_might_be_dangerous(&vec_str(&[
"bash",
"-lc",
"git status"
])));
}
#[test]
fn sudo_git_reset_is_dangerous() {
assert!(command_might_be_dangerous(&vec_str(&[
"sudo", "git", "reset", "--hard"
])));
}
#[test]
fn usr_bin_git_is_dangerous() {
assert!(command_might_be_dangerous(&vec_str(&[
"/usr/bin/git",
"reset",
"--hard"
])));
}
#[test]
fn rm_rf_is_dangerous() {
assert!(command_might_be_dangerous(&vec_str(&["rm", "-rf", "/"])));
}
#[test]
fn rm_f_is_dangerous() {
assert!(command_might_be_dangerous(&vec_str(&["rm", "-f", "/"])));
}
}

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