mirror of
https://github.com/openai/codex.git
synced 2026-02-02 23:13:37 +00:00
Compare commits
14 Commits
pr752
...
codex/task
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
980778f529 | ||
|
|
6e7d4a4b45 | ||
|
|
841e19b05d | ||
|
|
f466a73428 | ||
|
|
1a868d35f3 | ||
|
|
9c563054e0 | ||
|
|
ca7204537c | ||
|
|
132e87cc8c | ||
|
|
8e80716169 | ||
|
|
d28aedb07b | ||
|
|
586ee0ec71 | ||
|
|
9065e61455 | ||
|
|
6686f28338 | ||
|
|
3818df7ba4 |
37
.github/dotslash-config.json
vendored
37
.github/dotslash-config.json
vendored
@@ -1,37 +0,0 @@
|
||||
{
|
||||
"outputs": {
|
||||
"codex-repl": {
|
||||
"platforms": {
|
||||
"macos-aarch64": { "regex": "^codex-repl-aarch64-apple-darwin\\.zst$", "path": "codex-repl" },
|
||||
"macos-x86_64": { "regex": "^codex-repl-x86_64-apple-darwin\\.zst$", "path": "codex-repl" },
|
||||
"linux-x86_64": { "regex": "^codex-repl-x86_64-unknown-linux-musl\\.zst$", "path": "codex-repl" },
|
||||
"linux-aarch64": { "regex": "^codex-repl-aarch64-unknown-linux-gnu\\.zst$", "path": "codex-repl" }
|
||||
}
|
||||
},
|
||||
|
||||
"codex-exec": {
|
||||
"platforms": {
|
||||
"macos-aarch64": { "regex": "^codex-exec-aarch64-apple-darwin\\.zst$", "path": "codex-exec" },
|
||||
"macos-x86_64": { "regex": "^codex-exec-x86_64-apple-darwin\\.zst$", "path": "codex-exec" },
|
||||
"linux-x86_64": { "regex": "^codex-exec-x86_64-unknown-linux-musl\\.zst$", "path": "codex-exec" },
|
||||
"linux-aarch64": { "regex": "^codex-exec-aarch64-unknown-linux-gnu\\.zst$", "path": "codex-exec" }
|
||||
}
|
||||
},
|
||||
|
||||
"codex": {
|
||||
"platforms": {
|
||||
"macos-aarch64": { "regex": "^codex-aarch64-apple-darwin\\.zst$", "path": "codex" },
|
||||
"macos-x86_64": { "regex": "^codex-x86_64-apple-darwin\\.zst$", "path": "codex" },
|
||||
"linux-x86_64": { "regex": "^codex-x86_64-unknown-linux-musl\\.zst$", "path": "codex" },
|
||||
"linux-aarch64": { "regex": "^codex-aarch64-unknown-linux-gnu\\.zst$", "path": "codex" }
|
||||
}
|
||||
},
|
||||
|
||||
"codex-linux-sandbox": {
|
||||
"platforms": {
|
||||
"linux-x86_64": { "regex": "^codex-linux-sandbox-x86_64-unknown-linux-musl\\.zst$", "path": "codex-linux-sandbox" },
|
||||
"linux-aarch64": { "regex": "^codex-linux-sandbox-aarch64-unknown-linux-gnu\\.zst$", "path": "codex-linux-sandbox" }
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
157
.github/workflows/rust-release.yml
vendored
157
.github/workflows/rust-release.yml
vendored
@@ -1,157 +0,0 @@
|
||||
# Release workflow for codex-rs.
|
||||
# To release, follow a workflow like:
|
||||
# ```
|
||||
# git tag -a rust-v0.1.0 -m "Release 0.1.0"
|
||||
# git push origin rust-v0.1.0
|
||||
# ```
|
||||
|
||||
name: rust-release
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "rust-v.*.*.*"
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}
|
||||
cancel-in-progress: true
|
||||
|
||||
env:
|
||||
TAG_REGEX: '^rust-v\.[0-9]+\.[0-9]+\.[0-9]+$'
|
||||
|
||||
jobs:
|
||||
tag-check:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Validate tag matches Cargo.toml version
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
echo "::group::Tag validation"
|
||||
|
||||
# 1. Must be a tag and match the regex
|
||||
[[ "${GITHUB_REF_TYPE}" == "tag" ]] \
|
||||
|| { echo "❌ Not a tag push"; exit 1; }
|
||||
[[ "${GITHUB_REF_NAME}" =~ ${TAG_REGEX} ]] \
|
||||
|| { echo "❌ Tag '${GITHUB_REF_NAME}' != ${TAG_REGEX}"; exit 1; }
|
||||
|
||||
# 2. Extract versions
|
||||
tag_ver="${GITHUB_REF_NAME#rust-v.}"
|
||||
cargo_ver="$(grep -m1 '^version' codex-rs/Cargo.toml \
|
||||
| sed -E 's/version *= *"([^"]+)".*/\1/')"
|
||||
|
||||
# 3. Compare
|
||||
[[ "${tag_ver}" == "${cargo_ver}" ]] \
|
||||
|| { echo "❌ Tag ${tag_ver} ≠ Cargo.toml ${cargo_ver}"; exit 1; }
|
||||
|
||||
echo "✅ Tag and Cargo.toml agree (${tag_ver})"
|
||||
echo "::endgroup::"
|
||||
|
||||
build:
|
||||
needs: tag-check
|
||||
name: ${{ matrix.runner }} - ${{ matrix.target }}
|
||||
runs-on: ${{ matrix.runner }}
|
||||
timeout-minutes: 30
|
||||
defaults:
|
||||
run:
|
||||
working-directory: codex-rs
|
||||
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- runner: macos-14
|
||||
target: aarch64-apple-darwin
|
||||
- runner: macos-14
|
||||
target: x86_64-apple-darwin
|
||||
- runner: ubuntu-24.04
|
||||
target: x86_64-unknown-linux-musl
|
||||
- runner: ubuntu-24.04
|
||||
target: x86_64-unknown-linux-gnu
|
||||
- runner: ubuntu-24.04-arm
|
||||
target: aarch64-unknown-linux-gnu
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
targets: ${{ matrix.target }}
|
||||
|
||||
- uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/bin/
|
||||
~/.cargo/registry/index/
|
||||
~/.cargo/registry/cache/
|
||||
~/.cargo/git/db/
|
||||
${{ github.workspace }}/codex-rs/target/
|
||||
key: cargo-release-${{ matrix.runner }}-${{ matrix.target }}-${{ hashFiles('**/Cargo.lock') }}
|
||||
|
||||
- if: ${{ matrix.target == 'x86_64-unknown-linux-musl' }}
|
||||
name: Install musl build tools
|
||||
run: |
|
||||
sudo apt install -y musl-tools pkg-config
|
||||
|
||||
- name: Cargo build
|
||||
run: cargo build --target ${{ matrix.target }} --release --all-targets --all-features
|
||||
|
||||
- name: Stage artifacts
|
||||
shell: bash
|
||||
run: |
|
||||
dest="dist/${{ matrix.target }}"
|
||||
mkdir -p "$dest"
|
||||
|
||||
cp target/${{ matrix.target }}/release/codex-repl "$dest/codex-repl-${{ matrix.target }}"
|
||||
cp target/${{ matrix.target }}/release/codex-exec "$dest/codex-exec-${{ matrix.target }}"
|
||||
cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
|
||||
|
||||
- if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'x86_64-unknown-linux-gnu' || matrix.target == 'aarch64-unknown-linux-gnu' }}
|
||||
name: Stage Linux-only artifacts
|
||||
shell: bash
|
||||
run: |
|
||||
dest="dist/${{ matrix.target }}"
|
||||
cp target/${{ matrix.target }}/release/codex-linux-sandbox "$dest/codex-linux-sandbox-${{ matrix.target }}"
|
||||
|
||||
- name: Compress artifacts
|
||||
shell: bash
|
||||
run: |
|
||||
dest="dist/${{ matrix.target }}"
|
||||
zstd -T0 -19 --rm "$dest"/*
|
||||
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ${{ matrix.target }}
|
||||
path: codex-rs/dist/${{ matrix.target }}/*
|
||||
|
||||
release:
|
||||
needs: build
|
||||
name: release
|
||||
runs-on: ubuntu-24.04
|
||||
env:
|
||||
RELEASE_TAG: codex-rs-${{ github.sha }}-${{ github.run_attempt }}-${{ github.ref_name }}
|
||||
|
||||
steps:
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: dist
|
||||
|
||||
- name: List
|
||||
run: ls -R dist/
|
||||
|
||||
- uses: softprops/action-gh-release@v2
|
||||
with:
|
||||
tag_name: ${{ env.RELEASE_TAG }}
|
||||
files: dist/**
|
||||
# TODO(ragona): I'm going to leave these as prerelease/draft for now.
|
||||
# It gives us 1) clarity that these are not yet a stable version, and
|
||||
# 2) allows a human step to review the release before publishing the draft.
|
||||
prerelease: true
|
||||
draft: true
|
||||
|
||||
- uses: facebook/dotslash-publish-release@v2
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
with:
|
||||
tag: ${{ env.RELEASE_TAG }}
|
||||
config: .github/dotslash-config.json
|
||||
@@ -2,26 +2,6 @@
|
||||
set -euo pipefail # Exit on error, undefined vars, and pipeline failures
|
||||
IFS=$'\n\t' # Stricter word splitting
|
||||
|
||||
# Read allowed domains from file
|
||||
ALLOWED_DOMAINS_FILE="/etc/codex/allowed_domains.txt"
|
||||
if [ -f "$ALLOWED_DOMAINS_FILE" ]; then
|
||||
ALLOWED_DOMAINS=()
|
||||
while IFS= read -r domain; do
|
||||
ALLOWED_DOMAINS+=("$domain")
|
||||
done < "$ALLOWED_DOMAINS_FILE"
|
||||
echo "Using domains from file: ${ALLOWED_DOMAINS[*]}"
|
||||
else
|
||||
# Fallback to default domains
|
||||
ALLOWED_DOMAINS=("api.openai.com")
|
||||
echo "Domains file not found, using default: ${ALLOWED_DOMAINS[*]}"
|
||||
fi
|
||||
|
||||
# Ensure we have at least one domain
|
||||
if [ ${#ALLOWED_DOMAINS[@]} -eq 0 ]; then
|
||||
echo "ERROR: No allowed domains specified"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Flush existing rules and delete existing ipsets
|
||||
iptables -F
|
||||
iptables -X
|
||||
@@ -44,7 +24,8 @@ iptables -A OUTPUT -o lo -j ACCEPT
|
||||
ipset create allowed-domains hash:net
|
||||
|
||||
# Resolve and add other allowed domains
|
||||
for domain in "${ALLOWED_DOMAINS[@]}"; do
|
||||
for domain in \
|
||||
"api.openai.com"; do
|
||||
echo "Resolving $domain..."
|
||||
ips=$(dig +short A "$domain")
|
||||
if [ -z "$ips" ]; then
|
||||
@@ -106,7 +87,7 @@ else
|
||||
echo "Firewall verification passed - unable to reach https://example.com as expected"
|
||||
fi
|
||||
|
||||
# Always verify OpenAI API access is working
|
||||
# Verify OpenAI API access
|
||||
if ! curl --connect-timeout 5 https://api.openai.com >/dev/null 2>&1; then
|
||||
echo "ERROR: Firewall verification failed - unable to reach https://api.openai.com"
|
||||
exit 1
|
||||
|
||||
@@ -10,8 +10,6 @@ set -e
|
||||
|
||||
# Default the work directory to WORKSPACE_ROOT_DIR if not provided.
|
||||
WORK_DIR="${WORKSPACE_ROOT_DIR:-$(pwd)}"
|
||||
# Default allowed domains - can be overridden with OPENAI_ALLOWED_DOMAINS env var
|
||||
OPENAI_ALLOWED_DOMAINS="${OPENAI_ALLOWED_DOMAINS:-api.openai.com}"
|
||||
|
||||
# Parse optional flag.
|
||||
if [ "$1" = "--work_dir" ]; then
|
||||
@@ -47,12 +45,6 @@ if [ -z "$WORK_DIR" ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify that OPENAI_ALLOWED_DOMAINS is not empty
|
||||
if [ -z "$OPENAI_ALLOWED_DOMAINS" ]; then
|
||||
echo "Error: OPENAI_ALLOWED_DOMAINS is empty."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Kill any existing container for the working directory using cleanup(), centralizing removal logic.
|
||||
cleanup
|
||||
|
||||
@@ -65,25 +57,8 @@ docker run --name "$CONTAINER_NAME" -d \
|
||||
codex \
|
||||
sleep infinity
|
||||
|
||||
# Write the allowed domains to a file in the container
|
||||
docker exec --user root "$CONTAINER_NAME" bash -c "mkdir -p /etc/codex"
|
||||
for domain in $OPENAI_ALLOWED_DOMAINS; do
|
||||
# Validate domain format to prevent injection
|
||||
if [[ ! "$domain" =~ ^[a-zA-Z0-9][a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$ ]]; then
|
||||
echo "Error: Invalid domain format: $domain"
|
||||
exit 1
|
||||
fi
|
||||
echo "$domain" | docker exec --user root -i "$CONTAINER_NAME" bash -c "cat >> /etc/codex/allowed_domains.txt"
|
||||
done
|
||||
|
||||
# Set proper permissions on the domains file
|
||||
docker exec --user root "$CONTAINER_NAME" bash -c "chmod 444 /etc/codex/allowed_domains.txt && chown root:root /etc/codex/allowed_domains.txt"
|
||||
|
||||
# Initialize the firewall inside the container as root user
|
||||
docker exec --user root "$CONTAINER_NAME" bash -c "/usr/local/bin/init_firewall.sh"
|
||||
|
||||
# Remove the firewall script after running it
|
||||
docker exec --user root "$CONTAINER_NAME" bash -c "rm -f /usr/local/bin/init_firewall.sh"
|
||||
# Initialize the firewall inside the container with root privileges.
|
||||
docker exec --user root "$CONTAINER_NAME" /usr/local/bin/init_firewall.sh
|
||||
|
||||
# Execute the provided command in the container, ensuring it runs in the work directory.
|
||||
# We use a parameterized bash command to safely handle the command and directory.
|
||||
|
||||
@@ -1137,7 +1137,7 @@ export class AgentLoop {
|
||||
content: [
|
||||
{
|
||||
type: "input_text",
|
||||
text: "⚠️ Insufficient quota. Please check your billing details and retry.",
|
||||
text: `\u26a0 Insufficient quota: ${err instanceof Error && err.message ? err.message.trim() : "No remaining quota."} Manage or purchase credits at https://platform.openai.com/account/billing.`,
|
||||
},
|
||||
],
|
||||
});
|
||||
|
||||
23
codex-rs/Cargo.lock
generated
23
codex-rs/Cargo.lock
generated
@@ -469,7 +469,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "codex-cli"
|
||||
version = "0.0.2504292236"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"clap",
|
||||
@@ -504,7 +504,6 @@ dependencies = [
|
||||
"mime_guess",
|
||||
"openssl-sys",
|
||||
"patch",
|
||||
"path-absolutize",
|
||||
"predicates",
|
||||
"rand",
|
||||
"reqwest",
|
||||
@@ -524,14 +523,12 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "codex-exec"
|
||||
version = "0.0.2504292236"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"chrono",
|
||||
"clap",
|
||||
"codex-core",
|
||||
"owo-colors 4.2.0",
|
||||
"shlex",
|
||||
"owo-colors",
|
||||
"tokio",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
@@ -559,12 +556,12 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "codex-repl"
|
||||
version = "0.0.2504292236"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"clap",
|
||||
"codex-core",
|
||||
"owo-colors 4.2.0",
|
||||
"owo-colors",
|
||||
"rand",
|
||||
"tokio",
|
||||
"tracing",
|
||||
@@ -602,7 +599,7 @@ dependencies = [
|
||||
"eyre",
|
||||
"indenter",
|
||||
"once_cell",
|
||||
"owo-colors 3.5.0",
|
||||
"owo-colors",
|
||||
"tracing-error",
|
||||
]
|
||||
|
||||
@@ -613,7 +610,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "cd6be1b2a7e382e2b98b43b2adcca6bb0e465af0bdd38123873ae61eb17a72c2"
|
||||
dependencies = [
|
||||
"once_cell",
|
||||
"owo-colors 3.5.0",
|
||||
"owo-colors",
|
||||
"tracing-core",
|
||||
"tracing-error",
|
||||
]
|
||||
@@ -2228,12 +2225,6 @@ version = "0.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b15813163c1d831bf4a13c3610c05c0d03b39feb07f7e09fa234dac9b15aaf39"
|
||||
|
||||
[[package]]
|
||||
name = "owo-colors"
|
||||
version = "3.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c1b04fb49957986fdce4d6ee7a65027d55d4b6d2265e5848bbb507b58ccfdb6f"
|
||||
|
||||
[[package]]
|
||||
name = "owo-colors"
|
||||
version = "4.2.0"
|
||||
|
||||
@@ -10,12 +10,3 @@ members = [
|
||||
"repl",
|
||||
"tui",
|
||||
]
|
||||
|
||||
[workspace.package]
|
||||
version = "0.0.2504292236"
|
||||
|
||||
[profile.release]
|
||||
lto = "fat"
|
||||
# Because we bundle some of these executables with the TypeScript CLI, we
|
||||
# remove everything to make the binary as small as possible.
|
||||
strip = "symbols"
|
||||
|
||||
@@ -1,20 +1,12 @@
|
||||
[package]
|
||||
name = "codex-cli"
|
||||
version = { workspace = true }
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[[bin]]
|
||||
name = "codex"
|
||||
path = "src/main.rs"
|
||||
|
||||
[[bin]]
|
||||
name = "codex-linux-sandbox"
|
||||
path = "src/linux-sandbox/main.rs"
|
||||
|
||||
[lib]
|
||||
name = "codex_cli"
|
||||
path = "src/lib.rs"
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1"
|
||||
clap = { version = "4", features = ["derive"] }
|
||||
|
||||
@@ -5,20 +5,34 @@
|
||||
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use std::os::unix::process::ExitStatusExt;
|
||||
use std::path::PathBuf;
|
||||
use std::process;
|
||||
use std::process::Command;
|
||||
use std::process::ExitStatus;
|
||||
|
||||
/// Execute `command` in a Linux sandbox (Landlock + seccomp) the way Codex
|
||||
/// would.
|
||||
pub fn run_landlock(command: Vec<String>, sandbox_policy: SandboxPolicy) -> anyhow::Result<()> {
|
||||
pub(crate) fn run_landlock(
|
||||
command: Vec<String>,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
writable_roots: Vec<PathBuf>,
|
||||
) -> anyhow::Result<()> {
|
||||
if command.is_empty() {
|
||||
anyhow::bail!("command args are empty");
|
||||
}
|
||||
|
||||
// Spawn a new thread and apply the sandbox policies there.
|
||||
let handle = std::thread::spawn(move || -> anyhow::Result<ExitStatus> {
|
||||
codex_core::linux::apply_sandbox_policy_to_current_thread(sandbox_policy)?;
|
||||
// Apply sandbox policies inside this thread so only the child inherits
|
||||
// them, not the entire CLI process.
|
||||
if sandbox_policy.is_network_restricted() {
|
||||
codex_core::linux::install_network_seccomp_filter_on_current_thread()?;
|
||||
}
|
||||
|
||||
if sandbox_policy.is_file_write_restricted() {
|
||||
codex_core::linux::install_filesystem_landlock_rules_on_current_thread(writable_roots)?;
|
||||
}
|
||||
|
||||
let status = Command::new(&command[0]).args(&command[1..]).status()?;
|
||||
Ok(status)
|
||||
});
|
||||
|
||||
@@ -1,47 +0,0 @@
|
||||
#[cfg(target_os = "linux")]
|
||||
pub mod landlock;
|
||||
pub mod proto;
|
||||
pub mod seatbelt;
|
||||
|
||||
use clap::Parser;
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use codex_core::SandboxPermissionOption;
|
||||
|
||||
#[derive(Debug, Parser)]
|
||||
pub struct SeatbeltCommand {
|
||||
/// Convenience alias for low-friction sandboxed automatic execution (network-disabled sandbox that can write to cwd and TMPDIR)
|
||||
#[arg(long = "full-auto", default_value_t = false)]
|
||||
pub full_auto: bool,
|
||||
|
||||
#[clap(flatten)]
|
||||
pub sandbox: SandboxPermissionOption,
|
||||
|
||||
/// Full command args to run under seatbelt.
|
||||
#[arg(trailing_var_arg = true)]
|
||||
pub command: Vec<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Parser)]
|
||||
pub struct LandlockCommand {
|
||||
/// Convenience alias for low-friction sandboxed automatic execution (network-disabled sandbox that can write to cwd and TMPDIR)
|
||||
#[arg(long = "full-auto", default_value_t = false)]
|
||||
pub full_auto: bool,
|
||||
|
||||
#[clap(flatten)]
|
||||
pub sandbox: SandboxPermissionOption,
|
||||
|
||||
/// Full command args to run under landlock.
|
||||
#[arg(trailing_var_arg = true)]
|
||||
pub command: Vec<String>,
|
||||
}
|
||||
|
||||
pub fn create_sandbox_policy(full_auto: bool, sandbox: SandboxPermissionOption) -> SandboxPolicy {
|
||||
if full_auto {
|
||||
SandboxPolicy::new_full_auto_policy()
|
||||
} else {
|
||||
match sandbox.permissions.map(Into::into) {
|
||||
Some(sandbox_policy) => sandbox_policy,
|
||||
None => SandboxPolicy::new_read_only_policy(),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
#[cfg(not(target_os = "linux"))]
|
||||
fn main() -> anyhow::Result<()> {
|
||||
eprintln!("codex-linux-sandbox is not supported on this platform.");
|
||||
std::process::exit(1);
|
||||
}
|
||||
|
||||
#[cfg(target_os = "linux")]
|
||||
fn main() -> anyhow::Result<()> {
|
||||
use clap::Parser;
|
||||
use codex_cli::create_sandbox_policy;
|
||||
use codex_cli::landlock;
|
||||
use codex_cli::LandlockCommand;
|
||||
|
||||
let LandlockCommand {
|
||||
full_auto,
|
||||
sandbox,
|
||||
command,
|
||||
} = LandlockCommand::parse();
|
||||
let sandbox_policy = create_sandbox_policy(full_auto, sandbox);
|
||||
landlock::run_landlock(command, sandbox_policy)?;
|
||||
Ok(())
|
||||
}
|
||||
@@ -1,9 +1,13 @@
|
||||
#[cfg(target_os = "linux")]
|
||||
mod landlock;
|
||||
mod proto;
|
||||
mod seatbelt;
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
use clap::ArgAction;
|
||||
use clap::Parser;
|
||||
use codex_cli::create_sandbox_policy;
|
||||
use codex_cli::proto;
|
||||
use codex_cli::seatbelt;
|
||||
use codex_cli::LandlockCommand;
|
||||
use codex_cli::SeatbeltCommand;
|
||||
use codex_core::SandboxModeCliArg;
|
||||
use codex_exec::Cli as ExecCli;
|
||||
use codex_repl::Cli as ReplCli;
|
||||
use codex_tui::Cli as TuiCli;
|
||||
@@ -61,6 +65,36 @@ enum DebugCommand {
|
||||
Landlock(LandlockCommand),
|
||||
}
|
||||
|
||||
#[derive(Debug, Parser)]
|
||||
struct SeatbeltCommand {
|
||||
/// Writable folder for sandbox (can be specified multiple times).
|
||||
#[arg(long = "writable-root", short = 'w', value_name = "DIR", action = ArgAction::Append, use_value_delimiter = false)]
|
||||
writable_roots: Vec<PathBuf>,
|
||||
|
||||
/// Configure the process restrictions for the command.
|
||||
#[arg(long = "sandbox", short = 's')]
|
||||
sandbox_policy: SandboxModeCliArg,
|
||||
|
||||
/// Full command args to run under seatbelt.
|
||||
#[arg(trailing_var_arg = true)]
|
||||
command: Vec<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Parser)]
|
||||
struct LandlockCommand {
|
||||
/// Writable folder for sandbox (can be specified multiple times).
|
||||
#[arg(long = "writable-root", short = 'w', value_name = "DIR", action = ArgAction::Append, use_value_delimiter = false)]
|
||||
writable_roots: Vec<PathBuf>,
|
||||
|
||||
/// Configure the process restrictions for the command.
|
||||
#[arg(long = "sandbox", short = 's')]
|
||||
sandbox_policy: SandboxModeCliArg,
|
||||
|
||||
/// Full command args to run under landlock.
|
||||
#[arg(trailing_var_arg = true)]
|
||||
command: Vec<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Parser)]
|
||||
struct ReplProto {}
|
||||
|
||||
@@ -84,20 +118,18 @@ async fn main() -> anyhow::Result<()> {
|
||||
Some(Subcommand::Debug(debug_args)) => match debug_args.cmd {
|
||||
DebugCommand::Seatbelt(SeatbeltCommand {
|
||||
command,
|
||||
sandbox,
|
||||
full_auto,
|
||||
sandbox_policy,
|
||||
writable_roots,
|
||||
}) => {
|
||||
let sandbox_policy = create_sandbox_policy(full_auto, sandbox);
|
||||
seatbelt::run_seatbelt(command, sandbox_policy).await?;
|
||||
seatbelt::run_seatbelt(command, sandbox_policy.into(), writable_roots).await?;
|
||||
}
|
||||
#[cfg(target_os = "linux")]
|
||||
DebugCommand::Landlock(LandlockCommand {
|
||||
command,
|
||||
sandbox,
|
||||
full_auto,
|
||||
sandbox_policy,
|
||||
writable_roots,
|
||||
}) => {
|
||||
let sandbox_policy = create_sandbox_policy(full_auto, sandbox);
|
||||
codex_cli::landlock::run_landlock(command, sandbox_policy)?;
|
||||
landlock::run_landlock(command, sandbox_policy.into(), writable_roots)?;
|
||||
}
|
||||
#[cfg(not(target_os = "linux"))]
|
||||
DebugCommand::Landlock(_) => {
|
||||
|
||||
@@ -1,11 +1,13 @@
|
||||
use codex_core::exec::create_seatbelt_command;
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use std::path::PathBuf;
|
||||
|
||||
pub async fn run_seatbelt(
|
||||
pub(crate) async fn run_seatbelt(
|
||||
command: Vec<String>,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
writable_roots: Vec<PathBuf>,
|
||||
) -> anyhow::Result<()> {
|
||||
let seatbelt_command = create_seatbelt_command(command, &sandbox_policy);
|
||||
let seatbelt_command = create_seatbelt_command(command, sandbox_policy, &writable_roots);
|
||||
let status = tokio::process::Command::new(seatbelt_command[0].clone())
|
||||
.args(&seatbelt_command[1..])
|
||||
.spawn()
|
||||
|
||||
@@ -21,7 +21,6 @@ fs-err = "3.1.0"
|
||||
futures = "0.3"
|
||||
mime_guess = "2.0"
|
||||
patch = "0.7"
|
||||
path-absolutize = "3.1.1"
|
||||
rand = "0.9"
|
||||
reqwest = { version = "0.12", features = ["json", "stream"] }
|
||||
serde = { version = "1", features = ["derive"] }
|
||||
|
||||
@@ -1,14 +1,10 @@
|
||||
//! Standard type to use with the `--approval-mode` CLI option.
|
||||
//! Available when the `cli` feature is enabled for the crate.
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
use clap::ArgAction;
|
||||
use clap::Parser;
|
||||
use clap::ValueEnum;
|
||||
|
||||
use crate::protocol::AskForApproval;
|
||||
use crate::protocol::SandboxPermission;
|
||||
use crate::protocol::SandboxPolicy;
|
||||
|
||||
#[derive(Clone, Copy, Debug, ValueEnum)]
|
||||
#[value(rename_all = "kebab-case")]
|
||||
@@ -28,6 +24,19 @@ pub enum ApprovalModeCliArg {
|
||||
Never,
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, ValueEnum)]
|
||||
#[value(rename_all = "kebab-case")]
|
||||
pub enum SandboxModeCliArg {
|
||||
/// Network syscalls will be blocked
|
||||
NetworkRestricted,
|
||||
/// Filesystem writes will be restricted
|
||||
FileWriteRestricted,
|
||||
/// Network and filesystem writes will be restricted
|
||||
NetworkAndFileWriteRestricted,
|
||||
/// No restrictions; full "unsandboxed" mode
|
||||
DangerousNoRestrictions,
|
||||
}
|
||||
|
||||
impl From<ApprovalModeCliArg> for AskForApproval {
|
||||
fn from(value: ApprovalModeCliArg) -> Self {
|
||||
match value {
|
||||
@@ -38,83 +47,15 @@ impl From<ApprovalModeCliArg> for AskForApproval {
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Parser, Debug)]
|
||||
pub struct SandboxPermissionOption {
|
||||
/// Specify this flag multiple times to specify the full set of permissions
|
||||
/// to grant to Codex.
|
||||
///
|
||||
/// ```shell
|
||||
/// codex -s disk-full-read-access \
|
||||
/// -s disk-write-cwd \
|
||||
/// -s disk-write-platform-user-temp-folder \
|
||||
/// -s disk-write-platform-global-temp-folder
|
||||
/// ```
|
||||
///
|
||||
/// Note disk-write-folder takes a value:
|
||||
///
|
||||
/// ```shell
|
||||
/// -s disk-write-folder=$HOME/.pyenv/shims
|
||||
/// ```
|
||||
///
|
||||
/// These permissions are quite broad and should be used with caution:
|
||||
///
|
||||
/// ```shell
|
||||
/// -s disk-full-write-access
|
||||
/// -s network-full-access
|
||||
/// ```
|
||||
#[arg(long = "sandbox-permission", short = 's', action = ArgAction::Append, value_parser = parse_sandbox_permission)]
|
||||
pub permissions: Option<Vec<SandboxPermission>>,
|
||||
}
|
||||
|
||||
/// Custom value-parser so we can keep the CLI surface small *and*
|
||||
/// still handle the parameterised `disk-write-folder` case.
|
||||
fn parse_sandbox_permission(raw: &str) -> std::io::Result<SandboxPermission> {
|
||||
let base_path = std::env::current_dir()?;
|
||||
parse_sandbox_permission_with_base_path(raw, base_path)
|
||||
}
|
||||
|
||||
pub(crate) fn parse_sandbox_permission_with_base_path(
|
||||
raw: &str,
|
||||
base_path: PathBuf,
|
||||
) -> std::io::Result<SandboxPermission> {
|
||||
use SandboxPermission::*;
|
||||
|
||||
if let Some(path) = raw.strip_prefix("disk-write-folder=") {
|
||||
return if path.is_empty() {
|
||||
Err(std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidInput,
|
||||
"--sandbox-permission disk-write-folder=<PATH> requires a non-empty PATH",
|
||||
))
|
||||
} else {
|
||||
use path_absolutize::*;
|
||||
|
||||
let file = PathBuf::from(path);
|
||||
let absolute_path = if file.is_relative() {
|
||||
file.absolutize_from(base_path)
|
||||
} else {
|
||||
file.absolutize()
|
||||
impl From<SandboxModeCliArg> for SandboxPolicy {
|
||||
fn from(value: SandboxModeCliArg) -> Self {
|
||||
match value {
|
||||
SandboxModeCliArg::NetworkRestricted => SandboxPolicy::NetworkRestricted,
|
||||
SandboxModeCliArg::FileWriteRestricted => SandboxPolicy::FileWriteRestricted,
|
||||
SandboxModeCliArg::NetworkAndFileWriteRestricted => {
|
||||
SandboxPolicy::NetworkAndFileWriteRestricted
|
||||
}
|
||||
.map(|path| path.into_owned())?;
|
||||
Ok(DiskWriteFolder {
|
||||
folder: absolute_path,
|
||||
})
|
||||
};
|
||||
}
|
||||
|
||||
match raw {
|
||||
"disk-full-read-access" => Ok(DiskFullReadAccess),
|
||||
"disk-write-platform-user-temp-folder" => Ok(DiskWritePlatformUserTempFolder),
|
||||
"disk-write-platform-global-temp-folder" => Ok(DiskWritePlatformGlobalTempFolder),
|
||||
"disk-write-cwd" => Ok(DiskWriteCwd),
|
||||
"disk-full-write-access" => Ok(DiskFullWriteAccess),
|
||||
"network-full-access" => Ok(NetworkFullAccess),
|
||||
_ => Err(
|
||||
std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidInput,
|
||||
format!(
|
||||
"`{raw}` is not a recognised permission.\nRun with `--help` to see the accepted values."
|
||||
),
|
||||
)
|
||||
),
|
||||
SandboxModeCliArg::DangerousNoRestrictions => SandboxPolicy::DangerousNoRestrictions,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -861,7 +861,7 @@ async fn handle_function_call(
|
||||
assess_command_safety(
|
||||
¶ms.command,
|
||||
sess.approval_policy,
|
||||
&sess.sandbox_policy,
|
||||
sess.sandbox_policy,
|
||||
&state.approved_commands,
|
||||
)
|
||||
};
|
||||
@@ -916,11 +916,14 @@ async fn handle_function_call(
|
||||
)
|
||||
.await;
|
||||
|
||||
let roots_snapshot = { sess.writable_roots.lock().unwrap().clone() };
|
||||
|
||||
let output_result = process_exec_tool_call(
|
||||
params.clone(),
|
||||
sandbox_type,
|
||||
&roots_snapshot,
|
||||
sess.ctrl_c.clone(),
|
||||
&sess.sandbox_policy,
|
||||
sess.sandbox_policy,
|
||||
)
|
||||
.await;
|
||||
|
||||
@@ -979,13 +982,17 @@ async fn handle_function_call(
|
||||
)
|
||||
.await;
|
||||
|
||||
match rx_approve.await.unwrap_or_default() {
|
||||
let decision = rx_approve.await.unwrap_or_default();
|
||||
|
||||
if matches!(decision, ReviewDecision::ApprovedForSession) {
|
||||
// Persist this command as pre-approved for the
|
||||
// remainder of the session so future executions
|
||||
// can skip the sandbox directly.
|
||||
sess.add_approved_command(params.command.clone());
|
||||
}
|
||||
|
||||
match decision {
|
||||
ReviewDecision::Approved | ReviewDecision::ApprovedForSession => {
|
||||
// Persist this command as pre‑approved for the
|
||||
// remainder of the session so future
|
||||
// executions skip the sandbox directly.
|
||||
// TODO(ragona): Isn't this a bug? It always saves the command in an | fork?
|
||||
sess.add_approved_command(params.command.clone());
|
||||
// Inform UI we are retrying without sandbox.
|
||||
sess.notify_background_event(
|
||||
&sub_id,
|
||||
@@ -1003,13 +1010,16 @@ async fn handle_function_call(
|
||||
)
|
||||
.await;
|
||||
|
||||
let retry_roots = { sess.writable_roots.lock().unwrap().clone() };
|
||||
|
||||
// This is an escalated retry; the policy will not be
|
||||
// examined and the sandbox has been set to `None`.
|
||||
let retry_output_result = process_exec_tool_call(
|
||||
params.clone(),
|
||||
SandboxType::None,
|
||||
&retry_roots,
|
||||
sess.ctrl_c.clone(),
|
||||
&sess.sandbox_policy,
|
||||
sess.sandbox_policy,
|
||||
)
|
||||
.await;
|
||||
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
use crate::approval_mode_cli_arg::parse_sandbox_permission_with_base_path;
|
||||
use crate::flags::OPENAI_DEFAULT_MODEL;
|
||||
use crate::protocol::AskForApproval;
|
||||
use crate::protocol::SandboxPermission;
|
||||
use crate::protocol::SandboxPolicy;
|
||||
use dirs::home_dir;
|
||||
use serde::Deserialize;
|
||||
@@ -13,98 +11,27 @@ use std::path::PathBuf;
|
||||
const EMBEDDED_INSTRUCTIONS: &str = include_str!("../prompt.md");
|
||||
|
||||
/// Application configuration loaded from disk and merged with overrides.
|
||||
#[derive(Debug, Clone)]
|
||||
#[derive(Deserialize, Debug, Clone)]
|
||||
pub struct Config {
|
||||
/// Optional override of model selection.
|
||||
#[serde(default = "default_model")]
|
||||
pub model: String,
|
||||
|
||||
/// Approval policy for executing commands.
|
||||
/// Default approval policy for executing commands.
|
||||
#[serde(default)]
|
||||
pub approval_policy: AskForApproval,
|
||||
|
||||
#[serde(default)]
|
||||
pub sandbox_policy: SandboxPolicy,
|
||||
|
||||
/// Disable server-side response storage (sends the full conversation
|
||||
/// context with every request). Currently necessary for OpenAI customers
|
||||
/// who have opted into Zero Data Retention (ZDR).
|
||||
#[serde(default)]
|
||||
pub disable_response_storage: bool,
|
||||
|
||||
/// System instructions.
|
||||
pub instructions: Option<String>,
|
||||
}
|
||||
|
||||
/// Base config deserialized from ~/.codex/config.toml.
|
||||
#[derive(Deserialize, Debug, Clone, Default)]
|
||||
pub struct ConfigToml {
|
||||
/// Optional override of model selection.
|
||||
pub model: Option<String>,
|
||||
|
||||
/// Default approval policy for executing commands.
|
||||
pub approval_policy: Option<AskForApproval>,
|
||||
|
||||
// The `default` attribute ensures that the field is treated as `None` when
|
||||
// the key is omitted from the TOML. Without it, Serde treats the field as
|
||||
// required because we supply a custom deserializer.
|
||||
#[serde(default, deserialize_with = "deserialize_sandbox_permissions")]
|
||||
pub sandbox_permissions: Option<Vec<SandboxPermission>>,
|
||||
|
||||
/// Disable server-side response storage (sends the full conversation
|
||||
/// context with every request). Currently necessary for OpenAI customers
|
||||
/// who have opted into Zero Data Retention (ZDR).
|
||||
pub disable_response_storage: Option<bool>,
|
||||
|
||||
/// System instructions.
|
||||
pub instructions: Option<String>,
|
||||
}
|
||||
|
||||
impl ConfigToml {
|
||||
/// Attempt to parse the file at `~/.codex/config.toml`. If it does not
|
||||
/// exist, return a default config. Though if it exists and cannot be
|
||||
/// parsed, report that to the user and force them to fix it.
|
||||
fn load_from_toml() -> std::io::Result<Self> {
|
||||
let config_toml_path = codex_dir()?.join("config.toml");
|
||||
match std::fs::read_to_string(&config_toml_path) {
|
||||
Ok(contents) => toml::from_str::<Self>(&contents).map_err(|e| {
|
||||
tracing::error!("Failed to parse config.toml: {e}");
|
||||
std::io::Error::new(std::io::ErrorKind::InvalidData, e)
|
||||
}),
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
|
||||
tracing::info!("config.toml not found, using defaults");
|
||||
Ok(Self::default())
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::error!("Failed to read config.toml: {e}");
|
||||
Err(e)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn deserialize_sandbox_permissions<'de, D>(
|
||||
deserializer: D,
|
||||
) -> Result<Option<Vec<SandboxPermission>>, D::Error>
|
||||
where
|
||||
D: serde::Deserializer<'de>,
|
||||
{
|
||||
let permissions: Option<Vec<String>> = Option::deserialize(deserializer)?;
|
||||
|
||||
match permissions {
|
||||
Some(raw_permissions) => {
|
||||
let base_path = codex_dir().map_err(serde::de::Error::custom)?;
|
||||
|
||||
let converted = raw_permissions
|
||||
.into_iter()
|
||||
.map(|raw| {
|
||||
parse_sandbox_permission_with_base_path(&raw, base_path.clone())
|
||||
.map_err(serde::de::Error::custom)
|
||||
})
|
||||
.collect::<Result<Vec<_>, D::Error>>()?;
|
||||
|
||||
Ok(Some(converted))
|
||||
}
|
||||
None => Ok(None),
|
||||
}
|
||||
}
|
||||
|
||||
/// Optional overrides for user configuration (e.g., from CLI flags).
|
||||
#[derive(Default, Debug, Clone)]
|
||||
pub struct ConfigOverrides {
|
||||
@@ -119,14 +46,11 @@ impl Config {
|
||||
/// ~/.codex/config.toml, ~/.codex/instructions.md, embedded defaults, and
|
||||
/// any values provided in `overrides` (highest precedence).
|
||||
pub fn load_with_overrides(overrides: ConfigOverrides) -> std::io::Result<Self> {
|
||||
let cfg: ConfigToml = ConfigToml::load_from_toml()?;
|
||||
let mut cfg: Config = Self::load_from_toml()?;
|
||||
tracing::warn!("Config parsed from config.toml: {cfg:?}");
|
||||
Ok(Self::load_from_base_config_with_overrides(cfg, overrides))
|
||||
}
|
||||
|
||||
fn load_from_base_config_with_overrides(cfg: ConfigToml, overrides: ConfigOverrides) -> Self {
|
||||
// Instructions: user-provided instructions.md > embedded default.
|
||||
let instructions =
|
||||
cfg.instructions =
|
||||
Self::load_instructions().or_else(|| Some(EMBEDDED_INSTRUCTIONS.to_string()));
|
||||
|
||||
// Destructure ConfigOverrides fully to ensure all overrides are applied.
|
||||
@@ -137,32 +61,50 @@ impl Config {
|
||||
disable_response_storage,
|
||||
} = overrides;
|
||||
|
||||
let sandbox_policy = match sandbox_policy {
|
||||
Some(sandbox_policy) => sandbox_policy,
|
||||
None => {
|
||||
// Derive a SandboxPolicy from the permissions in the config.
|
||||
match cfg.sandbox_permissions {
|
||||
// Note this means the user can explicitly set permissions
|
||||
// to the empty list in the config file, granting it no
|
||||
// permissions whatsoever.
|
||||
Some(permissions) => SandboxPolicy::from(permissions),
|
||||
// Default to read only rather than completely locked down.
|
||||
None => SandboxPolicy::new_read_only_policy(),
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
Self {
|
||||
model: model.or(cfg.model).unwrap_or_else(default_model),
|
||||
approval_policy: approval_policy
|
||||
.or(cfg.approval_policy)
|
||||
.unwrap_or_else(AskForApproval::default),
|
||||
sandbox_policy,
|
||||
disable_response_storage: disable_response_storage
|
||||
.or(cfg.disable_response_storage)
|
||||
.unwrap_or(false),
|
||||
instructions,
|
||||
if let Some(model) = model {
|
||||
cfg.model = model;
|
||||
}
|
||||
if let Some(approval_policy) = approval_policy {
|
||||
cfg.approval_policy = approval_policy;
|
||||
}
|
||||
if let Some(sandbox_policy) = sandbox_policy {
|
||||
cfg.sandbox_policy = sandbox_policy;
|
||||
}
|
||||
if let Some(disable_response_storage) = disable_response_storage {
|
||||
cfg.disable_response_storage = disable_response_storage;
|
||||
}
|
||||
Ok(cfg)
|
||||
}
|
||||
|
||||
/// Attempt to parse the file at `~/.codex/config.toml` into a Config.
|
||||
fn load_from_toml() -> std::io::Result<Self> {
|
||||
let config_toml_path = codex_dir()?.join("config.toml");
|
||||
match std::fs::read_to_string(&config_toml_path) {
|
||||
Ok(contents) => toml::from_str::<Self>(&contents).map_err(|e| {
|
||||
tracing::error!("Failed to parse config.toml: {e}");
|
||||
std::io::Error::new(std::io::ErrorKind::InvalidData, e)
|
||||
}),
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
|
||||
tracing::info!("config.toml not found, using defaults");
|
||||
Ok(Self::load_default_config())
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::error!("Failed to read config.toml: {e}");
|
||||
Err(e)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Meant to be used exclusively for tests: load_with_overrides() should be
|
||||
/// used in all other cases.
|
||||
pub fn load_default_config_for_test() -> Self {
|
||||
Self::load_default_config()
|
||||
}
|
||||
|
||||
fn load_default_config() -> Self {
|
||||
// Load from an empty string to exercise #[serde(default)] to
|
||||
// get the default values for each field.
|
||||
toml::from_str::<Self>("").expect("empty string should parse as TOML")
|
||||
}
|
||||
|
||||
fn load_instructions() -> Option<String> {
|
||||
@@ -170,15 +112,6 @@ impl Config {
|
||||
p.push("instructions.md");
|
||||
std::fs::read_to_string(&p).ok()
|
||||
}
|
||||
|
||||
/// Meant to be used exclusively for tests: `load_with_overrides()` should
|
||||
/// be used in all other cases.
|
||||
pub fn load_default_config_for_test() -> Self {
|
||||
Self::load_from_base_config_with_overrides(
|
||||
ConfigToml::default(),
|
||||
ConfigOverrides::default(),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
fn default_model() -> String {
|
||||
@@ -205,60 +138,3 @@ pub fn log_dir() -> std::io::Result<PathBuf> {
|
||||
p.push("log");
|
||||
Ok(p)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// Verify that the `sandbox_permissions` field on `ConfigToml` correctly
|
||||
/// differentiates between a value that is completely absent in the
|
||||
/// provided TOML (i.e. `None`) and one that is explicitly specified as an
|
||||
/// empty array (i.e. `Some(vec![])`). This ensures that downstream logic
|
||||
/// that treats these two cases differently (default read-only policy vs a
|
||||
/// fully locked-down sandbox) continues to function.
|
||||
#[test]
|
||||
fn test_sandbox_permissions_none_vs_empty_vec() {
|
||||
// Case 1: `sandbox_permissions` key is *absent* from the TOML source.
|
||||
let toml_source_without_key = "";
|
||||
let cfg_without_key: ConfigToml = toml::from_str(toml_source_without_key)
|
||||
.expect("TOML deserialization without key should succeed");
|
||||
assert!(cfg_without_key.sandbox_permissions.is_none());
|
||||
|
||||
// Case 2: `sandbox_permissions` is present but set to an *empty array*.
|
||||
let toml_source_with_empty = "sandbox_permissions = []";
|
||||
let cfg_with_empty: ConfigToml = toml::from_str(toml_source_with_empty)
|
||||
.expect("TOML deserialization with empty array should succeed");
|
||||
assert_eq!(Some(vec![]), cfg_with_empty.sandbox_permissions);
|
||||
|
||||
// Case 3: `sandbox_permissions` contains a non-empty list of valid values.
|
||||
let toml_source_with_values = r#"
|
||||
sandbox_permissions = ["disk-full-read-access", "network-full-access"]
|
||||
"#;
|
||||
let cfg_with_values: ConfigToml = toml::from_str(toml_source_with_values)
|
||||
.expect("TOML deserialization with valid permissions should succeed");
|
||||
|
||||
assert_eq!(
|
||||
Some(vec![
|
||||
SandboxPermission::DiskFullReadAccess,
|
||||
SandboxPermission::NetworkFullAccess
|
||||
]),
|
||||
cfg_with_values.sandbox_permissions
|
||||
);
|
||||
}
|
||||
|
||||
/// Deserializing a TOML string containing an *invalid* permission should
|
||||
/// fail with a helpful error rather than silently defaulting or
|
||||
/// succeeding.
|
||||
#[test]
|
||||
fn test_sandbox_permissions_illegal_value() {
|
||||
let toml_bad = r#"sandbox_permissions = ["not-a-real-permission"]"#;
|
||||
|
||||
let err = toml::from_str::<ConfigToml>(toml_bad)
|
||||
.expect_err("Deserialization should fail for invalid permission");
|
||||
|
||||
// Make sure the error message contains the invalid value so users have
|
||||
// useful feedback.
|
||||
let msg = err.to_string();
|
||||
assert!(msg.contains("not-a-real-permission"));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
use std::io;
|
||||
#[cfg(target_family = "unix")]
|
||||
use std::os::unix::process::ExitStatusExt;
|
||||
use std::path::PathBuf;
|
||||
use std::process::ExitStatus;
|
||||
use std::process::Stdio;
|
||||
use std::sync::Arc;
|
||||
@@ -32,7 +33,7 @@ const DEFAULT_TIMEOUT_MS: u64 = 10_000;
|
||||
const SIGKILL_CODE: i32 = 9;
|
||||
const TIMEOUT_CODE: i32 = 64;
|
||||
|
||||
const MACOS_SEATBELT_BASE_POLICY: &str = include_str!("seatbelt_base_policy.sbpl");
|
||||
const MACOS_SEATBELT_READONLY_POLICY: &str = include_str!("seatbelt_readonly_policy.sbpl");
|
||||
|
||||
/// When working with `sandbox-exec`, only consider `sandbox-exec` in `/usr/bin`
|
||||
/// to defend against an attacker trying to inject a malicious version on the
|
||||
@@ -66,17 +67,19 @@ pub enum SandboxType {
|
||||
#[cfg(target_os = "linux")]
|
||||
async fn exec_linux(
|
||||
params: ExecParams,
|
||||
writable_roots: &[PathBuf],
|
||||
ctrl_c: Arc<Notify>,
|
||||
sandbox_policy: &SandboxPolicy,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
) -> Result<RawExecToolCallOutput> {
|
||||
crate::linux::exec_linux(params, ctrl_c, sandbox_policy).await
|
||||
crate::linux::exec_linux(params, writable_roots, ctrl_c, sandbox_policy).await
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "linux"))]
|
||||
async fn exec_linux(
|
||||
_params: ExecParams,
|
||||
_writable_roots: &[PathBuf],
|
||||
_ctrl_c: Arc<Notify>,
|
||||
_sandbox_policy: &SandboxPolicy,
|
||||
_sandbox_policy: SandboxPolicy,
|
||||
) -> Result<RawExecToolCallOutput> {
|
||||
Err(CodexErr::Io(io::Error::new(
|
||||
io::ErrorKind::InvalidInput,
|
||||
@@ -87,8 +90,9 @@ async fn exec_linux(
|
||||
pub async fn process_exec_tool_call(
|
||||
params: ExecParams,
|
||||
sandbox_type: SandboxType,
|
||||
writable_roots: &[PathBuf],
|
||||
ctrl_c: Arc<Notify>,
|
||||
sandbox_policy: &SandboxPolicy,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
) -> Result<ExecToolCallOutput> {
|
||||
let start = Instant::now();
|
||||
|
||||
@@ -100,7 +104,7 @@ pub async fn process_exec_tool_call(
|
||||
workdir,
|
||||
timeout_ms,
|
||||
} = params;
|
||||
let seatbelt_command = create_seatbelt_command(command, sandbox_policy);
|
||||
let seatbelt_command = create_seatbelt_command(command, sandbox_policy, writable_roots);
|
||||
exec(
|
||||
ExecParams {
|
||||
command: seatbelt_command,
|
||||
@@ -111,7 +115,9 @@ pub async fn process_exec_tool_call(
|
||||
)
|
||||
.await
|
||||
}
|
||||
SandboxType::LinuxSeccomp => exec_linux(params, ctrl_c, sandbox_policy).await,
|
||||
SandboxType::LinuxSeccomp => {
|
||||
exec_linux(params, writable_roots, ctrl_c, sandbox_policy).await
|
||||
}
|
||||
};
|
||||
let duration = start.elapsed();
|
||||
match raw_output_result {
|
||||
@@ -156,61 +162,41 @@ pub async fn process_exec_tool_call(
|
||||
|
||||
pub fn create_seatbelt_command(
|
||||
command: Vec<String>,
|
||||
sandbox_policy: &SandboxPolicy,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
writable_roots: &[PathBuf],
|
||||
) -> Vec<String> {
|
||||
let (file_write_policy, extra_cli_args) = {
|
||||
if sandbox_policy.has_full_disk_write_access() {
|
||||
// Allegedly, this is more permissive than `(allow file-write*)`.
|
||||
(
|
||||
r#"(allow file-write* (regex #"^/"))"#.to_string(),
|
||||
Vec::<String>::new(),
|
||||
)
|
||||
} else {
|
||||
let writable_roots = sandbox_policy.get_writable_roots();
|
||||
let (writable_folder_policies, cli_args): (Vec<String>, Vec<String>) = writable_roots
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(index, root)| {
|
||||
let param_name = format!("WRITABLE_ROOT_{index}");
|
||||
let policy: String = format!("(subpath (param \"{param_name}\"))");
|
||||
let cli_arg = format!("-D{param_name}={}", root.to_string_lossy());
|
||||
(policy, cli_arg)
|
||||
})
|
||||
.unzip();
|
||||
if writable_folder_policies.is_empty() {
|
||||
("".to_string(), Vec::<String>::new())
|
||||
} else {
|
||||
let file_write_policy = format!(
|
||||
"(allow file-write*\n{}\n)",
|
||||
writable_folder_policies.join(" ")
|
||||
);
|
||||
(file_write_policy, cli_args)
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
let file_read_policy = if sandbox_policy.has_full_disk_read_access() {
|
||||
"; allow read-only file operations\n(allow file-read*)"
|
||||
} else {
|
||||
""
|
||||
};
|
||||
let (policies, cli_args): (Vec<String>, Vec<String>) = writable_roots
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(index, root)| {
|
||||
let param_name = format!("WRITABLE_ROOT_{index}");
|
||||
let policy: String = format!("(subpath (param \"{param_name}\"))");
|
||||
let cli_arg = format!("-D{param_name}={}", root.to_string_lossy());
|
||||
(policy, cli_arg)
|
||||
})
|
||||
.unzip();
|
||||
|
||||
// TODO(ragona): The seatbelt policy should reflect the SandboxPolicy that
|
||||
// is passed, but everything is currently hardcoded to use
|
||||
// MACOS_SEATBELT_READONLY_POLICY.
|
||||
// TODO(mbolin): apply_patch calls must also honor the SandboxPolicy.
|
||||
let network_policy = if sandbox_policy.has_full_network_access() {
|
||||
"(allow network-outbound)\n(allow network-inbound)\n(allow system-socket)"
|
||||
if !matches!(sandbox_policy, SandboxPolicy::NetworkRestricted) {
|
||||
tracing::error!("specified sandbox policy {sandbox_policy:?} will not be honroed");
|
||||
}
|
||||
|
||||
let full_policy = if policies.is_empty() {
|
||||
MACOS_SEATBELT_READONLY_POLICY.to_string()
|
||||
} else {
|
||||
""
|
||||
let scoped_write_policy = format!("(allow file-write*\n{}\n)", policies.join(" "));
|
||||
format!("{MACOS_SEATBELT_READONLY_POLICY}\n{scoped_write_policy}")
|
||||
};
|
||||
|
||||
let full_policy = format!(
|
||||
"{MACOS_SEATBELT_BASE_POLICY}\n{file_read_policy}\n{file_write_policy}\n{network_policy}"
|
||||
);
|
||||
let mut seatbelt_command: Vec<String> = vec![
|
||||
MACOS_PATH_TO_SEATBELT_EXECUTABLE.to_string(),
|
||||
"-p".to_string(),
|
||||
full_policy,
|
||||
full_policy.to_string(),
|
||||
];
|
||||
seatbelt_command.extend(extra_cli_args);
|
||||
seatbelt_command.extend(cli_args);
|
||||
seatbelt_command.push("--".to_string());
|
||||
seatbelt_command.extend(command);
|
||||
seatbelt_command
|
||||
|
||||
@@ -28,4 +28,4 @@ mod approval_mode_cli_arg;
|
||||
#[cfg(feature = "cli")]
|
||||
pub use approval_mode_cli_arg::ApprovalModeCliArg;
|
||||
#[cfg(feature = "cli")]
|
||||
pub use approval_mode_cli_arg::SandboxPermissionOption;
|
||||
pub use approval_mode_cli_arg::SandboxModeCliArg;
|
||||
|
||||
@@ -32,13 +32,14 @@ use tokio::sync::Notify;
|
||||
|
||||
pub async fn exec_linux(
|
||||
params: ExecParams,
|
||||
writable_roots: &[PathBuf],
|
||||
ctrl_c: Arc<Notify>,
|
||||
sandbox_policy: &SandboxPolicy,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
) -> Result<RawExecToolCallOutput> {
|
||||
// Allow READ on /
|
||||
// Allow WRITE on /dev/null
|
||||
let ctrl_c_copy = ctrl_c.clone();
|
||||
let sandbox_policy = sandbox_policy.clone();
|
||||
let writable_roots_copy = writable_roots.to_vec();
|
||||
|
||||
// Isolate thread to run the sandbox from
|
||||
let tool_call_output = std::thread::spawn(move || {
|
||||
@@ -48,7 +49,14 @@ pub async fn exec_linux(
|
||||
.expect("Failed to create runtime");
|
||||
|
||||
rt.block_on(async {
|
||||
apply_sandbox_policy_to_current_thread(sandbox_policy)?;
|
||||
if sandbox_policy.is_network_restricted() {
|
||||
install_network_seccomp_filter_on_current_thread()?;
|
||||
}
|
||||
|
||||
if sandbox_policy.is_file_write_restricted() {
|
||||
install_filesystem_landlock_rules_on_current_thread(writable_roots_copy)?;
|
||||
}
|
||||
|
||||
exec(params, ctrl_c_copy).await
|
||||
})
|
||||
})
|
||||
@@ -64,31 +72,15 @@ pub async fn exec_linux(
|
||||
}
|
||||
}
|
||||
|
||||
/// Apply sandbox policies inside this thread so only the child inherits
|
||||
/// them, not the entire CLI process.
|
||||
pub fn apply_sandbox_policy_to_current_thread(sandbox_policy: SandboxPolicy) -> Result<()> {
|
||||
if !sandbox_policy.has_full_network_access() {
|
||||
install_network_seccomp_filter_on_current_thread()?;
|
||||
}
|
||||
|
||||
if !sandbox_policy.has_full_disk_write_access() {
|
||||
let writable_roots = sandbox_policy.get_writable_roots();
|
||||
install_filesystem_landlock_rules_on_current_thread(writable_roots)?;
|
||||
}
|
||||
|
||||
// TODO(ragona): Add appropriate restrictions if
|
||||
// `sandbox_policy.has_full_disk_read_access()` is `false`.
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Installs Landlock file-system rules on the current thread allowing read
|
||||
/// access to the entire file-system while restricting write access to
|
||||
/// `/dev/null` and the provided list of `writable_roots`.
|
||||
///
|
||||
/// # Errors
|
||||
/// Returns [`CodexErr::Sandbox`] variants when the ruleset fails to apply.
|
||||
fn install_filesystem_landlock_rules_on_current_thread(writable_roots: Vec<PathBuf>) -> Result<()> {
|
||||
pub fn install_filesystem_landlock_rules_on_current_thread(
|
||||
writable_roots: Vec<PathBuf>,
|
||||
) -> Result<()> {
|
||||
let abi = ABI::V5;
|
||||
let access_rw = AccessFs::from_all(abi);
|
||||
let access_ro = AccessFs::from_read(abi);
|
||||
@@ -116,7 +108,7 @@ fn install_filesystem_landlock_rules_on_current_thread(writable_roots: Vec<PathB
|
||||
|
||||
/// Installs a seccomp filter that blocks outbound network access except for
|
||||
/// AF_UNIX domain sockets.
|
||||
fn install_network_seccomp_filter_on_current_thread() -> std::result::Result<(), SandboxErr> {
|
||||
pub fn install_network_seccomp_filter_on_current_thread() -> std::result::Result<(), SandboxErr> {
|
||||
// Build rule map.
|
||||
let mut rules: BTreeMap<i64, Vec<SeccompRule>> = BTreeMap::new();
|
||||
|
||||
@@ -192,14 +184,15 @@ mod tests_linux {
|
||||
workdir: None,
|
||||
timeout_ms: Some(timeout_ms),
|
||||
};
|
||||
|
||||
let sandbox_policy =
|
||||
SandboxPolicy::new_read_only_policy_with_writable_roots(writable_roots);
|
||||
let ctrl_c = Arc::new(Notify::new());
|
||||
let res =
|
||||
process_exec_tool_call(params, SandboxType::LinuxSeccomp, ctrl_c, &sandbox_policy)
|
||||
.await
|
||||
.unwrap();
|
||||
let res = process_exec_tool_call(
|
||||
params,
|
||||
SandboxType::LinuxSeccomp,
|
||||
writable_roots,
|
||||
Arc::new(Notify::new()),
|
||||
SandboxPolicy::NetworkAndFileWriteRestricted,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
if res.exit_code != 0 {
|
||||
println!("stdout:\n{}", res.stdout);
|
||||
@@ -268,11 +261,14 @@ mod tests_linux {
|
||||
timeout_ms: Some(2_000),
|
||||
};
|
||||
|
||||
let sandbox_policy = SandboxPolicy::new_read_only_policy();
|
||||
let ctrl_c = Arc::new(Notify::new());
|
||||
let result =
|
||||
process_exec_tool_call(params, SandboxType::LinuxSeccomp, ctrl_c, &sandbox_policy)
|
||||
.await;
|
||||
let result = process_exec_tool_call(
|
||||
params,
|
||||
SandboxType::LinuxSeccomp,
|
||||
&[],
|
||||
Arc::new(Notify::new()),
|
||||
SandboxPolicy::NetworkRestricted,
|
||||
)
|
||||
.await;
|
||||
|
||||
let (exit_code, stdout, stderr) = match result {
|
||||
Ok(output) => (output.exit_code, output.stdout, output.stderr),
|
||||
|
||||
@@ -93,159 +93,44 @@ pub enum AskForApproval {
|
||||
}
|
||||
|
||||
/// Determines execution restrictions for model shell commands
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Deserialize, Serialize)]
|
||||
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Hash, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "kebab-case")]
|
||||
pub struct SandboxPolicy {
|
||||
permissions: Vec<SandboxPermission>,
|
||||
}
|
||||
|
||||
impl From<Vec<SandboxPermission>> for SandboxPolicy {
|
||||
fn from(permissions: Vec<SandboxPermission>) -> Self {
|
||||
Self { permissions }
|
||||
}
|
||||
pub enum SandboxPolicy {
|
||||
/// Network syscalls will be blocked
|
||||
NetworkRestricted,
|
||||
/// Filesystem writes will be restricted
|
||||
FileWriteRestricted,
|
||||
/// Network and filesystem writes will be restricted
|
||||
#[default]
|
||||
NetworkAndFileWriteRestricted,
|
||||
/// No restrictions; full "unsandboxed" mode
|
||||
DangerousNoRestrictions,
|
||||
}
|
||||
|
||||
impl SandboxPolicy {
|
||||
pub fn new_read_only_policy() -> Self {
|
||||
Self {
|
||||
permissions: vec![SandboxPermission::DiskFullReadAccess],
|
||||
pub fn is_dangerous(&self) -> bool {
|
||||
match self {
|
||||
SandboxPolicy::NetworkRestricted => false,
|
||||
SandboxPolicy::FileWriteRestricted => false,
|
||||
SandboxPolicy::NetworkAndFileWriteRestricted => false,
|
||||
SandboxPolicy::DangerousNoRestrictions => true,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn new_read_only_policy_with_writable_roots(writable_roots: &[PathBuf]) -> Self {
|
||||
let mut permissions = Self::new_read_only_policy().permissions;
|
||||
permissions.extend(writable_roots.iter().map(|folder| {
|
||||
SandboxPermission::DiskWriteFolder {
|
||||
folder: folder.clone(),
|
||||
}
|
||||
}));
|
||||
Self { permissions }
|
||||
pub fn is_network_restricted(&self) -> bool {
|
||||
matches!(
|
||||
self,
|
||||
SandboxPolicy::NetworkRestricted | SandboxPolicy::NetworkAndFileWriteRestricted
|
||||
)
|
||||
}
|
||||
|
||||
pub fn new_full_auto_policy() -> Self {
|
||||
Self {
|
||||
permissions: vec![
|
||||
SandboxPermission::DiskFullReadAccess,
|
||||
SandboxPermission::DiskWritePlatformUserTempFolder,
|
||||
SandboxPermission::DiskWriteCwd,
|
||||
],
|
||||
}
|
||||
}
|
||||
|
||||
pub fn has_full_disk_read_access(&self) -> bool {
|
||||
self.permissions
|
||||
.iter()
|
||||
.any(|perm| matches!(perm, SandboxPermission::DiskFullReadAccess))
|
||||
}
|
||||
|
||||
pub fn has_full_disk_write_access(&self) -> bool {
|
||||
self.permissions
|
||||
.iter()
|
||||
.any(|perm| matches!(perm, SandboxPermission::DiskFullWriteAccess))
|
||||
}
|
||||
|
||||
pub fn has_full_network_access(&self) -> bool {
|
||||
self.permissions
|
||||
.iter()
|
||||
.any(|perm| matches!(perm, SandboxPermission::NetworkFullAccess))
|
||||
}
|
||||
|
||||
pub fn get_writable_roots(&self) -> Vec<PathBuf> {
|
||||
let mut writable_roots = Vec::<PathBuf>::new();
|
||||
for perm in &self.permissions {
|
||||
use SandboxPermission::*;
|
||||
match perm {
|
||||
DiskWritePlatformUserTempFolder => {
|
||||
if cfg!(target_os = "macos") {
|
||||
if let Some(tempdir) = std::env::var_os("TMPDIR") {
|
||||
// Likely something that starts with /var/folders/...
|
||||
let tmpdir_path = PathBuf::from(&tempdir);
|
||||
if tmpdir_path.is_absolute() {
|
||||
writable_roots.push(tmpdir_path.clone());
|
||||
match tmpdir_path.canonicalize() {
|
||||
Ok(canonicalized) => {
|
||||
// Likely something that starts with /private/var/folders/...
|
||||
if canonicalized != tmpdir_path {
|
||||
writable_roots.push(canonicalized);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::error!("Failed to canonicalize TMPDIR: {e}");
|
||||
}
|
||||
}
|
||||
} else {
|
||||
tracing::error!("TMPDIR is not an absolute path: {tempdir:?}");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// For Linux, should this be XDG_RUNTIME_DIR, /run/user/<uid>, or something else?
|
||||
}
|
||||
DiskWritePlatformGlobalTempFolder => {
|
||||
if cfg!(unix) {
|
||||
writable_roots.push(PathBuf::from("/tmp"));
|
||||
}
|
||||
}
|
||||
DiskWriteCwd => match std::env::current_dir() {
|
||||
Ok(cwd) => writable_roots.push(cwd),
|
||||
Err(err) => {
|
||||
tracing::error!("Failed to get current working directory: {err}");
|
||||
}
|
||||
},
|
||||
DiskWriteFolder { folder } => {
|
||||
writable_roots.push(folder.clone());
|
||||
}
|
||||
DiskFullReadAccess | NetworkFullAccess => {}
|
||||
DiskFullWriteAccess => {
|
||||
// Currently, we expect callers to only invoke this method
|
||||
// after verifying has_full_disk_write_access() is false.
|
||||
}
|
||||
}
|
||||
}
|
||||
writable_roots
|
||||
}
|
||||
|
||||
pub fn is_unrestricted(&self) -> bool {
|
||||
self.has_full_disk_read_access()
|
||||
&& self.has_full_disk_write_access()
|
||||
&& self.has_full_network_access()
|
||||
pub fn is_file_write_restricted(&self) -> bool {
|
||||
matches!(
|
||||
self,
|
||||
SandboxPolicy::FileWriteRestricted | SandboxPolicy::NetworkAndFileWriteRestricted
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
/// Permissions that should be granted to the sandbox in which the agent
|
||||
/// operates.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "kebab-case")]
|
||||
pub enum SandboxPermission {
|
||||
/// Is allowed to read all files on disk.
|
||||
DiskFullReadAccess,
|
||||
|
||||
/// Is allowed to write to the operating system's temp dir that
|
||||
/// is restricted to the user the agent is running as. For
|
||||
/// example, on macOS, this is generally something under
|
||||
/// `/var/folders` as opposed to `/tmp`.
|
||||
DiskWritePlatformUserTempFolder,
|
||||
|
||||
/// Is allowed to write to the operating system's shared temp
|
||||
/// dir. On UNIX, this is generally `/tmp`.
|
||||
DiskWritePlatformGlobalTempFolder,
|
||||
|
||||
/// Is allowed to write to the current working directory (in practice, this
|
||||
/// is the `cwd` where `codex` was spawned).
|
||||
DiskWriteCwd,
|
||||
|
||||
/// Is allowed to the specified folder. `PathBuf` must be an
|
||||
/// absolute path, though it is up to the caller to canonicalize
|
||||
/// it if the path contains symlinks.
|
||||
DiskWriteFolder { folder: PathBuf },
|
||||
|
||||
/// Is allowed to write to any file on disk.
|
||||
DiskFullWriteAccess,
|
||||
|
||||
/// Can make arbitrary network requests.
|
||||
NetworkFullAccess,
|
||||
}
|
||||
|
||||
/// User input
|
||||
#[non_exhaustive]
|
||||
#[derive(Debug, Clone, Deserialize, Serialize)]
|
||||
|
||||
@@ -65,7 +65,7 @@ pub fn assess_patch_safety(
|
||||
pub fn assess_command_safety(
|
||||
command: &[String],
|
||||
approval_policy: AskForApproval,
|
||||
sandbox_policy: &SandboxPolicy,
|
||||
sandbox_policy: SandboxPolicy,
|
||||
approved: &HashSet<Vec<String>>,
|
||||
) -> SafetyCheck {
|
||||
let approve_without_sandbox = || SafetyCheck::AutoApprove {
|
||||
@@ -81,10 +81,11 @@ pub fn assess_command_safety(
|
||||
}
|
||||
|
||||
// Command was not known-safe or allow-listed
|
||||
if sandbox_policy.is_unrestricted() {
|
||||
approve_without_sandbox()
|
||||
} else {
|
||||
match get_platform_sandbox() {
|
||||
match sandbox_policy {
|
||||
// Only the dangerous sandbox policy will run arbitrary commands outside a sandbox
|
||||
SandboxPolicy::DangerousNoRestrictions => approve_without_sandbox(),
|
||||
// All other policies try to run the command in a sandbox if it is available
|
||||
_ => match get_platform_sandbox() {
|
||||
// We have a sandbox, so we can approve the command in all modes
|
||||
Some(sandbox_type) => SafetyCheck::AutoApprove { sandbox_type },
|
||||
None => {
|
||||
@@ -98,7 +99,7 @@ pub fn assess_command_safety(
|
||||
_ => SafetyCheck::AskUser,
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -6,6 +6,9 @@
|
||||
; start with closed-by-default
|
||||
(deny default)
|
||||
|
||||
; allow read-only file operations
|
||||
(allow file-read*)
|
||||
|
||||
; child processes inherit the policy of their parent
|
||||
(allow process-exec)
|
||||
(allow process-fork)
|
||||
@@ -55,7 +55,7 @@ async fn spawn_codex() -> Codex {
|
||||
model: config.model,
|
||||
instructions: None,
|
||||
approval_policy: config.approval_policy,
|
||||
sandbox_policy: SandboxPolicy::new_read_only_policy(),
|
||||
sandbox_policy: SandboxPolicy::NetworkAndFileWriteRestricted,
|
||||
disable_response_storage: false,
|
||||
},
|
||||
})
|
||||
|
||||
@@ -95,7 +95,7 @@ async fn keeps_previous_response_id_between_tasks() {
|
||||
model: config.model,
|
||||
instructions: None,
|
||||
approval_policy: config.approval_policy,
|
||||
sandbox_policy: SandboxPolicy::new_read_only_policy(),
|
||||
sandbox_policy: SandboxPolicy::NetworkAndFileWriteRestricted,
|
||||
disable_response_storage: false,
|
||||
},
|
||||
})
|
||||
|
||||
@@ -78,7 +78,7 @@ async fn retries_on_early_close() {
|
||||
model: config.model,
|
||||
instructions: None,
|
||||
approval_policy: config.approval_policy,
|
||||
sandbox_policy: SandboxPolicy::new_read_only_policy(),
|
||||
sandbox_policy: SandboxPolicy::NetworkAndFileWriteRestricted,
|
||||
disable_response_storage: false,
|
||||
},
|
||||
})
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "codex-exec"
|
||||
version = { workspace = true }
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[[bin]]
|
||||
@@ -13,11 +13,8 @@ path = "src/lib.rs"
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1"
|
||||
chrono = "0.4.40"
|
||||
clap = { version = "4", features = ["derive"] }
|
||||
codex-core = { path = "../core", features = ["cli"] }
|
||||
owo-colors = "4.2.0"
|
||||
shlex = "1.3.0"
|
||||
tokio = { version = "1", features = [
|
||||
"io-std",
|
||||
"macros",
|
||||
@@ -27,3 +24,4 @@ tokio = { version = "1", features = [
|
||||
] }
|
||||
tracing = { version = "0.1.41", features = ["log"] }
|
||||
tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
|
||||
owo-colors = "4.2.0"
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
use clap::Parser;
|
||||
use clap::ValueEnum;
|
||||
use codex_core::SandboxPermissionOption;
|
||||
use codex_core::SandboxModeCliArg;
|
||||
use std::path::PathBuf;
|
||||
|
||||
#[derive(Parser, Debug)]
|
||||
@@ -14,12 +13,11 @@ pub struct Cli {
|
||||
#[arg(long, short = 'm')]
|
||||
pub model: Option<String>,
|
||||
|
||||
/// Convenience alias for low-friction sandboxed automatic execution (network-disabled sandbox that can write to cwd and TMPDIR)
|
||||
#[arg(long = "full-auto", default_value_t = false)]
|
||||
pub full_auto: bool,
|
||||
|
||||
#[clap(flatten)]
|
||||
pub sandbox: SandboxPermissionOption,
|
||||
/// Configure the process restrictions when a command is executed.
|
||||
///
|
||||
/// Uses OS-specific sandboxing tools; Seatbelt on OSX, landlock+seccomp on Linux.
|
||||
#[arg(long = "sandbox", short = 's')]
|
||||
pub sandbox_policy: Option<SandboxModeCliArg>,
|
||||
|
||||
/// Allow running Codex outside a Git repository.
|
||||
#[arg(long = "skip-git-repo-check", default_value_t = false)]
|
||||
@@ -29,19 +27,6 @@ pub struct Cli {
|
||||
#[arg(long = "disable-response-storage", default_value_t = false)]
|
||||
pub disable_response_storage: bool,
|
||||
|
||||
/// Specifies color settings for use in the output.
|
||||
#[arg(long = "color", value_enum, default_value_t = Color::Auto)]
|
||||
pub color: Color,
|
||||
|
||||
/// Initial instructions for the agent.
|
||||
pub prompt: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, ValueEnum)]
|
||||
#[value(rename_all = "kebab-case")]
|
||||
pub enum Color {
|
||||
Always,
|
||||
Never,
|
||||
#[default]
|
||||
Auto,
|
||||
pub prompt: Option<String>,
|
||||
}
|
||||
|
||||
@@ -1,307 +0,0 @@
|
||||
use chrono::Utc;
|
||||
use codex_core::protocol::Event;
|
||||
use codex_core::protocol::EventMsg;
|
||||
use codex_core::protocol::FileChange;
|
||||
use owo_colors::OwoColorize;
|
||||
use owo_colors::Style;
|
||||
use shlex::try_join;
|
||||
use std::collections::HashMap;
|
||||
|
||||
/// This should be configurable. When used in CI, users may not want to impose
|
||||
/// a limit so they can see the full transcript.
|
||||
const MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL: usize = 20;
|
||||
|
||||
pub(crate) struct EventProcessor {
|
||||
call_id_to_command: HashMap<String, ExecCommandBegin>,
|
||||
call_id_to_patch: HashMap<String, PatchApplyBegin>,
|
||||
|
||||
// To ensure that --color=never is respected, ANSI escapes _must_ be added
|
||||
// using .style() with one of these fields. If you need a new style, add a
|
||||
// new field here.
|
||||
bold: Style,
|
||||
dimmed: Style,
|
||||
|
||||
magenta: Style,
|
||||
red: Style,
|
||||
green: Style,
|
||||
}
|
||||
|
||||
impl EventProcessor {
|
||||
pub(crate) fn create_with_ansi(with_ansi: bool) -> Self {
|
||||
let call_id_to_command = HashMap::new();
|
||||
let call_id_to_patch = HashMap::new();
|
||||
|
||||
if with_ansi {
|
||||
Self {
|
||||
call_id_to_command,
|
||||
call_id_to_patch,
|
||||
bold: Style::new().bold(),
|
||||
dimmed: Style::new().dimmed(),
|
||||
magenta: Style::new().magenta(),
|
||||
red: Style::new().red(),
|
||||
green: Style::new().green(),
|
||||
}
|
||||
} else {
|
||||
Self {
|
||||
call_id_to_command,
|
||||
call_id_to_patch,
|
||||
bold: Style::new(),
|
||||
dimmed: Style::new(),
|
||||
magenta: Style::new(),
|
||||
red: Style::new(),
|
||||
green: Style::new(),
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
struct ExecCommandBegin {
|
||||
command: Vec<String>,
|
||||
start_time: chrono::DateTime<Utc>,
|
||||
}
|
||||
|
||||
struct PatchApplyBegin {
|
||||
start_time: chrono::DateTime<Utc>,
|
||||
auto_approved: bool,
|
||||
}
|
||||
|
||||
macro_rules! ts_println {
|
||||
($($arg:tt)*) => {{
|
||||
let now = Utc::now();
|
||||
let formatted = now.format("%Y-%m-%dT%H:%M:%S").to_string();
|
||||
print!("[{}] ", formatted);
|
||||
println!($($arg)*);
|
||||
}};
|
||||
}
|
||||
|
||||
impl EventProcessor {
|
||||
pub(crate) fn process_event(&mut self, event: Event) {
|
||||
let Event { id, msg } = event;
|
||||
match msg {
|
||||
EventMsg::Error { message } => {
|
||||
let prefix = "ERROR:".style(self.red);
|
||||
ts_println!("{prefix} {message}");
|
||||
}
|
||||
EventMsg::BackgroundEvent { message } => {
|
||||
ts_println!("{}", message.style(self.dimmed));
|
||||
}
|
||||
EventMsg::TaskStarted => {
|
||||
let msg = format!("Task started: {id}");
|
||||
ts_println!("{}", msg.style(self.dimmed));
|
||||
}
|
||||
EventMsg::TaskComplete => {
|
||||
let msg = format!("Task complete: {id}");
|
||||
ts_println!("{}", msg.style(self.bold));
|
||||
}
|
||||
EventMsg::AgentMessage { message } => {
|
||||
let prefix = "Agent message:".style(self.bold);
|
||||
ts_println!("{prefix} {message}");
|
||||
}
|
||||
EventMsg::ExecCommandBegin {
|
||||
call_id,
|
||||
command,
|
||||
cwd,
|
||||
} => {
|
||||
self.call_id_to_command.insert(
|
||||
call_id.clone(),
|
||||
ExecCommandBegin {
|
||||
command: command.clone(),
|
||||
start_time: Utc::now(),
|
||||
},
|
||||
);
|
||||
ts_println!(
|
||||
"{} {} in {}",
|
||||
"exec".style(self.magenta),
|
||||
escape_command(&command).style(self.bold),
|
||||
cwd,
|
||||
);
|
||||
}
|
||||
EventMsg::ExecCommandEnd {
|
||||
call_id,
|
||||
stdout,
|
||||
stderr,
|
||||
exit_code,
|
||||
} => {
|
||||
let exec_command = self.call_id_to_command.remove(&call_id);
|
||||
let (duration, call) = if let Some(ExecCommandBegin {
|
||||
command,
|
||||
start_time,
|
||||
}) = exec_command
|
||||
{
|
||||
(
|
||||
format_duration(start_time),
|
||||
format!("{}", escape_command(&command).style(self.bold)),
|
||||
)
|
||||
} else {
|
||||
("".to_string(), format!("exec('{call_id}')"))
|
||||
};
|
||||
|
||||
let output = if exit_code == 0 { stdout } else { stderr };
|
||||
let truncated_output = output
|
||||
.lines()
|
||||
.take(MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL)
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n");
|
||||
match exit_code {
|
||||
0 => {
|
||||
let title = format!("{call} succeded{duration}:");
|
||||
ts_println!("{}", title.style(self.green));
|
||||
}
|
||||
_ => {
|
||||
let title = format!("{call} exited {exit_code}{duration}:");
|
||||
ts_println!("{}", title.style(self.red));
|
||||
}
|
||||
}
|
||||
println!("{}", truncated_output.style(self.dimmed));
|
||||
}
|
||||
EventMsg::PatchApplyBegin {
|
||||
call_id,
|
||||
auto_approved,
|
||||
changes,
|
||||
} => {
|
||||
// Store metadata so we can calculate duration later when we
|
||||
// receive the corresponding PatchApplyEnd event.
|
||||
self.call_id_to_patch.insert(
|
||||
call_id.clone(),
|
||||
PatchApplyBegin {
|
||||
start_time: Utc::now(),
|
||||
auto_approved,
|
||||
},
|
||||
);
|
||||
|
||||
ts_println!(
|
||||
"{} auto_approved={}:",
|
||||
"apply_patch".style(self.magenta),
|
||||
auto_approved,
|
||||
);
|
||||
|
||||
// Pretty-print the patch summary with colored diff markers so
|
||||
// it’s easy to scan in the terminal output.
|
||||
for (path, change) in changes.iter() {
|
||||
match change {
|
||||
FileChange::Add { content } => {
|
||||
let header = format!(
|
||||
"{} {}",
|
||||
format_file_change(change),
|
||||
path.to_string_lossy()
|
||||
);
|
||||
println!("{}", header.style(self.magenta));
|
||||
for line in content.lines() {
|
||||
println!("{}", line.style(self.green));
|
||||
}
|
||||
}
|
||||
FileChange::Delete => {
|
||||
let header = format!(
|
||||
"{} {}",
|
||||
format_file_change(change),
|
||||
path.to_string_lossy()
|
||||
);
|
||||
println!("{}", header.style(self.magenta));
|
||||
}
|
||||
FileChange::Update {
|
||||
unified_diff,
|
||||
move_path,
|
||||
} => {
|
||||
let header = if let Some(dest) = move_path {
|
||||
format!(
|
||||
"{} {} -> {}",
|
||||
format_file_change(change),
|
||||
path.to_string_lossy(),
|
||||
dest.to_string_lossy()
|
||||
)
|
||||
} else {
|
||||
format!("{} {}", format_file_change(change), path.to_string_lossy())
|
||||
};
|
||||
println!("{}", header.style(self.magenta));
|
||||
|
||||
// Colorize diff lines. We keep file header lines
|
||||
// (--- / +++) without extra coloring so they are
|
||||
// still readable.
|
||||
for diff_line in unified_diff.lines() {
|
||||
if diff_line.starts_with('+') && !diff_line.starts_with("+++") {
|
||||
println!("{}", diff_line.style(self.green));
|
||||
} else if diff_line.starts_with('-')
|
||||
&& !diff_line.starts_with("---")
|
||||
{
|
||||
println!("{}", diff_line.style(self.red));
|
||||
} else {
|
||||
println!("{diff_line}");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
EventMsg::PatchApplyEnd {
|
||||
call_id,
|
||||
stdout,
|
||||
stderr,
|
||||
success,
|
||||
} => {
|
||||
let patch_begin = self.call_id_to_patch.remove(&call_id);
|
||||
|
||||
// Compute duration and summary label similar to exec commands.
|
||||
let (duration, label) = if let Some(PatchApplyBegin {
|
||||
start_time,
|
||||
auto_approved,
|
||||
}) = patch_begin
|
||||
{
|
||||
(
|
||||
format_duration(start_time),
|
||||
format!("apply_patch(auto_approved={})", auto_approved),
|
||||
)
|
||||
} else {
|
||||
(String::new(), format!("apply_patch('{call_id}')"))
|
||||
};
|
||||
|
||||
let (exit_code, output, title_style) = if success {
|
||||
(0, stdout, self.green)
|
||||
} else {
|
||||
(1, stderr, self.red)
|
||||
};
|
||||
|
||||
let title = format!("{label} exited {exit_code}{duration}:");
|
||||
ts_println!("{}", title.style(title_style));
|
||||
for line in output.lines() {
|
||||
println!("{}", line.style(self.dimmed));
|
||||
}
|
||||
}
|
||||
EventMsg::ExecApprovalRequest { .. } => {
|
||||
// Should we exit?
|
||||
}
|
||||
EventMsg::ApplyPatchApprovalRequest { .. } => {
|
||||
// Should we exit?
|
||||
}
|
||||
_ => {
|
||||
// Ignore event.
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn escape_command(command: &[String]) -> String {
|
||||
try_join(command.iter().map(|s| s.as_str())).unwrap_or_else(|_| command.join(" "))
|
||||
}
|
||||
|
||||
fn format_file_change(change: &FileChange) -> &'static str {
|
||||
match change {
|
||||
FileChange::Add { .. } => "A",
|
||||
FileChange::Delete => "D",
|
||||
FileChange::Update {
|
||||
move_path: Some(_), ..
|
||||
} => "R",
|
||||
FileChange::Update {
|
||||
move_path: None, ..
|
||||
} => "M",
|
||||
}
|
||||
}
|
||||
|
||||
fn format_duration(start_time: chrono::DateTime<Utc>) -> String {
|
||||
let elapsed = Utc::now().signed_duration_since(start_time);
|
||||
let millis = elapsed.num_milliseconds();
|
||||
if millis < 1000 {
|
||||
format!(" in {}ms", millis)
|
||||
} else {
|
||||
format!(" in {:.2}s", millis as f64 / 1000.0)
|
||||
}
|
||||
}
|
||||
@@ -1,7 +1,4 @@
|
||||
mod cli;
|
||||
mod event_processor;
|
||||
|
||||
use std::io::IsTerminal;
|
||||
use std::sync::Arc;
|
||||
|
||||
pub use cli::Cli;
|
||||
@@ -11,71 +8,80 @@ use codex_core::config::ConfigOverrides;
|
||||
use codex_core::protocol::AskForApproval;
|
||||
use codex_core::protocol::Event;
|
||||
use codex_core::protocol::EventMsg;
|
||||
use codex_core::protocol::FileChange;
|
||||
use codex_core::protocol::InputItem;
|
||||
use codex_core::protocol::Op;
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use codex_core::util::is_inside_git_repo;
|
||||
use event_processor::EventProcessor;
|
||||
use owo_colors::OwoColorize;
|
||||
use owo_colors::Style;
|
||||
use tracing::debug;
|
||||
use tracing::error;
|
||||
use tracing::info;
|
||||
use tracing_subscriber::EnvFilter;
|
||||
|
||||
/// Returns `true` if a recognised API key is present in the environment.
|
||||
///
|
||||
/// At present we only support `OPENAI_API_KEY`, mirroring the behaviour of the
|
||||
/// Node-based `codex-cli`. Additional providers can be added here when the
|
||||
/// Rust implementation gains first-class support for them.
|
||||
fn has_api_key() -> bool {
|
||||
std::env::var("OPENAI_API_KEY")
|
||||
.map(|s| !s.trim().is_empty())
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
pub async fn run_main(cli: Cli) -> anyhow::Result<()> {
|
||||
let Cli {
|
||||
images,
|
||||
model,
|
||||
full_auto,
|
||||
sandbox,
|
||||
skip_git_repo_check,
|
||||
disable_response_storage,
|
||||
color,
|
||||
prompt,
|
||||
} = cli;
|
||||
|
||||
let (stdout_with_ansi, stderr_with_ansi) = match color {
|
||||
cli::Color::Always => (true, true),
|
||||
cli::Color::Never => (false, false),
|
||||
cli::Color::Auto => (
|
||||
std::io::stdout().is_terminal(),
|
||||
std::io::stderr().is_terminal(),
|
||||
),
|
||||
};
|
||||
|
||||
assert_api_key(stderr_with_ansi);
|
||||
|
||||
if !skip_git_repo_check && !is_inside_git_repo() {
|
||||
eprintln!("Not inside a Git repo and --skip-git-repo-check was not specified.");
|
||||
std::process::exit(1);
|
||||
}
|
||||
|
||||
// TODO(mbolin): Take a more thoughtful approach to logging.
|
||||
let default_level = "error";
|
||||
let allow_ansi = true;
|
||||
let _ = tracing_subscriber::fmt()
|
||||
.with_env_filter(
|
||||
EnvFilter::try_from_default_env()
|
||||
.or_else(|_| EnvFilter::try_new(default_level))
|
||||
.unwrap(),
|
||||
)
|
||||
.with_ansi(stderr_with_ansi)
|
||||
.with_ansi(allow_ansi)
|
||||
.with_writer(std::io::stderr)
|
||||
.try_init();
|
||||
|
||||
let sandbox_policy = if full_auto {
|
||||
Some(SandboxPolicy::new_full_auto_policy())
|
||||
} else {
|
||||
sandbox.permissions.clone().map(Into::into)
|
||||
};
|
||||
let Cli {
|
||||
images,
|
||||
model,
|
||||
sandbox_policy,
|
||||
skip_git_repo_check,
|
||||
disable_response_storage,
|
||||
prompt,
|
||||
..
|
||||
} = cli;
|
||||
|
||||
// ---------------------------------------------------------------------
|
||||
// API key handling
|
||||
// ---------------------------------------------------------------------
|
||||
|
||||
if !has_api_key() {
|
||||
eprintln!(
|
||||
"\n{msg}\n\nSet the environment variable {var} and re-run this command.\nYou can create a key here: {url}\n",
|
||||
msg = "Missing OpenAI API key.".red(),
|
||||
var = "OPENAI_API_KEY".bold(),
|
||||
url = "https://platform.openai.com/account/api-keys".bold().underline(),
|
||||
);
|
||||
std::process::exit(1);
|
||||
}
|
||||
|
||||
if !skip_git_repo_check && !is_inside_git_repo() {
|
||||
eprintln!("Not inside a Git repo and --skip-git-repo-check was not specified.");
|
||||
std::process::exit(1);
|
||||
} else if images.is_empty() && prompt.is_none() {
|
||||
eprintln!("No images or prompt specified.");
|
||||
std::process::exit(1);
|
||||
}
|
||||
|
||||
// Load configuration and determine approval policy
|
||||
let overrides = ConfigOverrides {
|
||||
model,
|
||||
model: model.clone(),
|
||||
// This CLI is intended to be headless and has no affordances for asking
|
||||
// the user for approval.
|
||||
approval_policy: Some(AskForApproval::Never),
|
||||
sandbox_policy,
|
||||
sandbox_policy: sandbox_policy.map(Into::into),
|
||||
disable_response_storage: if disable_response_storage {
|
||||
Some(true)
|
||||
} else {
|
||||
@@ -109,6 +115,7 @@ pub async fn run_main(cli: Cli) -> anyhow::Result<()> {
|
||||
res = codex.next_event() => match res {
|
||||
Ok(event) => {
|
||||
debug!("Received event: {event:?}");
|
||||
process_event(&event);
|
||||
if let Err(e) = tx.send(event) {
|
||||
error!("Error sending event: {e:?}");
|
||||
break;
|
||||
@@ -124,8 +131,8 @@ pub async fn run_main(cli: Cli) -> anyhow::Result<()> {
|
||||
});
|
||||
}
|
||||
|
||||
// Send images first, if any.
|
||||
if !images.is_empty() {
|
||||
// Send images first.
|
||||
let items: Vec<InputItem> = images
|
||||
.into_iter()
|
||||
.map(|path| InputItem::LocalImage { path })
|
||||
@@ -139,56 +146,101 @@ pub async fn run_main(cli: Cli) -> anyhow::Result<()> {
|
||||
}
|
||||
}
|
||||
|
||||
// Send the prompt.
|
||||
let items: Vec<InputItem> = vec![InputItem::Text { text: prompt }];
|
||||
let initial_prompt_task_id = codex.submit(Op::UserInput { items }).await?;
|
||||
info!("Sent prompt with event ID: {initial_prompt_task_id}");
|
||||
|
||||
// Run the loop until the task is complete.
|
||||
let mut event_processor = EventProcessor::create_with_ansi(stdout_with_ansi);
|
||||
while let Some(event) = rx.recv().await {
|
||||
let last_event =
|
||||
event.id == initial_prompt_task_id && matches!(event.msg, EventMsg::TaskComplete);
|
||||
event_processor.process_event(event);
|
||||
if last_event {
|
||||
break;
|
||||
if let Some(prompt) = prompt {
|
||||
// Send the prompt.
|
||||
let items: Vec<InputItem> = vec![InputItem::Text { text: prompt }];
|
||||
let initial_prompt_task_id = codex.submit(Op::UserInput { items }).await?;
|
||||
info!("Sent prompt with event ID: {initial_prompt_task_id}");
|
||||
while let Some(event) = rx.recv().await {
|
||||
if event.id == initial_prompt_task_id && matches!(event.msg, EventMsg::TaskComplete) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// If a valid API key is not present in the environment, print an error to
|
||||
/// stderr and exits with 1; otherwise, does nothing.
|
||||
fn assert_api_key(stderr_with_ansi: bool) {
|
||||
if !has_api_key() {
|
||||
let (msg_style, var_style, url_style) = if stderr_with_ansi {
|
||||
(
|
||||
Style::new().red(),
|
||||
Style::new().bold(),
|
||||
Style::new().bold().underline(),
|
||||
)
|
||||
} else {
|
||||
(Style::new(), Style::new(), Style::new())
|
||||
};
|
||||
|
||||
eprintln!(
|
||||
"\n{msg}\n\nSet the environment variable {var} and re-run this command.\nYou can create a key here: {url}\n",
|
||||
msg = "Missing OpenAI API key.".style(msg_style),
|
||||
var = "OPENAI_API_KEY".style(var_style),
|
||||
url = "https://platform.openai.com/account/api-keys".style(url_style),
|
||||
);
|
||||
std::process::exit(1);
|
||||
fn process_event(event: &Event) {
|
||||
let Event { id, msg } = event;
|
||||
match msg {
|
||||
EventMsg::Error { message } => {
|
||||
println!("Error: {message}");
|
||||
}
|
||||
EventMsg::BackgroundEvent { .. } => {
|
||||
// Ignore these for now.
|
||||
}
|
||||
EventMsg::TaskStarted => {
|
||||
println!("Task started: {id}");
|
||||
}
|
||||
EventMsg::TaskComplete => {
|
||||
println!("Task complete: {id}");
|
||||
}
|
||||
EventMsg::AgentMessage { message } => {
|
||||
println!("Agent message: {message}");
|
||||
}
|
||||
EventMsg::ExecCommandBegin {
|
||||
call_id,
|
||||
command,
|
||||
cwd,
|
||||
} => {
|
||||
println!("exec('{call_id}'): {:?} in {cwd}", command);
|
||||
}
|
||||
EventMsg::ExecCommandEnd {
|
||||
call_id,
|
||||
stdout,
|
||||
stderr,
|
||||
exit_code,
|
||||
} => {
|
||||
let output = if *exit_code == 0 { stdout } else { stderr };
|
||||
let truncated_output = output.lines().take(5).collect::<Vec<_>>().join("\n");
|
||||
println!("exec('{call_id}') exited {exit_code}:\n{truncated_output}");
|
||||
}
|
||||
EventMsg::PatchApplyBegin {
|
||||
call_id,
|
||||
auto_approved,
|
||||
changes,
|
||||
} => {
|
||||
let changes = changes
|
||||
.iter()
|
||||
.map(|(path, change)| {
|
||||
format!("{} {}", format_file_change(change), path.to_string_lossy())
|
||||
})
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n");
|
||||
println!("apply_patch('{call_id}') auto_approved={auto_approved}:\n{changes}");
|
||||
}
|
||||
EventMsg::PatchApplyEnd {
|
||||
call_id,
|
||||
stdout,
|
||||
stderr,
|
||||
success,
|
||||
} => {
|
||||
let (exit_code, output) = if *success { (0, stdout) } else { (1, stderr) };
|
||||
let truncated_output = output.lines().take(5).collect::<Vec<_>>().join("\n");
|
||||
println!("apply_patch('{call_id}') exited {exit_code}:\n{truncated_output}");
|
||||
}
|
||||
EventMsg::ExecApprovalRequest { .. } => {
|
||||
// Should we exit?
|
||||
}
|
||||
EventMsg::ApplyPatchApprovalRequest { .. } => {
|
||||
// Should we exit?
|
||||
}
|
||||
_ => {
|
||||
// Ignore event.
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Returns `true` if a recognized API key is present in the environment.
|
||||
///
|
||||
/// At present we only support `OPENAI_API_KEY`, mirroring the behavior of the
|
||||
/// Node-based `codex-cli`. Additional providers can be added here when the
|
||||
/// Rust implementation gains first-class support for them.
|
||||
fn has_api_key() -> bool {
|
||||
std::env::var("OPENAI_API_KEY")
|
||||
.map(|s| !s.trim().is_empty())
|
||||
.unwrap_or(false)
|
||||
fn format_file_change(change: &FileChange) -> &'static str {
|
||||
match change {
|
||||
FileChange::Add { .. } => "A",
|
||||
FileChange::Delete => "D",
|
||||
FileChange::Update {
|
||||
move_path: Some(_), ..
|
||||
} => "R",
|
||||
FileChange::Update {
|
||||
move_path: None, ..
|
||||
} => "M",
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "codex-repl"
|
||||
version = { workspace = true }
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[[bin]]
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use clap::ArgAction;
|
||||
use clap::Parser;
|
||||
use codex_core::ApprovalModeCliArg;
|
||||
use codex_core::SandboxPermissionOption;
|
||||
use codex_core::SandboxModeCliArg;
|
||||
use std::path::PathBuf;
|
||||
|
||||
/// Command‑line arguments.
|
||||
@@ -37,12 +37,11 @@ pub struct Cli {
|
||||
#[arg(long = "ask-for-approval", short = 'a')]
|
||||
pub approval_policy: Option<ApprovalModeCliArg>,
|
||||
|
||||
/// Convenience alias for low-friction sandboxed automatic execution (-a on-failure, network-disabled sandbox that can write to cwd and TMPDIR)
|
||||
#[arg(long = "full-auto", default_value_t = false)]
|
||||
pub full_auto: bool,
|
||||
|
||||
#[clap(flatten)]
|
||||
pub sandbox: SandboxPermissionOption,
|
||||
/// Configure the process restrictions when a command is executed.
|
||||
///
|
||||
/// Uses OS-specific sandboxing tools; Seatbelt on OSX, landlock+seccomp on Linux.
|
||||
#[arg(long = "sandbox", short = 's')]
|
||||
pub sandbox_policy: Option<SandboxModeCliArg>,
|
||||
|
||||
/// Allow running Codex outside a Git repository. By default the CLI
|
||||
/// aborts early when the current working directory is **not** inside a
|
||||
|
||||
@@ -6,9 +6,7 @@ use std::sync::Arc;
|
||||
use codex_core::config::Config;
|
||||
use codex_core::config::ConfigOverrides;
|
||||
use codex_core::protocol;
|
||||
use codex_core::protocol::AskForApproval;
|
||||
use codex_core::protocol::FileChange;
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use codex_core::util::is_inside_git_repo;
|
||||
use codex_core::util::notify_on_sigint;
|
||||
use codex_core::Codex;
|
||||
@@ -78,21 +76,11 @@ pub async fn run_main(cli: Cli) -> anyhow::Result<()> {
|
||||
// Initialize logging before any other work so early errors are captured.
|
||||
init_logger(cli.verbose, !cli.no_ansi);
|
||||
|
||||
let (sandbox_policy, approval_policy) = if cli.full_auto {
|
||||
(
|
||||
Some(SandboxPolicy::new_full_auto_policy()),
|
||||
Some(AskForApproval::OnFailure),
|
||||
)
|
||||
} else {
|
||||
let sandbox_policy = cli.sandbox.permissions.clone().map(Into::into);
|
||||
(sandbox_policy, cli.approval_policy.map(Into::into))
|
||||
};
|
||||
|
||||
// Load config file and apply CLI overrides (model & approval policy)
|
||||
let overrides = ConfigOverrides {
|
||||
model: cli.model.clone(),
|
||||
approval_policy,
|
||||
sandbox_policy,
|
||||
approval_policy: cli.approval_policy.map(Into::into),
|
||||
sandbox_policy: cli.sandbox_policy.map(Into::into),
|
||||
disable_response_storage: if cli.disable_response_storage {
|
||||
Some(true)
|
||||
} else {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use clap::Parser;
|
||||
use codex_core::ApprovalModeCliArg;
|
||||
use codex_core::SandboxPermissionOption;
|
||||
use codex_core::SandboxModeCliArg;
|
||||
use std::path::PathBuf;
|
||||
|
||||
#[derive(Parser, Debug)]
|
||||
@@ -21,12 +21,11 @@ pub struct Cli {
|
||||
#[arg(long = "ask-for-approval", short = 'a')]
|
||||
pub approval_policy: Option<ApprovalModeCliArg>,
|
||||
|
||||
/// Convenience alias for low-friction sandboxed automatic execution (-a on-failure, network-disabled sandbox that can write to cwd and TMPDIR)
|
||||
#[arg(long = "full-auto", default_value_t = false)]
|
||||
pub full_auto: bool,
|
||||
|
||||
#[clap(flatten)]
|
||||
pub sandbox: SandboxPermissionOption,
|
||||
/// Configure the process restrictions when a command is executed.
|
||||
///
|
||||
/// Uses OS-specific sandboxing tools; Seatbelt on OSX, landlock+seccomp on Linux.
|
||||
#[arg(long = "sandbox", short = 's')]
|
||||
pub sandbox_policy: Option<SandboxModeCliArg>,
|
||||
|
||||
/// Allow running Codex outside a Git repository.
|
||||
#[arg(long = "skip-git-repo-check", default_value_t = false)]
|
||||
@@ -35,4 +34,12 @@ pub struct Cli {
|
||||
/// Disable server‑side response storage (sends the full conversation context with every request)
|
||||
#[arg(long = "disable-response-storage", default_value_t = false)]
|
||||
pub disable_response_storage: bool,
|
||||
|
||||
/// Convenience alias for low-friction sandboxed automatic execution (-a on-failure, -s network-and-file-write-restricted)
|
||||
#[arg(long = "full-auto", default_value_t = true)]
|
||||
pub full_auto: bool,
|
||||
|
||||
/// Convenience alias for supervised sandboxed execution (-a unless-allow-listed, -s network-and-file-write-restricted)
|
||||
#[arg(long = "suggest", default_value_t = false)]
|
||||
pub suggest: bool,
|
||||
}
|
||||
|
||||
@@ -6,8 +6,6 @@
|
||||
use app::App;
|
||||
use codex_core::config::Config;
|
||||
use codex_core::config::ConfigOverrides;
|
||||
use codex_core::protocol::AskForApproval;
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use codex_core::util::is_inside_git_repo;
|
||||
use log_layer::TuiLogLayer;
|
||||
use std::fs::OpenOptions;
|
||||
@@ -35,22 +33,12 @@ pub use cli::Cli;
|
||||
pub fn run_main(cli: Cli) -> std::io::Result<()> {
|
||||
assert_env_var_set();
|
||||
|
||||
let (sandbox_policy, approval_policy) = if cli.full_auto {
|
||||
(
|
||||
Some(SandboxPolicy::new_full_auto_policy()),
|
||||
Some(AskForApproval::OnFailure),
|
||||
)
|
||||
} else {
|
||||
let sandbox_policy = cli.sandbox.permissions.clone().map(Into::into);
|
||||
(sandbox_policy, cli.approval_policy.map(Into::into))
|
||||
};
|
||||
|
||||
let config = {
|
||||
// Load configuration and support CLI overrides.
|
||||
let overrides = ConfigOverrides {
|
||||
model: cli.model.clone(),
|
||||
approval_policy,
|
||||
sandbox_policy,
|
||||
approval_policy: cli.approval_policy.map(Into::into),
|
||||
sandbox_policy: cli.sandbox_policy.map(Into::into),
|
||||
disable_response_storage: if cli.disable_response_storage {
|
||||
Some(true)
|
||||
} else {
|
||||
|
||||
@@ -1,152 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Automate the release procedure documented in `../README.md → Releasing codex`.
|
||||
|
||||
Run this script from the repository *root*:
|
||||
|
||||
```bash
|
||||
python release_codex.py
|
||||
```
|
||||
|
||||
It performs the same steps that the README lists manually:
|
||||
|
||||
1. Create and switch to a `bump-version-<timestamp>` branch.
|
||||
2. Bump the timestamp-based version in `codex-cli/package.json` **and**
|
||||
`codex-cli/src/utils/session.ts`.
|
||||
3. Commit with a DCO sign-off.
|
||||
4. Copy the top-level `README.md` into `codex-cli/` (npm consumers see it).
|
||||
5. Run `pnpm release` (copies README again, builds, publishes to npm).
|
||||
6. Push the branch so you can open a PR that merges the version bump.
|
||||
|
||||
The current directory can live anywhere; all paths are resolved relative to
|
||||
this file so moving it elsewhere (e.g. into `scripts/`) still works.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import datetime as _dt
|
||||
import json as _json
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import subprocess as _sp
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Paths
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# repo-root/
|
||||
# ├── codex-cli/
|
||||
# ├── scripts/ <-- you are here
|
||||
# └── README.md
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
CODEX_CLI = REPO_ROOT / "codex-cli"
|
||||
PKG_JSON = CODEX_CLI / "package.json"
|
||||
SESSION_TS = CODEX_CLI / "src" / "utils" / "session.ts"
|
||||
README_SRC = REPO_ROOT / "README.md"
|
||||
README_DST = CODEX_CLI / "README.md"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def sh(cmd: list[str] | str, *, cwd: Path | None = None) -> None:
|
||||
"""Run *cmd* printing it first and exit on non-zero status."""
|
||||
|
||||
if isinstance(cmd, list):
|
||||
printable = " ".join(cmd)
|
||||
else:
|
||||
printable = cmd
|
||||
|
||||
print("+", printable)
|
||||
|
||||
_sp.run(cmd, cwd=cwd, shell=isinstance(cmd, str), check=True)
|
||||
|
||||
|
||||
def _new_version() -> str:
|
||||
"""Return a new timestamp version string such as `0.1.2504301234`."""
|
||||
|
||||
return "0.1." + _dt.datetime.utcnow().strftime("%y%m%d%H%M")
|
||||
|
||||
|
||||
def bump_version() -> str:
|
||||
"""Update package.json and session.ts, returning the new version."""
|
||||
|
||||
new_ver = _new_version()
|
||||
|
||||
# ---- package.json
|
||||
data = _json.loads(PKG_JSON.read_text())
|
||||
old_ver = data.get("version", "<unknown>")
|
||||
data["version"] = new_ver
|
||||
PKG_JSON.write_text(_json.dumps(data, indent=2) + "\n")
|
||||
|
||||
# ---- session.ts
|
||||
pattern = r'CLI_VERSION = "0\\.1\\.\\d{10}"'
|
||||
repl = f'CLI_VERSION = "{new_ver}"'
|
||||
_text = SESSION_TS.read_text()
|
||||
if re.search(pattern, _text):
|
||||
SESSION_TS.write_text(re.sub(pattern, repl, _text))
|
||||
else:
|
||||
print(
|
||||
"WARNING: CLI_VERSION constant not found – file format may have changed",
|
||||
file=sys.stderr,
|
||||
)
|
||||
|
||||
print(f"Version bump: {old_ver} → {new_ver}")
|
||||
return new_ver
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def main() -> None: # noqa: C901 – readable top-level flow is desired
|
||||
# Ensure we can locate required files.
|
||||
for p in (CODEX_CLI, PKG_JSON, SESSION_TS, README_SRC):
|
||||
if not p.exists():
|
||||
sys.exit(f"Required path missing: {p.relative_to(REPO_ROOT)}")
|
||||
|
||||
os.chdir(REPO_ROOT)
|
||||
|
||||
# ------------------------------- create release branch
|
||||
branch = "bump-version-" + _dt.datetime.utcnow().strftime("%Y%m%d-%H%M")
|
||||
sh(["git", "checkout", "-b", branch])
|
||||
|
||||
# ------------------------------- bump version + commit
|
||||
new_ver = bump_version()
|
||||
sh(
|
||||
[
|
||||
"git",
|
||||
"add",
|
||||
str(PKG_JSON.relative_to(REPO_ROOT)),
|
||||
str(SESSION_TS.relative_to(REPO_ROOT)),
|
||||
]
|
||||
)
|
||||
sh(["git", "commit", "-s", "-m", f"chore(release): codex-cli v{new_ver}"])
|
||||
|
||||
# ------------------------------- copy README (shown on npmjs.com)
|
||||
shutil.copyfile(README_SRC, README_DST)
|
||||
|
||||
# ------------------------------- build + publish via pnpm script
|
||||
sh(["pnpm", "install"], cwd=CODEX_CLI)
|
||||
sh(["pnpm", "release"], cwd=CODEX_CLI)
|
||||
|
||||
# ------------------------------- push branch
|
||||
sh(["git", "push", "-u", "origin", branch])
|
||||
|
||||
print("\n✅ Release script finished!")
|
||||
print(f" • npm publish run by pnpm script (branch: {branch})")
|
||||
print(" • Open a PR to merge the version bump once CI passes.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
main()
|
||||
except KeyboardInterrupt:
|
||||
sys.exit("\nCancelled by user")
|
||||
Reference in New Issue
Block a user