Compare commits

..

3 Commits

Author SHA1 Message Date
zhao-oai
b81cb7ceb3 Fix sandbox detection for user shell commands (#6094) 2025-11-01 17:27:03 -04:00
kevin zhao
c7a3428986 fix 2025-10-31 17:27:35 -04:00
kevin zhao
d609dfa2fc escalating permissions 2025-10-31 17:15:50 -04:00
487 changed files with 36834 additions and 42675 deletions

View File

@@ -1,3 +1,3 @@
model = "gpt-5.1"
model = "gpt-5"
# Consider setting [mcp_servers] here!

View File

@@ -4,5 +4,3 @@ Before opening this Pull Request, please read the dedicated "Contributing" markd
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.

View File

@@ -46,7 +46,7 @@ jobs:
echo "pack_output=$PACK_OUTPUT" >> "$GITHUB_OUTPUT"
- name: Upload staged npm package artifact
uses: actions/upload-artifact@v5
uses: actions/upload-artifact@v4
with:
name: codex-npm-staging
path: ${{ steps.stage_npm_package.outputs.pack_output }}

View File

@@ -13,39 +13,17 @@ permissions:
jobs:
cla:
# Only run the CLA assistant for the canonical openai repo so forks are not blocked
# and contributors who signed previously do not receive duplicate CLA notifications.
if: ${{ github.repository_owner == 'openai' }}
runs-on: ubuntu-latest
steps:
- uses: contributor-assistant/github-action@v2.6.1
# Run on close only if the PR was merged. This will lock the PR to preserve
# the CLA agreement. We don't want to lock PRs that have been closed without
# merging because the contributor may want to respond with additional comments.
# This action has a "lock-pullrequest-aftermerge" option that can be set to false,
# but that would unconditionally skip locking even in cases where the PR was merged.
if: |
(
github.event_name == 'pull_request_target' &&
(
github.event.action == 'opened' ||
github.event.action == 'synchronize' ||
(github.event.action == 'closed' && github.event.pull_request.merged == true)
)
) ||
(
github.event_name == 'issue_comment' &&
(
github.event.comment.body == 'recheck' ||
github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA'
)
)
github.event_name == 'pull_request_target' ||
github.event.comment.body == 'recheck' ||
github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA'
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
path-to-document: https://github.com/openai/codex/blob/main/docs/CLA.md
path-to-signatures: signatures/cla.json
branch: cla-signatures
allowlist: |
codex
dependabot[bot]
allowlist: dependabot[bot]

View File

@@ -1,105 +0,0 @@
name: Close stale contributor PRs
on:
workflow_dispatch:
schedule:
- cron: "0 6 * * *"
permissions:
contents: read
issues: write
pull-requests: write
jobs:
close-stale-contributor-prs:
runs-on: ubuntu-latest
steps:
- name: Close inactive PRs from contributors
uses: actions/github-script@v8
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |
const DAYS_INACTIVE = 14;
const cutoff = new Date(Date.now() - DAYS_INACTIVE * 24 * 60 * 60 * 1000);
const { owner, repo } = context.repo;
const dryRun = false;
const stalePrs = [];
core.info(`Dry run mode: ${dryRun}`);
const prs = await github.paginate(github.rest.pulls.list, {
owner,
repo,
state: "open",
per_page: 100,
sort: "updated",
direction: "asc",
});
for (const pr of prs) {
const lastUpdated = new Date(pr.updated_at);
if (lastUpdated > cutoff) {
core.info(`PR ${pr.number} is fresh`);
continue;
}
if (!pr.user || pr.user.type !== "User") {
core.info(`PR ${pr.number} wasn't created by a user`);
continue;
}
let permission;
try {
const permissionResponse = await github.rest.repos.getCollaboratorPermissionLevel({
owner,
repo,
username: pr.user.login,
});
permission = permissionResponse.data.permission;
} catch (error) {
if (error.status === 404) {
core.info(`Author ${pr.user.login} is not a collaborator; skipping #${pr.number}`);
continue;
}
throw error;
}
const hasContributorAccess = ["admin", "maintain", "write"].includes(permission);
if (!hasContributorAccess) {
core.info(`Author ${pr.user.login} has ${permission} access; skipping #${pr.number}`);
continue;
}
stalePrs.push(pr);
}
if (!stalePrs.length) {
core.info("No stale contributor pull requests found.");
return;
}
for (const pr of stalePrs) {
const issue_number = pr.number;
const closeComment = `Closing this pull request because it has had no updates for more than ${DAYS_INACTIVE} days. If you plan to continue working on it, feel free to reopen or open a new PR.`;
if (dryRun) {
core.info(`[dry-run] Would close contributor PR #${issue_number} from ${pr.user.login}`);
continue;
}
await github.rest.issues.createComment({
owner,
repo,
issue_number,
body: closeComment,
});
await github.rest.pulls.update({
owner,
repo,
pull_number: issue_number,
state: "closed",
});
core.info(`Closed contributor PR #${issue_number} from ${pr.user.login}`);
}

View File

@@ -22,6 +22,6 @@ jobs:
- name: Annotate locations with typos
uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
- name: Codespell
uses: codespell-project/actions-codespell@8f01853be192eb0f849a5c7d721450e7a467c579 # v2.2
uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2.1
with:
ignore_words_file: .codespellignore

View File

@@ -46,6 +46,7 @@ jobs:
with:
openai-api-key: ${{ secrets.CODEX_OPENAI_API_KEY }}
allow-users: "*"
model: gpt-5
prompt: |
You are an assistant that triages new GitHub issues by identifying potential duplicates.

View File

@@ -26,36 +26,21 @@ jobs:
prompt: |
You are an assistant that reviews GitHub issues for the repository.
Your job is to choose the most appropriate labels for the issue described later in this prompt.
Your job is to choose the most appropriate existing labels for the issue described later in this prompt.
Follow these rules:
- Only pick labels out of the list below.
- Prefer a small set of precise labels over many broad ones.
- Add one (and only one) of the following three labels to distinguish the type of issue. Default to "bug" if unsure.
Labels to apply:
1. bug — Reproducible defects in Codex products (CLI, VS Code extension, web, auth).
2. enhancement — Feature requests or usability improvements that ask for new capabilities, better ergonomics, or quality-of-life tweaks.
3. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
- If applicable, add one of the following labels to specify which sub-product or product surface the issue relates to.
1. CLI — the Codex command line interface.
2. extension — VS Code (or other IDE) extension-specific issues.
3. codex-web — Issues targeting the Codex web UI/Cloud experience.
4. github-actionIssues with the Codex GitHub action.
5. iOS — Issues with the Codex iOS app.
- Additionally add zero or more of the following labels that are relevant to the issue content. Prefer a small set of precise labels over many broad ones.
1. windows-os — Bugs or friction specific to Windows environments (always when PowerShell is mentioned, path handling, copy/paste, OS-specific auth or tooling failures).
2. mcp — Topics involving Model Context Protocol servers/clients.
3. mcp-server — Problems related to the codex mcp-server command, where codex runs as an MCP server.
4. azure — Problems or requests tied to Azure OpenAI deployments.
5. model-behavior — Undesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
6. code-review — Issues related to the code review feature or functionality.
7. auth - Problems related to authentication, login, or access tokens.
8. codex-exec - Problems related to the "codex exec" command or functionality.
9. context-management - Problems related to compaction, context windows, or available context reporting.
10. custom-model - Problems that involve using custom model providers, local models, or OSS models.
11. rate-limits - Problems related to token limits, rate limits, or token usage reporting.
12. sandbox - Issues related to local sandbox environments or tool call approvals to override sandbox restrictions.
13. tool-calls - Problems related to specific tool call invocations including unexpected errors, failures, or hangs.
14. TUI - Problems with the terminal user interface (TUI) including keyboard shortcuts, copy & pasting, menus, or screen update issues.
3. extension — VS Code (or other IDE) extension-specific issues.
4. windows-os — Bugs or friction specific to Windows environments (always when PowerShell is mentioned, path handling, copy/paste, OS-specific auth or tooling failures).
5. mcp — Topics involving Model Context Protocol servers/clients.
6. codex-web — Issues targeting the Codex web UI/Cloud experience.
8. azure — Problems or requests tied to Azure OpenAI deployments.
9. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
10. model-behaviorUndesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
Issue number: ${{ github.event.issue.number }}

View File

@@ -76,7 +76,7 @@ jobs:
steps:
- uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
- uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
- uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: cargo-shear
version: 1.5.1
@@ -95,8 +95,8 @@ jobs:
run:
working-directory: codex-rs
env:
# Speed up repeated builds across CI runs by caching compiled objects (non-Windows).
USE_SCCACHE: ${{ startsWith(matrix.runner, 'windows') && 'false' || 'true' }}
# Speed up repeated builds across CI runs by caching compiled objects.
RUSTC_WRAPPER: sccache
CARGO_INCREMENTAL: "0"
SCCACHE_CACHE_SIZE: 10G
@@ -170,14 +170,12 @@ jobs:
# Install and restore sccache cache
- name: Install sccache
if: ${{ env.USE_SCCACHE == 'true' }}
uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: sccache
version: 0.7.5
- name: Configure sccache backend
if: ${{ env.USE_SCCACHE == 'true' }}
shell: bash
run: |
set -euo pipefail
@@ -190,13 +188,8 @@ jobs:
echo "Using sccache local disk + actions/cache fallback"
fi
- name: Enable sccache wrapper
if: ${{ env.USE_SCCACHE == 'true' }}
shell: bash
run: echo "RUSTC_WRAPPER=sccache" >> "$GITHUB_ENV"
- name: Restore sccache cache (fallback)
if: ${{ env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true' }}
if: ${{ env.SCCACHE_GHA_ENABLED != 'true' }}
id: cache_sccache_restore
uses: actions/cache/restore@v4
with:
@@ -235,7 +228,7 @@ jobs:
- name: Install cargo-chef
if: ${{ matrix.profile == 'release' }}
uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: cargo-chef
version: 0.1.71
@@ -281,7 +274,7 @@ jobs:
key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
- name: Save sccache cache (fallback)
if: always() && !cancelled() && env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true'
if: always() && !cancelled() && env.SCCACHE_GHA_ENABLED != 'true'
continue-on-error: true
uses: actions/cache/save@v4
with:
@@ -289,12 +282,12 @@ jobs:
key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
- name: sccache stats
if: always() && env.USE_SCCACHE == 'true'
if: always()
continue-on-error: true
run: sccache --show-stats || true
- name: sccache summary
if: always() && env.USE_SCCACHE == 'true'
if: always()
shell: bash
run: |
{
@@ -333,8 +326,7 @@ jobs:
run:
working-directory: codex-rs
env:
# Speed up repeated builds across CI runs by caching compiled objects (non-Windows).
USE_SCCACHE: ${{ startsWith(matrix.runner, 'windows') && 'false' || 'true' }}
RUSTC_WRAPPER: sccache
CARGO_INCREMENTAL: "0"
SCCACHE_CACHE_SIZE: 10G
@@ -378,14 +370,12 @@ jobs:
cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
- name: Install sccache
if: ${{ env.USE_SCCACHE == 'true' }}
uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: sccache
version: 0.7.5
- name: Configure sccache backend
if: ${{ env.USE_SCCACHE == 'true' }}
shell: bash
run: |
set -euo pipefail
@@ -398,13 +388,8 @@ jobs:
echo "Using sccache local disk + actions/cache fallback"
fi
- name: Enable sccache wrapper
if: ${{ env.USE_SCCACHE == 'true' }}
shell: bash
run: echo "RUSTC_WRAPPER=sccache" >> "$GITHUB_ENV"
- name: Restore sccache cache (fallback)
if: ${{ env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true' }}
if: ${{ env.SCCACHE_GHA_ENABLED != 'true' }}
id: cache_sccache_restore
uses: actions/cache/restore@v4
with:
@@ -414,17 +399,17 @@ jobs:
sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-
sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
- uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
- uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
with:
tool: nextest
version: 0.9.103
- name: tests
id: test
continue-on-error: true
run: cargo nextest run --all-features --no-fail-fast --target ${{ matrix.target }} --cargo-profile ci-test
env:
RUST_BACKTRACE: 1
NEXTEST_STATUS_LEVEL: leak
- name: Save cargo home cache
if: always() && !cancelled() && steps.cache_cargo_home_restore.outputs.cache-hit != 'true'
@@ -439,7 +424,7 @@ jobs:
key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
- name: Save sccache cache (fallback)
if: always() && !cancelled() && env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true'
if: always() && !cancelled() && env.SCCACHE_GHA_ENABLED != 'true'
continue-on-error: true
uses: actions/cache/save@v4
with:
@@ -447,12 +432,12 @@ jobs:
key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
- name: sccache stats
if: always() && env.USE_SCCACHE == 'true'
if: always()
continue-on-error: true
run: sccache --show-stats || true
- name: sccache summary
if: always() && env.USE_SCCACHE == 'true'
if: always()
shell: bash
run: |
{

View File

@@ -295,15 +295,6 @@ jobs:
# ${{ matrix.target }}
dest="dist/${{ matrix.target }}"
# We want to ship the raw Windows executables in the GitHub Release
# in addition to the compressed archives. Keep the originals for
# Windows targets; remove them elsewhere to limit the number of
# artifacts that end up in the GitHub Release.
keep_originals=false
if [[ "${{ matrix.runner }}" == windows* ]]; then
keep_originals=true
fi
# For compatibility with environments that lack the `zstd` tool we
# additionally create a `.tar.gz` for all platforms and `.zip` for
# Windows alongside every single binary that we publish. The end result is:
@@ -333,11 +324,7 @@ jobs:
# Also create .zst (existing behaviour) *and* remove the original
# uncompressed binary to keep the directory small.
zstd_args=(-T0 -19)
if [[ "${keep_originals}" == false ]]; then
zstd_args+=(--rm)
fi
zstd "${zstd_args[@]}" "$dest/$base"
zstd -T0 -19 --rm "$dest/$base"
done
- name: Remove signing keychain
@@ -363,7 +350,7 @@ jobs:
fi
fi
- uses: actions/upload-artifact@v5
- uses: actions/upload-artifact@v4
with:
name: ${{ matrix.target }}
# Upload the per-binary .zst files as well as the new .tar.gz
@@ -371,20 +358,8 @@ jobs:
path: |
codex-rs/dist/${{ matrix.target }}/*
shell-tool-mcp:
name: shell-tool-mcp
needs: tag-check
uses: ./.github/workflows/shell-tool-mcp.yml
with:
release-tag: ${{ github.ref_name }}
# We are not ready to publish yet.
publish: false
secrets: inherit
release:
needs:
- build
- shell-tool-mcp
needs: build
name: release
runs-on: ubuntu-latest
permissions:
@@ -407,14 +382,6 @@ jobs:
- name: List
run: ls -R dist/
# This is a temporary fix: we should modify shell-tool-mcp.yml so these
# files do not end up in dist/ in the first place.
- name: Delete entries from dist/ that should not go in the release
run: |
rm -rf dist/shell-tool-mcp*
ls -R dist/
- name: Define release name
id: release_name
run: |

View File

@@ -1,48 +0,0 @@
name: shell-tool-mcp CI
on:
push:
paths:
- "shell-tool-mcp/**"
- ".github/workflows/shell-tool-mcp-ci.yml"
- "pnpm-lock.yaml"
- "pnpm-workspace.yaml"
pull_request:
paths:
- "shell-tool-mcp/**"
- ".github/workflows/shell-tool-mcp-ci.yml"
- "pnpm-lock.yaml"
- "pnpm-workspace.yaml"
env:
NODE_VERSION: 22
jobs:
test:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v5
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
run_install: false
- name: Setup Node.js
uses: actions/setup-node@v5
with:
node-version: ${{ env.NODE_VERSION }}
cache: "pnpm"
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Format check
run: pnpm --filter @openai/codex-shell-tool-mcp run format
- name: Run tests
run: pnpm --filter @openai/codex-shell-tool-mcp test
- name: Build
run: pnpm --filter @openai/codex-shell-tool-mcp run build

View File

@@ -1,412 +0,0 @@
name: shell-tool-mcp
on:
workflow_call:
inputs:
release-version:
description: Version to publish (x.y.z or x.y.z-alpha.N). Defaults to GITHUB_REF_NAME when it starts with rust-v.
required: false
type: string
release-tag:
description: Tag name to use when downloading release artifacts (defaults to rust-v<version>).
required: false
type: string
publish:
description: Whether to publish to npm when the version is releasable.
required: false
default: true
type: boolean
env:
NODE_VERSION: 22
jobs:
metadata:
runs-on: ubuntu-latest
outputs:
version: ${{ steps.compute.outputs.version }}
release_tag: ${{ steps.compute.outputs.release_tag }}
should_publish: ${{ steps.compute.outputs.should_publish }}
npm_tag: ${{ steps.compute.outputs.npm_tag }}
steps:
- name: Compute version and tags
id: compute
run: |
set -euo pipefail
version="${{ inputs.release-version }}"
release_tag="${{ inputs.release-tag }}"
if [[ -z "$version" ]]; then
if [[ -n "$release_tag" && "$release_tag" =~ ^rust-v.+ ]]; then
version="${release_tag#rust-v}"
elif [[ "${GITHUB_REF_NAME:-}" =~ ^rust-v.+ ]]; then
version="${GITHUB_REF_NAME#rust-v}"
release_tag="${GITHUB_REF_NAME}"
else
echo "release-version is required when GITHUB_REF_NAME is not a rust-v tag."
exit 1
fi
fi
if [[ -z "$release_tag" ]]; then
release_tag="rust-v${version}"
fi
npm_tag=""
should_publish="false"
if [[ "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
should_publish="true"
elif [[ "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+-alpha\.[0-9]+$ ]]; then
should_publish="true"
npm_tag="alpha"
fi
echo "version=${version}" >> "$GITHUB_OUTPUT"
echo "release_tag=${release_tag}" >> "$GITHUB_OUTPUT"
echo "npm_tag=${npm_tag}" >> "$GITHUB_OUTPUT"
echo "should_publish=${should_publish}" >> "$GITHUB_OUTPUT"
rust-binaries:
name: Build Rust - ${{ matrix.target }}
needs: metadata
runs-on: ${{ matrix.runner }}
timeout-minutes: 30
defaults:
run:
working-directory: codex-rs
strategy:
fail-fast: false
matrix:
include:
- runner: macos-15-xlarge
target: aarch64-apple-darwin
- runner: macos-15-xlarge
target: x86_64-apple-darwin
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
install_musl: true
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
install_musl: true
steps:
- name: Checkout repository
uses: actions/checkout@v5
- uses: dtolnay/rust-toolchain@1.90
with:
targets: ${{ matrix.target }}
- if: ${{ matrix.install_musl }}
name: Install musl build dependencies
run: |
sudo apt-get update
sudo apt-get install -y musl-tools pkg-config
- name: Build exec server binaries
run: cargo build --release --target ${{ matrix.target }} --bin codex-exec-mcp-server --bin codex-execve-wrapper
- name: Stage exec server binaries
run: |
dest="${GITHUB_WORKSPACE}/artifacts/vendor/${{ matrix.target }}"
mkdir -p "$dest"
cp "target/${{ matrix.target }}/release/codex-exec-mcp-server" "$dest/"
cp "target/${{ matrix.target }}/release/codex-execve-wrapper" "$dest/"
- uses: actions/upload-artifact@v4
with:
name: shell-tool-mcp-rust-${{ matrix.target }}
path: artifacts/**
if-no-files-found: error
bash-linux:
name: Build Bash (Linux) - ${{ matrix.variant }} - ${{ matrix.target }}
needs: metadata
runs-on: ${{ matrix.runner }}
timeout-minutes: 30
container:
image: ${{ matrix.image }}
strategy:
fail-fast: false
matrix:
include:
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
variant: ubuntu-24.04
image: ubuntu:24.04
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
variant: ubuntu-22.04
image: ubuntu:22.04
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
variant: ubuntu-20.04
image: ubuntu:20.04
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
variant: debian-12
image: debian:12
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
variant: debian-11
image: debian:11
- runner: ubuntu-24.04
target: x86_64-unknown-linux-musl
variant: centos-9
image: quay.io/centos/centos:stream9
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
variant: ubuntu-24.04
image: arm64v8/ubuntu:24.04
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
variant: ubuntu-22.04
image: arm64v8/ubuntu:22.04
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
variant: ubuntu-20.04
image: arm64v8/ubuntu:20.04
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
variant: debian-12
image: arm64v8/debian:12
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
variant: debian-11
image: arm64v8/debian:11
- runner: ubuntu-24.04-arm
target: aarch64-unknown-linux-musl
variant: centos-9
image: quay.io/centos/centos:stream9
steps:
- name: Install build prerequisites
shell: bash
run: |
set -euo pipefail
if command -v apt-get >/dev/null 2>&1; then
apt-get update
DEBIAN_FRONTEND=noninteractive apt-get install -y git build-essential bison autoconf gettext
elif command -v dnf >/dev/null 2>&1; then
dnf install -y git gcc gcc-c++ make bison autoconf gettext
elif command -v yum >/dev/null 2>&1; then
yum install -y git gcc gcc-c++ make bison autoconf gettext
else
echo "Unsupported package manager in container"
exit 1
fi
- name: Checkout repository
uses: actions/checkout@v5
- name: Build patched Bash
shell: bash
run: |
set -euo pipefail
git clone --depth 1 https://github.com/bminor/bash /tmp/bash
cd /tmp/bash
git fetch --depth 1 origin a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
git apply "${GITHUB_WORKSPACE}/shell-tool-mcp/patches/bash-exec-wrapper.patch"
./configure --without-bash-malloc
cores="$(command -v nproc >/dev/null 2>&1 && nproc || getconf _NPROCESSORS_ONLN)"
make -j"${cores}"
dest="${GITHUB_WORKSPACE}/artifacts/vendor/${{ matrix.target }}/bash/${{ matrix.variant }}"
mkdir -p "$dest"
cp bash "$dest/bash"
- uses: actions/upload-artifact@v4
with:
name: shell-tool-mcp-bash-${{ matrix.target }}-${{ matrix.variant }}
path: artifacts/**
if-no-files-found: error
bash-darwin:
name: Build Bash (macOS) - ${{ matrix.variant }} - ${{ matrix.target }}
needs: metadata
runs-on: ${{ matrix.runner }}
timeout-minutes: 30
strategy:
fail-fast: false
matrix:
include:
- runner: macos-15-xlarge
target: aarch64-apple-darwin
variant: macos-15
- runner: macos-14
target: aarch64-apple-darwin
variant: macos-14
- runner: macos-13
target: x86_64-apple-darwin
variant: macos-13
steps:
- name: Checkout repository
uses: actions/checkout@v5
- name: Build patched Bash
shell: bash
run: |
set -euo pipefail
git clone --depth 1 https://github.com/bminor/bash /tmp/bash
cd /tmp/bash
git fetch --depth 1 origin a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
git apply "${GITHUB_WORKSPACE}/shell-tool-mcp/patches/bash-exec-wrapper.patch"
./configure --without-bash-malloc
cores="$(getconf _NPROCESSORS_ONLN)"
make -j"${cores}"
dest="${GITHUB_WORKSPACE}/artifacts/vendor/${{ matrix.target }}/bash/${{ matrix.variant }}"
mkdir -p "$dest"
cp bash "$dest/bash"
- uses: actions/upload-artifact@v4
with:
name: shell-tool-mcp-bash-${{ matrix.target }}-${{ matrix.variant }}
path: artifacts/**
if-no-files-found: error
package:
name: Package npm module
needs:
- metadata
- rust-binaries
- bash-linux
- bash-darwin
runs-on: ubuntu-latest
env:
PACKAGE_VERSION: ${{ needs.metadata.outputs.version }}
steps:
- name: Checkout repository
uses: actions/checkout@v5
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
version: 10.8.1
run_install: false
- name: Setup Node.js
uses: actions/setup-node@v5
with:
node-version: ${{ env.NODE_VERSION }}
- name: Install JavaScript dependencies
run: pnpm install --frozen-lockfile
- name: Build (shell-tool-mcp)
run: pnpm --filter @openai/codex-shell-tool-mcp run build
- name: Download build artifacts
uses: actions/download-artifact@v4
with:
path: artifacts
- name: Assemble staging directory
id: staging
shell: bash
run: |
set -euo pipefail
staging="${STAGING_DIR}"
mkdir -p "$staging" "$staging/vendor"
cp shell-tool-mcp/README.md "$staging/"
cp shell-tool-mcp/package.json "$staging/"
cp -R shell-tool-mcp/bin "$staging/"
found_vendor="false"
shopt -s nullglob
for vendor_dir in artifacts/*/vendor; do
rsync -av "$vendor_dir/" "$staging/vendor/"
found_vendor="true"
done
if [[ "$found_vendor" == "false" ]]; then
echo "No vendor payloads were downloaded."
exit 1
fi
node - <<'NODE'
import fs from "node:fs";
import path from "node:path";
const stagingDir = process.env.STAGING_DIR;
const version = process.env.PACKAGE_VERSION;
const pkgPath = path.join(stagingDir, "package.json");
const pkg = JSON.parse(fs.readFileSync(pkgPath, "utf8"));
pkg.version = version;
fs.writeFileSync(pkgPath, JSON.stringify(pkg, null, 2) + "\n");
NODE
echo "dir=$staging" >> "$GITHUB_OUTPUT"
env:
STAGING_DIR: ${{ runner.temp }}/shell-tool-mcp
- name: Ensure binaries are executable
run: |
set -euo pipefail
staging="${{ steps.staging.outputs.dir }}"
chmod +x \
"$staging"/vendor/*/codex-exec-mcp-server \
"$staging"/vendor/*/codex-execve-wrapper \
"$staging"/vendor/*/bash/*/bash
- name: Create npm tarball
shell: bash
run: |
set -euo pipefail
mkdir -p dist/npm
staging="${{ steps.staging.outputs.dir }}"
pack_info=$(cd "$staging" && npm pack --ignore-scripts --json --pack-destination "${GITHUB_WORKSPACE}/dist/npm")
filename=$(PACK_INFO="$pack_info" node -e 'const data = JSON.parse(process.env.PACK_INFO); console.log(data[0].filename);')
mv "dist/npm/${filename}" "dist/npm/codex-shell-tool-mcp-npm-${PACKAGE_VERSION}.tgz"
- uses: actions/upload-artifact@v4
with:
name: codex-shell-tool-mcp-npm
path: dist/npm/codex-shell-tool-mcp-npm-${{ env.PACKAGE_VERSION }}.tgz
if-no-files-found: error
publish:
name: Publish npm package
needs:
- metadata
- package
if: ${{ inputs.publish && needs.metadata.outputs.should_publish == 'true' }}
runs-on: ubuntu-latest
permissions:
id-token: write
contents: read
steps:
- name: Setup pnpm
uses: pnpm/action-setup@v4
with:
version: 10.8.1
run_install: false
- name: Setup Node.js
uses: actions/setup-node@v5
with:
node-version: ${{ env.NODE_VERSION }}
registry-url: https://registry.npmjs.org
scope: "@openai"
- name: Update npm
run: npm install -g npm@latest
- name: Download npm tarball
uses: actions/download-artifact@v4
with:
name: codex-shell-tool-mcp-npm
path: dist/npm
- name: Publish to npm
env:
NPM_TAG: ${{ needs.metadata.outputs.npm_tag }}
VERSION: ${{ needs.metadata.outputs.version }}
shell: bash
run: |
set -euo pipefail
tag_args=()
if [[ -n "${NPM_TAG}" ]]; then
tag_args+=(--tag "${NPM_TAG}")
fi
npm publish "dist/npm/codex-shell-tool-mcp-npm-${VERSION}.tgz" "${tag_args[@]}"

3
.gitignore vendored
View File

@@ -64,9 +64,6 @@ apply_patch/
# coverage
coverage/
# personal files
personal/
# os
.DS_Store
Thumbs.db

View File

@@ -84,8 +84,6 @@ If you dont have the tool:
- Use `ResponseMock::single_request()` when a test should only issue one POST, or `ResponseMock::requests()` to inspect every captured `ResponsesRequest`.
- `ResponsesRequest` exposes helpers (`body_json`, `input`, `function_call_output`, `custom_tool_call_output`, `call_output`, `header`, `path`, `query_param`) so assertions can target structured payloads instead of manual JSON digging.
- Build SSE payloads with the provided `ev_*` constructors and the `sse(...)`.
- Prefer `wait_for_event` over `wait_for_event_with_timeout`.
- Prefer `mount_sse_once` over `mount_sse_once_match` or `mount_sse_sequence`
- Typical pattern:

View File

@@ -69,50 +69,17 @@ Codex can access MCP servers. To configure them, refer to the [config docs](./do
Codex CLI supports a rich set of configuration options, with preferences stored in `~/.codex/config.toml`. For full configuration options, see [Configuration](./docs/config.md).
### Execpolicy Quickstart
Codex can enforce your own rules-based execution policy before it runs shell commands.
1. Create a policy directory: `mkdir -p ~/.codex/policy`.
2. Create one or more `.codexpolicy` files in that folder. Codex automatically loads every `.codexpolicy` file in there on startup.
3. Write `prefix_rule` entries to describe the commands you want to allow, prompt, or block:
```starlark
prefix_rule(
pattern = ["git", ["push", "fetch"]],
decision = "prompt", # allow | prompt | forbidden
match = [["git", "push", "origin", "main"]], # examples that must match
not_match = [["git", "status"]], # examples that must not match
)
```
- `pattern` is a list of shell tokens, evaluated from left to right; wrap tokens in a nested list to express alternatives (e.g., match both `push` and `fetch`).
- `decision` sets the severity; Codex picks the strictest decision when multiple rules match (forbidden > prompt > allow).
- `match` and `not_match` act as (optional) unit tests. Codex validates them when it loads your policy, so you get feedback if an example has unexpected behavior.
In this example rule, if Codex wants to run commands with the prefix `git push` or `git fetch`, it will first ask for user approval.
Use the `codex execpolicy check` subcommand to preview decisions before you save a rule (see the [`codex-execpolicy` README](./codex-rs/execpolicy/README.md) for syntax details):
```shell
codex execpolicy check --policy ~/.codex/policy/default.codexpolicy git push origin main
```
Pass multiple `--policy` flags to test how several files combine, and use `--pretty` for formatted JSON output. See the [`codex-rs/execpolicy` README](./codex-rs/execpolicy/README.md) for a more detailed walkthrough of the available syntax.
## Note: `execpolicy` commands are still in preview. The API may have breaking changes in the future.
---
### Docs & FAQ
- [**Getting started**](./docs/getting-started.md)
- [CLI usage](./docs/getting-started.md#cli-usage)
- [Slash Commands](./docs/slash_commands.md)
- [Running with a prompt as input](./docs/getting-started.md#running-with-a-prompt-as-input)
- [Example prompts](./docs/getting-started.md#example-prompts)
- [Custom prompts](./docs/prompts.md)
- [Memory with AGENTS.md](./docs/getting-started.md#memory-with-agentsmd)
- [**Configuration**](./docs/config.md)
- [Example config](./docs/example-config.md)
- [**Sandbox & approvals**](./docs/sandbox.md)
- [**Authentication**](./docs/authentication.md)
- [Auth methods](./docs/authentication.md#forcing-a-specific-auth-method-advanced)

View File

@@ -1,13 +0,0 @@
[profile.default]
# Do not increase, fix your test instead
slow-timeout = { period = "15s", terminate-after = 2 }
[[profile.default.overrides]]
# Do not add new tests here
filter = 'test(rmcp_client) | test(humanlike_typing_1000_chars_appears_live_no_placeholder)'
slow-timeout = { period = "1m", terminate-after = 4 }
[[profile.default.overrides]]
filter = 'test(approval_matrix_covers_all_modes)'
slow-timeout = { period = "30s", terminate-after = 2 }

415
codex-rs/Cargo.lock generated
View File

@@ -186,13 +186,9 @@ dependencies = [
"chrono",
"codex-app-server-protocol",
"codex-core",
"codex-protocol",
"core_test_support",
"serde",
"serde_json",
"shlex",
"tokio",
"uuid",
"wiremock",
]
@@ -213,7 +209,6 @@ dependencies = [
"parking_lot",
"percent-encoding",
"windows-sys 0.59.0",
"wl-clipboard-rs",
"x11rb",
]
@@ -240,44 +235,46 @@ dependencies = [
[[package]]
name = "askama"
version = "0.14.0"
version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f75363874b771be265f4ffe307ca705ef6f3baa19011c149da8674a87f1b75c4"
checksum = "b79091df18a97caea757e28cd2d5fda49c6cd4bd01ddffd7ff01ace0c0ad2c28"
dependencies = [
"askama_derive",
"itoa",
"askama_escape",
"humansize",
"num-traits",
"percent-encoding",
"serde",
"serde_json",
]
[[package]]
name = "askama_derive"
version = "0.14.0"
version = "0.12.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "129397200fe83088e8a68407a8e2b1f826cf0086b21ccdb866a722c8bcd3a94f"
checksum = "19fe8d6cb13c4714962c072ea496f3392015f0989b1a2847bb4b2d9effd71d83"
dependencies = [
"askama_parser",
"basic-toml",
"memchr",
"mime",
"mime_guess",
"proc-macro2",
"quote",
"rustc-hash",
"serde",
"serde_derive",
"syn 2.0.104",
]
[[package]]
name = "askama_parser"
version = "0.14.0"
name = "askama_escape"
version = "0.10.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d6ab5630b3d5eaf232620167977f95eb51f3432fc76852328774afbd242d4358"
checksum = "619743e34b5ba4e9703bba34deac3427c72507c7159f5fd030aea8cac0cfe341"
[[package]]
name = "askama_parser"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "acb1161c6b64d1c3d83108213c2a2533a342ac225aabd0bda218278c2ddb00c0"
dependencies = [
"memchr",
"serde",
"serde_derive",
"winnow",
"nom",
]
[[package]]
@@ -728,17 +725,6 @@ version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
[[package]]
name = "chardetng"
version = "0.1.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "14b8f0b65b7b08ae3c8187e8d77174de20cb6777864c6b832d8ad365999cf1ea"
dependencies = [
"cfg-if",
"encoding_rs",
"memchr",
]
[[package]]
name = "chrono"
version = "0.4.42"
@@ -863,14 +849,12 @@ dependencies = [
"codex-protocol",
"codex-utils-json-to-toml",
"core_test_support",
"mcp-types",
"opentelemetry-appender-tracing",
"os_info",
"pretty_assertions",
"serde",
"serde_json",
"serial_test",
"shlex",
"tempfile",
"tokio",
"toml",
@@ -887,30 +871,16 @@ dependencies = [
"anyhow",
"clap",
"codex-protocol",
"mcp-types",
"paste",
"pretty_assertions",
"schemars 0.8.22",
"serde",
"serde_json",
"strum_macros 0.27.2",
"thiserror 2.0.17",
"ts-rs",
"uuid",
]
[[package]]
name = "codex-app-server-test-client"
version = "0.0.0"
dependencies = [
"anyhow",
"clap",
"codex-app-server-protocol",
"codex-protocol",
"serde",
"serde_json",
"uuid",
]
[[package]]
name = "codex-apply-patch"
version = "0.0.0"
@@ -1004,28 +974,24 @@ dependencies = [
"codex-common",
"codex-core",
"codex-exec",
"codex-execpolicy",
"codex-login",
"codex-mcp-server",
"codex-process-hardening",
"codex-protocol",
"codex-protocol-ts",
"codex-responses-api-proxy",
"codex-rmcp-client",
"codex-stdio-to-uds",
"codex-tui",
"codex-windows-sandbox",
"ctor 0.5.0",
"libc",
"owo-colors",
"predicates",
"pretty_assertions",
"regex-lite",
"serde_json",
"supports-color",
"tempfile",
"tokio",
"toml",
"tracing",
]
[[package]]
@@ -1076,10 +1042,7 @@ dependencies = [
"clap",
"codex-app-server-protocol",
"codex-core",
"codex-lmstudio",
"codex-ollama",
"codex-protocol",
"once_cell",
"serde",
"toml",
]
@@ -1096,13 +1059,10 @@ dependencies = [
"async-trait",
"base64",
"bytes",
"chardetng",
"chrono",
"codex-app-server-protocol",
"codex-apply-patch",
"codex-arg0",
"codex-async-utils",
"codex-execpolicy",
"codex-file-search",
"codex-git",
"codex-keyring-store",
@@ -1112,13 +1072,12 @@ dependencies = [
"codex-utils-pty",
"codex-utils-readiness",
"codex-utils-string",
"codex-utils-tokenizer",
"codex-windows-sandbox",
"core-foundation 0.9.4",
"core_test_support",
"ctor 0.5.0",
"dirs",
"dunce",
"encoding_rs",
"env-flags",
"escargot",
"eventsource-stream",
@@ -1148,7 +1107,6 @@ dependencies = [
"similar",
"strum_macros 0.27.2",
"tempfile",
"test-case",
"test-log",
"thiserror 2.0.17",
"time",
@@ -1178,6 +1136,7 @@ dependencies = [
"codex-arg0",
"codex-common",
"codex-core",
"codex-ollama",
"codex-protocol",
"core_test_support",
"libc",
@@ -1200,47 +1159,9 @@ dependencies = [
"wiremock",
]
[[package]]
name = "codex-exec-server"
version = "0.0.0"
dependencies = [
"anyhow",
"async-trait",
"clap",
"codex-core",
"libc",
"path-absolutize",
"pretty_assertions",
"rmcp",
"serde",
"serde_json",
"shlex",
"socket2 0.6.0",
"tempfile",
"tokio",
"tokio-util",
"tracing",
"tracing-subscriber",
]
[[package]]
name = "codex-execpolicy"
version = "0.0.0"
dependencies = [
"anyhow",
"clap",
"multimap",
"pretty_assertions",
"serde",
"serde_json",
"shlex",
"starlark",
"thiserror 2.0.17",
]
[[package]]
name = "codex-execpolicy-legacy"
version = "0.0.0"
dependencies = [
"allocative",
"anyhow",
@@ -1319,19 +1240,6 @@ dependencies = [
"tokio",
]
[[package]]
name = "codex-lmstudio"
version = "0.0.0"
dependencies = [
"codex-core",
"reqwest",
"serde_json",
"tokio",
"tracing",
"which",
"wiremock",
]
[[package]]
name = "codex-login"
version = "0.0.0"
@@ -1407,7 +1315,6 @@ dependencies = [
"codex-app-server-protocol",
"codex-protocol",
"eventsource-stream",
"http",
"opentelemetry",
"opentelemetry-otlp",
"opentelemetry-semantic-conventions",
@@ -1441,7 +1348,6 @@ dependencies = [
"icu_provider",
"mcp-types",
"mime_guess",
"pretty_assertions",
"schemars 0.8.22",
"serde",
"serde_json",
@@ -1455,6 +1361,16 @@ dependencies = [
"uuid",
]
[[package]]
name = "codex-protocol-ts"
version = "0.0.0"
dependencies = [
"anyhow",
"clap",
"codex-app-server-protocol",
"ts-rs",
]
[[package]]
name = "codex-responses-api-proxy"
version = "0.0.0"
@@ -1498,7 +1414,6 @@ dependencies = [
"tracing",
"urlencoding",
"webbrowser",
"which",
]
[[package]]
@@ -1526,17 +1441,15 @@ dependencies = [
"codex-ansi-escape",
"codex-app-server-protocol",
"codex-arg0",
"codex-backend-client",
"codex-common",
"codex-core",
"codex-feedback",
"codex-file-search",
"codex-login",
"codex-ollama",
"codex-protocol",
"codex-windows-sandbox",
"color-eyre",
"crossterm",
"derive_more 2.0.1",
"diffy",
"dirs",
"dunce",
@@ -1554,10 +1467,8 @@ dependencies = [
"ratatui",
"ratatui-macros",
"regex-lite",
"reqwest",
"serde",
"serde_json",
"serial_test",
"shlex",
"strum 0.27.2",
"strum_macros 0.27.2",
@@ -1632,14 +1543,22 @@ dependencies = [
name = "codex-utils-string"
version = "0.0.0"
[[package]]
name = "codex-utils-tokenizer"
version = "0.0.0"
dependencies = [
"anyhow",
"pretty_assertions",
"thiserror 2.0.17",
"tiktoken-rs",
]
[[package]]
name = "codex-windows-sandbox"
version = "0.1.0"
dependencies = [
"anyhow",
"codex-protocol",
"dirs-next",
"dunce",
"rand 0.8.5",
"serde",
"serde_json",
@@ -1733,15 +1652,6 @@ dependencies = [
"unicode-segmentation",
]
[[package]]
name = "convert_case"
version = "0.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bb402b8d4c85569410425650ce3eddc7d698ed96d39a73f941b08fb63082f1e7"
dependencies = [
"unicode-segmentation",
]
[[package]]
name = "core-foundation"
version = "0.9.4"
@@ -1779,7 +1689,6 @@ dependencies = [
"notify",
"regex-lite",
"serde_json",
"shlex",
"tempfile",
"tokio",
"walkdir",
@@ -1841,7 +1750,8 @@ checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
[[package]]
name = "crossterm"
version = "0.28.1"
source = "git+https://github.com/nornagon/crossterm?branch=nornagon%2Fcolor-query#87db8bfa6dc99427fd3b071681b07fc31c6ce995"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "829d955a0bb380ef178a640b91779e3987da38c9aea133b20614cfed8cdea9c6"
dependencies = [
"bitflags 2.10.0",
"crossterm_winapi",
@@ -2088,7 +1998,7 @@ version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cb7330aeadfbe296029522e6c40f315320aba36fc43a5b3632f3795348f3bd22"
dependencies = [
"convert_case 0.6.0",
"convert_case",
"proc-macro2",
"quote",
"syn 2.0.104",
@@ -2101,7 +2011,6 @@ version = "2.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bda628edc44c4bb645fbe0f758797143e4e07926f7ebf4e9bdfbd3d2ce621df3"
dependencies = [
"convert_case 0.7.1",
"proc-macro2",
"quote",
"syn 2.0.104",
@@ -2454,6 +2363,17 @@ dependencies = [
"once_cell",
]
[[package]]
name = "fancy-regex"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "531e46835a22af56d1e3b66f04844bed63158bc094a628bec1d321d9b4c44bf2"
dependencies = [
"bit-set",
"regex-automata",
"regex-syntax 0.8.5",
]
[[package]]
name = "fastrand"
version = "2.3.0"
@@ -2954,6 +2874,15 @@ version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
[[package]]
name = "humansize"
version = "2.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6cb51c9a029ddc91b07a787f1d86b53ccfa49b0e86688c946ebe8d3555685dd7"
dependencies = [
"libm",
]
[[package]]
name = "hyper"
version = "1.7.0"
@@ -3597,6 +3526,12 @@ dependencies = [
"pkg-config",
]
[[package]]
name = "libm"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
[[package]]
name = "libredox"
version = "0.1.6"
@@ -3741,13 +3676,11 @@ dependencies = [
"assert_cmd",
"codex-core",
"codex-mcp-server",
"core_test_support",
"mcp-types",
"os_info",
"pretty_assertions",
"serde",
"serde_json",
"shlex",
"tokio",
"wiremock",
]
@@ -4365,16 +4298,6 @@ dependencies = [
"windows-sys 0.52.0",
]
[[package]]
name = "os_pipe"
version = "1.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "db335f4760b14ead6290116f2427bf33a14d4f0617d49f78a246de10c1831224"
dependencies = [
"libc",
"windows-sys 0.59.0",
]
[[package]]
name = "owo-colors"
version = "4.2.2"
@@ -4522,7 +4445,7 @@ checksum = "3af6b589e163c5a788fab00ce0c0366f6efbb9959c2f9874b224936af7fce7e1"
dependencies = [
"base64",
"indexmap 2.12.0",
"quick-xml 0.38.0",
"quick-xml",
"serde",
"time",
]
@@ -4751,15 +4674,6 @@ version = "2.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
[[package]]
name = "quick-xml"
version = "0.37.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "331e97a1af0bf59823e6eadffe373d7b27f485be8748f71471c662c1f269b7fb"
dependencies = [
"memchr",
]
[[package]]
name = "quick-xml"
version = "0.38.0"
@@ -4780,7 +4694,7 @@ dependencies = [
"pin-project-lite",
"quinn-proto",
"quinn-udp",
"rustc-hash",
"rustc-hash 2.1.1",
"rustls",
"socket2 0.6.0",
"thiserror 2.0.17",
@@ -4800,7 +4714,7 @@ dependencies = [
"lru-slab",
"rand 0.9.2",
"ring",
"rustc-hash",
"rustc-hash 2.1.1",
"rustls",
"rustls-pki-types",
"slab",
@@ -5094,9 +5008,9 @@ dependencies = [
[[package]]
name = "rmcp"
version = "0.8.5"
version = "0.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5947688160b56fb6c827e3c20a72c90392a1d7e9dec74749197aa1780ac42ca"
checksum = "1fdad1258f7259fdc0f2dfc266939c82c3b5d1fd72bcde274d600cdc27e60243"
dependencies = [
"base64",
"bytes",
@@ -5128,9 +5042,9 @@ dependencies = [
[[package]]
name = "rmcp-macros"
version = "0.8.5"
version = "0.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "01263441d3f8635c628e33856c468b96ebbce1af2d3699ea712ca71432d4ee7a"
checksum = "ede0589a208cc7ce81d1be68aa7e74b917fcd03c81528408bab0457e187dcd9b"
dependencies = [
"darling 0.21.3",
"proc-macro2",
@@ -5145,6 +5059,12 @@ version = "0.1.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "989e6739f80c4ad5b13e0fd7fe89531180375b18520cc8c82080e4dc4035b84f"
[[package]]
name = "rustc-hash"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
[[package]]
name = "rustc-hash"
version = "2.1.1"
@@ -5192,7 +5112,6 @@ version = "0.23.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2491382039b29b9b11ff08b76ff6c97cf287671dbb74f0be44bda389fffe9bd1"
dependencies = [
"log",
"once_cell",
"ring",
"rustls-pki-types",
@@ -5766,12 +5685,6 @@ dependencies = [
"digest",
]
[[package]]
name = "sha1_smol"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbfa15b3dddfee50a0fff136974b3e1bde555604ba463834a7eb7deb6417705d"
[[package]]
name = "sha2"
version = "0.10.9"
@@ -6227,39 +6140,6 @@ version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f50febec83f5ee1df3015341d8bd429f2d1cc62bcba7ea2076759d315084683"
[[package]]
name = "test-case"
version = "3.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eb2550dd13afcd286853192af8601920d959b14c401fcece38071d53bf0768a8"
dependencies = [
"test-case-macros",
]
[[package]]
name = "test-case-core"
version = "3.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "adcb7fd841cd518e279be3d5a3eb0636409487998a4aff22f3de87b81e88384f"
dependencies = [
"cfg-if",
"proc-macro2",
"quote",
"syn 2.0.104",
]
[[package]]
name = "test-case-macros"
version = "3.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c89e72a01ed4c579669add59014b9a524d609c0c88c6a585ce37485879f6ffb"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.104",
"test-case-core",
]
[[package]]
name = "test-log"
version = "0.2.18"
@@ -6365,6 +6245,21 @@ dependencies = [
"zune-jpeg",
]
[[package]]
name = "tiktoken-rs"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "25563eeba904d770acf527e8b370fe9a5547bacd20ff84a0b6c3bc41288e5625"
dependencies = [
"anyhow",
"base64",
"bstr",
"fancy-regex",
"lazy_static",
"regex",
"rustc-hash 1.1.0",
]
[[package]]
name = "time"
version = "0.3.44"
@@ -6605,10 +6500,8 @@ dependencies = [
"percent-encoding",
"pin-project",
"prost",
"rustls-native-certs",
"socket2 0.5.10",
"tokio",
"tokio-rustls",
"tokio-stream",
"tower",
"tower-layer",
@@ -6812,18 +6705,6 @@ version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c4013970217383f67b18aef68f6fb2e8d409bc5755227092d32efb0422ba24b8"
[[package]]
name = "tree_magic_mini"
version = "3.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f943391d896cdfe8eec03a04d7110332d445be7df856db382dd96a730667562c"
dependencies = [
"memchr",
"nom",
"once_cell",
"petgraph",
]
[[package]]
name = "try-lock"
version = "0.2.5"
@@ -6991,7 +6872,6 @@ dependencies = [
"getrandom 0.3.3",
"js-sys",
"serde",
"sha1_smol",
"wasm-bindgen",
]
@@ -7161,76 +7041,6 @@ dependencies = [
"web-sys",
]
[[package]]
name = "wayland-backend"
version = "0.3.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "673a33c33048a5ade91a6b139580fa174e19fb0d23f396dca9fa15f2e1e49b35"
dependencies = [
"cc",
"downcast-rs",
"rustix 1.0.8",
"smallvec",
"wayland-sys",
]
[[package]]
name = "wayland-client"
version = "0.31.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c66a47e840dc20793f2264eb4b3e4ecb4b75d91c0dd4af04b456128e0bdd449d"
dependencies = [
"bitflags 2.10.0",
"rustix 1.0.8",
"wayland-backend",
"wayland-scanner",
]
[[package]]
name = "wayland-protocols"
version = "0.32.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "efa790ed75fbfd71283bd2521a1cfdc022aabcc28bdcff00851f9e4ae88d9901"
dependencies = [
"bitflags 2.10.0",
"wayland-backend",
"wayland-client",
"wayland-scanner",
]
[[package]]
name = "wayland-protocols-wlr"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "efd94963ed43cf9938a090ca4f7da58eb55325ec8200c3848963e98dc25b78ec"
dependencies = [
"bitflags 2.10.0",
"wayland-backend",
"wayland-client",
"wayland-protocols",
"wayland-scanner",
]
[[package]]
name = "wayland-scanner"
version = "0.31.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "54cb1e9dc49da91950bdfd8b848c49330536d9d1fb03d4bfec8cae50caa50ae3"
dependencies = [
"proc-macro2",
"quick-xml 0.37.5",
"quote",
]
[[package]]
name = "wayland-sys"
version = "0.31.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34949b42822155826b41db8e5d0c1be3a2bd296c747577a43a3e6daefc296142"
dependencies = [
"pkg-config",
]
[[package]]
name = "web-sys"
version = "0.3.77"
@@ -7802,25 +7612,6 @@ dependencies = [
"bitflags 2.10.0",
]
[[package]]
name = "wl-clipboard-rs"
version = "0.9.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e5ff8d0e60065f549fafd9d6cb626203ea64a798186c80d8e7df4f8af56baeb"
dependencies = [
"libc",
"log",
"os_pipe",
"rustix 0.38.44",
"tempfile",
"thiserror 2.0.17",
"tree_magic_mini",
"wayland-backend",
"wayland-client",
"wayland-protocols",
"wayland-protocols-wlr",
]
[[package]]
name = "writeable"
version = "0.6.2"
@@ -7989,9 +7780,9 @@ dependencies = [
[[package]]
name = "zeroize"
version = "1.8.2"
version = "1.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde"
dependencies = [
"zeroize_derive",
]

View File

@@ -5,7 +5,6 @@ members = [
"async-utils",
"app-server",
"app-server-protocol",
"app-server-test-client",
"apply-patch",
"arg0",
"feedback",
@@ -16,19 +15,17 @@ members = [
"common",
"core",
"exec",
"exec-server",
"execpolicy",
"execpolicy-legacy",
"keyring-store",
"file-search",
"linux-sandbox",
"lmstudio",
"login",
"mcp-server",
"mcp-types",
"ollama",
"process-hardening",
"protocol",
"protocol-ts",
"rmcp-client",
"responses-api-proxy",
"stdio-to-uds",
@@ -41,6 +38,7 @@ members = [
"utils/pty",
"utils/readiness",
"utils/string",
"utils/tokenizer",
]
resolver = "2"
@@ -66,19 +64,18 @@ codex-chatgpt = { path = "chatgpt" }
codex-common = { path = "common" }
codex-core = { path = "core" }
codex-exec = { path = "exec" }
codex-execpolicy = { path = "execpolicy" }
codex-feedback = { path = "feedback" }
codex-file-search = { path = "file-search" }
codex-git = { path = "utils/git" }
codex-keyring-store = { path = "keyring-store" }
codex-linux-sandbox = { path = "linux-sandbox" }
codex-lmstudio = { path = "lmstudio" }
codex-login = { path = "login" }
codex-mcp-server = { path = "mcp-server" }
codex-ollama = { path = "ollama" }
codex-otel = { path = "otel" }
codex-process-hardening = { path = "process-hardening" }
codex-protocol = { path = "protocol" }
codex-protocol-ts = { path = "protocol-ts" }
codex-responses-api-proxy = { path = "responses-api-proxy" }
codex-rmcp-client = { path = "rmcp-client" }
codex-stdio-to-uds = { path = "stdio-to-uds" }
@@ -89,7 +86,8 @@ codex-utils-json-to-toml = { path = "utils/json-to-toml" }
codex-utils-pty = { path = "utils/pty" }
codex-utils-readiness = { path = "utils/readiness" }
codex-utils-string = { path = "utils/string" }
codex-windows-sandbox = { path = "windows-sandbox-rs" }
codex-utils-tokenizer = { path = "utils/tokenizer" }
codex-windows-sandbox = { path = "windows-sandbox" }
core_test_support = { path = "core/tests/common" }
mcp-types = { path = "mcp-types" }
mcp_test_support = { path = "mcp-server/tests/common" }
@@ -98,8 +96,8 @@ mcp_test_support = { path = "mcp-server/tests/common" }
allocative = "0.3.3"
ansi-to-tui = "7.0.0"
anyhow = "1"
arboard = { version = "3", features = ["wayland-data-control"] }
askama = "0.14"
arboard = "3"
askama = "0.12"
assert_cmd = "2"
assert_matches = "1.5.0"
async-channel = "2.3.1"
@@ -109,7 +107,6 @@ axum = { version = "0.8", default-features = false }
base64 = "0.22.1"
bytes = "1.10.1"
chrono = "0.4.42"
chardetng = "0.1.17"
clap = "4"
clap_complete = "4"
color-eyre = "0.6.3"
@@ -122,20 +119,19 @@ dotenvy = "0.15.7"
dunce = "1.0.4"
env-flags = "0.1.1"
env_logger = "0.11.5"
encoding_rs = "0.8.35"
escargot = "0.5"
eventsource-stream = "0.2.3"
futures = { version = "0.3", default-features = false }
http = "1.3.1"
icu_decimal = "2.1"
icu_locale_core = "2.1"
icu_provider = { version = "2.1", features = ["sync"] }
icu_locale_core = "2.1"
ignore = "0.4.23"
image = { version = "^0.25.8", default-features = false }
indexmap = "2.12.0"
insta = "1.43.2"
itertools = "0.14.0"
keyring = { version = "3.6", default-features = false }
keyring = "3.6"
landlock = "0.4.1"
lazy_static = "1"
libc = "0.2.175"
@@ -146,7 +142,6 @@ mime_guess = "2.0.5"
multimap = "0.10.0"
notify = "8.2.0"
nucleo-matcher = "0.3.1"
once_cell = "1"
openssl-sys = "*"
opentelemetry = "0.30.0"
opentelemetry-appender-tracing = "0.30.0"
@@ -155,6 +150,7 @@ opentelemetry-semantic-conventions = "0.30.0"
opentelemetry_sdk = "0.30.0"
os_info = "3.12.0"
owo-colors = "4.2.0"
paste = "1.0.15"
path-absolutize = "3.1.1"
pathdiff = "0.2"
portable-pty = "0.9.0"
@@ -166,9 +162,10 @@ ratatui = "0.29.0"
ratatui-macros = "0.6.0"
regex-lite = "0.1.7"
reqwest = "0.12"
rmcp = { version = "0.8.5", default-features = false }
rmcp = { version = "0.8.3", default-features = false }
schemars = "0.8.22"
seccompiler = "0.5.0"
sentry = "0.34.0"
serde = "1"
serde_json = "1"
serde_with = "3.14"
@@ -177,7 +174,6 @@ sha1 = "0.10.6"
sha2 = "0.10"
shlex = "1.3.0"
similar = "2.7.0"
socket2 = "0.6.0"
starlark = "0.13.0"
strum = "0.27.2"
strum_macros = "0.27.2"
@@ -217,7 +213,7 @@ which = "6"
wildmatch = "2.5.0"
wiremock = "0.6"
zeroize = "1.8.2"
zeroize = "1.8.1"
[workspace.lints]
rust = {}
@@ -260,11 +256,7 @@ unwrap_used = "deny"
# cargo-shear cannot see the platform-specific openssl-sys usage, so we
# silence the false positive here instead of deleting a real dependency.
[workspace.metadata.cargo-shear]
ignored = [
"icu_provider",
"openssl-sys",
"codex-utils-readiness",
]
ignored = ["icu_provider", "openssl-sys", "codex-utils-readiness", "codex-utils-tokenizer"]
[profile.release]
lto = "fat"
@@ -283,7 +275,6 @@ opt-level = 0
[patch.crates-io]
# Uncomment to debug local changes.
# ratatui = { path = "../../ratatui" }
crossterm = { git = "https://github.com/nornagon/crossterm", branch = "nornagon/color-query" }
ratatui = { git = "https://github.com/nornagon/ratatui", branch = "nornagon-v0.29.0-patch" }
# Uncomment to debug local changes.

View File

@@ -58,7 +58,7 @@ To test to see what happens when a command is run under the sandbox provided by
```
# macOS
codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...
codex sandbox macos [--full-auto] [COMMAND]...
# Linux
codex sandbox linux [--full-auto] [COMMAND]...
@@ -67,7 +67,7 @@ codex sandbox linux [--full-auto] [COMMAND]...
codex sandbox windows [--full-auto] [COMMAND]...
# Legacy aliases
codex debug seatbelt [--full-auto] [--log-denials] [COMMAND]...
codex debug seatbelt [--full-auto] [COMMAND]...
codex debug landlock [--full-auto] [COMMAND]...
```

View File

@@ -14,12 +14,11 @@ workspace = true
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive"] }
codex-protocol = { workspace = true }
mcp-types = { workspace = true }
paste = { workspace = true }
schemars = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
strum_macros = { workspace = true }
thiserror = { workspace = true }
ts-rs = { workspace = true }
uuid = { workspace = true, features = ["serde", "v7"] }

View File

@@ -2,24 +2,20 @@ use crate::ClientNotification;
use crate::ClientRequest;
use crate::ServerNotification;
use crate::ServerRequest;
use crate::export_client_notification_schemas;
use crate::export_client_param_schemas;
use crate::export_client_response_schemas;
use crate::export_client_responses;
use crate::export_server_notification_schemas;
use crate::export_server_param_schemas;
use crate::export_server_response_schemas;
use crate::export_server_responses;
use anyhow::Context;
use anyhow::Result;
use anyhow::anyhow;
use codex_protocol::protocol::EventMsg;
use schemars::JsonSchema;
use schemars::schema::RootSchema;
use schemars::schema_for;
use serde::Serialize;
use serde_json::Map;
use serde_json::Value;
use std::collections::HashMap;
use std::collections::BTreeMap;
use std::collections::HashSet;
use std::ffi::OsStr;
use std::fs;
@@ -32,64 +28,91 @@ use ts_rs::TS;
const HEADER: &str = "// GENERATED CODE! DO NOT MODIFY BY HAND!\n\n";
#[derive(Clone)]
pub struct GeneratedSchema {
namespace: Option<String>,
logical_name: String,
value: Value,
in_v1_dir: bool,
macro_rules! for_each_schema_type {
($macro:ident) => {
$macro!(crate::RequestId);
$macro!(crate::JSONRPCMessage);
$macro!(crate::JSONRPCRequest);
$macro!(crate::JSONRPCNotification);
$macro!(crate::JSONRPCResponse);
$macro!(crate::JSONRPCError);
$macro!(crate::JSONRPCErrorError);
$macro!(crate::AddConversationListenerParams);
$macro!(crate::AddConversationSubscriptionResponse);
$macro!(crate::ApplyPatchApprovalParams);
$macro!(crate::ApplyPatchApprovalResponse);
$macro!(crate::ArchiveConversationParams);
$macro!(crate::ArchiveConversationResponse);
$macro!(crate::AuthMode);
$macro!(crate::AuthStatusChangeNotification);
$macro!(crate::CancelLoginChatGptParams);
$macro!(crate::CancelLoginChatGptResponse);
$macro!(crate::ClientInfo);
$macro!(crate::ClientNotification);
$macro!(crate::ClientRequest);
$macro!(crate::ConversationSummary);
$macro!(crate::ExecCommandApprovalParams);
$macro!(crate::ExecCommandApprovalResponse);
$macro!(crate::ExecOneOffCommandParams);
$macro!(crate::ExecOneOffCommandResponse);
$macro!(crate::FuzzyFileSearchParams);
$macro!(crate::FuzzyFileSearchResponse);
$macro!(crate::FuzzyFileSearchResult);
$macro!(crate::GetAuthStatusParams);
$macro!(crate::GetAuthStatusResponse);
$macro!(crate::GetUserAgentResponse);
$macro!(crate::GetUserSavedConfigResponse);
$macro!(crate::GitDiffToRemoteParams);
$macro!(crate::GitDiffToRemoteResponse);
$macro!(crate::GitSha);
$macro!(crate::InitializeParams);
$macro!(crate::InitializeResponse);
$macro!(crate::InputItem);
$macro!(crate::InterruptConversationParams);
$macro!(crate::InterruptConversationResponse);
$macro!(crate::ListConversationsParams);
$macro!(crate::ListConversationsResponse);
$macro!(crate::LoginApiKeyParams);
$macro!(crate::LoginApiKeyResponse);
$macro!(crate::LoginChatGptCompleteNotification);
$macro!(crate::LoginChatGptResponse);
$macro!(crate::LogoutChatGptParams);
$macro!(crate::LogoutChatGptResponse);
$macro!(crate::NewConversationParams);
$macro!(crate::NewConversationResponse);
$macro!(crate::Profile);
$macro!(crate::RemoveConversationListenerParams);
$macro!(crate::RemoveConversationSubscriptionResponse);
$macro!(crate::ResumeConversationParams);
$macro!(crate::ResumeConversationResponse);
$macro!(crate::SandboxSettings);
$macro!(crate::SendUserMessageParams);
$macro!(crate::SendUserMessageResponse);
$macro!(crate::SendUserTurnParams);
$macro!(crate::SendUserTurnResponse);
$macro!(crate::ServerNotification);
$macro!(crate::ServerRequest);
$macro!(crate::SessionConfiguredNotification);
$macro!(crate::SetDefaultModelParams);
$macro!(crate::SetDefaultModelResponse);
$macro!(crate::Tools);
$macro!(crate::UserInfoResponse);
$macro!(crate::UserSavedConfig);
$macro!(codex_protocol::protocol::EventMsg);
$macro!(codex_protocol::protocol::FileChange);
$macro!(codex_protocol::parse_command::ParsedCommand);
$macro!(codex_protocol::protocol::SandboxPolicy);
};
}
impl GeneratedSchema {
fn namespace(&self) -> Option<&str> {
self.namespace.as_deref()
}
fn logical_name(&self) -> &str {
&self.logical_name
}
fn value(&self) -> &Value {
&self.value
}
}
type JsonSchemaEmitter = fn(&Path) -> Result<GeneratedSchema>;
pub fn generate_types(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
generate_ts(out_dir, prettier)?;
generate_json(out_dir)?;
Ok(())
}
#[derive(Clone, Copy, Debug)]
pub struct GenerateTsOptions {
pub generate_indices: bool,
pub ensure_headers: bool,
pub run_prettier: bool,
}
impl Default for GenerateTsOptions {
fn default() -> Self {
Self {
generate_indices: true,
ensure_headers: true,
run_prettier: true,
}
}
}
pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
generate_ts_with_options(out_dir, prettier, GenerateTsOptions::default())
}
pub fn generate_ts_with_options(
out_dir: &Path,
prettier: Option<&Path>,
options: GenerateTsOptions,
) -> Result<()> {
let v2_out_dir = out_dir.join("v2");
ensure_dir(out_dir)?;
ensure_dir(&v2_out_dir)?;
ClientRequest::export_all_to(out_dir)?;
export_client_responses(out_dir)?;
@@ -99,34 +122,18 @@ pub fn generate_ts_with_options(
export_server_responses(out_dir)?;
ServerNotification::export_all_to(out_dir)?;
if options.generate_indices {
generate_index_ts(out_dir)?;
generate_index_ts(&v2_out_dir)?;
generate_index_ts(out_dir)?;
let ts_files = ts_files_in(out_dir)?;
for file in &ts_files {
prepend_header_if_missing(file)?;
}
// Ensure our header is present on all TS files (root + subdirs like v2/).
let mut ts_files = Vec::new();
let should_collect_ts_files =
options.ensure_headers || (options.run_prettier && prettier.is_some());
if should_collect_ts_files {
ts_files = ts_files_in_recursive(out_dir)?;
}
if options.ensure_headers {
for file in &ts_files {
prepend_header_if_missing(file)?;
}
}
// Optionally run Prettier on all generated TS files.
if options.run_prettier
&& let Some(prettier_bin) = prettier
if let Some(prettier_bin) = prettier
&& !ts_files.is_empty()
{
let status = Command::new(prettier_bin)
.arg("--write")
.arg("--log-level")
.arg("warn")
.args(ts_files.iter().map(|p| p.as_os_str()))
.status()
.with_context(|| format!("Failed to invoke Prettier at {}", prettier_bin.display()))?;
@@ -140,115 +147,51 @@ pub fn generate_ts_with_options(
pub fn generate_json(out_dir: &Path) -> Result<()> {
ensure_dir(out_dir)?;
let envelope_emitters: &[JsonSchemaEmitter] = &[
|d| write_json_schema_with_return::<crate::RequestId>(d, "RequestId"),
|d| write_json_schema_with_return::<crate::JSONRPCMessage>(d, "JSONRPCMessage"),
|d| write_json_schema_with_return::<crate::JSONRPCRequest>(d, "JSONRPCRequest"),
|d| write_json_schema_with_return::<crate::JSONRPCNotification>(d, "JSONRPCNotification"),
|d| write_json_schema_with_return::<crate::JSONRPCResponse>(d, "JSONRPCResponse"),
|d| write_json_schema_with_return::<crate::JSONRPCError>(d, "JSONRPCError"),
|d| write_json_schema_with_return::<crate::JSONRPCErrorError>(d, "JSONRPCErrorError"),
|d| write_json_schema_with_return::<crate::ClientRequest>(d, "ClientRequest"),
|d| write_json_schema_with_return::<crate::ServerRequest>(d, "ServerRequest"),
|d| write_json_schema_with_return::<crate::ClientNotification>(d, "ClientNotification"),
|d| write_json_schema_with_return::<crate::ServerNotification>(d, "ServerNotification"),
|d| write_json_schema_with_return::<EventMsg>(d, "EventMsg"),
];
let mut bundle: BTreeMap<String, RootSchema> = BTreeMap::new();
let mut schemas: Vec<GeneratedSchema> = Vec::new();
for emit in envelope_emitters {
schemas.push(emit(out_dir)?);
macro_rules! add_schema {
($ty:path) => {{
let name = type_basename(stringify!($ty));
let schema = write_json_schema_with_return::<$ty>(out_dir, &name)?;
bundle.insert(name, schema);
}};
}
schemas.extend(export_client_param_schemas(out_dir)?);
schemas.extend(export_client_response_schemas(out_dir)?);
schemas.extend(export_server_param_schemas(out_dir)?);
schemas.extend(export_server_response_schemas(out_dir)?);
schemas.extend(export_client_notification_schemas(out_dir)?);
schemas.extend(export_server_notification_schemas(out_dir)?);
for_each_schema_type!(add_schema);
let bundle = build_schema_bundle(schemas)?;
write_pretty_json(
out_dir.join("codex_app_server_protocol.schemas.json"),
&bundle,
)?;
export_client_response_schemas(out_dir)?;
export_server_response_schemas(out_dir)?;
Ok(())
}
let mut definitions = Map::new();
fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<Value> {
const SPECIAL_DEFINITIONS: &[&str] = &[
"ClientNotification",
"ClientRequest",
"EventMsg",
"FileChange",
"InputItem",
"ParsedCommand",
"SandboxPolicy",
"ServerNotification",
"ServerRequest",
];
const IGNORED_DEFINITIONS: &[&str] = &["Option<()>"];
let namespaced_types = collect_namespaced_types(&schemas);
let mut definitions = Map::new();
for (name, schema) in bundle {
let mut schema_value = serde_json::to_value(schema)?;
annotate_schema(&mut schema_value, Some(name.as_str()));
for schema in schemas {
let GeneratedSchema {
namespace,
logical_name,
mut value,
in_v1_dir,
} = schema;
if IGNORED_DEFINITIONS.contains(&logical_name.as_str()) {
continue;
}
if let Some(ref ns) = namespace {
rewrite_refs_to_namespace(&mut value, ns);
}
let mut forced_namespace_refs: Vec<(String, String)> = Vec::new();
if let Value::Object(ref mut obj) = value
if let Value::Object(ref mut obj) = schema_value
&& let Some(defs) = obj.remove("definitions")
&& let Value::Object(defs_obj) = defs
{
for (def_name, mut def_schema) in defs_obj {
if IGNORED_DEFINITIONS.contains(&def_name.as_str()) {
continue;
}
if SPECIAL_DEFINITIONS.contains(&def_name.as_str()) {
continue;
}
annotate_schema(&mut def_schema, Some(def_name.as_str()));
let target_namespace = match namespace {
Some(ref ns) => Some(ns.clone()),
None => namespace_for_definition(&def_name, &namespaced_types)
.cloned()
.filter(|_| !in_v1_dir),
};
if let Some(ref ns) = target_namespace {
if namespace.as_deref() == Some(ns.as_str()) {
rewrite_refs_to_namespace(&mut def_schema, ns);
insert_into_namespace(&mut definitions, ns, def_name.clone(), def_schema)?;
} else if !forced_namespace_refs
.iter()
.any(|(name, existing_ns)| name == &def_name && existing_ns == ns)
{
forced_namespace_refs.push((def_name.clone(), ns.clone()));
}
} else {
if !SPECIAL_DEFINITIONS.contains(&def_name.as_str()) {
annotate_schema(&mut def_schema, Some(def_name.as_str()));
definitions.insert(def_name, def_schema);
}
}
}
for (name, ns) in forced_namespace_refs {
rewrite_named_ref_to_namespace(&mut value, &ns, &name);
}
if let Some(ref ns) = namespace {
insert_into_namespace(&mut definitions, ns, logical_name.clone(), value)?;
} else {
definitions.insert(logical_name, value);
}
definitions.insert(name, schema_value);
}
let mut root = Map::new();
@@ -263,28 +206,15 @@ fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<Value> {
root.insert("type".to_string(), Value::String("object".into()));
root.insert("definitions".to_string(), Value::Object(definitions));
Ok(Value::Object(root))
write_pretty_json(
out_dir.join("codex_app_server_protocol.schemas.json"),
&Value::Object(root),
)?;
Ok(())
}
fn insert_into_namespace(
definitions: &mut Map<String, Value>,
namespace: &str,
name: String,
schema: Value,
) -> Result<()> {
let entry = definitions
.entry(namespace.to_string())
.or_insert_with(|| Value::Object(Map::new()));
match entry {
Value::Object(map) => {
map.insert(name, schema);
Ok(())
}
_ => Err(anyhow!("expected namespace {namespace} to be an object")),
}
}
fn write_json_schema_with_return<T>(out_dir: &Path, name: &str) -> Result<GeneratedSchema>
fn write_json_schema_with_return<T>(out_dir: &Path, name: &str) -> Result<RootSchema>
where
T: JsonSchema,
{
@@ -292,37 +222,17 @@ where
let schema = schema_for!(T);
let mut schema_value = serde_json::to_value(schema)?;
annotate_schema(&mut schema_value, Some(file_stem));
// If the name looks like a namespaced path (e.g., "v2::Type"), mirror
// the TypeScript layout and write to out_dir/v2/Type.json. Otherwise
// write alongside the legacy files.
let (raw_namespace, logical_name) = split_namespace(file_stem);
let out_path = if let Some(ns) = raw_namespace {
let dir = out_dir.join(ns);
ensure_dir(&dir)?;
dir.join(format!("{logical_name}.json"))
} else {
out_dir.join(format!("{file_stem}.json"))
};
write_pretty_json(out_path, &schema_value)
write_pretty_json(out_dir.join(format!("{file_stem}.json")), &schema_value)
.with_context(|| format!("Failed to write JSON schema for {file_stem}"))?;
let namespace = match raw_namespace {
Some("v1") | None => None,
Some(ns) => Some(ns.to_string()),
};
Ok(GeneratedSchema {
in_v1_dir: raw_namespace == Some("v1"),
namespace,
logical_name: logical_name.to_string(),
value: schema_value,
})
let annotated_schema = serde_json::from_value(schema_value)?;
Ok(annotated_schema)
}
pub(crate) fn write_json_schema<T>(out_dir: &Path, name: &str) -> Result<GeneratedSchema>
pub(crate) fn write_json_schema<T>(out_dir: &Path, name: &str) -> Result<()>
where
T: JsonSchema,
{
write_json_schema_with_return::<T>(out_dir, name)
write_json_schema_with_return::<T>(out_dir, name).map(|_| ())
}
fn write_pretty_json(path: PathBuf, value: &impl Serialize) -> Result<()> {
@@ -331,73 +241,13 @@ fn write_pretty_json(path: PathBuf, value: &impl Serialize) -> Result<()> {
fs::write(&path, json).with_context(|| format!("Failed to write {}", path.display()))?;
Ok(())
}
/// Split a fully-qualified type name like "v2::Type" into its namespace and logical name.
fn split_namespace(name: &str) -> (Option<&str>, &str) {
name.split_once("::")
.map_or((None, name), |(ns, rest)| (Some(ns), rest))
}
/// Recursively rewrite $ref values that point at "#/definitions/..." so that
/// they point to a namespaced location under the bundle.
fn rewrite_refs_to_namespace(value: &mut Value, ns: &str) {
match value {
Value::Object(obj) => {
if let Some(Value::String(r)) = obj.get_mut("$ref")
&& let Some(suffix) = r.strip_prefix("#/definitions/")
{
let prefix = format!("{ns}/");
if !suffix.starts_with(&prefix) {
*r = format!("#/definitions/{ns}/{suffix}");
}
}
for v in obj.values_mut() {
rewrite_refs_to_namespace(v, ns);
}
}
Value::Array(items) => {
for v in items.iter_mut() {
rewrite_refs_to_namespace(v, ns);
}
}
_ => {}
}
}
fn collect_namespaced_types(schemas: &[GeneratedSchema]) -> HashMap<String, String> {
let mut types = HashMap::new();
for schema in schemas {
if let Some(ns) = schema.namespace() {
types
.entry(schema.logical_name().to_string())
.or_insert_with(|| ns.to_string());
if let Some(Value::Object(defs)) = schema.value().get("definitions") {
for key in defs.keys() {
types.entry(key.clone()).or_insert_with(|| ns.to_string());
}
}
if let Some(Value::Object(defs)) = schema.value().get("$defs") {
for key in defs.keys() {
types.entry(key.clone()).or_insert_with(|| ns.to_string());
}
}
}
}
types
}
fn namespace_for_definition<'a>(
name: &str,
types: &'a HashMap<String, String>,
) -> Option<&'a String> {
if let Some(ns) = types.get(name) {
return Some(ns);
}
let trimmed = name.trim_end_matches(|c: char| c.is_ascii_digit());
if trimmed != name {
return types.get(trimmed);
}
None
fn type_basename(type_path: &str) -> String {
type_path
.rsplit_once("::")
.map(|(_, name)| name)
.unwrap_or(type_path)
.trim()
.to_string()
}
fn variant_definition_name(base: &str, variant: &Value) -> Option<String> {
@@ -419,6 +269,14 @@ fn variant_definition_name(base: &str, variant: &Value) -> Option<String> {
});
}
if let Some(mode_literal) = literal_from_property(props, "mode") {
let pascal = to_pascal_case(mode_literal);
return Some(match base {
"SandboxPolicy" => format!("{pascal}SandboxPolicy"),
_ => format!("{pascal}{base}"),
});
}
if props.len() == 1
&& let Some(key) = props.keys().next()
{
@@ -609,33 +467,6 @@ fn ensure_dir(dir: &Path) -> Result<()> {
.with_context(|| format!("Failed to create output directory {}", dir.display()))
}
fn rewrite_named_ref_to_namespace(value: &mut Value, ns: &str, name: &str) {
let direct = format!("#/definitions/{name}");
let prefixed = format!("{direct}/");
let replacement = format!("#/definitions/{ns}/{name}");
let replacement_prefixed = format!("{replacement}/");
match value {
Value::Object(obj) => {
if let Some(Value::String(reference)) = obj.get_mut("$ref") {
if reference == &direct {
*reference = replacement;
} else if let Some(rest) = reference.strip_prefix(&prefixed) {
*reference = format!("{replacement_prefixed}{rest}");
}
}
for child in obj.values_mut() {
rewrite_named_ref_to_namespace(child, ns, name);
}
}
Value::Array(items) => {
for child in items {
rewrite_named_ref_to_namespace(child, ns, name);
}
}
_ => {}
}
}
fn prepend_header_if_missing(path: &Path) -> Result<()> {
let mut content = String::new();
{
@@ -673,28 +504,6 @@ fn ts_files_in(dir: &Path) -> Result<Vec<PathBuf>> {
Ok(files)
}
fn ts_files_in_recursive(dir: &Path) -> Result<Vec<PathBuf>> {
let mut files = Vec::new();
let mut stack = vec![dir.to_path_buf()];
while let Some(d) = stack.pop() {
for entry in
fs::read_dir(&d).with_context(|| format!("Failed to read dir {}", d.display()))?
{
let entry = entry?;
let path = entry.path();
if path.is_dir() {
stack.push(path);
} else if path.is_file() && path.extension() == Some(OsStr::new("ts")) {
files.push(path);
}
}
}
files.sort();
Ok(files)
}
/// Generate an index.ts file that re-exports all generated types.
/// This allows consumers to import all types from a single file.
fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
let mut entries: Vec<String> = Vec::new();
let mut stems: Vec<String> = ts_files_in(out_dir)?
@@ -711,14 +520,6 @@ fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
entries.push(format!("export type {{ {name} }} from \"./{name}\";\n"));
}
// If this is the root out_dir and a ./v2 folder exists with TS files,
// expose it as a namespace to avoid symbol collisions at the root.
let v2_dir = out_dir.join("v2");
let has_v2_ts = ts_files_in(&v2_dir).map(|v| !v.is_empty()).unwrap_or(false);
if has_v2_ts {
entries.push("export * as v2 from \"./v2\";\n".to_string());
}
let mut content =
String::with_capacity(HEADER.len() + entries.iter().map(String::len).sum::<usize>());
content.push_str(HEADER);
@@ -745,7 +546,6 @@ mod tests {
#[test]
fn generated_ts_has_no_optional_nullable_fields() -> Result<()> {
// Assert that there are no types of the form "?: T | null" in the generated TS files.
let output_dir = std::env::temp_dir().join(format!("codex_ts_types_{}", Uuid::now_v7()));
fs::create_dir(&output_dir)?;
@@ -759,13 +559,7 @@ mod tests {
let _guard = TempDirGuard(output_dir.clone());
// Avoid doing more work than necessary to keep the test from timing out.
let options = GenerateTsOptions {
generate_indices: false,
ensure_headers: false,
run_prettier: false,
};
generate_ts_with_options(&output_dir, None, options)?;
generate_ts(&output_dir, None)?;
let mut undefined_offenders = Vec::new();
let mut optional_nullable_offenders = BTreeSet::new();

View File

@@ -7,6 +7,5 @@ pub use export::generate_ts;
pub use export::generate_types;
pub use jsonrpc_lite::*;
pub use protocol::common::*;
pub use protocol::thread_history::*;
pub use protocol::v1::*;
pub use protocol::v2::*;

View File

@@ -1,12 +1,18 @@
use std::path::Path;
use std::collections::HashMap;
use std::path::PathBuf;
use crate::JSONRPCNotification;
use crate::JSONRPCRequest;
use crate::RequestId;
use crate::export::GeneratedSchema;
use crate::export::write_json_schema;
use crate::protocol::v1;
use crate::protocol::v2;
use codex_protocol::ConversationId;
use codex_protocol::parse_command::ParsedCommand;
use codex_protocol::protocol::FileChange;
use codex_protocol::protocol::RateLimitSnapshot;
use codex_protocol::protocol::ReviewDecision;
use codex_protocol::protocol::SandboxCommandAssessment;
use paste::paste;
use schemars::JsonSchema;
use serde::Deserialize;
use serde::Serialize;
@@ -38,7 +44,7 @@ macro_rules! client_request_definitions {
(
$(
$(#[$variant_meta:meta])*
$variant:ident $(=> $wire:literal)? {
$variant:ident {
params: $(#[$params_meta:meta])* $params:ty,
response: $response:ty,
}
@@ -50,7 +56,6 @@ macro_rules! client_request_definitions {
pub enum ClientRequest {
$(
$(#[$variant_meta])*
$(#[serde(rename = $wire)] #[ts(rename = $wire)])?
$variant {
#[serde(rename = "id")]
request_id: RequestId,
@@ -69,107 +74,66 @@ macro_rules! client_request_definitions {
Ok(())
}
#[allow(clippy::vec_init_then_push)]
pub fn export_client_response_schemas(
out_dir: &::std::path::Path,
) -> ::anyhow::Result<Vec<GeneratedSchema>> {
let mut schemas = Vec::new();
) -> ::anyhow::Result<()> {
$(
schemas.push(write_json_schema::<$response>(out_dir, stringify!($response))?);
crate::export::write_json_schema::<$response>(out_dir, stringify!($response))?;
)*
Ok(schemas)
}
#[allow(clippy::vec_init_then_push)]
pub fn export_client_param_schemas(
out_dir: &::std::path::Path,
) -> ::anyhow::Result<Vec<GeneratedSchema>> {
let mut schemas = Vec::new();
$(
schemas.push(write_json_schema::<$params>(out_dir, stringify!($params))?);
)*
Ok(schemas)
Ok(())
}
};
}
client_request_definitions! {
Initialize {
params: v1::InitializeParams,
response: v1::InitializeResponse,
},
/// NEW APIs
// Thread lifecycle
ThreadStart => "thread/start" {
params: v2::ThreadStartParams,
response: v2::ThreadStartResponse,
},
ThreadResume => "thread/resume" {
params: v2::ThreadResumeParams,
response: v2::ThreadResumeResponse,
},
ThreadArchive => "thread/archive" {
params: v2::ThreadArchiveParams,
response: v2::ThreadArchiveResponse,
},
ThreadList => "thread/list" {
params: v2::ThreadListParams,
response: v2::ThreadListResponse,
},
ThreadCompact => "thread/compact" {
params: v2::ThreadCompactParams,
response: v2::ThreadCompactResponse,
},
TurnStart => "turn/start" {
params: v2::TurnStartParams,
response: v2::TurnStartResponse,
},
TurnInterrupt => "turn/interrupt" {
params: v2::TurnInterruptParams,
response: v2::TurnInterruptResponse,
},
ReviewStart => "review/start" {
params: v2::ReviewStartParams,
response: v2::TurnStartResponse,
#[serde(rename = "model/list")]
#[ts(rename = "model/list")]
ListModels {
params: v2::ListModelsParams,
response: v2::ListModelsResponse,
},
ModelList => "model/list" {
params: v2::ModelListParams,
response: v2::ModelListResponse,
},
LoginAccount => "account/login/start" {
#[serde(rename = "account/login")]
#[ts(rename = "account/login")]
LoginAccount {
params: v2::LoginAccountParams,
response: v2::LoginAccountResponse,
},
CancelLoginAccount => "account/login/cancel" {
params: v2::CancelLoginAccountParams,
response: v2::CancelLoginAccountResponse,
},
LogoutAccount => "account/logout" {
#[serde(rename = "account/logout")]
#[ts(rename = "account/logout")]
LogoutAccount {
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: v2::LogoutAccountResponse,
},
GetAccountRateLimits => "account/rateLimits/read" {
#[serde(rename = "account/rateLimits/read")]
#[ts(rename = "account/rateLimits/read")]
GetAccountRateLimits {
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: v2::GetAccountRateLimitsResponse,
},
FeedbackUpload => "feedback/upload" {
params: v2::FeedbackUploadParams,
response: v2::FeedbackUploadResponse,
#[serde(rename = "feedback/upload")]
#[ts(rename = "feedback/upload")]
UploadFeedback {
params: v2::UploadFeedbackParams,
response: v2::UploadFeedbackResponse,
},
GetAccount => "account/read" {
params: v2::GetAccountParams,
#[serde(rename = "account/read")]
#[ts(rename = "account/read")]
GetAccount {
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: v2::GetAccountResponse,
},
/// DEPRECATED APIs below
Initialize {
params: v1::InitializeParams,
response: v1::InitializeResponse,
},
NewConversation {
params: v1::NewConversationParams,
response: v1::NewConversationResponse,
@@ -224,7 +188,6 @@ client_request_definitions! {
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: v1::LoginChatGptResponse,
},
// DEPRECATED in favor of CancelLoginAccount
CancelLoginChatGpt {
params: v1::CancelLoginChatGptParams,
response: v1::CancelLoginChatGptResponse,
@@ -233,7 +196,6 @@ client_request_definitions! {
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
response: v1::LogoutChatGptResponse,
},
/// DEPRECATED in favor of GetAccount
GetAuthStatus {
params: v1::GetAuthStatusParams,
response: v1::GetAuthStatusResponse,
@@ -273,36 +235,34 @@ macro_rules! server_request_definitions {
(
$(
$(#[$variant_meta:meta])*
$variant:ident $(=> $wire:literal)? {
params: $params:ty,
response: $response:ty,
}
$variant:ident
),* $(,)?
) => {
/// Request initiated from the server and sent to the client.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(tag = "method", rename_all = "camelCase")]
pub enum ServerRequest {
$(
$(#[$variant_meta])*
$(#[serde(rename = $wire)] #[ts(rename = $wire)])?
$variant {
#[serde(rename = "id")]
request_id: RequestId,
params: $params,
},
)*
}
paste! {
/// Request initiated from the server and sent to the client.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(tag = "method", rename_all = "camelCase")]
pub enum ServerRequest {
$(
$(#[$variant_meta])*
$variant {
#[serde(rename = "id")]
request_id: RequestId,
params: [<$variant Params>],
},
)*
}
#[derive(Debug, Clone, PartialEq, JsonSchema)]
pub enum ServerRequestPayload {
$( $variant($params), )*
}
#[derive(Debug, Clone, PartialEq, JsonSchema)]
pub enum ServerRequestPayload {
$( $variant([<$variant Params>]), )*
}
impl ServerRequestPayload {
pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
match self {
$(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
impl ServerRequestPayload {
pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
match self {
$(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
}
}
}
}
@@ -310,113 +270,19 @@ macro_rules! server_request_definitions {
pub fn export_server_responses(
out_dir: &::std::path::Path,
) -> ::std::result::Result<(), ::ts_rs::ExportError> {
$(
<$response as ::ts_rs::TS>::export_all_to(out_dir)?;
)*
paste! {
$(<[<$variant Response>] as ::ts_rs::TS>::export_all_to(out_dir)?;)*
}
Ok(())
}
#[allow(clippy::vec_init_then_push)]
pub fn export_server_response_schemas(
out_dir: &Path,
) -> ::anyhow::Result<Vec<GeneratedSchema>> {
let mut schemas = Vec::new();
$(
schemas.push(crate::export::write_json_schema::<$response>(
out_dir,
concat!(stringify!($variant), "Response"),
)?);
)*
Ok(schemas)
}
#[allow(clippy::vec_init_then_push)]
pub fn export_server_param_schemas(
out_dir: &Path,
) -> ::anyhow::Result<Vec<GeneratedSchema>> {
let mut schemas = Vec::new();
$(
schemas.push(crate::export::write_json_schema::<$params>(
out_dir,
concat!(stringify!($variant), "Params"),
)?);
)*
Ok(schemas)
}
};
}
/// Generates `ServerNotification` enum and helpers, including a JSON Schema
/// exporter for each notification.
macro_rules! server_notification_definitions {
(
$(
$(#[$variant_meta:meta])*
$variant:ident $(=> $wire:literal)? ( $payload:ty )
),* $(,)?
) => {
/// Notification sent from the server to the client.
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS, Display)]
#[serde(tag = "method", content = "params", rename_all = "camelCase")]
#[strum(serialize_all = "camelCase")]
pub enum ServerNotification {
$(
$(#[$variant_meta])*
$(#[serde(rename = $wire)] #[ts(rename = $wire)] #[strum(serialize = $wire)])?
$variant($payload),
)*
}
impl ServerNotification {
pub fn to_params(self) -> Result<serde_json::Value, serde_json::Error> {
match self {
$(Self::$variant(params) => serde_json::to_value(params),)*
}
}
}
impl TryFrom<JSONRPCNotification> for ServerNotification {
type Error = serde_json::Error;
fn try_from(value: JSONRPCNotification) -> Result<Self, serde_json::Error> {
serde_json::from_value(serde_json::to_value(value)?)
}
}
#[allow(clippy::vec_init_then_push)]
pub fn export_server_notification_schemas(
out_dir: &::std::path::Path,
) -> ::anyhow::Result<Vec<GeneratedSchema>> {
let mut schemas = Vec::new();
$(schemas.push(crate::export::write_json_schema::<$payload>(out_dir, stringify!($payload))?);)*
Ok(schemas)
}
};
}
/// Notifications sent from the client to the server.
macro_rules! client_notification_definitions {
(
$(
$(#[$variant_meta:meta])*
$variant:ident $( ( $payload:ty ) )?
),* $(,)?
) => {
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS, Display)]
#[serde(tag = "method", content = "params", rename_all = "camelCase")]
#[strum(serialize_all = "camelCase")]
pub enum ClientNotification {
$(
$(#[$variant_meta])*
$variant $( ( $payload ) )?,
)*
}
pub fn export_client_notification_schemas(
_out_dir: &::std::path::Path,
) -> ::anyhow::Result<Vec<GeneratedSchema>> {
let schemas = Vec::new();
$( $(schemas.push(crate::export::write_json_schema::<$payload>(_out_dir, stringify!($payload))?);)? )*
Ok(schemas)
) -> ::anyhow::Result<()> {
paste! {
$(crate::export::write_json_schema::<[<$variant Response>]>(out_dir, stringify!([<$variant Response>]))?;)*
}
Ok(())
}
};
}
@@ -430,34 +296,49 @@ impl TryFrom<JSONRPCRequest> for ServerRequest {
}
server_request_definitions! {
/// NEW APIs
/// Sent when approval is requested for a specific command execution.
/// This request is used for Turns started via turn/start.
CommandExecutionRequestApproval => "item/commandExecution/requestApproval" {
params: v2::CommandExecutionRequestApprovalParams,
response: v2::CommandExecutionRequestApprovalResponse,
},
/// Sent when approval is requested for a specific file change.
/// This request is used for Turns started via turn/start.
FileChangeRequestApproval => "item/fileChange/requestApproval" {
params: v2::FileChangeRequestApprovalParams,
response: v2::FileChangeRequestApprovalResponse,
},
/// DEPRECATED APIs below
/// Request to approve a patch.
/// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
ApplyPatchApproval {
params: v1::ApplyPatchApprovalParams,
response: v1::ApplyPatchApprovalResponse,
},
ApplyPatchApproval,
/// Request to exec a command.
/// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
ExecCommandApproval {
params: v1::ExecCommandApprovalParams,
response: v1::ExecCommandApprovalResponse,
},
ExecCommandApproval,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct ApplyPatchApprovalParams {
pub conversation_id: ConversationId,
/// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
/// and [codex_core::protocol::PatchApplyEndEvent].
pub call_id: String,
pub file_changes: HashMap<PathBuf, FileChange>,
/// Optional explanatory reason (e.g. request for extra write access).
pub reason: Option<String>,
/// When set, the agent is asking the user to allow writes under this root
/// for the remainder of the session (unclear if this is honored today).
pub grant_root: Option<PathBuf>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct ExecCommandApprovalParams {
pub conversation_id: ConversationId,
/// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
/// and [codex_core::protocol::ExecCommandEndEvent].
pub call_id: String,
pub command: Vec<String>,
pub cwd: PathBuf,
pub reason: Option<String>,
pub risk: Option<SandboxCommandAssessment>,
pub parsed_cmd: Vec<ParsedCommand>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
pub struct ExecCommandApprovalResponse {
pub decision: ReviewDecision,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
pub struct ApplyPatchApprovalResponse {
pub decision: ReviewDecision,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
@@ -485,40 +366,52 @@ pub struct FuzzyFileSearchResponse {
pub files: Vec<FuzzyFileSearchResult>,
}
server_notification_definitions! {
/// Notification sent from the server to the client.
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS, Display)]
#[serde(tag = "method", content = "params", rename_all = "camelCase")]
#[strum(serialize_all = "camelCase")]
pub enum ServerNotification {
/// NEW NOTIFICATIONS
Error => "error" (v2::ErrorNotification),
ThreadStarted => "thread/started" (v2::ThreadStartedNotification),
TurnStarted => "turn/started" (v2::TurnStartedNotification),
TurnCompleted => "turn/completed" (v2::TurnCompletedNotification),
ItemStarted => "item/started" (v2::ItemStartedNotification),
ItemCompleted => "item/completed" (v2::ItemCompletedNotification),
AgentMessageDelta => "item/agentMessage/delta" (v2::AgentMessageDeltaNotification),
CommandExecutionOutputDelta => "item/commandExecution/outputDelta" (v2::CommandExecutionOutputDeltaNotification),
McpToolCallProgress => "item/mcpToolCall/progress" (v2::McpToolCallProgressNotification),
AccountUpdated => "account/updated" (v2::AccountUpdatedNotification),
AccountRateLimitsUpdated => "account/rateLimits/updated" (v2::AccountRateLimitsUpdatedNotification),
ReasoningSummaryTextDelta => "item/reasoning/summaryTextDelta" (v2::ReasoningSummaryTextDeltaNotification),
ReasoningSummaryPartAdded => "item/reasoning/summaryPartAdded" (v2::ReasoningSummaryPartAddedNotification),
ReasoningTextDelta => "item/reasoning/textDelta" (v2::ReasoningTextDeltaNotification),
/// Notifies the user of world-writable directories on Windows, which cannot be protected by the sandbox.
WindowsWorldWritableWarning => "windows/worldWritableWarning" (v2::WindowsWorldWritableWarningNotification),
#[serde(rename = "account/login/completed")]
#[ts(rename = "account/login/completed")]
#[strum(serialize = "account/login/completed")]
AccountLoginCompleted(v2::AccountLoginCompletedNotification),
#[serde(rename = "account/rateLimits/updated")]
#[ts(rename = "account/rateLimits/updated")]
#[strum(serialize = "account/rateLimits/updated")]
AccountRateLimitsUpdated(RateLimitSnapshot),
/// DEPRECATED NOTIFICATIONS below
/// Authentication status changed
AuthStatusChange(v1::AuthStatusChangeNotification),
/// Deprecated: use `account/login/completed` instead.
/// ChatGPT login flow completed
LoginChatGptComplete(v1::LoginChatGptCompleteNotification),
/// The special session configured event for a new or resumed conversation.
SessionConfigured(v1::SessionConfiguredNotification),
}
client_notification_definitions! {
impl ServerNotification {
pub fn to_params(self) -> Result<serde_json::Value, serde_json::Error> {
match self {
ServerNotification::AccountRateLimitsUpdated(params) => serde_json::to_value(params),
ServerNotification::AuthStatusChange(params) => serde_json::to_value(params),
ServerNotification::LoginChatGptComplete(params) => serde_json::to_value(params),
ServerNotification::SessionConfigured(params) => serde_json::to_value(params),
}
}
}
impl TryFrom<JSONRPCNotification> for ServerNotification {
type Error = serde_json::Error;
fn try_from(value: JSONRPCNotification) -> Result<Self, Self::Error> {
serde_json::from_value(serde_json::to_value(value)?)
}
}
/// Notification sent from the client to the server.
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS, Display)]
#[serde(tag = "method", content = "params", rename_all = "camelCase")]
#[strum(serialize_all = "camelCase")]
pub enum ClientNotification {
Initialized,
}
@@ -526,20 +419,17 @@ client_notification_definitions! {
mod tests {
use super::*;
use anyhow::Result;
use codex_protocol::ConversationId;
use codex_protocol::account::PlanType;
use codex_protocol::parse_command::ParsedCommand;
use codex_protocol::protocol::AskForApproval;
use pretty_assertions::assert_eq;
use serde_json::json;
use std::path::PathBuf;
#[test]
fn serialize_new_conversation() -> Result<()> {
let request = ClientRequest::NewConversation {
request_id: RequestId::Integer(42),
params: v1::NewConversationParams {
model: Some("gpt-5.1-codex-max".to_string()),
model: Some("gpt-5-codex".to_string()),
model_provider: None,
profile: None,
cwd: None,
@@ -557,7 +447,7 @@ mod tests {
"method": "newConversation",
"id": 42,
"params": {
"model": "gpt-5.1-codex-max",
"model": "gpt-5-codex",
"modelProvider": null,
"profile": null,
"cwd": null,
@@ -612,7 +502,7 @@ mod tests {
#[test]
fn serialize_server_request() -> Result<()> {
let conversation_id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
let params = v1::ExecCommandApprovalParams {
let params = ExecCommandApprovalParams {
conversation_id,
call_id: "call-42".to_string(),
command: vec!["echo".to_string(), "hello".to_string()],
@@ -681,7 +571,7 @@ mod tests {
};
assert_eq!(
json!({
"method": "account/login/start",
"method": "account/login",
"id": 2,
"params": {
"type": "apiKey",
@@ -697,11 +587,11 @@ mod tests {
fn serialize_account_login_chatgpt() -> Result<()> {
let request = ClientRequest::LoginAccount {
request_id: RequestId::Integer(3),
params: v2::LoginAccountParams::Chatgpt,
params: v2::LoginAccountParams::ChatGpt,
};
assert_eq!(
json!({
"method": "account/login/start",
"method": "account/login",
"id": 3,
"params": {
"type": "chatgpt"
@@ -732,17 +622,12 @@ mod tests {
fn serialize_get_account() -> Result<()> {
let request = ClientRequest::GetAccount {
request_id: RequestId::Integer(5),
params: v2::GetAccountParams {
refresh_token: false,
},
params: None,
};
assert_eq!(
json!({
"method": "account/read",
"id": 5,
"params": {
"refreshToken": false
}
}),
serde_json::to_value(&request)?,
);
@@ -751,16 +636,19 @@ mod tests {
#[test]
fn account_serializes_fields_in_camel_case() -> Result<()> {
let api_key = v2::Account::ApiKey {};
let api_key = v2::Account::ApiKey {
api_key: "secret".to_string(),
};
assert_eq!(
json!({
"type": "apiKey",
"apiKey": "secret",
}),
serde_json::to_value(&api_key)?,
);
let chatgpt = v2::Account::Chatgpt {
email: "user@example.com".to_string(),
let chatgpt = v2::Account::ChatGpt {
email: Some("user@example.com".to_string()),
plan_type: PlanType::Plus,
};
assert_eq!(
@@ -777,16 +665,16 @@ mod tests {
#[test]
fn serialize_list_models() -> Result<()> {
let request = ClientRequest::ModelList {
let request = ClientRequest::ListModels {
request_id: RequestId::Integer(6),
params: v2::ModelListParams::default(),
params: v2::ListModelsParams::default(),
};
assert_eq!(
json!({
"method": "model/list",
"id": 6,
"params": {
"limit": null,
"pageSize": null,
"cursor": null
}
}),

View File

@@ -2,6 +2,5 @@
// Exposes protocol pieces used by `lib.rs` via `pub use protocol::common::*;`.
pub mod common;
pub mod thread_history;
pub mod v1;
pub mod v2;

View File

@@ -1,409 +0,0 @@
use crate::protocol::v2::ThreadItem;
use crate::protocol::v2::Turn;
use crate::protocol::v2::TurnStatus;
use crate::protocol::v2::UserInput;
use codex_protocol::protocol::AgentReasoningEvent;
use codex_protocol::protocol::AgentReasoningRawContentEvent;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::TurnAbortedEvent;
use codex_protocol::protocol::UserMessageEvent;
/// Convert persisted [`EventMsg`] entries into a sequence of [`Turn`] values.
///
/// The purpose of this is to convert the EventMsgs persisted in a rollout file
/// into a sequence of Turns and ThreadItems, which allows the client to render
/// the historical messages when resuming a thread.
pub fn build_turns_from_event_msgs(events: &[EventMsg]) -> Vec<Turn> {
let mut builder = ThreadHistoryBuilder::new();
for event in events {
builder.handle_event(event);
}
builder.finish()
}
struct ThreadHistoryBuilder {
turns: Vec<Turn>,
current_turn: Option<PendingTurn>,
next_turn_index: i64,
next_item_index: i64,
}
impl ThreadHistoryBuilder {
fn new() -> Self {
Self {
turns: Vec::new(),
current_turn: None,
next_turn_index: 1,
next_item_index: 1,
}
}
fn finish(mut self) -> Vec<Turn> {
self.finish_current_turn();
self.turns
}
/// This function should handle all EventMsg variants that can be persisted in a rollout file.
/// See `should_persist_event_msg` in `codex-rs/core/rollout/policy.rs`.
fn handle_event(&mut self, event: &EventMsg) {
match event {
EventMsg::UserMessage(payload) => self.handle_user_message(payload),
EventMsg::AgentMessage(payload) => self.handle_agent_message(payload.message.clone()),
EventMsg::AgentReasoning(payload) => self.handle_agent_reasoning(payload),
EventMsg::AgentReasoningRawContent(payload) => {
self.handle_agent_reasoning_raw_content(payload)
}
EventMsg::TokenCount(_) => {}
EventMsg::EnteredReviewMode(_) => {}
EventMsg::ExitedReviewMode(_) => {}
EventMsg::UndoCompleted(_) => {}
EventMsg::TurnAborted(payload) => self.handle_turn_aborted(payload),
_ => {}
}
}
fn handle_user_message(&mut self, payload: &UserMessageEvent) {
self.finish_current_turn();
let mut turn = self.new_turn();
let id = self.next_item_id();
let content = self.build_user_inputs(payload);
turn.items.push(ThreadItem::UserMessage { id, content });
self.current_turn = Some(turn);
}
fn handle_agent_message(&mut self, text: String) {
if text.is_empty() {
return;
}
let id = self.next_item_id();
self.ensure_turn()
.items
.push(ThreadItem::AgentMessage { id, text });
}
fn handle_agent_reasoning(&mut self, payload: &AgentReasoningEvent) {
if payload.text.is_empty() {
return;
}
// If the last item is a reasoning item, add the new text to the summary.
if let Some(ThreadItem::Reasoning { summary, .. }) = self.ensure_turn().items.last_mut() {
summary.push(payload.text.clone());
return;
}
// Otherwise, create a new reasoning item.
let id = self.next_item_id();
self.ensure_turn().items.push(ThreadItem::Reasoning {
id,
summary: vec![payload.text.clone()],
content: Vec::new(),
});
}
fn handle_agent_reasoning_raw_content(&mut self, payload: &AgentReasoningRawContentEvent) {
if payload.text.is_empty() {
return;
}
// If the last item is a reasoning item, add the new text to the content.
if let Some(ThreadItem::Reasoning { content, .. }) = self.ensure_turn().items.last_mut() {
content.push(payload.text.clone());
return;
}
// Otherwise, create a new reasoning item.
let id = self.next_item_id();
self.ensure_turn().items.push(ThreadItem::Reasoning {
id,
summary: Vec::new(),
content: vec![payload.text.clone()],
});
}
fn handle_turn_aborted(&mut self, _payload: &TurnAbortedEvent) {
let Some(turn) = self.current_turn.as_mut() else {
return;
};
turn.status = TurnStatus::Interrupted;
}
fn finish_current_turn(&mut self) {
if let Some(turn) = self.current_turn.take() {
if turn.items.is_empty() {
return;
}
self.turns.push(turn.into());
}
}
fn new_turn(&mut self) -> PendingTurn {
PendingTurn {
id: self.next_turn_id(),
items: Vec::new(),
status: TurnStatus::Completed,
}
}
fn ensure_turn(&mut self) -> &mut PendingTurn {
if self.current_turn.is_none() {
let turn = self.new_turn();
return self.current_turn.insert(turn);
}
if let Some(turn) = self.current_turn.as_mut() {
return turn;
}
unreachable!("current turn must exist after initialization");
}
fn next_turn_id(&mut self) -> String {
let id = format!("turn-{}", self.next_turn_index);
self.next_turn_index += 1;
id
}
fn next_item_id(&mut self) -> String {
let id = format!("item-{}", self.next_item_index);
self.next_item_index += 1;
id
}
fn build_user_inputs(&self, payload: &UserMessageEvent) -> Vec<UserInput> {
let mut content = Vec::new();
if !payload.message.trim().is_empty() {
content.push(UserInput::Text {
text: payload.message.clone(),
});
}
if let Some(images) = &payload.images {
for image in images {
content.push(UserInput::Image { url: image.clone() });
}
}
content
}
}
struct PendingTurn {
id: String,
items: Vec<ThreadItem>,
status: TurnStatus,
}
impl From<PendingTurn> for Turn {
fn from(value: PendingTurn) -> Self {
Self {
id: value.id,
items: value.items,
status: value.status,
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use codex_protocol::protocol::AgentMessageEvent;
use codex_protocol::protocol::AgentReasoningEvent;
use codex_protocol::protocol::AgentReasoningRawContentEvent;
use codex_protocol::protocol::TurnAbortReason;
use codex_protocol::protocol::TurnAbortedEvent;
use codex_protocol::protocol::UserMessageEvent;
use pretty_assertions::assert_eq;
#[test]
fn builds_multiple_turns_with_reasoning_items() {
let events = vec![
EventMsg::UserMessage(UserMessageEvent {
message: "First turn".into(),
images: Some(vec!["https://example.com/one.png".into()]),
}),
EventMsg::AgentMessage(AgentMessageEvent {
message: "Hi there".into(),
}),
EventMsg::AgentReasoning(AgentReasoningEvent {
text: "thinking".into(),
}),
EventMsg::AgentReasoningRawContent(AgentReasoningRawContentEvent {
text: "full reasoning".into(),
}),
EventMsg::UserMessage(UserMessageEvent {
message: "Second turn".into(),
images: None,
}),
EventMsg::AgentMessage(AgentMessageEvent {
message: "Reply two".into(),
}),
];
let turns = build_turns_from_event_msgs(&events);
assert_eq!(turns.len(), 2);
let first = &turns[0];
assert_eq!(first.id, "turn-1");
assert_eq!(first.status, TurnStatus::Completed);
assert_eq!(first.items.len(), 3);
assert_eq!(
first.items[0],
ThreadItem::UserMessage {
id: "item-1".into(),
content: vec![
UserInput::Text {
text: "First turn".into(),
},
UserInput::Image {
url: "https://example.com/one.png".into(),
}
],
}
);
assert_eq!(
first.items[1],
ThreadItem::AgentMessage {
id: "item-2".into(),
text: "Hi there".into(),
}
);
assert_eq!(
first.items[2],
ThreadItem::Reasoning {
id: "item-3".into(),
summary: vec!["thinking".into()],
content: vec!["full reasoning".into()],
}
);
let second = &turns[1];
assert_eq!(second.id, "turn-2");
assert_eq!(second.items.len(), 2);
assert_eq!(
second.items[0],
ThreadItem::UserMessage {
id: "item-4".into(),
content: vec![UserInput::Text {
text: "Second turn".into()
}],
}
);
assert_eq!(
second.items[1],
ThreadItem::AgentMessage {
id: "item-5".into(),
text: "Reply two".into(),
}
);
}
#[test]
fn splits_reasoning_when_interleaved() {
let events = vec![
EventMsg::UserMessage(UserMessageEvent {
message: "Turn start".into(),
images: None,
}),
EventMsg::AgentReasoning(AgentReasoningEvent {
text: "first summary".into(),
}),
EventMsg::AgentReasoningRawContent(AgentReasoningRawContentEvent {
text: "first content".into(),
}),
EventMsg::AgentMessage(AgentMessageEvent {
message: "interlude".into(),
}),
EventMsg::AgentReasoning(AgentReasoningEvent {
text: "second summary".into(),
}),
];
let turns = build_turns_from_event_msgs(&events);
assert_eq!(turns.len(), 1);
let turn = &turns[0];
assert_eq!(turn.items.len(), 4);
assert_eq!(
turn.items[1],
ThreadItem::Reasoning {
id: "item-2".into(),
summary: vec!["first summary".into()],
content: vec!["first content".into()],
}
);
assert_eq!(
turn.items[3],
ThreadItem::Reasoning {
id: "item-4".into(),
summary: vec!["second summary".into()],
content: Vec::new(),
}
);
}
#[test]
fn marks_turn_as_interrupted_when_aborted() {
let events = vec![
EventMsg::UserMessage(UserMessageEvent {
message: "Please do the thing".into(),
images: None,
}),
EventMsg::AgentMessage(AgentMessageEvent {
message: "Working...".into(),
}),
EventMsg::TurnAborted(TurnAbortedEvent {
reason: TurnAbortReason::Replaced,
}),
EventMsg::UserMessage(UserMessageEvent {
message: "Let's try again".into(),
images: None,
}),
EventMsg::AgentMessage(AgentMessageEvent {
message: "Second attempt complete.".into(),
}),
];
let turns = build_turns_from_event_msgs(&events);
assert_eq!(turns.len(), 2);
let first_turn = &turns[0];
assert_eq!(first_turn.status, TurnStatus::Interrupted);
assert_eq!(first_turn.items.len(), 2);
assert_eq!(
first_turn.items[0],
ThreadItem::UserMessage {
id: "item-1".into(),
content: vec![UserInput::Text {
text: "Please do the thing".into()
}],
}
);
assert_eq!(
first_turn.items[1],
ThreadItem::AgentMessage {
id: "item-2".into(),
text: "Working...".into(),
}
);
let second_turn = &turns[1];
assert_eq!(second_turn.status, TurnStatus::Completed);
assert_eq!(second_turn.items.len(), 2);
assert_eq!(
second_turn.items[0],
ThreadItem::UserMessage {
id: "item-3".into(),
content: vec![UserInput::Text {
text: "Let's try again".into()
}],
}
);
assert_eq!(
second_turn.items[1],
ThreadItem::AgentMessage {
id: "item-4".into(),
text: "Second attempt complete.".into(),
}
);
}
}

View File

@@ -8,14 +8,9 @@ use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::config_types::SandboxMode;
use codex_protocol::config_types::Verbosity;
use codex_protocol::models::ResponseItem;
use codex_protocol::parse_command::ParsedCommand;
use codex_protocol::protocol::AskForApproval;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::FileChange;
use codex_protocol::protocol::ReviewDecision;
use codex_protocol::protocol::SandboxCommandAssessment;
use codex_protocol::protocol::SandboxPolicy;
use codex_protocol::protocol::SessionSource;
use codex_protocol::protocol::TurnAbortReason;
use schemars::JsonSchema;
use serde::Deserialize;
@@ -118,18 +113,6 @@ pub struct ConversationSummary {
pub preview: String,
pub timestamp: Option<String>,
pub model_provider: String,
pub cwd: PathBuf,
pub cli_version: String,
pub source: SessionSource,
pub git_info: Option<ConversationGitInfo>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "snake_case")]
pub struct ConversationGitInfo {
pub sha: Option<String>,
pub branch: Option<String>,
pub origin_url: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
@@ -195,46 +178,6 @@ pub struct GitDiffToRemoteResponse {
pub diff: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct ApplyPatchApprovalParams {
pub conversation_id: ConversationId,
/// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
/// and [codex_core::protocol::PatchApplyEndEvent].
pub call_id: String,
pub file_changes: HashMap<PathBuf, FileChange>,
/// Optional explanatory reason (e.g. request for extra write access).
pub reason: Option<String>,
/// When set, the agent is asking the user to allow writes under this root
/// for the remainder of the session (unclear if this is honored today).
pub grant_root: Option<PathBuf>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct ApplyPatchApprovalResponse {
pub decision: ReviewDecision,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct ExecCommandApprovalParams {
pub conversation_id: ConversationId,
/// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
/// and [codex_core::protocol::ExecCommandEndEvent].
pub call_id: String,
pub command: Vec<String>,
pub cwd: PathBuf,
pub reason: Option<String>,
pub risk: Option<SandboxCommandAssessment>,
pub parsed_cmd: Vec<ParsedCommand>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
pub struct ExecCommandApprovalResponse {
pub decision: ReviewDecision,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct CancelLoginChatGptParams {
@@ -431,9 +374,10 @@ pub enum InputItem {
LocalImage { path: PathBuf },
}
// Deprecated notifications (v1)
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
/// Deprecated in favor of AccountLoginCompletedNotification.
pub struct LoginChatGptCompleteNotification {
#[schemars(with = "String")]
pub login_id: Uuid,
@@ -456,7 +400,6 @@ pub struct SessionConfiguredNotification {
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
/// Deprecated notification. Use AccountUpdatedNotification instead.
pub struct AuthStatusChangeNotification {
pub auth_method: Option<AuthMode>,
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,16 +0,0 @@
[package]
name = "codex-app-server-test-client"
version = { workspace = true }
edition = "2024"
[lints]
workspace = true
[dependencies]
anyhow = { workspace = true }
clap = { workspace = true, features = ["derive", "env"] }
codex-app-server-protocol = { workspace = true }
codex-protocol = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }
uuid = { workspace = true, features = ["v4"] }

View File

@@ -1,2 +0,0 @@
# App Server Test Client
Exercises simple `codex app-server` flows end-to-end, logging JSON-RPC messages sent between client and server to stdout.

View File

@@ -1,809 +0,0 @@
use std::collections::VecDeque;
use std::io::BufRead;
use std::io::BufReader;
use std::io::Write;
use std::process::Child;
use std::process::ChildStdin;
use std::process::ChildStdout;
use std::process::Command;
use std::process::Stdio;
use std::thread;
use std::time::Duration;
use anyhow::Context;
use anyhow::Result;
use anyhow::bail;
use clap::Parser;
use clap::Subcommand;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
use codex_app_server_protocol::ApprovalDecision;
use codex_app_server_protocol::AskForApproval;
use codex_app_server_protocol::ClientInfo;
use codex_app_server_protocol::ClientRequest;
use codex_app_server_protocol::CommandExecutionRequestAcceptSettings;
use codex_app_server_protocol::CommandExecutionRequestApprovalParams;
use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
use codex_app_server_protocol::FileChangeRequestApprovalParams;
use codex_app_server_protocol::FileChangeRequestApprovalResponse;
use codex_app_server_protocol::GetAccountRateLimitsResponse;
use codex_app_server_protocol::InitializeParams;
use codex_app_server_protocol::InitializeResponse;
use codex_app_server_protocol::InputItem;
use codex_app_server_protocol::JSONRPCMessage;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCRequest;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::LoginChatGptCompleteNotification;
use codex_app_server_protocol::LoginChatGptResponse;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::NewConversationResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SandboxPolicy;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserMessageResponse;
use codex_app_server_protocol::ServerNotification;
use codex_app_server_protocol::ServerRequest;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::TurnStartParams;
use codex_app_server_protocol::TurnStartResponse;
use codex_app_server_protocol::TurnStatus;
use codex_app_server_protocol::UserInput as V2UserInput;
use codex_protocol::ConversationId;
use codex_protocol::protocol::Event;
use codex_protocol::protocol::EventMsg;
use serde::Serialize;
use serde::de::DeserializeOwned;
use serde_json::Value;
use uuid::Uuid;
/// Minimal launcher that initializes the Codex app-server and logs the handshake.
#[derive(Parser)]
#[command(author = "Codex", version, about = "Bootstrap Codex app-server", long_about = None)]
struct Cli {
/// Path to the `codex` CLI binary.
#[arg(long, env = "CODEX_BIN", default_value = "codex")]
codex_bin: String,
#[command(subcommand)]
command: CliCommand,
}
#[derive(Subcommand)]
enum CliCommand {
/// Send a user message through the Codex app-server.
SendMessage {
/// User message to send to Codex.
#[arg()]
user_message: String,
},
/// Send a user message through the app-server V2 thread/turn APIs.
SendMessageV2 {
/// User message to send to Codex.
#[arg()]
user_message: String,
},
/// Start a V2 turn that elicits an ExecCommand approval.
#[command(name = "trigger-cmd-approval")]
TriggerCmdApproval {
/// Optional prompt; defaults to a simple python command.
#[arg()]
user_message: Option<String>,
},
/// Start a V2 turn that elicits an ApplyPatch approval.
#[command(name = "trigger-patch-approval")]
TriggerPatchApproval {
/// Optional prompt; defaults to creating a file via apply_patch.
#[arg()]
user_message: Option<String>,
},
/// Start a V2 turn that should not elicit an ExecCommand approval.
#[command(name = "no-trigger-cmd-approval")]
NoTriggerCmdApproval,
/// Trigger the ChatGPT login flow and wait for completion.
TestLogin,
/// Fetch the current account rate limits from the Codex app-server.
GetAccountRateLimits,
}
fn main() -> Result<()> {
let Cli { codex_bin, command } = Cli::parse();
match command {
CliCommand::SendMessage { user_message } => send_message(codex_bin, user_message),
CliCommand::SendMessageV2 { user_message } => send_message_v2(codex_bin, user_message),
CliCommand::TriggerCmdApproval { user_message } => {
trigger_cmd_approval(codex_bin, user_message)
}
CliCommand::TriggerPatchApproval { user_message } => {
trigger_patch_approval(codex_bin, user_message)
}
CliCommand::NoTriggerCmdApproval => no_trigger_cmd_approval(codex_bin),
CliCommand::TestLogin => test_login(codex_bin),
CliCommand::GetAccountRateLimits => get_account_rate_limits(codex_bin),
}
}
fn send_message(codex_bin: String, user_message: String) -> Result<()> {
let mut client = CodexClient::spawn(codex_bin)?;
let initialize = client.initialize()?;
println!("< initialize response: {initialize:?}");
let conversation = client.new_conversation()?;
println!("< newConversation response: {conversation:?}");
let subscription = client.add_conversation_listener(&conversation.conversation_id)?;
println!("< addConversationListener response: {subscription:?}");
let send_response = client.send_user_message(&conversation.conversation_id, &user_message)?;
println!("< sendUserMessage response: {send_response:?}");
client.stream_conversation(&conversation.conversation_id)?;
client.remove_conversation_listener(subscription.subscription_id)?;
Ok(())
}
fn send_message_v2(codex_bin: String, user_message: String) -> Result<()> {
send_message_v2_with_policies(codex_bin, user_message, None, None)
}
fn trigger_cmd_approval(codex_bin: String, user_message: Option<String>) -> Result<()> {
let default_prompt =
"Run `touch /tmp/should-trigger-approval` so I can confirm the file exists.";
let message = user_message.unwrap_or_else(|| default_prompt.to_string());
send_message_v2_with_policies(
codex_bin,
message,
Some(AskForApproval::OnRequest),
Some(SandboxPolicy::ReadOnly),
)
}
fn trigger_patch_approval(codex_bin: String, user_message: Option<String>) -> Result<()> {
let default_prompt =
"Create a file named APPROVAL_DEMO.txt containing a short hello message using apply_patch.";
let message = user_message.unwrap_or_else(|| default_prompt.to_string());
send_message_v2_with_policies(
codex_bin,
message,
Some(AskForApproval::OnRequest),
Some(SandboxPolicy::ReadOnly),
)
}
fn no_trigger_cmd_approval(codex_bin: String) -> Result<()> {
let prompt = "Run `touch should_not_trigger_approval.txt`";
send_message_v2_with_policies(codex_bin, prompt.to_string(), None, None)
}
fn send_message_v2_with_policies(
codex_bin: String,
user_message: String,
approval_policy: Option<AskForApproval>,
sandbox_policy: Option<SandboxPolicy>,
) -> Result<()> {
let mut client = CodexClient::spawn(codex_bin)?;
let initialize = client.initialize()?;
println!("< initialize response: {initialize:?}");
let thread_response = client.thread_start(ThreadStartParams::default())?;
println!("< thread/start response: {thread_response:?}");
let mut turn_params = TurnStartParams {
thread_id: thread_response.thread.id.clone(),
input: vec![V2UserInput::Text { text: user_message }],
..Default::default()
};
turn_params.approval_policy = approval_policy;
turn_params.sandbox_policy = sandbox_policy;
let turn_response = client.turn_start(turn_params)?;
println!("< turn/start response: {turn_response:?}");
client.stream_turn(&thread_response.thread.id, &turn_response.turn.id)?;
Ok(())
}
fn test_login(codex_bin: String) -> Result<()> {
let mut client = CodexClient::spawn(codex_bin)?;
let initialize = client.initialize()?;
println!("< initialize response: {initialize:?}");
let login_response = client.login_chat_gpt()?;
println!("< loginChatGpt response: {login_response:?}");
println!(
"Open the following URL in your browser to continue:\n{}",
login_response.auth_url
);
let completion = client.wait_for_login_completion(&login_response.login_id)?;
println!("< loginChatGptComplete notification: {completion:?}");
if completion.success {
println!("Login succeeded.");
Ok(())
} else {
bail!(
"login failed: {}",
completion
.error
.as_deref()
.unwrap_or("unknown error from loginChatGptComplete")
);
}
}
fn get_account_rate_limits(codex_bin: String) -> Result<()> {
let mut client = CodexClient::spawn(codex_bin)?;
let initialize = client.initialize()?;
println!("< initialize response: {initialize:?}");
let response = client.get_account_rate_limits()?;
println!("< account/rateLimits/read response: {response:?}");
Ok(())
}
struct CodexClient {
child: Child,
stdin: Option<ChildStdin>,
stdout: BufReader<ChildStdout>,
pending_notifications: VecDeque<JSONRPCNotification>,
}
impl CodexClient {
fn spawn(codex_bin: String) -> Result<Self> {
let mut codex_app_server = Command::new(&codex_bin)
.arg("app-server")
.stdin(Stdio::piped())
.stdout(Stdio::piped())
.stderr(Stdio::inherit())
.spawn()
.with_context(|| format!("failed to start `{codex_bin}` app-server"))?;
let stdin = codex_app_server
.stdin
.take()
.context("codex app-server stdin unavailable")?;
let stdout = codex_app_server
.stdout
.take()
.context("codex app-server stdout unavailable")?;
Ok(Self {
child: codex_app_server,
stdin: Some(stdin),
stdout: BufReader::new(stdout),
pending_notifications: VecDeque::new(),
})
}
fn initialize(&mut self) -> Result<InitializeResponse> {
let request_id = self.request_id();
let request = ClientRequest::Initialize {
request_id: request_id.clone(),
params: InitializeParams {
client_info: ClientInfo {
name: "codex-toy-app-server".to_string(),
title: Some("Codex Toy App Server".to_string()),
version: env!("CARGO_PKG_VERSION").to_string(),
},
},
};
self.send_request(request, request_id, "initialize")
}
fn new_conversation(&mut self) -> Result<NewConversationResponse> {
let request_id = self.request_id();
let request = ClientRequest::NewConversation {
request_id: request_id.clone(),
params: NewConversationParams::default(),
};
self.send_request(request, request_id, "newConversation")
}
fn add_conversation_listener(
&mut self,
conversation_id: &ConversationId,
) -> Result<AddConversationSubscriptionResponse> {
let request_id = self.request_id();
let request = ClientRequest::AddConversationListener {
request_id: request_id.clone(),
params: AddConversationListenerParams {
conversation_id: *conversation_id,
experimental_raw_events: false,
},
};
self.send_request(request, request_id, "addConversationListener")
}
fn remove_conversation_listener(&mut self, subscription_id: Uuid) -> Result<()> {
let request_id = self.request_id();
let request = ClientRequest::RemoveConversationListener {
request_id: request_id.clone(),
params: codex_app_server_protocol::RemoveConversationListenerParams { subscription_id },
};
self.send_request::<codex_app_server_protocol::RemoveConversationSubscriptionResponse>(
request,
request_id,
"removeConversationListener",
)?;
Ok(())
}
fn send_user_message(
&mut self,
conversation_id: &ConversationId,
message: &str,
) -> Result<SendUserMessageResponse> {
let request_id = self.request_id();
let request = ClientRequest::SendUserMessage {
request_id: request_id.clone(),
params: SendUserMessageParams {
conversation_id: *conversation_id,
items: vec![InputItem::Text {
text: message.to_string(),
}],
},
};
self.send_request(request, request_id, "sendUserMessage")
}
fn thread_start(&mut self, params: ThreadStartParams) -> Result<ThreadStartResponse> {
let request_id = self.request_id();
let request = ClientRequest::ThreadStart {
request_id: request_id.clone(),
params,
};
self.send_request(request, request_id, "thread/start")
}
fn turn_start(&mut self, params: TurnStartParams) -> Result<TurnStartResponse> {
let request_id = self.request_id();
let request = ClientRequest::TurnStart {
request_id: request_id.clone(),
params,
};
self.send_request(request, request_id, "turn/start")
}
fn login_chat_gpt(&mut self) -> Result<LoginChatGptResponse> {
let request_id = self.request_id();
let request = ClientRequest::LoginChatGpt {
request_id: request_id.clone(),
params: None,
};
self.send_request(request, request_id, "loginChatGpt")
}
fn get_account_rate_limits(&mut self) -> Result<GetAccountRateLimitsResponse> {
let request_id = self.request_id();
let request = ClientRequest::GetAccountRateLimits {
request_id: request_id.clone(),
params: None,
};
self.send_request(request, request_id, "account/rateLimits/read")
}
fn stream_conversation(&mut self, conversation_id: &ConversationId) -> Result<()> {
loop {
let notification = self.next_notification()?;
if !notification.method.starts_with("codex/event/") {
continue;
}
if let Some(event) = self.extract_event(notification, conversation_id)? {
match &event.msg {
EventMsg::AgentMessage(event) => {
println!("{}", event.message);
}
EventMsg::AgentMessageDelta(event) => {
print!("{}", event.delta);
std::io::stdout().flush().ok();
}
EventMsg::TaskComplete(event) => {
println!("\n[task complete: {event:?}]");
break;
}
EventMsg::TurnAborted(event) => {
println!("\n[turn aborted: {:?}]", event.reason);
break;
}
EventMsg::Error(event) => {
println!("[error] {event:?}");
}
_ => {
println!("[UNKNOWN EVENT] {:?}", event.msg);
}
}
}
}
Ok(())
}
fn wait_for_login_completion(
&mut self,
expected_login_id: &Uuid,
) -> Result<LoginChatGptCompleteNotification> {
loop {
let notification = self.next_notification()?;
if let Ok(server_notification) = ServerNotification::try_from(notification) {
match server_notification {
ServerNotification::LoginChatGptComplete(completion) => {
if &completion.login_id == expected_login_id {
return Ok(completion);
}
println!(
"[ignoring loginChatGptComplete for unexpected login_id: {}]",
completion.login_id
);
}
ServerNotification::AuthStatusChange(status) => {
println!("< authStatusChange notification: {status:?}");
}
ServerNotification::AccountRateLimitsUpdated(snapshot) => {
println!("< accountRateLimitsUpdated notification: {snapshot:?}");
}
ServerNotification::SessionConfigured(_) => {
// SessionConfigured notifications are unrelated to login; skip.
}
_ => {}
}
}
// Not a server notification (likely a conversation event); keep waiting.
}
}
fn stream_turn(&mut self, thread_id: &str, turn_id: &str) -> Result<()> {
loop {
let notification = self.next_notification()?;
let Ok(server_notification) = ServerNotification::try_from(notification) else {
continue;
};
match server_notification {
ServerNotification::ThreadStarted(payload) => {
if payload.thread.id == thread_id {
println!("< thread/started notification: {:?}", payload.thread);
}
}
ServerNotification::TurnStarted(payload) => {
if payload.turn.id == turn_id {
println!("< turn/started notification: {:?}", payload.turn.status);
}
}
ServerNotification::AgentMessageDelta(delta) => {
print!("{}", delta.delta);
std::io::stdout().flush().ok();
}
ServerNotification::CommandExecutionOutputDelta(delta) => {
print!("{}", delta.delta);
std::io::stdout().flush().ok();
}
ServerNotification::ItemStarted(payload) => {
println!("\n< item started: {:?}", payload.item);
}
ServerNotification::ItemCompleted(payload) => {
println!("< item completed: {:?}", payload.item);
}
ServerNotification::TurnCompleted(payload) => {
if payload.turn.id == turn_id {
println!("\n< turn/completed notification: {:?}", payload.turn.status);
if let TurnStatus::Failed { error } = &payload.turn.status {
println!("[turn error] {}", error.message);
}
break;
}
}
ServerNotification::McpToolCallProgress(payload) => {
println!("< MCP tool progress: {}", payload.message);
}
_ => {
println!("[UNKNOWN SERVER NOTIFICATION] {server_notification:?}");
}
}
}
Ok(())
}
fn extract_event(
&self,
notification: JSONRPCNotification,
conversation_id: &ConversationId,
) -> Result<Option<Event>> {
let params = notification
.params
.context("event notification missing params")?;
let mut map = match params {
Value::Object(map) => map,
other => bail!("unexpected params shape: {other:?}"),
};
let conversation_value = map
.remove("conversationId")
.context("event missing conversationId")?;
let notification_conversation: ConversationId = serde_json::from_value(conversation_value)
.context("conversationId was not a valid UUID")?;
if &notification_conversation != conversation_id {
return Ok(None);
}
let event_value = Value::Object(map);
let event: Event =
serde_json::from_value(event_value).context("failed to decode event payload")?;
Ok(Some(event))
}
fn send_request<T>(
&mut self,
request: ClientRequest,
request_id: RequestId,
method: &str,
) -> Result<T>
where
T: DeserializeOwned,
{
self.write_request(&request)?;
self.wait_for_response(request_id, method)
}
fn write_request(&mut self, request: &ClientRequest) -> Result<()> {
let request_json = serde_json::to_string(request)?;
let request_pretty = serde_json::to_string_pretty(request)?;
print_multiline_with_prefix("> ", &request_pretty);
if let Some(stdin) = self.stdin.as_mut() {
writeln!(stdin, "{request_json}")?;
stdin
.flush()
.context("failed to flush request to codex app-server")?;
} else {
bail!("codex app-server stdin closed");
}
Ok(())
}
fn wait_for_response<T>(&mut self, request_id: RequestId, method: &str) -> Result<T>
where
T: DeserializeOwned,
{
loop {
let message = self.read_jsonrpc_message()?;
match message {
JSONRPCMessage::Response(JSONRPCResponse { id, result }) => {
if id == request_id {
return serde_json::from_value(result)
.with_context(|| format!("{method} response missing payload"));
}
}
JSONRPCMessage::Error(err) => {
if err.id == request_id {
bail!("{method} failed: {err:?}");
}
}
JSONRPCMessage::Notification(notification) => {
self.pending_notifications.push_back(notification);
}
JSONRPCMessage::Request(request) => {
self.handle_server_request(request)?;
}
}
}
}
fn next_notification(&mut self) -> Result<JSONRPCNotification> {
if let Some(notification) = self.pending_notifications.pop_front() {
return Ok(notification);
}
loop {
let message = self.read_jsonrpc_message()?;
match message {
JSONRPCMessage::Notification(notification) => return Ok(notification),
JSONRPCMessage::Response(_) | JSONRPCMessage::Error(_) => {
// No outstanding requests, so ignore stray responses/errors for now.
continue;
}
JSONRPCMessage::Request(request) => {
self.handle_server_request(request)?;
}
}
}
}
fn read_jsonrpc_message(&mut self) -> Result<JSONRPCMessage> {
loop {
let mut response_line = String::new();
let bytes = self
.stdout
.read_line(&mut response_line)
.context("failed to read from codex app-server")?;
if bytes == 0 {
bail!("codex app-server closed stdout");
}
let trimmed = response_line.trim();
if trimmed.is_empty() {
continue;
}
let parsed: Value =
serde_json::from_str(trimmed).context("response was not valid JSON-RPC")?;
let pretty = serde_json::to_string_pretty(&parsed)?;
print_multiline_with_prefix("< ", &pretty);
let message: JSONRPCMessage = serde_json::from_value(parsed)
.context("response was not a valid JSON-RPC message")?;
return Ok(message);
}
}
fn request_id(&self) -> RequestId {
RequestId::String(Uuid::new_v4().to_string())
}
fn handle_server_request(&mut self, request: JSONRPCRequest) -> Result<()> {
let server_request = ServerRequest::try_from(request)
.context("failed to deserialize ServerRequest from JSONRPCRequest")?;
match server_request {
ServerRequest::CommandExecutionRequestApproval { request_id, params } => {
self.handle_command_execution_request_approval(request_id, params)?;
}
ServerRequest::FileChangeRequestApproval { request_id, params } => {
self.approve_file_change_request(request_id, params)?;
}
other => {
bail!("received unsupported server request: {other:?}");
}
}
Ok(())
}
fn handle_command_execution_request_approval(
&mut self,
request_id: RequestId,
params: CommandExecutionRequestApprovalParams,
) -> Result<()> {
let CommandExecutionRequestApprovalParams {
thread_id,
turn_id,
item_id,
reason,
risk,
} = params;
println!(
"\n< commandExecution approval requested for thread {thread_id}, turn {turn_id}, item {item_id}"
);
if let Some(reason) = reason.as_deref() {
println!("< reason: {reason}");
}
if let Some(risk) = risk.as_ref() {
println!("< risk assessment: {risk:?}");
}
let response = CommandExecutionRequestApprovalResponse {
decision: ApprovalDecision::Accept,
accept_settings: Some(CommandExecutionRequestAcceptSettings { for_session: false }),
};
self.send_server_request_response(request_id, &response)?;
println!("< approved commandExecution request for item {item_id}");
Ok(())
}
fn approve_file_change_request(
&mut self,
request_id: RequestId,
params: FileChangeRequestApprovalParams,
) -> Result<()> {
let FileChangeRequestApprovalParams {
thread_id,
turn_id,
item_id,
reason,
grant_root,
} = params;
println!(
"\n< fileChange approval requested for thread {thread_id}, turn {turn_id}, item {item_id}"
);
if let Some(reason) = reason.as_deref() {
println!("< reason: {reason}");
}
if let Some(grant_root) = grant_root.as_deref() {
println!("< grant root: {}", grant_root.display());
}
let response = FileChangeRequestApprovalResponse {
decision: ApprovalDecision::Accept,
};
self.send_server_request_response(request_id, &response)?;
println!("< approved fileChange request for item {item_id}");
Ok(())
}
fn send_server_request_response<T>(&mut self, request_id: RequestId, response: &T) -> Result<()>
where
T: Serialize,
{
let message = JSONRPCMessage::Response(JSONRPCResponse {
id: request_id,
result: serde_json::to_value(response)?,
});
self.write_jsonrpc_message(message)
}
fn write_jsonrpc_message(&mut self, message: JSONRPCMessage) -> Result<()> {
let payload = serde_json::to_string(&message)?;
let pretty = serde_json::to_string_pretty(&message)?;
print_multiline_with_prefix("> ", &pretty);
if let Some(stdin) = self.stdin.as_mut() {
writeln!(stdin, "{payload}")?;
stdin
.flush()
.context("failed to flush response to codex app-server")?;
return Ok(());
}
bail!("codex app-server stdin closed")
}
}
fn print_multiline_with_prefix(prefix: &str, payload: &str) {
for line in payload.lines() {
println!("{prefix}{line}");
}
}
impl Drop for CodexClient {
fn drop(&mut self) {
let _ = self.stdin.take();
if let Ok(Some(status)) = self.child.try_wait() {
println!("[codex app-server exited: {status}]");
return;
}
thread::sleep(Duration::from_millis(100));
if let Ok(Some(status)) = self.child.try_wait() {
println!("[codex app-server exited: {status}]");
return;
}
let _ = self.child.kill();
let _ = self.child.wait();
}
}

View File

@@ -46,11 +46,9 @@ app_test_support = { workspace = true }
assert_cmd = { workspace = true }
base64 = { workspace = true }
core_test_support = { workspace = true }
mcp-types = { workspace = true }
os_info = { workspace = true }
pretty_assertions = { workspace = true }
serial_test = { workspace = true }
tempfile = { workspace = true }
toml = { workspace = true }
wiremock = { workspace = true }
shlex = { workspace = true }

View File

@@ -1,16 +1,6 @@
# codex-app-server
`codex app-server` is the interface Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt). The message schema is currently unstable, but those who wish to build experimental UIs on top of Codex may find it valuable.
## Table of Contents
- [Protocol](#protocol)
- [Message Schema](#message-schema)
- [Lifecycle Overview](#lifecycle-overview)
- [Initialization](#initialization)
- [Core primitives](#core-primitives)
- [Thread & turn endpoints](#thread--turn-endpoints)
- [Auth endpoints](#auth-endpoints)
- [Events (work-in-progress)](#v2-streaming-events-work-in-progress)
`codex app-server` is the harness Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt). The message schema is currently unstable, but those who wish to build experimental UIs on top of Codex may find it valuable.
## Protocol
@@ -18,367 +8,8 @@ Similar to [MCP](https://modelcontextprotocol.io/), `codex app-server` supports
## Message Schema
Currently, you can dump a TypeScript version of the schema using `codex app-server generate-ts`, or a JSON Schema bundle via `codex app-server generate-json-schema`. Each output is specific to the version of Codex you used to run the command, so the generated artifacts are guaranteed to match that version.
Currently, you can dump a TypeScript version of the schema using `codex generate-ts`. It is specific to the version of Codex you used to run `generate-ts`, so the two are guaranteed to be compatible.
```
codex app-server generate-ts --out DIR
codex app-server generate-json-schema --out DIR
codex generate-ts --out DIR
```
## Lifecycle Overview
- Initialize once: Immediately after launching the codex app-server process, send an `initialize` request with your client metadata, then emit an `initialized` notification. Any other request before this handshake gets rejected.
- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and youll also get a `thread/started` notification. If youre continuing an existing conversation, call `thread/resume` with its ID instead.
- Begin a turn: To send user input, call `turn/start` with the target `threadId` and the user's input. Optional fields let you override model, cwd, sandbox policy, etc. This immediately returns the new turn object and triggers a `turn/started` notification.
- Stream events: After `turn/start`, keep reading JSON-RPC notifications on stdout. Youll see `item/started`, `item/completed`, deltas like `item/agentMessage/delta`, tool progress, etc. These represent streaming model output plus any side effects (commands, tool calls, reasoning notes).
- Finish the turn: When the model is done (or the turn is interrupted via making the `turn/interrupt` call), the server sends `turn/completed` with the final turn state and token usage.
## Initialization
Clients must send a single `initialize` request before invoking any other method, then acknowledge with an `initialized` notification. The server returns the user agent string it will present to upstream services; subsequent requests issued before initialization receive a `"Not initialized"` error, and repeated `initialize` calls receive an `"Already initialized"` error.
Example:
```json
{ "method": "initialize", "id": 0, "params": {
"clientInfo": { "name": "codex-vscode", "title": "Codex VS Code Extension", "version": "0.1.0" }
} }
{ "id": 0, "result": { "userAgent": "codex-app-server/0.1.0 codex-vscode/0.1.0" } }
{ "method": "initialized" }
```
## Core primitives
We have 3 top level primitives:
- Thread - a conversation between the Codex agent and a user. Each thread contains multiple turns.
- Turn - one turn of the conversation, typically starting with a user message and finishing with an agent message. Each turn contains multiple items.
- Item - represents user inputs and agent outputs as part of the turn, persisted and used as the context for future conversations.
## Thread & turn endpoints
The JSON-RPC API exposes dedicated methods for managing Codex conversations. Threads store long-lived conversation metadata, and turns store the per-message exchange (input → Codex output, including streamed items). Use the thread APIs to create, list, or archive sessions, then drive the conversation with turn APIs and notifications.
### Quick reference
- `thread/start` — create a new thread; emits `thread/started` and auto-subscribes you to turn/item events for that thread.
- `thread/resume` — reopen an existing thread by id so subsequent `turn/start` calls append to it.
- `thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
- `thread/archive` — move a threads rollout file into the archived directory; returns `{}` on success.
- `turn/start` — add user input to a thread and begin Codex generation; responds with the initial `turn` object and streams `turn/started`, `item/*`, and `turn/completed` notifications.
- `turn/interrupt` — request cancellation of an in-flight turn by `(thread_id, turn_id)`; success is an empty `{}` response and the turn finishes with `status: "interrupted"`.
- `review/start` — kick off Codexs automated reviewer for a thread; responds like `turn/start` and emits a `item/completed` notification with a `codeReview` item when results are ready.
### 1) Start or resume a thread
Start a fresh thread when you need a new Codex conversation.
```json
{ "method": "thread/start", "id": 10, "params": {
// Optionally set config settings. If not specified, will use the user's
// current config settings.
"model": "gpt-5.1-codex",
"cwd": "/Users/me/project",
"approvalPolicy": "never",
"sandbox": "workspaceWrite",
} }
{ "id": 10, "result": {
"thread": {
"id": "thr_123",
"preview": "",
"modelProvider": "openai",
"createdAt": 1730910000
}
} }
{ "method": "thread/started", "params": { "thread": { } } }
```
To continue a stored session, call `thread/resume` with the `thread.id` you previously recorded. The response shape matches `thread/start`, and no additional notifications are emitted:
```json
{ "method": "thread/resume", "id": 11, "params": { "threadId": "thr_123" } }
{ "id": 11, "result": { "thread": { "id": "thr_123", } } }
```
### 2) List threads (pagination & filters)
`thread/list` lets you render a history UI. Pass any combination of:
- `cursor` — opaque string from a prior response; omit for the first page.
- `limit` — server defaults to a reasonable page size if unset.
- `modelProviders` — restrict results to specific providers; unset, null, or an empty array will include all providers.
Example:
```json
{ "method": "thread/list", "id": 20, "params": {
"cursor": null,
"limit": 25,
} }
{ "id": 20, "result": {
"data": [
{ "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111 },
{ "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000 }
],
"nextCursor": "opaque-token-or-null"
} }
```
When `nextCursor` is `null`, youve reached the final page.
### 3) Archive a thread
Use `thread/archive` to move the persisted rollout (stored as a JSONL file on disk) into the archived sessions directory.
```json
{ "method": "thread/archive", "id": 21, "params": { "threadId": "thr_b" } }
{ "id": 21, "result": {} }
```
An archived thread will not appear in future calls to `thread/list`.
### 4) Start a turn (send user input)
Turns attach user input (text or images) to a thread and trigger Codex generation. The `input` field is a list of discriminated unions:
- `{"type":"text","text":"Explain this diff"}`
- `{"type":"image","url":"https://…png"}`
- `{"type":"localImage","path":"/tmp/screenshot.png"}`
You can optionally specify config overrides on the new turn. If specified, these settings become the default for subsequent turns on the same thread.
```json
{ "method": "turn/start", "id": 30, "params": {
"threadId": "thr_123",
"input": [ { "type": "text", "text": "Run tests" } ],
// Below are optional config overrides
"cwd": "/Users/me/project",
"approvalPolicy": "unlessTrusted",
"sandboxPolicy": {
"mode": "workspaceWrite",
"writableRoots": ["/Users/me/project"],
"networkAccess": true
},
"model": "gpt-5.1-codex",
"effort": "medium",
"summary": "concise"
} }
{ "id": 30, "result": { "turn": {
"id": "turn_456",
"status": "inProgress",
"items": [],
"error": null
} } }
```
### 5) Interrupt an active turn
You can cancel a running Turn with `turn/interrupt`.
```json
{ "method": "turn/interrupt", "id": 31, "params": {
"threadId": "thr_123",
"turnId": "turn_456"
} }
{ "id": 31, "result": {} }
```
The server requests cancellations for running subprocesses, then emits a `turn/completed` event with `status: "interrupted"`. Rely on the `turn/completed` to know when Codex-side cleanup is done.
### 6) Request a code review
Use `review/start` to run Codexs reviewer on the currently checked-out project. The request takes the thread id plus a `target` describing what should be reviewed:
- `{"type":"uncommittedChanges"}` — staged, unstaged, and untracked files.
- `{"type":"baseBranch","branch":"main"}` — diff against the provided branchs upstream (see prompt for the exact `git merge-base`/`git diff` instructions Codex will run).
- `{"type":"commit","sha":"abc1234","title":"Optional subject"}` — review a specific commit.
- `{"type":"custom","instructions":"Free-form reviewer instructions"}` — fallback prompt equivalent to the legacy manual review request.
- `appendToOriginalThread` (bool, default `false`) — when `true`, Codex also records a final assistant-style message with the review summary in the original thread. When `false`, only the `codeReview` item is emitted for the review run and no extra message is added to the original thread.
Example request/response:
```json
{ "method": "review/start", "id": 40, "params": {
"threadId": "thr_123",
"appendToOriginalThread": true,
"target": { "type": "commit", "sha": "1234567deadbeef", "title": "Polish tui colors" }
} }
{ "id": 40, "result": { "turn": {
"id": "turn_900",
"status": "inProgress",
"items": [
{ "type": "userMessage", "id": "turn_900", "content": [ { "type": "text", "text": "Review commit 1234567: Polish tui colors" } ] }
],
"error": null
} } }
```
Codex streams the usual `turn/started` notification followed by an `item/started`
with the same `codeReview` item id so clients can show progress:
```json
{ "method": "item/started", "params": { "item": {
"type": "codeReview",
"id": "turn_900",
"review": "current changes"
} } }
```
When the reviewer finishes, the server emits `item/completed` containing the same
`codeReview` item with the final review text:
```json
{ "method": "item/completed", "params": { "item": {
"type": "codeReview",
"id": "turn_900",
"review": "Looks solid overall...\n\n- Prefer Stylize helpers — app.rs:10-20\n ..."
} } }
```
The `review` string is plain text that already bundles the overall explanation plus a bullet list for each structured finding (matching `ThreadItem::CodeReview` in the generated schema). Use this notification to render the reviewer output in your client.
## Auth endpoints
The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.
### Quick reference
- `account/read` — fetch current account info; optionally refresh tokens.
- `account/login/start` — begin login (`apiKey` or `chatgpt`).
- `account/login/completed` (notify) — emitted when a login attempt finishes (success or error).
- `account/login/cancel` — cancel a pending ChatGPT login by `loginId`.
- `account/logout` — sign out; triggers `account/updated`.
- `account/updated` (notify) — emitted whenever auth mode changes (`authMode`: `apikey`, `chatgpt`, or `null`).
- `account/rateLimits/read` — fetch ChatGPT rate limits; updates arrive via `account/rateLimits/updated` (notify).
### 1) Check auth state
Request:
```json
{ "method": "account/read", "id": 1, "params": { "refreshToken": false } }
```
Response examples:
```json
{ "id": 1, "result": { "account": null, "requiresOpenaiAuth": false } } // No OpenAI auth needed (e.g., OSS/local models)
{ "id": 1, "result": { "account": null, "requiresOpenaiAuth": true } } // OpenAI auth required (typical for OpenAI-hosted models)
{ "id": 1, "result": { "account": { "type": "apiKey" }, "requiresOpenaiAuth": true } }
{ "id": 1, "result": { "account": { "type": "chatgpt", "email": "user@example.com", "planType": "pro" }, "requiresOpenaiAuth": true } }
```
Field notes:
- `refreshToken` (bool): set `true` to force a token refresh.
- `requiresOpenaiAuth` reflects the active provider; when `false`, Codex can run without OpenAI credentials.
### 2) Log in with an API key
1. Send:
```json
{ "method": "account/login/start", "id": 2, "params": { "type": "apiKey", "apiKey": "sk-…" } }
```
2. Expect:
```json
{ "id": 2, "result": { "type": "apiKey" } }
```
3. Notifications:
```json
{ "method": "account/login/completed", "params": { "loginId": null, "success": true, "error": null } }
{ "method": "account/updated", "params": { "authMode": "apikey" } }
```
### 3) Log in with ChatGPT (browser flow)
1. Start:
```json
{ "method": "account/login/start", "id": 3, "params": { "type": "chatgpt" } }
{ "id": 3, "result": { "type": "chatgpt", "loginId": "<uuid>", "authUrl": "https://chatgpt.com/…&redirect_uri=http%3A%2F%2Flocalhost%3A<port>%2Fauth%2Fcallback" } }
```
2. Open `authUrl` in a browser; the app-server hosts the local callback.
3. Wait for notifications:
```json
{ "method": "account/login/completed", "params": { "loginId": "<uuid>", "success": true, "error": null } }
{ "method": "account/updated", "params": { "authMode": "chatgpt" } }
```
### 4) Cancel a ChatGPT login
```json
{ "method": "account/login/cancel", "id": 4, "params": { "loginId": "<uuid>" } }
{ "method": "account/login/completed", "params": { "loginId": "<uuid>", "success": false, "error": "…" } }
```
### 5) Logout
```json
{ "method": "account/logout", "id": 5 }
{ "id": 5, "result": {} }
{ "method": "account/updated", "params": { "authMode": null } }
```
### 6) Rate limits (ChatGPT)
```json
{ "method": "account/rateLimits/read", "id": 6 }
{ "id": 6, "result": { "rateLimits": { "primary": { "usedPercent": 25, "windowDurationMins": 15, "resetsAt": 1730947200 }, "secondary": null } } }
{ "method": "account/rateLimits/updated", "params": { "rateLimits": { … } } }
```
Field notes:
- `usedPercent` is current usage within the OpenAI quota window.
- `windowDurationMins` is the quota window length.
- `resetsAt` is a Unix timestamp (seconds) for the next reset.
### Dev notes
- `codex app-server generate-ts --out <dir>` emits v2 types under `v2/`.
- `codex app-server generate-json-schema --out <dir>` outputs `codex_app_server_protocol.schemas.json`.
- See [“Authentication and authorization” in the config docs](../../docs/config.md#authentication-and-authorization) for configuration knobs.
## Events (work-in-progress)
Event notifications are the server-initiated event stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading stdout for `thread/started`, `turn/*`, and `item/*` notifications.
### Turn events
The app-server streams JSON-RPC notifications while a turn is running. Each turn starts with `turn/started` (initial `turn`) and ends with `turn/completed` (final `turn` plus token `usage`), and clients subscribe to the events they care about, rendering each item incrementally as updates arrive. The per-item lifecycle is always: `item/started` → zero or more item-specific deltas → `item/completed`.
- `turn/started` — `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.
- `turn/completed` — `{ turn }` where `turn.status` is `completed`, `interrupted`, or `failed`; failures carry `{ error: { message, codexErrorInfo? } }`.
Today both notifications carry an empty `items` array even when item events were streamed; rely on `item/*` notifications for the canonical item list until this is fixed.
#### Errors
`error` event is emitted whenever the server hits an error mid-turn (for example, upstream model errors or quota limits). Carries the same `{ error: { message, codexErrorInfo? } }` payload as `turn.status: "failed"` and may precede that terminal notification.
`codexErrorInfo` maps to the `CodexErrorInfo` enum. Common values:
- `ContextWindowExceeded`
- `UsageLimitExceeded`
- `HttpConnectionFailed { httpStatusCode? }`: upstream HTTP failures including 4xx/5xx
- `ResponseStreamConnectionFailed { httpStatusCode? }`: failure to connect to the response SSE stream
- `ResponseStreamDisconnected { httpStatusCode? }`: disconnect of the response SSE stream in the middle of a turn before completion
- `ResponseTooManyFailedAttempts { httpStatusCode? }`
- `BadRequest`
- `Unauthorized`
- `SandboxError`
- `InternalServerError`
- `Other`: all unclassified errors
When an upstream HTTP status is available (for example, from the Responses API or a provider), it is forwarded in `httpStatusCode` on the relevant `codexErrorInfo` variant.
#### Thread items
`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Currently we support events for the following items:
- `userMessage` — `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).
- `agentMessage` — `{id, text}` containing the accumulated agent reply.
- `reasoning` — `{id, summary, content}` where `summary` holds streamed reasoning summaries (applicable for most OpenAI models) and `content` holds raw reasoning blocks (applicable for e.g. open source models).
- `mcpToolCall` — `{id, server, tool, status, arguments, result?, error?}` describing MCP calls; `status` is `inProgress`, `completed`, or `failed`.
- `webSearch` — `{id, query}` for a web search request issued by the agent.
All items emit two shared lifecycle events:
- `item/started` — emits the full `item` when a new unit of work begins so the UI can render it immediately; the `item.id` in this payload matches the `itemId` used by deltas.
- `item/completed` — sends the final `item` once that work finishes (e.g., after a tool call or message completes); treat this as the authoritative state.
There are additional item-specific events:
#### agentMessage
- `item/agentMessage/delta` — appends streamed text for the agent message; concatenate `delta` values for the same `itemId` in order to reconstruct the full reply.
#### reasoning
- `item/reasoning/summaryTextDelta` — streams readable reasoning summaries; `summaryIndex` increments when a new summary section opens.
- `item/reasoning/summaryPartAdded` — marks the boundary between reasoning summary sections for an `itemId`; subsequent `summaryTextDelta` entries share the same `summaryIndex`.
- `item/reasoning/textDelta` — streams raw reasoning text (only applicable for e.g. open source models); use `contentIndex` to group deltas that belong together before showing them in the UI.

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -19,10 +19,6 @@ pub(crate) async fn run_fuzzy_file_search(
roots: Vec<String>,
cancellation_flag: Arc<AtomicBool>,
) -> Vec<FuzzyFileSearchResult> {
if roots.is_empty() {
return Vec::new();
}
#[expect(clippy::expect_used)]
let limit_per_root =
NonZero::new(LIMIT_PER_ROOT).expect("LIMIT_PER_ROOT should be a valid non-zero usize");

View File

@@ -28,7 +28,6 @@ use tracing_subscriber::filter::Targets;
use tracing_subscriber::layer::SubscriberExt;
use tracing_subscriber::util::SubscriberInitExt;
mod bespoke_event_handling;
mod codex_message_processor;
mod error_code;
mod fuzzy_file_search;
@@ -47,7 +46,7 @@ pub async fn run_main(
) -> IoResult<()> {
// Set up channels.
let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(CHANNEL_CAPACITY);
let (outgoing_tx, mut outgoing_rx) = mpsc::unbounded_channel::<OutgoingMessage>();
// Task: read from stdin, push to `incoming_tx`.
let stdin_reader_handle = tokio::spawn({

View File

@@ -6,6 +6,7 @@ use crate::outgoing_message::OutgoingMessageSender;
use codex_app_server_protocol::ClientInfo;
use codex_app_server_protocol::ClientRequest;
use codex_app_server_protocol::InitializeResponse;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCErrorError;
use codex_app_server_protocol::JSONRPCNotification;
@@ -63,80 +64,64 @@ impl MessageProcessor {
pub(crate) async fn process_request(&mut self, request: JSONRPCRequest) {
let request_id = request.id.clone();
let request_json = match serde_json::to_value(&request) {
Ok(request_json) => request_json,
Err(err) => {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: format!("Invalid request: {err}"),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
}
};
if let Ok(request_json) = serde_json::to_value(request)
&& let Ok(codex_request) = serde_json::from_value::<ClientRequest>(request_json)
{
match codex_request {
// Handle Initialize internally so CodexMessageProcessor does not have to concern
// itself with the `initialized` bool.
ClientRequest::Initialize { request_id, params } => {
if self.initialized {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Already initialized".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
} else {
let ClientInfo {
name,
title: _title,
version,
} = params.client_info;
let user_agent_suffix = format!("{name}; {version}");
if let Ok(mut suffix) = USER_AGENT_SUFFIX.lock() {
*suffix = Some(user_agent_suffix);
}
let codex_request = match serde_json::from_value::<ClientRequest>(request_json) {
Ok(codex_request) => codex_request,
Err(err) => {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: format!("Invalid request: {err}"),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
}
};
let user_agent = get_codex_user_agent();
let response = InitializeResponse { user_agent };
self.outgoing.send_response(request_id, response).await;
match codex_request {
// Handle Initialize internally so CodexMessageProcessor does not have to concern
// itself with the `initialized` bool.
ClientRequest::Initialize { request_id, params } => {
if self.initialized {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Already initialized".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
} else {
let ClientInfo {
name,
title: _title,
version,
} = params.client_info;
let user_agent_suffix = format!("{name}; {version}");
if let Ok(mut suffix) = USER_AGENT_SUFFIX.lock() {
*suffix = Some(user_agent_suffix);
self.initialized = true;
return;
}
}
_ => {
if !self.initialized {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Not initialized".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
}
let user_agent = get_codex_user_agent();
let response = InitializeResponse { user_agent };
self.outgoing.send_response(request_id, response).await;
self.initialized = true;
return;
}
}
_ => {
if !self.initialized {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Not initialized".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
return;
}
}
self.codex_message_processor
.process_request(codex_request)
.await;
} else {
let error = JSONRPCErrorError {
code: INVALID_REQUEST_ERROR_CODE,
message: "Invalid request".to_string(),
data: None,
};
self.outgoing.send_error(request_id, error).await;
}
self.codex_message_processor
.process_request(codex_request)
.await;
}
pub(crate) async fn process_notification(&self, notification: JSONRPCNotification) {

View File

@@ -1,12 +1,11 @@
use codex_app_server_protocol::AuthMode;
use codex_app_server_protocol::Model;
use codex_app_server_protocol::ReasoningEffortOption;
use codex_common::model_presets::ModelPreset;
use codex_common::model_presets::ReasoningEffortPreset;
use codex_common::model_presets::builtin_model_presets;
pub fn supported_models(auth_mode: Option<AuthMode>) -> Vec<Model> {
builtin_model_presets(auth_mode)
pub fn supported_models() -> Vec<Model> {
builtin_model_presets(None)
.into_iter()
.map(model_from_preset)
.collect()

View File

@@ -19,12 +19,12 @@ use crate::error_code::INTERNAL_ERROR_CODE;
/// Sends messages to the client and manages request callbacks.
pub(crate) struct OutgoingMessageSender {
next_request_id: AtomicI64,
sender: mpsc::Sender<OutgoingMessage>,
sender: mpsc::UnboundedSender<OutgoingMessage>,
request_id_to_callback: Mutex<HashMap<RequestId, oneshot::Sender<Result>>>,
}
impl OutgoingMessageSender {
pub(crate) fn new(sender: mpsc::Sender<OutgoingMessage>) -> Self {
pub(crate) fn new(sender: mpsc::UnboundedSender<OutgoingMessage>) -> Self {
Self {
next_request_id: AtomicI64::new(0),
sender,
@@ -45,12 +45,8 @@ impl OutgoingMessageSender {
}
let outgoing_message =
OutgoingMessage::Request(request.request_with_id(outgoing_message_id.clone()));
if let Err(err) = self.sender.send(outgoing_message).await {
warn!("failed to send request {outgoing_message_id:?} to client: {err:?}");
let mut request_id_to_callback = self.request_id_to_callback.lock().await;
request_id_to_callback.remove(&outgoing_message_id);
}
OutgoingMessage::Request(request.request_with_id(outgoing_message_id));
let _ = self.sender.send(outgoing_message);
rx_approve
}
@@ -76,9 +72,7 @@ impl OutgoingMessageSender {
match serde_json::to_value(response) {
Ok(result) => {
let outgoing_message = OutgoingMessage::Response(OutgoingResponse { id, result });
if let Err(err) = self.sender.send(outgoing_message).await {
warn!("failed to send response to client: {err:?}");
}
let _ = self.sender.send(outgoing_message);
}
Err(err) => {
self.send_error(
@@ -95,29 +89,21 @@ impl OutgoingMessageSender {
}
pub(crate) async fn send_server_notification(&self, notification: ServerNotification) {
if let Err(err) = self
let _ = self
.sender
.send(OutgoingMessage::AppServerNotification(notification))
.await
{
warn!("failed to send server notification to client: {err:?}");
}
.send(OutgoingMessage::AppServerNotification(notification));
}
/// All notifications should be migrated to [`ServerNotification`] and
/// [`OutgoingMessage::Notification`] should be removed.
pub(crate) async fn send_notification(&self, notification: OutgoingNotification) {
let outgoing_message = OutgoingMessage::Notification(notification);
if let Err(err) = self.sender.send(outgoing_message).await {
warn!("failed to send notification to client: {err:?}");
}
let _ = self.sender.send(outgoing_message);
}
pub(crate) async fn send_error(&self, id: RequestId, error: JSONRPCErrorError) {
let outgoing_message = OutgoingMessage::Error(OutgoingError { id, error });
if let Err(err) = self.sender.send(outgoing_message).await {
warn!("failed to send error to client: {err:?}");
}
let _ = self.sender.send(outgoing_message);
}
}
@@ -155,13 +141,9 @@ pub(crate) struct OutgoingError {
#[cfg(test)]
mod tests {
use codex_app_server_protocol::AccountLoginCompletedNotification;
use codex_app_server_protocol::AccountRateLimitsUpdatedNotification;
use codex_app_server_protocol::AccountUpdatedNotification;
use codex_app_server_protocol::AuthMode;
use codex_app_server_protocol::LoginChatGptCompleteNotification;
use codex_app_server_protocol::RateLimitSnapshot;
use codex_app_server_protocol::RateLimitWindow;
use codex_protocol::protocol::RateLimitSnapshot;
use codex_protocol::protocol::RateLimitWindow;
use pretty_assertions::assert_eq;
use serde_json::json;
use uuid::Uuid;
@@ -193,80 +175,28 @@ mod tests {
);
}
#[test]
fn verify_account_login_completed_notification_serialization() {
let notification =
ServerNotification::AccountLoginCompleted(AccountLoginCompletedNotification {
login_id: Some(Uuid::nil().to_string()),
success: true,
error: None,
});
let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
assert_eq!(
json!({
"method": "account/login/completed",
"params": {
"loginId": Uuid::nil().to_string(),
"success": true,
"error": null,
},
}),
serde_json::to_value(jsonrpc_notification)
.expect("ensure the notification serializes correctly"),
"ensure the notification serializes correctly"
);
}
#[test]
fn verify_account_rate_limits_notification_serialization() {
let notification =
ServerNotification::AccountRateLimitsUpdated(AccountRateLimitsUpdatedNotification {
rate_limits: RateLimitSnapshot {
primary: Some(RateLimitWindow {
used_percent: 25,
window_duration_mins: Some(15),
resets_at: Some(123),
}),
secondary: None,
credits: None,
},
});
let notification = ServerNotification::AccountRateLimitsUpdated(RateLimitSnapshot {
primary: Some(RateLimitWindow {
used_percent: 25.0,
window_minutes: Some(15),
resets_at: Some(123),
}),
secondary: None,
});
let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
assert_eq!(
json!({
"method": "account/rateLimits/updated",
"params": {
"rateLimits": {
"primary": {
"usedPercent": 25,
"windowDurationMins": 15,
"resetsAt": 123
},
"secondary": null,
"credits": null
}
},
}),
serde_json::to_value(jsonrpc_notification)
.expect("ensure the notification serializes correctly"),
"ensure the notification serializes correctly"
);
}
#[test]
fn verify_account_updated_notification_serialization() {
let notification = ServerNotification::AccountUpdated(AccountUpdatedNotification {
auth_mode: Some(AuthMode::ApiKey),
});
let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
assert_eq!(
json!({
"method": "account/updated",
"params": {
"authMode": "apikey"
"primary": {
"used_percent": 25.0,
"window_minutes": 15,
"resets_at": 123,
},
"secondary": null,
},
}),
serde_json::to_value(jsonrpc_notification)

View File

@@ -13,7 +13,6 @@ base64 = { workspace = true }
chrono = { workspace = true }
codex-app-server-protocol = { workspace = true }
codex-core = { workspace = true }
codex-protocol = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true, features = [
@@ -22,7 +21,4 @@ tokio = { workspace = true, features = [
"process",
"rt-multi-thread",
] }
uuid = { workspace = true }
wiremock = { workspace = true }
core_test_support = { path = "../../../core/tests/common" }
shlex = { workspace = true }

View File

@@ -2,22 +2,17 @@ mod auth_fixtures;
mod mcp_process;
mod mock_model_server;
mod responses;
mod rollout;
pub use auth_fixtures::ChatGptAuthFixture;
pub use auth_fixtures::ChatGptIdTokenClaims;
pub use auth_fixtures::encode_id_token;
pub use auth_fixtures::write_chatgpt_auth;
use codex_app_server_protocol::JSONRPCResponse;
pub use core_test_support::format_with_current_shell;
pub use core_test_support::format_with_current_shell_display;
pub use mcp_process::McpProcess;
pub use mock_model_server::create_mock_chat_completions_server;
pub use mock_model_server::create_mock_chat_completions_server_unchecked;
pub use responses::create_apply_patch_sse_response;
pub use responses::create_final_assistant_message_sse_response;
pub use responses::create_shell_command_sse_response;
pub use rollout::create_fake_rollout;
pub use responses::create_shell_sse_response;
use serde::de::DeserializeOwned;
pub fn to_response<T: DeserializeOwned>(response: JSONRPCResponse) -> anyhow::Result<T> {

View File

@@ -14,38 +14,30 @@ use anyhow::Context;
use assert_cmd::prelude::*;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::ArchiveConversationParams;
use codex_app_server_protocol::CancelLoginAccountParams;
use codex_app_server_protocol::CancelLoginChatGptParams;
use codex_app_server_protocol::ClientInfo;
use codex_app_server_protocol::ClientNotification;
use codex_app_server_protocol::FeedbackUploadParams;
use codex_app_server_protocol::GetAccountParams;
use codex_app_server_protocol::GetAuthStatusParams;
use codex_app_server_protocol::InitializeParams;
use codex_app_server_protocol::InterruptConversationParams;
use codex_app_server_protocol::ListConversationsParams;
use codex_app_server_protocol::ListModelsParams;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::RemoveConversationListenerParams;
use codex_app_server_protocol::ResumeConversationParams;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserTurnParams;
use codex_app_server_protocol::ServerRequest;
use codex_app_server_protocol::SetDefaultModelParams;
use codex_app_server_protocol::UploadFeedbackParams;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCMessage;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCRequest;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::ListConversationsParams;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::ModelListParams;
use codex_app_server_protocol::NewConversationParams;
use codex_app_server_protocol::RemoveConversationListenerParams;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ResumeConversationParams;
use codex_app_server_protocol::ReviewStartParams;
use codex_app_server_protocol::SendUserMessageParams;
use codex_app_server_protocol::SendUserTurnParams;
use codex_app_server_protocol::ServerRequest;
use codex_app_server_protocol::SetDefaultModelParams;
use codex_app_server_protocol::ThreadArchiveParams;
use codex_app_server_protocol::ThreadListParams;
use codex_app_server_protocol::ThreadResumeParams;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::TurnInterruptParams;
use codex_app_server_protocol::TurnStartParams;
use std::process::Command as StdCommand;
use tokio::process::Command;
@@ -251,19 +243,10 @@ impl McpProcess {
self.send_request("account/rateLimits/read", None).await
}
/// Send an `account/read` JSON-RPC request.
pub async fn send_get_account_request(
&mut self,
params: GetAccountParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("account/read", params).await
}
/// Send a `feedback/upload` JSON-RPC request.
pub async fn send_feedback_upload_request(
pub async fn send_upload_feedback_request(
&mut self,
params: FeedbackUploadParams,
params: UploadFeedbackParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("feedback/upload", params).await
@@ -292,46 +275,10 @@ impl McpProcess {
self.send_request("listConversations", params).await
}
/// Send a `thread/start` JSON-RPC request.
pub async fn send_thread_start_request(
&mut self,
params: ThreadStartParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("thread/start", params).await
}
/// Send a `thread/resume` JSON-RPC request.
pub async fn send_thread_resume_request(
&mut self,
params: ThreadResumeParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("thread/resume", params).await
}
/// Send a `thread/archive` JSON-RPC request.
pub async fn send_thread_archive_request(
&mut self,
params: ThreadArchiveParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("thread/archive", params).await
}
/// Send a `thread/list` JSON-RPC request.
pub async fn send_thread_list_request(
&mut self,
params: ThreadListParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("thread/list", params).await
}
/// Send a `model/list` JSON-RPC request.
pub async fn send_list_models_request(
&mut self,
params: ModelListParams,
params: ListModelsParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("model/list", params).await
@@ -360,33 +307,6 @@ impl McpProcess {
self.send_request("loginChatGpt", None).await
}
/// Send a `turn/start` JSON-RPC request (v2).
pub async fn send_turn_start_request(
&mut self,
params: TurnStartParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("turn/start", params).await
}
/// Send a `turn/interrupt` JSON-RPC request (v2).
pub async fn send_turn_interrupt_request(
&mut self,
params: TurnInterruptParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("turn/interrupt", params).await
}
/// Send a `review/start` JSON-RPC request (v2).
pub async fn send_review_start_request(
&mut self,
params: ReviewStartParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("review/start", params).await
}
/// Send a `cancelLoginChatGpt` JSON-RPC request.
pub async fn send_cancel_login_chat_gpt_request(
&mut self,
@@ -401,40 +321,6 @@ impl McpProcess {
self.send_request("logoutChatGpt", None).await
}
/// Send an `account/logout` JSON-RPC request.
pub async fn send_logout_account_request(&mut self) -> anyhow::Result<i64> {
self.send_request("account/logout", None).await
}
/// Send an `account/login/start` JSON-RPC request for API key login.
pub async fn send_login_account_api_key_request(
&mut self,
api_key: &str,
) -> anyhow::Result<i64> {
let params = serde_json::json!({
"type": "apiKey",
"apiKey": api_key,
});
self.send_request("account/login/start", Some(params)).await
}
/// Send an `account/login/start` JSON-RPC request for ChatGPT login.
pub async fn send_login_account_chatgpt_request(&mut self) -> anyhow::Result<i64> {
let params = serde_json::json!({
"type": "chatgpt"
});
self.send_request("account/login/start", Some(params)).await
}
/// Send an `account/login/cancel` JSON-RPC request.
pub async fn send_cancel_login_account_request(
&mut self,
params: CancelLoginAccountParams,
) -> anyhow::Result<i64> {
let params = Some(serde_json::to_value(params)?);
self.send_request("account/login/cancel", params).await
}
/// Send a `fuzzyFileSearch` JSON-RPC request.
pub async fn send_fuzzy_file_search_request(
&mut self,

View File

@@ -29,25 +29,6 @@ pub async fn create_mock_chat_completions_server(responses: Vec<String>) -> Mock
server
}
/// Same as `create_mock_chat_completions_server` but does not enforce an
/// expectation on the number of calls.
pub async fn create_mock_chat_completions_server_unchecked(responses: Vec<String>) -> MockServer {
let server = MockServer::start().await;
let seq_responder = SeqResponder {
num_calls: AtomicUsize::new(0),
responses,
};
Mock::given(method("POST"))
.and(path("/v1/chat/completions"))
.respond_with(seq_responder)
.mount(&server)
.await;
server
}
struct SeqResponder {
num_calls: AtomicUsize,
responses: Vec<String>,

View File

@@ -1,18 +1,17 @@
use serde_json::json;
use std::path::Path;
pub fn create_shell_command_sse_response(
pub fn create_shell_sse_response(
command: Vec<String>,
workdir: Option<&Path>,
timeout_ms: Option<u64>,
call_id: &str,
) -> anyhow::Result<String> {
// The `arguments` for the `shell_command` tool is a serialized JSON object.
let command_str = shlex::try_join(command.iter().map(String::as_str))?;
// The `arguments`` for the `shell` tool is a serialized JSON object.
let tool_call_arguments = serde_json::to_string(&json!({
"command": command_str,
"command": command,
"workdir": workdir.map(|w| w.to_string_lossy()),
"timeout_ms": timeout_ms
"timeout": timeout_ms
}))?;
let tool_call = json!({
"choices": [
@@ -22,7 +21,7 @@ pub fn create_shell_command_sse_response(
{
"id": call_id,
"function": {
"name": "shell_command",
"name": "shell",
"arguments": tool_call_arguments
}
}
@@ -63,10 +62,10 @@ pub fn create_apply_patch_sse_response(
patch_content: &str,
call_id: &str,
) -> anyhow::Result<String> {
// Use shell_command to call apply_patch with heredoc format
let command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
// Use shell command to call apply_patch with heredoc format
let shell_command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
let tool_call_arguments = serde_json::to_string(&json!({
"command": command
"command": ["bash", "-lc", shell_command]
}))?;
let tool_call = json!({
@@ -77,7 +76,7 @@ pub fn create_apply_patch_sse_response(
{
"id": call_id,
"function": {
"name": "shell_command",
"name": "shell",
"arguments": tool_call_arguments
}
}

View File

@@ -1,82 +0,0 @@
use anyhow::Result;
use codex_protocol::ConversationId;
use codex_protocol::protocol::SessionMeta;
use codex_protocol::protocol::SessionSource;
use serde_json::json;
use std::fs;
use std::path::Path;
use std::path::PathBuf;
use uuid::Uuid;
/// Create a minimal rollout file under `CODEX_HOME/sessions/YYYY/MM/DD/`.
///
/// - `filename_ts` is the filename timestamp component in `YYYY-MM-DDThh-mm-ss` format.
/// - `meta_rfc3339` is the envelope timestamp used in JSON lines.
/// - `preview` is the user message preview text.
/// - `model_provider` optionally sets the provider in the session meta payload.
///
/// Returns the generated conversation/session UUID as a string.
pub fn create_fake_rollout(
codex_home: &Path,
filename_ts: &str,
meta_rfc3339: &str,
preview: &str,
model_provider: Option<&str>,
) -> Result<String> {
let uuid = Uuid::new_v4();
let uuid_str = uuid.to_string();
let conversation_id = ConversationId::from_string(&uuid_str)?;
// sessions/YYYY/MM/DD derived from filename_ts (YYYY-MM-DDThh-mm-ss)
let year = &filename_ts[0..4];
let month = &filename_ts[5..7];
let day = &filename_ts[8..10];
let dir = codex_home.join("sessions").join(year).join(month).join(day);
fs::create_dir_all(&dir)?;
let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
// Build JSONL lines
let payload = serde_json::to_value(SessionMeta {
id: conversation_id,
timestamp: meta_rfc3339.to_string(),
cwd: PathBuf::from("/"),
originator: "codex".to_string(),
cli_version: "0.0.0".to_string(),
instructions: None,
source: SessionSource::Cli,
model_provider: model_provider.map(str::to_string),
})?;
let lines = [
json!({
"timestamp": meta_rfc3339,
"type": "session_meta",
"payload": payload
})
.to_string(),
json!({
"timestamp": meta_rfc3339,
"type":"response_item",
"payload": {
"type":"message",
"role":"user",
"content":[{"type":"input_text","text": preview}]
}
})
.to_string(),
json!({
"timestamp": meta_rfc3339,
"type":"event_msg",
"payload": {
"type":"user_message",
"message": preview,
"kind": "plain"
}
})
.to_string(),
];
fs::write(file_path, lines.join("\n") + "\n")?;
Ok(uuid_str)
}

View File

@@ -12,7 +12,7 @@ use std::path::Path;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(20);
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn archive_conversation_moves_rollout_into_archived_directory() -> Result<()> {

View File

@@ -2,8 +2,7 @@ use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::create_shell_command_sse_response;
use app_test_support::format_with_current_shell;
use app_test_support::create_shell_sse_response;
use app_test_support::to_response;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
@@ -57,7 +56,7 @@ async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
// Create a mock model server that immediately ends each turn.
// Two turns are expected: initial session configure + one user message.
let responses = vec![
create_shell_command_sse_response(
create_shell_sse_response(
vec!["ls".to_string()],
Some(&working_directory),
Some(5000),
@@ -176,7 +175,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
// Mock server will request a python shell call for the first and second turn, then finish.
let responses = vec![
create_shell_command_sse_response(
create_shell_sse_response(
vec![
"python3".to_string(),
"-c".to_string(),
@@ -187,7 +186,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
"call1",
)?,
create_final_assistant_message_sse_response("done 1")?,
create_shell_command_sse_response(
create_shell_sse_response(
vec![
"python3".to_string(),
"-c".to_string(),
@@ -268,7 +267,11 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
ExecCommandApprovalParams {
conversation_id,
call_id: "call1".to_string(),
command: format_with_current_shell("python3 -c 'print(42)'"),
command: vec![
"python3".to_string(),
"-c".to_string(),
"print(42)".to_string(),
],
cwd: working_directory.clone(),
reason: None,
risk: None,
@@ -350,15 +353,23 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
std::fs::create_dir(&second_cwd)?;
let responses = vec![
create_shell_command_sse_response(
vec!["echo".to_string(), "first".to_string(), "turn".to_string()],
create_shell_sse_response(
vec![
"bash".to_string(),
"-lc".to_string(),
"echo first turn".to_string(),
],
None,
Some(5000),
"call-first",
)?,
create_final_assistant_message_sse_response("done first")?,
create_shell_command_sse_response(
vec!["echo".to_string(), "second".to_string(), "turn".to_string()],
create_shell_sse_response(
vec![
"bash".to_string(),
"-lc".to_string(),
"echo second turn".to_string(),
],
None,
Some(5000),
"call-second",
@@ -470,9 +481,13 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
exec_begin.cwd, second_cwd,
"exec turn should run from updated cwd"
);
let expected_command = format_with_current_shell("echo second turn");
assert_eq!(
exec_begin.command, expected_command,
exec_begin.command,
vec![
"bash".to_string(),
"-lc".to_string(),
"echo second turn".to_string()
],
"exec turn should run expected command"
);

View File

@@ -27,7 +27,7 @@ fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
std::fs::write(
config_toml,
r#"
model = "gpt-5.1-codex-max"
model = "gpt-5-codex"
approval_policy = "on-request"
sandbox_mode = "workspace-write"
model_reasoning_summary = "detailed"
@@ -87,7 +87,7 @@ async fn get_config_toml_parses_all_fields() -> Result<()> {
}),
forced_chatgpt_workspace_id: Some("12345678-0000-0000-0000-000000000000".into()),
forced_login_method: Some(ForcedLoginMethod::Chatgpt),
model: Some("gpt-5.1-codex-max".into()),
model: Some("gpt-5-codex".into()),
model_reasoning_effort: Some(ReasoningEffort::High),
model_reasoning_summary: Some(ReasoningSummary::Detailed),
model_verbosity: Some(Verbosity::Medium),

View File

@@ -19,7 +19,7 @@ use tokio::time::timeout;
use app_test_support::McpProcess;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::create_shell_command_sse_response;
use app_test_support::create_shell_sse_response;
use app_test_support::to_response;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
@@ -56,7 +56,7 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
std::fs::create_dir(&working_directory)?;
// Create mock server with a single SSE response: the long sleep command
let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
let server = create_mock_chat_completions_server(vec![create_shell_sse_response(
shell_command.clone(),
Some(&working_directory),
Some(10_000), // 10 seconds timeout in ms
@@ -146,7 +146,7 @@ fn create_config_toml(codex_home: &Path, server_uri: String) -> std::io::Result<
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "read-only"
sandbox_mode = "danger-full-access"
model_provider = "mock_provider"

View File

@@ -1,6 +1,5 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_fake_rollout;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
@@ -16,8 +15,12 @@ use codex_core::protocol::EventMsg;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ResponseItem;
use pretty_assertions::assert_eq;
use serde_json::json;
use std::fs;
use std::path::Path;
use tempfile::TempDir;
use tokio::time::timeout;
use uuid::Uuid;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
@@ -354,3 +357,70 @@ async fn test_list_and_resume_conversations() -> Result<()> {
Ok(())
}
fn create_fake_rollout(
codex_home: &Path,
filename_ts: &str,
meta_rfc3339: &str,
preview: &str,
model_provider: Option<&str>,
) -> Result<()> {
let uuid = Uuid::new_v4();
// sessions/YYYY/MM/DD/ derived from filename_ts (YYYY-MM-DDThh-mm-ss)
let year = &filename_ts[0..4];
let month = &filename_ts[5..7];
let day = &filename_ts[8..10];
let dir = codex_home.join("sessions").join(year).join(month).join(day);
fs::create_dir_all(&dir)?;
let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
let mut lines = Vec::new();
// Meta line with timestamp (flattened meta in payload for new schema)
let mut payload = json!({
"id": uuid,
"timestamp": meta_rfc3339,
"cwd": "/",
"originator": "codex",
"cli_version": "0.0.0",
"instructions": null,
});
if let Some(provider) = model_provider {
payload["model_provider"] = json!(provider);
}
lines.push(
json!({
"timestamp": meta_rfc3339,
"type": "session_meta",
"payload": payload
})
.to_string(),
);
// Minimal user message entry as a persisted response item (with envelope timestamp)
lines.push(
json!({
"timestamp": meta_rfc3339,
"type":"response_item",
"payload": {
"type":"message",
"role":"user",
"content":[{"type":"input_text","text": preview}]
}
})
.to_string(),
);
// Add a matching user message event line to satisfy filters
lines.push(
json!({
"timestamp": meta_rfc3339,
"type":"event_msg",
"payload": {
"type":"user_message",
"message": preview,
"kind": "plain"
}
})
.to_string(),
);
fs::write(file_path, lines.join("\n") + "\n")?;
Ok(())
}

View File

@@ -7,8 +7,9 @@ mod fuzzy_file_search;
mod interrupt;
mod list_resume;
mod login;
mod model_list;
mod rate_limits;
mod send_message;
mod set_default_model;
mod user_agent;
mod user_info;
mod v2;

View File

@@ -6,9 +6,9 @@ use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::ListModelsParams;
use codex_app_server_protocol::ListModelsResponse;
use codex_app_server_protocol::Model;
use codex_app_server_protocol::ModelListParams;
use codex_app_server_protocol::ModelListResponse;
use codex_app_server_protocol::ReasoningEffortOption;
use codex_app_server_protocol::RequestId;
use codex_protocol::config_types::ReasoningEffort;
@@ -19,7 +19,7 @@ use tokio::time::timeout;
const DEFAULT_TIMEOUT: Duration = Duration::from_secs(10);
const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
#[tokio::test]
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
let codex_home = TempDir::new()?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
@@ -27,8 +27,8 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
let request_id = mcp
.send_list_models_request(ModelListParams {
limit: Some(100),
.send_list_models_request(ListModelsParams {
page_size: Some(100),
cursor: None,
})
.await?;
@@ -39,44 +39,14 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
)
.await??;
let ModelListResponse {
data: items,
next_cursor,
} = to_response::<ModelListResponse>(response)?;
let ListModelsResponse { items, next_cursor } = to_response::<ListModelsResponse>(response)?;
let expected_models = vec![
Model {
id: "gpt-5.1-codex-max".to_string(),
model: "gpt-5.1-codex-max".to_string(),
display_name: "gpt-5.1-codex-max".to_string(),
description: "Latest Codex-optimized flagship for deep and fast reasoning.".to_string(),
supported_reasoning_efforts: vec![
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::Low,
description: "Fast responses with lighter reasoning".to_string(),
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::Medium,
description: "Balances speed and reasoning depth for everyday tasks"
.to_string(),
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex problems".to_string(),
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::XHigh,
description: "Extra high reasoning depth for complex problems".to_string(),
},
],
default_reasoning_effort: ReasoningEffort::Medium,
is_default: true,
},
Model {
id: "gpt-5.1-codex".to_string(),
model: "gpt-5.1-codex".to_string(),
display_name: "gpt-5.1-codex".to_string(),
description: "Optimized for codex.".to_string(),
id: "gpt-5-codex".to_string(),
model: "gpt-5-codex".to_string(),
display_name: "gpt-5-codex".to_string(),
description: "Optimized for coding tasks with many tools.".to_string(),
supported_reasoning_efforts: vec![
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::Low,
@@ -93,33 +63,18 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
},
],
default_reasoning_effort: ReasoningEffort::Medium,
is_default: false,
is_default: true,
},
Model {
id: "gpt-5.1-codex-mini".to_string(),
model: "gpt-5.1-codex-mini".to_string(),
display_name: "gpt-5.1-codex-mini".to_string(),
description: "Optimized for codex. Cheaper, faster, but less capable.".to_string(),
supported_reasoning_efforts: vec![
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::Medium,
description: "Dynamically adjusts reasoning based on the task".to_string(),
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems"
.to_string(),
},
],
default_reasoning_effort: ReasoningEffort::Medium,
is_default: false,
},
Model {
id: "gpt-5.1".to_string(),
model: "gpt-5.1".to_string(),
display_name: "gpt-5.1".to_string(),
id: "gpt-5".to_string(),
model: "gpt-5".to_string(),
display_name: "gpt-5".to_string(),
description: "Broad world knowledge with strong general reasoning.".to_string(),
supported_reasoning_efforts: vec![
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::Minimal,
description: "Fastest responses with little reasoning".to_string(),
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::Low,
description: "Balances speed with some reasoning; useful for straightforward \
@@ -148,7 +103,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
Ok(())
}
#[tokio::test]
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn list_models_pagination_works() -> Result<()> {
let codex_home = TempDir::new()?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
@@ -156,8 +111,8 @@ async fn list_models_pagination_works() -> Result<()> {
timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
let first_request = mcp
.send_list_models_request(ModelListParams {
limit: Some(1),
.send_list_models_request(ListModelsParams {
page_size: Some(1),
cursor: None,
})
.await?;
@@ -168,18 +123,18 @@ async fn list_models_pagination_works() -> Result<()> {
)
.await??;
let ModelListResponse {
data: first_items,
let ListModelsResponse {
items: first_items,
next_cursor: first_cursor,
} = to_response::<ModelListResponse>(first_response)?;
} = to_response::<ListModelsResponse>(first_response)?;
assert_eq!(first_items.len(), 1);
assert_eq!(first_items[0].id, "gpt-5.1-codex-max");
assert_eq!(first_items[0].id, "gpt-5-codex");
let next_cursor = first_cursor.ok_or_else(|| anyhow!("cursor for second page"))?;
let second_request = mcp
.send_list_models_request(ModelListParams {
limit: Some(1),
.send_list_models_request(ListModelsParams {
page_size: Some(1),
cursor: Some(next_cursor.clone()),
})
.await?;
@@ -190,62 +145,18 @@ async fn list_models_pagination_works() -> Result<()> {
)
.await??;
let ModelListResponse {
data: second_items,
let ListModelsResponse {
items: second_items,
next_cursor: second_cursor,
} = to_response::<ModelListResponse>(second_response)?;
} = to_response::<ListModelsResponse>(second_response)?;
assert_eq!(second_items.len(), 1);
assert_eq!(second_items[0].id, "gpt-5.1-codex");
let third_cursor = second_cursor.ok_or_else(|| anyhow!("cursor for third page"))?;
let third_request = mcp
.send_list_models_request(ModelListParams {
limit: Some(1),
cursor: Some(third_cursor.clone()),
})
.await?;
let third_response: JSONRPCResponse = timeout(
DEFAULT_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(third_request)),
)
.await??;
let ModelListResponse {
data: third_items,
next_cursor: third_cursor,
} = to_response::<ModelListResponse>(third_response)?;
assert_eq!(third_items.len(), 1);
assert_eq!(third_items[0].id, "gpt-5.1-codex-mini");
let fourth_cursor = third_cursor.ok_or_else(|| anyhow!("cursor for fourth page"))?;
let fourth_request = mcp
.send_list_models_request(ModelListParams {
limit: Some(1),
cursor: Some(fourth_cursor.clone()),
})
.await?;
let fourth_response: JSONRPCResponse = timeout(
DEFAULT_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(fourth_request)),
)
.await??;
let ModelListResponse {
data: fourth_items,
next_cursor: fourth_cursor,
} = to_response::<ModelListResponse>(fourth_response)?;
assert_eq!(fourth_items.len(), 1);
assert_eq!(fourth_items[0].id, "gpt-5.1");
assert!(fourth_cursor.is_none());
assert_eq!(second_items[0].id, "gpt-5");
assert!(second_cursor.is_none());
Ok(())
}
#[tokio::test]
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn list_models_rejects_invalid_cursor() -> Result<()> {
let codex_home = TempDir::new()?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
@@ -253,8 +164,8 @@ async fn list_models_rejects_invalid_cursor() -> Result<()> {
timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
let request_id = mcp
.send_list_models_request(ModelListParams {
limit: None,
.send_list_models_request(ListModelsParams {
page_size: None,
cursor: Some("invalid".to_string()),
})
.await?;

View File

@@ -7,10 +7,10 @@ use codex_app_server_protocol::GetAccountRateLimitsResponse;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::LoginApiKeyParams;
use codex_app_server_protocol::RateLimitSnapshot;
use codex_app_server_protocol::RateLimitWindow;
use codex_app_server_protocol::RequestId;
use codex_core::auth::AuthCredentialsStoreMode;
use codex_protocol::protocol::RateLimitSnapshot;
use codex_protocol::protocol::RateLimitWindow;
use pretty_assertions::assert_eq;
use serde_json::json;
use std::path::Path;
@@ -26,7 +26,7 @@ use wiremock::matchers::path;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
#[tokio::test]
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_account_rate_limits_requires_auth() -> Result<()> {
let codex_home = TempDir::new()?;
@@ -51,7 +51,7 @@ async fn get_account_rate_limits_requires_auth() -> Result<()> {
Ok(())
}
#[tokio::test]
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
let codex_home = TempDir::new()?;
@@ -78,7 +78,7 @@ async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
Ok(())
}
#[tokio::test]
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
let codex_home = TempDir::new()?;
write_chatgpt_auth(
@@ -143,16 +143,15 @@ async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
let expected = GetAccountRateLimitsResponse {
rate_limits: RateLimitSnapshot {
primary: Some(RateLimitWindow {
used_percent: 42,
window_duration_mins: Some(60),
used_percent: 42.0,
window_minutes: Some(60),
resets_at: Some(primary_reset_timestamp),
}),
secondary: Some(RateLimitWindow {
used_percent: 5,
window_duration_mins: Some(1440),
used_percent: 5.0,
window_minutes: Some(1440),
resets_at: Some(secondary_reset_timestamp),
}),
credits: None,
},
};
assert_eq!(received, expected);

View File

@@ -57,7 +57,7 @@ fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
std::fs::write(
config_toml,
r#"
model = "gpt-5.1-codex-max"
model = "gpt-5-codex"
model_reasoning_effort = "medium"
"#,
)

View File

@@ -1,492 +0,0 @@
use anyhow::Result;
use anyhow::bail;
use app_test_support::McpProcess;
use app_test_support::to_response;
use app_test_support::ChatGptAuthFixture;
use app_test_support::write_chatgpt_auth;
use codex_app_server_protocol::Account;
use codex_app_server_protocol::AuthMode;
use codex_app_server_protocol::CancelLoginAccountParams;
use codex_app_server_protocol::CancelLoginAccountResponse;
use codex_app_server_protocol::GetAccountParams;
use codex_app_server_protocol::GetAccountResponse;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::LoginAccountResponse;
use codex_app_server_protocol::LogoutAccountResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ServerNotification;
use codex_core::auth::AuthCredentialsStoreMode;
use codex_login::login_with_api_key;
use codex_protocol::account::PlanType as AccountPlanType;
use pretty_assertions::assert_eq;
use serial_test::serial;
use std::path::Path;
use std::time::Duration;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
// Helper to create a minimal config.toml for the app server
#[derive(Default)]
struct CreateConfigTomlParams {
forced_method: Option<String>,
forced_workspace_id: Option<String>,
requires_openai_auth: Option<bool>,
}
fn create_config_toml(codex_home: &Path, params: CreateConfigTomlParams) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
let forced_line = if let Some(method) = params.forced_method {
format!("forced_login_method = \"{method}\"\n")
} else {
String::new()
};
let forced_workspace_line = if let Some(ws) = params.forced_workspace_id {
format!("forced_chatgpt_workspace_id = \"{ws}\"\n")
} else {
String::new()
};
let requires_line = match params.requires_openai_auth {
Some(true) => "requires_openai_auth = true\n".to_string(),
Some(false) => String::new(),
None => String::new(),
};
let contents = format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "danger-full-access"
{forced_line}
{forced_workspace_line}
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "http://127.0.0.1:0/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
{requires_line}
"#
);
std::fs::write(config_toml, contents)
}
#[tokio::test]
async fn logout_account_removes_auth_and_notifies() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
login_with_api_key(
codex_home.path(),
"sk-test-key",
AuthCredentialsStoreMode::File,
)?;
assert!(codex_home.path().join("auth.json").exists());
let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let id = mcp.send_logout_account_request().await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(id)),
)
.await??;
let _ok: LogoutAccountResponse = to_response(resp)?;
let note = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("account/updated"),
)
.await??;
let parsed: ServerNotification = note.try_into()?;
let ServerNotification::AccountUpdated(payload) = parsed else {
bail!("unexpected notification: {parsed:?}");
};
assert!(
payload.auth_mode.is_none(),
"auth_method should be None after logout"
);
assert!(
!codex_home.path().join("auth.json").exists(),
"auth.json should be deleted"
);
let get_id = mcp
.send_get_account_request(GetAccountParams {
refresh_token: false,
})
.await?;
let get_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(get_id)),
)
.await??;
let account: GetAccountResponse = to_response(get_resp)?;
assert_eq!(account.account, None);
Ok(())
}
#[tokio::test]
async fn login_account_api_key_succeeds_and_notifies() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let req_id = mcp
.send_login_account_api_key_request("sk-test-key")
.await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
)
.await??;
let login: LoginAccountResponse = to_response(resp)?;
assert_eq!(login, LoginAccountResponse::ApiKey {});
let note = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("account/login/completed"),
)
.await??;
let parsed: ServerNotification = note.try_into()?;
let ServerNotification::AccountLoginCompleted(payload) = parsed else {
bail!("unexpected notification: {parsed:?}");
};
pretty_assertions::assert_eq!(payload.login_id, None);
pretty_assertions::assert_eq!(payload.success, true);
pretty_assertions::assert_eq!(payload.error, None);
let note = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("account/updated"),
)
.await??;
let parsed: ServerNotification = note.try_into()?;
let ServerNotification::AccountUpdated(payload) = parsed else {
bail!("unexpected notification: {parsed:?}");
};
pretty_assertions::assert_eq!(payload.auth_mode, Some(AuthMode::ApiKey));
assert!(codex_home.path().join("auth.json").exists());
Ok(())
}
#[tokio::test]
async fn login_account_api_key_rejected_when_forced_chatgpt() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
forced_method: Some("chatgpt".to_string()),
..Default::default()
},
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let request_id = mcp
.send_login_account_api_key_request("sk-test-key")
.await?;
let err: JSONRPCError = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
)
.await??;
assert_eq!(
err.error.message,
"API key login is disabled. Use ChatGPT login instead."
);
Ok(())
}
#[tokio::test]
async fn login_account_chatgpt_rejected_when_forced_api() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
forced_method: Some("api".to_string()),
..Default::default()
},
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let request_id = mcp.send_login_account_chatgpt_request().await?;
let err: JSONRPCError = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
)
.await??;
assert_eq!(
err.error.message,
"ChatGPT login is disabled. Use API key login instead."
);
Ok(())
}
#[tokio::test]
// Serialize tests that launch the login server since it binds to a fixed port.
#[serial(login_port)]
async fn login_account_chatgpt_start() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let request_id = mcp.send_login_account_chatgpt_request().await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await??;
let login: LoginAccountResponse = to_response(resp)?;
let LoginAccountResponse::Chatgpt { login_id, auth_url } = login else {
bail!("unexpected login response: {login:?}");
};
assert!(
auth_url.contains("redirect_uri=http%3A%2F%2Flocalhost"),
"auth_url should contain a redirect_uri to localhost"
);
let cancel_id = mcp
.send_cancel_login_account_request(CancelLoginAccountParams {
login_id: login_id.clone(),
})
.await?;
let cancel_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(cancel_id)),
)
.await??;
let _ok: CancelLoginAccountResponse = to_response(cancel_resp)?;
let note = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("account/login/completed"),
)
.await??;
let parsed: ServerNotification = note.try_into()?;
let ServerNotification::AccountLoginCompleted(payload) = parsed else {
bail!("unexpected notification: {parsed:?}");
};
pretty_assertions::assert_eq!(payload.login_id, Some(login_id));
pretty_assertions::assert_eq!(payload.success, false);
assert!(
payload.error.is_some(),
"expected a non-empty error on cancel"
);
let maybe_updated = timeout(
Duration::from_millis(500),
mcp.read_stream_until_notification_message("account/updated"),
)
.await;
assert!(
maybe_updated.is_err(),
"account/updated should not be emitted when login is cancelled"
);
Ok(())
}
#[tokio::test]
// Serialize tests that launch the login server since it binds to a fixed port.
#[serial(login_port)]
async fn login_account_chatgpt_includes_forced_workspace_query_param() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
forced_workspace_id: Some("ws-forced".to_string()),
..Default::default()
},
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let request_id = mcp.send_login_account_chatgpt_request().await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await??;
let login: LoginAccountResponse = to_response(resp)?;
let LoginAccountResponse::Chatgpt { auth_url, .. } = login else {
bail!("unexpected login response: {login:?}");
};
assert!(
auth_url.contains("allowed_workspace_id=ws-forced"),
"auth URL should include forced workspace"
);
Ok(())
}
#[tokio::test]
async fn get_account_no_auth() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
requires_openai_auth: Some(true),
..Default::default()
},
)?;
let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let params = GetAccountParams {
refresh_token: false,
};
let request_id = mcp.send_get_account_request(params).await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await??;
let account: GetAccountResponse = to_response(resp)?;
assert_eq!(account.account, None, "expected no account");
assert_eq!(account.requires_openai_auth, true);
Ok(())
}
#[tokio::test]
async fn get_account_with_api_key() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
requires_openai_auth: Some(true),
..Default::default()
},
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let req_id = mcp
.send_login_account_api_key_request("sk-test-key")
.await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
)
.await??;
let _login_ok = to_response::<LoginAccountResponse>(resp)?;
let params = GetAccountParams {
refresh_token: false,
};
let request_id = mcp.send_get_account_request(params).await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await??;
let received: GetAccountResponse = to_response(resp)?;
let expected = GetAccountResponse {
account: Some(Account::ApiKey {}),
requires_openai_auth: true,
};
assert_eq!(received, expected);
Ok(())
}
#[tokio::test]
async fn get_account_when_auth_not_required() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
requires_openai_auth: Some(false),
..Default::default()
},
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let params = GetAccountParams {
refresh_token: false,
};
let request_id = mcp.send_get_account_request(params).await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await??;
let received: GetAccountResponse = to_response(resp)?;
let expected = GetAccountResponse {
account: None,
requires_openai_auth: false,
};
assert_eq!(received, expected);
Ok(())
}
#[tokio::test]
async fn get_account_with_chatgpt() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(
codex_home.path(),
CreateConfigTomlParams {
requires_openai_auth: Some(true),
..Default::default()
},
)?;
write_chatgpt_auth(
codex_home.path(),
ChatGptAuthFixture::new("access-chatgpt")
.email("user@example.com")
.plan_type("pro"),
AuthCredentialsStoreMode::File,
)?;
let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let params = GetAccountParams {
refresh_token: false,
};
let request_id = mcp.send_get_account_request(params).await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
)
.await??;
let received: GetAccountResponse = to_response(resp)?;
let expected = GetAccountResponse {
account: Some(Account::Chatgpt {
email: "user@example.com".to_string(),
plan_type: AccountPlanType::Pro,
}),
requires_openai_auth: true,
};
assert_eq!(received, expected);
Ok(())
}

View File

@@ -1,10 +0,0 @@
mod account;
mod model_list;
mod rate_limits;
mod review;
mod thread_archive;
mod thread_list;
mod thread_resume;
mod thread_start;
mod turn_interrupt;
mod turn_start;

View File

@@ -1,279 +0,0 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server_unchecked;
use app_test_support::to_response;
use codex_app_server_protocol::ItemCompletedNotification;
use codex_app_server_protocol::ItemStartedNotification;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ReviewStartParams;
use codex_app_server_protocol::ReviewTarget;
use codex_app_server_protocol::ThreadItem;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::TurnStartResponse;
use codex_app_server_protocol::TurnStatus;
use serde_json::json;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
#[tokio::test]
async fn review_start_runs_review_turn_and_emits_code_review_item() -> Result<()> {
let review_payload = json!({
"findings": [
{
"title": "Prefer Stylize helpers",
"body": "Use .dim()/.bold() chaining instead of manual Style.",
"confidence_score": 0.9,
"priority": 1,
"code_location": {
"absolute_file_path": "/tmp/file.rs",
"line_range": {"start": 10, "end": 20}
}
}
],
"overall_correctness": "good",
"overall_explanation": "Looks solid overall with minor polish suggested.",
"overall_confidence_score": 0.75
})
.to_string();
let responses = vec![create_final_assistant_message_sse_response(
&review_payload,
)?];
let server = create_mock_chat_completions_server_unchecked(responses).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_id = start_default_thread(&mut mcp).await?;
let review_req = mcp
.send_review_start_request(ReviewStartParams {
thread_id: thread_id.clone(),
append_to_original_thread: true,
target: ReviewTarget::Commit {
sha: "1234567deadbeef".to_string(),
title: Some("Tidy UI colors".to_string()),
},
})
.await?;
let review_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(review_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(review_resp)?;
let turn_id = turn.id.clone();
assert_eq!(turn.status, TurnStatus::InProgress);
assert_eq!(turn.items.len(), 1);
match &turn.items[0] {
ThreadItem::UserMessage { content, .. } => {
assert_eq!(content.len(), 1);
assert!(matches!(
&content[0],
codex_app_server_protocol::UserInput::Text { .. }
));
}
other => panic!("expected user message, got {other:?}"),
}
let _started: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/started"),
)
.await??;
let item_started: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("item/started"),
)
.await??;
let started: ItemStartedNotification =
serde_json::from_value(item_started.params.expect("params must be present"))?;
match started.item {
ThreadItem::CodeReview { id, review } => {
assert_eq!(id, turn_id);
assert_eq!(review, "commit 1234567");
}
other => panic!("expected code review item, got {other:?}"),
}
let mut review_body: Option<String> = None;
for _ in 0..5 {
let review_notif: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("item/completed"),
)
.await??;
let completed: ItemCompletedNotification =
serde_json::from_value(review_notif.params.expect("params must be present"))?;
match completed.item {
ThreadItem::CodeReview { id, review } => {
assert_eq!(id, turn_id);
review_body = Some(review);
break;
}
ThreadItem::UserMessage { .. } => continue,
other => panic!("unexpected item/completed payload: {other:?}"),
}
}
let review = review_body.expect("did not observe a code review item");
assert!(review.contains("Prefer Stylize helpers"));
assert!(review.contains("/tmp/file.rs:10-20"));
Ok(())
}
#[tokio::test]
async fn review_start_rejects_empty_base_branch() -> Result<()> {
let server = create_mock_chat_completions_server_unchecked(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_id = start_default_thread(&mut mcp).await?;
let request_id = mcp
.send_review_start_request(ReviewStartParams {
thread_id,
append_to_original_thread: true,
target: ReviewTarget::BaseBranch {
branch: " ".to_string(),
},
})
.await?;
let error: JSONRPCError = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
)
.await??;
assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
assert!(
error.error.message.contains("branch must not be empty"),
"unexpected message: {}",
error.error.message
);
Ok(())
}
#[tokio::test]
async fn review_start_rejects_empty_commit_sha() -> Result<()> {
let server = create_mock_chat_completions_server_unchecked(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_id = start_default_thread(&mut mcp).await?;
let request_id = mcp
.send_review_start_request(ReviewStartParams {
thread_id,
append_to_original_thread: true,
target: ReviewTarget::Commit {
sha: "\t".to_string(),
title: None,
},
})
.await?;
let error: JSONRPCError = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
)
.await??;
assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
assert!(
error.error.message.contains("sha must not be empty"),
"unexpected message: {}",
error.error.message
);
Ok(())
}
#[tokio::test]
async fn review_start_rejects_empty_custom_instructions() -> Result<()> {
let server = create_mock_chat_completions_server_unchecked(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_id = start_default_thread(&mut mcp).await?;
let request_id = mcp
.send_review_start_request(ReviewStartParams {
thread_id,
append_to_original_thread: true,
target: ReviewTarget::Custom {
instructions: "\n\n".to_string(),
},
})
.await?;
let error: JSONRPCError = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
)
.await??;
assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
assert!(
error
.error
.message
.contains("instructions must not be empty"),
"unexpected message: {}",
error.error.message
);
Ok(())
}
async fn start_default_thread(mcp: &mut McpProcess) -> Result<String> {
let thread_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let thread_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
Ok(thread.id)
}
fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "read-only"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -1,93 +0,0 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ThreadArchiveParams;
use codex_app_server_protocol::ThreadArchiveResponse;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_core::ARCHIVED_SESSIONS_SUBDIR;
use codex_core::find_conversation_path_by_id_str;
use std::path::Path;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn thread_archive_moves_rollout_into_archived_directory() -> Result<()> {
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Start a thread.
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
assert!(!thread.id.is_empty());
// Locate the rollout path recorded for this thread id.
let rollout_path = find_conversation_path_by_id_str(codex_home.path(), &thread.id)
.await?
.expect("expected rollout path for thread id to exist");
assert!(
rollout_path.exists(),
"expected {} to exist",
rollout_path.display()
);
// Archive the thread.
let archive_id = mcp
.send_thread_archive_request(ThreadArchiveParams {
thread_id: thread.id.clone(),
})
.await?;
let archive_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(archive_id)),
)
.await??;
let _: ThreadArchiveResponse = to_response::<ThreadArchiveResponse>(archive_resp)?;
// Verify file moved.
let archived_directory = codex_home.path().join(ARCHIVED_SESSIONS_SUBDIR);
// The archived file keeps the original filename (rollout-...-<id>.jsonl).
let archived_rollout_path =
archived_directory.join(rollout_path.file_name().expect("rollout file name"));
assert!(
!rollout_path.exists(),
"expected rollout path {} to be moved",
rollout_path.display()
);
assert!(
archived_rollout_path.exists(),
"expected archived rollout path {} to exist",
archived_rollout_path.display()
);
Ok(())
}
fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(config_toml, config_contents())
}
fn config_contents() -> &'static str {
r#"model = "mock-model"
approval_policy = "never"
sandbox_mode = "read-only"
"#
}

View File

@@ -1,185 +0,0 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_fake_rollout;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ThreadListParams;
use codex_app_server_protocol::ThreadListResponse;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn thread_list_basic_empty() -> Result<()> {
let codex_home = TempDir::new()?;
create_minimal_config(codex_home.path())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// List threads in an empty CODEX_HOME; should return an empty page with nextCursor: null.
let list_id = mcp
.send_thread_list_request(ThreadListParams {
cursor: None,
limit: Some(10),
model_providers: None,
})
.await?;
let list_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
)
.await??;
let ThreadListResponse { data, next_cursor } = to_response::<ThreadListResponse>(list_resp)?;
assert!(data.is_empty());
assert_eq!(next_cursor, None);
Ok(())
}
// Minimal config.toml for listing.
fn create_minimal_config(codex_home: &std::path::Path) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
r#"
model = "mock-model"
approval_policy = "never"
"#,
)
}
#[tokio::test]
async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
let codex_home = TempDir::new()?;
create_minimal_config(codex_home.path())?;
// Create three rollouts so we can paginate with limit=2.
let _a = create_fake_rollout(
codex_home.path(),
"2025-01-02T12-00-00",
"2025-01-02T12:00:00Z",
"Hello",
Some("mock_provider"),
)?;
let _b = create_fake_rollout(
codex_home.path(),
"2025-01-01T13-00-00",
"2025-01-01T13:00:00Z",
"Hello",
Some("mock_provider"),
)?;
let _c = create_fake_rollout(
codex_home.path(),
"2025-01-01T12-00-00",
"2025-01-01T12:00:00Z",
"Hello",
Some("mock_provider"),
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Page 1: limit 2 → expect next_cursor Some.
let page1_id = mcp
.send_thread_list_request(ThreadListParams {
cursor: None,
limit: Some(2),
model_providers: Some(vec!["mock_provider".to_string()]),
})
.await?;
let page1_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(page1_id)),
)
.await??;
let ThreadListResponse {
data: data1,
next_cursor: cursor1,
} = to_response::<ThreadListResponse>(page1_resp)?;
assert_eq!(data1.len(), 2);
for thread in &data1 {
assert_eq!(thread.preview, "Hello");
assert_eq!(thread.model_provider, "mock_provider");
assert!(thread.created_at > 0);
}
let cursor1 = cursor1.expect("expected nextCursor on first page");
// Page 2: with cursor → expect next_cursor None when no more results.
let page2_id = mcp
.send_thread_list_request(ThreadListParams {
cursor: Some(cursor1),
limit: Some(2),
model_providers: Some(vec!["mock_provider".to_string()]),
})
.await?;
let page2_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(page2_id)),
)
.await??;
let ThreadListResponse {
data: data2,
next_cursor: cursor2,
} = to_response::<ThreadListResponse>(page2_resp)?;
assert!(data2.len() <= 2);
for thread in &data2 {
assert_eq!(thread.preview, "Hello");
assert_eq!(thread.model_provider, "mock_provider");
assert!(thread.created_at > 0);
}
assert_eq!(cursor2, None, "expected nextCursor to be null on last page");
Ok(())
}
#[tokio::test]
async fn thread_list_respects_provider_filter() -> Result<()> {
let codex_home = TempDir::new()?;
create_minimal_config(codex_home.path())?;
// Create rollouts under two providers.
let _a = create_fake_rollout(
codex_home.path(),
"2025-01-02T10-00-00",
"2025-01-02T10:00:00Z",
"X",
Some("mock_provider"),
)?; // mock_provider
let _b = create_fake_rollout(
codex_home.path(),
"2025-01-02T11-00-00",
"2025-01-02T11:00:00Z",
"X",
Some("other_provider"),
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Filter to only other_provider; expect 1 item, nextCursor None.
let list_id = mcp
.send_thread_list_request(ThreadListParams {
cursor: None,
limit: Some(10),
model_providers: Some(vec!["other_provider".to_string()]),
})
.await?;
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
)
.await??;
let ThreadListResponse { data, next_cursor } = to_response::<ThreadListResponse>(resp)?;
assert_eq!(data.len(), 1);
assert_eq!(next_cursor, None);
let thread = &data[0];
assert_eq!(thread.preview, "X");
assert_eq!(thread.model_provider, "other_provider");
let expected_ts = chrono::DateTime::parse_from_rfc3339("2025-01-02T11:00:00Z")?.timestamp();
assert_eq!(thread.created_at, expected_ts);
Ok(())
}

View File

@@ -1,249 +0,0 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_fake_rollout;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ThreadItem;
use codex_app_server_protocol::ThreadResumeParams;
use codex_app_server_protocol::ThreadResumeResponse;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::TurnStatus;
use codex_app_server_protocol::UserInput;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ResponseItem;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn thread_resume_returns_original_thread() -> Result<()> {
let server = create_mock_chat_completions_server(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Start a thread.
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("gpt-5.1-codex-max".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
// Resume it via v2 API.
let resume_id = mcp
.send_thread_resume_request(ThreadResumeParams {
thread_id: thread.id.clone(),
..Default::default()
})
.await?;
let resume_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
)
.await??;
let ThreadResumeResponse {
thread: resumed, ..
} = to_response::<ThreadResumeResponse>(resume_resp)?;
assert_eq!(resumed, thread);
Ok(())
}
#[tokio::test]
async fn thread_resume_returns_rollout_history() -> Result<()> {
let server = create_mock_chat_completions_server(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let preview = "Saved user message";
let conversation_id = create_fake_rollout(
codex_home.path(),
"2025-01-05T12-00-00",
"2025-01-05T12:00:00Z",
preview,
Some("mock_provider"),
)?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let resume_id = mcp
.send_thread_resume_request(ThreadResumeParams {
thread_id: conversation_id.clone(),
..Default::default()
})
.await?;
let resume_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
)
.await??;
let ThreadResumeResponse { thread, .. } = to_response::<ThreadResumeResponse>(resume_resp)?;
assert_eq!(thread.id, conversation_id);
assert_eq!(thread.preview, preview);
assert_eq!(thread.model_provider, "mock_provider");
assert!(thread.path.is_absolute());
assert_eq!(
thread.turns.len(),
1,
"expected rollouts to include one turn"
);
let turn = &thread.turns[0];
assert_eq!(turn.status, TurnStatus::Completed);
assert_eq!(turn.items.len(), 1, "expected user message item");
match &turn.items[0] {
ThreadItem::UserMessage { content, .. } => {
assert_eq!(
content,
&vec![UserInput::Text {
text: preview.to_string()
}]
);
}
other => panic!("expected user message item, got {other:?}"),
}
Ok(())
}
#[tokio::test]
async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
let server = create_mock_chat_completions_server(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("gpt-5.1-codex-max".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
let thread_path = thread.path.clone();
let resume_id = mcp
.send_thread_resume_request(ThreadResumeParams {
thread_id: "not-a-valid-thread-id".to_string(),
path: Some(thread_path),
..Default::default()
})
.await?;
let resume_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
)
.await??;
let ThreadResumeResponse {
thread: resumed, ..
} = to_response::<ThreadResumeResponse>(resume_resp)?;
assert_eq!(resumed, thread);
Ok(())
}
#[tokio::test]
async fn thread_resume_supports_history_and_overrides() -> Result<()> {
let server = create_mock_chat_completions_server(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Start a thread.
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("gpt-5.1-codex-max".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
let history_text = "Hello from history";
let history = vec![ResponseItem::Message {
id: None,
role: "user".to_string(),
content: vec![ContentItem::InputText {
text: history_text.to_string(),
}],
}];
// Resume with explicit history and override the model.
let resume_id = mcp
.send_thread_resume_request(ThreadResumeParams {
thread_id: thread.id,
history: Some(history),
model: Some("mock-model".to_string()),
model_provider: Some("mock_provider".to_string()),
..Default::default()
})
.await?;
let resume_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
)
.await??;
let ThreadResumeResponse {
thread: resumed,
model_provider,
..
} = to_response::<ThreadResumeResponse>(resume_resp)?;
assert!(!resumed.id.is_empty());
assert_eq!(model_provider, "mock_provider");
assert_eq!(resumed.preview, history_text);
Ok(())
}
// Helper to create a config.toml pointing at the mock model server.
fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "read-only"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -1,94 +0,0 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::ThreadStartedNotification;
use std::path::Path;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
// Provide a mock server and config so model wiring is valid.
let server = create_mock_chat_completions_server(vec![]).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
// Start server and initialize.
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Start a v2 thread with an explicit model override.
let req_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("gpt-5.1".to_string()),
..Default::default()
})
.await?;
// Expect a proper JSON-RPC response with a thread id.
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
)
.await??;
let ThreadStartResponse {
thread,
model_provider,
..
} = to_response::<ThreadStartResponse>(resp)?;
assert!(!thread.id.is_empty(), "thread id should not be empty");
assert!(
thread.preview.is_empty(),
"new threads should start with an empty preview"
);
assert_eq!(model_provider, "mock_provider");
assert!(
thread.created_at > 0,
"created_at should be a positive UNIX timestamp"
);
// A corresponding thread/started notification should arrive.
let notif: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("thread/started"),
)
.await??;
let started: ThreadStartedNotification =
serde_json::from_value(notif.params.expect("params must be present"))?;
assert_eq!(started.thread, thread);
Ok(())
}
// Helper to create a config.toml pointing at the mock model server.
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "read-only"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -1,142 +0,0 @@
#![cfg(unix)]
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::create_shell_command_sse_response;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::TurnCompletedNotification;
use codex_app_server_protocol::TurnInterruptParams;
use codex_app_server_protocol::TurnInterruptResponse;
use codex_app_server_protocol::TurnStartParams;
use codex_app_server_protocol::TurnStartResponse;
use codex_app_server_protocol::TurnStatus;
use codex_app_server_protocol::UserInput as V2UserInput;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn turn_interrupt_aborts_running_turn() -> Result<()> {
// Use a portable sleep command to keep the turn running.
#[cfg(target_os = "windows")]
let shell_command = vec![
"powershell".to_string(),
"-Command".to_string(),
"Start-Sleep -Seconds 10".to_string(),
];
#[cfg(not(target_os = "windows"))]
let shell_command = vec!["sleep".to_string(), "10".to_string()];
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home)?;
let working_directory = tmp.path().join("workdir");
std::fs::create_dir(&working_directory)?;
// Mock server: long-running shell command then (after abort) nothing else needed.
let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
shell_command.clone(),
Some(&working_directory),
Some(10_000),
"call_sleep",
)?])
.await;
create_config_toml(&codex_home, &server.uri())?;
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Start a v2 thread and capture its id.
let thread_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let thread_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
// Start a turn that triggers a long-running command.
let turn_req = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "run sleep".to_string(),
}],
cwd: Some(working_directory.clone()),
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
// Give the command a brief moment to start.
tokio::time::sleep(std::time::Duration::from_secs(1)).await;
// Interrupt the in-progress turn by id (v2 API).
let interrupt_id = mcp
.send_turn_interrupt_request(TurnInterruptParams {
thread_id: thread.id,
turn_id: turn.id,
})
.await?;
let interrupt_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(interrupt_id)),
)
.await??;
let _resp: TurnInterruptResponse = to_response::<TurnInterruptResponse>(interrupt_resp)?;
let completed_notif: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/completed"),
)
.await??;
let completed: TurnCompletedNotification = serde_json::from_value(
completed_notif
.params
.expect("turn/completed params must be present"),
)?;
assert_eq!(completed.turn.status, TurnStatus::Interrupted);
Ok(())
}
// Helper to create a config.toml pointing at the mock model server.
fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "workspace-write"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -1,942 +0,0 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_apply_patch_sse_response;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::create_mock_chat_completions_server_unchecked;
use app_test_support::create_shell_command_sse_response;
use app_test_support::format_with_current_shell_display;
use app_test_support::to_response;
use codex_app_server_protocol::ApprovalDecision;
use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
use codex_app_server_protocol::CommandExecutionStatus;
use codex_app_server_protocol::FileChangeRequestApprovalResponse;
use codex_app_server_protocol::ItemCompletedNotification;
use codex_app_server_protocol::ItemStartedNotification;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::PatchApplyStatus;
use codex_app_server_protocol::PatchChangeKind;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ServerRequest;
use codex_app_server_protocol::ThreadItem;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::TurnCompletedNotification;
use codex_app_server_protocol::TurnStartParams;
use codex_app_server_protocol::TurnStartResponse;
use codex_app_server_protocol::TurnStartedNotification;
use codex_app_server_protocol::TurnStatus;
use codex_app_server_protocol::UserInput as V2UserInput;
use codex_core::protocol_config_types::ReasoningEffort;
use codex_core::protocol_config_types::ReasoningSummary;
use core_test_support::skip_if_no_network;
use pretty_assertions::assert_eq;
use std::path::Path;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<()> {
// Provide a mock server and config so model wiring is valid.
// Three Codex turns hit the mock model (session start + two turn/start calls).
let responses = vec![
create_final_assistant_message_sse_response("Done")?,
create_final_assistant_message_sse_response("Done")?,
create_final_assistant_message_sse_response("Done")?,
];
let server = create_mock_chat_completions_server_unchecked(responses).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri(), "never")?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// Start a thread (v2) and capture its id.
let thread_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let thread_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
// Start a turn with only input and thread_id set (no overrides).
let turn_req = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "Hello".to_string(),
}],
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
assert!(!turn.id.is_empty());
// Expect a turn/started notification.
let notif: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/started"),
)
.await??;
let started: TurnStartedNotification =
serde_json::from_value(notif.params.expect("params must be present"))?;
assert_eq!(
started.turn.status,
codex_app_server_protocol::TurnStatus::InProgress
);
// Send a second turn that exercises the overrides path: change the model.
let turn_req2 = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "Second".to_string(),
}],
model: Some("mock-model-override".to_string()),
..Default::default()
})
.await?;
let turn_resp2: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req2)),
)
.await??;
let TurnStartResponse { turn: turn2 } = to_response::<TurnStartResponse>(turn_resp2)?;
assert!(!turn2.id.is_empty());
// Ensure the second turn has a different id than the first.
assert_ne!(turn.id, turn2.id);
// Expect a second turn/started notification as well.
let _notif2: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/started"),
)
.await??;
let completed_notif: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/completed"),
)
.await??;
let completed: TurnCompletedNotification = serde_json::from_value(
completed_notif
.params
.expect("turn/completed params must be present"),
)?;
assert_eq!(completed.turn.status, TurnStatus::Completed);
Ok(())
}
#[tokio::test]
async fn turn_start_accepts_local_image_input() -> Result<()> {
// Two Codex turns hit the mock model (session start + turn/start).
let responses = vec![
create_final_assistant_message_sse_response("Done")?,
create_final_assistant_message_sse_response("Done")?,
];
// Use the unchecked variant because the request payload includes a LocalImage
// which the strict matcher does not currently cover.
let server = create_mock_chat_completions_server_unchecked(responses).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri(), "never")?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let thread_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
let image_path = codex_home.path().join("image.png");
// No need to actually write the file; we just exercise the input path.
let turn_req = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::LocalImage { path: image_path }],
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
assert!(!turn.id.is_empty());
// This test only validates that turn/start responds and returns a turn.
Ok(())
}
#[tokio::test]
async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
skip_if_no_network!(Ok(()));
let tmp = TempDir::new()?;
let codex_home = tmp.path().to_path_buf();
// Mock server: first turn requests a shell call (elicitation), then completes.
// Second turn same, but we'll set approval_policy=never to avoid elicitation.
let responses = vec![
create_shell_command_sse_response(
vec![
"python3".to_string(),
"-c".to_string(),
"print(42)".to_string(),
],
None,
Some(5000),
"call1",
)?,
create_final_assistant_message_sse_response("done 1")?,
create_shell_command_sse_response(
vec![
"python3".to_string(),
"-c".to_string(),
"print(42)".to_string(),
],
None,
Some(5000),
"call2",
)?,
create_final_assistant_message_sse_response("done 2")?,
];
let server = create_mock_chat_completions_server(responses).await;
// Default approval is untrusted to force elicitation on first turn.
create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
let mut mcp = McpProcess::new(codex_home.as_path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// thread/start
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
// turn/start — expect CommandExecutionRequestApproval request from server
let first_turn_id = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "run python".to_string(),
}],
..Default::default()
})
.await?;
// Acknowledge RPC
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(first_turn_id)),
)
.await??;
// Receive elicitation
let server_req = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_request_message(),
)
.await??;
let ServerRequest::CommandExecutionRequestApproval { request_id, params } = server_req else {
panic!("expected CommandExecutionRequestApproval request");
};
assert_eq!(params.item_id, "call1");
// Approve and wait for task completion
mcp.send_response(
request_id,
serde_json::json!({ "decision": codex_core::protocol::ReviewDecision::Approved }),
)
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/completed"),
)
.await??;
// Second turn with approval_policy=never should not elicit approval
let second_turn_id = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "run python again".to_string(),
}],
approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::DangerFullAccess),
model: Some("mock-model".to_string()),
effort: Some(ReasoningEffort::Medium),
summary: Some(ReasoningSummary::Auto),
..Default::default()
})
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(second_turn_id)),
)
.await??;
// Ensure we do NOT receive a CommandExecutionRequestApproval request before task completes
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("turn/completed"),
)
.await??;
Ok(())
}
#[tokio::test]
async fn turn_start_exec_approval_decline_v2() -> Result<()> {
skip_if_no_network!(Ok(()));
let tmp = TempDir::new()?;
let codex_home = tmp.path().to_path_buf();
let workspace = tmp.path().join("workspace");
std::fs::create_dir(&workspace)?;
let responses = vec![
create_shell_command_sse_response(
vec![
"python3".to_string(),
"-c".to_string(),
"print(42)".to_string(),
],
None,
Some(5000),
"call-decline",
)?,
create_final_assistant_message_sse_response("done")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
let mut mcp = McpProcess::new(codex_home.as_path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
let turn_id = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "run python".to_string(),
}],
cwd: Some(workspace.clone()),
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
let started_command_execution = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let started_notif = mcp
.read_stream_until_notification_message("item/started")
.await?;
let started: ItemStartedNotification =
serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
if let ThreadItem::CommandExecution { .. } = started.item {
return Ok::<ThreadItem, anyhow::Error>(started.item);
}
}
})
.await??;
let ThreadItem::CommandExecution { id, status, .. } = started_command_execution else {
unreachable!("loop ensures we break on command execution items");
};
assert_eq!(id, "call-decline");
assert_eq!(status, CommandExecutionStatus::InProgress);
let server_req = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_request_message(),
)
.await??;
let ServerRequest::CommandExecutionRequestApproval { request_id, params } = server_req else {
panic!("expected CommandExecutionRequestApproval request")
};
assert_eq!(params.item_id, "call-decline");
assert_eq!(params.thread_id, thread.id);
assert_eq!(params.turn_id, turn.id);
mcp.send_response(
request_id,
serde_json::to_value(CommandExecutionRequestApprovalResponse {
decision: ApprovalDecision::Decline,
accept_settings: None,
})?,
)
.await?;
let completed_command_execution = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let completed_notif = mcp
.read_stream_until_notification_message("item/completed")
.await?;
let completed: ItemCompletedNotification = serde_json::from_value(
completed_notif
.params
.clone()
.expect("item/completed params"),
)?;
if let ThreadItem::CommandExecution { .. } = completed.item {
return Ok::<ThreadItem, anyhow::Error>(completed.item);
}
}
})
.await??;
let ThreadItem::CommandExecution {
id,
status,
exit_code,
aggregated_output,
..
} = completed_command_execution
else {
unreachable!("loop ensures we break on command execution items");
};
assert_eq!(id, "call-decline");
assert_eq!(status, CommandExecutionStatus::Declined);
assert!(exit_code.is_none());
assert!(aggregated_output.is_none());
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
Ok(())
}
#[tokio::test]
async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
skip_if_no_network!(Ok(()));
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home)?;
let workspace_root = tmp.path().join("workspace");
std::fs::create_dir(&workspace_root)?;
let first_cwd = workspace_root.join("turn1");
let second_cwd = workspace_root.join("turn2");
std::fs::create_dir(&first_cwd)?;
std::fs::create_dir(&second_cwd)?;
let responses = vec![
create_shell_command_sse_response(
vec!["echo".to_string(), "first".to_string(), "turn".to_string()],
None,
Some(5000),
"call-first",
)?,
create_final_assistant_message_sse_response("done first")?,
create_shell_command_sse_response(
vec!["echo".to_string(), "second".to_string(), "turn".to_string()],
None,
Some(5000),
"call-second",
)?,
create_final_assistant_message_sse_response("done second")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// thread/start
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
// first turn with workspace-write sandbox and first_cwd
let first_turn = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "first turn".to_string(),
}],
cwd: Some(first_cwd.clone()),
approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::WorkspaceWrite {
writable_roots: vec![first_cwd.clone()],
network_access: false,
exclude_tmpdir_env_var: false,
exclude_slash_tmp: false,
}),
model: Some("mock-model".to_string()),
effort: Some(ReasoningEffort::Medium),
summary: Some(ReasoningSummary::Auto),
})
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(first_turn)),
)
.await??;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
// second turn with workspace-write and second_cwd, ensure exec begins in second_cwd
let second_turn = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "second turn".to_string(),
}],
cwd: Some(second_cwd.clone()),
approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::DangerFullAccess),
model: Some("mock-model".to_string()),
effort: Some(ReasoningEffort::Medium),
summary: Some(ReasoningSummary::Auto),
})
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(second_turn)),
)
.await??;
let command_exec_item = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let item_started_notification = mcp
.read_stream_until_notification_message("item/started")
.await?;
let params = item_started_notification
.params
.clone()
.expect("item/started params");
let item_started: ItemStartedNotification =
serde_json::from_value(params).expect("deserialize item/started notification");
if matches!(item_started.item, ThreadItem::CommandExecution { .. }) {
return Ok::<ThreadItem, anyhow::Error>(item_started.item);
}
}
})
.await??;
let ThreadItem::CommandExecution {
cwd,
command,
status,
..
} = command_exec_item
else {
unreachable!("loop ensures we break on command execution items");
};
assert_eq!(cwd, second_cwd);
let expected_command = format_with_current_shell_display("echo second turn");
assert_eq!(command, expected_command);
assert_eq!(status, CommandExecutionStatus::InProgress);
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
Ok(())
}
#[tokio::test]
async fn turn_start_file_change_approval_v2() -> Result<()> {
skip_if_no_network!(Ok(()));
if cfg!(windows) {
// TODO apply_patch approvals are not parsed from powershell commands yet
return Ok(());
}
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home)?;
let workspace = tmp.path().join("workspace");
std::fs::create_dir(&workspace)?;
let patch = r#"*** Begin Patch
*** Add File: README.md
+new line
*** End Patch
"#;
let responses = vec![
create_apply_patch_sse_response(patch, "patch-call")?,
create_final_assistant_message_sse_response("patch applied")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let start_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
cwd: Some(workspace.to_string_lossy().into_owned()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
let turn_req = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "apply patch".into(),
}],
cwd: Some(workspace.clone()),
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
let started_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let started_notif = mcp
.read_stream_until_notification_message("item/started")
.await?;
let started: ItemStartedNotification =
serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
if let ThreadItem::FileChange { .. } = started.item {
return Ok::<ThreadItem, anyhow::Error>(started.item);
}
}
})
.await??;
let ThreadItem::FileChange {
ref id,
status,
ref changes,
} = started_file_change
else {
unreachable!("loop ensures we break on file change items");
};
assert_eq!(id, "patch-call");
assert_eq!(status, PatchApplyStatus::InProgress);
let started_changes = changes.clone();
let server_req = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_request_message(),
)
.await??;
let ServerRequest::FileChangeRequestApproval { request_id, params } = server_req else {
panic!("expected FileChangeRequestApproval request")
};
assert_eq!(params.item_id, "patch-call");
assert_eq!(params.thread_id, thread.id);
assert_eq!(params.turn_id, turn.id);
let expected_readme_path = workspace.join("README.md");
let expected_readme_path = expected_readme_path.to_string_lossy().into_owned();
pretty_assertions::assert_eq!(
started_changes,
vec![codex_app_server_protocol::FileUpdateChange {
path: expected_readme_path.clone(),
kind: PatchChangeKind::Add,
diff: "new line\n".to_string(),
}]
);
mcp.send_response(
request_id,
serde_json::to_value(FileChangeRequestApprovalResponse {
decision: ApprovalDecision::Accept,
})?,
)
.await?;
let completed_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let completed_notif = mcp
.read_stream_until_notification_message("item/completed")
.await?;
let completed: ItemCompletedNotification = serde_json::from_value(
completed_notif
.params
.clone()
.expect("item/completed params"),
)?;
if let ThreadItem::FileChange { .. } = completed.item {
return Ok::<ThreadItem, anyhow::Error>(completed.item);
}
}
})
.await??;
let ThreadItem::FileChange { ref id, status, .. } = completed_file_change else {
unreachable!("loop ensures we break on file change items");
};
assert_eq!(id, "patch-call");
assert_eq!(status, PatchApplyStatus::Completed);
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
let readme_contents = std::fs::read_to_string(expected_readme_path)?;
assert_eq!(readme_contents, "new line\n");
Ok(())
}
#[tokio::test]
async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
skip_if_no_network!(Ok(()));
if cfg!(windows) {
// TODO apply_patch approvals are not parsed from powershell commands yet
return Ok(());
}
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home)?;
let workspace = tmp.path().join("workspace");
std::fs::create_dir(&workspace)?;
let patch = r#"*** Begin Patch
*** Add File: README.md
+new line
*** End Patch
"#;
let responses = vec![
create_apply_patch_sse_response(patch, "patch-call")?,
create_final_assistant_message_sse_response("patch declined")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let start_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
cwd: Some(workspace.to_string_lossy().into_owned()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
let turn_req = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "apply patch".into(),
}],
cwd: Some(workspace.clone()),
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
let started_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let started_notif = mcp
.read_stream_until_notification_message("item/started")
.await?;
let started: ItemStartedNotification =
serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
if let ThreadItem::FileChange { .. } = started.item {
return Ok::<ThreadItem, anyhow::Error>(started.item);
}
}
})
.await??;
let ThreadItem::FileChange {
ref id,
status,
ref changes,
} = started_file_change
else {
unreachable!("loop ensures we break on file change items");
};
assert_eq!(id, "patch-call");
assert_eq!(status, PatchApplyStatus::InProgress);
let started_changes = changes.clone();
let server_req = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_request_message(),
)
.await??;
let ServerRequest::FileChangeRequestApproval { request_id, params } = server_req else {
panic!("expected FileChangeRequestApproval request")
};
assert_eq!(params.item_id, "patch-call");
assert_eq!(params.thread_id, thread.id);
assert_eq!(params.turn_id, turn.id);
let expected_readme_path = workspace.join("README.md");
let expected_readme_path_str = expected_readme_path.to_string_lossy().into_owned();
pretty_assertions::assert_eq!(
started_changes,
vec![codex_app_server_protocol::FileUpdateChange {
path: expected_readme_path_str.clone(),
kind: PatchChangeKind::Add,
diff: "new line\n".to_string(),
}]
);
mcp.send_response(
request_id,
serde_json::to_value(FileChangeRequestApprovalResponse {
decision: ApprovalDecision::Decline,
})?,
)
.await?;
let completed_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let completed_notif = mcp
.read_stream_until_notification_message("item/completed")
.await?;
let completed: ItemCompletedNotification = serde_json::from_value(
completed_notif
.params
.clone()
.expect("item/completed params"),
)?;
if let ThreadItem::FileChange { .. } = completed.item {
return Ok::<ThreadItem, anyhow::Error>(completed.item);
}
}
})
.await??;
let ThreadItem::FileChange { ref id, status, .. } = completed_file_change else {
unreachable!("loop ensures we break on file change items");
};
assert_eq!(id, "patch-call");
assert_eq!(status, PatchApplyStatus::Declined);
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
assert!(
!expected_readme_path.exists(),
"declined patch should not be applied"
);
Ok(())
}
// Helper to create a config.toml pointing at the mock model server.
fn create_config_toml(
codex_home: &Path,
server_uri: &str,
approval_policy: &str,
) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "{approval_policy}"
sandbox_mode = "read-only"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -30,7 +30,6 @@ pub use standalone_executable::main;
pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_tool_instructions.md");
const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
const APPLY_PATCH_SHELLS: [&str; 3] = ["bash", "zsh", "sh"];
#[derive(Debug, Error, PartialEq)]
pub enum ApplyPatchError {
@@ -97,13 +96,6 @@ pub struct ApplyPatchArgs {
pub workdir: Option<String>,
}
fn shell_supports_apply_patch(shell: &str) -> bool {
std::path::Path::new(shell)
.file_name()
.and_then(|name| name.to_str())
.is_some_and(|name| APPLY_PATCH_SHELLS.contains(&name))
}
pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
match argv {
// Direct invocation: apply_patch <patch>
@@ -112,7 +104,7 @@ pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
Err(e) => MaybeApplyPatch::PatchParseError(e),
},
// Bash heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
[shell, flag, script] if shell_supports_apply_patch(shell) && flag == "-lc" => {
[bash, flag, script] if bash == "bash" && flag == "-lc" => {
match extract_apply_patch_from_bash(script) {
Ok((body, workdir)) => match parse_patch(&body) {
Ok(mut source) => {
@@ -232,12 +224,12 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
);
}
}
[shell, flag, script]
if shell_supports_apply_patch(shell)
&& flag == "-lc"
&& parse_patch(script).is_ok() =>
{
return MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation);
[bash, flag, script] if bash == "bash" && flag == "-lc" => {
if parse_patch(script).is_ok() {
return MaybeApplyPatchVerified::CorrectnessError(
ApplyPatchError::ImplicitInvocation,
);
}
}
_ => {}
}
@@ -296,7 +288,7 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
path,
ApplyPatchFileChange::Update {
unified_diff,
move_path: move_path.map(|p| effective_cwd.join(p)),
move_path: move_path.map(|p| cwd.join(p)),
new_content: contents,
},
);
@@ -1611,53 +1603,6 @@ g
);
}
#[test]
fn test_apply_patch_resolves_move_path_with_effective_cwd() {
let session_dir = tempdir().unwrap();
let worktree_rel = "alt";
let worktree_dir = session_dir.path().join(worktree_rel);
fs::create_dir_all(&worktree_dir).unwrap();
let source_name = "old.txt";
let dest_name = "renamed.txt";
let source_path = worktree_dir.join(source_name);
fs::write(&source_path, "before\n").unwrap();
let patch = wrap_patch(&format!(
r#"*** Update File: {source_name}
*** Move to: {dest_name}
@@
-before
+after"#
));
let shell_script = format!("cd {worktree_rel} && apply_patch <<'PATCH'\n{patch}\nPATCH");
let argv = vec!["bash".into(), "-lc".into(), shell_script];
let result = maybe_parse_apply_patch_verified(&argv, session_dir.path());
let action = match result {
MaybeApplyPatchVerified::Body(action) => action,
other => panic!("expected verified body, got {other:?}"),
};
assert_eq!(action.cwd, worktree_dir);
let change = action
.changes()
.get(&worktree_dir.join(source_name))
.expect("source file change present");
match change {
ApplyPatchFileChange::Update { move_path, .. } => {
assert_eq!(
move_path.as_deref(),
Some(worktree_dir.join(dest_name).as_path())
);
}
other => panic!("expected update change, got {other:?}"),
}
}
#[test]
fn test_apply_patch_fails_on_write_error() {
let dir = tempdir().unwrap();

View File

@@ -11,7 +11,32 @@ const LINUX_SANDBOX_ARG0: &str = "codex-linux-sandbox";
const APPLY_PATCH_ARG0: &str = "apply_patch";
const MISSPELLED_APPLY_PATCH_ARG0: &str = "applypatch";
pub fn arg0_dispatch() -> Option<TempDir> {
/// While we want to deploy the Codex CLI as a single executable for simplicity,
/// we also want to expose some of its functionality as distinct CLIs, so we use
/// the "arg0 trick" to determine which CLI to dispatch. This effectively allows
/// us to simulate deploying multiple executables as a single binary on Mac and
/// Linux (but not Windows).
///
/// When the current executable is invoked through the hard-link or alias named
/// `codex-linux-sandbox` we *directly* execute
/// [`codex_linux_sandbox::run_main`] (which never returns). Otherwise we:
///
/// 1. Load `.env` values from `~/.codex/.env` before creating any threads.
/// 2. Construct a Tokio multi-thread runtime.
/// 3. Derive the path to the current executable (so children can re-invoke the
/// sandbox) when running on Linux.
/// 4. Execute the provided async `main_fn` inside that runtime, forwarding any
/// error. Note that `main_fn` receives `codex_linux_sandbox_exe:
/// Option<PathBuf>`, as an argument, which is generally needed as part of
/// constructing [`codex_core::config::Config`].
///
/// This function should be used to wrap any `main()` function in binary crates
/// in this workspace that depends on these helper CLIs.
pub fn arg0_dispatch_or_else<F, Fut>(main_fn: F) -> anyhow::Result<()>
where
F: FnOnce(Option<PathBuf>) -> Fut,
Fut: Future<Output = anyhow::Result<()>>,
{
// Determine if we were invoked via the special alias.
let mut args = std::env::args_os();
let argv0 = args.next().unwrap_or_default();
@@ -51,7 +76,10 @@ pub fn arg0_dispatch() -> Option<TempDir> {
// before creating any threads/the Tokio runtime.
load_dotenv();
match prepend_path_entry_for_codex_aliases() {
// Retain the TempDir so it exists for the lifetime of the invocation of
// this executable. Admittedly, we could invoke `keep()` on it, but it
// would be nice to avoid leaving temporary directories behind, if possible.
let _path_entry = match prepend_path_entry_for_apply_patch() {
Ok(path_entry) => Some(path_entry),
Err(err) => {
// It is possible that Codex will proceed successfully even if
@@ -59,39 +87,7 @@ pub fn arg0_dispatch() -> Option<TempDir> {
eprintln!("WARNING: proceeding, even though we could not update PATH: {err}");
None
}
}
}
/// While we want to deploy the Codex CLI as a single executable for simplicity,
/// we also want to expose some of its functionality as distinct CLIs, so we use
/// the "arg0 trick" to determine which CLI to dispatch. This effectively allows
/// us to simulate deploying multiple executables as a single binary on Mac and
/// Linux (but not Windows).
///
/// When the current executable is invoked through the hard-link or alias named
/// `codex-linux-sandbox` we *directly* execute
/// [`codex_linux_sandbox::run_main`] (which never returns). Otherwise we:
///
/// 1. Load `.env` values from `~/.codex/.env` before creating any threads.
/// 2. Construct a Tokio multi-thread runtime.
/// 3. Derive the path to the current executable (so children can re-invoke the
/// sandbox) when running on Linux.
/// 4. Execute the provided async `main_fn` inside that runtime, forwarding any
/// error. Note that `main_fn` receives `codex_linux_sandbox_exe:
/// Option<PathBuf>`, as an argument, which is generally needed as part of
/// constructing [`codex_core::config::Config`].
///
/// This function should be used to wrap any `main()` function in binary crates
/// in this workspace that depends on these helper CLIs.
pub fn arg0_dispatch_or_else<F, Fut>(main_fn: F) -> anyhow::Result<()>
where
F: FnOnce(Option<PathBuf>) -> Fut,
Fut: Future<Output = anyhow::Result<()>>,
{
// Retain the TempDir so it exists for the lifetime of the invocation of
// this executable. Admittedly, we could invoke `keep()` on it, but it
// would be nice to avoid leaving temporary directories behind, if possible.
let _path_entry = arg0_dispatch();
};
// Regular invocation create a Tokio runtime and execute the provided
// async entry-point.
@@ -148,16 +144,11 @@ where
///
/// IMPORTANT: This function modifies the PATH environment variable, so it MUST
/// be called before multiple threads are spawned.
pub fn prepend_path_entry_for_codex_aliases() -> std::io::Result<TempDir> {
fn prepend_path_entry_for_apply_patch() -> std::io::Result<TempDir> {
let temp_dir = TempDir::new()?;
let path = temp_dir.path();
for filename in &[
APPLY_PATCH_ARG0,
MISSPELLED_APPLY_PATCH_ARG0,
#[cfg(target_os = "linux")]
LINUX_SANDBOX_ARG0,
] {
for filename in &[APPLY_PATCH_ARG0, MISSPELLED_APPLY_PATCH_ARG0] {
let exe = std::env::current_exe()?;
#[cfg(unix)]

View File

@@ -1,5 +1,4 @@
use crate::types::CodeTaskDetailsResponse;
use crate::types::CreditStatusDetails;
use crate::types::PaginatedListTaskListItem;
use crate::types::RateLimitStatusPayload;
use crate::types::RateLimitWindowSnapshot;
@@ -7,7 +6,6 @@ use crate::types::TurnAttemptsSiblingTurnsResponse;
use anyhow::Result;
use codex_core::auth::CodexAuth;
use codex_core::default_client::get_codex_user_agent;
use codex_protocol::protocol::CreditsSnapshot;
use codex_protocol::protocol::RateLimitSnapshot;
use codex_protocol::protocol::RateLimitWindow;
use reqwest::header::AUTHORIZATION;
@@ -274,23 +272,19 @@ impl Client {
// rate limit helpers
fn rate_limit_snapshot_from_payload(payload: RateLimitStatusPayload) -> RateLimitSnapshot {
let rate_limit_details = payload
let Some(details) = payload
.rate_limit
.and_then(|inner| inner.map(|boxed| *boxed));
let (primary, secondary) = if let Some(details) = rate_limit_details {
(
Self::map_rate_limit_window(details.primary_window),
Self::map_rate_limit_window(details.secondary_window),
)
} else {
(None, None)
.and_then(|inner| inner.map(|boxed| *boxed))
else {
return RateLimitSnapshot {
primary: None,
secondary: None,
};
};
RateLimitSnapshot {
primary,
secondary,
credits: Self::map_credits(payload.credits),
primary: Self::map_rate_limit_window(details.primary_window),
secondary: Self::map_rate_limit_window(details.secondary_window),
}
}
@@ -312,19 +306,6 @@ impl Client {
})
}
fn map_credits(credits: Option<Option<Box<CreditStatusDetails>>>) -> Option<CreditsSnapshot> {
let details = match credits {
Some(Some(details)) => *details,
_ => return None,
};
Some(CreditsSnapshot {
has_credits: details.has_credits,
unlimited: details.unlimited,
balance: details.balance.and_then(|inner| inner),
})
}
fn window_minutes_from_seconds(seconds: i32) -> Option<i64> {
if seconds <= 0 {
return None;

View File

@@ -1,4 +1,3 @@
pub use codex_backend_openapi_models::models::CreditStatusDetails;
pub use codex_backend_openapi_models::models::PaginatedListTaskListItem;
pub use codex_backend_openapi_models::models::PlanType;
pub use codex_backend_openapi_models::models::RateLimitStatusDetails;

View File

@@ -26,22 +26,19 @@ codex-cloud-tasks = { path = "../cloud-tasks" }
codex-common = { workspace = true, features = ["cli"] }
codex-core = { workspace = true }
codex-exec = { workspace = true }
codex-execpolicy = { workspace = true }
codex-login = { workspace = true }
codex-mcp-server = { workspace = true }
codex-process-hardening = { workspace = true }
codex-protocol = { workspace = true }
codex-protocol-ts = { workspace = true }
codex-responses-api-proxy = { workspace = true }
codex-rmcp-client = { workspace = true }
codex-stdio-to-uds = { workspace = true }
codex-tui = { workspace = true }
ctor = { workspace = true }
libc = { workspace = true }
owo-colors = { workspace = true }
regex-lite = { workspace = true}
serde_json = { workspace = true }
supports-color = { workspace = true }
toml = { workspace = true }
tokio = { workspace = true, features = [
"io-std",
"macros",
@@ -49,7 +46,6 @@ tokio = { workspace = true, features = [
"rt-multi-thread",
"signal",
] }
tracing = { workspace = true }
[target.'cfg(target_os = "windows")'.dependencies]
codex_windows_sandbox = { package = "codex-windows-sandbox", path = "../windows-sandbox-rs" }

View File

@@ -1,8 +1,3 @@
#[cfg(target_os = "macos")]
mod pid_tracker;
#[cfg(target_os = "macos")]
mod seatbelt;
use std::path::PathBuf;
use codex_common::CliConfigOverrides;
@@ -10,7 +5,6 @@ use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::exec_env::create_env;
use codex_core::landlock::spawn_command_under_linux_sandbox;
#[cfg(target_os = "macos")]
use codex_core::seatbelt::spawn_command_under_seatbelt;
use codex_core::spawn::StdioPolicy;
use codex_protocol::config_types::SandboxMode;
@@ -20,17 +14,12 @@ use crate::SeatbeltCommand;
use crate::WindowsCommand;
use crate::exit_status::handle_exit_status;
#[cfg(target_os = "macos")]
use seatbelt::DenialLogger;
#[cfg(target_os = "macos")]
pub async fn run_command_under_seatbelt(
command: SeatbeltCommand,
codex_linux_sandbox_exe: Option<PathBuf>,
) -> anyhow::Result<()> {
let SeatbeltCommand {
full_auto,
log_denials,
config_overrides,
command,
} = command;
@@ -40,19 +29,10 @@ pub async fn run_command_under_seatbelt(
config_overrides,
codex_linux_sandbox_exe,
SandboxType::Seatbelt,
log_denials,
)
.await
}
#[cfg(not(target_os = "macos"))]
pub async fn run_command_under_seatbelt(
_command: SeatbeltCommand,
_codex_linux_sandbox_exe: Option<PathBuf>,
) -> anyhow::Result<()> {
anyhow::bail!("Seatbelt sandbox is only available on macOS");
}
pub async fn run_command_under_landlock(
command: LandlockCommand,
codex_linux_sandbox_exe: Option<PathBuf>,
@@ -68,7 +48,6 @@ pub async fn run_command_under_landlock(
config_overrides,
codex_linux_sandbox_exe,
SandboxType::Landlock,
false,
)
.await
}
@@ -88,13 +67,11 @@ pub async fn run_command_under_windows(
config_overrides,
codex_linux_sandbox_exe,
SandboxType::Windows,
false,
)
.await
}
enum SandboxType {
#[cfg(target_os = "macos")]
Seatbelt,
Landlock,
Windows,
@@ -106,7 +83,6 @@ async fn run_command_under_sandbox(
config_overrides: CliConfigOverrides,
codex_linux_sandbox_exe: Option<PathBuf>,
sandbox_type: SandboxType,
log_denials: bool,
) -> anyhow::Result<()> {
let sandbox_mode = create_sandbox_mode(full_auto);
let config = Config::load_with_cli_overrides(
@@ -138,20 +114,20 @@ async fn run_command_under_sandbox(
{
use codex_windows_sandbox::run_windows_sandbox_capture;
let policy_str = serde_json::to_string(&config.sandbox_policy)?;
let policy_str = match &config.sandbox_policy {
codex_core::protocol::SandboxPolicy::DangerFullAccess => "workspace-write",
codex_core::protocol::SandboxPolicy::ReadOnly => "read-only",
codex_core::protocol::SandboxPolicy::WorkspaceWrite { .. } => "workspace-write",
};
let sandbox_cwd = sandbox_policy_cwd.clone();
let cwd_clone = cwd.clone();
let env_map = env.clone();
let command_vec = command.clone();
let base_dir = config.codex_home.clone();
// Preflight audit is invoked elsewhere at the appropriate times.
let res = tokio::task::spawn_blocking(move || {
run_windows_sandbox_capture(
policy_str.as_str(),
policy_str,
&sandbox_cwd,
base_dir.as_path(),
command_vec,
&cwd_clone,
env_map,
@@ -189,13 +165,7 @@ async fn run_command_under_sandbox(
}
}
#[cfg(target_os = "macos")]
let mut denial_logger = log_denials.then(DenialLogger::new).flatten();
#[cfg(not(target_os = "macos"))]
let _ = log_denials;
let mut child = match sandbox_type {
#[cfg(target_os = "macos")]
SandboxType::Seatbelt => {
spawn_command_under_seatbelt(
command,
@@ -227,27 +197,8 @@ async fn run_command_under_sandbox(
unreachable!("Windows sandbox should have been handled above");
}
};
#[cfg(target_os = "macos")]
if let Some(denial_logger) = &mut denial_logger {
denial_logger.on_child_spawn(&child);
}
let status = child.wait().await?;
#[cfg(target_os = "macos")]
if let Some(denial_logger) = denial_logger {
let denials = denial_logger.finish().await;
eprintln!("\n=== Sandbox denials ===");
if denials.is_empty() {
eprintln!("None found.");
} else {
for seatbelt::SandboxDenial { name, capability } in denials {
eprintln!("({name}) {capability}");
}
}
}
handle_exit_status(status);
}

View File

@@ -1,372 +0,0 @@
use std::collections::HashSet;
use tokio::task::JoinHandle;
use tracing::warn;
/// Tracks the (recursive) descendants of a process by using `kqueue` to watch for fork events, and
/// `proc_listchildpids` to list the children of a process.
pub(crate) struct PidTracker {
kq: libc::c_int,
handle: JoinHandle<HashSet<i32>>,
}
impl PidTracker {
pub(crate) fn new(root_pid: i32) -> Option<Self> {
if root_pid <= 0 {
return None;
}
let kq = unsafe { libc::kqueue() };
let handle = tokio::task::spawn_blocking(move || track_descendants(kq, root_pid));
Some(Self { kq, handle })
}
pub(crate) async fn stop(self) -> HashSet<i32> {
trigger_stop_event(self.kq);
self.handle.await.unwrap_or_default()
}
}
unsafe extern "C" {
fn proc_listchildpids(
ppid: libc::c_int,
buffer: *mut libc::c_void,
buffersize: libc::c_int,
) -> libc::c_int;
}
/// Wrap proc_listchildpids.
fn list_child_pids(parent: i32) -> Vec<i32> {
unsafe {
let mut capacity: usize = 16;
loop {
let mut buf: Vec<i32> = vec![0; capacity];
let count = proc_listchildpids(
parent as libc::c_int,
buf.as_mut_ptr() as *mut libc::c_void,
(buf.len() * std::mem::size_of::<i32>()) as libc::c_int,
);
if count <= 0 {
return Vec::new();
}
let returned = count as usize;
if returned < capacity {
buf.truncate(returned);
return buf;
}
capacity = capacity.saturating_mul(2).max(returned + 16);
}
}
}
fn pid_is_alive(pid: i32) -> bool {
if pid <= 0 {
return false;
}
let res = unsafe { libc::kill(pid as libc::pid_t, 0) };
if res == 0 {
true
} else {
matches!(
std::io::Error::last_os_error().raw_os_error(),
Some(libc::EPERM)
)
}
}
enum WatchPidError {
ProcessGone,
Other(std::io::Error),
}
/// Add `pid` to the watch list in `kq`.
fn watch_pid(kq: libc::c_int, pid: i32) -> Result<(), WatchPidError> {
if pid <= 0 {
return Err(WatchPidError::ProcessGone);
}
let kev = libc::kevent {
ident: pid as libc::uintptr_t,
filter: libc::EVFILT_PROC,
flags: libc::EV_ADD | libc::EV_CLEAR,
fflags: libc::NOTE_FORK | libc::NOTE_EXEC | libc::NOTE_EXIT,
data: 0,
udata: std::ptr::null_mut(),
};
let res = unsafe { libc::kevent(kq, &kev, 1, std::ptr::null_mut(), 0, std::ptr::null()) };
if res < 0 {
let err = std::io::Error::last_os_error();
if err.raw_os_error() == Some(libc::ESRCH) {
Err(WatchPidError::ProcessGone)
} else {
Err(WatchPidError::Other(err))
}
} else {
Ok(())
}
}
fn watch_children(
kq: libc::c_int,
parent: i32,
seen: &mut HashSet<i32>,
active: &mut HashSet<i32>,
) {
for child_pid in list_child_pids(parent) {
add_pid_watch(kq, child_pid, seen, active);
}
}
/// Watch `pid` and its children, updating `seen` and `active` sets.
fn add_pid_watch(kq: libc::c_int, pid: i32, seen: &mut HashSet<i32>, active: &mut HashSet<i32>) {
if pid <= 0 {
return;
}
let newly_seen = seen.insert(pid);
let mut should_recurse = newly_seen;
if active.insert(pid) {
match watch_pid(kq, pid) {
Ok(()) => {
should_recurse = true;
}
Err(WatchPidError::ProcessGone) => {
active.remove(&pid);
return;
}
Err(WatchPidError::Other(err)) => {
warn!("failed to watch pid {pid}: {err}");
active.remove(&pid);
return;
}
}
}
if should_recurse {
watch_children(kq, pid, seen, active);
}
}
const STOP_IDENT: libc::uintptr_t = 1;
fn register_stop_event(kq: libc::c_int) -> bool {
let kev = libc::kevent {
ident: STOP_IDENT,
filter: libc::EVFILT_USER,
flags: libc::EV_ADD | libc::EV_CLEAR,
fflags: 0,
data: 0,
udata: std::ptr::null_mut(),
};
let res = unsafe { libc::kevent(kq, &kev, 1, std::ptr::null_mut(), 0, std::ptr::null()) };
res >= 0
}
fn trigger_stop_event(kq: libc::c_int) {
if kq < 0 {
return;
}
let kev = libc::kevent {
ident: STOP_IDENT,
filter: libc::EVFILT_USER,
flags: 0,
fflags: libc::NOTE_TRIGGER,
data: 0,
udata: std::ptr::null_mut(),
};
let _ = unsafe { libc::kevent(kq, &kev, 1, std::ptr::null_mut(), 0, std::ptr::null()) };
}
/// Put all of the above together to track all the descendants of `root_pid`.
fn track_descendants(kq: libc::c_int, root_pid: i32) -> HashSet<i32> {
if kq < 0 {
let mut seen = HashSet::new();
seen.insert(root_pid);
return seen;
}
if !register_stop_event(kq) {
let mut seen = HashSet::new();
seen.insert(root_pid);
let _ = unsafe { libc::close(kq) };
return seen;
}
let mut seen: HashSet<i32> = HashSet::new();
let mut active: HashSet<i32> = HashSet::new();
add_pid_watch(kq, root_pid, &mut seen, &mut active);
const EVENTS_CAP: usize = 32;
let mut events: [libc::kevent; EVENTS_CAP] =
unsafe { std::mem::MaybeUninit::zeroed().assume_init() };
let mut stop_requested = false;
loop {
if active.is_empty() {
if !pid_is_alive(root_pid) {
break;
}
add_pid_watch(kq, root_pid, &mut seen, &mut active);
if active.is_empty() {
continue;
}
}
let nev = unsafe {
libc::kevent(
kq,
std::ptr::null::<libc::kevent>(),
0,
events.as_mut_ptr(),
EVENTS_CAP as libc::c_int,
std::ptr::null(),
)
};
if nev < 0 {
let err = std::io::Error::last_os_error();
if err.kind() == std::io::ErrorKind::Interrupted {
continue;
}
break;
}
if nev == 0 {
continue;
}
for ev in events.iter().take(nev as usize) {
let pid = ev.ident as i32;
if ev.filter == libc::EVFILT_USER && ev.ident == STOP_IDENT {
stop_requested = true;
break;
}
if (ev.flags & libc::EV_ERROR) != 0 {
if ev.data == libc::ESRCH as isize {
active.remove(&pid);
}
continue;
}
if (ev.fflags & libc::NOTE_FORK) != 0 {
watch_children(kq, pid, &mut seen, &mut active);
}
if (ev.fflags & libc::NOTE_EXIT) != 0 {
active.remove(&pid);
}
}
if stop_requested {
break;
}
}
let _ = unsafe { libc::close(kq) };
seen
}
#[cfg(test)]
mod tests {
use super::*;
use std::process::Command;
use std::process::Stdio;
use std::time::Duration;
#[test]
fn pid_is_alive_detects_current_process() {
let pid = std::process::id() as i32;
assert!(pid_is_alive(pid));
}
#[cfg(target_os = "macos")]
#[test]
fn list_child_pids_includes_spawned_child() {
let mut child = Command::new("/bin/sleep")
.arg("5")
.stdin(Stdio::null())
.spawn()
.expect("failed to spawn child process");
let child_pid = child.id() as i32;
let parent_pid = std::process::id() as i32;
let mut found = false;
for _ in 0..100 {
if list_child_pids(parent_pid).contains(&child_pid) {
found = true;
break;
}
std::thread::sleep(Duration::from_millis(10));
}
let _ = child.kill();
let _ = child.wait();
assert!(found, "expected to find child pid {child_pid} in list");
}
#[cfg(target_os = "macos")]
#[tokio::test]
async fn pid_tracker_collects_spawned_children() {
let tracker = PidTracker::new(std::process::id() as i32).expect("failed to create tracker");
let mut child = Command::new("/bin/sleep")
.arg("0.1")
.stdin(Stdio::null())
.spawn()
.expect("failed to spawn child process");
let child_pid = child.id() as i32;
let parent_pid = std::process::id() as i32;
let _ = child.wait();
let seen = tracker.stop().await;
assert!(
seen.contains(&parent_pid),
"expected tracker to include parent pid {parent_pid}"
);
assert!(
seen.contains(&child_pid),
"expected tracker to include child pid {child_pid}"
);
}
#[cfg(target_os = "macos")]
#[tokio::test]
async fn pid_tracker_collects_bash_subshell_descendants() {
let tracker = PidTracker::new(std::process::id() as i32).expect("failed to create tracker");
let child = Command::new("/bin/bash")
.arg("-c")
.arg("(sleep 0.1 & echo $!; wait)")
.stdin(Stdio::null())
.stdout(Stdio::piped())
.stderr(Stdio::null())
.spawn()
.expect("failed to spawn bash");
let output = child.wait_with_output().unwrap().stdout;
let subshell_pid = String::from_utf8_lossy(&output)
.trim()
.parse::<i32>()
.expect("failed to parse subshell pid");
let seen = tracker.stop().await;
assert!(
seen.contains(&subshell_pid),
"expected tracker to include subshell pid {subshell_pid}"
);
}
}

View File

@@ -1,114 +0,0 @@
use std::collections::HashSet;
use tokio::io::AsyncBufReadExt;
use tokio::process::Child;
use tokio::task::JoinHandle;
use super::pid_tracker::PidTracker;
pub struct SandboxDenial {
pub name: String,
pub capability: String,
}
pub struct DenialLogger {
log_stream: Child,
pid_tracker: Option<PidTracker>,
log_reader: Option<JoinHandle<Vec<u8>>>,
}
impl DenialLogger {
pub(crate) fn new() -> Option<Self> {
let mut log_stream = start_log_stream()?;
let stdout = log_stream.stdout.take()?;
let log_reader = tokio::spawn(async move {
let mut reader = tokio::io::BufReader::new(stdout);
let mut logs = Vec::new();
let mut chunk = Vec::new();
loop {
match reader.read_until(b'\n', &mut chunk).await {
Ok(0) | Err(_) => break,
Ok(_) => {
logs.extend_from_slice(&chunk);
chunk.clear();
}
}
}
logs
});
Some(Self {
log_stream,
pid_tracker: None,
log_reader: Some(log_reader),
})
}
pub(crate) fn on_child_spawn(&mut self, child: &Child) {
if let Some(root_pid) = child.id() {
self.pid_tracker = PidTracker::new(root_pid as i32);
}
}
pub(crate) async fn finish(mut self) -> Vec<SandboxDenial> {
let pid_set = match self.pid_tracker {
Some(tracker) => tracker.stop().await,
None => Default::default(),
};
if pid_set.is_empty() {
return Vec::new();
}
let _ = self.log_stream.kill().await;
let _ = self.log_stream.wait().await;
let logs_bytes = match self.log_reader.take() {
Some(handle) => handle.await.unwrap_or_default(),
None => Vec::new(),
};
let logs = String::from_utf8_lossy(&logs_bytes);
let mut seen: HashSet<(String, String)> = HashSet::new();
let mut denials: Vec<SandboxDenial> = Vec::new();
for line in logs.lines() {
if let Ok(json) = serde_json::from_str::<serde_json::Value>(line)
&& let Some(msg) = json.get("eventMessage").and_then(|v| v.as_str())
&& let Some((pid, name, capability)) = parse_message(msg)
&& pid_set.contains(&pid)
&& seen.insert((name.clone(), capability.clone()))
{
denials.push(SandboxDenial { name, capability });
}
}
denials
}
}
fn start_log_stream() -> Option<Child> {
use std::process::Stdio;
const PREDICATE: &str = r#"(((processID == 0) AND (senderImagePath CONTAINS "/Sandbox")) OR (subsystem == "com.apple.sandbox.reporting"))"#;
tokio::process::Command::new("log")
.args(["stream", "--style", "ndjson", "--predicate", PREDICATE])
.stdin(Stdio::null())
.stdout(Stdio::piped())
.stderr(Stdio::null())
.kill_on_drop(true)
.spawn()
.ok()
}
fn parse_message(msg: &str) -> Option<(i32, String, String)> {
// Example message:
// Sandbox: processname(1234) deny(1) capability-name args...
static RE: std::sync::OnceLock<regex_lite::Regex> = std::sync::OnceLock::new();
let re = RE.get_or_init(|| {
#[expect(clippy::unwrap_used)]
regex_lite::Regex::new(r"^Sandbox:\s*(.+?)\((\d+)\)\s+deny\(.*?\)\s*(.+)$").unwrap()
});
let (_, [name, pid_str, capability]) = re.captures(msg)?.extract();
let pid = pid_str.trim().parse::<i32>().ok()?;
Some((pid, name.to_string(), capability.to_string()))
}

View File

@@ -11,10 +11,6 @@ pub struct SeatbeltCommand {
#[arg(long = "full-auto", default_value_t = false)]
pub full_auto: bool,
/// While the command runs, capture macOS sandbox denials via `log stream` and print them after exit
#[arg(long = "log-denials", default_value_t = false)]
pub log_denials: bool,
#[clap(skip)]
pub config_overrides: CliConfigOverrides,

View File

@@ -1,4 +1,3 @@
use clap::Args;
use clap::CommandFactory;
use clap::Parser;
use clap_complete::Shell;
@@ -18,21 +17,17 @@ use codex_cli::login::run_logout;
use codex_cloud_tasks::Cli as CloudTasksCli;
use codex_common::CliConfigOverrides;
use codex_exec::Cli as ExecCli;
use codex_execpolicy::ExecPolicyCheckCommand;
use codex_responses_api_proxy::Args as ResponsesApiProxyArgs;
use codex_tui::AppExitInfo;
use codex_tui::Cli as TuiCli;
use codex_tui::update_action::UpdateAction;
use codex_tui::updates::UpdateAction;
use owo_colors::OwoColorize;
use std::path::PathBuf;
use supports_color::Stream;
mod mcp_cmd;
#[cfg(not(windows))]
mod wsl_paths;
use crate::mcp_cmd::McpCli;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::features::is_known_feature_key;
@@ -84,8 +79,8 @@ enum Subcommand {
/// [experimental] Run the Codex MCP server (stdio transport).
McpServer,
/// [experimental] Run the app server or related tooling.
AppServer(AppServerCommand),
/// [experimental] Run the app server.
AppServer,
/// Generate shell completion scripts.
Completion(CompletionCommand),
@@ -94,10 +89,6 @@ enum Subcommand {
#[clap(visible_alias = "debug")]
Sandbox(SandboxArgs),
/// Execpolicy tooling.
#[clap(hide = true)]
Execpolicy(ExecpolicyCommand),
/// Apply the latest diff produced by Codex agent as a `git apply` to your local working tree.
#[clap(visible_alias = "a")]
Apply(ApplyCommand),
@@ -105,6 +96,9 @@ enum Subcommand {
/// Resume a previous interactive session (picker by default; use --last to continue the most recent).
Resume(ResumeCommand),
/// Internal: generate TypeScript protocol bindings.
#[clap(hide = true)]
GenerateTs(GenerateTsCommand),
/// [EXPERIMENTAL] Browse tasks from Codex Cloud and apply changes locally.
#[clap(name = "cloud", alias = "cloud-tasks")]
Cloud(CloudTasksCli),
@@ -139,10 +133,6 @@ struct ResumeCommand {
#[arg(long = "last", default_value_t = false, conflicts_with = "session_id")]
last: bool,
/// Show all sessions (disables cwd filtering and shows CWD column).
#[arg(long = "all", default_value_t = false)]
all: bool,
#[clap(flatten)]
config_overrides: TuiCli,
}
@@ -167,19 +157,6 @@ enum SandboxCommand {
Windows(WindowsCommand),
}
#[derive(Debug, Parser)]
struct ExecpolicyCommand {
#[command(subcommand)]
sub: ExecpolicySubcommand,
}
#[derive(Debug, clap::Subcommand)]
enum ExecpolicySubcommand {
/// Check execpolicy files against a command.
#[clap(name = "check")]
Check(ExecPolicyCheckCommand),
}
#[derive(Debug, Parser)]
struct LoginCommand {
#[clap(skip)]
@@ -228,22 +205,6 @@ struct LogoutCommand {
}
#[derive(Debug, Parser)]
struct AppServerCommand {
/// Omit to run the app server; specify a subcommand for tooling.
#[command(subcommand)]
subcommand: Option<AppServerSubcommand>,
}
#[derive(Debug, clap::Subcommand)]
enum AppServerSubcommand {
/// [experimental] Generate TypeScript bindings for the app server protocol.
GenerateTs(GenerateTsCommand),
/// [experimental] Generate JSON Schema for the app server protocol.
GenerateJsonSchema(GenerateJsonSchemaCommand),
}
#[derive(Debug, Args)]
struct GenerateTsCommand {
/// Output directory where .ts files will be written
#[arg(short = 'o', long = "out", value_name = "DIR")]
@@ -254,13 +215,6 @@ struct GenerateTsCommand {
prettier: Option<PathBuf>,
}
#[derive(Debug, Args)]
struct GenerateJsonSchemaCommand {
/// Output directory where the schema bundle will be written
#[arg(short = 'o', long = "out", value_name = "DIR")]
out_dir: PathBuf,
}
#[derive(Debug, Parser)]
struct StdioToUdsCommand {
/// Path to the Unix domain socket to connect to.
@@ -313,30 +267,10 @@ fn handle_app_exit(exit_info: AppExitInfo) -> anyhow::Result<()> {
/// Run the update action and print the result.
fn run_update_action(action: UpdateAction) -> anyhow::Result<()> {
println!();
let (cmd, args) = action.command_args();
let cmd_str = action.command_str();
println!("Updating Codex via `{cmd_str}`...");
let status = {
#[cfg(windows)]
{
// On Windows, run via cmd.exe so .CMD/.BAT are correctly resolved (PATHEXT semantics).
std::process::Command::new("cmd")
.args(["/C", &cmd_str])
.status()?
}
#[cfg(not(windows))]
{
let (cmd, args) = action.command_args();
let command_path = crate::wsl_paths::normalize_for_wsl(cmd);
let normalized_args: Vec<String> = args
.iter()
.map(crate::wsl_paths::normalize_for_wsl)
.collect();
std::process::Command::new(&command_path)
.args(&normalized_args)
.status()?
}
};
let status = std::process::Command::new(cmd).args(args).status()?;
if !status.success() {
anyhow::bail!("`{cmd_str}` failed with status {status}");
}
@@ -345,10 +279,6 @@ fn run_update_action(action: UpdateAction) -> anyhow::Result<()> {
Ok(())
}
fn run_execpolicycheck(cmd: ExecPolicyCheckCommand) -> anyhow::Result<()> {
cmd.run()
}
#[derive(Debug, Default, Parser, Clone)]
struct FeatureToggles {
/// Enable a feature (repeatable). Equivalent to `-c features.<name>=true`.
@@ -457,24 +387,12 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
prepend_config_flags(&mut mcp_cli.config_overrides, root_config_overrides.clone());
mcp_cli.run().await?;
}
Some(Subcommand::AppServer(app_server_cli)) => match app_server_cli.subcommand {
None => {
codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
}
Some(AppServerSubcommand::GenerateTs(gen_cli)) => {
codex_app_server_protocol::generate_ts(
&gen_cli.out_dir,
gen_cli.prettier.as_deref(),
)?;
}
Some(AppServerSubcommand::GenerateJsonSchema(gen_cli)) => {
codex_app_server_protocol::generate_json(&gen_cli.out_dir)?;
}
},
Some(Subcommand::AppServer) => {
codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
}
Some(Subcommand::Resume(ResumeCommand {
session_id,
last,
all,
config_overrides,
})) => {
interactive = finalize_resume_interactive(
@@ -482,7 +400,6 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
root_config_overrides.clone(),
session_id,
last,
all,
config_overrides,
);
let exit_info = codex_tui::run_main(interactive, codex_linux_sandbox_exe).await?;
@@ -571,9 +488,6 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
.await?;
}
},
Some(Subcommand::Execpolicy(ExecpolicyCommand { sub })) => match sub {
ExecpolicySubcommand::Check(cmd) => run_execpolicycheck(cmd)?,
},
Some(Subcommand::Apply(mut apply_cli)) => {
prepend_config_flags(
&mut apply_cli.config_overrides,
@@ -590,24 +504,21 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
tokio::task::spawn_blocking(move || codex_stdio_to_uds::run(socket_path.as_path()))
.await??;
}
Some(Subcommand::GenerateTs(gen_cli)) => {
codex_protocol_ts::generate_ts(&gen_cli.out_dir, gen_cli.prettier.as_deref())?;
}
Some(Subcommand::Features(FeaturesCli { sub })) => match sub {
FeaturesSubcommand::List => {
// Respect root-level `-c` overrides plus top-level flags like `--profile`.
let mut cli_kv_overrides = root_config_overrides
let cli_kv_overrides = root_config_overrides
.parse_overrides()
.map_err(anyhow::Error::msg)?;
// Honor `--search` via the new feature toggle.
if interactive.web_search {
cli_kv_overrides.push((
"features.web_search_request".to_string(),
toml::Value::Boolean(true),
));
}
// Thread through relevant top-level flags (at minimum, `--profile`).
// Also honor `--search` since it maps to a feature toggle.
let overrides = ConfigOverrides {
config_profile: interactive.config_profile.clone(),
tools_web_search_request: interactive.web_search.then_some(true),
..Default::default()
};
@@ -642,7 +553,6 @@ fn finalize_resume_interactive(
root_config_overrides: CliConfigOverrides,
session_id: Option<String>,
last: bool,
show_all: bool,
resume_cli: TuiCli,
) -> TuiCli {
// Start with the parsed interactive CLI so resume shares the same
@@ -651,7 +561,6 @@ fn finalize_resume_interactive(
interactive.resume_picker = resume_session_id.is_none() && !last;
interactive.resume_last = last;
interactive.resume_session_id = resume_session_id;
interactive.resume_show_all = show_all;
// Merge resume-scoped flags and overrides with highest precedence.
merge_resume_cli_flags(&mut interactive, resume_cli);
@@ -735,21 +644,13 @@ mod tests {
let Subcommand::Resume(ResumeCommand {
session_id,
last,
all,
config_overrides: resume_cli,
}) = subcommand.expect("resume present")
else {
unreachable!()
};
finalize_resume_interactive(
interactive,
root_overrides,
session_id,
last,
all,
resume_cli,
)
finalize_resume_interactive(interactive, root_overrides, session_id, last, resume_cli)
}
fn sample_exit_info(conversation: Option<&str>) -> AppExitInfo {
@@ -802,9 +703,9 @@ mod tests {
#[test]
fn resume_model_flag_applies_when_no_root_flags() {
let interactive = finalize_from_args(["codex", "resume", "-m", "gpt-5.1-test"].as_ref());
let interactive = finalize_from_args(["codex", "resume", "-m", "gpt-5-test"].as_ref());
assert_eq!(interactive.model.as_deref(), Some("gpt-5.1-test"));
assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
@@ -816,7 +717,6 @@ mod tests {
assert!(interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
assert!(!interactive.resume_show_all);
}
#[test]
@@ -825,7 +725,6 @@ mod tests {
assert!(!interactive.resume_picker);
assert!(interactive.resume_last);
assert_eq!(interactive.resume_session_id, None);
assert!(!interactive.resume_show_all);
}
#[test]
@@ -834,14 +733,6 @@ mod tests {
assert!(!interactive.resume_picker);
assert!(!interactive.resume_last);
assert_eq!(interactive.resume_session_id.as_deref(), Some("1234"));
assert!(!interactive.resume_show_all);
}
#[test]
fn resume_all_flag_sets_show_all() {
let interactive = finalize_from_args(["codex", "resume", "--all"].as_ref());
assert!(interactive.resume_picker);
assert!(interactive.resume_show_all);
}
#[test]
@@ -859,7 +750,7 @@ mod tests {
"--ask-for-approval",
"on-request",
"-m",
"gpt-5.1-test",
"gpt-5-test",
"-p",
"my-profile",
"-C",
@@ -870,7 +761,7 @@ mod tests {
.as_ref(),
);
assert_eq!(interactive.model.as_deref(), Some("gpt-5.1-test"));
assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
assert!(interactive.oss);
assert_eq!(interactive.config_profile.as_deref(), Some("my-profile"));
assert_matches!(

View File

@@ -79,7 +79,6 @@ pub struct GetArgs {
}
#[derive(Debug, clap::Parser)]
#[command(override_usage = "codex mcp add [OPTIONS] <NAME> (--url <URL> | -- <COMMAND>...)")]
pub struct AddArgs {
/// Name for the MCP server configuration.
pub name: String,
@@ -354,9 +353,7 @@ async fn run_login(config_overrides: &CliConfigOverrides, login_args: LoginArgs)
.context("failed to load configuration")?;
if !config.features.enabled(Feature::RmcpClient) {
bail!(
"OAuth login is only supported when [features].rmcp_client is true in config.toml. See https://github.com/openai/codex/blob/main/docs/config.md#feature-flags for details."
);
bail!("OAuth login is only supported when [feature].rmcp_client is true in config.toml.");
}
let LoginArgs { name, scopes } = login_args;

View File

@@ -1,76 +0,0 @@
use std::ffi::OsStr;
/// WSL-specific path helpers used by the updater logic.
///
/// See https://github.com/openai/codex/issues/6086.
pub fn is_wsl() -> bool {
#[cfg(target_os = "linux")]
{
if std::env::var_os("WSL_DISTRO_NAME").is_some() {
return true;
}
match std::fs::read_to_string("/proc/version") {
Ok(version) => version.to_lowercase().contains("microsoft"),
Err(_) => false,
}
}
#[cfg(not(target_os = "linux"))]
{
false
}
}
/// Convert a Windows absolute path (`C:\foo\bar` or `C:/foo/bar`) to a WSL mount path (`/mnt/c/foo/bar`).
/// Returns `None` if the input does not look like a Windows drive path.
pub fn win_path_to_wsl(path: &str) -> Option<String> {
let bytes = path.as_bytes();
if bytes.len() < 3
|| bytes[1] != b':'
|| !(bytes[2] == b'\\' || bytes[2] == b'/')
|| !bytes[0].is_ascii_alphabetic()
{
return None;
}
let drive = (bytes[0] as char).to_ascii_lowercase();
let tail = path[3..].replace('\\', "/");
if tail.is_empty() {
return Some(format!("/mnt/{drive}"));
}
Some(format!("/mnt/{drive}/{tail}"))
}
/// If under WSL and given a Windows-style path, return the equivalent `/mnt/<drive>/…` path.
/// Otherwise returns the input unchanged.
pub fn normalize_for_wsl<P: AsRef<OsStr>>(path: P) -> String {
let value = path.as_ref().to_string_lossy().to_string();
if !is_wsl() {
return value;
}
if let Some(mapped) = win_path_to_wsl(&value) {
return mapped;
}
value
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn win_to_wsl_basic() {
assert_eq!(
win_path_to_wsl(r"C:\Temp\codex.zip").as_deref(),
Some("/mnt/c/Temp/codex.zip")
);
assert_eq!(
win_path_to_wsl("D:/Work/codex.tgz").as_deref(),
Some("/mnt/d/Work/codex.tgz")
);
assert!(win_path_to_wsl("/home/user/codex").is_none());
}
#[test]
fn normalize_is_noop_on_unix_paths() {
assert_eq!(normalize_for_wsl("/home/u/x"), "/home/u/x");
}
}

View File

@@ -1,58 +0,0 @@
use std::fs;
use assert_cmd::Command;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
#[test]
fn execpolicy_check_matches_expected_json() -> Result<(), Box<dyn std::error::Error>> {
let codex_home = TempDir::new()?;
let policy_path = codex_home.path().join("policy.codexpolicy");
fs::write(
&policy_path,
r#"
prefix_rule(
pattern = ["git", "push"],
decision = "forbidden",
)
"#,
)?;
let output = Command::cargo_bin("codex")?
.env("CODEX_HOME", codex_home.path())
.args([
"execpolicy",
"check",
"--policy",
policy_path
.to_str()
.expect("policy path should be valid UTF-8"),
"git",
"push",
"origin",
"main",
])
.output()?;
assert!(output.status.success());
let result: serde_json::Value = serde_json::from_slice(&output.stdout)?;
assert_eq!(
result,
json!({
"match": {
"decision": "forbidden",
"matchedRules": [
{
"prefixRuleMatch": {
"matchedPrefix": ["git", "push"],
"decision": "forbidden"
}
}
]
}
})
);
Ok(())
}

View File

@@ -8,7 +8,6 @@ pub mod util;
pub use cli::Cli;
use anyhow::anyhow;
use codex_login::AuthManager;
use std::io::IsTerminal;
use std::io::Read;
use std::path::PathBuf;
@@ -57,8 +56,20 @@ async fn init_backend(user_agent_suffix: &str) -> anyhow::Result<BackendContext>
};
append_error_log(format!("startup: base_url={base_url} path_style={style}"));
let auth_manager = util::load_auth_manager().await;
let auth = match auth_manager.as_ref().and_then(AuthManager::auth) {
let auth = match codex_core::config::find_codex_home()
.ok()
.map(|home| {
let store_mode = codex_core::config::Config::load_from_base_config_with_overrides(
codex_core::config::ConfigToml::default(),
codex_core::config::ConfigOverrides::default(),
home.clone(),
)
.map(|cfg| cfg.cli_auth_credentials_store_mode)
.unwrap_or_default();
codex_login::AuthManager::new(home, false, store_mode)
})
.and_then(|am| am.auth())
{
Some(auth) => auth,
None => {
eprintln!(
@@ -1033,7 +1044,7 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
// Close task modal/pending apply if present before opening env modal
app.diff_overlay = None;
app.env_modal = Some(app::EnvModalState { query: String::new(), selected: 0 });
// Cache environments while the modal is open to avoid repeated fetches.
// Cache environments until user explicitly refreshes with 'r' inside the modal.
let should_fetch = app.environments.is_empty();
if should_fetch {
app.env_loading = true;
@@ -1104,7 +1115,7 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
let _ = tx.send(evt);
});
} else {
app.status = "No environment selected".to_string();
app.status = "No environment selected (press 'e' to choose)".to_string();
}
}
needs_redraw = true;
@@ -1302,6 +1313,18 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
// Environment modal key handling
match key.code {
KeyCode::Esc => { app.env_modal = None; needs_redraw = true; }
KeyCode::Char('r') | KeyCode::Char('R') => {
// Trigger refresh of environments
app.env_loading = true; app.env_error = None; needs_redraw = true;
let _ = frame_tx.send(Instant::now() + Duration::from_millis(100));
let tx = tx.clone();
tokio::spawn(async move {
let base_url = crate::util::normalize_base_url(&std::env::var("CODEX_CLOUD_TASKS_BASE_URL").unwrap_or_else(|_| "https://chatgpt.com/backend-api".to_string()));
let headers = crate::util::build_chatgpt_headers().await;
let res = crate::env_detect::list_environments(&base_url, &headers).await;
let _ = tx.send(app::AppEvent::EnvironmentsLoaded(res));
});
}
KeyCode::Char(ch) if !key.modifiers.contains(KeyModifiers::CONTROL) && !key.modifiers.contains(KeyModifiers::ALT) => {
if let Some(m) = app.env_modal.as_mut() { m.query.push(ch); }
needs_redraw = true;
@@ -1408,7 +1431,7 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
}
KeyCode::Char('o') | KeyCode::Char('O') => {
app.env_modal = Some(app::EnvModalState { query: String::new(), selected: 0 });
// Cache environments while the modal is open to avoid repeated fetches.
// Cache environments until user explicitly refreshes with 'r' inside the modal.
let should_fetch = app.environments.is_empty();
if should_fetch { app.env_loading = true; app.env_error = None; }
needs_redraw = true;
@@ -1721,7 +1744,6 @@ mod tests {
use ratatui::layout::Rect;
#[test]
#[ignore = "very slow"]
fn composer_input_renders_typed_characters() {
let mut composer = ComposerInput::new();
let key = KeyEvent::new(KeyCode::Char('a'), KeyModifiers::NONE);

View File

@@ -945,7 +945,9 @@ pub fn draw_env_modal(frame: &mut Frame, area: Rect, app: &mut App) {
// Subheader with usage hints (dim cyan)
let subheader = Paragraph::new(Line::from(
"Type to search, Enter select, Esc cancel".cyan().dim(),
"Type to search, Enter select, Esc cancel; r refresh"
.cyan()
.dim(),
))
.wrap(Wrap { trim: true });
frame.render_widget(subheader, rows[0]);

View File

@@ -2,10 +2,6 @@ use base64::Engine as _;
use chrono::Utc;
use reqwest::header::HeaderMap;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_login::AuthManager;
pub fn set_user_agent_suffix(suffix: &str) {
if let Ok(mut guard) = codex_core::default_client::USER_AGENT_SUFFIX.lock() {
guard.replace(suffix.to_string());
@@ -58,18 +54,6 @@ pub fn extract_chatgpt_account_id(token: &str) -> Option<String> {
.map(str::to_string)
}
pub async fn load_auth_manager() -> Option<AuthManager> {
// TODO: pass in cli overrides once cloud tasks properly support them.
let config = Config::load_with_cli_overrides(Vec::new(), ConfigOverrides::default())
.await
.ok()?;
Some(AuthManager::new(
config.codex_home,
false,
config.cli_auth_credentials_store_mode,
))
}
/// Build headers for ChatGPT-backed requests: `User-Agent`, optional `Authorization`,
/// and optional `ChatGPT-Account-Id`.
pub async fn build_chatgpt_headers() -> HeaderMap {
@@ -85,22 +69,31 @@ pub async fn build_chatgpt_headers() -> HeaderMap {
USER_AGENT,
HeaderValue::from_str(&ua).unwrap_or(HeaderValue::from_static("codex-cli")),
);
if let Some(am) = load_auth_manager().await
&& let Some(auth) = am.auth()
&& let Ok(tok) = auth.get_token().await
&& !tok.is_empty()
{
let v = format!("Bearer {tok}");
if let Ok(hv) = HeaderValue::from_str(&v) {
headers.insert(AUTHORIZATION, hv);
}
if let Some(acc) = auth
.get_account_id()
.or_else(|| extract_chatgpt_account_id(&tok))
&& let Ok(name) = HeaderName::from_bytes(b"ChatGPT-Account-Id")
&& let Ok(hv) = HeaderValue::from_str(&acc)
if let Ok(home) = codex_core::config::find_codex_home() {
let store_mode = codex_core::config::Config::load_from_base_config_with_overrides(
codex_core::config::ConfigToml::default(),
codex_core::config::ConfigOverrides::default(),
home.clone(),
)
.map(|cfg| cfg.cli_auth_credentials_store_mode)
.unwrap_or_default();
let am = codex_login::AuthManager::new(home, false, store_mode);
if let Some(auth) = am.auth()
&& let Ok(tok) = auth.get_token().await
&& !tok.is_empty()
{
headers.insert(name, hv);
let v = format!("Bearer {tok}");
if let Ok(hv) = HeaderValue::from_str(&v) {
headers.insert(AUTHORIZATION, hv);
}
if let Some(acc) = auth
.get_account_id()
.or_else(|| extract_chatgpt_account_id(&tok))
&& let Ok(name) = HeaderName::from_bytes(b"ChatGPT-Account-Id")
&& let Ok(hv) = HeaderValue::from_str(&acc)
{
headers.insert(name, hv);
}
}
}
headers

View File

@@ -1,52 +0,0 @@
/*
* codex-backend
*
* codex-backend
*
* The version of the OpenAPI document: 0.0.1
*
* Generated by: https://openapi-generator.tech
*/
use serde::Deserialize;
use serde::Serialize;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
pub struct CreditStatusDetails {
#[serde(rename = "has_credits")]
pub has_credits: bool,
#[serde(rename = "unlimited")]
pub unlimited: bool,
#[serde(
rename = "balance",
default,
with = "::serde_with::rust::double_option",
skip_serializing_if = "Option::is_none"
)]
pub balance: Option<Option<String>>,
#[serde(
rename = "approx_local_messages",
default,
with = "::serde_with::rust::double_option",
skip_serializing_if = "Option::is_none"
)]
pub approx_local_messages: Option<Option<Vec<serde_json::Value>>>,
#[serde(
rename = "approx_cloud_messages",
default,
with = "::serde_with::rust::double_option",
skip_serializing_if = "Option::is_none"
)]
pub approx_cloud_messages: Option<Option<Vec<serde_json::Value>>>,
}
impl CreditStatusDetails {
pub fn new(has_credits: bool, unlimited: bool) -> CreditStatusDetails {
CreditStatusDetails {
has_credits,
unlimited,
balance: None,
approx_local_messages: None,
approx_cloud_messages: None,
}
}
}

View File

@@ -32,6 +32,3 @@ pub use self::rate_limit_status_details::RateLimitStatusDetails;
pub mod rate_limit_window_snapshot;
pub use self::rate_limit_window_snapshot::RateLimitWindowSnapshot;
pub mod credit_status_details;
pub use self::credit_status_details::CreditStatusDetails;

View File

@@ -23,13 +23,6 @@ pub struct RateLimitStatusPayload {
skip_serializing_if = "Option::is_none"
)]
pub rate_limit: Option<Option<Box<models::RateLimitStatusDetails>>>,
#[serde(
rename = "credits",
default,
with = "::serde_with::rust::double_option",
skip_serializing_if = "Option::is_none"
)]
pub credits: Option<Option<Box<models::CreditStatusDetails>>>,
}
impl RateLimitStatusPayload {
@@ -37,15 +30,12 @@ impl RateLimitStatusPayload {
RateLimitStatusPayload {
plan_type,
rate_limit: None,
credits: None,
}
}
}
#[derive(Clone, Copy, Debug, Eq, PartialEq, Ord, PartialOrd, Hash, Serialize, Deserialize)]
pub enum PlanType {
#[serde(rename = "guest")]
Guest,
#[serde(rename = "free")]
Free,
#[serde(rename = "go")]
@@ -54,8 +44,6 @@ pub enum PlanType {
Plus,
#[serde(rename = "pro")]
Pro,
#[serde(rename = "free_workspace")]
FreeWorkspace,
#[serde(rename = "team")]
Team,
#[serde(rename = "business")]
@@ -64,8 +52,6 @@ pub enum PlanType {
Education,
#[serde(rename = "quorum")]
Quorum,
#[serde(rename = "k12")]
K12,
#[serde(rename = "enterprise")]
Enterprise,
#[serde(rename = "edu")]
@@ -74,6 +60,6 @@ pub enum PlanType {
impl Default for PlanType {
fn default() -> PlanType {
Self::Guest
Self::Free
}
}

View File

@@ -7,6 +7,7 @@
*
* Generated by: https://openapi-generator.tech
*/
use serde::Deserialize;
use serde::Serialize;

View File

@@ -8,12 +8,9 @@ workspace = true
[dependencies]
clap = { workspace = true, features = ["derive", "wrap_help"], optional = true }
codex-app-server-protocol = { workspace = true }
codex-core = { workspace = true }
codex-lmstudio = { workspace = true }
codex-ollama = { workspace = true }
codex-protocol = { workspace = true }
once_cell = { workspace = true }
codex-app-server-protocol = { workspace = true }
serde = { workspace = true, optional = true }
toml = { workspace = true, optional = true }

View File

@@ -24,21 +24,21 @@ pub fn builtin_approval_presets() -> Vec<ApprovalPreset> {
ApprovalPreset {
id: "read-only",
label: "Read Only",
description: "Requires approval to edit files and run commands.",
description: "Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network.",
approval: AskForApproval::OnRequest,
sandbox: SandboxPolicy::ReadOnly,
},
ApprovalPreset {
id: "auto",
label: "Agent",
description: "Read and edit files, and run commands.",
label: "Auto",
description: "Codex can read files, make edits, and run commands in the workspace. Codex requires approval to work outside the workspace or access network.",
approval: AskForApproval::OnRequest,
sandbox: SandboxPolicy::new_workspace_write_policy(),
},
ApprovalPreset {
id: "full-access",
label: "Agent (full access)",
description: "Codex can edit files outside this workspace and run commands with network access. Exercise caution when using.",
label: "Full Access",
description: "Codex can read files, make edits, and run commands with network access, without approval. Exercise caution.",
approval: AskForApproval::Never,
sandbox: SandboxPolicy::DangerFullAccess,
},

View File

@@ -19,8 +19,8 @@ use toml::Value;
pub struct CliConfigOverrides {
/// Override a configuration value that would otherwise be loaded from
/// `~/.codex/config.toml`. Use a dotted path (`foo.bar.baz`) to override
/// nested values. The `value` portion is parsed as TOML. If it fails to
/// parse as TOML, the raw string is used as a literal.
/// nested values. The `value` portion is parsed as JSON. If it fails to
/// parse as JSON, the raw string is used as a literal.
///
/// Examples:
/// - `-c model="o3"`
@@ -59,7 +59,7 @@ impl CliConfigOverrides {
return Err(format!("Empty key in override: {s}"));
}
// Attempt to parse as TOML. If that fails, treat it as a raw
// Attempt to parse as JSON. If that fails, treat it as a raw
// string. This allows convenient usage such as
// `-c model=o3` without the quotes.
let value: Value = match parse_toml_value(value_str) {
@@ -151,15 +151,6 @@ mod tests {
assert_eq!(v.as_integer(), Some(42));
}
#[test]
fn parses_bool() {
let true_literal = parse_toml_value("true").expect("parse");
assert_eq!(true_literal.as_bool(), Some(true));
let false_literal = parse_toml_value("false").expect("parse");
assert_eq!(false_literal.as_bool(), Some(false));
}
#[test]
fn fails_on_unquoted_string() {
assert!(parse_toml_value("hello").is_err());

View File

@@ -15,12 +15,13 @@ pub fn create_config_summary_entries(config: &Config) -> Vec<(&'static str, Stri
if config.model_provider.wire_api == WireApi::Responses
&& config.model_family.supports_reasoning_summaries
{
let reasoning_effort = config
.model_reasoning_effort
.or(config.model_family.default_reasoning_effort)
.map(|effort| effort.to_string())
.unwrap_or_else(|| "none".to_string());
entries.push(("reasoning effort", reasoning_effort));
entries.push((
"reasoning effort",
config
.model_reasoning_effort
.map(|effort| effort.to_string())
.unwrap_or_else(|| "none".to_string()),
));
entries.push((
"reasoning summaries",
config.model_reasoning_summary.to_string(),

View File

@@ -37,5 +37,3 @@ pub mod model_presets;
// Shared approval presets (AskForApproval + Sandbox) used by TUI and MCP server
// Not to be confused with AskForApproval, which we should probably rename to EscalationPolicy.
pub mod approval_presets;
// Shared OSS provider utilities used by TUI and exec
pub mod oss;

View File

@@ -1,12 +1,5 @@
use std::collections::HashMap;
use codex_app_server_protocol::AuthMode;
use codex_core::protocol_config_types::ReasoningEffort;
use once_cell::sync::Lazy;
pub const HIDE_GPT5_1_MIGRATION_PROMPT_CONFIG: &str = "hide_gpt5_1_migration_prompt";
pub const HIDE_GPT_5_1_CODEX_MAX_MIGRATION_PROMPT_CONFIG: &str =
"hide_gpt-5.1-codex-max_migration_prompt";
/// A reasoning effort option that can be surfaced for a model.
#[derive(Debug, Clone, Copy)]
@@ -17,15 +10,8 @@ pub struct ReasoningEffortPreset {
pub description: &'static str,
}
#[derive(Debug, Clone)]
pub struct ModelUpgrade {
pub id: &'static str,
pub reasoning_effort_mapping: Option<HashMap<ReasoningEffort, ReasoningEffort>>,
pub migration_config_key: &'static str,
}
/// Metadata describing a Codex-supported model.
#[derive(Debug, Clone)]
#[derive(Debug, Clone, Copy)]
pub struct ModelPreset {
/// Stable identifier for the preset.
pub id: &'static str,
@@ -41,243 +27,70 @@ pub struct ModelPreset {
pub supported_reasoning_efforts: &'static [ReasoningEffortPreset],
/// Whether this is the default model for new users.
pub is_default: bool,
/// recommended upgrade model
pub upgrade: Option<ModelUpgrade>,
/// Whether this preset should appear in the picker UI.
pub show_in_picker: bool,
}
static PRESETS: Lazy<Vec<ModelPreset>> = Lazy::new(|| {
vec![
ModelPreset {
id: "gpt-5.1-codex-max",
model: "gpt-5.1-codex-max",
display_name: "gpt-5.1-codex-max",
description: "Latest Codex-optimized flagship for deep and fast reasoning.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Fast responses with lighter reasoning",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Balances speed and reasoning depth for everyday tasks",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex problems",
},
ReasoningEffortPreset {
effort: ReasoningEffort::XHigh,
description: "Extra high reasoning depth for complex problems",
},
],
is_default: true,
upgrade: None,
show_in_picker: true,
},
ModelPreset {
id: "gpt-5.1-codex",
model: "gpt-5.1-codex",
display_name: "gpt-5.1-codex",
description: "Optimized for codex.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Fastest responses with limited reasoning",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Dynamically adjusts reasoning based on the task",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
upgrade: Some(ModelUpgrade {
id: "gpt-5.1-codex-max",
reasoning_effort_mapping: None,
migration_config_key: HIDE_GPT_5_1_CODEX_MAX_MIGRATION_PROMPT_CONFIG,
}),
show_in_picker: true,
},
ModelPreset {
id: "gpt-5.1-codex-mini",
model: "gpt-5.1-codex-mini",
display_name: "gpt-5.1-codex-mini",
description: "Optimized for codex. Cheaper, faster, but less capable.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Dynamically adjusts reasoning based on the task",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
upgrade: Some(ModelUpgrade {
id: "gpt-5.1-codex-max",
reasoning_effort_mapping: None,
migration_config_key: HIDE_GPT_5_1_CODEX_MAX_MIGRATION_PROMPT_CONFIG,
}),
show_in_picker: true,
},
ModelPreset {
id: "gpt-5.1",
model: "gpt-5.1",
display_name: "gpt-5.1",
description: "Broad world knowledge with strong general reasoning.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Balances speed with some reasoning; useful for straightforward queries and short explanations",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Provides a solid balance of reasoning depth and latency for general-purpose tasks",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
upgrade: Some(ModelUpgrade {
id: "gpt-5.1-codex-max",
reasoning_effort_mapping: None,
migration_config_key: HIDE_GPT_5_1_CODEX_MAX_MIGRATION_PROMPT_CONFIG,
}),
show_in_picker: true,
},
// Deprecated models.
ModelPreset {
id: "gpt-5-codex",
model: "gpt-5-codex",
display_name: "gpt-5-codex",
description: "Optimized for codex.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Fastest responses with limited reasoning",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Dynamically adjusts reasoning based on the task",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
upgrade: Some(ModelUpgrade {
id: "gpt-5.1-codex-max",
reasoning_effort_mapping: None,
migration_config_key: HIDE_GPT_5_1_CODEX_MAX_MIGRATION_PROMPT_CONFIG,
}),
show_in_picker: false,
},
ModelPreset {
id: "gpt-5-codex-mini",
model: "gpt-5-codex-mini",
display_name: "gpt-5-codex-mini",
description: "Optimized for codex. Cheaper, faster, but less capable.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Dynamically adjusts reasoning based on the task",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
upgrade: Some(ModelUpgrade {
id: "gpt-5.1-codex-mini",
reasoning_effort_mapping: None,
migration_config_key: HIDE_GPT5_1_MIGRATION_PROMPT_CONFIG,
}),
show_in_picker: false,
},
ModelPreset {
id: "gpt-5",
model: "gpt-5",
display_name: "gpt-5",
description: "Broad world knowledge with strong general reasoning.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Minimal,
description: "Fastest responses with little reasoning",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Balances speed with some reasoning; useful for straightforward queries and short explanations",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Provides a solid balance of reasoning depth and latency for general-purpose tasks",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
upgrade: Some(ModelUpgrade {
id: "gpt-5.1-codex-max",
reasoning_effort_mapping: None,
migration_config_key: HIDE_GPT_5_1_CODEX_MAX_MIGRATION_PROMPT_CONFIG,
}),
show_in_picker: false,
},
]
});
const PRESETS: &[ModelPreset] = &[
ModelPreset {
id: "gpt-5-codex",
model: "gpt-5-codex",
display_name: "gpt-5-codex",
description: "Optimized for coding tasks with many tools.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Fastest responses with limited reasoning",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Dynamically adjusts reasoning based on the task",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: true,
},
ModelPreset {
id: "gpt-5",
model: "gpt-5",
display_name: "gpt-5",
description: "Broad world knowledge with strong general reasoning.",
default_reasoning_effort: ReasoningEffort::Medium,
supported_reasoning_efforts: &[
ReasoningEffortPreset {
effort: ReasoningEffort::Minimal,
description: "Fastest responses with little reasoning",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Low,
description: "Balances speed with some reasoning; useful for straightforward queries and short explanations",
},
ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: "Provides a solid balance of reasoning depth and latency for general-purpose tasks",
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems",
},
],
is_default: false,
},
];
pub fn builtin_model_presets(auth_mode: Option<AuthMode>) -> Vec<ModelPreset> {
PRESETS
.iter()
.filter(|preset| match auth_mode {
Some(AuthMode::ApiKey) => preset.show_in_picker && preset.id != "gpt-5.1-codex-max",
_ => preset.show_in_picker,
})
.cloned()
.collect()
}
pub fn all_model_presets() -> &'static Vec<ModelPreset> {
&PRESETS
pub fn builtin_model_presets(_auth_mode: Option<AuthMode>) -> Vec<ModelPreset> {
PRESETS.to_vec()
}
#[cfg(test)]
mod tests {
use super::*;
use codex_app_server_protocol::AuthMode;
#[test]
fn only_one_default_model_is_configured() {
let default_models = PRESETS.iter().filter(|preset| preset.is_default).count();
assert!(default_models == 1);
}
#[test]
fn gpt_5_1_codex_max_hidden_for_api_key_auth() {
let presets = builtin_model_presets(Some(AuthMode::ApiKey));
assert!(
presets
.iter()
.all(|preset| preset.id != "gpt-5.1-codex-max")
);
}
}

View File

@@ -1,60 +0,0 @@
//! OSS provider utilities shared between TUI and exec.
use codex_core::LMSTUDIO_OSS_PROVIDER_ID;
use codex_core::OLLAMA_OSS_PROVIDER_ID;
use codex_core::config::Config;
/// Returns the default model for a given OSS provider.
pub fn get_default_model_for_oss_provider(provider_id: &str) -> Option<&'static str> {
match provider_id {
LMSTUDIO_OSS_PROVIDER_ID => Some(codex_lmstudio::DEFAULT_OSS_MODEL),
OLLAMA_OSS_PROVIDER_ID => Some(codex_ollama::DEFAULT_OSS_MODEL),
_ => None,
}
}
/// Ensures the specified OSS provider is ready (models downloaded, service reachable).
pub async fn ensure_oss_provider_ready(
provider_id: &str,
config: &Config,
) -> Result<(), std::io::Error> {
match provider_id {
LMSTUDIO_OSS_PROVIDER_ID => {
codex_lmstudio::ensure_oss_ready(config)
.await
.map_err(|e| std::io::Error::other(format!("OSS setup failed: {e}")))?;
}
OLLAMA_OSS_PROVIDER_ID => {
codex_ollama::ensure_oss_ready(config)
.await
.map_err(|e| std::io::Error::other(format!("OSS setup failed: {e}")))?;
}
_ => {
// Unknown provider, skip setup
}
}
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_get_default_model_for_provider_lmstudio() {
let result = get_default_model_for_oss_provider(LMSTUDIO_OSS_PROVIDER_ID);
assert_eq!(result, Some(codex_lmstudio::DEFAULT_OSS_MODEL));
}
#[test]
fn test_get_default_model_for_provider_ollama() {
let result = get_default_model_for_oss_provider(OLLAMA_OSS_PROVIDER_ID);
assert_eq!(result, Some(codex_ollama::DEFAULT_OSS_MODEL));
}
#[test]
fn test_get_default_model_for_provider_unknown() {
let result = get_default_model_for_oss_provider("unknown-provider");
assert_eq!(result, None);
}
}

View File

@@ -19,11 +19,9 @@ async-trait = { workspace = true }
base64 = { workspace = true }
bytes = { workspace = true }
chrono = { workspace = true, features = ["serde"] }
chardetng = { workspace = true }
codex-app-server-protocol = { workspace = true }
codex-apply-patch = { workspace = true }
codex-async-utils = { workspace = true }
codex-execpolicy = { workspace = true }
codex-file-search = { workspace = true }
codex-git = { workspace = true }
codex-keyring-store = { workspace = true }
@@ -33,16 +31,20 @@ codex-rmcp-client = { workspace = true }
codex-utils-pty = { workspace = true }
codex-utils-readiness = { workspace = true }
codex-utils-string = { workspace = true }
codex-windows-sandbox = { package = "codex-windows-sandbox", path = "../windows-sandbox-rs" }
codex-utils-tokenizer = { workspace = true }
dirs = { workspace = true }
dunce = { workspace = true }
env-flags = { workspace = true }
encoding_rs = { workspace = true }
eventsource-stream = { workspace = true }
futures = { workspace = true }
http = { workspace = true }
indexmap = { workspace = true }
keyring = { workspace = true, features = ["crypto-rust"] }
keyring = { workspace = true, features = [
"apple-native",
"crypto-rust",
"linux-native-async-persistent",
"windows-native",
] }
libc = { workspace = true }
mcp-types = { workspace = true }
os_info = { workspace = true }
@@ -57,7 +59,6 @@ shlex = { workspace = true }
similar = { workspace = true }
strum_macros = { workspace = true }
tempfile = { workspace = true }
test-case = "3.3.1"
test-log = { workspace = true }
thiserror = { workspace = true }
time = { workspace = true, features = [
@@ -79,19 +80,18 @@ toml_edit = { workspace = true }
tracing = { workspace = true, features = ["log"] }
tree-sitter = { workspace = true }
tree-sitter-bash = { workspace = true }
uuid = { workspace = true, features = ["serde", "v4", "v5"] }
uuid = { workspace = true, features = ["serde", "v4"] }
which = { workspace = true }
wildmatch = { workspace = true }
codex_windows_sandbox = { package = "codex-windows-sandbox", path = "../windows-sandbox-rs" }
[target.'cfg(target_os = "linux")'.dependencies]
landlock = { workspace = true }
seccompiler = { workspace = true }
keyring = { workspace = true, features = ["linux-native-async-persistent"] }
[target.'cfg(target_os = "macos")'.dependencies]
core-foundation = "0.9"
keyring = { workspace = true, features = ["apple-native"] }
# Build OpenSSL from source for musl builds.
[target.x86_64-unknown-linux-musl.dependencies]
@@ -101,18 +101,10 @@ openssl-sys = { workspace = true, features = ["vendored"] }
[target.aarch64-unknown-linux-musl.dependencies]
openssl-sys = { workspace = true, features = ["vendored"] }
[target.'cfg(target_os = "windows")'.dependencies]
keyring = { workspace = true, features = ["windows-native"] }
[target.'cfg(any(target_os = "freebsd", target_os = "openbsd"))'.dependencies]
keyring = { workspace = true, features = ["sync-secret-service"] }
[dev-dependencies]
assert_cmd = { workspace = true }
assert_matches = { workspace = true }
codex-arg0 = { workspace = true }
core_test_support = { workspace = true }
ctor = { workspace = true }
escargot = { workspace = true }
image = { workspace = true, features = ["jpeg", "png"] }
maplit = { workspace = true }

View File

@@ -1,117 +0,0 @@
You are Codex, based on GPT-5. You are running as a coding agent in the Codex CLI on a user's computer.
## General
- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
## Editing constraints
- Default to ASCII when editing or creating files. Only introduce non-ASCII or other Unicode characters when there is a clear justification and the file already uses them.
- Add succinct code comments that explain what is going on if code is not self-explanatory. You should not add comments like "Assigns the value to the variable", but a brief comment might be useful ahead of a complex code block that the user would otherwise have to spend time parsing out. Usage of these comments should be rare.
- Try to use apply_patch for single file edits, but it is fine to explore other options to make the edit if it does not work well. Do not use apply_patch for changes that are auto-generated (i.e. generating package.json or running a lint or format command like gofmt) or when scripting is more efficient (such as search and replacing a string across a codebase).
- You may be in a dirty git worktree.
* NEVER revert existing changes you did not make unless explicitly requested, since these changes were made by the user.
* If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, don't revert those changes.
* If the changes are in files you've touched recently, you should read carefully and understand how you can work with the changes rather than reverting them.
* If the changes are in unrelated files, just ignore them and don't revert them.
- Do not amend a commit unless explicitly requested to do so.
- While you are working, you might notice unexpected changes that you didn't make. If this happens, STOP IMMEDIATELY and ask the user how they would like to proceed.
- **NEVER** use destructive commands like `git reset --hard` or `git checkout --` unless specifically requested or approved by the user.
## Plan tool
When using the planning tool:
- Skip using the planning tool for straightforward tasks (roughly the easiest 25%).
- Do not make single-step plans.
- When you made a plan, update it after having performed one of the sub-tasks that you shared on the plan.
## Codex CLI harness, sandboxing, and approvals
The Codex CLI harness supports several different configurations for sandboxing and escalation approvals that the user can choose from.
Filesystem sandboxing defines which files can be read or written. The options for `sandbox_mode` are:
- **read-only**: The sandbox only permits reading files.
- **workspace-write**: The sandbox permits reading files, and editing files in `cwd` and `writable_roots`. Editing files in other directories requires approval.
- **danger-full-access**: No filesystem sandboxing - all commands are permitted.
Network sandboxing defines whether network can be accessed without approval. Options for `network_access` are:
- **restricted**: Requires approval
- **enabled**: No approval needed
Approvals are your mechanism to get user consent to run shell commands without the sandbox. Possible configuration options for `approval_policy` are
- **untrusted**: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
- **on-failure**: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
- **on-request**: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for it in the `shell` command description.)
- **never**: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is paired with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
When you are running with `approval_policy == on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /var)
- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval. ALWAYS proceed to use the `with_escalated_permissions` and `justification` parameters - do not message the user before requesting approval for the command.
- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
- (for all of these, you should weigh alternative paths that do not require approval)
When `sandbox_mode` is set to read-only, you'll need to request approval for any command that isn't a read.
You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing enabled, and approval on-failure.
Although they introduce friction to the user because your work is paused until the user responds, you should leverage them when necessary to accomplish important work. If the completing the task requires escalated permissions, Do not let these settings or the sandbox deter you from attempting to accomplish the user's task unless it is set to "never", in which case never ask for approvals.
When requesting approval to execute a command that will require escalated privileges:
- Provide the `with_escalated_permissions` parameter with the boolean value true
- Include a short, 1 sentence explanation for why you need to enable `with_escalated_permissions` in the justification parameter
## Special user requests
- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such as `date`), you should do so.
- If the user asks for a "review", default to a code review mindset: prioritise identifying bugs, risks, behavioural regressions, and missing tests. Findings must be the primary focus of the response - keep summaries or overviews brief and only after enumerating the issues. Present findings first (ordered by severity with file/line references), follow with open questions or assumptions, and offer a change-summary only as a secondary detail. If no findings are discovered, state that explicitly and mention any residual risks or testing gaps.
## Frontend tasks
When doing frontend design tasks, avoid collapsing into "AI slop" or safe, average-looking layouts.
Aim for interfaces that feel intentional, bold, and a bit surprising.
- Typography: Use expressive, purposeful fonts and avoid default stacks (Inter, Roboto, Arial, system).
- Color & Look: Choose a clear visual direction; define CSS variables; avoid purple-on-white defaults. No purple bias or dark mode bias.
- Motion: Use a few meaningful animations (page-load, staggered reveals) instead of generic micro-motions.
- Background: Don't rely on flat, single-color backgrounds; use gradients, shapes, or subtle patterns to build atmosphere.
- Overall: Avoid boilerplate layouts and interchangeable UI patterns. Vary themes, type families, and visual languages across outputs.
- Ensure the page loads properly on both desktop and mobile
Exception: If working within an existing website or design system, preserve the established patterns, structure, and visual language.
## Presenting your work and final message
You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
- Default: be very concise; friendly coding teammate tone.
- Ask only when needed; suggest ideas; mirror the user's style.
- For substantial work, summarize clearly; follow finalanswer formatting.
- Skip heavy formatting for simple confirmations.
- Don't dump large files you've written; reference paths only.
- No "save/copy this file" - User is on the same machine.
- Offer logical next steps (tests, commits, build) briefly; add verify steps if you couldn't do something.
- For code changes:
* Lead with a quick explanation of the change, and then give more details on the context covering where and why a change was made. Do not start this explanation with "summary", just jump right in.
* If there are natural next steps the user may want to take, suggest them at the end of your response. Do not make suggestions if there are no natural next steps.
* When suggesting multiple options, use numeric lists for the suggestions so the user can quickly respond with a single number.
- The user does not command execution outputs. When asked to show the output of a command (e.g. `git show`), relay the important details in your answer or summarize the key lines so the user understands the result.
### Final answer structure and style guidelines
- Plain text; CLI handles styling. Use structure only when it helps scanability.
- Headers: optional; short Title Case (1-3 words) wrapped in **…**; no blank line before the first bullet; add only if they truly help.
- Bullets: use - ; merge related points; keep to one line when possible; 46 per list ordered by importance; keep phrasing consistent.
- Monospace: backticks for commands/paths/env vars/code ids and inline examples; use for literal keyword bullets; never combine with **.
- Code samples or multi-line snippets should be wrapped in fenced code blocks; include an info string as often as possible.
- Structure: group related bullets; order sections general → specific → supporting; for subsections, start with a bolded keyword bullet, then items; match complexity to the task.
- Tone: collaborative, concise, factual; present tense, active voice; selfcontained; no "above/below"; parallel wording.
- Don'ts: no nested bullets/hierarchies; no ANSI codes; don't cram unrelated keywords; keep keyword lists short—wrap/reformat if long; avoid naming formatting styles in answers.
- Adaptation: code explanations → precise, structured with code refs; simple tasks → lead with outcome; big changes → logical walkthrough + rationale + next actions; casual one-offs → plain sentences, no headers/bullets.
- File References: When referencing files in your response follow the below rules:
* Use inline code to make file paths clickable.
* Each reference should have a stand alone path. Even if it's the same file.
* Accepted: absolute, workspacerelative, a/ or b/ diff prefixes, or bare filename/suffix.
* Optionally include line/column (1based): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
* Do not use URIs like file://, vscode://, or https://.
* Do not provide range of lines
* Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5

View File

@@ -1,368 +0,0 @@
You are GPT-5.1 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.
Your capabilities:
- Receive user prompts and other context provided by the harness, such as files in the workspace.
- Communicate with the user by streaming thinking & responses, and by making & updating plans.
- Emit function calls to run terminal commands and apply patches. Depending on how this specific run is configured, you can request that these function calls be escalated to the user for approval before running. More on this in the "Sandbox and approvals" section.
Within this context, Codex refers to the open-source agentic coding interface (not the old Codex language model built by OpenAI).
# How you work
## Personality
Your default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
# AGENTS.md spec
- Repos often contain AGENTS.md files. These files can appear anywhere within the repository.
- These files are a way for humans to give you (the agent) instructions or tips for working within the container.
- Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.
- Instructions in AGENTS.md files:
- The scope of an AGENTS.md file is the entire directory tree rooted at the folder that contains it.
- For every file you touch in the final patch, you must obey instructions in any AGENTS.md file whose scope includes that file.
- Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the file states otherwise.
- More-deeply-nested AGENTS.md files take precedence in the case of conflicting instructions.
- Direct system/developer/user instructions (as part of a prompt) take precedence over AGENTS.md instructions.
- The contents of the AGENTS.md file at the root of the repo and any directories from the CWD up to the root are included with the developer message and don't need to be re-read. When working in a subdirectory of CWD, or a directory outside the CWD, check for any AGENTS.md files that may be applicable.
## Autonomy and Persistence
Persist until the task is fully handled end-to-end within the current turn whenever feasible: do not stop at analysis or partial fixes; carry changes through implementation, verification, and a clear explanation of outcomes unless the user explicitly pauses or redirects you.
Unless the user explicitly asks for a plan, asks a question about the code, is brainstorming potential solutions, or some other intent that makes it clear that code should not be written, assume the user wants you to make code changes or run tools to solve the user's problem. In these cases, it's bad to output your proposed solution in a message, you should go ahead and actually implement the change. If you encounter challenges or blockers, you should attempt to resolve them yourself.
## Responsiveness
### User Updates Spec
You'll work for stretches with tool calls — it's critical to keep the user updated as you work.
Frequency & Length:
- Send short updates (12 sentences) whenever there is a meaningful, important insight you need to share with the user to keep them informed.
- If you expect a longer headsdown stretch, post a brief headsdown note with why and when you'll report back; when you resume, summarize what you learned.
- Only the initial plan, plan updates, and final recap can be longer, with multiple bullets and paragraphs
Tone:
- Friendly, confident, senior-engineer energy. Positive, collaborative, humble; fix mistakes quickly.
Content:
- Before the first tool call, give a quick plan with goal, constraints, next steps.
- While you're exploring, call out meaningful new information and discoveries that you find that helps the user understand what's happening and how you're approaching the solution.
- If you change the plan (e.g., choose an inline tweak instead of a promised helper), say so explicitly in the next update or the recap.
**Examples:**
- “Ive explored the repo; now checking the API route definitions.”
- “Next, Ill patch the config and update the related tests.”
- “Im about to scaffold the CLI commands and helper functions.”
- “Ok cool, so Ive wrapped my head around the repo. Now digging into the API routes.”
- “Configs looking tidy. Next up is patching helpers to keep things in sync.”
- “Finished poking at the DB gateway. I will now chase down error handling.”
- “Alright, build pipeline order is interesting. Checking how it reports failures.”
- “Spotted a clever caching util; now hunting where it gets used.”
## Planning
You have access to an `update_plan` tool which tracks steps and progress and renders them to the user. Using the tool helps demonstrate that you've understood the task and convey how you're approaching it. Plans can help to make complex, ambiguous, or multi-phase work clearer and more collaborative for the user. A good plan should break the task into meaningful, logically ordered steps that are easy to verify as you go.
Note that plans are not for padding out simple work with filler steps or stating the obvious. The content of your plan should not involve doing anything that you aren't capable of doing (i.e. don't try to test things that you can't test). Do not use plans for simple or single-step queries that you can just do or answer immediately.
Do not repeat the full contents of the plan after an `update_plan` call — the harness already displays it. Instead, summarize the change made and highlight any important context or next step.
Before running a command, consider whether or not you have completed the previous step, and make sure to mark it as completed before moving on to the next step. It may be the case that you complete all steps in your plan after a single pass of implementation. If this is the case, you can simply mark all the planned steps as completed. Sometimes, you may need to change plans in the middle of a task: call `update_plan` with the updated plan and make sure to provide an `explanation` of the rationale when doing so.
Maintain statuses in the tool: exactly one item in_progress at a time; mark items complete when done; post timely status transitions. Do not jump an item from pending to completed: always set it to in_progress first. Do not batch-complete multiple items after the fact. Finish with all items completed or explicitly canceled/deferred before ending the turn. Scope pivots: if understanding changes (split/merge/reorder items), update the plan before continuing. Do not let the plan go stale while coding.
Use a plan when:
- The task is non-trivial and will require multiple actions over a long time horizon.
- There are logical phases or dependencies where sequencing matters.
- The work has ambiguity that benefits from outlining high-level goals.
- You want intermediate checkpoints for feedback and validation.
- When the user asked you to do more than one thing in a single prompt
- The user has asked you to use the plan tool (aka "TODOs")
- You generate additional steps while working, and plan to do them before yielding to the user
### Examples
**High-quality plans**
Example 1:
1. Add CLI entry with file args
2. Parse Markdown via CommonMark library
3. Apply semantic HTML template
4. Handle code blocks, images, links
5. Add error handling for invalid files
Example 2:
1. Define CSS variables for colors
2. Add toggle with localStorage state
3. Refactor components to use variables
4. Verify all views for readability
5. Add smooth theme-change transition
Example 3:
1. Set up Node.js + WebSocket server
2. Add join/leave broadcast events
3. Implement messaging with timestamps
4. Add usernames + mention highlighting
5. Persist messages in lightweight DB
6. Add typing indicators + unread count
**Low-quality plans**
Example 1:
1. Create CLI tool
2. Add Markdown parser
3. Convert to HTML
Example 2:
1. Add dark mode toggle
2. Save preference
3. Make styles look good
Example 3:
1. Create single-file HTML game
2. Run quick sanity check
3. Summarize usage instructions
If you need to write a plan, only write high quality plans, not low quality ones.
## Task execution
You are a coding agent. You must keep going until the query or task is completely resolved, before ending your turn and yielding back to the user. Persist until the task is fully handled end-to-end within the current turn whenever feasible and persevere even when function calls fail. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability, using the tools available to you, before coming back to the user. Do NOT guess or make up an answer.
You MUST adhere to the following criteria when solving queries:
- Working on the repo(s) in the current environment is allowed, even if they are proprietary.
- Analyzing code for vulnerabilities is allowed.
- Showing user code and tool call details is allowed.
- Use the `apply_patch` tool to edit files (NEVER try `applypatch` or `apply-patch`, only `apply_patch`). This is a FREEFORM tool, so do not wrap the patch in JSON.
If completing the user's task requires writing or modifying files, your code and final answer should follow these coding guidelines, though user instructions (i.e. AGENTS.md) may override these guidelines:
- Fix the problem at the root cause rather than applying surface-level patches, when possible.
- Avoid unneeded complexity in your solution.
- Do not attempt to fix unrelated bugs or broken tests. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
- Update documentation as necessary.
- Keep changes consistent with the style of the existing codebase. Changes should be minimal and focused on the task.
- Use `git log` and `git blame` to search the history of the codebase if additional context is required.
- NEVER add copyright or license headers unless specifically requested.
- Do not waste tokens by re-reading files after calling `apply_patch` on them. The tool call will fail if it didn't work. The same goes for making folders, deleting folders, etc.
- Do not `git commit` your changes or create new git branches unless explicitly requested.
- Do not add inline comments within code unless explicitly requested.
- Do not use one-letter variable names unless explicitly requested.
- NEVER output inline citations like "【F:README.md†L5-L14】" in your outputs. The CLI is not able to render these so they will just be broken in the UI. Instead, if you output valid filepaths, users will be able to click on them to open the files in their editor.
## Codex CLI harness, sandboxing, and approvals
The Codex CLI harness supports several different configurations for sandboxing and escalation approvals that the user can choose from.
Filesystem sandboxing defines which files can be read or written. The options for `sandbox_mode` are:
- **read-only**: The sandbox only permits reading files.
- **workspace-write**: The sandbox permits reading files, and editing files in `cwd` and `writable_roots`. Editing files in other directories requires approval.
- **danger-full-access**: No filesystem sandboxing - all commands are permitted.
Network sandboxing defines whether network can be accessed without approval. Options for `network_access` are:
- **restricted**: Requires approval
- **enabled**: No approval needed
Approvals are your mechanism to get user consent to run shell commands without the sandbox. Possible configuration options for `approval_policy` are
- **untrusted**: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
- **on-failure**: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
- **on-request**: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for escalating in the tool definition.)
- **never**: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is paired with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
When you are running with `approval_policy == on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /var)
- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval. ALWAYS proceed to use the `with_escalated_permissions` and `justification` parameters. Within this harness, prefer requesting approval via the tool over asking in natural language.
- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
- (for all of these, you should weigh alternative paths that do not require approval)
When `sandbox_mode` is set to read-only, you'll need to request approval for any command that isn't a read.
You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing enabled, and approval on-failure.
Although they introduce friction to the user because your work is paused until the user responds, you should leverage them when necessary to accomplish important work. If the completing the task requires escalated permissions, Do not let these settings or the sandbox deter you from attempting to accomplish the user's task unless it is set to "never", in which case never ask for approvals.
When requesting approval to execute a command that will require escalated privileges:
- Provide the `with_escalated_permissions` parameter with the boolean value true
- Include a short, 1 sentence explanation for why you need to enable `with_escalated_permissions` in the justification parameter
## Validating your work
If the codebase has tests or the ability to build or run, consider using them to verify changes once your work is complete.
When testing, your philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests.
Similarly, once you're confident in correctness, you can suggest or use formatting commands to ensure that your code is well formatted. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.
For all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
Be mindful of whether to run validation commands proactively. In the absence of behavioral guidance:
- When running in non-interactive approval modes like **never** or **on-failure**, you can proactively run tests, lint and do whatever you need to ensure you've completed the task. If you are unable to run tests, you must still do your utmost best to complete the task.
- When working in interactive approval modes like **untrusted**, or **on-request**, hold off on running tests or lint commands until the user is ready for you to finalize your output, because these commands take time to run and slow down iteration. Instead suggest what you want to do next, and let the user confirm first.
- When working on test-related tasks, such as adding tests, fixing tests, or reproducing a bug to verify behavior, you may proactively run tests regardless of approval mode. Use your judgement to decide whether this is a test-related task.
## Ambition vs. precision
For tasks that have no prior context (i.e. the user is starting something brand new), you should feel free to be ambitious and demonstrate creativity with your implementation.
If you're operating in an existing codebase, you should make sure you do exactly what the user asks with surgical precision. Treat the surrounding codebase with respect, and don't overstep (i.e. changing filenames or variables unnecessarily). You should balance being sufficiently ambitious and proactive when completing tasks of this nature.
You should use judicious initiative to decide on the right level of detail and complexity to deliver based on the user's needs. This means showing good judgment that you're capable of doing the right extras without gold-plating. This might be demonstrated by high-value, creative touches when scope of the task is vague; while being surgical and targeted when scope is tightly specified.
## Sharing progress updates
For especially longer tasks that you work on (i.e. requiring many tool calls, or a plan with multiple steps), you should provide progress updates back to the user at reasonable intervals. These updates should be structured as a concise sentence or two (no more than 8-10 words long) recapping progress so far in plain language: this update demonstrates your understanding of what needs to be done, progress so far (i.e. files explores, subtasks complete), and where you're going next.
Before doing large chunks of work that may incur latency as experienced by the user (i.e. writing a new file), you should send a concise message to the user with an update indicating what you're about to do to ensure they know what you're spending time on. Don't start editing or writing large files before informing the user what you are doing and why.
The messages you send before tool calls should describe what is immediately about to be done next in very concise language. If there was previous work done, this preamble message should also include a note about the work done so far to bring the user along.
## Presenting your work and final message
Your final message should read naturally, like an update from a concise teammate. For casual conversation, brainstorming tasks, or quick questions from the user, respond in a friendly, conversational tone. You should ask questions, suggest ideas, and adapt to the users style. If you've finished a large amount of work, when describing what you've done to the user, you should follow the final answer formatting guidelines to communicate substantive changes. You don't need to add structured formatting for one-word answers, greetings, or purely conversational exchanges.
You can skip heavy formatting for single, simple actions or confirmations. In these cases, respond in plain sentences with any relevant next step or quick option. Reserve multi-section structured responses for results that need grouping or explanation.
The user is working on the same computer as you, and has access to your work. As such there's no need to show the contents of files you have already written unless the user explicitly asks for them. Similarly, if you've created or modified files using `apply_patch`, there's no need to tell users to "save the file" or "copy the code into a file"—just reference the file path.
If there's something that you think you could help with as a logical next step, concisely ask the user if they want you to do so. Good examples of this are running tests, committing changes, or building out the next logical component. If theres something that you couldn't do (even with approval) but that the user might want to do (such as verifying changes by running the app), include those instructions succinctly.
Brevity is very important as a default. You should be very concise (i.e. no more than 10 lines), but can relax this requirement for tasks where additional detail and comprehensiveness is important for the user's understanding.
### Final answer structure and style guidelines
You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
**Section Headers**
- Use only when they improve clarity — they are not mandatory for every answer.
- Choose descriptive names that fit the content
- Keep headers short (13 words) and in `**Title Case**`. Always start headers with `**` and end with `**`
- Leave no blank line before the first bullet under a header.
- Section headers should only be used where they genuinely improve scanability; avoid fragmenting the answer.
**Bullets**
- Use `-` followed by a space for every bullet.
- Merge related points when possible; avoid a bullet for every trivial detail.
- Keep bullets to one line unless breaking for clarity is unavoidable.
- Group into short lists (46 bullets) ordered by importance.
- Use consistent keyword phrasing and formatting across sections.
**Monospace**
- Wrap all commands, file paths, env vars, code identifiers, and code samples in backticks (`` `...` ``).
- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.
- Never mix monospace and bold markers; choose one based on whether its a keyword (`**`) or inline code/path (`` ` ``).
**File References**
When referencing files in your response, make sure to include the relevant start line and always follow the below rules:
* Use inline code to make file paths clickable.
* Each reference should have a stand alone path. Even if it's the same file.
* Accepted: absolute, workspacerelative, a/ or b/ diff prefixes, or bare filename/suffix.
* Line/column (1based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
* Do not use URIs like file://, vscode://, or https://.
* Do not provide range of lines
* Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5
**Structure**
- Place related bullets together; dont mix unrelated concepts in the same section.
- Order sections from general → specific → supporting info.
- For subsections (e.g., “Binaries” under “Rust Workspace”), introduce with a bolded keyword bullet, then list items under it.
- Match structure to complexity:
- Multi-part or detailed results → use clear headers and grouped bullets.
- Simple results → minimal headers, possibly just a short list or paragraph.
**Tone**
- Keep the voice collaborative and natural, like a coding partner handing off work.
- Be concise and factual — no filler or conversational commentary and avoid unnecessary repetition
- Use present tense and active voice (e.g., “Runs tests” not “This will run tests”).
- Keep descriptions self-contained; dont refer to “above” or “below”.
- Use parallel structure in lists for consistency.
**Verbosity**
- Final answer compactness rules (enforced):
- Tiny/small single-file change (≤ ~10 lines): 25 sentences or ≤3 bullets. No headings. 01 short snippet (≤3 lines) only if essential.
- Medium change (single area or a few files): ≤6 bullets or 610 sentences. At most 12 short snippets total (≤8 lines each).
- Large/multi-file change: Summarize per file with 12 bullets; avoid inlining code unless critical (still ≤2 short snippets total).
- Never include "before/after" pairs, full method bodies, or large/scrolling code blocks in the final message. Prefer referencing file/symbol names instead.
**Dont**
- Dont use literal words “bold” or “monospace” in the content.
- Dont nest bullets or create deep hierarchies.
- Dont output ANSI escape codes directly — the CLI renderer applies them.
- Dont cram unrelated keywords into a single bullet; split for clarity.
- Dont let keyword lists run long — wrap or reformat for scanability.
Generally, ensure your final answers adapt their shape and depth to the request. For example, answers to code explanations should have a precise, structured explanation with code references that answer the question directly. For tasks with a simple implementation, lead with the outcome and supplement only with whats needed for clarity. Larger changes can be presented as a logical walkthrough of your approach, grouping related steps, explaining rationale where it adds value, and highlighting next actions to accelerate the user. Your answers should provide the right level of detail while being easily scannable.
For casual greetings, acknowledgements, or other one-off conversational messages that are not delivering substantive information or structured results, respond naturally without section headers or bullet formatting.
# Tool Guidelines
## Shell commands
When using the shell, you must adhere to the following guidelines:
- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
- Read files in chunks with a max chunk size of 250 lines. Do not use python scripts to attempt to output larger chunks of a file. Command line output will be truncated after 10 kilobytes or 256 lines of output, regardless of the command used.
## apply_patch
Use the `apply_patch` tool to edit files. Your patch language is a strippeddown, fileoriented diff format designed to be easy to parse and safe to apply. You can think of it as a highlevel envelope:
*** Begin Patch
[ one or more file sections ]
*** End Patch
Within that envelope, you get a sequence of file operations.
You MUST include a header to specify the action you are taking.
Each operation starts with one of three headers:
*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
*** Delete File: <path> - remove an existing file. Nothing follows.
*** Update File: <path> - patch an existing file in place (optionally with a rename).
Example patch:
```
*** Begin Patch
*** Add File: hello.txt
+Hello world
*** Update File: src/app.py
*** Move to: src/main.py
@@ def greet():
-print("Hi")
+print("Hello, world!")
*** Delete File: obsolete.txt
*** End Patch
```
It is important to remember:
- You must include a header with your intended action (Add/Delete/Update)
- You must prefix new lines with `+` even when creating a new file
## `update_plan`
A tool named `update_plan` is available to you. You can use it to keep an uptodate, stepbystep plan for the task.
To create a new plan, call `update_plan` with a short list of 1sentence steps (no more than 5-7 words each) with a `status` for each step (`pending`, `in_progress`, or `completed`).
When steps have been completed, use `update_plan` to mark each finished step as `completed` and the next step you are working on as `in_progress`. There should always be exactly one `in_progress` step until everything is done. You can mark multiple items as complete in a single `update_plan` call.
If all steps are complete, ensure you call `update_plan` to mark all steps as `completed`.

View File

@@ -2,6 +2,8 @@ You are Codex, based on GPT-5. You are running as a coding agent in the Codex CL
## General
- The arguments to `shell` will be passed to execvp(). Most terminal commands should be prefixed with ["bash", "-lc"].
- Always set the `workdir` param when using the shell function. Do not use `cd` unless absolutely necessary.
- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
## Editing constraints
@@ -14,7 +16,6 @@ You are Codex, based on GPT-5. You are running as a coding agent in the Codex CL
* If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, don't revert those changes.
* If the changes are in files you've touched recently, you should read carefully and understand how you can work with the changes rather than reverting them.
* If the changes are in unrelated files, just ignore them and don't revert them.
- Do not amend a commit unless explicitly requested to do so.
- While you are working, you might notice unexpected changes that you didn't make. If this happens, STOP IMMEDIATELY and ask the user how they would like to proceed.
- **NEVER** use destructive commands like `git reset --hard` or `git checkout --` unless specifically requested or approved by the user.

View File

@@ -1,14 +1,12 @@
mod storage;
use chrono::Utc;
use reqwest::StatusCode;
use serde::Deserialize;
use serde::Serialize;
#[cfg(test)]
use serial_test::serial;
use std::env;
use std::fmt::Debug;
use std::io::ErrorKind;
use std::path::Path;
use std::path::PathBuf;
use std::sync::Arc;
@@ -24,16 +22,10 @@ use crate::auth::storage::AuthStorageBackend;
use crate::auth::storage::create_auth_storage;
use crate::config::Config;
use crate::default_client::CodexHttpClient;
use crate::error::RefreshTokenFailedError;
use crate::error::RefreshTokenFailedReason;
use crate::token_data::KnownPlan as InternalKnownPlan;
use crate::token_data::PlanType as InternalPlanType;
use crate::token_data::PlanType;
use crate::token_data::TokenData;
use crate::token_data::parse_id_token;
use crate::util::try_parse_error_message;
use codex_protocol::account::PlanType as AccountPlanType;
use serde_json::Value;
use thiserror::Error;
#[derive(Debug, Clone)]
pub struct CodexAuth {
@@ -54,54 +46,18 @@ impl PartialEq for CodexAuth {
// TODO(pakrym): use token exp field to check for expiration instead
const TOKEN_REFRESH_INTERVAL: i64 = 8;
const REFRESH_TOKEN_EXPIRED_MESSAGE: &str = "Your access token could not be refreshed because your refresh token has expired. Please log out and sign in again.";
const REFRESH_TOKEN_REUSED_MESSAGE: &str = "Your access token could not be refreshed because your refresh token was already used. Please log out and sign in again.";
const REFRESH_TOKEN_INVALIDATED_MESSAGE: &str = "Your access token could not be refreshed because your refresh token was revoked. Please log out and sign in again.";
const REFRESH_TOKEN_UNKNOWN_MESSAGE: &str =
"Your access token could not be refreshed. Please log out and sign in again.";
const REFRESH_TOKEN_URL: &str = "https://auth.openai.com/oauth/token";
pub const REFRESH_TOKEN_URL_OVERRIDE_ENV_VAR: &str = "CODEX_REFRESH_TOKEN_URL_OVERRIDE";
#[derive(Debug, Error)]
pub enum RefreshTokenError {
#[error("{0}")]
Permanent(#[from] RefreshTokenFailedError),
#[error(transparent)]
Transient(#[from] std::io::Error),
}
impl RefreshTokenError {
pub fn failed_reason(&self) -> Option<RefreshTokenFailedReason> {
match self {
Self::Permanent(error) => Some(error.reason),
Self::Transient(_) => None,
}
}
fn other_with_message(message: impl Into<String>) -> Self {
Self::Transient(std::io::Error::other(message.into()))
}
}
impl From<RefreshTokenError> for std::io::Error {
fn from(err: RefreshTokenError) -> Self {
match err {
RefreshTokenError::Permanent(failed) => std::io::Error::other(failed),
RefreshTokenError::Transient(inner) => inner,
}
}
}
impl CodexAuth {
pub async fn refresh_token(&self) -> Result<String, RefreshTokenError> {
pub async fn refresh_token(&self) -> Result<String, std::io::Error> {
tracing::info!("Refreshing token");
let token_data = self.get_current_token_data().ok_or_else(|| {
RefreshTokenError::Transient(std::io::Error::other("Token data is not available."))
})?;
let token_data = self
.get_current_token_data()
.ok_or(std::io::Error::other("Token data is not available."))?;
let token = token_data.refresh_token;
let refresh_response = try_refresh_token(token, &self.client).await?;
let refresh_response = try_refresh_token(token, &self.client)
.await
.map_err(std::io::Error::other)?;
let updated = update_tokens(
&self.storage,
@@ -109,8 +65,7 @@ impl CodexAuth {
refresh_response.access_token,
refresh_response.refresh_token,
)
.await
.map_err(RefreshTokenError::from)?;
.await?;
if let Ok(mut auth_lock) = self.auth_dot_json.lock() {
*auth_lock = Some(updated.clone());
@@ -119,7 +74,7 @@ impl CodexAuth {
let access = match updated.tokens {
Some(t) => t.access_token,
None => {
return Err(RefreshTokenError::other_with_message(
return Err(std::io::Error::other(
"Token data is not available after refresh.",
));
}
@@ -144,21 +99,15 @@ impl CodexAuth {
..
}) => {
if last_refresh < Utc::now() - chrono::Duration::days(TOKEN_REFRESH_INTERVAL) {
let refresh_result = tokio::time::timeout(
let refresh_response = tokio::time::timeout(
Duration::from_secs(60),
try_refresh_token(tokens.refresh_token.clone(), &self.client),
)
.await;
let refresh_response = match refresh_result {
Ok(Ok(response)) => response,
Ok(Err(err)) => return Err(err.into()),
Err(_) => {
return Err(std::io::Error::new(
ErrorKind::TimedOut,
"timed out while refreshing OpenAI API key",
));
}
};
.await
.map_err(|_| {
std::io::Error::other("timed out while refreshing OpenAI API key")
})?
.map_err(std::io::Error::other)?;
let updated_auth_dot_json = update_tokens(
&self.storage,
@@ -204,42 +153,7 @@ impl CodexAuth {
self.get_current_token_data().and_then(|t| t.id_token.email)
}
/// Account-facing plan classification derived from the current token.
/// Returns a high-level `AccountPlanType` (e.g., Free/Plus/Pro/Team/…)
/// mapped from the ID token's internal plan value. Prefer this when you
/// need to make UI or product decisions based on the user's subscription.
pub fn account_plan_type(&self) -> Option<AccountPlanType> {
let map_known = |kp: &InternalKnownPlan| match kp {
InternalKnownPlan::Free => AccountPlanType::Free,
InternalKnownPlan::Plus => AccountPlanType::Plus,
InternalKnownPlan::Pro => AccountPlanType::Pro,
InternalKnownPlan::Team => AccountPlanType::Team,
InternalKnownPlan::Business => AccountPlanType::Business,
InternalKnownPlan::Enterprise => AccountPlanType::Enterprise,
InternalKnownPlan::Edu => AccountPlanType::Edu,
};
self.get_current_token_data()
.and_then(|t| t.id_token.chatgpt_plan_type)
.map(|pt| match pt {
InternalPlanType::Known(k) => map_known(&k),
InternalPlanType::Unknown(_) => AccountPlanType::Unknown,
})
}
/// Raw plan string from the ID token (including unknown/new plan types).
pub fn raw_plan_type(&self) -> Option<String> {
self.get_plan_type().map(|plan| match plan {
InternalPlanType::Known(k) => format!("{k:?}"),
InternalPlanType::Unknown(raw) => raw,
})
}
/// Raw internal plan value from the ID token.
/// Exposes the underlying `token_data::PlanType` without mapping it to the
/// public `AccountPlanType`. Use this when downstream code needs to inspect
/// internal/unknown plan strings exactly as issued in the token.
pub(crate) fn get_plan_type(&self) -> Option<InternalPlanType> {
pub(crate) fn get_plan_type(&self) -> Option<PlanType> {
self.get_current_token_data()
.and_then(|t| t.id_token.chatgpt_plan_type)
}
@@ -343,10 +257,7 @@ pub fn save_auth(
}
/// Load CLI auth data using the configured credential store backend.
/// Returns `None` when no credentials are stored. This function is
/// provided only for tests. Production code should not directly load
/// from the auth.json storage. It should use the AuthManager abstraction
/// instead.
/// Returns `None` when no credentials are stored.
pub fn load_auth_dot_json(
codex_home: &Path,
auth_credentials_store_mode: AuthCredentialsStoreMode,
@@ -514,7 +425,7 @@ async fn update_tokens(
async fn try_refresh_token(
refresh_token: String,
client: &CodexHttpClient,
) -> Result<RefreshResponse, RefreshTokenError> {
) -> std::io::Result<RefreshResponse> {
let refresh_request = RefreshRequest {
client_id: CLIENT_ID,
grant_type: "refresh_token",
@@ -522,93 +433,30 @@ async fn try_refresh_token(
scope: "openid profile email",
};
let endpoint = refresh_token_endpoint();
// Use shared client factory to include standard headers
let response = client
.post(endpoint.as_str())
.post("https://auth.openai.com/oauth/token")
.header("Content-Type", "application/json")
.json(&refresh_request)
.send()
.await
.map_err(|err| RefreshTokenError::Transient(std::io::Error::other(err)))?;
.map_err(std::io::Error::other)?;
let status = response.status();
if status.is_success() {
if response.status().is_success() {
let refresh_response = response
.json::<RefreshResponse>()
.await
.map_err(|err| RefreshTokenError::Transient(std::io::Error::other(err)))?;
.map_err(std::io::Error::other)?;
Ok(refresh_response)
} else {
let body = response.text().await.unwrap_or_default();
if status == StatusCode::UNAUTHORIZED {
let failed = classify_refresh_token_failure(&body);
Err(RefreshTokenError::Permanent(failed))
} else {
let message = try_parse_error_message(&body);
Err(RefreshTokenError::Transient(std::io::Error::other(
format!("Failed to refresh token: {status}: {message}"),
)))
}
Err(std::io::Error::other(format!(
"Failed to refresh token: {}: {}",
response.status(),
try_parse_error_message(&response.text().await.unwrap_or_default()),
)))
}
}
fn classify_refresh_token_failure(body: &str) -> RefreshTokenFailedError {
let code = extract_refresh_token_error_code(body);
let normalized_code = code.as_deref().map(str::to_ascii_lowercase);
let reason = match normalized_code.as_deref() {
Some("refresh_token_expired") => RefreshTokenFailedReason::Expired,
Some("refresh_token_reused") => RefreshTokenFailedReason::Exhausted,
Some("refresh_token_invalidated") => RefreshTokenFailedReason::Revoked,
_ => RefreshTokenFailedReason::Other,
};
if reason == RefreshTokenFailedReason::Other {
tracing::warn!(
backend_code = normalized_code.as_deref(),
backend_body = body,
"Encountered unknown 401 response while refreshing token"
);
}
let message = match reason {
RefreshTokenFailedReason::Expired => REFRESH_TOKEN_EXPIRED_MESSAGE.to_string(),
RefreshTokenFailedReason::Exhausted => REFRESH_TOKEN_REUSED_MESSAGE.to_string(),
RefreshTokenFailedReason::Revoked => REFRESH_TOKEN_INVALIDATED_MESSAGE.to_string(),
RefreshTokenFailedReason::Other => REFRESH_TOKEN_UNKNOWN_MESSAGE.to_string(),
};
RefreshTokenFailedError::new(reason, message)
}
fn extract_refresh_token_error_code(body: &str) -> Option<String> {
if body.trim().is_empty() {
return None;
}
let Value::Object(map) = serde_json::from_str::<Value>(body).ok()? else {
return None;
};
if let Some(error_value) = map.get("error") {
match error_value {
Value::Object(obj) => {
if let Some(code) = obj.get("code").and_then(Value::as_str) {
return Some(code.to_string());
}
}
Value::String(code) => {
return Some(code.to_string());
}
_ => {}
}
}
map.get("code").and_then(Value::as_str).map(str::to_string)
}
#[derive(Serialize)]
struct RefreshRequest {
client_id: &'static str,
@@ -627,11 +475,6 @@ struct RefreshResponse {
// Shared constant for token refresh (client id used for oauth token refresh flow)
pub const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
fn refresh_token_endpoint() -> String {
std::env::var(REFRESH_TOKEN_URL_OVERRIDE_ENV_VAR)
.unwrap_or_else(|_| REFRESH_TOKEN_URL.to_string())
}
use std::sync::RwLock;
/// Internal cached auth state.
@@ -649,9 +492,8 @@ mod tests {
use crate::config::ConfigOverrides;
use crate::config::ConfigToml;
use crate::token_data::IdTokenInfo;
use crate::token_data::KnownPlan as InternalKnownPlan;
use crate::token_data::PlanType as InternalPlanType;
use codex_protocol::account::PlanType as AccountPlanType;
use crate::token_data::KnownPlan;
use crate::token_data::PlanType;
use base64::Engine;
use codex_protocol::config_types::ForcedLoginMethod;
@@ -768,7 +610,7 @@ mod tests {
tokens: Some(TokenData {
id_token: IdTokenInfo {
email: Some("user@example.com".to_string()),
chatgpt_plan_type: Some(InternalPlanType::Known(InternalKnownPlan::Pro)),
chatgpt_plan_type: Some(PlanType::Known(KnownPlan::Pro)),
chatgpt_account_id: None,
raw_jwt: fake_jwt,
},
@@ -1022,54 +864,6 @@ mod tests {
.contains("ChatGPT login is required, but an API key is currently being used.")
);
}
#[test]
fn plan_type_maps_known_plan() {
let codex_home = tempdir().unwrap();
let _jwt = write_auth_file(
AuthFileParams {
openai_api_key: None,
chatgpt_plan_type: "pro".to_string(),
chatgpt_account_id: None,
},
codex_home.path(),
)
.expect("failed to write auth file");
let auth = super::load_auth(codex_home.path(), false, AuthCredentialsStoreMode::File)
.expect("load auth")
.expect("auth available");
pretty_assertions::assert_eq!(auth.account_plan_type(), Some(AccountPlanType::Pro));
pretty_assertions::assert_eq!(
auth.get_plan_type(),
Some(InternalPlanType::Known(InternalKnownPlan::Pro))
);
}
#[test]
fn plan_type_maps_unknown_to_unknown() {
let codex_home = tempdir().unwrap();
let _jwt = write_auth_file(
AuthFileParams {
openai_api_key: None,
chatgpt_plan_type: "mystery-tier".to_string(),
chatgpt_account_id: None,
},
codex_home.path(),
)
.expect("failed to write auth file");
let auth = super::load_auth(codex_home.path(), false, AuthCredentialsStoreMode::File)
.expect("load auth")
.expect("auth available");
pretty_assertions::assert_eq!(auth.account_plan_type(), Some(AccountPlanType::Unknown));
pretty_assertions::assert_eq!(
auth.get_plan_type(),
Some(InternalPlanType::Unknown("mystery-tier".to_string()))
);
}
}
/// Central manager providing a single source of truth for auth.json derived
@@ -1171,9 +965,7 @@ impl AuthManager {
/// Attempt to refresh the current auth token (if any). On success, reload
/// the auth state from disk so other components observe refreshed token.
/// If the token refresh fails in a permanent (nontransient) way, logs out
/// to clear invalid auth state.
pub async fn refresh_token(&self) -> Result<Option<String>, RefreshTokenError> {
pub async fn refresh_token(&self) -> std::io::Result<Option<String>> {
let auth = match self.auth() {
Some(a) => a,
None => return Ok(None),

View File

@@ -1,13 +1,8 @@
use std::path::PathBuf;
use tree_sitter::Node;
use tree_sitter::Parser;
use tree_sitter::Tree;
use tree_sitter_bash::LANGUAGE as BASH;
use crate::shell::ShellType;
use crate::shell::detect_shell_type;
/// Parse the provided bash source using tree-sitter-bash, returning a Tree on
/// success or None if parsing failed.
pub fn try_parse_shell(shell_lc_arg: &str) -> Option<Tree> {
@@ -93,26 +88,17 @@ pub fn try_parse_word_only_commands_sequence(tree: &Tree, src: &str) -> Option<V
Some(commands)
}
pub fn extract_bash_command(command: &[String]) -> Option<(&str, &str)> {
let [shell, flag, script] = command else {
return None;
};
if !matches!(flag.as_str(), "-lc" | "-c")
|| !matches!(
detect_shell_type(&PathBuf::from(shell)),
Some(ShellType::Zsh) | Some(ShellType::Bash) | Some(ShellType::Sh)
)
{
return None;
}
Some((shell, script))
}
/// Returns the sequence of plain commands within a `bash -lc "..."` or
/// `zsh -lc "..."` invocation when the script only contains word-only commands
/// joined by safe operators.
pub fn parse_shell_lc_plain_commands(command: &[String]) -> Option<Vec<Vec<String>>> {
let (_, script) = extract_bash_command(command)?;
let [shell, flag, script] = command else {
return None;
};
if flag != "-lc" || !(shell == "bash" || shell == "zsh") {
return None;
}
let tree = try_parse_shell(script)?;
try_parse_word_only_commands_sequence(&tree, script)

View File

@@ -81,7 +81,6 @@ pub(crate) async fn stream_chat_completions(
ResponseItem::CustomToolCallOutput { .. } => {}
ResponseItem::WebSearchCall { .. } => {}
ResponseItem::GhostSnapshot { .. } => {}
ResponseItem::CompactionSummary { .. } => {}
}
}
@@ -321,8 +320,7 @@ pub(crate) async fn stream_chat_completions(
}
ResponseItem::Reasoning { .. }
| ResponseItem::WebSearchCall { .. }
| ResponseItem::Other
| ResponseItem::CompactionSummary { .. } => {
| ResponseItem::Other => {
// Omit these items from the conversation history.
continue;
}
@@ -340,7 +338,7 @@ pub(crate) async fn stream_chat_completions(
debug!(
"POST to {}: {}",
provider.get_full_url(&None),
payload.to_string()
serde_json::to_string_pretty(&payload).unwrap_or_default()
);
let mut attempt = 0;
@@ -479,14 +477,10 @@ async fn append_reasoning_text(
..
}) = reasoning_item
{
let content_index = content.len() as i64;
content.push(ReasoningItemContent::ReasoningText { text: text.clone() });
let _ = tx_event
.send(Ok(ResponseEvent::ReasoningContentDelta {
delta: text.clone(),
content_index,
}))
.send(Ok(ResponseEvent::ReasoningContentDelta(text.clone())))
.await;
}
}
@@ -675,9 +669,7 @@ async fn process_chat_sse<S>(
}
// Emit end-of-turn when finish_reason signals completion.
if let Some(finish_reason) = choice.get("finish_reason").and_then(|v| v.as_str())
&& !finish_reason.is_empty()
{
if let Some(finish_reason) = choice.get("finish_reason").and_then(|v| v.as_str()) {
match finish_reason {
"tool_calls" if fn_call_state.active => {
// First, flush the terminal raw reasoning so UIs can finalize
@@ -906,26 +898,20 @@ where
continue;
}
}
Poll::Ready(Some(Ok(ResponseEvent::ReasoningContentDelta {
delta,
content_index,
}))) => {
Poll::Ready(Some(Ok(ResponseEvent::ReasoningContentDelta(delta)))) => {
// Always accumulate reasoning deltas so we can emit a final Reasoning item at Completed.
this.cumulative_reasoning.push_str(&delta);
if matches!(this.mode, AggregateMode::Streaming) {
// In streaming mode, also forward the delta immediately.
return Poll::Ready(Some(Ok(ResponseEvent::ReasoningContentDelta {
delta,
content_index,
})));
return Poll::Ready(Some(Ok(ResponseEvent::ReasoningContentDelta(delta))));
} else {
continue;
}
}
Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryDelta { .. }))) => {
Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryDelta(_)))) => {
continue;
}
Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryPartAdded { .. }))) => {
Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryPartAdded))) => {
continue;
}
Poll::Ready(Some(Ok(ResponseEvent::OutputItemAdded(item)))) => {

View File

@@ -26,20 +26,18 @@ use tokio::sync::mpsc;
use tokio::time::timeout;
use tokio_util::io::ReaderStream;
use tracing::debug;
use tracing::enabled;
use tracing::trace;
use tracing::warn;
use crate::AuthManager;
use crate::auth::CodexAuth;
use crate::auth::RefreshTokenError;
use crate::chat_completions::AggregateStreamExt;
use crate::chat_completions::stream_chat_completions;
use crate::client_common::Prompt;
use crate::client_common::Reasoning;
use crate::client_common::ResponseEvent;
use crate::client_common::ResponseStream;
use crate::client_common::ResponsesApiRequest;
use crate::client_common::create_reasoning_param_for_request;
use crate::client_common::create_text_param_for_request;
use crate::config::Config;
use crate::default_client::CodexHttpClient;
@@ -56,7 +54,6 @@ use crate::model_family::ModelFamily;
use crate::model_provider_info::ModelProviderInfo;
use crate::model_provider_info::WireApi;
use crate::openai_model_info::get_model_info;
use crate::protocol::CreditsSnapshot;
use crate::protocol::RateLimitSnapshot;
use crate::protocol::RateLimitWindow;
use crate::protocol::TokenUsage;
@@ -80,18 +77,6 @@ struct Error {
resets_at: Option<i64>,
}
#[derive(Debug, Serialize)]
struct CompactHistoryRequest<'a> {
model: &'a str,
input: &'a [ResponseItem],
instructions: &'a str,
}
#[derive(Debug, Deserialize)]
struct CompactHistoryResponse {
output: Vec<ResponseItem>,
}
#[derive(Debug, Clone)]
pub struct ModelClient {
config: Arc<Config>,
@@ -213,18 +198,12 @@ impl ModelClient {
let auth_manager = self.auth_manager.clone();
let full_instructions = prompt.get_full_instructions(&self.config.model_family);
let tools_json: Vec<Value> = create_tools_json_for_responses_api(&prompt.tools)?;
let reasoning = if self.config.model_family.supports_reasoning_summaries {
Some(Reasoning {
effort: self
.effort
.or(self.config.model_family.default_reasoning_effort),
summary: Some(self.summary),
})
} else {
None
};
let tools_json = create_tools_json_for_responses_api(&prompt.tools)?;
let reasoning = create_reasoning_param_for_request(
&self.config.model_family,
self.effort,
self.summary,
);
let include: Vec<String> = if reasoning.is_some() {
vec!["reasoning.encrypted_content".to_string()]
@@ -235,9 +214,7 @@ impl ModelClient {
let input_with_instructions = prompt.get_formatted_input();
let verbosity = if self.config.model_family.support_verbosity {
self.config
.model_verbosity
.or(self.config.model_family.default_verbosity)
self.config.model_verbosity
} else {
if self.config.model_verbosity.is_some() {
warn!(
@@ -316,9 +293,10 @@ impl ModelClient {
let auth = auth_manager.as_ref().and_then(|m| m.auth());
trace!(
"POST to {}: {}",
"POST to {}: {:?}",
self.provider.get_full_url(&auth),
payload_json.to_string()
serde_json::to_string(payload_json)
.unwrap_or("<unable to serialize payload>".to_string())
);
let mut req_builder = self
@@ -411,17 +389,12 @@ impl ModelClient {
&& let Some(manager) = auth_manager.as_ref()
&& let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Err(err) = manager.refresh_token().await
{
let stream_error = match err {
RefreshTokenError::Permanent(failed) => {
StreamAttemptError::Fatal(CodexErr::RefreshTokenFailed(failed))
}
RefreshTokenError::Transient(other) => {
StreamAttemptError::RetryableTransportError(CodexErr::Io(other))
}
};
return Err(stream_error);
manager.refresh_token().await.map_err(|err| {
StreamAttemptError::Fatal(CodexErr::Fatal(format!(
"Failed to refresh ChatGPT credentials: {err}"
)))
})?;
}
// The OpenAI Responses endpoint returns structured JSON bodies even for 4xx/5xx
@@ -468,8 +441,6 @@ impl ModelClient {
return Err(StreamAttemptError::Fatal(codex_err));
} else if error.r#type.as_deref() == Some("usage_not_included") {
return Err(StreamAttemptError::Fatal(CodexErr::UsageNotIncluded));
} else if is_quota_exceeded_error(&error) {
return Err(StreamAttemptError::Fatal(CodexErr::QuotaExceeded));
}
}
}
@@ -521,70 +492,6 @@ impl ModelClient {
pub fn get_auth_manager(&self) -> Option<Arc<AuthManager>> {
self.auth_manager.clone()
}
pub async fn compact_conversation_history(&self, prompt: &Prompt) -> Result<Vec<ResponseItem>> {
if prompt.input.is_empty() {
return Ok(Vec::new());
}
let auth_manager = self.auth_manager.clone();
let auth = auth_manager.as_ref().and_then(|m| m.auth());
let mut req_builder = self
.provider
.create_compact_request_builder(&self.client, &auth)
.await?;
if let SessionSource::SubAgent(sub) = &self.session_source {
let subagent = if let crate::protocol::SubAgentSource::Other(label) = sub {
label.clone()
} else {
serde_json::to_value(sub)
.ok()
.and_then(|v| v.as_str().map(std::string::ToString::to_string))
.unwrap_or_else(|| "other".to_string())
};
req_builder = req_builder.header("x-openai-subagent", subagent);
}
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
&& let Some(account_id) = auth.get_account_id()
{
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
let payload = CompactHistoryRequest {
model: &self.config.model,
input: &prompt.input,
instructions: &prompt.get_full_instructions(&self.config.model_family),
};
if enabled!(tracing::Level::TRACE) {
trace!(
"POST to {}: {}",
self.provider
.get_compact_url(&auth)
.unwrap_or("<none>".to_string()),
serde_json::to_value(&payload).unwrap_or_default()
);
}
let response = req_builder
.json(&payload)
.send()
.await
.map_err(|source| CodexErr::ConnectionFailed(ConnectionFailedError { source }))?;
let status = response.status();
let body = response
.text()
.await
.map_err(|source| CodexErr::ConnectionFailed(ConnectionFailedError { source }))?;
if !status.is_success() {
return Err(CodexErr::UnexpectedStatus(UnexpectedResponseError {
status,
body,
request_id: None,
}));
}
let CompactHistoryResponse { output } = serde_json::from_str(&body)?;
Ok(output)
}
}
enum StreamAttemptError {
@@ -638,8 +545,6 @@ struct SseEvent {
response: Option<Value>,
item: Option<Value>,
delta: Option<String>,
summary_index: Option<i64>,
content_index: Option<i64>,
}
#[derive(Debug, Deserialize)]
@@ -727,13 +632,7 @@ fn parse_rate_limit_snapshot(headers: &HeaderMap) -> Option<RateLimitSnapshot> {
"x-codex-secondary-reset-at",
);
let credits = parse_credits_snapshot(headers);
Some(RateLimitSnapshot {
primary,
secondary,
credits,
})
Some(RateLimitSnapshot { primary, secondary })
}
fn parse_rate_limit_window(
@@ -760,20 +659,6 @@ fn parse_rate_limit_window(
})
}
fn parse_credits_snapshot(headers: &HeaderMap) -> Option<CreditsSnapshot> {
let has_credits = parse_header_bool(headers, "x-codex-credits-has-credits")?;
let unlimited = parse_header_bool(headers, "x-codex-credits-unlimited")?;
let balance = parse_header_str(headers, "x-codex-credits-balance")
.map(str::trim)
.filter(|value| !value.is_empty())
.map(std::string::ToString::to_string);
Some(CreditsSnapshot {
has_credits,
unlimited,
balance,
})
}
fn parse_header_f64(headers: &HeaderMap, name: &str) -> Option<f64> {
parse_header_str(headers, name)?
.parse::<f64>()
@@ -785,17 +670,6 @@ fn parse_header_i64(headers: &HeaderMap, name: &str) -> Option<i64> {
parse_header_str(headers, name)?.parse::<i64>().ok()
}
fn parse_header_bool(headers: &HeaderMap, name: &str) -> Option<bool> {
let raw = parse_header_str(headers, name)?;
if raw.eq_ignore_ascii_case("true") || raw == "1" {
Some(true)
} else if raw.eq_ignore_ascii_case("false") || raw == "0" {
Some(false)
} else {
None
}
}
fn parse_header_str<'a>(headers: &'a HeaderMap, name: &str) -> Option<&'a str> {
headers.get(name)?.to_str().ok()
}
@@ -930,22 +804,16 @@ async fn process_sse<S>(
}
}
"response.reasoning_summary_text.delta" => {
if let (Some(delta), Some(summary_index)) = (event.delta, event.summary_index) {
let event = ResponseEvent::ReasoningSummaryDelta {
delta,
summary_index,
};
if let Some(delta) = event.delta {
let event = ResponseEvent::ReasoningSummaryDelta(delta);
if tx_event.send(Ok(event)).await.is_err() {
return;
}
}
}
"response.reasoning_text.delta" => {
if let (Some(delta), Some(content_index)) = (event.delta, event.content_index) {
let event = ResponseEvent::ReasoningContentDelta {
delta,
content_index,
};
if let Some(delta) = event.delta {
let event = ResponseEvent::ReasoningContentDelta(delta);
if tx_event.send(Ok(event)).await.is_err() {
return;
}
@@ -970,8 +838,6 @@ async fn process_sse<S>(
Ok(error) => {
if is_context_window_error(&error) {
response_error = Some(CodexErr::ContextWindowExceeded);
} else if is_quota_exceeded_error(&error) {
response_error = Some(CodexErr::QuotaExceeded);
} else {
let delay = try_parse_retry_after(&error);
let message = error.message.clone().unwrap_or_default();
@@ -1022,12 +888,10 @@ async fn process_sse<S>(
}
}
"response.reasoning_summary_part.added" => {
if let Some(summary_index) = event.summary_index {
// Boundary between reasoning summary sections (e.g., titles).
let event = ResponseEvent::ReasoningSummaryPartAdded { summary_index };
if tx_event.send(Ok(event)).await.is_err() {
return;
}
// Boundary between reasoning summary sections (e.g., titles).
let event = ResponseEvent::ReasoningSummaryPartAdded;
if tx_event.send(Ok(event)).await.is_err() {
return;
}
}
"response.reasoning_summary_text.done" => {}
@@ -1067,10 +931,8 @@ async fn stream_from_fixture(
fn rate_limit_regex() -> &'static Regex {
static RE: OnceLock<Regex> = OnceLock::new();
// Match both OpenAI-style messages like "Please try again in 1.898s"
// and Azure OpenAI-style messages like "Try again in 35 seconds".
#[expect(clippy::unwrap_used)]
RE.get_or_init(|| Regex::new(r"(?i)try again in\s*(\d+(?:\.\d+)?)\s*(s|ms|seconds?)").unwrap())
RE.get_or_init(|| Regex::new(r"Please try again in (\d+(?:\.\d+)?)(s|ms)").unwrap())
}
fn try_parse_retry_after(err: &Error) -> Option<Duration> {
@@ -1078,8 +940,7 @@ fn try_parse_retry_after(err: &Error) -> Option<Duration> {
return None;
}
// parse retry hints like "try again in 1.898s" or
// "Try again in 35 seconds" using regex
// parse the Please try again in 1.898s format using regex
let re = rate_limit_regex();
if let Some(message) = &err.message
&& let Some(captures) = re.captures(message)
@@ -1089,9 +950,9 @@ fn try_parse_retry_after(err: &Error) -> Option<Duration> {
if let (Some(value), Some(unit)) = (seconds, unit) {
let value = value.as_str().parse::<f64>().ok()?;
let unit = unit.as_str().to_ascii_lowercase();
let unit = unit.as_str();
if unit == "s" || unit.starts_with("second") {
if unit == "s" {
return Some(Duration::from_secs_f64(value));
} else if unit == "ms" {
return Some(Duration::from_millis(value as u64));
@@ -1105,10 +966,6 @@ fn is_context_window_error(error: &Error) -> bool {
error.code.as_deref() == Some("context_length_exceeded")
}
fn is_quota_exceeded_error(error: &Error) -> bool {
error.code.as_deref() == Some("insufficient_quota")
}
#[cfg(test)]
mod tests {
use super::*;
@@ -1334,7 +1191,7 @@ mod tests {
#[tokio::test]
async fn error_when_error_event() {
let raw_error = r#"{"type":"response.failed","sequence_number":3,"response":{"id":"resp_689bcf18d7f08194bf3440ba62fe05d803fee0cdac429894","object":"response","created_at":1755041560,"status":"failed","background":false,"error":{"code":"rate_limit_exceeded","message":"Rate limit reached for gpt-5.1 in organization org-AAA on tokens per min (TPM): Limit 30000, Used 22999, Requested 12528. Please try again in 11.054s. Visit https://platform.openai.com/account/rate-limits to learn more."}, "usage":null,"user":null,"metadata":{}}}"#;
let raw_error = r#"{"type":"response.failed","sequence_number":3,"response":{"id":"resp_689bcf18d7f08194bf3440ba62fe05d803fee0cdac429894","object":"response","created_at":1755041560,"status":"failed","background":false,"error":{"code":"rate_limit_exceeded","message":"Rate limit reached for gpt-5 in organization org-AAA on tokens per min (TPM): Limit 30000, Used 22999, Requested 12528. Please try again in 11.054s. Visit https://platform.openai.com/account/rate-limits to learn more."}, "usage":null,"user":null,"metadata":{}}}"#;
let sse1 = format!("event: response.failed\ndata: {raw_error}\n\n");
let provider = ModelProviderInfo {
@@ -1363,7 +1220,7 @@ mod tests {
Err(CodexErr::Stream(msg, delay)) => {
assert_eq!(
msg,
"Rate limit reached for gpt-5.1 in organization org-AAA on tokens per min (TPM): Limit 30000, Used 22999, Requested 12528. Please try again in 11.054s. Visit https://platform.openai.com/account/rate-limits to learn more."
"Rate limit reached for gpt-5 in organization org-AAA on tokens per min (TPM): Limit 30000, Used 22999, Requested 12528. Please try again in 11.054s. Visit https://platform.openai.com/account/rate-limits to learn more."
);
assert_eq!(*delay, Some(Duration::from_secs_f64(11.054)));
}
@@ -1441,41 +1298,6 @@ mod tests {
}
}
#[tokio::test]
async fn quota_exceeded_error_is_fatal() {
let raw_error = r#"{"type":"response.failed","sequence_number":3,"response":{"id":"resp_fatal_quota","object":"response","created_at":1759771626,"status":"failed","background":false,"error":{"code":"insufficient_quota","message":"You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors."},"incomplete_details":null}}"#;
let sse1 = format!("event: response.failed\ndata: {raw_error}\n\n");
let provider = ModelProviderInfo {
name: "test".to_string(),
base_url: Some("https://test.com".to_string()),
env_key: Some("TEST_API_KEY".to_string()),
env_key_instructions: None,
experimental_bearer_token: None,
wire_api: WireApi::Responses,
query_params: None,
http_headers: None,
env_http_headers: None,
request_max_retries: Some(0),
stream_max_retries: Some(0),
stream_idle_timeout_ms: Some(1000),
requires_openai_auth: false,
};
let otel_event_manager = otel_event_manager();
let events = collect_events(&[sse1.as_bytes()], provider, otel_event_manager).await;
assert_eq!(events.len(), 1);
match &events[0] {
Err(err @ CodexErr::QuotaExceeded) => {
assert_eq!(err.to_string(), CodexErr::QuotaExceeded.to_string());
}
other => panic!("unexpected quota exceeded event: {other:?}"),
}
}
// ────────────────────────────
// Table-driven test from `main`
// ────────────────────────────
@@ -1582,7 +1404,7 @@ mod tests {
fn test_try_parse_retry_after() {
let err = Error {
r#type: None,
message: Some("Rate limit reached for gpt-5.1 in organization org- on tokens per min (TPM): Limit 1, Used 1, Requested 19304. Please try again in 28ms. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
message: Some("Rate limit reached for gpt-5 in organization org- on tokens per min (TPM): Limit 1, Used 1, Requested 19304. Please try again in 28ms. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
plan_type: None,
resets_at: None
@@ -1596,7 +1418,7 @@ mod tests {
fn test_try_parse_retry_after_no_delay() {
let err = Error {
r#type: None,
message: Some("Rate limit reached for gpt-5.1 in organization <ORG> on tokens per min (TPM): Limit 30000, Used 6899, Requested 24050. Please try again in 1.898s. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
message: Some("Rate limit reached for gpt-5 in organization <ORG> on tokens per min (TPM): Limit 30000, Used 6899, Requested 24050. Please try again in 1.898s. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
plan_type: None,
resets_at: None
@@ -1605,19 +1427,6 @@ mod tests {
assert_eq!(delay, Some(Duration::from_secs_f64(1.898)));
}
#[test]
fn test_try_parse_retry_after_azure() {
let err = Error {
r#type: None,
message: Some("Rate limit exceeded. Try again in 35 seconds.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
plan_type: None,
resets_at: None,
};
let delay = try_parse_retry_after(&err);
assert_eq!(delay, Some(Duration::from_secs(35)));
}
#[test]
fn error_response_deserializes_schema_known_plan_type_and_serializes_back() {
use crate::token_data::KnownPlan;

View File

@@ -165,9 +165,11 @@ fn build_structured_output(parsed: &ExecOutputJson) -> String {
));
let mut output = parsed.output.clone();
if let Some((stripped, total_lines)) = strip_total_output_header(&parsed.output) {
if let Some(total_lines) = extract_total_output_lines(&parsed.output) {
sections.push(format!("Total output lines: {total_lines}"));
output = stripped.to_string();
if let Some(stripped) = strip_total_output_header(&output) {
output = stripped.to_string();
}
}
sections.push("Output:".to_string());
@@ -176,12 +178,19 @@ fn build_structured_output(parsed: &ExecOutputJson) -> String {
sections.join("\n")
}
fn strip_total_output_header(output: &str) -> Option<(&str, u32)> {
fn extract_total_output_lines(output: &str) -> Option<u32> {
let marker_start = output.find("[... omitted ")?;
let marker = &output[marker_start..];
let (_, after_of) = marker.split_once(" of ")?;
let (total_segment, _) = after_of.split_once(' ')?;
total_segment.parse::<u32>().ok()
}
fn strip_total_output_header(output: &str) -> Option<&str> {
let after_prefix = output.strip_prefix("Total output lines: ")?;
let (total_segment, remainder) = after_prefix.split_once('\n')?;
let total_lines = total_segment.parse::<u32>().ok()?;
let (_, remainder) = after_prefix.split_once('\n')?;
let remainder = remainder.strip_prefix('\n').unwrap_or(remainder);
Some((remainder, total_lines))
Some(remainder)
}
#[derive(Debug)]
@@ -194,17 +203,9 @@ pub enum ResponseEvent {
token_usage: Option<TokenUsage>,
},
OutputTextDelta(String),
ReasoningSummaryDelta {
delta: String,
summary_index: i64,
},
ReasoningContentDelta {
delta: String,
content_index: i64,
},
ReasoningSummaryPartAdded {
summary_index: i64,
},
ReasoningSummaryDelta(String),
ReasoningContentDelta(String),
ReasoningSummaryPartAdded,
RateLimits(RateLimitSnapshot),
}
@@ -341,6 +342,21 @@ pub(crate) mod tools {
}
}
pub(crate) fn create_reasoning_param_for_request(
model_family: &ModelFamily,
effort: Option<ReasoningEffortConfig>,
summary: ReasoningSummaryConfig,
) -> Option<Reasoning> {
if !model_family.supports_reasoning_summaries {
return None;
}
Some(Reasoning {
effort,
summary: Some(summary),
})
}
pub(crate) fn create_text_param_for_request(
verbosity: Option<VerbosityConfig>,
output_schema: &Option<Value>,
@@ -405,10 +421,6 @@ mod tests {
slug: "gpt-5",
expects_apply_patch_instructions: true,
},
InstructionsTestCase {
slug: "gpt-5.1",
expects_apply_patch_instructions: false,
},
InstructionsTestCase {
slug: "codex-mini-latest",
expects_apply_patch_instructions: true,
@@ -418,11 +430,7 @@ mod tests {
expects_apply_patch_instructions: false,
},
InstructionsTestCase {
slug: "gpt-5.1-codex",
expects_apply_patch_instructions: false,
},
InstructionsTestCase {
slug: "gpt-5.1-codex-max",
slug: "gpt-5-codex",
expects_apply_patch_instructions: false,
},
];
@@ -448,7 +456,7 @@ mod tests {
let input: Vec<ResponseItem> = vec![];
let tools: Vec<serde_json::Value> = vec![];
let req = ResponsesApiRequest {
model: "gpt-5.1",
model: "gpt-5",
instructions: "i",
input: &input,
tools: &tools,
@@ -489,7 +497,7 @@ mod tests {
create_text_param_for_request(None, &Some(schema.clone())).expect("text controls");
let req = ResponsesApiRequest {
model: "gpt-5.1",
model: "gpt-5",
instructions: "i",
input: &input,
tools: &tools,
@@ -525,7 +533,7 @@ mod tests {
let input: Vec<ResponseItem> = vec![];
let tools: Vec<serde_json::Value> = vec![];
let req = ResponsesApiRequest {
model: "gpt-5.1",
model: "gpt-5",
instructions: "i",
input: &input,
tools: &tools,

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