chore(core) gpt-5.2-codex personality template (#10373)

## Summary
Consolidate prompts

## Testing
- [x] Existing tests pass

.bazelignore

@@ -0,0 +1,4 @@
+# Without this, Bazel will consider BUILD.bazel files in
+# .git/sl/origbackups (which can be populated by Sapling SCM).
+.git
+codex-rs/target

.bazelrc

@@ -0,0 +1,51 @@
+common --repo_env=BAZEL_DO_NOT_DETECT_CPP_TOOLCHAIN=1
+common --repo_env=BAZEL_NO_APPLE_CPP_TOOLCHAIN=1
+# Dummy xcode config so we don't need to build xcode_locator in repo rule.
+common --xcode_version_config=//:disable_xcode
+
+common --disk_cache=~/.cache/bazel-disk-cache
+common --repo_contents_cache=~/.cache/bazel-repo-contents-cache
+common --repository_cache=~/.cache/bazel-repo-cache
+common --remote_cache_compression
+startup --experimental_remote_repo_contents_cache
+
+common --experimental_platform_in_output_dir
+
+# Runfiles strategy rationale: codex-rs/utils/cargo-bin/README.md
+common --noenable_runfiles
+
+common --enable_platform_specific_config
+# TODO(zbarsky): We need to untangle these libc constraints to get linux remote builds working.
+common:linux --host_platform=//:local
+common --@rules_cc//cc/toolchains/args/archiver_flags:use_libtool_on_macos=False
+common --@toolchains_llvm_bootstrapped//config:experimental_stub_libgcc_s
+
+# We need to use the sh toolchain on windows so we don't send host bash paths to the linux executor.
+common:windows --@rules_rust//rust/settings:experimental_use_sh_toolchain_for_bootstrap_process_wrapper
+
+# TODO(zbarsky): rules_rust doesn't implement this flag properly with remote exec...
+# common --@rules_rust//rust/settings:pipelined_compilation
+
+common --incompatible_strict_action_env
+# Not ideal, but We need to allow dotslash to be found
+common --test_env=PATH=/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin
+
+common --test_output=errors
+common --bes_results_url=https://app.buildbuddy.io/invocation/
+common --bes_backend=grpcs://remote.buildbuddy.io
+common --remote_cache=grpcs://remote.buildbuddy.io
+common --remote_download_toplevel
+common --nobuild_runfile_links
+common --remote_timeout=3600
+common --noexperimental_throttle_remote_action_building
+common --experimental_remote_execution_keepalive
+common --grpc_keepalive_time=30s
+
+# This limits both in-flight executions and concurrent downloads. Even with high number
+# of jobs execution will still be limited by CPU cores, so this just pays a bit of
+# memory in exchange for higher download concurrency.
+common --jobs=30
+
+common:remote --extra_execution_platforms=//:rbe
+common:remote --remote_executor=grpcs://remote.buildbuddy.io
+common:remote --jobs=800

.bazelversion

@@ -0,0 +1 @@
+9.0.0

.codespellrc

@@ -1,6 +1,6 @@
 [codespell]
 # Ref: https://github.com/codespell-project/codespell#using-a-config-file
-skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl,frame*.txt
+skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl,frame*.txt,*.snap,*.snap.new
 check-hidden = true
 ignore-regex = ^\s*"image/\S+": ".*|\b(afterAll)\b
 ignore-words-list = ratatui,ser,iTerm,iterm2,iterm

.github/ISSUE_TEMPLATE/2-bug-report.yml

@@ -40,11 +40,18 @@ body:
       description: |
         For MacOS and Linux: copy the output of `uname -mprs`
         For Windows: copy the output of `"$([Environment]::OSVersion | ForEach-Object VersionString) $(if ([Environment]::Is64BitOperatingSystem) { "x64" } else { "x86" })"` in the PowerShell console
+  - type: input
+    id: terminal
+    attributes:
+      label: What terminal emulator and version are you using (if applicable)?
+      description: Also note any multiplexer in use (screen / tmux / zellij)
+      description: |
+        E.g, VSCode, Terminal.app, iTerm2, Ghostty, Windows Terminal (WSL / PowerShell)
   - type: textarea
     id: actual
     attributes:
       label: What issue are you seeing?
-      description: Please include the full error messages and prompts with PII redacted. If possible, please provide text instead of a screenshot. 
+      description: Please include the full error messages and prompts with PII redacted. If possible, please provide text instead of a screenshot.
     validations:
       required: true
   - type: textarea

.github/codex/labels/codex-rust-review.md

@@ -15,10 +15,10 @@ Things to look out for when doing the review:
 
 ## Code Organization
 
-- Each create in the Cargo workspace in `codex-rs` has a specific purpose: make a note if you believe new code is not introduced in the correct crate.
+- Each crate in the Cargo workspace in `codex-rs` has a specific purpose: make a note if you believe new code is not introduced in the correct crate.
 - When possible, try to keep the `core` crate as small as possible. Non-core but shared logic is often a good candidate for `codex-rs/common`.
 - Be wary of large files and offer suggestions for how to break things into more reasonably-sized files.
-- Rust files should generally be organized such that the public parts of the API appear near the top of the file and helper functions go below. This is analagous to the "inverted pyramid" structure that is favored in journalism.
+- Rust files should generally be organized such that the public parts of the API appear near the top of the file and helper functions go below. This is analogous to the "inverted pyramid" structure that is favored in journalism.
 
 ## Assertions in Tests
 

.github/scripts/install-musl-build-tools.sh

@@ -0,0 +1,163 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+: "${TARGET:?TARGET environment variable is required}"
+: "${GITHUB_ENV:?GITHUB_ENV environment variable is required}"
+
+apt_update_args=()
+if [[ -n "${APT_UPDATE_ARGS:-}" ]]; then
+  # shellcheck disable=SC2206
+  apt_update_args=(${APT_UPDATE_ARGS})
+fi
+
+apt_install_args=()
+if [[ -n "${APT_INSTALL_ARGS:-}" ]]; then
+  # shellcheck disable=SC2206
+  apt_install_args=(${APT_INSTALL_ARGS})
+fi
+
+sudo apt-get update "${apt_update_args[@]}"
+sudo apt-get install -y "${apt_install_args[@]}" musl-tools pkg-config g++ clang libc++-dev libc++abi-dev lld
+
+case "${TARGET}" in
+  x86_64-unknown-linux-musl)
+    arch="x86_64"
+    ;;
+  aarch64-unknown-linux-musl)
+    arch="aarch64"
+    ;;
+  *)
+    echo "Unexpected musl target: ${TARGET}" >&2
+    exit 1
+    ;;
+esac
+
+# Use the musl toolchain as the Rust linker to avoid Zig injecting its own CRT.
+if command -v "${arch}-linux-musl-gcc" >/dev/null; then
+  musl_linker="$(command -v "${arch}-linux-musl-gcc")"
+elif command -v musl-gcc >/dev/null; then
+  musl_linker="$(command -v musl-gcc)"
+else
+  echo "musl gcc not found after install; arch=${arch}" >&2
+  exit 1
+fi
+
+zig_target="${TARGET/-unknown-linux-musl/-linux-musl}"
+runner_temp="${RUNNER_TEMP:-/tmp}"
+tool_root="${runner_temp}/codex-musl-tools-${TARGET}"
+mkdir -p "${tool_root}"
+
+sysroot=""
+if command -v zig >/dev/null; then
+  zig_bin="$(command -v zig)"
+  cc="${tool_root}/zigcc"
+  cxx="${tool_root}/zigcxx"
+
+  cat >"${cc}" <<EOF
+#!/usr/bin/env bash
+set -euo pipefail
+
+args=()
+skip_next=0
+for arg in "\$@"; do
+  if [[ "\${skip_next}" -eq 1 ]]; then
+    skip_next=0
+    continue
+  fi
+  case "\${arg}" in
+    --target)
+      skip_next=1
+      continue
+      ;;
+    --target=*|-target=*|-target)
+      # Drop any explicit --target/-target flags. Zig expects -target and
+      # rejects Rust triples like *-unknown-linux-musl.
+      if [[ "\${arg}" == "-target" ]]; then
+        skip_next=1
+      fi
+      continue
+      ;;
+  esac
+  args+=("\${arg}")
+done
+
+exec "${zig_bin}" cc -target "${zig_target}" "\${args[@]}"
+EOF
+  cat >"${cxx}" <<EOF
+#!/usr/bin/env bash
+set -euo pipefail
+
+args=()
+skip_next=0
+for arg in "\$@"; do
+  if [[ "\${skip_next}" -eq 1 ]]; then
+    skip_next=0
+    continue
+  fi
+  case "\${arg}" in
+    --target)
+      skip_next=1
+      continue
+      ;;
+    --target=*|-target=*|-target)
+      if [[ "\${arg}" == "-target" ]]; then
+        skip_next=1
+      fi
+      continue
+      ;;
+  esac
+  args+=("\${arg}")
+done
+
+exec "${zig_bin}" c++ -target "${zig_target}" "\${args[@]}"
+EOF
+  chmod +x "${cc}" "${cxx}"
+
+  sysroot="$("${zig_bin}" cc -target "${zig_target}" -print-sysroot 2>/dev/null || true)"
+else
+  cc="${musl_linker}"
+
+  if command -v "${arch}-linux-musl-g++" >/dev/null; then
+    cxx="$(command -v "${arch}-linux-musl-g++")"
+  elif command -v musl-g++ >/dev/null; then
+    cxx="$(command -v musl-g++)"
+  else
+    cxx="${cc}"
+  fi
+fi
+
+if [[ -n "${sysroot}" && "${sysroot}" != "/" ]]; then
+  echo "BORING_BSSL_SYSROOT=${sysroot}" >> "$GITHUB_ENV"
+  boring_sysroot_var="BORING_BSSL_SYSROOT_${TARGET}"
+  boring_sysroot_var="${boring_sysroot_var//-/_}"
+  echo "${boring_sysroot_var}=${sysroot}" >> "$GITHUB_ENV"
+fi
+
+cflags="-pthread"
+cxxflags="-pthread"
+if [[ "${TARGET}" == "aarch64-unknown-linux-musl" ]]; then
+  # BoringSSL enables -Wframe-larger-than=25344 under clang and treats warnings as errors.
+  cflags="${cflags} -Wno-error=frame-larger-than"
+  cxxflags="${cxxflags} -Wno-error=frame-larger-than"
+fi
+
+echo "CFLAGS=${cflags}" >> "$GITHUB_ENV"
+echo "CXXFLAGS=${cxxflags}" >> "$GITHUB_ENV"
+echo "CC=${cc}" >> "$GITHUB_ENV"
+echo "TARGET_CC=${cc}" >> "$GITHUB_ENV"
+target_cc_var="CC_${TARGET}"
+target_cc_var="${target_cc_var//-/_}"
+echo "${target_cc_var}=${cc}" >> "$GITHUB_ENV"
+echo "CXX=${cxx}" >> "$GITHUB_ENV"
+echo "TARGET_CXX=${cxx}" >> "$GITHUB_ENV"
+target_cxx_var="CXX_${TARGET}"
+target_cxx_var="${target_cxx_var//-/_}"
+echo "${target_cxx_var}=${cxx}" >> "$GITHUB_ENV"
+
+cargo_linker_var="CARGO_TARGET_${TARGET^^}_LINKER"
+cargo_linker_var="${cargo_linker_var//-/_}"
+echo "${cargo_linker_var}=${musl_linker}" >> "$GITHUB_ENV"
+
+echo "CMAKE_C_COMPILER=${cc}" >> "$GITHUB_ENV"
+echo "CMAKE_CXX_COMPILER=${cxx}" >> "$GITHUB_ENV"
+echo "CMAKE_ARGS=-DCMAKE_HAVE_THREADS_LIBRARY=1 -DCMAKE_USE_PTHREADS_INIT=1 -DCMAKE_THREAD_LIBS_INIT=-pthread -DTHREADS_PREFER_PTHREAD_FLAG=ON" >> "$GITHUB_ENV"

.github/workflows/Dockerfile.bazel

@@ -0,0 +1,20 @@
+FROM ubuntu:24.04
+
+# TODO(mbolin): Published to docker.io/mbolin491/codex-bazel:latest for
+# initial debugging, but we should publish to a more proper location.
+#
+# docker buildx create --use
+# docker buildx build --platform linux/amd64,linux/arm64 -f .github/workflows/Dockerfile.bazel -t mbolin491/codex-bazel:latest --push .
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    curl git python3 ca-certificates && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install dotslash.
+RUN curl -LSfs "https://github.com/facebook/dotslash/releases/download/v0.5.8/dotslash-ubuntu-22.04.$(uname -m).tar.gz" | tar fxz - -C /usr/local/bin
+
+# Ubuntu 24.04 ships with user 'ubuntu' already created with UID 1000.
+USER ubuntu
+
+WORKDIR /workspace

.github/workflows/bazel.yml

@@ -0,0 +1,110 @@
+name: Bazel (experimental)
+
+# Note this workflow was originally derived from:
+# https://github.com/cerisier/toolchains_llvm_bootstrapped/blob/main/.github/workflows/ci.yaml
+
+on:
+  pull_request: {}
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+concurrency:
+  # Cancel previous actions from the same PR or branch except 'main' branch.
+  # See https://docs.github.com/en/actions/using-jobs/using-concurrency and https://docs.github.com/en/actions/learn-github-actions/contexts for more info.
+  group: concurrency-group::${{ github.workflow }}::${{ github.event.pull_request.number > 0 && format('pr-{0}', github.event.pull_request.number) || github.ref_name }}${{ github.ref_name == 'main' && format('::{0}', github.run_id) || ''}}
+  cancel-in-progress: ${{ github.ref_name != 'main' }}
+jobs:
+  test:
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          # macOS
+          - os: macos-15-xlarge
+            target: aarch64-apple-darwin
+          - os: macos-15-xlarge
+            target: x86_64-apple-darwin
+
+          # Linux
+          - os: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-gnu
+          - os: ubuntu-24.04
+            target: x86_64-unknown-linux-gnu
+          - os: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+          - os: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+          # TODO: Enable Windows once we fix the toolchain issues there.
+          #- os: windows-latest
+          #  target: x86_64-pc-windows-gnullvm
+    runs-on: ${{ matrix.os }}
+
+    # Configure a human readable name for each job
+    name: Local Bazel build on ${{ matrix.os }} for ${{ matrix.target }}
+
+    steps:
+      - uses: actions/checkout@v6
+
+      # Some integration tests rely on DotSlash being installed.
+      # See https://github.com/openai/codex/pull/7617.
+      - name: Install DotSlash
+        uses: facebook/install-dotslash@v2
+
+      - name: Make DotSlash available in PATH (Unix)
+        if: runner.os != 'Windows'
+        run: cp "$(which dotslash)" /usr/local/bin
+
+      - name: Make DotSlash available in PATH (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: Copy-Item (Get-Command dotslash).Source -Destination "$env:LOCALAPPDATA\Microsoft\WindowsApps\dotslash.exe"
+
+      # Install Bazel via Bazelisk
+      - name: Set up Bazel
+        uses: bazelbuild/setup-bazelisk@v3
+
+      # TODO(mbolin): Bring this back once we have caching working. Currently,
+      # we never seem to get a cache hit but we still end up paying the cost of
+      # uploading at the end of the build, which takes over a minute!
+      #
+      # Cache build and external artifacts so that the next ci build is incremental.
+      # Because github action caches cannot be updated after a build, we need to
+      # store the contents of each build in a unique cache key, then fall back to loading
+      # it on the next ci run. We use hashFiles(...) in the key and restore-keys- with
+      # the prefix to load the most recent cache for the branch on a cache miss. You
+      # should customize the contents of hashFiles to capture any bazel input sources,
+      # although this doesn't need to be perfect. If none of the input sources change
+      # then a cache hit will load an existing cache and bazel won't have to do any work.
+      # In the case of a cache miss, you want the fallback cache to contain most of the
+      # previously built artifacts to minimize build time. The more precise you are with
+      # hashFiles sources the less work bazel will have to do.
+      # - name: Mount bazel caches
+      #   uses: actions/cache@v5
+      #   with:
+      #     path: |
+      #       ~/.cache/bazel-repo-cache
+      #       ~/.cache/bazel-repo-contents-cache
+      #     key: bazel-cache-${{ matrix.os }}-${{ hashFiles('**/BUILD.bazel', '**/*.bzl', 'MODULE.bazel') }}
+      #     restore-keys: |
+      #       bazel-cache-${{ matrix.os }}
+
+      - name: Configure Bazel startup args (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          # Use a very short path to reduce argv/path length issues.
+          "BAZEL_STARTUP_ARGS=--output_user_root=C:\" | Out-File -FilePath $env:GITHUB_ENV -Encoding utf8 -Append
+
+      - name: bazel test //...
+        env:
+          BUILDBUDDY_API_KEY: ${{ secrets.BUILDBUDDY_API_KEY }}
+        shell: bash
+        run: |
+          bazel $BAZEL_STARTUP_ARGS --bazelrc=.github/workflows/ci.bazelrc test //... \
+            --build_metadata=REPO_URL=https://github.com/openai/codex.git \
+            --build_metadata=COMMIT_SHA=$(git rev-parse HEAD) \
+            --build_metadata=ROLE=CI \
+            --build_metadata=VISIBILITY=PUBLIC \
+            "--remote_header=x-buildbuddy-api-key=$BUILDBUDDY_API_KEY"

.github/workflows/ci.bazelrc

@@ -0,0 +1,20 @@
+common --remote_download_minimal
+common --nobuild_runfile_links
+common --keep_going
+
+# We prefer to run the build actions entirely remotely so we can dial up the concurrency.
+# We have platform-specific tests, so we want to execute the tests on all platforms using the strongest sandboxing available on each platform.
+
+# On linux, we can do a full remote build/test, by targeting the right (x86/arm) runners, so we have coverage of both.
+# Linux crossbuilds don't work until we untangle the libc constraint mess.
+common:linux --config=remote
+common:linux --strategy=remote
+common:linux --platforms=//:rbe
+
+# On mac, we can run all the build actions remotely but test actions locally.
+common:macos --config=remote
+common:macos --strategy=remote
+common:macos --strategy=TestRunner=darwin-sandbox,local
+
+common:windows --strategy=TestRunner=local
+

.github/workflows/rust-ci.yml

@@ -59,7 +59,7 @@ jobs:
         working-directory: codex-rs
     steps:
       - uses: actions/checkout@v6
-      - uses: dtolnay/rust-toolchain@1.90
+      - uses: dtolnay/rust-toolchain@1.93
         with:
           components: rustfmt
       - name: cargo fmt
@@ -77,7 +77,7 @@ jobs:
         working-directory: codex-rs
     steps:
       - uses: actions/checkout@v6
-      - uses: dtolnay/rust-toolchain@1.90
+      - uses: dtolnay/rust-toolchain@1.93
       - uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
         with:
           tool: cargo-shear
@@ -88,7 +88,7 @@ jobs:
   # --- CI to validate on different os/targets --------------------------------
   lint_build:
     name: Lint/Build — ${{ matrix.runner }} - ${{ matrix.target }}${{ matrix.profile == 'release' && ' (release)' || '' }}
-    runs-on: ${{ matrix.runner }}
+    runs-on: ${{ matrix.runs_on || matrix.runner }}
     timeout-minutes: 30
     needs: changed
     # Keep job-level if to avoid spinning up runners when not needed
@@ -106,55 +106,102 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - runner: macos-14
+          - runner: macos-15-xlarge
             target: aarch64-apple-darwin
             profile: dev
-          - runner: macos-14
+          - runner: macos-15-xlarge
             target: x86_64-apple-darwin
             profile: dev
           - runner: ubuntu-24.04
             target: x86_64-unknown-linux-musl
             profile: dev
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-x64
           - runner: ubuntu-24.04
             target: x86_64-unknown-linux-gnu
             profile: dev
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-x64
           - runner: ubuntu-24.04-arm
             target: aarch64-unknown-linux-musl
             profile: dev
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-arm64
           - runner: ubuntu-24.04-arm
             target: aarch64-unknown-linux-gnu
             profile: dev
-          - runner: windows-latest
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-arm64
+          - runner: windows-x64
             target: x86_64-pc-windows-msvc
             profile: dev
-          - runner: windows-11-arm
+            runs_on:
+              group: codex-runners
+              labels: codex-windows-x64
+          - runner: windows-arm64
             target: aarch64-pc-windows-msvc
             profile: dev
+            runs_on:
+              group: codex-runners
+              labels: codex-windows-arm64
 
           # Also run representative release builds on Mac and Linux because
           # there could be release-only build errors we want to catch.
           # Hopefully this also pre-populates the build cache to speed up
           # releases.
-          - runner: macos-14
+          - runner: macos-15-xlarge
             target: aarch64-apple-darwin
             profile: release
           - runner: ubuntu-24.04
             target: x86_64-unknown-linux-musl
             profile: release
-          - runner: windows-latest
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-x64
+          - runner: windows-x64
             target: x86_64-pc-windows-msvc
             profile: release
-          - runner: windows-11-arm
+            runs_on:
+              group: codex-runners
+              labels: codex-windows-x64
+          - runner: windows-arm64
             target: aarch64-pc-windows-msvc
             profile: release
+            runs_on:
+              group: codex-runners
+              labels: codex-windows-arm64
 
     steps:
       - uses: actions/checkout@v6
-      - uses: dtolnay/rust-toolchain@1.90
+      - name: Install UBSan runtime (musl)
+        if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          if command -v apt-get >/dev/null 2>&1; then
+            sudo apt-get update -y
+            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y libubsan1
+          fi
+      - uses: dtolnay/rust-toolchain@1.93
         with:
           targets: ${{ matrix.target }}
           components: clippy
 
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Use hermetic Cargo home (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          cargo_home="${GITHUB_WORKSPACE}/.cargo-home"
+          mkdir -p "${cargo_home}/bin"
+          echo "CARGO_HOME=${cargo_home}" >> "$GITHUB_ENV"
+          echo "${cargo_home}/bin" >> "$GITHUB_PATH"
+          : > "${cargo_home}/config.toml"
+
       - name: Compute lockfile hash
         id: lockhash
         working-directory: codex-rs
@@ -175,6 +222,10 @@ jobs:
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
+            ${{ github.workspace }}/.cargo-home/bin/
+            ${{ github.workspace }}/.cargo-home/registry/index/
+            ${{ github.workspace }}/.cargo-home/registry/cache/
+            ${{ github.workspace }}/.cargo-home/git/db/
           key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
           restore-keys: |
             cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
@@ -217,6 +268,14 @@ jobs:
             sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-
             sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
 
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Disable sccache wrapper (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          echo "RUSTC_WRAPPER=" >> "$GITHUB_ENV"
+          echo "RUSTC_WORKSPACE_WRAPPER=" >> "$GITHUB_ENV"
+
       - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
         name: Prepare APT cache directories (musl)
         shell: bash
@@ -234,15 +293,73 @@ jobs:
             /var/cache/apt
           key: apt-${{ matrix.runner }}-${{ matrix.target }}-v1
 
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Install Zig
+        uses: mlugg/setup-zig@v2
+        with:
+          version: 0.14.0
+
       - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
         name: Install musl build tools
         env:
           DEBIAN_FRONTEND: noninteractive
+          TARGET: ${{ matrix.target }}
+          APT_UPDATE_ARGS: -o Acquire::Retries=3
+          APT_INSTALL_ARGS: --no-install-recommends
+        shell: bash
+        run: bash "${GITHUB_WORKSPACE}/.github/scripts/install-musl-build-tools.sh"
+
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Configure rustc UBSan wrapper (musl host)
         shell: bash
         run: |
           set -euo pipefail
-          sudo apt-get -y update -o Acquire::Retries=3
-          sudo apt-get -y install --no-install-recommends musl-tools pkg-config
+          ubsan=""
+          if command -v ldconfig >/dev/null 2>&1; then
+            ubsan="$(ldconfig -p | grep -m1 'libubsan\.so\.1' | sed -E 's/.*=> (.*)$/\1/')"
+          fi
+          wrapper_root="${RUNNER_TEMP:-/tmp}"
+          wrapper="${wrapper_root}/rustc-ubsan-wrapper"
+          cat > "${wrapper}" <<EOF
+          #!/usr/bin/env bash
+          set -euo pipefail
+          if [[ -n "${ubsan}" ]]; then
+            export LD_PRELOAD="${ubsan}\${LD_PRELOAD:+:\${LD_PRELOAD}}"
+          fi
+          exec "\$1" "\${@:2}"
+          EOF
+          chmod +x "${wrapper}"
+          echo "RUSTC_WRAPPER=${wrapper}" >> "$GITHUB_ENV"
+          echo "RUSTC_WORKSPACE_WRAPPER=" >> "$GITHUB_ENV"
+
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Clear sanitizer flags (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          # Clear global Rust flags so host/proc-macro builds don't pull in UBSan.
+          echo "RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_ENCODED_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "RUSTDOCFLAGS=" >> "$GITHUB_ENV"
+          # Override any runner-level Cargo config rustflags as well.
+          echo "CARGO_BUILD_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_X86_64_UNKNOWN_LINUX_MUSL_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_RUSTFLAGS=" >> "$GITHUB_ENV"
+
+          sanitize_flags() {
+            local input="$1"
+            input="${input//-fsanitize=undefined/}"
+            input="${input//-fno-sanitize-recover=undefined/}"
+            input="${input//-fno-sanitize-trap=undefined/}"
+            echo "$input"
+          }
+
+          cflags="$(sanitize_flags "${CFLAGS-}")"
+          cxxflags="$(sanitize_flags "${CXXFLAGS-}")"
+          echo "CFLAGS=${cflags}" >> "$GITHUB_ENV"
+          echo "CXXFLAGS=${cxxflags}" >> "$GITHUB_ENV"
 
       - name: Install cargo-chef
         if: ${{ matrix.profile == 'release' }}
@@ -289,6 +406,10 @@ jobs:
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
+            ${{ github.workspace }}/.cargo-home/bin/
+            ${{ github.workspace }}/.cargo-home/registry/index/
+            ${{ github.workspace }}/.cargo-home/registry/cache/
+            ${{ github.workspace }}/.cargo-home/git/db/
           key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
 
       - name: Save sccache cache (fallback)
@@ -336,7 +457,7 @@ jobs:
 
   tests:
     name: Tests — ${{ matrix.runner }} - ${{ matrix.target }}
-    runs-on: ${{ matrix.runner }}
+    runs-on: ${{ matrix.runs_on || matrix.runner }}
     timeout-minutes: 30
     needs: changed
     if: ${{ needs.changed.outputs.codex == 'true' || needs.changed.outputs.workflows == 'true' || github.event_name == 'push' }}
@@ -353,46 +474,43 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - runner: macos-14
+          - runner: macos-15-xlarge
             target: aarch64-apple-darwin
             profile: dev
           - runner: ubuntu-24.04
             target: x86_64-unknown-linux-gnu
             profile: dev
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-x64
           - runner: ubuntu-24.04-arm
             target: aarch64-unknown-linux-gnu
             profile: dev
-          - runner: windows-latest
+            runs_on:
+              group: codex-runners
+              labels: codex-linux-arm64
+          - runner: windows-x64
             target: x86_64-pc-windows-msvc
             profile: dev
-          - runner: windows-11-arm
+            runs_on:
+              group: codex-runners
+              labels: codex-windows-x64
+          - runner: windows-arm64
             target: aarch64-pc-windows-msvc
             profile: dev
+            runs_on:
+              group: codex-runners
+              labels: codex-windows-arm64
 
     steps:
       - uses: actions/checkout@v6
 
-      # We have been running out of space when running this job on Linux for
-      # x86_64-unknown-linux-gnu, so remove some unnecessary dependencies.
-      - name: Remove unnecessary dependencies to save space
-        if: ${{ startsWith(matrix.runner, 'ubuntu') }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          sudo rm -rf \
-            /usr/local/lib/android \
-            /usr/share/dotnet \
-            /usr/local/share/boost \
-            /usr/local/lib/node_modules \
-            /opt/ghc
-          sudo apt-get remove -y docker.io docker-compose podman buildah
-
       # Some integration tests rely on DotSlash being installed.
       # See https://github.com/openai/codex/pull/7617.
       - name: Install DotSlash
         uses: facebook/install-dotslash@v2
 
-      - uses: dtolnay/rust-toolchain@1.90
+      - uses: dtolnay/rust-toolchain@1.93
         with:
           targets: ${{ matrix.target }}
 

.github/workflows/rust-release.yml

@@ -20,7 +20,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v6
-
+      - uses: dtolnay/rust-toolchain@1.92
       - name: Validate tag matches Cargo.toml version
         shell: bash
         run: |
@@ -45,11 +45,20 @@ jobs:
           echo "✅  Tag and Cargo.toml agree (${tag_ver})"
           echo "::endgroup::"
 
+      - name: Verify config schema fixture
+        shell: bash
+        working-directory: codex-rs
+        run: |
+          set -euo pipefail
+          echo "If this fails, run: just write-config-schema to overwrite fixture with intentional changes."
+          cargo run -p codex-core --bin codex-write-config-schema
+          git diff --exit-code core/config.schema.json
+
   build:
     needs: tag-check
     name: Build - ${{ matrix.runner }} - ${{ matrix.target }}
     runs-on: ${{ matrix.runner }}
-    timeout-minutes: 30
+    timeout-minutes: 60
     permissions:
       contents: read
       id-token: write
@@ -80,10 +89,30 @@ jobs:
 
     steps:
       - uses: actions/checkout@v6
-      - uses: dtolnay/rust-toolchain@1.90
+      - name: Install UBSan runtime (musl)
+        if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          if command -v apt-get >/dev/null 2>&1; then
+            sudo apt-get update -y
+            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y libubsan1
+          fi
+      - uses: dtolnay/rust-toolchain@1.93
         with:
           targets: ${{ matrix.target }}
 
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Use hermetic Cargo home (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          cargo_home="${GITHUB_WORKSPACE}/.cargo-home"
+          mkdir -p "${cargo_home}/bin"
+          echo "CARGO_HOME=${cargo_home}" >> "$GITHUB_ENV"
+          echo "${cargo_home}/bin" >> "$GITHUB_PATH"
+          : > "${cargo_home}/config.toml"
+
       - uses: actions/cache@v5
         with:
           path: |
@@ -91,14 +120,76 @@ jobs:
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
+            ${{ github.workspace }}/.cargo-home/bin/
+            ${{ github.workspace }}/.cargo-home/registry/index/
+            ${{ github.workspace }}/.cargo-home/registry/cache/
+            ${{ github.workspace }}/.cargo-home/git/db/
             ${{ github.workspace }}/codex-rs/target/
           key: cargo-${{ matrix.runner }}-${{ matrix.target }}-release-${{ hashFiles('**/Cargo.lock') }}
 
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Install Zig
+        uses: mlugg/setup-zig@v2
+        with:
+          version: 0.14.0
+
       - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
         name: Install musl build tools
+        env:
+          TARGET: ${{ matrix.target }}
+        run: bash "${GITHUB_WORKSPACE}/.github/scripts/install-musl-build-tools.sh"
+
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Configure rustc UBSan wrapper (musl host)
+        shell: bash
         run: |
-          sudo apt-get update
-          sudo apt-get install -y musl-tools pkg-config
+          set -euo pipefail
+          ubsan=""
+          if command -v ldconfig >/dev/null 2>&1; then
+            ubsan="$(ldconfig -p | grep -m1 'libubsan\.so\.1' | sed -E 's/.*=> (.*)$/\1/')"
+          fi
+          wrapper_root="${RUNNER_TEMP:-/tmp}"
+          wrapper="${wrapper_root}/rustc-ubsan-wrapper"
+          cat > "${wrapper}" <<EOF
+          #!/usr/bin/env bash
+          set -euo pipefail
+          if [[ -n "${ubsan}" ]]; then
+            export LD_PRELOAD="${ubsan}\${LD_PRELOAD:+:\${LD_PRELOAD}}"
+          fi
+          exec "\$1" "\${@:2}"
+          EOF
+          chmod +x "${wrapper}"
+          echo "RUSTC_WRAPPER=${wrapper}" >> "$GITHUB_ENV"
+          echo "RUSTC_WORKSPACE_WRAPPER=" >> "$GITHUB_ENV"
+
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Clear sanitizer flags (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          # Clear global Rust flags so host/proc-macro builds don't pull in UBSan.
+          echo "RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_ENCODED_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "RUSTDOCFLAGS=" >> "$GITHUB_ENV"
+          # Override any runner-level Cargo config rustflags as well.
+          echo "CARGO_BUILD_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_X86_64_UNKNOWN_LINUX_MUSL_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_RUSTFLAGS=" >> "$GITHUB_ENV"
+
+          sanitize_flags() {
+            local input="$1"
+            input="${input//-fsanitize=undefined/}"
+            input="${input//-fno-sanitize-recover=undefined/}"
+            input="${input//-fno-sanitize-trap=undefined/}"
+            echo "$input"
+          }
+
+          cflags="$(sanitize_flags "${CFLAGS-}")"
+          cxxflags="$(sanitize_flags "${CXXFLAGS-}")"
+          echo "CFLAGS=${cflags}" >> "$GITHUB_ENV"
+          echo "CXXFLAGS=${cxxflags}" >> "$GITHUB_ENV"
 
       - name: Cargo build
         shell: bash
@@ -236,6 +327,7 @@ jobs:
           # Path that contains the uncompressed binaries for the current
           # ${{ matrix.target }}
           dest="dist/${{ matrix.target }}"
+          repo_root=$PWD
 
           # We want to ship the raw Windows executables in the GitHub Release
           # in addition to the compressed archives. Keep the originals for
@@ -275,7 +367,30 @@ jobs:
             # Must run from inside the dest dir so 7z won't
             # embed the directory path inside the zip.
             if [[ "${{ matrix.runner }}" == windows* ]]; then
-              (cd "$dest" && 7z a "${base}.zip" "$base")
+              if [[ "$base" == "codex-${{ matrix.target }}.exe" ]]; then
+                # Bundle the sandbox helper binaries into the main codex zip so
+                # WinGet installs include the required helpers next to codex.exe.
+                # Fall back to the single-binary zip if the helpers are missing
+                # to avoid breaking releases.
+                bundle_dir="$(mktemp -d)"
+                runner_src="$dest/codex-command-runner-${{ matrix.target }}.exe"
+                setup_src="$dest/codex-windows-sandbox-setup-${{ matrix.target }}.exe"
+                if [[ -f "$runner_src" && -f "$setup_src" ]]; then
+                  cp "$dest/$base" "$bundle_dir/$base"
+                  cp "$runner_src" "$bundle_dir/codex-command-runner.exe"
+                  cp "$setup_src" "$bundle_dir/codex-windows-sandbox-setup.exe"
+                  # Use an absolute path so bundle zips land in the real dist
+                  # dir even when 7z runs from a temp directory.
+                  (cd "$bundle_dir" && 7z a "$repo_root/$dest/${base}.zip" .)
+                else
+                  echo "warning: missing sandbox binaries; falling back to single-binary zip"
+                  echo "warning: expected $runner_src and $setup_src"
+                  (cd "$dest" && 7z a "${base}.zip" "$base")
+                fi
+                rm -rf "$bundle_dir"
+              else
+                (cd "$dest" && 7z a "${base}.zip" "$base")
+              fi
             fi
 
             # Also create .zst (existing behaviour) *and* remove the original
@@ -358,6 +473,10 @@ jobs:
 
           ls -R dist/
 
+      - name: Add config schema release asset
+        run: |
+          cp codex-rs/core/config.schema.json dist/config-schema.json
+
       - name: Define release name
         id: release_name
         run: |
@@ -428,6 +547,19 @@ jobs:
           tag: ${{ github.ref_name }}
           config: .github/dotslash-config.json
 
+      - name: Trigger developers.openai.com deploy
+        # Only trigger the deploy if the release is not a pre-release.
+        # The deploy is used to update the developers.openai.com website with the new config schema json file.
+        if: ${{ !contains(steps.release_name.outputs.name, '-') }}
+        continue-on-error: true
+        env:
+          DEV_WEBSITE_VERCEL_DEPLOY_HOOK_URL: ${{ secrets.DEV_WEBSITE_VERCEL_DEPLOY_HOOK_URL }}
+        run: |
+          if ! curl -sS -f -o /dev/null -X POST "$DEV_WEBSITE_VERCEL_DEPLOY_HOOK_URL"; then
+            echo "::warning title=developers.openai.com deploy hook failed::Vercel deploy hook POST failed for ${GITHUB_REF_NAME}"
+            exit 1
+          fi
+
   # Publish to npm using OIDC authentication.
   # July 31, 2025: https://github.blog/changelog/2025-07-31-npm-trusted-publishing-with-oidc-is-generally-available/
   # npm docs: https://docs.npmjs.com/trusted-publishers

.github/workflows/sdk.yml

@@ -24,7 +24,7 @@ jobs:
           node-version: 22
           cache: pnpm
 
-      - uses: dtolnay/rust-toolchain@1.90
+      - uses: dtolnay/rust-toolchain@1.93
 
       - name: build codex
         run: cargo build --bin codex

.github/workflows/shell-tool-mcp.yml

@@ -93,15 +93,83 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v6
 
-      - uses: dtolnay/rust-toolchain@1.90
+      - name: Install UBSan runtime (musl)
+        if: ${{ matrix.install_musl }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          if command -v apt-get >/dev/null 2>&1; then
+            sudo apt-get update -y
+            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y libubsan1
+          fi
+
+      - uses: dtolnay/rust-toolchain@1.93
         with:
           targets: ${{ matrix.target }}
 
+      - if: ${{ matrix.install_musl }}
+        name: Install Zig
+        uses: mlugg/setup-zig@v2
+        with:
+          version: 0.14.0
+
       - if: ${{ matrix.install_musl }}
         name: Install musl build dependencies
+        env:
+          TARGET: ${{ matrix.target }}
+        run: bash "${GITHUB_WORKSPACE}/.github/scripts/install-musl-build-tools.sh"
+
+      - if: ${{ matrix.install_musl }}
+        name: Configure rustc UBSan wrapper (musl host)
+        shell: bash
         run: |
-          sudo apt-get update
-          sudo apt-get install -y musl-tools pkg-config
+          set -euo pipefail
+          ubsan=""
+          if command -v ldconfig >/dev/null 2>&1; then
+            ubsan="$(ldconfig -p | grep -m1 'libubsan\.so\.1' | sed -E 's/.*=> (.*)$/\1/')"
+          fi
+          wrapper_root="${RUNNER_TEMP:-/tmp}"
+          wrapper="${wrapper_root}/rustc-ubsan-wrapper"
+          cat > "${wrapper}" <<EOF
+          #!/usr/bin/env bash
+          set -euo pipefail
+          if [[ -n "${ubsan}" ]]; then
+            export LD_PRELOAD="${ubsan}\${LD_PRELOAD:+:\${LD_PRELOAD}}"
+          fi
+          exec "\$1" "\${@:2}"
+          EOF
+          chmod +x "${wrapper}"
+          echo "RUSTC_WRAPPER=${wrapper}" >> "$GITHUB_ENV"
+          echo "RUSTC_WORKSPACE_WRAPPER=" >> "$GITHUB_ENV"
+
+      - if: ${{ matrix.install_musl }}
+        name: Clear sanitizer flags (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          # Clear global Rust flags so host/proc-macro builds don't pull in UBSan.
+          echo "RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_ENCODED_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "RUSTDOCFLAGS=" >> "$GITHUB_ENV"
+          # Override any runner-level Cargo config rustflags as well.
+          echo "CARGO_BUILD_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_X86_64_UNKNOWN_LINUX_MUSL_RUSTFLAGS=" >> "$GITHUB_ENV"
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_RUSTFLAGS=" >> "$GITHUB_ENV"
+
+          sanitize_flags() {
+            local input="$1"
+            input="${input//-fsanitize=undefined/}"
+            input="${input//-fno-sanitize-recover=undefined/}"
+            input="${input//-fno-sanitize-trap=undefined/}"
+            echo "$input"
+          }
+
+          cflags="$(sanitize_flags "${CFLAGS-}")"
+          cxxflags="$(sanitize_flags "${CXXFLAGS-}")"
+          echo "CFLAGS=${cflags}" >> "$GITHUB_ENV"
+          echo "CXXFLAGS=${cxxflags}" >> "$GITHUB_ENV"
 
       - name: Build exec server binaries
         run: cargo build --release --target ${{ matrix.target }} --bin codex-exec-mcp-server --bin codex-execve-wrapper
@@ -198,7 +266,7 @@ jobs:
         shell: bash
         run: |
           set -euo pipefail
-          git clone --depth 1 https://github.com/bminor/bash /tmp/bash
+          git clone --depth 1 https://github.com/bolinfest/bash /tmp/bash
           cd /tmp/bash
           git fetch --depth 1 origin a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
           git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
@@ -240,7 +308,7 @@ jobs:
         shell: bash
         run: |
           set -euo pipefail
-          git clone --depth 1 https://github.com/bminor/bash /tmp/bash
+          git clone --depth 1 https://github.com/bolinfest/bash /tmp/bash
           cd /tmp/bash
           git fetch --depth 1 origin a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
           git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
@@ -276,7 +344,6 @@ jobs:
       - name: Setup pnpm
         uses: pnpm/action-setup@v4
         with:
-          version: 10.8.1
           run_install: false
 
       - name: Setup Node.js
@@ -369,12 +436,6 @@ jobs:
       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@v6
         with:
@@ -382,6 +443,7 @@ jobs:
           registry-url: https://registry.npmjs.org
           scope: "@openai"
 
+      # Trusted publishing requires npm CLI version 11.5.1 or later.
       - name: Update npm
         run: npm install -g npm@latest
 

.markdownlint-cli2.yaml

@@ -0,0 +1,6 @@
+config:
+  MD013:
+    line_length: 100
+
+globs:
+  - "docs/tui-chat-composer.md"

AGENTS.md

@@ -11,14 +11,17 @@ In the codex-rs folder where the rust code lives:
 - Always collapse if statements per https://rust-lang.github.io/rust-clippy/master/index.html#collapsible_if
 - Always inline format! args when possible per https://rust-lang.github.io/rust-clippy/master/index.html#uninlined_format_args
 - Use method references over closures when possible per https://rust-lang.github.io/rust-clippy/master/index.html#redundant_closure_for_method_calls
+- When possible, make `match` statements exhaustive and avoid wildcard arms.
 - When writing tests, prefer comparing the equality of entire objects over fields one by one.
 - When making a change that adds or changes an API, ensure that the documentation in the `docs/` folder is up to date if applicable.
+- If you change `ConfigToml` or nested config types, run `just write-config-schema` to update `codex-rs/core/config.schema.json`.
 
-Run `just fmt` (in `codex-rs` directory) automatically after making Rust code changes; do not ask for approval to run it. Before finalizing a change to `codex-rs`, run `just fix -p <project>` (in `codex-rs` directory) to fix any linter issues in the code. Prefer scoping with `-p` to avoid slow workspace‑wide Clippy builds; only run `just fix` without `-p` if you changed shared crates. Additionally, run the tests:
+Run `just fmt` (in `codex-rs` directory) automatically after you have finished making Rust code changes; do not ask for approval to run it. Additionally, run the tests:
 
 1. Run the test for the specific project that was changed. For example, if changes were made in `codex-rs/tui`, run `cargo test -p codex-tui`.
-2. Once those pass, if any changes were made in common, core, or protocol, run the complete test suite with `cargo test --all-features`.
-   When running interactively, ask the user before running `just fix` to finalize. `just fmt` does not require approval. project-specific or individual tests can be run without asking the user, but do ask the user before running the complete test suite.
+2. Once those pass, if any changes were made in common, core, or protocol, run the complete test suite with `cargo test --all-features`. project-specific or individual tests can be run without asking the user, but do ask the user before running the complete test suite.
+
+Before finalizing a large change to `codex-rs`, run `just fix -p <project>` (in `codex-rs` directory) to fix any linter issues in the code. Prefer scoping with `-p` to avoid slow workspace‑wide Clippy builds; only run `just fix` without `-p` if you changed shared crates.
 
 ## TUI style conventions
 

BUILD.bazel

@@ -0,0 +1,23 @@
+load("@apple_support//xcode:xcode_config.bzl", "xcode_config")
+
+xcode_config(name = "disable_xcode")
+
+# We mark the local platform as glibc-compatible so that rust can grab a toolchain for us.
+# TODO(zbarsky): Upstream a better libc constraint into rules_rust.
+# We only enable this on linux though for sanity, and because it breaks remote execution.
+platform(
+    name = "local",
+    constraint_values = [
+        "@toolchains_llvm_bootstrapped//constraints/libc:gnu.2.28",
+    ],
+    parents = [
+        "@platforms//host",
+    ],
+)
+
+alias(
+    name = "rbe",
+    actual = "@rbe_platform",
+)
+
+exports_files(["AGENTS.md"])

MODULE.bazel

@@ -0,0 +1,136 @@
+bazel_dep(name = "platforms", version = "1.0.0")
+bazel_dep(name = "toolchains_llvm_bootstrapped", version = "0.3.1")
+archive_override(
+    module_name = "toolchains_llvm_bootstrapped",
+    integrity = "sha256-4/2h4tYSUSptxFVI9G50yJxWGOwHSeTeOGBlaLQBV8g=",
+    strip_prefix = "toolchains_llvm_bootstrapped-d20baf67e04d8e2887e3779022890d1dc5e6b948",
+    urls = ["https://github.com/cerisier/toolchains_llvm_bootstrapped/archive/d20baf67e04d8e2887e3779022890d1dc5e6b948.tar.gz"],
+)
+
+osx = use_extension("@toolchains_llvm_bootstrapped//toolchain/extension:osx.bzl", "osx")
+osx.framework(name = "ApplicationServices")
+osx.framework(name = "AppKit")
+osx.framework(name = "ColorSync")
+osx.framework(name = "CoreFoundation")
+osx.framework(name = "CoreGraphics")
+osx.framework(name = "CoreServices")
+osx.framework(name = "CoreText")
+osx.framework(name = "CFNetwork")
+osx.framework(name = "Foundation")
+osx.framework(name = "ImageIO")
+osx.framework(name = "Kernel")
+osx.framework(name = "OSLog")
+osx.framework(name = "Security")
+osx.framework(name = "SystemConfiguration")
+
+register_toolchains(
+    "@toolchains_llvm_bootstrapped//toolchain:all",
+)
+
+# Needed to disable xcode...
+bazel_dep(name = "apple_support", version = "2.1.0")
+bazel_dep(name = "rules_cc", version = "0.2.16")
+bazel_dep(name = "rules_platform", version = "0.1.0")
+bazel_dep(name = "rules_rust", version = "0.68.1")
+single_version_override(
+    module_name = "rules_rust",
+    patch_strip = 1,
+    patches = [
+        "//patches:rules_rust.patch",
+        "//patches:rules_rust_windows_gnu.patch",
+        "//patches:rules_rust_musl.patch",
+    ],
+)
+
+RUST_TRIPLES = [
+    "aarch64-unknown-linux-musl",
+    "aarch64-apple-darwin",
+    "aarch64-pc-windows-gnullvm",
+    "x86_64-unknown-linux-musl",
+    "x86_64-apple-darwin",
+    "x86_64-pc-windows-gnullvm",
+]
+
+rust = use_extension("@rules_rust//rust:extensions.bzl", "rust")
+rust.toolchain(
+    edition = "2024",
+    extra_target_triples = RUST_TRIPLES,
+    versions = ["1.93.0"],
+)
+use_repo(rust, "rust_toolchains")
+
+register_toolchains("@rust_toolchains//:all")
+
+bazel_dep(name = "rules_rs", version = "0.0.23")
+
+crate = use_extension("@rules_rs//rs:extensions.bzl", "crate")
+crate.from_cargo(
+    cargo_lock = "//codex-rs:Cargo.lock",
+    cargo_toml = "//codex-rs:Cargo.toml",
+    platform_triples = RUST_TRIPLES,
+)
+crate.annotation(
+    crate = "nucleo-matcher",
+    strip_prefix = "matcher",
+    version = "0.3.1",
+)
+
+bazel_dep(name = "openssl", version = "3.5.4.bcr.0")
+
+crate.annotation(
+    build_script_data = [
+        "@openssl//:gen_dir",
+    ],
+    build_script_env = {
+        "OPENSSL_DIR": "$(execpath @openssl//:gen_dir)",
+        "OPENSSL_NO_VENDOR": "1",
+        "OPENSSL_STATIC": "1",
+    },
+    crate = "openssl-sys",
+    data = ["@openssl//:gen_dir"],
+)
+
+inject_repo(crate, "openssl")
+
+crate.annotation(
+    crate = "runfiles",
+    workspace_cargo_toml = "rust/runfiles/Cargo.toml",
+)
+
+# Fix readme inclusions
+crate.annotation(
+    crate = "windows-link",
+    patch_args = ["-p1"],
+    patches = [
+        "//patches:windows-link.patch",
+    ],
+)
+
+WINDOWS_IMPORT_LIB = """
+load("@rules_cc//cc:defs.bzl", "cc_import")
+
+cc_import(
+    name = "windows_import_lib",
+    static_library = glob(["lib/*.a"])[0],
+)
+"""
+
+crate.annotation(
+    additive_build_file_content = WINDOWS_IMPORT_LIB,
+    crate = "windows_x86_64_gnullvm",
+    gen_build_script = "off",
+    deps = [":windows_import_lib"],
+)
+crate.annotation(
+    additive_build_file_content = WINDOWS_IMPORT_LIB,
+    crate = "windows_aarch64_gnullvm",
+    gen_build_script = "off",
+    deps = [":windows_import_lib"],
+)
+use_repo(crate, "crates")
+
+rbe_platform_repository = use_repo_rule("//:rbe.bzl", "rbe_platform_repository")
+
+rbe_platform_repository(
+    name = "rbe_platform",
+)

PNPM.md

@@ -1,70 +0,0 @@
-# Migration to pnpm
-
-This project has been migrated from npm to pnpm to improve dependency management and developer experience.
-
-## Why pnpm?
-
-- **Faster installation**: pnpm is significantly faster than npm and yarn
-- **Disk space savings**: pnpm uses a content-addressable store to avoid duplication
-- **Phantom dependency prevention**: pnpm creates a strict node_modules structure
-- **Native workspaces support**: simplified monorepo management
-
-## How to use pnpm
-
-### Installation
-
-```bash
-# Global installation of pnpm
-npm install -g pnpm@10.8.1
-
-# Or with corepack (available with Node.js 22+)
-corepack enable
-corepack prepare pnpm@10.8.1 --activate
-```
-
-### Common commands
-
-| npm command     | pnpm equivalent  |
-| --------------- | ---------------- |
-| `npm install`   | `pnpm install`   |
-| `npm run build` | `pnpm run build` |
-| `npm test`      | `pnpm test`      |
-| `npm run lint`  | `pnpm run lint`  |
-
-### Workspace-specific commands
-
-| Action                                     | Command                                  |
-| ------------------------------------------ | ---------------------------------------- |
-| Run a command in a specific package        | `pnpm --filter @openai/codex run build`  |
-| Install a dependency in a specific package | `pnpm --filter @openai/codex add lodash` |
-| Run a command in all packages              | `pnpm -r run test`                       |
-
-## Monorepo structure
-
-```
-codex/
-├── pnpm-workspace.yaml    # Workspace configuration
-├── .npmrc                 # pnpm configuration
-├── package.json           # Root dependencies and scripts
-├── codex-cli/             # Main package
-│   └── package.json       # codex-cli specific dependencies
-└── docs/                  # Documentation (future package)
-```
-
-## Configuration files
-
-- **pnpm-workspace.yaml**: Defines the packages included in the monorepo
-- **.npmrc**: Configures pnpm behavior
-- **Root package.json**: Contains shared scripts and dependencies
-
-## CI/CD
-
-CI/CD workflows have been updated to use pnpm instead of npm. Make sure your CI environments use pnpm 10.8.1 or higher.
-
-## Known issues
-
-If you encounter issues with pnpm, try the following solutions:
-
-1. Remove the `node_modules` folder and `pnpm-lock.yaml` file, then run `pnpm install`
-2. Make sure you're using pnpm 10.8.1 or higher
-3. Verify that Node.js 22 or higher is installed

README.md

@@ -1,7 +1,7 @@
 <p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install --cask codex</code></p>
 <p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.
 <p align="center">
-  <img src="./.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" />
+  <img src="https://github.com/openai/codex/blob/main/.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" />
 </p>
 </br>
 If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href="https://developers.openai.com/codex/ide">install in your IDE.</a>

announcement_tip.toml

@@ -10,7 +10,8 @@ from_date = "2024-10-01"
 to_date = "2024-10-15"
 target_app = "cli"
 
+# Test announcement only for local build version until 2026-01-10 excluded (past)
 [[announcements]]
 content = "This is a test announcement"
 version_regex = "^0\\.0\\.0$"
-to_date = "2026-01-10"
+to_date = "2026-05-10"

codex-cli/bin/codex.js

@@ -95,7 +95,6 @@ function detectPackageManager() {
     return "bun";
   }
 
-
   if (
     __dirname.includes(".bun/install/global") ||
     __dirname.includes(".bun\\install\\global")

codex-cli/package-lock.json

@@ -1,18 +0,0 @@
-{
-  "name": "@openai/codex",
-  "version": "0.0.0-dev",
-  "lockfileVersion": 3,
-  "packages": {
-    "": {
-      "name": "@openai/codex",
-      "version": "0.0.0-dev",
-      "license": "Apache-2.0",
-      "bin": {
-        "codex": "bin/codex.js"
-      },
-      "engines": {
-        "node": ">=16"
-      }
-    }
-  }
-}

codex-cli/package.json

@@ -17,5 +17,6 @@
     "type": "git",
     "url": "git+https://github.com/openai/codex.git",
     "directory": "codex-cli"
-  }
+  },
+  "packageManager": "pnpm@10.28.2+sha512.41872f037ad22f7348e3b1debbaf7e867cfd448f2726d9cf74c08f19507c31d2c8e7a11525b983febc2df640b5438dee6023ebb1f84ed43cc2d654d2bc326264"
 }

codex-rs/BUILD.bazel

@@ -0,0 +1 @@
+

codex-rs/Cargo.toml

@@ -11,6 +11,7 @@ members = [
     "arg0",
     "feedback",
     "codex-backend-openapi-models",
+    "cloud-requirements",
     "cloud-tasks",
     "cloud-tasks-client",
     "cli",
@@ -27,6 +28,7 @@ members = [
     "login",
     "mcp-server",
     "mcp-types",
+    "network-proxy",
     "ollama",
     "process-hardening",
     "protocol",
@@ -35,18 +37,19 @@ members = [
     "stdio-to-uds",
     "otel",
     "tui",
-    "tui2",
     "utils/absolute-path",
     "utils/cargo-bin",
     "utils/git",
     "utils/cache",
     "utils/image",
     "utils/json-to-toml",
+    "utils/home-dir",
     "utils/pty",
     "utils/readiness",
     "utils/string",
     "codex-client",
     "codex-api",
+    "state",
 ]
 resolver = "2"
 
@@ -70,7 +73,9 @@ codex-apply-patch = { path = "apply-patch" }
 codex-arg0 = { path = "arg0" }
 codex-async-utils = { path = "async-utils" }
 codex-backend-client = { path = "backend-client" }
+codex-cloud-requirements = { path = "cloud-requirements" }
 codex-chatgpt = { path = "chatgpt" }
+codex-cli = { path = "cli"}
 codex-client = { path = "codex-client" }
 codex-common = { path = "common" }
 codex-core = { path = "core" }
@@ -90,14 +95,15 @@ codex-process-hardening = { path = "process-hardening" }
 codex-protocol = { path = "protocol" }
 codex-responses-api-proxy = { path = "responses-api-proxy" }
 codex-rmcp-client = { path = "rmcp-client" }
+codex-state = { path = "state" }
 codex-stdio-to-uds = { path = "stdio-to-uds" }
 codex-tui = { path = "tui" }
-codex-tui2 = { path = "tui2" }
 codex-utils-absolute-path = { path = "utils/absolute-path" }
 codex-utils-cache = { path = "utils/cache" }
 codex-utils-cargo-bin = { path = "utils/cargo-bin" }
 codex-utils-image = { path = "utils/image" }
 codex-utils-json-to-toml = { path = "utils/json-to-toml" }
+codex-utils-home-dir = { path = "utils/home-dir" }
 codex-utils-pty = { path = "utils/pty" }
 codex-utils-readiness = { path = "utils/readiness" }
 codex-utils-string = { path = "utils/string" }
@@ -121,12 +127,13 @@ axum = { version = "0.8", default-features = false }
 base64 = "0.22.1"
 bytes = "1.10.1"
 chardetng = "0.1.17"
-chrono = "0.4.42"
+chrono = "0.4.43"
 clap = "4"
 clap_complete = "4"
 color-eyre = "0.6.3"
 crossterm = "0.28.1"
-ctor = "0.5.0"
+crossbeam-channel = "0.5.15"
+ctor = "0.6.3"
 derive_more = "2"
 diffy = "0.4.2"
 dirs = "6"
@@ -137,11 +144,13 @@ env-flags = "0.1.1"
 env_logger = "0.11.5"
 eventsource-stream = "0.2.3"
 futures = { version = "0.3", default-features = false }
+globset = "0.4"
 http = "1.3.1"
 icu_decimal = "2.1"
 icu_locale_core = "2.1"
 icu_provider = { version = "2.1", features = ["sync"] }
 ignore = "0.4.23"
+indoc = "2.0"
 image = { version = "^0.25.9", default-features = false }
 include_dir = "0.7.4"
 indexmap = "2.12.0"
@@ -157,7 +166,7 @@ maplit = "1.0.2"
 mime_guess = "2.0.5"
 multimap = "0.10.0"
 notify = "8.2.0"
-nucleo-matcher = "0.3.1"
+nucleo = { git = "https://github.com/helix-editor/nucleo.git", rev = "4253de9faabb4e5c6d81d946a5e35a90f87347ee" }
 once_cell = "1.20.2"
 openssl-sys = "*"
 opentelemetry = "0.31.0"
@@ -176,25 +185,28 @@ pretty_assertions = "1.4.1"
 pulldown-cmark = "0.10"
 rand = "0.9"
 ratatui = "0.29.0"
-ratatui-core = "0.1.0"
 ratatui-macros = "0.6.0"
 regex = "1.12.2"
 regex-lite = "0.1.8"
 reqwest = "0.12"
 rmcp = { version = "0.12.0", default-features = false }
+runfiles = { git = "https://github.com/dzbarsky/rules_rust", rev = "b56cbaa8465e74127f1ea216f813cd377295ad81" }
 schemars = "0.8.22"
 seccompiler = "0.5.0"
 sentry = "0.46.0"
 serde = "1"
 serde_json = "1"
+serde_path_to_error = "0.1.20"
 serde_with = "3.16"
 serde_yaml = "0.9"
 serial_test = "3.2.0"
 sha1 = "0.10.6"
 sha2 = "0.10"
+semver = "1.0"
 shlex = "1.3.0"
 similar = "2.7.0"
 socket2 = "0.6.1"
+sqlx = { version = "0.8.6", default-features = false, features = ["chrono", "json", "macros", "migrate", "runtime-tokio-rustls", "sqlite", "time", "uuid"] }
 starlark = "0.13.0"
 strum = "0.27.2"
 strum_macros = "0.27.2"
@@ -209,10 +221,11 @@ tiny_http = "0.12"
 tokio = "1"
 tokio-stream = "0.1.18"
 tokio-test = "0.4"
-tokio-util = "0.7.16"
+tokio-tungstenite = { version = "0.28.0", features = ["proxy", "rustls-tls-native-roots"] }
+tokio-util = "0.7.18"
 toml = "0.9.5"
 toml_edit = "0.24.0"
-tracing = "0.1.43"
+tracing = "0.1.44"
 tracing-appender = "0.2.3"
 tracing-subscriber = "0.3.22"
 tracing-test = "0.2.5"
@@ -221,7 +234,6 @@ tree-sitter-bash = "0.25"
 zstd = "0.13"
 tree-sitter-highlight = "0.25.10"
 ts-rs = "11"
-tui-scrollbar = "0.2.1"
 uds_windows = "1.1.0"
 unicode-segmentation = "1.12.0"
 unicode-width = "0.2"
@@ -231,7 +243,7 @@ uuid = "1"
 vt100 = "0.16.2"
 walkdir = "2.5.0"
 webbrowser = "1.0"
-which = "6"
+which = "8"
 wildmatch = "2.6.1"
 
 wiremock = "0.6"
@@ -299,6 +311,10 @@ opt-level = 0
 # 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" }
+tokio-tungstenite = { git = "https://github.com/JakkuSakura/tokio-tungstenite", rev = "2ae536b0de793f3ddf31fc2f22d445bf1ef2023d" }
 
 # Uncomment to debug local changes.
 # rmcp = { path = "../../rust-sdk/crates/rmcp" }
+
+[patch."ssh://git@github.com/JakkuSakura/tungstenite-rs.git"]
+tungstenite = { git = "https://github.com/JakkuSakura/tungstenite-rs", rev = "f514de8644821113e5d18a027d6d28a5c8cc0a6e" }

codex-rs/ansi-escape/BUILD.bazel

@@ -0,0 +1,6 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "ansi-escape",
+    crate_name = "codex_ansi_escape",
+)

codex-rs/app-server-protocol/BUILD.bazel

@@ -0,0 +1,6 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "app-server-protocol",
+    crate_name = "codex_app_server_protocol",
+)

codex-rs/app-server-protocol/src/protocol/common.rs

@@ -23,11 +23,22 @@ impl GitSha {
     }
 }
 
+/// Authentication mode for OpenAI-backed providers.
 #[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, Display, JsonSchema, TS)]
 #[serde(rename_all = "lowercase")]
 pub enum AuthMode {
+    /// OpenAI API key provided by the caller and stored by Codex.
     ApiKey,
-    ChatGPT,
+    /// ChatGPT OAuth managed by Codex (tokens persisted and refreshed by Codex).
+    Chatgpt,
+    /// [UNSTABLE] FOR OPENAI INTERNAL USE ONLY - DO NOT USE.
+    ///
+    /// ChatGPT auth tokens are supplied by an external host app and are only
+    /// stored in memory. Token refresh must be handled by the external host app.
+    #[serde(rename = "chatgptAuthTokens")]
+    #[ts(rename = "chatgptAuthTokens")]
+    #[strum(serialize = "chatgptAuthTokens")]
+    ChatgptAuthTokens,
 }
 
 /// Generates an `enum ClientRequest` where each variant is a request that the
@@ -117,6 +128,14 @@ client_request_definitions! {
         params: v2::ThreadArchiveParams,
         response: v2::ThreadArchiveResponse,
     },
+    ThreadSetName => "thread/name/set" {
+        params: v2::ThreadSetNameParams,
+        response: v2::ThreadSetNameResponse,
+    },
+    ThreadUnarchive => "thread/unarchive" {
+        params: v2::ThreadUnarchiveParams,
+        response: v2::ThreadUnarchiveResponse,
+    },
     ThreadRollback => "thread/rollback" {
         params: v2::ThreadRollbackParams,
         response: v2::ThreadRollbackResponse,
@@ -129,10 +148,22 @@ client_request_definitions! {
         params: v2::ThreadLoadedListParams,
         response: v2::ThreadLoadedListResponse,
     },
+    ThreadRead => "thread/read" {
+        params: v2::ThreadReadParams,
+        response: v2::ThreadReadResponse,
+    },
     SkillsList => "skills/list" {
         params: v2::SkillsListParams,
         response: v2::SkillsListResponse,
     },
+    AppsList => "app/list" {
+        params: v2::AppsListParams,
+        response: v2::AppsListResponse,
+    },
+    SkillsConfigWrite => "skills/config/write" {
+        params: v2::SkillsConfigWriteParams,
+        response: v2::SkillsConfigWriteResponse,
+    },
     TurnStart => "turn/start" {
         params: v2::TurnStartParams,
         response: v2::TurnStartResponse,
@@ -150,12 +181,22 @@ client_request_definitions! {
         params: v2::ModelListParams,
         response: v2::ModelListResponse,
     },
+    /// EXPERIMENTAL - list collaboration mode presets.
+    CollaborationModeList => "collaborationMode/list" {
+        params: v2::CollaborationModeListParams,
+        response: v2::CollaborationModeListResponse,
+    },
 
     McpServerOauthLogin => "mcpServer/oauth/login" {
         params: v2::McpServerOauthLoginParams,
         response: v2::McpServerOauthLoginResponse,
     },
 
+    McpServerRefresh => "config/mcpServer/reload" {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v2::McpServerRefreshResponse,
+    },
+
     McpServerStatusList => "mcpServerStatus/list" {
         params: v2::ListMcpServerStatusParams,
         response: v2::ListMcpServerStatusResponse,
@@ -496,6 +537,23 @@ server_request_definitions! {
         response: v2::FileChangeRequestApprovalResponse,
     },
 
+    /// EXPERIMENTAL - Request input from the user for a tool call.
+    ToolRequestUserInput => "item/tool/requestUserInput" {
+        params: v2::ToolRequestUserInputParams,
+        response: v2::ToolRequestUserInputResponse,
+    },
+
+    /// Execute a dynamic tool call on the client.
+    DynamicToolCall => "item/tool/call" {
+        params: v2::DynamicToolCallParams,
+        response: v2::DynamicToolCallResponse,
+    },
+
+    ChatgptAuthTokensRefresh => "account/chatgptAuthTokens/refresh" {
+        params: v2::ChatgptAuthTokensRefreshParams,
+        response: v2::ChatgptAuthTokensRefreshResponse,
+    },
+
     /// DEPRECATED APIs below
     /// Request to approve a patch.
     /// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
@@ -540,6 +598,7 @@ server_notification_definitions! {
     /// NEW NOTIFICATIONS
     Error => "error" (v2::ErrorNotification),
     ThreadStarted => "thread/started" (v2::ThreadStartedNotification),
+    ThreadNameUpdated => "thread/name/updated" (v2::ThreadNameUpdatedNotification),
     ThreadTokenUsageUpdated => "thread/tokenUsage/updated" (v2::ThreadTokenUsageUpdatedNotification),
     TurnStarted => "turn/started" (v2::TurnStartedNotification),
     TurnCompleted => "turn/completed" (v2::TurnCompletedNotification),
@@ -550,6 +609,8 @@ server_notification_definitions! {
     /// This event is internal-only. Used by Codex Cloud.
     RawResponseItemCompleted => "rawResponseItem/completed" (v2::RawResponseItemCompletedNotification),
     AgentMessageDelta => "item/agentMessage/delta" (v2::AgentMessageDeltaNotification),
+    /// EXPERIMENTAL - proposed plan streaming deltas for plan items.
+    PlanDelta => "item/plan/delta" (v2::PlanDeltaNotification),
     CommandExecutionOutputDelta => "item/commandExecution/outputDelta" (v2::CommandExecutionOutputDeltaNotification),
     TerminalInteraction => "item/commandExecution/terminalInteraction" (v2::TerminalInteractionNotification),
     FileChangeOutputDelta => "item/fileChange/outputDelta" (v2::FileChangeOutputDeltaNotification),
@@ -560,8 +621,10 @@ server_notification_definitions! {
     ReasoningSummaryTextDelta => "item/reasoning/summaryTextDelta" (v2::ReasoningSummaryTextDeltaNotification),
     ReasoningSummaryPartAdded => "item/reasoning/summaryPartAdded" (v2::ReasoningSummaryPartAddedNotification),
     ReasoningTextDelta => "item/reasoning/textDelta" (v2::ReasoningTextDeltaNotification),
+    /// Deprecated: Use `ContextCompaction` item type instead.
     ContextCompacted => "thread/compacted" (v2::ContextCompactedNotification),
     DeprecationNotice => "deprecationNotice" (v2::DeprecationNoticeNotification),
+    ConfigWarning => "configWarning" (v2::ConfigWarningNotification),
 
     /// Notifies the user of world-writable directories on Windows, which cannot be protected by the sandbox.
     WindowsWorldWritableWarning => "windows/worldWritableWarning" (v2::WindowsWorldWritableWarningNotification),
@@ -713,6 +776,29 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn serialize_chatgpt_auth_tokens_refresh_request() -> Result<()> {
+        let request = ServerRequest::ChatgptAuthTokensRefresh {
+            request_id: RequestId::Integer(8),
+            params: v2::ChatgptAuthTokensRefreshParams {
+                reason: v2::ChatgptAuthTokensRefreshReason::Unauthorized,
+                previous_account_id: Some("org-123".to_string()),
+            },
+        };
+        assert_eq!(
+            json!({
+                "method": "account/chatgptAuthTokens/refresh",
+                "id": 8,
+                "params": {
+                    "reason": "unauthorized",
+                    "previousAccountId": "org-123"
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
     #[test]
     fn serialize_get_account_rate_limits() -> Result<()> {
         let request = ClientRequest::GetAccountRateLimits {
@@ -802,10 +888,34 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn serialize_account_login_chatgpt_auth_tokens() -> Result<()> {
+        let request = ClientRequest::LoginAccount {
+            request_id: RequestId::Integer(5),
+            params: v2::LoginAccountParams::ChatgptAuthTokens {
+                access_token: "access-token".to_string(),
+                id_token: "id-token".to_string(),
+            },
+        };
+        assert_eq!(
+            json!({
+                "method": "account/login/start",
+                "id": 5,
+                "params": {
+                    "type": "chatgptAuthTokens",
+                    "accessToken": "access-token",
+                    "idToken": "id-token"
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
     #[test]
     fn serialize_get_account() -> Result<()> {
         let request = ClientRequest::GetAccount {
-            request_id: RequestId::Integer(5),
+            request_id: RequestId::Integer(6),
             params: v2::GetAccountParams {
                 refresh_token: false,
             },
@@ -813,7 +923,7 @@ mod tests {
         assert_eq!(
             json!({
                 "method": "account/read",
-                "id": 5,
+                "id": 6,
                 "params": {
                     "refreshToken": false
                 }
@@ -868,4 +978,21 @@ mod tests {
         );
         Ok(())
     }
+
+    #[test]
+    fn serialize_list_collaboration_modes() -> Result<()> {
+        let request = ClientRequest::CollaborationModeList {
+            request_id: RequestId::Integer(7),
+            params: v2::CollaborationModeListParams::default(),
+        };
+        assert_eq!(
+            json!({
+                "method": "collaborationMode/list",
+                "id": 7,
+                "params": {}
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
 }

codex-rs/app-server-protocol/src/protocol/thread_history.rs

@@ -6,6 +6,7 @@ use crate::protocol::v2::UserInput;
 use codex_protocol::protocol::AgentReasoningEvent;
 use codex_protocol::protocol::AgentReasoningRawContentEvent;
 use codex_protocol::protocol::EventMsg;
+use codex_protocol::protocol::ItemCompletedEvent;
 use codex_protocol::protocol::ThreadRolledBackEvent;
 use codex_protocol::protocol::TurnAbortedEvent;
 use codex_protocol::protocol::UserMessageEvent;
@@ -55,6 +56,7 @@ impl ThreadHistoryBuilder {
             EventMsg::AgentReasoningRawContent(payload) => {
                 self.handle_agent_reasoning_raw_content(payload)
             }
+            EventMsg::ItemCompleted(payload) => self.handle_item_completed(payload),
             EventMsg::TokenCount(_) => {}
             EventMsg::EnteredReviewMode(_) => {}
             EventMsg::ExitedReviewMode(_) => {}
@@ -125,6 +127,19 @@ impl ThreadHistoryBuilder {
         });
     }
 
+    fn handle_item_completed(&mut self, payload: &ItemCompletedEvent) {
+        if let codex_protocol::items::TurnItem::Plan(plan) = &payload.item {
+            if plan.text.is_empty() {
+                return;
+            }
+            let id = self.next_item_id();
+            self.ensure_turn().items.push(ThreadItem::Plan {
+                id,
+                text: plan.text.clone(),
+            });
+        }
+    }
+
     fn handle_turn_aborted(&mut self, _payload: &TurnAbortedEvent) {
         let Some(turn) = self.current_turn.as_mut() else {
             return;
@@ -197,6 +212,12 @@ impl ThreadHistoryBuilder {
         if !payload.message.trim().is_empty() {
             content.push(UserInput::Text {
                 text: payload.message.clone(),
+                text_elements: payload
+                    .text_elements
+                    .iter()
+                    .cloned()
+                    .map(Into::into)
+                    .collect(),
             });
         }
         if let Some(images) = &payload.images {
@@ -204,6 +225,9 @@ impl ThreadHistoryBuilder {
                 content.push(UserInput::Image { url: image.clone() });
             }
         }
+        for path in &payload.local_images {
+            content.push(UserInput::LocalImage { path: path.clone() });
+        }
         content
     }
 }
@@ -244,6 +268,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "First turn".into(),
                 images: Some(vec!["https://example.com/one.png".into()]),
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "Hi there".into(),
@@ -257,6 +283,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Second turn".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "Reply two".into(),
@@ -277,6 +305,7 @@ mod tests {
                 content: vec![
                     UserInput::Text {
                         text: "First turn".into(),
+                        text_elements: Vec::new(),
                     },
                     UserInput::Image {
                         url: "https://example.com/one.png".into(),
@@ -308,7 +337,8 @@ mod tests {
             ThreadItem::UserMessage {
                 id: "item-4".into(),
                 content: vec![UserInput::Text {
-                    text: "Second turn".into()
+                    text: "Second turn".into(),
+                    text_elements: Vec::new(),
                 }],
             }
         );
@@ -327,6 +357,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Turn start".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentReasoning(AgentReasoningEvent {
                 text: "first summary".into(),
@@ -371,6 +403,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Please do the thing".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "Working...".into(),
@@ -381,6 +415,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Let's try again".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "Second attempt complete.".into(),
@@ -398,7 +434,8 @@ mod tests {
             ThreadItem::UserMessage {
                 id: "item-1".into(),
                 content: vec![UserInput::Text {
-                    text: "Please do the thing".into()
+                    text: "Please do the thing".into(),
+                    text_elements: Vec::new(),
                 }],
             }
         );
@@ -418,7 +455,8 @@ mod tests {
             ThreadItem::UserMessage {
                 id: "item-3".into(),
                 content: vec![UserInput::Text {
-                    text: "Let's try again".into()
+                    text: "Let's try again".into(),
+                    text_elements: Vec::new(),
                 }],
             }
         );
@@ -437,6 +475,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "First".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "A1".into(),
@@ -444,6 +484,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Second".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "A2".into(),
@@ -452,6 +494,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Third".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "A3".into(),
@@ -469,6 +513,7 @@ mod tests {
                         id: "item-1".into(),
                         content: vec![UserInput::Text {
                             text: "First".into(),
+                            text_elements: Vec::new(),
                         }],
                     },
                     ThreadItem::AgentMessage {
@@ -486,6 +531,7 @@ mod tests {
                         id: "item-3".into(),
                         content: vec![UserInput::Text {
                             text: "Third".into(),
+                            text_elements: Vec::new(),
                         }],
                     },
                     ThreadItem::AgentMessage {
@@ -504,6 +550,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "One".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "A1".into(),
@@ -511,6 +559,8 @@ mod tests {
             EventMsg::UserMessage(UserMessageEvent {
                 message: "Two".into(),
                 images: None,
+                text_elements: Vec::new(),
+                local_images: Vec::new(),
             }),
             EventMsg::AgentMessage(AgentMessageEvent {
                 message: "A2".into(),

codex-rs/app-server-protocol/src/protocol/v1.rs

@@ -16,6 +16,8 @@ use codex_protocol::protocol::ReviewDecision;
 use codex_protocol::protocol::SandboxPolicy;
 use codex_protocol::protocol::SessionSource;
 use codex_protocol::protocol::TurnAbortReason;
+use codex_protocol::user_input::ByteRange as CoreByteRange;
+use codex_protocol::user_input::TextElement as CoreTextElement;
 use codex_utils_absolute_path::AbsolutePathBuf;
 use schemars::JsonSchema;
 use serde::Deserialize;
@@ -126,6 +128,7 @@ pub struct ConversationSummary {
     pub path: PathBuf,
     pub preview: String,
     pub timestamp: Option<String>,
+    pub updated_at: Option<String>,
     pub model_provider: String,
     pub cwd: PathBuf,
     pub cli_version: String,
@@ -444,9 +447,71 @@ pub struct RemoveConversationListenerParams {
 #[serde(rename_all = "camelCase")]
 #[serde(tag = "type", content = "data")]
 pub enum InputItem {
-    Text { text: String },
-    Image { image_url: String },
-    LocalImage { path: PathBuf },
+    Text {
+        text: String,
+        /// UI-defined spans within `text` used to render or persist special elements.
+        #[serde(default)]
+        text_elements: Vec<V1TextElement>,
+    },
+    Image {
+        image_url: String,
+    },
+    LocalImage {
+        path: PathBuf,
+    },
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(rename = "ByteRange")]
+pub struct V1ByteRange {
+    /// Start byte offset (inclusive) within the UTF-8 text buffer.
+    pub start: usize,
+    /// End byte offset (exclusive) within the UTF-8 text buffer.
+    pub end: usize,
+}
+
+impl From<CoreByteRange> for V1ByteRange {
+    fn from(value: CoreByteRange) -> Self {
+        Self {
+            start: value.start,
+            end: value.end,
+        }
+    }
+}
+
+impl From<V1ByteRange> for CoreByteRange {
+    fn from(value: V1ByteRange) -> Self {
+        Self {
+            start: value.start,
+            end: value.end,
+        }
+    }
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(rename = "TextElement")]
+pub struct V1TextElement {
+    /// Byte range in the parent `text` buffer that this element occupies.
+    pub byte_range: V1ByteRange,
+    /// Optional human-readable placeholder for the element, displayed in the UI.
+    pub placeholder: Option<String>,
+}
+
+impl From<CoreTextElement> for V1TextElement {
+    fn from(value: CoreTextElement) -> Self {
+        Self {
+            byte_range: value.byte_range.into(),
+            placeholder: value._placeholder_for_conversion_only().map(str::to_string),
+        }
+    }
+}
+
+impl From<V1TextElement> for CoreTextElement {
+    fn from(value: V1TextElement) -> Self {
+        Self::new(value.byte_range.into(), value.placeholder)
+    }
 }
 
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]

codex-rs/app-server-test-client/BUILD.bazel

@@ -0,0 +1,6 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "codex-app-server-test-client",
+    crate_name = "codex_app_server_test_client",
+)

codex-rs/app-server-test-client/src/main.rs

@@ -256,7 +256,11 @@ fn send_message_v2_with_policies(
     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 }],
+        input: vec![V2UserInput::Text {
+            text: user_message,
+            // Test client sends plain text without UI element ranges.
+            text_elements: Vec::new(),
+        }],
         ..Default::default()
     };
     turn_params.approval_policy = approval_policy;
@@ -288,6 +292,8 @@ fn send_follow_up_v2(
         thread_id: thread_response.thread.id.clone(),
         input: vec![V2UserInput::Text {
             text: first_message,
+            // Test client sends plain text without UI element ranges.
+            text_elements: Vec::new(),
         }],
         ..Default::default()
     };
@@ -299,6 +305,8 @@ fn send_follow_up_v2(
         thread_id: thread_response.thread.id.clone(),
         input: vec![V2UserInput::Text {
             text: follow_up_message,
+            // Test client sends plain text without UI element ranges.
+            text_elements: Vec::new(),
         }],
         ..Default::default()
     };
@@ -471,6 +479,8 @@ impl CodexClient {
                 conversation_id: *conversation_id,
                 items: vec![InputItem::Text {
                     text: message.to_string(),
+                    // Test client sends plain text without UI element ranges.
+                    text_elements: Vec::new(),
                 }],
             },
         };
@@ -545,7 +555,7 @@ impl CodexClient {
                         print!("{}", event.delta);
                         std::io::stdout().flush().ok();
                     }
-                    EventMsg::TaskComplete(event) => {
+                    EventMsg::TurnComplete(event) => {
                         println!("\n[task complete: {event:?}]");
                         break;
                     }
@@ -832,6 +842,9 @@ impl CodexClient {
             turn_id,
             item_id,
             reason,
+            command,
+            cwd,
+            command_actions,
             proposed_execpolicy_amendment,
         } = params;
 
@@ -841,6 +854,17 @@ impl CodexClient {
         if let Some(reason) = reason.as_deref() {
             println!("< reason: {reason}");
         }
+        if let Some(command) = command.as_deref() {
+            println!("< command: {command}");
+        }
+        if let Some(cwd) = cwd.as_ref() {
+            println!("< cwd: {}", cwd.display());
+        }
+        if let Some(command_actions) = command_actions.as_ref()
+            && !command_actions.is_empty()
+        {
+            println!("< command actions: {command_actions:?}");
+        }
         if let Some(execpolicy_amendment) = proposed_execpolicy_amendment.as_ref() {
             println!("< proposed execpolicy amendment: {execpolicy_amendment:?}");
         }

codex-rs/app-server/BUILD.bazel

@@ -0,0 +1,8 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "app-server",
+    crate_name = "codex_app_server",
+    integration_deps_extra = ["//codex-rs/app-server/tests/common:common"],
+    test_tags = ["no-sandbox"],
+)

codex-rs/app-server/Cargo.toml

@@ -17,11 +17,14 @@ workspace = true
 
 [dependencies]
 anyhow = { workspace = true }
+async-trait = { workspace = true }
 codex-arg0 = { workspace = true }
+codex-cloud-requirements = { workspace = true }
 codex-common = { workspace = true, features = ["cli"] }
 codex-core = { workspace = true }
 codex-backend-client = { workspace = true }
 codex-file-search = { workspace = true }
+codex-chatgpt = { workspace = true }
 codex-login = { workspace = true }
 codex-protocol = { workspace = true }
 codex-app-server-protocol = { workspace = true }
@@ -34,6 +37,7 @@ serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
 mcp-types = { workspace = true }
 tempfile = { workspace = true }
+time = { workspace = true }
 toml = { workspace = true }
 tokio = { workspace = true, features = [
     "io-std",
@@ -48,11 +52,21 @@ uuid = { workspace = true, features = ["serde", "v7"] }
 
 [dev-dependencies]
 app_test_support = { workspace = true }
+axum = { workspace = true, default-features = false, features = [
+    "http1",
+    "json",
+    "tokio",
+] }
 base64 = { workspace = true }
+codex-execpolicy = { workspace = true }
 core_test_support = { workspace = true }
 mcp-types = { workspace = true }
 os_info = { workspace = true }
 pretty_assertions = { workspace = true }
+rmcp = { workspace = true, default-features = false, features = [
+    "server",
+    "transport-streamable-http-server",
+] }
 serial_test = { workspace = true }
 wiremock = { workspace = true }
 shlex = { workspace = true }

codex-rs/app-server/README.md

@@ -13,6 +13,7 @@
 - [Events](#events)
 - [Approvals](#approvals)
 - [Skills](#skills)
+- [Apps](#apps)
 - [Auth endpoints](#auth-endpoints)
 
 ## Protocol
@@ -52,6 +53,10 @@ Clients must send a single `initialize` request before invoking any other method
 
 Applications building on top of `codex app-server` should identify themselves via the `clientInfo` parameter.
 
+**Important**: `clientInfo.name` is used to identify the client for the OpenAI Compliance Logs Platform. If
+you are developing a new Codex integration that is intended for enterprise use, please contact us to get it
+added to a known clients list. For more context: https://chatgpt.com/admin/api-reference#tag/Logs:-Codex
+
 Example (from OpenAI's official VSCode extension):
 
 ```json
@@ -60,7 +65,7 @@ Example (from OpenAI's official VSCode extension):
   "id": 0,
   "params": {
     "clientInfo": {
-      "name": "codex-vscode",
+      "name": "codex_vscode",
       "title": "Codex VS Code Extension",
       "version": "0.1.0"
     }
@@ -75,22 +80,30 @@ Example (from OpenAI's official VSCode extension):
 - `thread/fork` — fork an existing thread into a new thread id by copying the stored history; emits `thread/started` and auto-subscribes you to turn/item events for the new thread.
 - `thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
 - `thread/loaded/list` — list the thread ids currently loaded in memory.
+- `thread/read` — read a stored thread by id without resuming it; optionally include turns via `includeTurns`.
 - `thread/archive` — move a thread’s rollout file into the archived directory; returns `{}` on success.
+- `thread/name/set` — set or update a thread’s user-facing name; returns `{}` on success. Thread names are not required to be unique; name lookups resolve to the most recently updated thread.
+- `thread/unarchive` — move an archived rollout file back into the sessions directory; returns the restored `thread` on success.
 - `thread/rollback` — drop the last N turns from the agent’s in-memory context and persist a rollback marker in the rollout so future resumes see the pruned history; returns the updated `thread` (with `turns` populated) 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 Codex’s automated reviewer for a thread; responds like `turn/start` and emits `item/started`/`item/completed` notifications with `enteredReviewMode` and `exitedReviewMode` items, plus a final assistant `agentMessage` containing the review.
 - `command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
 - `model/list` — list available models (with reasoning effort options).
+- `collaborationMode/list` — list available collaboration mode presets (experimental, no pagination).
 - `skills/list` — list skills for one or more `cwd` values (optional `forceReload`).
+- `app/list` — list available apps.
+- `skills/config/write` — write user-level skill config by path.
 - `mcpServer/oauth/login` — start an OAuth login for a configured MCP server; returns an `authorization_url` and later emits `mcpServer/oauthLogin/completed` once the browser flow finishes.
+- `tool/requestUserInput` — prompt the user with 1–3 short questions for a tool call and return their answers (experimental).
+- `config/mcpServer/reload` — reload MCP server config from disk and queue a refresh for loaded threads (applied on each thread's next active turn); returns `{}`. Use this after editing `config.toml` without restarting the server.
 - `mcpServerStatus/list` — enumerate configured MCP servers with their tools, resources, resource templates, and auth status; supports cursor+limit pagination.
 - `feedback/upload` — submit a feedback report (classification + optional reason/logs and conversation_id); returns the tracking thread id.
 - `command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
 - `config/read` — fetch the effective config on disk after resolving config layering.
 - `config/value/write` — write a single config key/value to the user's config.toml on disk.
 - `config/batchWrite` — apply multiple config edits atomically to the user's config.toml on disk.
-- `configRequirements/read` — fetch the loaded requirements allow-lists from `requirements.toml` and/or MDM (or `null` if none are configured).
+- `configRequirements/read` — fetch the loaded requirements allow-lists and `enforceResidency` from `requirements.toml` and/or MDM (or `null` if none are configured).
 
 ### Example: Start or resume a thread
 
@@ -104,6 +117,20 @@ Start a fresh thread when you need a new Codex conversation.
     "cwd": "/Users/me/project",
     "approvalPolicy": "never",
     "sandbox": "workspaceWrite",
+    "personality": "friendly",
+    "dynamicTools": [
+        {
+            "name": "lookup_ticket",
+            "description": "Fetch a ticket by id",
+            "inputSchema": {
+                "type": "object",
+                "properties": {
+                    "id": { "type": "string" }
+                },
+                "required": ["id"]
+            }
+        }
+    ],
 } }
 { "id": 10, "result": {
     "thread": {
@@ -116,10 +143,13 @@ Start a fresh thread when you need a new Codex conversation.
 { "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:
+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. You can also pass the same configuration overrides supported by `thread/start`, such as `personality`:
 
 ```json
-{ "method": "thread/resume", "id": 11, "params": { "threadId": "thr_123" } }
+{ "method": "thread/resume", "id": 11, "params": {
+    "threadId": "thr_123",
+    "personality": "friendly"
+} }
 { "id": 11, "result": { "thread": { "id": "thr_123", … } } }
 ```
 
@@ -133,11 +163,14 @@ To branch from a stored session, call `thread/fork` with the `thread.id`. This c
 
 ### Example: List threads (with pagination & filters)
 
-`thread/list` lets you render a history UI. Pass any combination of:
+`thread/list` lets you render a history UI. Results default to `createdAt` (newest first) descending. 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.
+- `sortKey` — `created_at` (default) or `updated_at`.
 - `modelProviders` — restrict results to specific providers; unset, null, or an empty array will include all providers.
+- `sourceKinds` — restrict results to specific sources; omit or pass `[]` for interactive sessions only (`cli`, `vscode`).
+- `archived` — when `true`, list archived threads only. When `false` or `null`, list non-archived threads (default).
 
 Example:
 
@@ -145,11 +178,12 @@ Example:
 { "method": "thread/list", "id": 20, "params": {
     "cursor": null,
     "limit": 25,
+    "sortKey": "created_at"
 } }
 { "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 }
+        { "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111 },
+        { "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000 }
     ],
     "nextCursor": "opaque-token-or-null"
 } }
@@ -168,6 +202,20 @@ When `nextCursor` is `null`, you’ve reached the final page.
 } }
 ```
 
+### Example: Read a thread
+
+Use `thread/read` to fetch a stored thread by id without resuming it. Pass `includeTurns` when you want the rollout history loaded into `thread.turns`.
+
+```json
+{ "method": "thread/read", "id": 22, "params": { "threadId": "thr_123" } }
+{ "id": 22, "result": { "thread": { "id": "thr_123", "turns": [] } } }
+```
+
+```json
+{ "method": "thread/read", "id": 23, "params": { "threadId": "thr_123", "includeTurns": true } }
+{ "id": 23, "result": { "thread": { "id": "thr_123", "turns": [ ... ] } } }
+```
+
 ### Example: Archive a thread
 
 Use `thread/archive` to move the persisted rollout (stored as a JSONL file on disk) into the archived sessions directory.
@@ -177,7 +225,16 @@ Use `thread/archive` to move the persisted rollout (stored as a JSONL file on di
 { "id": 21, "result": {} }
 ```
 
-An archived thread will not appear in future calls to `thread/list`.
+An archived thread will not appear in `thread/list` unless `archived` is set to `true`.
+
+### Example: Unarchive a thread
+
+Use `thread/unarchive` to move an archived rollout back into the sessions directory.
+
+```json
+{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }
+{ "id": 24, "result": { "thread": { "id": "thr_b" } } }
+```
 
 ### Example: Start a turn (send user input)
 
@@ -204,6 +261,7 @@ You can optionally specify config overrides on the new turn. If specified, these
     "model": "gpt-5.1-codex",
     "effort": "medium",
     "summary": "concise",
+    "personality": "friendly",
     // Optional JSON Schema to constrain the final assistant message for this turn.
     "outputSchema": {
         "type": "object",
@@ -240,6 +298,26 @@ Invoke a skill explicitly by including `$<skill-name>` in the text input and add
 } } }
 ```
 
+### Example: Start a turn (invoke an app)
+
+Invoke an app by including `$<app-slug>` in the text input and adding a `mention` input item with the app id in `app://<connector-id>` form.
+
+```json
+{ "method": "turn/start", "id": 34, "params": {
+    "threadId": "thr_123",
+    "input": [
+        { "type": "text", "text": "$demo-app Summarize the latest updates." },
+        { "type": "mention", "name": "Demo App", "path": "app://demo-app" }
+    ]
+} }
+{ "id": 34, "result": { "turn": {
+    "id": "turn_458",
+    "status": "inProgress",
+    "items": [],
+    "error": null
+} } }
+```
+
 ### Example: Interrupt an active turn
 
 You can cancel a running Turn with `turn/interrupt`.
@@ -366,15 +444,18 @@ Today both notifications carry an empty `items` array even when item events were
 
 - `userMessage` — `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).
 - `agentMessage` — `{id, text}` containing the accumulated agent reply.
+- `plan` — `{id, text}` emitted for plan-mode turns; plan text can stream via `item/plan/delta` (experimental).
 - `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).
 - `commandExecution` — `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}` for sandboxed commands; `status` is `inProgress`, `completed`, `failed`, or `declined`.
 - `fileChange` — `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}` and `status` is `inProgress`, `completed`, `failed`, or `declined`.
 - `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.
+- `collabToolCall` — `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}` describing collab tool calls (`spawn_agent`, `send_input`, `wait`, `close_agent`); `status` is `inProgress`, `completed`, or `failed`.
+- `webSearch` — `{id, query, action?}` for a web search request issued by the agent; `action` mirrors the Responses API web_search action payload (`search`, `open_page`, `find_in_page`) and may be omitted until completion.
 - `imageView` — `{id, path}` emitted when the agent invokes the image viewer tool.
 - `enteredReviewMode` — `{id, review}` sent when the reviewer starts; `review` is a short user-facing label such as `"current changes"` or the requested target description.
 - `exitedReviewMode` — `{id, review}` emitted when the reviewer finishes; `review` is the full plain-text review (usually, overall notes plus bullet point findings).
-- `compacted` - `{threadId, turnId}` when codex compacts the conversation history. This can happen automatically.
+- `contextCompaction` — `{id}` emitted when codex compacts the conversation history. This can happen automatically.
+- `compacted` - `{threadId, turnId}` when codex compacts the conversation history. This can happen automatically. **Deprecated:** Use `contextCompaction` instead.
 
 All items emit two shared lifecycle events:
 
@@ -387,6 +468,10 @@ There are additional item-specific events:
 
 - `item/agentMessage/delta` — appends streamed text for the agent message; concatenate `delta` values for the same `itemId` in order to reconstruct the full reply.
 
+#### plan
+
+- `item/plan/delta` — streams proposed plan content for plan items (experimental); concatenate `delta` values for the same plan `itemId`. These deltas correspond to the `<proposed_plan>` block.
+
 #### reasoning
 
 - `item/reasoning/summaryTextDelta` — streams readable reasoning summaries; `summaryIndex` increments when a new summary section opens.
@@ -434,7 +519,7 @@ Certain actions (shell commands or modifying files) may require explicit user ap
 Order of messages:
 
 1. `item/started` — shows the pending `commandExecution` item with `command`, `cwd`, and other fields so you can render the proposed action.
-2. `item/commandExecution/requestApproval` (request) — carries the same `itemId`, `threadId`, `turnId`, optionally `reason` or `risk`, plus `parsedCmd` for friendly display.
+2. `item/commandExecution/requestApproval` (request) — carries the same `itemId`, `threadId`, `turnId`, optionally `reason`, plus `command`, `cwd`, and `commandActions` for friendly display.
 3. Client response — `{ "decision": "accept", "acceptSettings": { "forSession": false } }` or `{ "decision": "decline" }`.
 4. `item/completed` — final `commandExecution` item with `status: "completed" | "failed" | "declined"` and execution output. Render this as the authoritative result.
 
@@ -460,8 +545,15 @@ Invoke a skill by including `$<skill-name>` in the text input. Add a `skill` inp
   "params": {
     "threadId": "thread-1",
     "input": [
-      { "type": "text", "text": "$skill-creator Add a new skill for triaging flaky CI." },
-      { "type": "skill", "name": "skill-creator", "path": "/Users/me/.codex/skills/skill-creator/SKILL.md" }
+      {
+        "type": "text",
+        "text": "$skill-creator Add a new skill for triaging flaky CI."
+      },
+      {
+        "type": "skill",
+        "name": "skill-creator",
+        "path": "/Users/me/.codex/skills/skill-creator/SKILL.md"
+      }
     ]
   }
 }
@@ -475,28 +567,115 @@ Example:
 $skill-creator Add a new skill for triaging flaky CI and include step-by-step usage.
 ```
 
-Use `skills/list` to fetch the available skills (optionally scoped by `cwd` and/or with `forceReload`).
+Use `skills/list` to fetch the available skills (optionally scoped by `cwds`, with `forceReload`).
 
 ```json
 { "method": "skills/list", "id": 25, "params": {
-    "cwd": "/Users/me/project",
+    "cwds": ["/Users/me/project"],
     "forceReload": false
 } }
 { "id": 25, "result": {
-    "skills": [
-        { "name": "skill-creator", "description": "Create or update a Codex skill" }
-    ]
+    "data": [{
+        "cwd": "/Users/me/project",
+        "skills": [
+            {
+              "name": "skill-creator",
+              "description": "Create or update a Codex skill",
+              "enabled": true,
+              "interface": {
+                "displayName": "Skill Creator",
+                "shortDescription": "Create or update a Codex skill",
+                "iconSmall": "icon.svg",
+                "iconLarge": "icon-large.svg",
+                "brandColor": "#111111",
+                "defaultPrompt": "Add a new skill for triaging flaky CI."
+              }
+            }
+        ],
+        "errors": []
+    }]
 } }
 ```
 
+To enable or disable a skill by path:
+
+```json
+{
+  "method": "skills/config/write",
+  "id": 26,
+  "params": {
+    "path": "/Users/me/.codex/skills/skill-creator/SKILL.md",
+    "enabled": false
+  }
+}
+```
+
+## Apps
+
+Use `app/list` to fetch available apps (connectors). Each entry includes metadata like the app `id`, display `name`, `installUrl`, and whether it is currently accessible.
+
+```json
+{ "method": "app/list", "id": 50, "params": {
+    "cursor": null,
+    "limit": 50
+} }
+{ "id": 50, "result": {
+    "data": [
+        {
+            "id": "demo-app",
+            "name": "Demo App",
+            "description": "Example connector for documentation.",
+            "logoUrl": "https://example.com/demo-app.png",
+            "logoUrlDark": null,
+            "distributionChannel": null,
+            "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",
+            "isAccessible": true
+        }
+    ],
+    "nextCursor": null
+} }
+```
+
+Invoke an app by inserting `$<app-slug>` in the text input. The slug is derived from the app name and lowercased with non-alphanumeric characters replaced by `-` (for example, "Demo App" becomes `$demo-app`). Add a `mention` input item (recommended) so the server uses the exact `app://<connector-id>` path rather than guessing by name.
+
+Example:
+
+```
+$demo-app Pull the latest updates from the team.
+```
+
+```json
+{
+  "method": "turn/start",
+  "id": 51,
+  "params": {
+    "threadId": "thread-1",
+    "input": [
+      {
+        "type": "text",
+        "text": "$demo-app Pull the latest updates from the team."
+      },
+      { "type": "mention", "name": "Demo App", "path": "app://demo-app" }
+    ]
+  }
+}
+```
+
 ## 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.
 
+### Authentication modes
+
+Codex supports these authentication modes. The current mode is surfaced in `account/updated` (`authMode`) and can be inferred from `account/read`.
+
+- **API key (`apiKey`)**: Caller supplies an OpenAI API key via `account/login/start` with `type: "apiKey"`. The API key is saved and used for API requests.
+- **ChatGPT managed (`chatgpt`)** (recommended): Codex owns the ChatGPT OAuth flow and refresh tokens. Start via `account/login/start` with `type: "chatgpt"`; Codex persists tokens to disk and refreshes them automatically.
+
 ### API Overview
 
 - `account/read` — fetch current account info; optionally refresh tokens.
-- `account/login/start` — begin login (`apiKey` or `chatgpt`).
+- `account/login/start` — begin login (`apiKey`, `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`.

codex-rs/app-server/src/bespoke_event_handling.rs

@@ -14,6 +14,9 @@ use codex_app_server_protocol::AgentMessageDeltaNotification;
 use codex_app_server_protocol::ApplyPatchApprovalParams;
 use codex_app_server_protocol::ApplyPatchApprovalResponse;
 use codex_app_server_protocol::CodexErrorInfo as V2CodexErrorInfo;
+use codex_app_server_protocol::CollabAgentState as V2CollabAgentStatus;
+use codex_app_server_protocol::CollabAgentTool;
+use codex_app_server_protocol::CollabAgentToolCallStatus as V2CollabToolCallStatus;
 use codex_app_server_protocol::CommandAction as V2ParsedCommand;
 use codex_app_server_protocol::CommandExecutionApprovalDecision;
 use codex_app_server_protocol::CommandExecutionOutputDeltaNotification;
@@ -22,6 +25,7 @@ use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
 use codex_app_server_protocol::CommandExecutionStatus;
 use codex_app_server_protocol::ContextCompactedNotification;
 use codex_app_server_protocol::DeprecationNoticeNotification;
+use codex_app_server_protocol::DynamicToolCallParams;
 use codex_app_server_protocol::ErrorNotification;
 use codex_app_server_protocol::ExecCommandApprovalParams;
 use codex_app_server_protocol::ExecCommandApprovalResponse;
@@ -40,6 +44,7 @@ use codex_app_server_protocol::McpToolCallResult;
 use codex_app_server_protocol::McpToolCallStatus;
 use codex_app_server_protocol::PatchApplyStatus;
 use codex_app_server_protocol::PatchChangeKind as V2PatchChangeKind;
+use codex_app_server_protocol::PlanDeltaNotification;
 use codex_app_server_protocol::RawResponseItemCompletedNotification;
 use codex_app_server_protocol::ReasoningSummaryPartAddedNotification;
 use codex_app_server_protocol::ReasoningSummaryTextDeltaNotification;
@@ -48,9 +53,14 @@ use codex_app_server_protocol::ServerNotification;
 use codex_app_server_protocol::ServerRequestPayload;
 use codex_app_server_protocol::TerminalInteractionNotification;
 use codex_app_server_protocol::ThreadItem;
+use codex_app_server_protocol::ThreadNameUpdatedNotification;
 use codex_app_server_protocol::ThreadRollbackResponse;
 use codex_app_server_protocol::ThreadTokenUsage;
 use codex_app_server_protocol::ThreadTokenUsageUpdatedNotification;
+use codex_app_server_protocol::ToolRequestUserInputOption;
+use codex_app_server_protocol::ToolRequestUserInputParams;
+use codex_app_server_protocol::ToolRequestUserInputQuestion;
+use codex_app_server_protocol::ToolRequestUserInputResponse;
 use codex_app_server_protocol::Turn;
 use codex_app_server_protocol::TurnCompletedNotification;
 use codex_app_server_protocol::TurnDiffUpdatedNotification;
@@ -78,8 +88,11 @@ use codex_core::protocol::TurnDiffEvent;
 use codex_core::review_format::format_review_findings_block;
 use codex_core::review_prompts;
 use codex_protocol::ThreadId;
+use codex_protocol::dynamic_tools::DynamicToolResponse as CoreDynamicToolResponse;
 use codex_protocol::plan_tool::UpdatePlanArgs;
 use codex_protocol::protocol::ReviewOutputEvent;
+use codex_protocol::request_user_input::RequestUserInputAnswer as CoreRequestUserInputAnswer;
+use codex_protocol::request_user_input::RequestUserInputResponse as CoreRequestUserInputResponse;
 use std::collections::HashMap;
 use std::convert::TryFrom;
 use std::path::PathBuf;
@@ -106,7 +119,8 @@ pub(crate) async fn apply_bespoke_event_handling(
         msg,
     } = event;
     match msg {
-        EventMsg::TaskComplete(_ev) => {
+        EventMsg::TurnStarted(_) => {}
+        EventMsg::TurnComplete(_ev) => {
             handle_turn_complete(
                 conversation_id,
                 event_turn_id,
@@ -232,6 +246,9 @@ pub(crate) async fn apply_bespoke_event_handling(
                     // and emit the corresponding EventMsg, we repurpose the call_id as the item_id.
                     item_id: item_id.clone(),
                     reason,
+                    command: Some(command_string.clone()),
+                    cwd: Some(cwd.clone()),
+                    command_actions: Some(command_actions.clone()),
                     proposed_execpolicy_amendment: proposed_execpolicy_amendment_v2,
                 };
                 let rx = outgoing
@@ -255,6 +272,93 @@ pub(crate) async fn apply_bespoke_event_handling(
                 });
             }
         },
+        EventMsg::RequestUserInput(request) => {
+            if matches!(api_version, ApiVersion::V2) {
+                let questions = request
+                    .questions
+                    .into_iter()
+                    .map(|question| ToolRequestUserInputQuestion {
+                        id: question.id,
+                        header: question.header,
+                        question: question.question,
+                        is_other: question.is_other,
+                        is_secret: question.is_secret,
+                        options: question.options.map(|options| {
+                            options
+                                .into_iter()
+                                .map(|option| ToolRequestUserInputOption {
+                                    label: option.label,
+                                    description: option.description,
+                                })
+                                .collect()
+                        }),
+                    })
+                    .collect();
+                let params = ToolRequestUserInputParams {
+                    thread_id: conversation_id.to_string(),
+                    turn_id: request.turn_id,
+                    item_id: request.call_id,
+                    questions,
+                };
+                let rx = outgoing
+                    .send_request(ServerRequestPayload::ToolRequestUserInput(params))
+                    .await;
+                tokio::spawn(async move {
+                    on_request_user_input_response(event_turn_id, rx, conversation).await;
+                });
+            } else {
+                error!(
+                    "request_user_input is only supported on api v2 (call_id: {})",
+                    request.call_id
+                );
+                let empty = CoreRequestUserInputResponse {
+                    answers: HashMap::new(),
+                };
+                if let Err(err) = conversation
+                    .submit(Op::UserInputAnswer {
+                        id: event_turn_id,
+                        response: empty,
+                    })
+                    .await
+                {
+                    error!("failed to submit UserInputAnswer: {err}");
+                }
+            }
+        }
+        EventMsg::DynamicToolCallRequest(request) => {
+            if matches!(api_version, ApiVersion::V2) {
+                let call_id = request.call_id;
+                let params = DynamicToolCallParams {
+                    thread_id: conversation_id.to_string(),
+                    turn_id: request.turn_id,
+                    call_id: call_id.clone(),
+                    tool: request.tool,
+                    arguments: request.arguments,
+                };
+                let rx = outgoing
+                    .send_request(ServerRequestPayload::DynamicToolCall(params))
+                    .await;
+                tokio::spawn(async move {
+                    crate::dynamic_tools::on_call_response(call_id, rx, conversation).await;
+                });
+            } else {
+                error!(
+                    "dynamic tool calls are only supported on api v2 (call_id: {})",
+                    request.call_id
+                );
+                let call_id = request.call_id;
+                let _ = conversation
+                    .submit(Op::DynamicToolResponse {
+                        id: call_id.clone(),
+                        response: CoreDynamicToolResponse {
+                            call_id,
+                            output: "dynamic tool calls require api v2".to_string(),
+                            success: false,
+                        },
+                    })
+                    .await;
+            }
+        }
         // TODO(celia): properly construct McpToolCall TurnItem in core.
         EventMsg::McpToolCallBegin(begin_event) => {
             let notification = construct_mcp_tool_call_notification(
@@ -278,15 +382,240 @@ pub(crate) async fn apply_bespoke_event_handling(
                 .send_server_notification(ServerNotification::ItemCompleted(notification))
                 .await;
         }
+        EventMsg::CollabAgentSpawnBegin(begin_event) => {
+            let item = ThreadItem::CollabAgentToolCall {
+                id: begin_event.call_id,
+                tool: CollabAgentTool::SpawnAgent,
+                status: V2CollabToolCallStatus::InProgress,
+                sender_thread_id: begin_event.sender_thread_id.to_string(),
+                receiver_thread_ids: Vec::new(),
+                prompt: Some(begin_event.prompt),
+                agents_states: HashMap::new(),
+            };
+            let notification = ItemStartedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemStarted(notification))
+                .await;
+        }
+        EventMsg::CollabAgentSpawnEnd(end_event) => {
+            let has_receiver = end_event.new_thread_id.is_some();
+            let status = match &end_event.status {
+                codex_protocol::protocol::AgentStatus::Errored(_)
+                | codex_protocol::protocol::AgentStatus::NotFound => V2CollabToolCallStatus::Failed,
+                _ if has_receiver => V2CollabToolCallStatus::Completed,
+                _ => V2CollabToolCallStatus::Failed,
+            };
+            let (receiver_thread_ids, agents_states) = match end_event.new_thread_id {
+                Some(id) => {
+                    let receiver_id = id.to_string();
+                    let received_status = V2CollabAgentStatus::from(end_event.status.clone());
+                    (
+                        vec![receiver_id.clone()],
+                        [(receiver_id, received_status)].into_iter().collect(),
+                    )
+                }
+                None => (Vec::new(), HashMap::new()),
+            };
+            let item = ThreadItem::CollabAgentToolCall {
+                id: end_event.call_id,
+                tool: CollabAgentTool::SpawnAgent,
+                status,
+                sender_thread_id: end_event.sender_thread_id.to_string(),
+                receiver_thread_ids,
+                prompt: Some(end_event.prompt),
+                agents_states,
+            };
+            let notification = ItemCompletedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemCompleted(notification))
+                .await;
+        }
+        EventMsg::CollabAgentInteractionBegin(begin_event) => {
+            let receiver_thread_ids = vec![begin_event.receiver_thread_id.to_string()];
+            let item = ThreadItem::CollabAgentToolCall {
+                id: begin_event.call_id,
+                tool: CollabAgentTool::SendInput,
+                status: V2CollabToolCallStatus::InProgress,
+                sender_thread_id: begin_event.sender_thread_id.to_string(),
+                receiver_thread_ids,
+                prompt: Some(begin_event.prompt),
+                agents_states: HashMap::new(),
+            };
+            let notification = ItemStartedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemStarted(notification))
+                .await;
+        }
+        EventMsg::CollabAgentInteractionEnd(end_event) => {
+            let status = match &end_event.status {
+                codex_protocol::protocol::AgentStatus::Errored(_)
+                | codex_protocol::protocol::AgentStatus::NotFound => V2CollabToolCallStatus::Failed,
+                _ => V2CollabToolCallStatus::Completed,
+            };
+            let receiver_id = end_event.receiver_thread_id.to_string();
+            let received_status = V2CollabAgentStatus::from(end_event.status);
+            let item = ThreadItem::CollabAgentToolCall {
+                id: end_event.call_id,
+                tool: CollabAgentTool::SendInput,
+                status,
+                sender_thread_id: end_event.sender_thread_id.to_string(),
+                receiver_thread_ids: vec![receiver_id.clone()],
+                prompt: Some(end_event.prompt),
+                agents_states: [(receiver_id, received_status)].into_iter().collect(),
+            };
+            let notification = ItemCompletedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemCompleted(notification))
+                .await;
+        }
+        EventMsg::CollabWaitingBegin(begin_event) => {
+            let receiver_thread_ids = begin_event
+                .receiver_thread_ids
+                .iter()
+                .map(ToString::to_string)
+                .collect();
+            let item = ThreadItem::CollabAgentToolCall {
+                id: begin_event.call_id,
+                tool: CollabAgentTool::Wait,
+                status: V2CollabToolCallStatus::InProgress,
+                sender_thread_id: begin_event.sender_thread_id.to_string(),
+                receiver_thread_ids,
+                prompt: None,
+                agents_states: HashMap::new(),
+            };
+            let notification = ItemStartedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemStarted(notification))
+                .await;
+        }
+        EventMsg::CollabWaitingEnd(end_event) => {
+            let status = if end_event.statuses.values().any(|status| {
+                matches!(
+                    status,
+                    codex_protocol::protocol::AgentStatus::Errored(_)
+                        | codex_protocol::protocol::AgentStatus::NotFound
+                )
+            }) {
+                V2CollabToolCallStatus::Failed
+            } else {
+                V2CollabToolCallStatus::Completed
+            };
+            let receiver_thread_ids = end_event.statuses.keys().map(ToString::to_string).collect();
+            let agents_states = end_event
+                .statuses
+                .iter()
+                .map(|(id, status)| (id.to_string(), V2CollabAgentStatus::from(status.clone())))
+                .collect();
+            let item = ThreadItem::CollabAgentToolCall {
+                id: end_event.call_id,
+                tool: CollabAgentTool::Wait,
+                status,
+                sender_thread_id: end_event.sender_thread_id.to_string(),
+                receiver_thread_ids,
+                prompt: None,
+                agents_states,
+            };
+            let notification = ItemCompletedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemCompleted(notification))
+                .await;
+        }
+        EventMsg::CollabCloseBegin(begin_event) => {
+            let item = ThreadItem::CollabAgentToolCall {
+                id: begin_event.call_id,
+                tool: CollabAgentTool::CloseAgent,
+                status: V2CollabToolCallStatus::InProgress,
+                sender_thread_id: begin_event.sender_thread_id.to_string(),
+                receiver_thread_ids: vec![begin_event.receiver_thread_id.to_string()],
+                prompt: None,
+                agents_states: HashMap::new(),
+            };
+            let notification = ItemStartedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemStarted(notification))
+                .await;
+        }
+        EventMsg::CollabCloseEnd(end_event) => {
+            let status = match &end_event.status {
+                codex_protocol::protocol::AgentStatus::Errored(_)
+                | codex_protocol::protocol::AgentStatus::NotFound => V2CollabToolCallStatus::Failed,
+                _ => V2CollabToolCallStatus::Completed,
+            };
+            let receiver_id = end_event.receiver_thread_id.to_string();
+            let agents_states = [(
+                receiver_id.clone(),
+                V2CollabAgentStatus::from(end_event.status),
+            )]
+            .into_iter()
+            .collect();
+            let item = ThreadItem::CollabAgentToolCall {
+                id: end_event.call_id,
+                tool: CollabAgentTool::CloseAgent,
+                status,
+                sender_thread_id: end_event.sender_thread_id.to_string(),
+                receiver_thread_ids: vec![receiver_id],
+                prompt: None,
+                agents_states,
+            };
+            let notification = ItemCompletedNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::ItemCompleted(notification))
+                .await;
+        }
         EventMsg::AgentMessageContentDelta(event) => {
+            let codex_protocol::protocol::AgentMessageContentDeltaEvent { item_id, delta, .. } =
+                event;
             let notification = AgentMessageDeltaNotification {
+                thread_id: conversation_id.to_string(),
+                turn_id: event_turn_id.clone(),
+                item_id,
+                delta,
+            };
+            outgoing
+                .send_server_notification(ServerNotification::AgentMessageDelta(notification))
+                .await;
+        }
+        EventMsg::PlanDelta(event) => {
+            let notification = PlanDeltaNotification {
                 thread_id: conversation_id.to_string(),
                 turn_id: event_turn_id.clone(),
                 item_id: event.item_id,
                 delta: event.delta,
             };
             outgoing
-                .send_server_notification(ServerNotification::AgentMessageDelta(notification))
+                .send_server_notification(ServerNotification::PlanDelta(notification))
                 .await;
         }
         EventMsg::ContextCompacted(..) => {
@@ -731,7 +1060,15 @@ pub(crate) async fn apply_bespoke_event_handling(
             };
 
             if let Some(request_id) = pending {
-                let rollout_path = conversation.rollout_path();
+                let Some(rollout_path) = conversation.rollout_path() else {
+                    let error = JSONRPCErrorError {
+                        code: INVALID_REQUEST_ERROR_CODE,
+                        message: "thread has no persisted rollout".to_string(),
+                        data: None,
+                    };
+                    outgoing.send_error(request_id, error).await;
+                    return;
+                };
                 let response = match read_summary_from_rollout(
                     rollout_path.as_path(),
                     fallback_model_provider.as_str(),
@@ -776,6 +1113,17 @@ pub(crate) async fn apply_bespoke_event_handling(
                 outgoing.send_response(request_id, response).await;
             }
         }
+        EventMsg::ThreadNameUpdated(thread_name_event) => {
+            if let ApiVersion::V2 = api_version {
+                let notification = ThreadNameUpdatedNotification {
+                    thread_id: thread_name_event.thread_id.to_string(),
+                    thread_name: thread_name_event.thread_name,
+                };
+                outgoing
+                    .send_server_notification(ServerNotification::ThreadNameUpdated(notification))
+                    .await;
+            }
+        }
         EventMsg::TurnDiff(turn_diff_event) => {
             handle_turn_diff(
                 conversation_id,
@@ -827,6 +1175,7 @@ async fn handle_turn_plan_update(
     api_version: ApiVersion,
     outgoing: &OutgoingMessageSender,
 ) {
+    // `update_plan` is a todo/checklist tool; it is not related to plan-mode updates
     if let ApiVersion::V2 = api_version {
         let notification = TurnPlanUpdatedNotification {
             thread_id: conversation_id.to_string(),
@@ -1132,6 +1481,65 @@ async fn on_exec_approval_response(
     }
 }
 
+async fn on_request_user_input_response(
+    event_turn_id: String,
+    receiver: oneshot::Receiver<JsonValue>,
+    conversation: Arc<CodexThread>,
+) {
+    let response = receiver.await;
+    let value = match response {
+        Ok(value) => value,
+        Err(err) => {
+            error!("request failed: {err:?}");
+            let empty = CoreRequestUserInputResponse {
+                answers: HashMap::new(),
+            };
+            if let Err(err) = conversation
+                .submit(Op::UserInputAnswer {
+                    id: event_turn_id,
+                    response: empty,
+                })
+                .await
+            {
+                error!("failed to submit UserInputAnswer: {err}");
+            }
+            return;
+        }
+    };
+
+    let response =
+        serde_json::from_value::<ToolRequestUserInputResponse>(value).unwrap_or_else(|err| {
+            error!("failed to deserialize ToolRequestUserInputResponse: {err}");
+            ToolRequestUserInputResponse {
+                answers: HashMap::new(),
+            }
+        });
+    let response = CoreRequestUserInputResponse {
+        answers: response
+            .answers
+            .into_iter()
+            .map(|(id, answer)| {
+                (
+                    id,
+                    CoreRequestUserInputAnswer {
+                        answers: answer.answers,
+                    },
+                )
+            })
+            .collect(),
+    };
+
+    if let Err(err) = conversation
+        .submit(Op::UserInputAnswer {
+            id: event_turn_id,
+            response,
+        })
+        .await
+    {
+        error!("failed to submit UserInputAnswer: {err}");
+    }
+}
+
 const REVIEW_FALLBACK_MESSAGE: &str = "Reviewer failed to output a response.";
 
 fn render_review_output_text(output: &ReviewOutputEvent) -> String {

codex-rs/app-server/src/config_api.rs

@@ -12,8 +12,10 @@ use codex_app_server_protocol::JSONRPCErrorError;
 use codex_app_server_protocol::SandboxMode;
 use codex_core::config::ConfigService;
 use codex_core::config::ConfigServiceError;
+use codex_core::config_loader::CloudRequirementsLoader;
 use codex_core::config_loader::ConfigRequirementsToml;
 use codex_core::config_loader::LoaderOverrides;
+use codex_core::config_loader::ResidencyRequirement as CoreResidencyRequirement;
 use codex_core::config_loader::SandboxModeRequirement as CoreSandboxModeRequirement;
 use serde_json::json;
 use std::path::PathBuf;
@@ -29,9 +31,15 @@ impl ConfigApi {
         codex_home: PathBuf,
         cli_overrides: Vec<(String, TomlValue)>,
         loader_overrides: LoaderOverrides,
+        cloud_requirements: CloudRequirementsLoader,
     ) -> Self {
         Self {
-            service: ConfigService::new(codex_home, cli_overrides, loader_overrides),
+            service: ConfigService::new(
+                codex_home,
+                cli_overrides,
+                loader_overrides,
+                cloud_requirements,
+            ),
         }
     }
 
@@ -84,6 +92,9 @@ fn map_requirements_toml_to_api(requirements: ConfigRequirementsToml) -> ConfigR
                 .filter_map(map_sandbox_mode_requirement_to_api)
                 .collect()
         }),
+        enforce_residency: requirements
+            .enforce_residency
+            .map(map_residency_requirement_to_api),
     }
 }
 
@@ -96,6 +107,14 @@ fn map_sandbox_mode_requirement_to_api(mode: CoreSandboxModeRequirement) -> Opti
     }
 }
 
+fn map_residency_requirement_to_api(
+    residency: CoreResidencyRequirement,
+) -> codex_app_server_protocol::ResidencyRequirement {
+    match residency {
+        CoreResidencyRequirement::Us => codex_app_server_protocol::ResidencyRequirement::Us,
+    }
+}
+
 fn map_error(err: ConfigServiceError) -> JSONRPCErrorError {
     if let Some(code) = err.write_error_code() {
         return config_write_error(code, err.to_string());
@@ -135,6 +154,9 @@ mod tests {
                 CoreSandboxModeRequirement::ReadOnly,
                 CoreSandboxModeRequirement::ExternalSandbox,
             ]),
+            mcp_servers: None,
+            rules: None,
+            enforce_residency: Some(CoreResidencyRequirement::Us),
         };
 
         let mapped = map_requirements_toml_to_api(requirements);
@@ -150,5 +172,9 @@ mod tests {
             mapped.allowed_sandbox_modes,
             Some(vec![SandboxMode::ReadOnly]),
         );
+        assert_eq!(
+            mapped.enforce_residency,
+            Some(codex_app_server_protocol::ResidencyRequirement::Us),
+        );
     }
 }

codex-rs/app-server/src/dynamic_tools.rs

@@ -0,0 +1,58 @@
+use codex_app_server_protocol::DynamicToolCallResponse;
+use codex_core::CodexThread;
+use codex_protocol::dynamic_tools::DynamicToolResponse as CoreDynamicToolResponse;
+use codex_protocol::protocol::Op;
+use std::sync::Arc;
+use tokio::sync::oneshot;
+use tracing::error;
+
+pub(crate) async fn on_call_response(
+    call_id: String,
+    receiver: oneshot::Receiver<serde_json::Value>,
+    conversation: Arc<CodexThread>,
+) {
+    let response = receiver.await;
+    let value = match response {
+        Ok(value) => value,
+        Err(err) => {
+            error!("request failed: {err:?}");
+            let fallback = CoreDynamicToolResponse {
+                call_id: call_id.clone(),
+                output: "dynamic tool request failed".to_string(),
+                success: false,
+            };
+            if let Err(err) = conversation
+                .submit(Op::DynamicToolResponse {
+                    id: call_id.clone(),
+                    response: fallback,
+                })
+                .await
+            {
+                error!("failed to submit DynamicToolResponse: {err}");
+            }
+            return;
+        }
+    };
+
+    let response = serde_json::from_value::<DynamicToolCallResponse>(value).unwrap_or_else(|err| {
+        error!("failed to deserialize DynamicToolCallResponse: {err}");
+        DynamicToolCallResponse {
+            output: "dynamic tool response was invalid".to_string(),
+            success: false,
+        }
+    });
+    let response = CoreDynamicToolResponse {
+        call_id: call_id.clone(),
+        output: response.output,
+        success: response.success,
+    };
+    if let Err(err) = conversation
+        .submit(Op::DynamicToolResponse {
+            id: call_id,
+            response,
+        })
+        .await
+    {
+        error!("failed to submit DynamicToolResponse: {err}");
+    }
+}

codex-rs/app-server/src/filters.rs

@@ -0,0 +1,155 @@
+use codex_app_server_protocol::ThreadSourceKind;
+use codex_core::INTERACTIVE_SESSION_SOURCES;
+use codex_protocol::protocol::SessionSource as CoreSessionSource;
+use codex_protocol::protocol::SubAgentSource as CoreSubAgentSource;
+
+pub(crate) fn compute_source_filters(
+    source_kinds: Option<Vec<ThreadSourceKind>>,
+) -> (Vec<CoreSessionSource>, Option<Vec<ThreadSourceKind>>) {
+    let Some(source_kinds) = source_kinds else {
+        return (INTERACTIVE_SESSION_SOURCES.to_vec(), None);
+    };
+
+    if source_kinds.is_empty() {
+        return (INTERACTIVE_SESSION_SOURCES.to_vec(), None);
+    }
+
+    let requires_post_filter = source_kinds.iter().any(|kind| {
+        matches!(
+            kind,
+            ThreadSourceKind::Exec
+                | ThreadSourceKind::AppServer
+                | ThreadSourceKind::SubAgent
+                | ThreadSourceKind::SubAgentReview
+                | ThreadSourceKind::SubAgentCompact
+                | ThreadSourceKind::SubAgentThreadSpawn
+                | ThreadSourceKind::SubAgentOther
+                | ThreadSourceKind::Unknown
+        )
+    });
+
+    if requires_post_filter {
+        (Vec::new(), Some(source_kinds))
+    } else {
+        let interactive_sources = source_kinds
+            .iter()
+            .filter_map(|kind| match kind {
+                ThreadSourceKind::Cli => Some(CoreSessionSource::Cli),
+                ThreadSourceKind::VsCode => Some(CoreSessionSource::VSCode),
+                ThreadSourceKind::Exec
+                | ThreadSourceKind::AppServer
+                | ThreadSourceKind::SubAgent
+                | ThreadSourceKind::SubAgentReview
+                | ThreadSourceKind::SubAgentCompact
+                | ThreadSourceKind::SubAgentThreadSpawn
+                | ThreadSourceKind::SubAgentOther
+                | ThreadSourceKind::Unknown => None,
+            })
+            .collect::<Vec<_>>();
+        (interactive_sources, Some(source_kinds))
+    }
+}
+
+pub(crate) fn source_kind_matches(source: &CoreSessionSource, filter: &[ThreadSourceKind]) -> bool {
+    filter.iter().any(|kind| match kind {
+        ThreadSourceKind::Cli => matches!(source, CoreSessionSource::Cli),
+        ThreadSourceKind::VsCode => matches!(source, CoreSessionSource::VSCode),
+        ThreadSourceKind::Exec => matches!(source, CoreSessionSource::Exec),
+        ThreadSourceKind::AppServer => matches!(source, CoreSessionSource::Mcp),
+        ThreadSourceKind::SubAgent => matches!(source, CoreSessionSource::SubAgent(_)),
+        ThreadSourceKind::SubAgentReview => {
+            matches!(
+                source,
+                CoreSessionSource::SubAgent(CoreSubAgentSource::Review)
+            )
+        }
+        ThreadSourceKind::SubAgentCompact => {
+            matches!(
+                source,
+                CoreSessionSource::SubAgent(CoreSubAgentSource::Compact)
+            )
+        }
+        ThreadSourceKind::SubAgentThreadSpawn => matches!(
+            source,
+            CoreSessionSource::SubAgent(CoreSubAgentSource::ThreadSpawn { .. })
+        ),
+        ThreadSourceKind::SubAgentOther => matches!(
+            source,
+            CoreSessionSource::SubAgent(CoreSubAgentSource::Other(_))
+        ),
+        ThreadSourceKind::Unknown => matches!(source, CoreSessionSource::Unknown),
+    })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use codex_protocol::ThreadId;
+    use pretty_assertions::assert_eq;
+    use uuid::Uuid;
+
+    #[test]
+    fn compute_source_filters_defaults_to_interactive_sources() {
+        let (allowed_sources, filter) = compute_source_filters(None);
+
+        assert_eq!(allowed_sources, INTERACTIVE_SESSION_SOURCES.to_vec());
+        assert_eq!(filter, None);
+    }
+
+    #[test]
+    fn compute_source_filters_empty_means_interactive_sources() {
+        let (allowed_sources, filter) = compute_source_filters(Some(Vec::new()));
+
+        assert_eq!(allowed_sources, INTERACTIVE_SESSION_SOURCES.to_vec());
+        assert_eq!(filter, None);
+    }
+
+    #[test]
+    fn compute_source_filters_interactive_only_skips_post_filtering() {
+        let source_kinds = vec![ThreadSourceKind::Cli, ThreadSourceKind::VsCode];
+        let (allowed_sources, filter) = compute_source_filters(Some(source_kinds.clone()));
+
+        assert_eq!(
+            allowed_sources,
+            vec![CoreSessionSource::Cli, CoreSessionSource::VSCode]
+        );
+        assert_eq!(filter, Some(source_kinds));
+    }
+
+    #[test]
+    fn compute_source_filters_subagent_variant_requires_post_filtering() {
+        let source_kinds = vec![ThreadSourceKind::SubAgentReview];
+        let (allowed_sources, filter) = compute_source_filters(Some(source_kinds.clone()));
+
+        assert_eq!(allowed_sources, Vec::new());
+        assert_eq!(filter, Some(source_kinds));
+    }
+
+    #[test]
+    fn source_kind_matches_distinguishes_subagent_variants() {
+        let parent_thread_id =
+            ThreadId::from_string(&Uuid::new_v4().to_string()).expect("valid thread id");
+        let review = CoreSessionSource::SubAgent(CoreSubAgentSource::Review);
+        let spawn = CoreSessionSource::SubAgent(CoreSubAgentSource::ThreadSpawn {
+            parent_thread_id,
+            depth: 1,
+        });
+
+        assert!(source_kind_matches(
+            &review,
+            &[ThreadSourceKind::SubAgentReview]
+        ));
+        assert!(!source_kind_matches(
+            &review,
+            &[ThreadSourceKind::SubAgentThreadSpawn]
+        ));
+        assert!(source_kind_matches(
+            &spawn,
+            &[ThreadSourceKind::SubAgentThreadSpawn]
+        ));
+        assert!(!source_kind_matches(
+            &spawn,
+            &[ThreadSourceKind::SubAgentReview]
+        ));
+    }
+}

codex-rs/app-server/src/fuzzy_file_search.rs

@@ -1,17 +1,14 @@
 use std::num::NonZero;
-use std::num::NonZeroUsize;
 use std::path::PathBuf;
 use std::sync::Arc;
 use std::sync::atomic::AtomicBool;
 
 use codex_app_server_protocol::FuzzyFileSearchResult;
 use codex_file_search as file_search;
-use tokio::task::JoinSet;
 use tracing::warn;
 
-const LIMIT_PER_ROOT: usize = 50;
+const MATCH_LIMIT: usize = 50;
 const MAX_THREADS: usize = 12;
-const COMPUTE_INDICES: bool = true;
 
 pub(crate) async fn run_fuzzy_file_search(
     query: String,
@@ -23,64 +20,54 @@ pub(crate) async fn run_fuzzy_file_search(
     }
 
     #[expect(clippy::expect_used)]
-    let limit_per_root =
-        NonZero::new(LIMIT_PER_ROOT).expect("LIMIT_PER_ROOT should be a valid non-zero usize");
+    let limit = NonZero::new(MATCH_LIMIT).expect("MATCH_LIMIT should be a valid non-zero usize");
 
     let cores = std::thread::available_parallelism()
         .map(std::num::NonZero::get)
         .unwrap_or(1);
     let threads = cores.min(MAX_THREADS);
-    let threads_per_root = (threads / roots.len()).max(1);
-    let threads = NonZero::new(threads_per_root).unwrap_or(NonZeroUsize::MIN);
+    #[expect(clippy::expect_used)]
+    let threads = NonZero::new(threads.max(1)).expect("threads should be non-zero");
+    let search_dirs: Vec<PathBuf> = roots.iter().map(PathBuf::from).collect();
 
-    let mut files: Vec<FuzzyFileSearchResult> = Vec::new();
-    let mut join_set = JoinSet::new();
-
-    for root in roots {
-        let search_dir = PathBuf::from(&root);
-        let query = query.clone();
-        let cancel_flag = cancellation_flag.clone();
-        join_set.spawn_blocking(move || {
-            match file_search::run(
-                query.as_str(),
-                limit_per_root,
-                &search_dir,
-                Vec::new(),
+    let mut files = match tokio::task::spawn_blocking(move || {
+        file_search::run(
+            query.as_str(),
+            search_dirs,
+            file_search::FileSearchOptions {
+                limit,
                 threads,
-                cancel_flag,
-                COMPUTE_INDICES,
-                true,
-            ) {
-                Ok(res) => Ok((root, res)),
-                Err(err) => Err((root, err)),
-            }
-        });
-    }
-
-    while let Some(res) = join_set.join_next().await {
-        match res {
-            Ok(Ok((root, res))) => {
-                for m in res.matches {
-                    let path = m.path;
-                    let file_name = file_search::file_name_from_path(&path);
-                    let result = FuzzyFileSearchResult {
-                        root: root.clone(),
-                        path,
-                        file_name,
-                        score: m.score,
-                        indices: m.indices,
-                    };
-                    files.push(result);
+                compute_indices: true,
+                ..Default::default()
+            },
+            Some(cancellation_flag),
+        )
+    })
+    .await
+    {
+        Ok(Ok(res)) => res
+            .matches
+            .into_iter()
+            .map(|m| {
+                let file_name = m.path.file_name().unwrap_or_default();
+                FuzzyFileSearchResult {
+                    root: m.root.to_string_lossy().to_string(),
+                    path: m.path.to_string_lossy().to_string(),
+                    file_name: file_name.to_string_lossy().to_string(),
+                    score: m.score,
+                    indices: m.indices,
                 }
-            }
-            Ok(Err((root, err))) => {
-                warn!("fuzzy-file-search in dir '{root}' failed: {err}");
-            }
-            Err(err) => {
-                warn!("fuzzy-file-search join_next failed: {err}");
-            }
+            })
+            .collect::<Vec<_>>(),
+        Ok(Err(err)) => {
+            warn!("fuzzy-file-search failed: {err}");
+            Vec::new()
         }
-    }
+        Err(err) => {
+            warn!("fuzzy-file-search join failed: {err}");
+            Vec::new()
+        }
+    };
 
     files.sort_by(file_search::cmp_by_score_desc_then_path_asc::<
         FuzzyFileSearchResult,

codex-rs/app-server/src/lib.rs

@@ -1,16 +1,30 @@
 #![deny(clippy::print_stdout, clippy::print_stderr)]
 
+use codex_cloud_requirements::cloud_requirements_loader;
 use codex_common::CliConfigOverrides;
+use codex_core::AuthManager;
+use codex_core::config::Config;
 use codex_core::config::ConfigBuilder;
+use codex_core::config_loader::CloudRequirementsLoader;
+use codex_core::config_loader::ConfigLayerStackOrdering;
 use codex_core::config_loader::LoaderOverrides;
 use std::io::ErrorKind;
 use std::io::Result as IoResult;
 use std::path::PathBuf;
 
 use crate::message_processor::MessageProcessor;
+use crate::message_processor::MessageProcessorArgs;
 use crate::outgoing_message::OutgoingMessage;
 use crate::outgoing_message::OutgoingMessageSender;
+use codex_app_server_protocol::ConfigLayerSource;
+use codex_app_server_protocol::ConfigWarningNotification;
 use codex_app_server_protocol::JSONRPCMessage;
+use codex_app_server_protocol::TextPosition as AppTextPosition;
+use codex_app_server_protocol::TextRange as AppTextRange;
+use codex_core::ExecPolicyError;
+use codex_core::check_execpolicy_for_warnings;
+use codex_core::config_loader::ConfigLoadError;
+use codex_core::config_loader::TextRange as CoreTextRange;
 use codex_feedback::CodexFeedback;
 use tokio::io::AsyncBufReadExt;
 use tokio::io::AsyncWriteExt;
@@ -21,6 +35,7 @@ use toml::Value as TomlValue;
 use tracing::debug;
 use tracing::error;
 use tracing::info;
+use tracing::warn;
 use tracing_subscriber::EnvFilter;
 use tracing_subscriber::Layer;
 use tracing_subscriber::layer::SubscriberExt;
@@ -29,7 +44,9 @@ use tracing_subscriber::util::SubscriberInitExt;
 mod bespoke_event_handling;
 mod codex_message_processor;
 mod config_api;
+mod dynamic_tools;
 mod error_code;
+mod filters;
 mod fuzzy_file_search;
 mod message_processor;
 mod models;
@@ -40,10 +57,121 @@ mod outgoing_message;
 /// plenty for an interactive CLI.
 const CHANNEL_CAPACITY: usize = 128;
 
+fn config_warning_from_error(
+    summary: impl Into<String>,
+    err: &std::io::Error,
+) -> ConfigWarningNotification {
+    let (path, range) = match config_error_location(err) {
+        Some((path, range)) => (Some(path), Some(range)),
+        None => (None, None),
+    };
+    ConfigWarningNotification {
+        summary: summary.into(),
+        details: Some(err.to_string()),
+        path,
+        range,
+    }
+}
+
+fn config_error_location(err: &std::io::Error) -> Option<(String, AppTextRange)> {
+    err.get_ref()
+        .and_then(|err| err.downcast_ref::<ConfigLoadError>())
+        .map(|err| {
+            let config_error = err.config_error();
+            (
+                config_error.path.to_string_lossy().to_string(),
+                app_text_range(&config_error.range),
+            )
+        })
+}
+
+fn exec_policy_warning_location(err: &ExecPolicyError) -> (Option<String>, Option<AppTextRange>) {
+    match err {
+        ExecPolicyError::ParsePolicy { path, source } => {
+            if let Some(location) = source.location() {
+                let range = AppTextRange {
+                    start: AppTextPosition {
+                        line: location.range.start.line,
+                        column: location.range.start.column,
+                    },
+                    end: AppTextPosition {
+                        line: location.range.end.line,
+                        column: location.range.end.column,
+                    },
+                };
+                return (Some(location.path), Some(range));
+            }
+            (Some(path.clone()), None)
+        }
+        _ => (None, None),
+    }
+}
+
+fn app_text_range(range: &CoreTextRange) -> AppTextRange {
+    AppTextRange {
+        start: AppTextPosition {
+            line: range.start.line,
+            column: range.start.column,
+        },
+        end: AppTextPosition {
+            line: range.end.line,
+            column: range.end.column,
+        },
+    }
+}
+
+fn project_config_warning(config: &Config) -> Option<ConfigWarningNotification> {
+    let mut disabled_folders = Vec::new();
+
+    for layer in config
+        .config_layer_stack
+        .get_layers(ConfigLayerStackOrdering::LowestPrecedenceFirst, true)
+    {
+        if !matches!(layer.name, ConfigLayerSource::Project { .. })
+            || layer.disabled_reason.is_none()
+        {
+            continue;
+        }
+        if let ConfigLayerSource::Project { dot_codex_folder } = &layer.name {
+            disabled_folders.push((
+                dot_codex_folder.as_path().display().to_string(),
+                layer
+                    .disabled_reason
+                    .as_ref()
+                    .map(ToString::to_string)
+                    .unwrap_or_else(|| "config.toml is disabled.".to_string()),
+            ));
+        }
+    }
+
+    if disabled_folders.is_empty() {
+        return None;
+    }
+
+    let mut message = concat!(
+        "Project config.toml files are disabled in the following folders. ",
+        "Settings in those files are ignored, but skills and exec policies still load.\n",
+    )
+    .to_string();
+    for (index, (folder, reason)) in disabled_folders.iter().enumerate() {
+        let display_index = index + 1;
+        message.push_str(&format!("    {display_index}. {folder}\n"));
+        message.push_str(&format!("       {reason}\n"));
+    }
+
+    Some(ConfigWarningNotification {
+        summary: message,
+        details: None,
+        path: None,
+        range: None,
+    })
+}
+
 pub async fn run_main(
     codex_linux_sandbox_exe: Option<PathBuf>,
     cli_config_overrides: CliConfigOverrides,
     loader_overrides: LoaderOverrides,
+    default_analytics_enabled: bool,
 ) -> IoResult<()> {
     // Set up channels.
     let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
@@ -80,25 +208,96 @@ pub async fn run_main(
             format!("error parsing -c overrides: {e}"),
         )
     })?;
-    let loader_overrides_for_config_api = loader_overrides.clone();
-    let config = ConfigBuilder::default()
+    let cloud_requirements = match ConfigBuilder::default()
         .cli_overrides(cli_kv_overrides.clone())
-        .loader_overrides(loader_overrides)
+        .loader_overrides(loader_overrides.clone())
         .build()
         .await
-        .map_err(|e| {
-            std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
-        })?;
+    {
+        Ok(config) => {
+            let effective_toml = config.config_layer_stack.effective_config();
+            match effective_toml.try_into() {
+                Ok(config_toml) => {
+                    if let Err(err) = codex_core::personality_migration::maybe_migrate_personality(
+                        &config.codex_home,
+                        &config_toml,
+                    )
+                    .await
+                    {
+                        warn!(error = %err, "Failed to run personality migration");
+                    }
+                }
+                Err(err) => {
+                    warn!(error = %err, "Failed to deserialize config for personality migration");
+                }
+            }
+
+            let auth_manager = AuthManager::shared(
+                config.codex_home.clone(),
+                false,
+                config.cli_auth_credentials_store_mode,
+            );
+            cloud_requirements_loader(auth_manager, config.chatgpt_base_url)
+        }
+        Err(err) => {
+            warn!(error = %err, "Failed to preload config for cloud requirements");
+            // TODO(gt): Make cloud requirements preload failures blocking once we can fail-closed.
+            CloudRequirementsLoader::default()
+        }
+    };
+    let loader_overrides_for_config_api = loader_overrides.clone();
+    let mut config_warnings = Vec::new();
+    let config = match ConfigBuilder::default()
+        .cli_overrides(cli_kv_overrides.clone())
+        .loader_overrides(loader_overrides)
+        .cloud_requirements(cloud_requirements.clone())
+        .build()
+        .await
+    {
+        Ok(config) => config,
+        Err(err) => {
+            let message = config_warning_from_error("Invalid configuration; using defaults.", &err);
+            config_warnings.push(message);
+            Config::load_default_with_cli_overrides(cli_kv_overrides.clone()).map_err(|e| {
+                std::io::Error::new(
+                    ErrorKind::InvalidData,
+                    format!("error loading default config after config error: {e}"),
+                )
+            })?
+        }
+    };
+
+    if let Ok(Some(err)) =
+        check_execpolicy_for_warnings(&config.features, &config.config_layer_stack).await
+    {
+        let (path, range) = exec_policy_warning_location(&err);
+        let message = ConfigWarningNotification {
+            summary: "Error parsing rules; custom rules not applied.".to_string(),
+            details: Some(err.to_string()),
+            path,
+            range,
+        };
+        config_warnings.push(message);
+    }
+
+    if let Some(warning) = project_config_warning(&config) {
+        config_warnings.push(warning);
+    }
 
     let feedback = CodexFeedback::new();
 
-    let otel =
-        codex_core::otel_init::build_provider(&config, env!("CARGO_PKG_VERSION")).map_err(|e| {
-            std::io::Error::new(
-                ErrorKind::InvalidData,
-                format!("error loading otel config: {e}"),
-            )
-        })?;
+    let otel = codex_core::otel_init::build_provider(
+        &config,
+        env!("CARGO_PKG_VERSION"),
+        Some("codex_app_server"),
+        default_analytics_enabled,
+    )
+    .map_err(|e| {
+        std::io::Error::new(
+            ErrorKind::InvalidData,
+            format!("error loading otel config: {e}"),
+        )
+    })?;
 
     // Install a simple subscriber so `tracing` output is visible.  Users can
     // control the log level with `RUST_LOG`.
@@ -121,27 +320,61 @@ pub async fn run_main(
         .with(otel_logger_layer)
         .with(otel_tracing_layer)
         .try_init();
+    for warning in &config_warnings {
+        match &warning.details {
+            Some(details) => error!("{} {}", warning.summary, details),
+            None => error!("{}", warning.summary),
+        }
+    }
 
     // Task: process incoming messages.
     let processor_handle = tokio::spawn({
         let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
         let cli_overrides: Vec<(String, TomlValue)> = cli_kv_overrides.clone();
         let loader_overrides = loader_overrides_for_config_api;
-        let mut processor = MessageProcessor::new(
-            outgoing_message_sender,
+        let mut processor = MessageProcessor::new(MessageProcessorArgs {
+            outgoing: outgoing_message_sender,
             codex_linux_sandbox_exe,
-            std::sync::Arc::new(config),
+            config: std::sync::Arc::new(config),
             cli_overrides,
             loader_overrides,
-            feedback.clone(),
-        );
+            cloud_requirements: cloud_requirements.clone(),
+            feedback: feedback.clone(),
+            config_warnings,
+        });
+        let mut thread_created_rx = processor.thread_created_receiver();
         async move {
-            while let Some(msg) = incoming_rx.recv().await {
-                match msg {
-                    JSONRPCMessage::Request(r) => processor.process_request(r).await,
-                    JSONRPCMessage::Response(r) => processor.process_response(r).await,
-                    JSONRPCMessage::Notification(n) => processor.process_notification(n).await,
-                    JSONRPCMessage::Error(e) => processor.process_error(e),
+            let mut listen_for_threads = true;
+            loop {
+                tokio::select! {
+                    msg = incoming_rx.recv() => {
+                        let Some(msg) = msg else {
+                            break;
+                        };
+                        match msg {
+                            JSONRPCMessage::Request(r) => processor.process_request(r).await,
+                            JSONRPCMessage::Response(r) => processor.process_response(r).await,
+                            JSONRPCMessage::Notification(n) => processor.process_notification(n).await,
+                            JSONRPCMessage::Error(e) => processor.process_error(e).await,
+                        }
+                    }
+                    created = thread_created_rx.recv(), if listen_for_threads => {
+                        match created {
+                            Ok(thread_id) => {
+                                processor.try_attach_thread_listener(thread_id).await;
+                            }
+                            Err(tokio::sync::broadcast::error::RecvError::Lagged(_)) => {
+                                // TODO(jif) handle lag.
+                                // Assumes thread creation volume is low enough that lag never happens.
+                                // If it does, we log and continue without resyncing to avoid attaching
+                                // listeners for threads that should remain unsubscribed.
+                                warn!("thread_created receiver lagged; skipping resync");
+                            }
+                            Err(tokio::sync::broadcast::error::RecvError::Closed) => {
+                                listen_for_threads = false;
+                            }
+                        }
+                    }
                 }
             }
 

codex-rs/app-server/src/main.rs

@@ -20,6 +20,7 @@ fn main() -> anyhow::Result<()> {
             codex_linux_sandbox_exe,
             CliConfigOverrides::default(),
             loader_overrides,
+            false,
         )
         .await?;
         Ok(())

codex-rs/app-server/src/message_processor.rs

@@ -2,14 +2,20 @@ use std::path::PathBuf;
 use std::sync::Arc;
 
 use crate::codex_message_processor::CodexMessageProcessor;
+use crate::codex_message_processor::CodexMessageProcessorArgs;
 use crate::config_api::ConfigApi;
 use crate::error_code::INVALID_REQUEST_ERROR_CODE;
 use crate::outgoing_message::OutgoingMessageSender;
+use async_trait::async_trait;
+use codex_app_server_protocol::ChatgptAuthTokensRefreshParams;
+use codex_app_server_protocol::ChatgptAuthTokensRefreshReason;
+use codex_app_server_protocol::ChatgptAuthTokensRefreshResponse;
 use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::ClientRequest;
 use codex_app_server_protocol::ConfigBatchWriteParams;
 use codex_app_server_protocol::ConfigReadParams;
 use codex_app_server_protocol::ConfigValueWriteParams;
+use codex_app_server_protocol::ConfigWarningNotification;
 use codex_app_server_protocol::InitializeResponse;
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCErrorError;
@@ -17,61 +23,157 @@ use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCRequest;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ServerNotification;
+use codex_app_server_protocol::ServerRequestPayload;
 use codex_core::AuthManager;
 use codex_core::ThreadManager;
+use codex_core::auth::ExternalAuthRefreshContext;
+use codex_core::auth::ExternalAuthRefreshReason;
+use codex_core::auth::ExternalAuthRefresher;
+use codex_core::auth::ExternalAuthTokens;
 use codex_core::config::Config;
+use codex_core::config_loader::CloudRequirementsLoader;
 use codex_core::config_loader::LoaderOverrides;
+use codex_core::default_client::SetOriginatorError;
 use codex_core::default_client::USER_AGENT_SUFFIX;
 use codex_core::default_client::get_codex_user_agent;
+use codex_core::default_client::set_default_client_residency_requirement;
+use codex_core::default_client::set_default_originator;
 use codex_feedback::CodexFeedback;
+use codex_protocol::ThreadId;
 use codex_protocol::protocol::SessionSource;
+use tokio::sync::broadcast;
+use tokio::time::Duration;
+use tokio::time::timeout;
 use toml::Value as TomlValue;
 
+const EXTERNAL_AUTH_REFRESH_TIMEOUT: Duration = Duration::from_secs(10);
+
+#[derive(Clone)]
+struct ExternalAuthRefreshBridge {
+    outgoing: Arc<OutgoingMessageSender>,
+}
+
+impl ExternalAuthRefreshBridge {
+    fn map_reason(reason: ExternalAuthRefreshReason) -> ChatgptAuthTokensRefreshReason {
+        match reason {
+            ExternalAuthRefreshReason::Unauthorized => ChatgptAuthTokensRefreshReason::Unauthorized,
+        }
+    }
+}
+
+#[async_trait]
+impl ExternalAuthRefresher for ExternalAuthRefreshBridge {
+    async fn refresh(
+        &self,
+        context: ExternalAuthRefreshContext,
+    ) -> std::io::Result<ExternalAuthTokens> {
+        let params = ChatgptAuthTokensRefreshParams {
+            reason: Self::map_reason(context.reason),
+            previous_account_id: context.previous_account_id,
+        };
+
+        let (request_id, rx) = self
+            .outgoing
+            .send_request_with_id(ServerRequestPayload::ChatgptAuthTokensRefresh(params))
+            .await;
+
+        let result = match timeout(EXTERNAL_AUTH_REFRESH_TIMEOUT, rx).await {
+            Ok(result) => result.map_err(|err| {
+                std::io::Error::other(format!("auth refresh request canceled: {err}"))
+            })?,
+            Err(_) => {
+                let _canceled = self.outgoing.cancel_request(&request_id).await;
+                return Err(std::io::Error::other(format!(
+                    "auth refresh request timed out after {}s",
+                    EXTERNAL_AUTH_REFRESH_TIMEOUT.as_secs()
+                )));
+            }
+        };
+
+        let response: ChatgptAuthTokensRefreshResponse =
+            serde_json::from_value(result).map_err(std::io::Error::other)?;
+
+        Ok(ExternalAuthTokens {
+            access_token: response.access_token,
+            id_token: response.id_token,
+        })
+    }
+}
+
 pub(crate) struct MessageProcessor {
     outgoing: Arc<OutgoingMessageSender>,
     codex_message_processor: CodexMessageProcessor,
     config_api: ConfigApi,
+    config: Arc<Config>,
     initialized: bool,
+    config_warnings: Vec<ConfigWarningNotification>,
+}
+
+pub(crate) struct MessageProcessorArgs {
+    pub(crate) outgoing: OutgoingMessageSender,
+    pub(crate) codex_linux_sandbox_exe: Option<PathBuf>,
+    pub(crate) config: Arc<Config>,
+    pub(crate) cli_overrides: Vec<(String, TomlValue)>,
+    pub(crate) loader_overrides: LoaderOverrides,
+    pub(crate) cloud_requirements: CloudRequirementsLoader,
+    pub(crate) feedback: CodexFeedback,
+    pub(crate) config_warnings: Vec<ConfigWarningNotification>,
 }
 
 impl MessageProcessor {
     /// Create a new `MessageProcessor`, retaining a handle to the outgoing
     /// `Sender` so handlers can enqueue messages to be written to stdout.
-    pub(crate) fn new(
-        outgoing: OutgoingMessageSender,
-        codex_linux_sandbox_exe: Option<PathBuf>,
-        config: Arc<Config>,
-        cli_overrides: Vec<(String, TomlValue)>,
-        loader_overrides: LoaderOverrides,
-        feedback: CodexFeedback,
-    ) -> Self {
+    pub(crate) fn new(args: MessageProcessorArgs) -> Self {
+        let MessageProcessorArgs {
+            outgoing,
+            codex_linux_sandbox_exe,
+            config,
+            cli_overrides,
+            loader_overrides,
+            cloud_requirements,
+            feedback,
+            config_warnings,
+        } = args;
         let outgoing = Arc::new(outgoing);
         let auth_manager = AuthManager::shared(
             config.codex_home.clone(),
             false,
             config.cli_auth_credentials_store_mode,
         );
+        auth_manager.set_forced_chatgpt_workspace_id(config.forced_chatgpt_workspace_id.clone());
+        auth_manager.set_external_auth_refresher(Arc::new(ExternalAuthRefreshBridge {
+            outgoing: outgoing.clone(),
+        }));
         let thread_manager = Arc::new(ThreadManager::new(
             config.codex_home.clone(),
             auth_manager.clone(),
             SessionSource::VSCode,
         ));
-        let codex_message_processor = CodexMessageProcessor::new(
+        let codex_message_processor = CodexMessageProcessor::new(CodexMessageProcessorArgs {
             auth_manager,
             thread_manager,
-            outgoing.clone(),
+            outgoing: outgoing.clone(),
             codex_linux_sandbox_exe,
-            Arc::clone(&config),
-            cli_overrides.clone(),
+            config: Arc::clone(&config),
+            cli_overrides: cli_overrides.clone(),
+            cloud_requirements: cloud_requirements.clone(),
             feedback,
+        });
+        let config_api = ConfigApi::new(
+            config.codex_home.clone(),
+            cli_overrides,
+            loader_overrides,
+            cloud_requirements,
         );
-        let config_api = ConfigApi::new(config.codex_home.clone(), cli_overrides, loader_overrides);
 
         Self {
             outgoing,
             codex_message_processor,
             config_api,
+            config,
             initialized: false,
+            config_warnings,
         }
     }
 
@@ -121,6 +223,28 @@ impl MessageProcessor {
                         title: _title,
                         version,
                     } = params.client_info;
+                    if let Err(error) = set_default_originator(name.clone()) {
+                        match error {
+                            SetOriginatorError::InvalidHeaderValue => {
+                                let error = JSONRPCErrorError {
+                                    code: INVALID_REQUEST_ERROR_CODE,
+                                    message: format!(
+                                        "Invalid clientInfo.name: '{name}'. Must be a valid HTTP header value."
+                                    ),
+                                    data: None,
+                                };
+                                self.outgoing.send_error(request_id, error).await;
+                                return;
+                            }
+                            SetOriginatorError::AlreadyInitialized => {
+                                // No-op. This is expected to happen if the originator is already set via env var.
+                                // TODO(owen): Once we remove support for CODEX_INTERNAL_ORIGINATOR_OVERRIDE,
+                                // this will be an unexpected state and we can return a JSON-RPC error indicating
+                                // internal server error.
+                            }
+                        }
+                    }
+                    set_default_client_residency_requirement(self.config.enforce_residency.value());
                     let user_agent_suffix = format!("{name}; {version}");
                     if let Ok(mut suffix) = USER_AGENT_SUFFIX.lock() {
                         *suffix = Some(user_agent_suffix);
@@ -131,6 +255,15 @@ impl MessageProcessor {
                     self.outgoing.send_response(request_id, response).await;
 
                     self.initialized = true;
+                    if !self.config_warnings.is_empty() {
+                        for notification in self.config_warnings.drain(..) {
+                            self.outgoing
+                                .send_server_notification(ServerNotification::ConfigWarning(
+                                    notification,
+                                ))
+                                .await;
+                        }
+                    }
 
                     return;
                 }
@@ -176,6 +309,19 @@ impl MessageProcessor {
         tracing::info!("<- notification: {:?}", notification);
     }
 
+    pub(crate) fn thread_created_receiver(&self) -> broadcast::Receiver<ThreadId> {
+        self.codex_message_processor.thread_created_receiver()
+    }
+
+    pub(crate) async fn try_attach_thread_listener(&mut self, thread_id: ThreadId) {
+        if !self.initialized {
+            return;
+        }
+        self.codex_message_processor
+            .try_attach_thread_listener(thread_id)
+            .await;
+    }
+
     /// Handle a standalone JSON-RPC response originating from the peer.
     pub(crate) async fn process_response(&mut self, response: JSONRPCResponse) {
         tracing::info!("<- response: {:?}", response);
@@ -184,8 +330,9 @@ impl MessageProcessor {
     }
 
     /// Handle an error object received from the peer.
-    pub(crate) fn process_error(&mut self, err: JSONRPCError) {
+    pub(crate) async fn process_error(&mut self, err: JSONRPCError) {
         tracing::error!("<- error: {:?}", err);
+        self.outgoing.notify_client_error(err.id, err.error).await;
     }
 
     async fn handle_config_read(&self, request_id: RequestId, params: ConfigReadParams) {

codex-rs/app-server/src/models.rs

@@ -4,12 +4,13 @@ use codex_app_server_protocol::Model;
 use codex_app_server_protocol::ReasoningEffortOption;
 use codex_core::ThreadManager;
 use codex_core::config::Config;
+use codex_core::models_manager::manager::RefreshStrategy;
 use codex_protocol::openai_models::ModelPreset;
 use codex_protocol::openai_models::ReasoningEffortPreset;
 
 pub async fn supported_models(thread_manager: Arc<ThreadManager>, config: &Config) -> Vec<Model> {
     thread_manager
-        .list_models(config)
+        .list_models(config, RefreshStrategy::OnlineIfUncached)
         .await
         .into_iter()
         .filter(|preset| preset.show_in_picker)
@@ -27,6 +28,7 @@ fn model_from_preset(preset: ModelPreset) -> Model {
             preset.supported_reasoning_efforts,
         ),
         default_reasoning_effort: preset.default_reasoning_effort,
+        supports_personality: preset.supports_personality,
         is_default: preset.is_default,
     }
 }

codex-rs/app-server/src/outgoing_message.rs

@@ -39,6 +39,14 @@ impl OutgoingMessageSender {
         &self,
         request: ServerRequestPayload,
     ) -> oneshot::Receiver<Result> {
+        let (_id, rx) = self.send_request_with_id(request).await;
+        rx
+    }
+
+    pub(crate) async fn send_request_with_id(
+        &self,
+        request: ServerRequestPayload,
+    ) -> (RequestId, oneshot::Receiver<Result>) {
         let id = RequestId::Integer(self.next_request_id.fetch_add(1, Ordering::Relaxed));
         let outgoing_message_id = id.clone();
         let (tx_approve, rx_approve) = oneshot::channel();
@@ -54,7 +62,7 @@ impl OutgoingMessageSender {
             let mut request_id_to_callback = self.request_id_to_callback.lock().await;
             request_id_to_callback.remove(&outgoing_message_id);
         }
-        rx_approve
+        (outgoing_message_id, rx_approve)
     }
 
     pub(crate) async fn notify_client_response(&self, id: RequestId, result: Result) {
@@ -75,6 +83,30 @@ impl OutgoingMessageSender {
         }
     }
 
+    pub(crate) async fn notify_client_error(&self, id: RequestId, error: JSONRPCErrorError) {
+        let entry = {
+            let mut request_id_to_callback = self.request_id_to_callback.lock().await;
+            request_id_to_callback.remove_entry(&id)
+        };
+
+        match entry {
+            Some((id, _sender)) => {
+                warn!("client responded with error for {id:?}: {error:?}");
+            }
+            None => {
+                warn!("could not find callback for {id:?}");
+            }
+        }
+    }
+
+    pub(crate) async fn cancel_request(&self, id: &RequestId) -> bool {
+        let entry = {
+            let mut request_id_to_callback = self.request_id_to_callback.lock().await;
+            request_id_to_callback.remove_entry(id)
+        };
+        entry.is_some()
+    }
+
     pub(crate) async fn send_response<T: Serialize>(&self, id: RequestId, response: T) {
         match serde_json::to_value(response) {
             Ok(result) => {
@@ -162,6 +194,7 @@ mod tests {
     use codex_app_server_protocol::AccountRateLimitsUpdatedNotification;
     use codex_app_server_protocol::AccountUpdatedNotification;
     use codex_app_server_protocol::AuthMode;
+    use codex_app_server_protocol::ConfigWarningNotification;
     use codex_app_server_protocol::LoginChatGptCompleteNotification;
     use codex_app_server_protocol::RateLimitSnapshot;
     use codex_app_server_protocol::RateLimitWindow;
@@ -279,4 +312,28 @@ mod tests {
             "ensure the notification serializes correctly"
         );
     }
+
+    #[test]
+    fn verify_config_warning_notification_serialization() {
+        let notification = ServerNotification::ConfigWarning(ConfigWarningNotification {
+            summary: "Config error: using defaults".to_string(),
+            details: Some("error loading config: bad config".to_string()),
+            path: None,
+            range: None,
+        });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!( {
+                "method": "configWarning",
+                "params": {
+                    "summary": "Config error: using defaults",
+                    "details": "error loading config: bad config",
+                },
+            }),
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
 }

codex-rs/app-server/tests/common/BUILD.bazel

@@ -0,0 +1,7 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "common",
+    crate_name = "app_test_support",
+    crate_srcs = glob(["*.rs"]),
+)

codex-rs/app-server/tests/common/auth_fixtures.rs

@@ -6,6 +6,7 @@ use base64::Engine;
 use base64::engine::general_purpose::URL_SAFE_NO_PAD;
 use chrono::DateTime;
 use chrono::Utc;
+use codex_app_server_protocol::AuthMode;
 use codex_core::auth::AuthCredentialsStoreMode;
 use codex_core::auth::AuthDotJson;
 use codex_core::auth::save_auth;
@@ -49,6 +50,16 @@ impl ChatGptAuthFixture {
         self
     }
 
+    pub fn chatgpt_user_id(mut self, chatgpt_user_id: impl Into<String>) -> Self {
+        self.claims.chatgpt_user_id = Some(chatgpt_user_id.into());
+        self
+    }
+
+    pub fn chatgpt_account_id(mut self, chatgpt_account_id: impl Into<String>) -> Self {
+        self.claims.chatgpt_account_id = Some(chatgpt_account_id.into());
+        self
+    }
+
     pub fn email(mut self, email: impl Into<String>) -> Self {
         self.claims.email = Some(email.into());
         self
@@ -69,6 +80,8 @@ impl ChatGptAuthFixture {
 pub struct ChatGptIdTokenClaims {
     pub email: Option<String>,
     pub plan_type: Option<String>,
+    pub chatgpt_user_id: Option<String>,
+    pub chatgpt_account_id: Option<String>,
 }
 
 impl ChatGptIdTokenClaims {
@@ -85,6 +98,16 @@ impl ChatGptIdTokenClaims {
         self.plan_type = Some(plan_type.into());
         self
     }
+
+    pub fn chatgpt_user_id(mut self, chatgpt_user_id: impl Into<String>) -> Self {
+        self.chatgpt_user_id = Some(chatgpt_user_id.into());
+        self
+    }
+
+    pub fn chatgpt_account_id(mut self, chatgpt_account_id: impl Into<String>) -> Self {
+        self.chatgpt_account_id = Some(chatgpt_account_id.into());
+        self
+    }
 }
 
 pub fn encode_id_token(claims: &ChatGptIdTokenClaims) -> Result<String> {
@@ -93,10 +116,20 @@ pub fn encode_id_token(claims: &ChatGptIdTokenClaims) -> Result<String> {
     if let Some(email) = &claims.email {
         payload.insert("email".to_string(), json!(email));
     }
+    let mut auth_payload = serde_json::Map::new();
     if let Some(plan_type) = &claims.plan_type {
+        auth_payload.insert("chatgpt_plan_type".to_string(), json!(plan_type));
+    }
+    if let Some(chatgpt_user_id) = &claims.chatgpt_user_id {
+        auth_payload.insert("chatgpt_user_id".to_string(), json!(chatgpt_user_id));
+    }
+    if let Some(chatgpt_account_id) = &claims.chatgpt_account_id {
+        auth_payload.insert("chatgpt_account_id".to_string(), json!(chatgpt_account_id));
+    }
+    if !auth_payload.is_empty() {
         payload.insert(
             "https://api.openai.com/auth".to_string(),
-            json!({ "chatgpt_plan_type": plan_type }),
+            serde_json::Value::Object(auth_payload),
         );
     }
     let payload = serde_json::Value::Object(payload);
@@ -126,6 +159,7 @@ pub fn write_chatgpt_auth(
     let last_refresh = fixture.last_refresh.unwrap_or_else(|| Some(Utc::now()));
 
     let auth = AuthDotJson {
+        auth_mode: Some(AuthMode::Chatgpt),
         openai_api_key: None,
         tokens: Some(tokens),
         last_refresh,

codex-rs/app-server/tests/common/config.rs

@@ -0,0 +1,72 @@
+use codex_core::features::FEATURES;
+use codex_core::features::Feature;
+use std::collections::BTreeMap;
+use std::path::Path;
+
+pub fn write_mock_responses_config_toml(
+    codex_home: &Path,
+    server_uri: &str,
+    feature_flags: &BTreeMap<Feature, bool>,
+    auto_compact_limit: i64,
+    requires_openai_auth: Option<bool>,
+    model_provider_id: &str,
+    compact_prompt: &str,
+) -> std::io::Result<()> {
+    // Phase 1: build the features block for config.toml.
+    let mut features = BTreeMap::from([(Feature::RemoteModels, false)]);
+    for (feature, enabled) in feature_flags {
+        features.insert(*feature, *enabled);
+    }
+    let feature_entries = features
+        .into_iter()
+        .map(|(feature, enabled)| {
+            let key = FEATURES
+                .iter()
+                .find(|spec| spec.id == feature)
+                .map(|spec| spec.key)
+                .unwrap_or_else(|| panic!("missing feature key for {feature:?}"));
+            format!("{key} = {enabled}")
+        })
+        .collect::<Vec<_>>()
+        .join("\n");
+    // Phase 2: build provider-specific config bits.
+    let requires_line = match requires_openai_auth {
+        Some(true) => "requires_openai_auth = true\n".to_string(),
+        Some(false) | None => String::new(),
+    };
+    let provider_block = if model_provider_id == "openai" {
+        String::new()
+    } else {
+        format!(
+            r#"
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "responses"
+request_max_retries = 0
+stream_max_retries = 0
+{requires_line}
+"#
+        )
+    };
+    // Phase 3: write the final config file.
+    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"
+compact_prompt = "{compact_prompt}"
+model_auto_compact_token_limit = {auto_compact_limit}
+
+model_provider = "{model_provider_id}"
+
+[features]
+{feature_entries}
+{provider_block}
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/common/lib.rs

@@ -1,4 +1,5 @@
 mod auth_fixtures;
+mod config;
 mod mcp_process;
 mod mock_model_server;
 mod models_cache;
@@ -10,6 +11,7 @@ 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 config::write_mock_responses_config_toml;
 pub use core_test_support::format_with_current_shell;
 pub use core_test_support::format_with_current_shell_display;
 pub use core_test_support::format_with_current_shell_display_non_login;
@@ -17,6 +19,7 @@ pub use core_test_support::format_with_current_shell_non_login;
 pub use core_test_support::test_path_buf_with_windows;
 pub use core_test_support::test_tmp_path;
 pub use core_test_support::test_tmp_path_buf;
+pub use mcp_process::DEFAULT_CLIENT_NAME;
 pub use mcp_process::McpProcess;
 pub use mock_model_server::create_mock_responses_server_repeating_assistant;
 pub use mock_model_server::create_mock_responses_server_sequence;
@@ -26,8 +29,12 @@ pub use models_cache::write_models_cache_with_models;
 pub use responses::create_apply_patch_sse_response;
 pub use responses::create_exec_command_sse_response;
 pub use responses::create_final_assistant_message_sse_response;
+pub use responses::create_request_user_input_sse_response;
 pub use responses::create_shell_command_sse_response;
 pub use rollout::create_fake_rollout;
+pub use rollout::create_fake_rollout_with_source;
+pub use rollout::create_fake_rollout_with_text_elements;
+pub use rollout::rollout_path;
 use serde::de::DeserializeOwned;
 
 pub fn to_response<T: DeserializeOwned>(response: JSONRPCResponse) -> anyhow::Result<T> {

codex-rs/app-server/tests/common/mcp_process.rs

@@ -12,11 +12,13 @@ use tokio::process::ChildStdout;
 
 use anyhow::Context;
 use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::AppsListParams;
 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::CollaborationModeListParams;
 use codex_app_server_protocol::ConfigBatchWriteParams;
 use codex_app_server_protocol::ConfigReadParams;
 use codex_app_server_protocol::ConfigValueWriteParams;
@@ -27,11 +29,13 @@ use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::InitializeParams;
 use codex_app_server_protocol::InterruptConversationParams;
 use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCErrorError;
 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::LoginAccountParams;
 use codex_app_server_protocol::LoginApiKeyParams;
 use codex_app_server_protocol::ModelListParams;
 use codex_app_server_protocol::NewConversationParams;
@@ -47,11 +51,14 @@ use codex_app_server_protocol::ThreadArchiveParams;
 use codex_app_server_protocol::ThreadForkParams;
 use codex_app_server_protocol::ThreadListParams;
 use codex_app_server_protocol::ThreadLoadedListParams;
+use codex_app_server_protocol::ThreadReadParams;
 use codex_app_server_protocol::ThreadResumeParams;
 use codex_app_server_protocol::ThreadRollbackParams;
 use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadUnarchiveParams;
 use codex_app_server_protocol::TurnInterruptParams;
 use codex_app_server_protocol::TurnStartParams;
+use codex_core::default_client::CODEX_INTERNAL_ORIGINATOR_OVERRIDE_ENV_VAR;
 use tokio::process::Command;
 
 pub struct McpProcess {
@@ -66,6 +73,8 @@ pub struct McpProcess {
     pending_messages: VecDeque<JSONRPCMessage>,
 }
 
+pub const DEFAULT_CLIENT_NAME: &str = "codex-app-server-tests";
+
 impl McpProcess {
     pub async fn new(codex_home: &Path) -> anyhow::Result<Self> {
         Self::new_with_env(codex_home, &[]).await
@@ -89,6 +98,7 @@ impl McpProcess {
         cmd.stderr(Stdio::piped());
         cmd.env("CODEX_HOME", codex_home);
         cmd.env("RUST_LOG", "debug");
+        cmd.env_remove(CODEX_INTERNAL_ORIGINATOR_OVERRIDE_ENV_VAR);
 
         for (k, v) in env_overrides {
             match v {
@@ -136,33 +146,62 @@ impl McpProcess {
 
     /// Performs the initialization handshake with the MCP server.
     pub async fn initialize(&mut self) -> anyhow::Result<()> {
-        let params = Some(serde_json::to_value(InitializeParams {
-            client_info: ClientInfo {
-                name: "codex-app-server-tests".to_string(),
+        let initialized = self
+            .initialize_with_client_info(ClientInfo {
+                name: DEFAULT_CLIENT_NAME.to_string(),
                 title: None,
                 version: "0.1.0".to_string(),
-            },
-        })?);
-        let req_id = self.send_request("initialize", params).await?;
-        let initialized = self.read_jsonrpc_message().await?;
-        let JSONRPCMessage::Response(response) = initialized else {
+            })
+            .await?;
+        let JSONRPCMessage::Response(_) = initialized else {
             unreachable!("expected JSONRPCMessage::Response for initialize, got {initialized:?}");
         };
-        if response.id != RequestId::Integer(req_id) {
-            anyhow::bail!(
-                "initialize response id mismatch: expected {}, got {:?}",
-                req_id,
-                response.id
-            );
-        }
-
-        // Send notifications/initialized to ack the response.
-        self.send_notification(ClientNotification::Initialized)
-            .await?;
-
         Ok(())
     }
 
+    /// Sends initialize with the provided client info and returns the response/error message.
+    pub async fn initialize_with_client_info(
+        &mut self,
+        client_info: ClientInfo,
+    ) -> anyhow::Result<JSONRPCMessage> {
+        let params = Some(serde_json::to_value(InitializeParams { client_info })?);
+        let request_id = self.send_request("initialize", params).await?;
+        let message = self.read_jsonrpc_message().await?;
+        match message {
+            JSONRPCMessage::Response(response) => {
+                if response.id != RequestId::Integer(request_id) {
+                    anyhow::bail!(
+                        "initialize response id mismatch: expected {}, got {:?}",
+                        request_id,
+                        response.id
+                    );
+                }
+
+                // Send notifications/initialized to ack the response.
+                self.send_notification(ClientNotification::Initialized)
+                    .await?;
+
+                Ok(JSONRPCMessage::Response(response))
+            }
+            JSONRPCMessage::Error(error) => {
+                if error.id != RequestId::Integer(request_id) {
+                    anyhow::bail!(
+                        "initialize error id mismatch: expected {}, got {:?}",
+                        request_id,
+                        error.id
+                    );
+                }
+                Ok(JSONRPCMessage::Error(error))
+            }
+            JSONRPCMessage::Notification(notification) => {
+                anyhow::bail!("unexpected JSONRPCMessage::Notification: {notification:?}");
+            }
+            JSONRPCMessage::Request(request) => {
+                anyhow::bail!("unexpected JSONRPCMessage::Request: {request:?}");
+            }
+        }
+    }
+
     /// Send a `newConversation` JSON-RPC request.
     pub async fn send_new_conversation_request(
         &mut self,
@@ -261,6 +300,20 @@ impl McpProcess {
         self.send_request("account/read", params).await
     }
 
+    /// Send an `account/login/start` JSON-RPC request with ChatGPT auth tokens.
+    pub async fn send_chatgpt_auth_tokens_login_request(
+        &mut self,
+        id_token: String,
+        access_token: String,
+    ) -> anyhow::Result<i64> {
+        let params = LoginAccountParams::ChatgptAuthTokens {
+            id_token,
+            access_token,
+        };
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/login/start", params).await
+    }
+
     /// Send a `feedback/upload` JSON-RPC request.
     pub async fn send_feedback_upload_request(
         &mut self,
@@ -329,6 +382,15 @@ impl McpProcess {
         self.send_request("thread/archive", params).await
     }
 
+    /// Send a `thread/unarchive` JSON-RPC request.
+    pub async fn send_thread_unarchive_request(
+        &mut self,
+        params: ThreadUnarchiveParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/unarchive", params).await
+    }
+
     /// Send a `thread/rollback` JSON-RPC request.
     pub async fn send_thread_rollback_request(
         &mut self,
@@ -356,6 +418,15 @@ impl McpProcess {
         self.send_request("thread/loaded/list", params).await
     }
 
+    /// Send a `thread/read` JSON-RPC request.
+    pub async fn send_thread_read_request(
+        &mut self,
+        params: ThreadReadParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/read", params).await
+    }
+
     /// Send a `model/list` JSON-RPC request.
     pub async fn send_list_models_request(
         &mut self,
@@ -365,6 +436,21 @@ impl McpProcess {
         self.send_request("model/list", params).await
     }
 
+    /// Send an `app/list` JSON-RPC request.
+    pub async fn send_apps_list_request(&mut self, params: AppsListParams) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("app/list", params).await
+    }
+
+    /// Send a `collaborationMode/list` JSON-RPC request.
+    pub async fn send_list_collaboration_modes_request(
+        &mut self,
+        params: CollaborationModeListParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("collaborationMode/list", params).await
+    }
+
     /// Send a `resumeConversation` JSON-RPC request.
     pub async fn send_resume_conversation_request(
         &mut self,
@@ -538,6 +624,15 @@ impl McpProcess {
             .await
     }
 
+    pub async fn send_error(
+        &mut self,
+        id: RequestId,
+        error: JSONRPCErrorError,
+    ) -> anyhow::Result<()> {
+        self.send_jsonrpc_message(JSONRPCMessage::Error(JSONRPCError { id, error }))
+            .await
+    }
+
     pub async fn send_notification(
         &mut self,
         notification: ClientNotification,
@@ -641,6 +736,10 @@ impl McpProcess {
         Ok(notification)
     }
 
+    pub async fn read_next_message(&mut self) -> anyhow::Result<JSONRPCMessage> {
+        self.read_stream_until_message(|_| true).await
+    }
+
     /// Clears any buffered messages so future reads only consider new stream items.
     ///
     /// We call this when e.g. we want to validate against the next turn and no longer care about

codex-rs/app-server/tests/common/models_cache.rs

@@ -25,8 +25,9 @@ fn preset_to_info(preset: &ModelPreset, priority: i32) -> ModelInfo {
         },
         supported_in_api: true,
         priority,
-        upgrade: preset.upgrade.as_ref().map(|u| u.id.clone()),
+        upgrade: preset.upgrade.as_ref().map(|u| u.into()),
         base_instructions: "base instructions".to_string(),
+        model_messages: None,
         supports_reasoning_summaries: false,
         support_verbosity: false,
         default_verbosity: None,

codex-rs/app-server/tests/common/responses.rs

@@ -60,3 +60,26 @@ pub fn create_exec_command_sse_response(call_id: &str) -> anyhow::Result<String>
         responses::ev_completed("resp-1"),
     ]))
 }
+
+pub fn create_request_user_input_sse_response(call_id: &str) -> anyhow::Result<String> {
+    let tool_call_arguments = serde_json::to_string(&json!({
+        "questions": [{
+            "id": "confirm_path",
+            "header": "Confirm",
+            "question": "Proceed with the plan?",
+            "options": [{
+                "label": "Yes (Recommended)",
+                "description": "Continue the current plan."
+            }, {
+                "label": "No",
+                "description": "Stop and revisit the approach."
+            }]
+        }]
+    }))?;
+
+    Ok(responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_function_call(call_id, "request_user_input", &tool_call_arguments),
+        responses::ev_completed("resp-1"),
+    ]))
+}

codex-rs/app-server/tests/common/rollout.rs

@@ -6,10 +6,23 @@ use codex_protocol::protocol::SessionMetaLine;
 use codex_protocol::protocol::SessionSource;
 use serde_json::json;
 use std::fs;
+use std::fs::FileTimes;
 use std::path::Path;
 use std::path::PathBuf;
 use uuid::Uuid;
 
+pub fn rollout_path(codex_home: &Path, filename_ts: &str, thread_id: &str) -> PathBuf {
+    let year = &filename_ts[0..4];
+    let month = &filename_ts[5..7];
+    let day = &filename_ts[8..10];
+    codex_home
+        .join("sessions")
+        .join(year)
+        .join(month)
+        .join(day)
+        .join(format!("rollout-{filename_ts}-{thread_id}.jsonl"))
+}
+
 /// 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.
@@ -25,30 +38,50 @@ pub fn create_fake_rollout(
     preview: &str,
     model_provider: Option<&str>,
     git_info: Option<GitInfo>,
+) -> Result<String> {
+    create_fake_rollout_with_source(
+        codex_home,
+        filename_ts,
+        meta_rfc3339,
+        preview,
+        model_provider,
+        git_info,
+        SessionSource::Cli,
+    )
+}
+
+/// Create a minimal rollout file with an explicit session source.
+pub fn create_fake_rollout_with_source(
+    codex_home: &Path,
+    filename_ts: &str,
+    meta_rfc3339: &str,
+    preview: &str,
+    model_provider: Option<&str>,
+    git_info: Option<GitInfo>,
+    source: SessionSource,
 ) -> Result<String> {
     let uuid = Uuid::new_v4();
     let uuid_str = uuid.to_string();
     let conversation_id = ThreadId::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"));
+    let file_path = rollout_path(codex_home, filename_ts, &uuid_str);
+    let dir = file_path
+        .parent()
+        .ok_or_else(|| anyhow::anyhow!("missing rollout parent directory"))?;
+    fs::create_dir_all(dir)?;
 
     // Build JSONL lines
     let meta = SessionMeta {
         id: conversation_id,
+        forked_from_id: None,
         timestamp: meta_rfc3339.to_string(),
         cwd: PathBuf::from("/"),
         originator: "codex".to_string(),
         cli_version: "0.0.0".to_string(),
-        instructions: None,
-        source: SessionSource::Cli,
+        source,
         model_provider: model_provider.map(str::to_string),
+        base_instructions: None,
+        dynamic_tools: None,
     };
     let payload = serde_json::to_value(SessionMetaLine {
         meta,
@@ -84,6 +117,86 @@ pub fn create_fake_rollout(
         .to_string(),
     ];
 
+    fs::write(&file_path, lines.join("\n") + "\n")?;
+    let parsed = chrono::DateTime::parse_from_rfc3339(meta_rfc3339)?.with_timezone(&chrono::Utc);
+    let times = FileTimes::new().set_modified(parsed.into());
+    std::fs::OpenOptions::new()
+        .append(true)
+        .open(&file_path)?
+        .set_times(times)?;
+    Ok(uuid_str)
+}
+
+pub fn create_fake_rollout_with_text_elements(
+    codex_home: &Path,
+    filename_ts: &str,
+    meta_rfc3339: &str,
+    preview: &str,
+    text_elements: Vec<serde_json::Value>,
+    model_provider: Option<&str>,
+    git_info: Option<GitInfo>,
+) -> Result<String> {
+    let uuid = Uuid::new_v4();
+    let uuid_str = uuid.to_string();
+    let conversation_id = ThreadId::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 meta = SessionMeta {
+        id: conversation_id,
+        forked_from_id: None,
+        timestamp: meta_rfc3339.to_string(),
+        cwd: PathBuf::from("/"),
+        originator: "codex".to_string(),
+        cli_version: "0.0.0".to_string(),
+        source: SessionSource::Cli,
+        model_provider: model_provider.map(str::to_string),
+        base_instructions: None,
+        dynamic_tools: None,
+    };
+    let payload = serde_json::to_value(SessionMetaLine {
+        meta,
+        git: git_info,
+    })?;
+
+    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,
+                "text_elements": text_elements,
+                "local_images": []
+            }
+        })
+        .to_string(),
+    ];
+
     fs::write(file_path, lines.join("\n") + "\n")?;
     Ok(uuid_str)
 }

codex-rs/app-server/tests/suite/codex_message_processor_flow.rs

@@ -108,12 +108,17 @@ async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
     let AddConversationSubscriptionResponse { subscription_id } =
         to_response::<AddConversationSubscriptionResponse>(add_listener_resp)?;
 
+    // Drop any buffered events from conversation setup to avoid
+    // matching an earlier task_complete.
+    mcp.clear_message_buffer();
+
     // 3) sendUserMessage (should trigger notifications; we only validate an OK response)
     let send_user_id = mcp
         .send_send_user_message_request(SendUserMessageParams {
             conversation_id,
             items: vec![codex_app_server_protocol::InputItem::Text {
                 text: "text".to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;
@@ -124,13 +129,38 @@ async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
     .await??;
     let SendUserMessageResponse {} = to_response::<SendUserMessageResponse>(send_user_resp)?;
 
-    // Verify the task_finished notification is received.
-    // Note this also ensures that the final request to the server was made.
-    let task_finished_notification: JSONRPCNotification = timeout(
+    let task_started_notification: JSONRPCNotification = timeout(
         DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+        mcp.read_stream_until_notification_message("codex/event/task_started"),
     )
     .await??;
+    let task_started_event: Event = serde_json::from_value(
+        task_started_notification
+            .params
+            .clone()
+            .expect("task_started should have params"),
+    )
+    .expect("task_started should deserialize to Event");
+
+    // Verify the task_finished notification for this turn is received.
+    // Note this also ensures that the final request to the server was made.
+    let task_finished_notification: JSONRPCNotification = loop {
+        let notification: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("codex/event/task_complete"),
+        )
+        .await??;
+        let event: Event = serde_json::from_value(
+            notification
+                .params
+                .clone()
+                .expect("task_complete should have params"),
+        )
+        .expect("task_complete should deserialize to Event");
+        if event.id == task_started_event.id {
+            break notification;
+        }
+    };
     let serde_json::Value::Object(map) = task_finished_notification
         .params
         .expect("notification should have params")
@@ -241,6 +271,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
             conversation_id,
             items: vec![codex_app_server_protocol::InputItem::Text {
                 text: "run python".to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;
@@ -283,7 +314,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
     )
     .await?;
 
-    // Wait for first TaskComplete
+    // Wait for first TurnComplete
     let _ = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
@@ -296,6 +327,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
             conversation_id,
             items: vec![codex_app_server_protocol::InputItem::Text {
                 text: "run python again".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: working_directory.clone(),
             approval_policy: AskForApproval::Never,
@@ -405,6 +437,7 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
             conversation_id,
             items: vec![InputItem::Text {
                 text: "first turn".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: first_cwd.clone(),
             approval_policy: AskForApproval::Never,
@@ -437,6 +470,7 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
             conversation_id,
             items: vec![InputItem::Text {
                 text: "second turn".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: second_cwd.clone(),
             approval_policy: AskForApproval::Never,

codex-rs/app-server/tests/suite/create_thread.rs

@@ -77,6 +77,7 @@ async fn test_conversation_create_and_send_message_ok() -> Result<()> {
             conversation_id,
             items: vec![InputItem::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;

codex-rs/app-server/tests/suite/fuzzy_file_search.rs

@@ -48,8 +48,7 @@ async fn test_fuzzy_file_search_sorts_and_includes_indices() -> Result<()> {
     .await??;
 
     let value = resp.result;
-    // The path separator on Windows affects the score.
-    let expected_score = if cfg!(windows) { 69 } else { 72 };
+    let expected_score = 72;
 
     assert_eq!(
         value,
@@ -59,16 +58,9 @@ async fn test_fuzzy_file_search_sorts_and_includes_indices() -> Result<()> {
                     "root": root_path.clone(),
                     "path": "abexy",
                     "file_name": "abexy",
-                    "score": 88,
+                    "score": 84,
                     "indices": [0, 1, 2],
                 },
-                {
-                    "root": root_path.clone(),
-                    "path": "abcde",
-                    "file_name": "abcde",
-                    "score": 74,
-                    "indices": [0, 1, 4],
-                },
                 {
                     "root": root_path.clone(),
                     "path": sub_abce_rel,
@@ -76,6 +68,13 @@ async fn test_fuzzy_file_search_sorts_and_includes_indices() -> Result<()> {
                     "score": expected_score,
                     "indices": [4, 5, 7],
                 },
+                {
+                    "root": root_path.clone(),
+                    "path": "abcde",
+                    "file_name": "abcde",
+                    "score": 71,
+                    "indices": [0, 1, 4],
+                },
             ]
         })
     );

codex-rs/app-server/tests/suite/interrupt.rs

@@ -105,6 +105,7 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
             conversation_id,
             items: vec![codex_app_server_protocol::InputItem::Text {
                 text: "run first sleep command".to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;

codex-rs/app-server/tests/suite/list_resume.rs

@@ -307,6 +307,7 @@ async fn test_list_and_resume_conversations() -> Result<()> {
         content: vec![ContentItem::InputText {
             text: fork_history_text.to_string(),
         }],
+        end_turn: None,
     }];
     let resume_with_history_req_id = mcp
         .send_resume_conversation_request(ResumeConversationParams {

codex-rs/app-server/tests/suite/output_schema.rs

@@ -80,6 +80,7 @@ async fn send_user_turn_accepts_output_schema_v1() -> Result<()> {
             conversation_id,
             items: vec![InputItem::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: codex_home.path().to_path_buf(),
             approval_policy: AskForApproval::Never,
@@ -181,6 +182,7 @@ async fn send_user_turn_output_schema_is_per_turn_v1() -> Result<()> {
             conversation_id,
             items: vec![InputItem::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: codex_home.path().to_path_buf(),
             approval_policy: AskForApproval::Never,
@@ -228,6 +230,7 @@ async fn send_user_turn_output_schema_is_per_turn_v1() -> Result<()> {
             conversation_id,
             items: vec![InputItem::Text {
                 text: "Hello again".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: codex_home.path().to_path_buf(),
             approval_policy: AskForApproval::Never,

codex-rs/app-server/tests/suite/send_message.rs

@@ -11,13 +11,18 @@ use codex_app_server_protocol::NewConversationResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::SendUserMessageParams;
 use codex_app_server_protocol::SendUserMessageResponse;
+use codex_execpolicy::Policy;
 use codex_protocol::ThreadId;
 use codex_protocol::models::ContentItem;
+use codex_protocol::models::DeveloperInstructions;
 use codex_protocol::models::ResponseItem;
+use codex_protocol::protocol::AskForApproval;
 use codex_protocol::protocol::RawResponseItemEvent;
+use codex_protocol::protocol::SandboxPolicy;
 use core_test_support::responses;
 use pretty_assertions::assert_eq;
 use std::path::Path;
+use std::path::PathBuf;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
@@ -97,6 +102,7 @@ async fn send_message(
             conversation_id,
             items: vec![InputItem::Text {
                 text: message.to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;
@@ -190,10 +196,14 @@ async fn test_send_message_raw_notifications_opt_in() -> Result<()> {
             conversation_id,
             items: vec![InputItem::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;
 
+    let permissions = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_permissions_message(&permissions);
+
     let developer = read_raw_response_item(&mut mcp, conversation_id).await;
     assert_developer_message(&developer, "Use the test harness tools.");
 
@@ -238,6 +248,7 @@ async fn test_send_message_session_not_found() -> Result<()> {
             conversation_id: unknown,
             items: vec![InputItem::Text {
                 text: "ping".to_string(),
+                text_elements: Vec::new(),
             }],
         })
         .await?;
@@ -340,6 +351,29 @@ fn assert_instructions_message(item: &ResponseItem) {
     }
 }
 
+fn assert_permissions_message(item: &ResponseItem) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "developer");
+            let texts = content_texts(content);
+            let expected = DeveloperInstructions::from_policy(
+                &SandboxPolicy::DangerFullAccess,
+                AskForApproval::Never,
+                &Policy::empty(),
+                false,
+                &PathBuf::from("/tmp"),
+            )
+            .into_text();
+            assert_eq!(
+                texts,
+                vec![expected.as_str()],
+                "expected permissions developer message, got {texts:?}"
+            );
+        }
+        other => panic!("expected permissions message, got {other:?}"),
+    }
+}
+
 fn assert_developer_message(item: &ResponseItem, expected_text: &str) {
     match item {
         ResponseItem::Message { role, content, .. } => {
@@ -397,7 +431,7 @@ fn content_texts(content: &[ContentItem]) -> Vec<&str> {
     content
         .iter()
         .filter_map(|item| match item {
-            ContentItem::InputText { text } | ContentItem::OutputText { text } => {
+            ContentItem::InputText { text, .. } | ContentItem::OutputText { text } => {
                 Some(text.as_str())
             }
             _ => None,

codex-rs/app-server/tests/suite/user_agent.rs

@@ -1,4 +1,5 @@
 use anyhow::Result;
+use app_test_support::DEFAULT_CLIENT_NAME;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
 use codex_app_server_protocol::GetUserAgentResponse;
@@ -25,13 +26,13 @@ async fn get_user_agent_returns_current_codex_user_agent() -> Result<()> {
     .await??;
 
     let os_info = os_info::get();
-    let originator = codex_core::default_client::originator().value.as_str();
+    let originator = DEFAULT_CLIENT_NAME;
     let os_type = os_info.os_type();
     let os_version = os_info.version();
     let architecture = os_info.architecture().unwrap_or("unknown");
     let terminal_ua = codex_core::terminal::user_agent();
     let user_agent = format!(
-        "{originator}/0.0.0 ({os_type} {os_version}; {architecture}) {terminal_ua} (codex-app-server-tests; 0.1.0)"
+        "{originator}/0.0.0 ({os_type} {os_version}; {architecture}) {terminal_ua} ({DEFAULT_CLIENT_NAME}; 0.1.0)"
     );
 
     let received: GetUserAgentResponse = to_response(response)?;

codex-rs/app-server/tests/suite/v2/account.rs

@@ -4,28 +4,43 @@ use app_test_support::McpProcess;
 use app_test_support::to_response;
 
 use app_test_support::ChatGptAuthFixture;
+use app_test_support::ChatGptIdTokenClaims;
+use app_test_support::encode_id_token;
 use app_test_support::write_chatgpt_auth;
+use app_test_support::write_models_cache;
 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::CancelLoginAccountStatus;
+use codex_app_server_protocol::ChatgptAuthTokensRefreshReason;
+use codex_app_server_protocol::ChatgptAuthTokensRefreshResponse;
 use codex_app_server_protocol::GetAccountParams;
 use codex_app_server_protocol::GetAccountResponse;
 use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCErrorError;
+use codex_app_server_protocol::JSONRPCNotification;
 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_app_server_protocol::ServerRequest;
+use codex_app_server_protocol::TurnCompletedNotification;
+use codex_app_server_protocol::TurnStatus;
 use codex_core::auth::AuthCredentialsStoreMode;
 use codex_login::login_with_api_key;
 use codex_protocol::account::PlanType as AccountPlanType;
+use core_test_support::responses;
 use pretty_assertions::assert_eq;
+use serde_json::json;
 use serial_test::serial;
 use std::path::Path;
 use std::time::Duration;
 use tempfile::TempDir;
 use tokio::time::timeout;
+use wiremock::MockServer;
+use wiremock::ResponseTemplate;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
@@ -35,10 +50,14 @@ struct CreateConfigTomlParams {
     forced_method: Option<String>,
     forced_workspace_id: Option<String>,
     requires_openai_auth: Option<bool>,
+    base_url: Option<String>,
 }
 
 fn create_config_toml(codex_home: &Path, params: CreateConfigTomlParams) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");
+    let base_url = params
+        .base_url
+        .unwrap_or_else(|| "http://127.0.0.1:0/v1".to_string());
     let forced_line = if let Some(method) = params.forced_method {
         format!("forced_login_method = \"{method}\"\n")
     } else {
@@ -66,7 +85,7 @@ model_provider = "mock_provider"
 
 [model_providers.mock_provider]
 name = "Mock provider for test"
-base_url = "http://127.0.0.1:0/v1"
+base_url = "{base_url}"
 wire_api = "responses"
 request_max_retries = 0
 stream_max_retries = 0
@@ -133,6 +152,627 @@ async fn logout_account_removes_auth_and_notifies() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn set_auth_token_updates_account_and_notifies() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mock_server = MockServer::start().await;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            base_url: Some(format!("{}/v1", mock_server.uri())),
+            ..Default::default()
+        },
+    )?;
+    write_models_cache(codex_home.path())?;
+
+    let id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("embedded@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-embedded"),
+    )?;
+    let access_token = "access-embedded".to_string();
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(id_token.clone(), access_token)
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+
+    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_eq!(payload.auth_mode, Some(AuthMode::ChatgptAuthTokens));
+
+    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,
+        GetAccountResponse {
+            account: Some(Account::Chatgpt {
+                email: "embedded@example.com".to_string(),
+                plan_type: AccountPlanType::Pro,
+            }),
+            requires_openai_auth: true,
+        }
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn account_read_refresh_token_is_noop_in_external_mode() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            ..Default::default()
+        },
+    )?;
+    write_models_cache(codex_home.path())?;
+
+    let id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("embedded@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-embedded"),
+    )?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(id_token, "access-embedded".to_string())
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+    let _updated = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+
+    let get_id = mcp
+        .send_get_account_request(GetAccountParams {
+            refresh_token: true,
+        })
+        .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,
+        GetAccountResponse {
+            account: Some(Account::Chatgpt {
+                email: "embedded@example.com".to_string(),
+                plan_type: AccountPlanType::Pro,
+            }),
+            requires_openai_auth: true,
+        }
+    );
+
+    let refresh_request = timeout(
+        Duration::from_millis(250),
+        mcp.read_stream_until_request_message(),
+    )
+    .await;
+    assert!(
+        refresh_request.is_err(),
+        "external mode should not emit account/chatgptAuthTokens/refresh for refreshToken=true"
+    );
+
+    Ok(())
+}
+
+async fn respond_to_refresh_request(
+    mcp: &mut McpProcess,
+    access_token: &str,
+    id_token: &str,
+) -> Result<()> {
+    let refresh_req: ServerRequest = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ChatgptAuthTokensRefresh { request_id, params } = refresh_req else {
+        bail!("expected account/chatgptAuthTokens/refresh request, got {refresh_req:?}");
+    };
+    assert_eq!(params.reason, ChatgptAuthTokensRefreshReason::Unauthorized);
+    let response = ChatgptAuthTokensRefreshResponse {
+        access_token: access_token.to_string(),
+        id_token: id_token.to_string(),
+    };
+    mcp.send_response(request_id, serde_json::to_value(response)?)
+        .await?;
+    Ok(())
+}
+
+#[tokio::test]
+// 401 response triggers account/chatgptAuthTokens/refresh and retries with new tokens.
+async fn external_auth_refreshes_on_unauthorized() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mock_server = MockServer::start().await;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            base_url: Some(format!("{}/v1", mock_server.uri())),
+            ..Default::default()
+        },
+    )?;
+    write_models_cache(codex_home.path())?;
+
+    let success_sse = responses::sse(vec![
+        responses::ev_response_created("resp-turn"),
+        responses::ev_assistant_message("msg-turn", "turn ok"),
+        responses::ev_completed("resp-turn"),
+    ]);
+    let unauthorized = ResponseTemplate::new(401).set_body_json(json!({
+        "error": { "message": "unauthorized" }
+    }));
+    let responses_mock = responses::mount_response_sequence(
+        &mock_server,
+        vec![unauthorized, responses::sse_response(success_sse)],
+    )
+    .await;
+
+    let initial_id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("initial@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-initial"),
+    )?;
+    let refreshed_id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("refreshed@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-refreshed"),
+    )?;
+    let initial_access_token = "access-initial".to_string();
+    let refreshed_access_token = "access-refreshed".to_string();
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(
+            initial_id_token.clone(),
+            initial_access_token.clone(),
+        )
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+    let _updated = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+
+    let thread_req = mcp
+        .send_thread_start_request(codex_app_server_protocol::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 thread = to_response::<codex_app_server_protocol::ThreadStartResponse>(thread_resp)?;
+
+    let turn_req = mcp
+        .send_turn_start_request(codex_app_server_protocol::TurnStartParams {
+            thread_id: thread.thread.id,
+            input: vec![codex_app_server_protocol::UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    respond_to_refresh_request(&mut mcp, &refreshed_access_token, &refreshed_id_token).await?;
+    let _turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let _turn_completed = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let requests = responses_mock.requests();
+    assert_eq!(requests.len(), 2);
+    assert_eq!(
+        requests[0].header("authorization"),
+        Some(format!("Bearer {initial_access_token}"))
+    );
+    assert_eq!(
+        requests[1].header("authorization"),
+        Some(format!("Bearer {refreshed_access_token}"))
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+// Client returns JSON-RPC error to refresh; turn fails.
+async fn external_auth_refresh_error_fails_turn() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mock_server = MockServer::start().await;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            base_url: Some(format!("{}/v1", mock_server.uri())),
+            ..Default::default()
+        },
+    )?;
+    write_models_cache(codex_home.path())?;
+
+    let unauthorized = ResponseTemplate::new(401).set_body_json(json!({
+        "error": { "message": "unauthorized" }
+    }));
+    let _responses_mock =
+        responses::mount_response_sequence(&mock_server, vec![unauthorized]).await;
+
+    let initial_id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("initial@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-initial"),
+    )?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(initial_id_token, "access-initial".to_string())
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+    let _updated = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+
+    let thread_req = mcp
+        .send_thread_start_request(codex_app_server_protocol::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 thread = to_response::<codex_app_server_protocol::ThreadStartResponse>(thread_resp)?;
+
+    let turn_req = mcp
+        .send_turn_start_request(codex_app_server_protocol::TurnStartParams {
+            thread_id: thread.thread.id.clone(),
+            input: vec![codex_app_server_protocol::UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+
+    let refresh_req: ServerRequest = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ChatgptAuthTokensRefresh { request_id, .. } = refresh_req else {
+        bail!("expected account/chatgptAuthTokens/refresh request, got {refresh_req:?}");
+    };
+
+    mcp.send_error(
+        request_id,
+        JSONRPCErrorError {
+            code: -32_000,
+            message: "refresh failed".to_string(),
+            data: None,
+        },
+    )
+    .await?;
+
+    let _turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .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::Failed);
+    assert!(completed.turn.error.is_some());
+
+    Ok(())
+}
+
+#[tokio::test]
+// Refresh returns tokens for the wrong workspace; turn fails.
+async fn external_auth_refresh_mismatched_workspace_fails_turn() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mock_server = MockServer::start().await;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            forced_workspace_id: Some("org-expected".to_string()),
+            requires_openai_auth: Some(true),
+            base_url: Some(format!("{}/v1", mock_server.uri())),
+            ..Default::default()
+        },
+    )?;
+    write_models_cache(codex_home.path())?;
+
+    let unauthorized = ResponseTemplate::new(401).set_body_json(json!({
+        "error": { "message": "unauthorized" }
+    }));
+    let _responses_mock =
+        responses::mount_response_sequence(&mock_server, vec![unauthorized]).await;
+
+    let initial_id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("initial@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-expected"),
+    )?;
+    let refreshed_id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("refreshed@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-other"),
+    )?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(initial_id_token, "access-initial".to_string())
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+    let _updated = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+
+    let thread_req = mcp
+        .send_thread_start_request(codex_app_server_protocol::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 thread = to_response::<codex_app_server_protocol::ThreadStartResponse>(thread_resp)?;
+
+    let turn_req = mcp
+        .send_turn_start_request(codex_app_server_protocol::TurnStartParams {
+            thread_id: thread.thread.id.clone(),
+            input: vec![codex_app_server_protocol::UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+
+    let refresh_req: ServerRequest = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ChatgptAuthTokensRefresh { request_id, .. } = refresh_req else {
+        bail!("expected account/chatgptAuthTokens/refresh request, got {refresh_req:?}");
+    };
+
+    mcp.send_response(
+        request_id,
+        serde_json::to_value(ChatgptAuthTokensRefreshResponse {
+            access_token: "access-refreshed".to_string(),
+            id_token: refreshed_id_token,
+        })?,
+    )
+    .await?;
+
+    let _turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .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::Failed);
+    assert!(completed.turn.error.is_some());
+
+    Ok(())
+}
+
+#[tokio::test]
+// Refresh returns a malformed id_token; turn fails.
+async fn external_auth_refresh_invalid_id_token_fails_turn() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mock_server = MockServer::start().await;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            base_url: Some(format!("{}/v1", mock_server.uri())),
+            ..Default::default()
+        },
+    )?;
+    write_models_cache(codex_home.path())?;
+
+    let unauthorized = ResponseTemplate::new(401).set_body_json(json!({
+        "error": { "message": "unauthorized" }
+    }));
+    let _responses_mock =
+        responses::mount_response_sequence(&mock_server, vec![unauthorized]).await;
+
+    let initial_id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("initial@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-initial"),
+    )?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(initial_id_token, "access-initial".to_string())
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+    let _updated = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+
+    let thread_req = mcp
+        .send_thread_start_request(codex_app_server_protocol::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 thread = to_response::<codex_app_server_protocol::ThreadStartResponse>(thread_resp)?;
+
+    let turn_req = mcp
+        .send_turn_start_request(codex_app_server_protocol::TurnStartParams {
+            thread_id: thread.thread.id.clone(),
+            input: vec![codex_app_server_protocol::UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+
+    let refresh_req: ServerRequest = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ChatgptAuthTokensRefresh { request_id, .. } = refresh_req else {
+        bail!("expected account/chatgptAuthTokens/refresh request, got {refresh_req:?}");
+    };
+
+    mcp.send_response(
+        request_id,
+        serde_json::to_value(ChatgptAuthTokensRefreshResponse {
+            access_token: "access-refreshed".to_string(),
+            id_token: "not-a-jwt".to_string(),
+        })?,
+    )
+    .await?;
+
+    let _turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .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::Failed);
+    assert!(completed.turn.error.is_some());
+
+    Ok(())
+}
+
 #[tokio::test]
 async fn login_account_api_key_succeeds_and_notifies() -> Result<()> {
     let codex_home = TempDir::new()?;
@@ -304,6 +944,71 @@ async fn login_account_chatgpt_start_can_be_cancelled() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn set_auth_token_cancels_active_chatgpt_login() -> 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??;
+
+    // Initiate the ChatGPT login flow
+    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, .. } = login else {
+        bail!("unexpected login response: {login:?}");
+    };
+
+    let id_token = encode_id_token(
+        &ChatGptIdTokenClaims::new()
+            .email("embedded@example.com")
+            .plan_type("pro")
+            .chatgpt_account_id("org-embedded"),
+    )?;
+    // Set an external auth token instead of completing the ChatGPT login flow.
+    // This should cancel the active login attempt.
+    let set_id = mcp
+        .send_chatgpt_auth_tokens_login_request(id_token, "access-embedded".to_string())
+        .await?;
+    let set_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(set_id)),
+    )
+    .await??;
+    let response: LoginAccountResponse = to_response(set_resp)?;
+    assert_eq!(response, LoginAccountResponse::ChatgptAuthTokens {});
+    let _updated = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+
+    // Verify that the active login attempt was cancelled.
+    // We check this by trying to cancel it and expecting a not found error.
+    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 cancel: CancelLoginAccountResponse = to_response(cancel_resp)?;
+    assert_eq!(cancel.status, CancelLoginAccountStatus::NotFound);
+
+    Ok(())
+}
+
 #[tokio::test]
 // Serialize tests that launch the login server since it binds to a fixed port.
 #[serial(login_port)]

codex-rs/app-server/tests/suite/v2/analytics.rs

@@ -0,0 +1,66 @@
+use anyhow::Result;
+use codex_core::config::ConfigBuilder;
+use codex_core::config::types::OtelExporterKind;
+use codex_core::config::types::OtelHttpProtocol;
+use pretty_assertions::assert_eq;
+use std::collections::HashMap;
+use tempfile::TempDir;
+
+const SERVICE_VERSION: &str = "0.0.0-test";
+
+fn set_metrics_exporter(config: &mut codex_core::config::Config) {
+    config.otel.metrics_exporter = OtelExporterKind::OtlpHttp {
+        endpoint: "http://localhost:4318".to_string(),
+        headers: HashMap::new(),
+        protocol: OtelHttpProtocol::Json,
+        tls: None,
+    };
+}
+
+#[tokio::test]
+async fn app_server_default_analytics_disabled_without_flag() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut config = ConfigBuilder::default()
+        .codex_home(codex_home.path().to_path_buf())
+        .build()
+        .await?;
+    set_metrics_exporter(&mut config);
+    config.analytics_enabled = None;
+
+    let provider = codex_core::otel_init::build_provider(
+        &config,
+        SERVICE_VERSION,
+        Some("codex_app_server"),
+        false,
+    )
+    .map_err(|err| anyhow::anyhow!(err.to_string()))?;
+
+    // With analytics unset in the config and the default flag is false, metrics are disabled.
+    // No provider is built.
+    assert_eq!(provider.is_none(), true);
+    Ok(())
+}
+
+#[tokio::test]
+async fn app_server_default_analytics_enabled_with_flag() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut config = ConfigBuilder::default()
+        .codex_home(codex_home.path().to_path_buf())
+        .build()
+        .await?;
+    set_metrics_exporter(&mut config);
+    config.analytics_enabled = None;
+
+    let provider = codex_core::otel_init::build_provider(
+        &config,
+        SERVICE_VERSION,
+        Some("codex_app_server"),
+        true,
+    )
+    .map_err(|err| anyhow::anyhow!(err.to_string()))?;
+
+    // With analytics unset in the config and the default flag is true, metrics are enabled.
+    let has_metrics = provider.as_ref().and_then(|otel| otel.metrics()).is_some();
+    assert_eq!(has_metrics, true);
+    Ok(())
+}

codex-rs/app-server/tests/suite/v2/app_list.rs

@@ -0,0 +1,400 @@
+use std::borrow::Cow;
+use std::sync::Arc;
+use std::time::Duration;
+
+use anyhow::Result;
+use app_test_support::ChatGptAuthFixture;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use app_test_support::write_chatgpt_auth;
+use axum::Json;
+use axum::Router;
+use axum::extract::State;
+use axum::http::HeaderMap;
+use axum::http::StatusCode;
+use axum::http::header::AUTHORIZATION;
+use axum::routing::get;
+use codex_app_server_protocol::AppInfo;
+use codex_app_server_protocol::AppsListParams;
+use codex_app_server_protocol::AppsListResponse;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_core::auth::AuthCredentialsStoreMode;
+use pretty_assertions::assert_eq;
+use rmcp::handler::server::ServerHandler;
+use rmcp::model::JsonObject;
+use rmcp::model::ListToolsResult;
+use rmcp::model::Meta;
+use rmcp::model::ServerCapabilities;
+use rmcp::model::ServerInfo;
+use rmcp::model::Tool;
+use rmcp::model::ToolAnnotations;
+use rmcp::transport::StreamableHttpServerConfig;
+use rmcp::transport::StreamableHttpService;
+use rmcp::transport::streamable_http_server::session::local::LocalSessionManager;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::net::TcpListener;
+use tokio::task::JoinHandle;
+use tokio::time::timeout;
+
+const DEFAULT_TIMEOUT: Duration = Duration::from_secs(10);
+
+#[tokio::test]
+async fn list_apps_returns_empty_when_connectors_disabled() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_apps_list_request(AppsListParams {
+            limit: Some(50),
+            cursor: None,
+        })
+        .await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let AppsListResponse { data, next_cursor } = to_response(response)?;
+
+    assert!(data.is_empty());
+    assert!(next_cursor.is_none());
+    Ok(())
+}
+
+#[tokio::test]
+async fn list_apps_returns_connectors_with_accessible_flags() -> Result<()> {
+    let connectors = vec![
+        AppInfo {
+            id: "alpha".to_string(),
+            name: "Alpha".to_string(),
+            description: Some("Alpha connector".to_string()),
+            logo_url: Some("https://example.com/alpha.png".to_string()),
+            logo_url_dark: None,
+            distribution_channel: None,
+            install_url: None,
+            is_accessible: false,
+        },
+        AppInfo {
+            id: "beta".to_string(),
+            name: "beta".to_string(),
+            description: None,
+            logo_url: None,
+            logo_url_dark: None,
+            distribution_channel: None,
+            install_url: None,
+            is_accessible: false,
+        },
+    ];
+
+    let tools = vec![connector_tool("beta", "Beta App")?];
+    let (server_url, server_handle) = start_apps_server(connectors.clone(), tools).await?;
+
+    let codex_home = TempDir::new()?;
+    write_connectors_config(codex_home.path(), &server_url)?;
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("chatgpt-token")
+            .account_id("account-123")
+            .chatgpt_user_id("user-123")
+            .chatgpt_account_id("account-123"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_apps_list_request(AppsListParams {
+            limit: None,
+            cursor: None,
+        })
+        .await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let AppsListResponse { data, next_cursor } = to_response(response)?;
+
+    let expected = vec![
+        AppInfo {
+            id: "beta".to_string(),
+            name: "Beta App".to_string(),
+            description: None,
+            logo_url: None,
+            logo_url_dark: None,
+            distribution_channel: None,
+            install_url: Some("https://chatgpt.com/apps/beta/beta".to_string()),
+            is_accessible: true,
+        },
+        AppInfo {
+            id: "alpha".to_string(),
+            name: "Alpha".to_string(),
+            description: Some("Alpha connector".to_string()),
+            logo_url: Some("https://example.com/alpha.png".to_string()),
+            logo_url_dark: None,
+            distribution_channel: None,
+            install_url: Some("https://chatgpt.com/apps/alpha/alpha".to_string()),
+            is_accessible: false,
+        },
+    ];
+
+    assert_eq!(data, expected);
+    assert!(next_cursor.is_none());
+
+    server_handle.abort();
+    Ok(())
+}
+
+#[tokio::test]
+async fn list_apps_paginates_results() -> Result<()> {
+    let connectors = vec![
+        AppInfo {
+            id: "alpha".to_string(),
+            name: "Alpha".to_string(),
+            description: Some("Alpha connector".to_string()),
+            logo_url: None,
+            logo_url_dark: None,
+            distribution_channel: None,
+            install_url: None,
+            is_accessible: false,
+        },
+        AppInfo {
+            id: "beta".to_string(),
+            name: "beta".to_string(),
+            description: None,
+            logo_url: None,
+            logo_url_dark: None,
+            distribution_channel: None,
+            install_url: None,
+            is_accessible: false,
+        },
+    ];
+
+    let tools = vec![connector_tool("beta", "Beta App")?];
+    let (server_url, server_handle) = start_apps_server(connectors.clone(), tools).await?;
+
+    let codex_home = TempDir::new()?;
+    write_connectors_config(codex_home.path(), &server_url)?;
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("chatgpt-token")
+            .account_id("account-123")
+            .chatgpt_user_id("user-123")
+            .chatgpt_account_id("account-123"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let first_request = mcp
+        .send_apps_list_request(AppsListParams {
+            limit: Some(1),
+            cursor: None,
+        })
+        .await?;
+    let first_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(first_request)),
+    )
+    .await??;
+    let AppsListResponse {
+        data: first_page,
+        next_cursor: first_cursor,
+    } = to_response(first_response)?;
+
+    let expected_first = vec![AppInfo {
+        id: "beta".to_string(),
+        name: "Beta App".to_string(),
+        description: None,
+        logo_url: None,
+        logo_url_dark: None,
+        distribution_channel: None,
+        install_url: Some("https://chatgpt.com/apps/beta/beta".to_string()),
+        is_accessible: true,
+    }];
+
+    assert_eq!(first_page, expected_first);
+    let next_cursor = first_cursor.ok_or_else(|| anyhow::anyhow!("missing cursor"))?;
+
+    let second_request = mcp
+        .send_apps_list_request(AppsListParams {
+            limit: Some(1),
+            cursor: Some(next_cursor),
+        })
+        .await?;
+    let second_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(second_request)),
+    )
+    .await??;
+    let AppsListResponse {
+        data: second_page,
+        next_cursor: second_cursor,
+    } = to_response(second_response)?;
+
+    let expected_second = vec![AppInfo {
+        id: "alpha".to_string(),
+        name: "Alpha".to_string(),
+        description: Some("Alpha connector".to_string()),
+        logo_url: None,
+        logo_url_dark: None,
+        distribution_channel: None,
+        install_url: Some("https://chatgpt.com/apps/alpha/alpha".to_string()),
+        is_accessible: false,
+    }];
+
+    assert_eq!(second_page, expected_second);
+    assert!(second_cursor.is_none());
+
+    server_handle.abort();
+    Ok(())
+}
+
+#[derive(Clone)]
+struct AppsServerState {
+    expected_bearer: String,
+    expected_account_id: String,
+    response: serde_json::Value,
+}
+
+#[derive(Clone)]
+struct AppListMcpServer {
+    tools: Arc<Vec<Tool>>,
+}
+
+impl AppListMcpServer {
+    fn new(tools: Arc<Vec<Tool>>) -> Self {
+        Self { tools }
+    }
+}
+
+impl ServerHandler for AppListMcpServer {
+    fn get_info(&self) -> ServerInfo {
+        ServerInfo {
+            capabilities: ServerCapabilities::builder().enable_tools().build(),
+            ..ServerInfo::default()
+        }
+    }
+
+    fn list_tools(
+        &self,
+        _request: Option<rmcp::model::PaginatedRequestParam>,
+        _context: rmcp::service::RequestContext<rmcp::service::RoleServer>,
+    ) -> impl std::future::Future<Output = Result<ListToolsResult, rmcp::ErrorData>> + Send + '_
+    {
+        let tools = self.tools.clone();
+        async move {
+            Ok(ListToolsResult {
+                tools: (*tools).clone(),
+                next_cursor: None,
+                meta: None,
+            })
+        }
+    }
+}
+
+async fn start_apps_server(
+    connectors: Vec<AppInfo>,
+    tools: Vec<Tool>,
+) -> Result<(String, JoinHandle<()>)> {
+    let state = AppsServerState {
+        expected_bearer: "Bearer chatgpt-token".to_string(),
+        expected_account_id: "account-123".to_string(),
+        response: json!({ "apps": connectors, "next_token": null }),
+    };
+    let state = Arc::new(state);
+    let tools = Arc::new(tools);
+
+    let listener = TcpListener::bind("127.0.0.1:0").await?;
+    let addr = listener.local_addr()?;
+
+    let mcp_service = StreamableHttpService::new(
+        {
+            let tools = tools.clone();
+            move || Ok(AppListMcpServer::new(tools.clone()))
+        },
+        Arc::new(LocalSessionManager::default()),
+        StreamableHttpServerConfig::default(),
+    );
+
+    let router = Router::new()
+        .route("/connectors/directory/list", get(list_directory_connectors))
+        .route(
+            "/connectors/directory/list_workspace",
+            get(list_directory_connectors),
+        )
+        .with_state(state)
+        .nest_service("/api/codex/apps", mcp_service);
+
+    let handle = tokio::spawn(async move {
+        let _ = axum::serve(listener, router).await;
+    });
+
+    Ok((format!("http://{addr}"), handle))
+}
+
+async fn list_directory_connectors(
+    State(state): State<Arc<AppsServerState>>,
+    headers: HeaderMap,
+) -> Result<impl axum::response::IntoResponse, StatusCode> {
+    let bearer_ok = headers
+        .get(AUTHORIZATION)
+        .and_then(|value| value.to_str().ok())
+        .is_some_and(|value| value == state.expected_bearer);
+    let account_ok = headers
+        .get("chatgpt-account-id")
+        .and_then(|value| value.to_str().ok())
+        .is_some_and(|value| value == state.expected_account_id);
+
+    if bearer_ok && account_ok {
+        Ok(Json(state.response.clone()))
+    } else {
+        Err(StatusCode::UNAUTHORIZED)
+    }
+}
+
+fn connector_tool(connector_id: &str, connector_name: &str) -> Result<Tool> {
+    let schema: JsonObject = serde_json::from_value(json!({
+        "type": "object",
+        "additionalProperties": false
+    }))?;
+    let mut tool = Tool::new(
+        Cow::Owned(format!("connector_{connector_id}")),
+        Cow::Borrowed("Connector test tool"),
+        Arc::new(schema),
+    );
+    tool.annotations = Some(ToolAnnotations::new().read_only(true));
+
+    let mut meta = Meta::new();
+    meta.0
+        .insert("connector_id".to_string(), json!(connector_id));
+    meta.0
+        .insert("connector_name".to_string(), json!(connector_name));
+    tool.meta = Some(meta);
+    Ok(tool)
+}
+
+fn write_connectors_config(codex_home: &std::path::Path, base_url: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+chatgpt_base_url = "{base_url}"
+
+[features]
+connectors = true
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/suite/v2/collaboration_mode_list.rs

@@ -0,0 +1,111 @@
+//! Validates that the collaboration mode list endpoint returns the expected default presets.
+//!
+//! The test drives the app server through the MCP harness and asserts that the list response
+//! includes the plan, coding, pair programming, and execute modes with their default model and reasoning
+//! effort settings, which keeps the API contract visible in one place.
+
+#![allow(clippy::unwrap_used)]
+
+use std::time::Duration;
+
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::CollaborationModeListParams;
+use codex_app_server_protocol::CollaborationModeListResponse;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_core::models_manager::test_builtin_collaboration_mode_presets;
+use codex_protocol::config_types::CollaborationModeMask;
+use codex_protocol::config_types::ModeKind;
+use pretty_assertions::assert_eq;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_TIMEOUT: Duration = Duration::from_secs(10);
+
+/// Confirms the server returns the default collaboration mode presets in a stable order.
+#[tokio::test]
+async fn list_collaboration_modes_returns_presets() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_list_collaboration_modes_request(CollaborationModeListParams {})
+        .await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let CollaborationModeListResponse { data: items } =
+        to_response::<CollaborationModeListResponse>(response)?;
+
+    let expected = [
+        plan_preset(),
+        code_preset(),
+        pair_programming_preset(),
+        execute_preset(),
+    ];
+    assert_eq!(expected.len(), items.len());
+    for (expected_mask, actual_mask) in expected.iter().zip(items.iter()) {
+        assert_eq!(expected_mask.name, actual_mask.name);
+        assert_eq!(expected_mask.mode, actual_mask.mode);
+        assert_eq!(expected_mask.model, actual_mask.model);
+        assert_eq!(expected_mask.reasoning_effort, actual_mask.reasoning_effort);
+        assert_eq!(
+            expected_mask.developer_instructions,
+            actual_mask.developer_instructions
+        );
+    }
+    Ok(())
+}
+
+/// Builds the plan preset that the list response is expected to return.
+///
+/// If the defaults change in the app server, this helper should be updated alongside the
+/// contract, or the test will fail in ways that imply a regression in the API.
+fn plan_preset() -> CollaborationModeMask {
+    let presets = test_builtin_collaboration_mode_presets();
+    presets
+        .into_iter()
+        .find(|p| p.mode == Some(ModeKind::Plan))
+        .unwrap()
+}
+
+/// Builds the pair programming preset that the list response is expected to return.
+///
+/// The helper keeps the expected model and reasoning defaults co-located with the test
+/// so that mismatches point directly at the API contract being exercised.
+fn pair_programming_preset() -> CollaborationModeMask {
+    let presets = test_builtin_collaboration_mode_presets();
+    presets
+        .into_iter()
+        .find(|p| p.mode == Some(ModeKind::PairProgramming))
+        .unwrap()
+}
+
+/// Builds the code preset that the list response is expected to return.
+fn code_preset() -> CollaborationModeMask {
+    let presets = test_builtin_collaboration_mode_presets();
+    presets
+        .into_iter()
+        .find(|p| p.mode == Some(ModeKind::Code))
+        .unwrap()
+}
+
+/// Builds the execute preset that the list response is expected to return.
+///
+/// The execute preset uses a different reasoning effort to capture the higher-effort
+/// execution contract the server currently exposes.
+fn execute_preset() -> CollaborationModeMask {
+    let presets = test_builtin_collaboration_mode_presets();
+    presets
+        .into_iter()
+        .find(|p| p.mode == Some(ModeKind::Execute))
+        .unwrap()
+}

codex-rs/app-server/tests/suite/v2/compaction.rs

@@ -0,0 +1,282 @@
+//! End-to-end compaction flow tests.
+//!
+//! Phases:
+//! 1) Arrange: mock responses/compact endpoints + config.
+//! 2) Act: start a thread and submit multiple turns to trigger auto-compaction.
+//! 3) Assert: verify item/started + item/completed notifications for context compaction.
+
+#![expect(clippy::expect_used)]
+
+use anyhow::Result;
+use app_test_support::ChatGptAuthFixture;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use app_test_support::write_chatgpt_auth;
+use app_test_support::write_mock_responses_config_toml;
+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::RequestId;
+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::UserInput as V2UserInput;
+use codex_core::auth::AuthCredentialsStoreMode;
+use codex_core::features::Feature;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
+use core_test_support::responses;
+use core_test_support::skip_if_no_network;
+use pretty_assertions::assert_eq;
+use std::collections::BTreeMap;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+const AUTO_COMPACT_LIMIT: i64 = 1_000;
+const COMPACT_PROMPT: &str = "Summarize the conversation.";
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn auto_compaction_local_emits_started_and_completed_items() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = responses::start_mock_server().await;
+    let sse1 = responses::sse(vec![
+        responses::ev_assistant_message("m1", "FIRST_REPLY"),
+        responses::ev_completed_with_tokens("r1", 70_000),
+    ]);
+    let sse2 = responses::sse(vec![
+        responses::ev_assistant_message("m2", "SECOND_REPLY"),
+        responses::ev_completed_with_tokens("r2", 330_000),
+    ]);
+    let sse3 = responses::sse(vec![
+        responses::ev_assistant_message("m3", "LOCAL_SUMMARY"),
+        responses::ev_completed_with_tokens("r3", 200),
+    ]);
+    let sse4 = responses::sse(vec![
+        responses::ev_assistant_message("m4", "FINAL_REPLY"),
+        responses::ev_completed_with_tokens("r4", 120),
+    ]);
+    responses::mount_sse_sequence(&server, vec![sse1, sse2, sse3, sse4]).await;
+
+    let codex_home = TempDir::new()?;
+    write_mock_responses_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        &BTreeMap::default(),
+        AUTO_COMPACT_LIMIT,
+        None,
+        "mock_provider",
+        COMPACT_PROMPT,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let thread_id = start_thread(&mut mcp).await?;
+    for message in ["first", "second", "third"] {
+        send_turn_and_wait(&mut mcp, &thread_id, message).await?;
+    }
+
+    let started = wait_for_context_compaction_started(&mut mcp).await?;
+    let completed = wait_for_context_compaction_completed(&mut mcp).await?;
+
+    let ThreadItem::ContextCompaction { id: started_id } = started.item else {
+        unreachable!("started item should be context compaction");
+    };
+    let ThreadItem::ContextCompaction { id: completed_id } = completed.item else {
+        unreachable!("completed item should be context compaction");
+    };
+
+    assert_eq!(started.thread_id, thread_id);
+    assert_eq!(completed.thread_id, thread_id);
+    assert_eq!(started_id, completed_id);
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn auto_compaction_remote_emits_started_and_completed_items() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = responses::start_mock_server().await;
+    let sse1 = responses::sse(vec![
+        responses::ev_assistant_message("m1", "FIRST_REPLY"),
+        responses::ev_completed_with_tokens("r1", 70_000),
+    ]);
+    let sse2 = responses::sse(vec![
+        responses::ev_assistant_message("m2", "SECOND_REPLY"),
+        responses::ev_completed_with_tokens("r2", 330_000),
+    ]);
+    let sse3 = responses::sse(vec![
+        responses::ev_assistant_message("m3", "FINAL_REPLY"),
+        responses::ev_completed_with_tokens("r3", 120),
+    ]);
+    let responses_log = responses::mount_sse_sequence(&server, vec![sse1, sse2, sse3]).await;
+
+    let compacted_history = vec![
+        ResponseItem::Message {
+            id: None,
+            role: "assistant".to_string(),
+            content: vec![ContentItem::OutputText {
+                text: "REMOTE_COMPACT_SUMMARY".to_string(),
+            }],
+            end_turn: None,
+        },
+        ResponseItem::Compaction {
+            encrypted_content: "ENCRYPTED_COMPACTION_SUMMARY".to_string(),
+        },
+    ];
+    let compact_mock = responses::mount_compact_json_once(
+        &server,
+        serde_json::json!({ "output": compacted_history }),
+    )
+    .await;
+
+    let codex_home = TempDir::new()?;
+    let mut features = BTreeMap::default();
+    features.insert(Feature::RemoteCompaction, true);
+    write_mock_responses_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        &features,
+        AUTO_COMPACT_LIMIT,
+        Some(true),
+        "openai",
+        COMPACT_PROMPT,
+    )?;
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("access-chatgpt").plan_type("pro"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let server_base_url = format!("{}/v1", server.uri());
+    let mut mcp = McpProcess::new_with_env(
+        codex_home.path(),
+        &[
+            ("OPENAI_BASE_URL", Some(server_base_url.as_str())),
+            ("OPENAI_API_KEY", None),
+        ],
+    )
+    .await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let thread_id = start_thread(&mut mcp).await?;
+    for message in ["first", "second", "third"] {
+        send_turn_and_wait(&mut mcp, &thread_id, message).await?;
+    }
+
+    let started = wait_for_context_compaction_started(&mut mcp).await?;
+    let completed = wait_for_context_compaction_completed(&mut mcp).await?;
+
+    let ThreadItem::ContextCompaction { id: started_id } = started.item else {
+        unreachable!("started item should be context compaction");
+    };
+    let ThreadItem::ContextCompaction { id: completed_id } = completed.item else {
+        unreachable!("completed item should be context compaction");
+    };
+
+    assert_eq!(started.thread_id, thread_id);
+    assert_eq!(completed.thread_id, thread_id);
+    assert_eq!(started_id, completed_id);
+
+    let compact_requests = compact_mock.requests();
+    assert_eq!(compact_requests.len(), 1);
+    assert_eq!(compact_requests[0].path(), "/v1/responses/compact");
+
+    let response_requests = responses_log.requests();
+    assert_eq!(response_requests.len(), 3);
+
+    Ok(())
+}
+
+async fn start_thread(mcp: &mut McpProcess) -> Result<String> {
+    let thread_id = 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_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
+    Ok(thread.id)
+}
+
+async fn send_turn_and_wait(mcp: &mut McpProcess, thread_id: &str, text: &str) -> Result<String> {
+    let turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread_id.to_string(),
+            input: vec![V2UserInput::Text {
+                text: text.to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..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)?;
+    wait_for_turn_completed(mcp, &turn.id).await?;
+    Ok(turn.id)
+}
+
+async fn wait_for_turn_completed(mcp: &mut McpProcess, turn_id: &str) -> Result<()> {
+    loop {
+        let notification: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("turn/completed"),
+        )
+        .await??;
+        let completed: TurnCompletedNotification =
+            serde_json::from_value(notification.params.clone().expect("turn/completed params"))?;
+        if completed.turn.id == turn_id {
+            return Ok(());
+        }
+    }
+}
+
+async fn wait_for_context_compaction_started(
+    mcp: &mut McpProcess,
+) -> Result<ItemStartedNotification> {
+    loop {
+        let notification: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("item/started"),
+        )
+        .await??;
+        let started: ItemStartedNotification =
+            serde_json::from_value(notification.params.clone().expect("item/started params"))?;
+        if let ThreadItem::ContextCompaction { .. } = started.item {
+            return Ok(started);
+        }
+    }
+}
+
+async fn wait_for_context_compaction_completed(
+    mcp: &mut McpProcess,
+) -> Result<ItemCompletedNotification> {
+    loop {
+        let notification: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("item/completed"),
+        )
+        .await??;
+        let completed: ItemCompletedNotification =
+            serde_json::from_value(notification.params.clone().expect("item/completed params"))?;
+        if let ThreadItem::ContextCompaction { .. } = completed.item {
+            return Ok(completed);
+        }
+    }
+}

codex-rs/app-server/tests/suite/v2/config_rpc.rs

@@ -18,7 +18,10 @@ use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::SandboxMode;
 use codex_app_server_protocol::ToolsV2;
 use codex_app_server_protocol::WriteStatus;
+use codex_core::config::set_project_trust_level;
 use codex_core::config_loader::SYSTEM_CONFIG_TOML_FILE_UNIX;
+use codex_protocol::config_types::TrustLevel;
+use codex_protocol::openai_models::ReasoningEffort;
 use codex_utils_absolute_path::AbsolutePathBuf;
 use pretty_assertions::assert_eq;
 use serde_json::json;
@@ -53,6 +56,7 @@ sandbox_mode = "workspace-write"
     let request_id = mcp
         .send_config_read_request(ConfigReadParams {
             include_layers: true,
+            cwd: None,
         })
         .await?;
     let resp: JSONRPCResponse = timeout(
@@ -101,6 +105,7 @@ view_image = false
     let request_id = mcp
         .send_config_read_request(ConfigReadParams {
             include_layers: true,
+            cwd: None,
         })
         .await?;
     let resp: JSONRPCResponse = timeout(
@@ -141,6 +146,52 @@ view_image = false
     Ok(())
 }
 
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_read_includes_project_layers_for_cwd() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_config(&codex_home, r#"model = "gpt-user""#)?;
+
+    let workspace = TempDir::new()?;
+    let project_config_dir = workspace.path().join(".codex");
+    std::fs::create_dir_all(&project_config_dir)?;
+    std::fs::write(
+        project_config_dir.join("config.toml"),
+        r#"
+model_reasoning_effort = "high"
+"#,
+    )?;
+    set_project_trust_level(codex_home.path(), workspace.path(), TrustLevel::Trusted)?;
+    let project_config = AbsolutePathBuf::try_from(project_config_dir)?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_config_read_request(ConfigReadParams {
+            include_layers: true,
+            cwd: Some(workspace.path().to_string_lossy().into_owned()),
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ConfigReadResponse {
+        config, origins, ..
+    } = to_response(resp)?;
+
+    assert_eq!(config.model_reasoning_effort, Some(ReasoningEffort::High));
+    assert_eq!(
+        origins.get("model_reasoning_effort").expect("origin").name,
+        ConfigLayerSource::Project {
+            dot_codex_folder: project_config
+        }
+    );
+
+    Ok(())
+}
+
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn config_read_includes_system_layer_and_overrides() -> Result<()> {
     let codex_home = TempDir::new()?;
@@ -195,6 +246,7 @@ writable_roots = [{}]
     let request_id = mcp
         .send_config_read_request(ConfigReadParams {
             include_layers: true,
+            cwd: None,
         })
         .await?;
     let resp: JSONRPCResponse = timeout(
@@ -281,6 +333,7 @@ model = "gpt-old"
     let read_id = mcp
         .send_config_read_request(ConfigReadParams {
             include_layers: false,
+            cwd: None,
         })
         .await?;
     let read_resp: JSONRPCResponse = timeout(
@@ -315,6 +368,7 @@ model = "gpt-old"
     let verify_id = mcp
         .send_config_read_request(ConfigReadParams {
             include_layers: false,
+            cwd: None,
         })
         .await?;
     let verify_resp: JSONRPCResponse = timeout(
@@ -411,6 +465,7 @@ async fn config_batch_write_applies_multiple_edits() -> Result<()> {
     let read_id = mcp
         .send_config_read_request(ConfigReadParams {
             include_layers: false,
+            cwd: None,
         })
         .await?;
     let read_resp: JSONRPCResponse = timeout(

codex-rs/app-server/tests/suite/v2/dynamic_tools.rs

@@ -0,0 +1,286 @@
+use anyhow::Context;
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_responses_server_sequence_unchecked;
+use app_test_support::to_response;
+use codex_app_server_protocol::DynamicToolCallParams;
+use codex_app_server_protocol::DynamicToolCallResponse;
+use codex_app_server_protocol::DynamicToolSpec;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+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::UserInput as V2UserInput;
+use core_test_support::responses;
+use pretty_assertions::assert_eq;
+use serde_json::Value;
+use serde_json::json;
+use std::path::Path;
+use std::time::Duration;
+use tempfile::TempDir;
+use tokio::time::timeout;
+use wiremock::MockServer;
+
+const DEFAULT_READ_TIMEOUT: Duration = Duration::from_secs(10);
+
+/// Ensures dynamic tool specs are serialized into the model request payload.
+#[tokio::test]
+async fn thread_start_injects_dynamic_tools_into_model_requests() -> Result<()> {
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
+    let server = create_mock_responses_server_sequence_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??;
+
+    // Use a minimal JSON schema so we can assert the tool payload round-trips.
+    let input_schema = json!({
+        "type": "object",
+        "properties": {
+            "city": { "type": "string" }
+        },
+        "required": ["city"],
+        "additionalProperties": false,
+    });
+    let dynamic_tool = DynamicToolSpec {
+        name: "demo_tool".to_string(),
+        description: "Demo dynamic tool".to_string(),
+        input_schema: input_schema.clone(),
+    };
+
+    // Thread start injects dynamic tools into the thread's tool registry.
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            dynamic_tools: Some(vec![dynamic_tool.clone()]),
+            ..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 so a model request is issued.
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp)?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    // Inspect the captured model request to assert the tool spec made it through.
+    let bodies = responses_bodies(&server).await?;
+    let body = bodies
+        .first()
+        .context("expected at least one responses request")?;
+    let tool = find_tool(body, &dynamic_tool.name)
+        .context("expected dynamic tool to be injected into request")?;
+
+    assert_eq!(
+        tool.get("description"),
+        Some(&Value::String(dynamic_tool.description.clone()))
+    );
+    assert_eq!(tool.get("parameters"), Some(&input_schema));
+
+    Ok(())
+}
+
+/// Exercises the full dynamic tool call path (server request, client response, model output).
+#[tokio::test]
+async fn dynamic_tool_call_round_trip_sends_output_to_model() -> Result<()> {
+    let call_id = "dyn-call-1";
+    let tool_name = "demo_tool";
+    let tool_args = json!({ "city": "Paris" });
+    let tool_call_arguments = serde_json::to_string(&tool_args)?;
+
+    // First response triggers a dynamic tool call, second closes the turn.
+    let responses = vec![
+        responses::sse(vec![
+            responses::ev_response_created("resp-1"),
+            responses::ev_function_call(call_id, tool_name, &tool_call_arguments),
+            responses::ev_completed("resp-1"),
+        ]),
+        create_final_assistant_message_sse_response("Done")?,
+    ];
+    let server = create_mock_responses_server_sequence_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 dynamic_tool = DynamicToolSpec {
+        name: tool_name.to_string(),
+        description: "Demo dynamic tool".to_string(),
+        input_schema: json!({
+            "type": "object",
+            "properties": {
+                "city": { "type": "string" }
+            },
+            "required": ["city"],
+            "additionalProperties": false,
+        }),
+    };
+
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            dynamic_tools: Some(vec![dynamic_tool]),
+            ..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 so the tool call is emitted.
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Run the tool".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..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)?;
+
+    // Read the tool call request from the app server.
+    let request = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let (request_id, params) = match request {
+        ServerRequest::DynamicToolCall { request_id, params } => (request_id, params),
+        other => panic!("expected DynamicToolCall request, got {other:?}"),
+    };
+
+    let expected = DynamicToolCallParams {
+        thread_id: thread.id,
+        turn_id: turn.id,
+        call_id: call_id.to_string(),
+        tool: tool_name.to_string(),
+        arguments: tool_args.clone(),
+    };
+    assert_eq!(params, expected);
+
+    // Respond to the tool call so the model receives a function_call_output.
+    let response = DynamicToolCallResponse {
+        output: "dynamic-ok".to_string(),
+        success: true,
+    };
+    mcp.send_response(request_id, serde_json::to_value(response)?)
+        .await?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let bodies = responses_bodies(&server).await?;
+    let output = bodies
+        .iter()
+        .find_map(|body| function_call_output_text(body, call_id))
+        .context("expected function_call_output in follow-up request")?;
+    assert_eq!(output, "dynamic-ok");
+
+    Ok(())
+}
+
+async fn responses_bodies(server: &MockServer) -> Result<Vec<Value>> {
+    let requests = server
+        .received_requests()
+        .await
+        .context("failed to fetch received requests")?;
+
+    requests
+        .into_iter()
+        .filter(|req| req.url.path().ends_with("/responses"))
+        .map(|req| {
+            req.body_json::<Value>()
+                .context("request body should be JSON")
+        })
+        .collect()
+}
+
+fn find_tool<'a>(body: &'a Value, name: &str) -> Option<&'a Value> {
+    body.get("tools")
+        .and_then(Value::as_array)
+        .and_then(|tools| {
+            tools
+                .iter()
+                .find(|tool| tool.get("name").and_then(Value::as_str) == Some(name))
+        })
+}
+
+fn function_call_output_text(body: &Value, call_id: &str) -> Option<String> {
+    body.get("input")
+        .and_then(Value::as_array)
+        .and_then(|items| {
+            items.iter().find(|item| {
+                item.get("type").and_then(Value::as_str) == Some("function_call_output")
+                    && item.get("call_id").and_then(Value::as_str) == Some(call_id)
+            })
+        })
+        .and_then(|item| item.get("output"))
+        .and_then(Value::as_str)
+        .map(str::to_string)
+}
+
+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 = "responses"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/suite/v2/initialize.rs

@@ -0,0 +1,137 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_mock_responses_server_sequence_unchecked;
+use app_test_support::to_response;
+use codex_app_server_protocol::ClientInfo;
+use codex_app_server_protocol::InitializeResponse;
+use codex_app_server_protocol::JSONRPCMessage;
+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 initialize_uses_client_info_name_as_originator() -> Result<()> {
+    let responses = Vec::new();
+    let server = create_mock_responses_server_sequence_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?;
+
+    let message = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.initialize_with_client_info(ClientInfo {
+            name: "codex_vscode".to_string(),
+            title: Some("Codex VS Code Extension".to_string()),
+            version: "0.1.0".to_string(),
+        }),
+    )
+    .await??;
+
+    let JSONRPCMessage::Response(response) = message else {
+        anyhow::bail!("expected initialize response, got {message:?}");
+    };
+    let InitializeResponse { user_agent } = to_response::<InitializeResponse>(response)?;
+
+    assert!(user_agent.starts_with("codex_vscode/"));
+    Ok(())
+}
+
+#[tokio::test]
+async fn initialize_respects_originator_override_env_var() -> Result<()> {
+    let responses = Vec::new();
+    let server = create_mock_responses_server_sequence_unchecked(responses).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri(), "never")?;
+    let mut mcp = McpProcess::new_with_env(
+        codex_home.path(),
+        &[(
+            "CODEX_INTERNAL_ORIGINATOR_OVERRIDE",
+            Some("codex_originator_via_env_var"),
+        )],
+    )
+    .await?;
+
+    let message = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.initialize_with_client_info(ClientInfo {
+            name: "codex_vscode".to_string(),
+            title: Some("Codex VS Code Extension".to_string()),
+            version: "0.1.0".to_string(),
+        }),
+    )
+    .await??;
+
+    let JSONRPCMessage::Response(response) = message else {
+        anyhow::bail!("expected initialize response, got {message:?}");
+    };
+    let InitializeResponse { user_agent } = to_response::<InitializeResponse>(response)?;
+
+    assert!(user_agent.starts_with("codex_originator_via_env_var/"));
+    Ok(())
+}
+
+#[tokio::test]
+async fn initialize_rejects_invalid_client_name() -> Result<()> {
+    let responses = Vec::new();
+    let server = create_mock_responses_server_sequence_unchecked(responses).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri(), "never")?;
+    let mut mcp = McpProcess::new_with_env(
+        codex_home.path(),
+        &[("CODEX_INTERNAL_ORIGINATOR_OVERRIDE", None)],
+    )
+    .await?;
+
+    let message = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.initialize_with_client_info(ClientInfo {
+            name: "bad\rname".to_string(),
+            title: Some("Bad Client".to_string()),
+            version: "0.1.0".to_string(),
+        }),
+    )
+    .await??;
+
+    let JSONRPCMessage::Error(error) = message else {
+        anyhow::bail!("expected initialize error, got {message:?}");
+    };
+
+    assert_eq!(error.error.code, -32600);
+    assert_eq!(
+        error.error.message,
+        "Invalid clientInfo.name: 'bad\rname'. Must be a valid HTTP header value."
+    );
+    assert_eq!(error.error.data, None);
+    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 = "responses"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/suite/v2/mod.rs

@@ -1,15 +1,25 @@
 mod account;
+mod analytics;
+mod app_list;
+mod collaboration_mode_list;
+mod compaction;
 mod config_rpc;
+mod dynamic_tools;
+mod initialize;
 mod model_list;
 mod output_schema;
+mod plan_item;
 mod rate_limits;
+mod request_user_input;
 mod review;
 mod thread_archive;
 mod thread_fork;
 mod thread_list;
 mod thread_loaded_list;
+mod thread_read;
 mod thread_resume;
 mod thread_rollback;
 mod thread_start;
+mod thread_unarchive;
 mod turn_interrupt;
 mod turn_start;

codex-rs/app-server/tests/suite/v2/model_list.rs

@@ -72,6 +72,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
                 },
             ],
             default_reasoning_effort: ReasoningEffort::Medium,
+            supports_personality: false,
             is_default: true,
         },
         Model {
@@ -99,6 +100,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
                 },
             ],
             default_reasoning_effort: ReasoningEffort::Medium,
+            supports_personality: false,
             is_default: false,
         },
         Model {
@@ -118,6 +120,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
                 },
             ],
             default_reasoning_effort: ReasoningEffort::Medium,
+            supports_personality: false,
             is_default: false,
         },
         Model {
@@ -151,6 +154,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
                 },
             ],
             default_reasoning_effort: ReasoningEffort::Medium,
+            supports_personality: false,
             is_default: false,
         },
     ];

codex-rs/app-server/tests/suite/v2/output_schema.rs

@@ -61,6 +61,7 @@ async fn turn_start_accepts_output_schema_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
             output_schema: Some(output_schema.clone()),
             ..Default::default()
@@ -142,6 +143,7 @@ async fn turn_start_output_schema_is_per_turn_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
             output_schema: Some(output_schema.clone()),
             ..Default::default()
@@ -183,6 +185,7 @@ async fn turn_start_output_schema_is_per_turn_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "Hello again".to_string(),
+                text_elements: Vec::new(),
             }],
             output_schema: None,
             ..Default::default()

codex-rs/app-server/tests/suite/v2/plan_item.rs

@@ -0,0 +1,257 @@
+use anyhow::Result;
+use anyhow::anyhow;
+use app_test_support::McpProcess;
+use app_test_support::create_mock_responses_server_sequence;
+use app_test_support::to_response;
+use codex_app_server_protocol::ItemCompletedNotification;
+use codex_app_server_protocol::ItemStartedNotification;
+use codex_app_server_protocol::JSONRPCMessage;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::PlanDeltaNotification;
+use codex_app_server_protocol::RequestId;
+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::TurnStatus;
+use codex_app_server_protocol::UserInput as V2UserInput;
+use codex_core::features::FEATURES;
+use codex_core::features::Feature;
+use codex_protocol::config_types::CollaborationMode;
+use codex_protocol::config_types::ModeKind;
+use codex_protocol::config_types::Settings;
+use core_test_support::responses;
+use core_test_support::skip_if_no_network;
+use pretty_assertions::assert_eq;
+use std::collections::BTreeMap;
+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 plan_mode_uses_proposed_plan_block_for_plan_item() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let plan_block = "<proposed_plan>\n# Final plan\n- first\n- second\n</proposed_plan>\n";
+    let full_message = format!("Preface\n{plan_block}Postscript");
+    let responses = vec![responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_message_item_added("msg-1", ""),
+        responses::ev_output_text_delta(&full_message),
+        responses::ev_assistant_message("msg-1", &full_message),
+        responses::ev_completed("resp-1"),
+    ])];
+    let server = create_mock_responses_server_sequence(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 turn = start_plan_mode_turn(&mut mcp).await?;
+    let (_, completed_items, plan_deltas, turn_completed) =
+        collect_turn_notifications(&mut mcp).await?;
+
+    assert_eq!(turn_completed.turn.id, turn.id);
+    assert_eq!(turn_completed.turn.status, TurnStatus::Completed);
+
+    let expected_plan = ThreadItem::Plan {
+        id: format!("{}-plan", turn.id),
+        text: "# Final plan\n- first\n- second\n".to_string(),
+    };
+    let expected_plan_id = format!("{}-plan", turn.id);
+    let streamed_plan = plan_deltas
+        .iter()
+        .map(|delta| delta.delta.as_str())
+        .collect::<String>();
+    assert_eq!(streamed_plan, "# Final plan\n- first\n- second\n");
+    assert!(
+        plan_deltas
+            .iter()
+            .all(|delta| delta.item_id == expected_plan_id)
+    );
+    let plan_items = completed_items
+        .iter()
+        .filter_map(|item| match item {
+            ThreadItem::Plan { .. } => Some(item.clone()),
+            _ => None,
+        })
+        .collect::<Vec<_>>();
+    assert_eq!(plan_items, vec![expected_plan]);
+    assert!(
+        completed_items
+            .iter()
+            .any(|item| matches!(item, ThreadItem::AgentMessage { .. })),
+        "agent message items should still be emitted alongside the plan item"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn plan_mode_without_proposed_plan_does_not_emit_plan_item() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let responses = vec![responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_assistant_message("msg-1", "Done"),
+        responses::ev_completed("resp-1"),
+    ])];
+    let server = create_mock_responses_server_sequence(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 _turn = start_plan_mode_turn(&mut mcp).await?;
+    let (_, completed_items, plan_deltas, _) = collect_turn_notifications(&mut mcp).await?;
+
+    let has_plan_item = completed_items
+        .iter()
+        .any(|item| matches!(item, ThreadItem::Plan { .. }));
+    assert!(!has_plan_item);
+    assert!(plan_deltas.is_empty());
+
+    Ok(())
+}
+
+async fn start_plan_mode_turn(mcp: &mut McpProcess) -> Result<codex_app_server_protocol::Turn> {
+    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 thread = to_response::<ThreadStartResponse>(thread_resp)?.thread;
+
+    let collaboration_mode = CollaborationMode {
+        mode: ModeKind::Plan,
+        settings: Settings {
+            model: "mock-model".to_string(),
+            reasoning_effort: None,
+            developer_instructions: None,
+        },
+    };
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id,
+            input: vec![V2UserInput::Text {
+                text: "Plan this".to_string(),
+                text_elements: Vec::new(),
+            }],
+            collaboration_mode: Some(collaboration_mode),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    Ok(to_response::<TurnStartResponse>(turn_resp)?.turn)
+}
+
+async fn collect_turn_notifications(
+    mcp: &mut McpProcess,
+) -> Result<(
+    Vec<ThreadItem>,
+    Vec<ThreadItem>,
+    Vec<PlanDeltaNotification>,
+    TurnCompletedNotification,
+)> {
+    let mut started_items = Vec::new();
+    let mut completed_items = Vec::new();
+    let mut plan_deltas = Vec::new();
+
+    loop {
+        let message = timeout(DEFAULT_READ_TIMEOUT, mcp.read_next_message()).await??;
+        let JSONRPCMessage::Notification(notification) = message else {
+            continue;
+        };
+        match notification.method.as_str() {
+            "item/started" => {
+                let params = notification
+                    .params
+                    .ok_or_else(|| anyhow!("item/started notifications must include params"))?;
+                let payload: ItemStartedNotification = serde_json::from_value(params)?;
+                started_items.push(payload.item);
+            }
+            "item/completed" => {
+                let params = notification
+                    .params
+                    .ok_or_else(|| anyhow!("item/completed notifications must include params"))?;
+                let payload: ItemCompletedNotification = serde_json::from_value(params)?;
+                completed_items.push(payload.item);
+            }
+            "item/plan/delta" => {
+                let params = notification
+                    .params
+                    .ok_or_else(|| anyhow!("item/plan/delta notifications must include params"))?;
+                let payload: PlanDeltaNotification = serde_json::from_value(params)?;
+                plan_deltas.push(payload);
+            }
+            "turn/completed" => {
+                let params = notification
+                    .params
+                    .ok_or_else(|| anyhow!("turn/completed notifications must include params"))?;
+                let payload: TurnCompletedNotification = serde_json::from_value(params)?;
+                return Ok((started_items, completed_items, plan_deltas, payload));
+            }
+            _ => {}
+        }
+    }
+}
+
+fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
+    let features = BTreeMap::from([
+        (Feature::RemoteModels, false),
+        (Feature::CollaborationModes, true),
+    ]);
+    let feature_entries = features
+        .into_iter()
+        .map(|(feature, enabled)| {
+            let key = FEATURES
+                .iter()
+                .find(|spec| spec.id == feature)
+                .map(|spec| spec.key)
+                .unwrap_or_else(|| panic!("missing feature key for {feature:?}"));
+            format!("{key} = {enabled}")
+        })
+        .collect::<Vec<_>>()
+        .join("\n");
+    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"
+
+[features]
+{feature_entries}
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "responses"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/suite/v2/request_user_input.rs

@@ -0,0 +1,138 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_responses_server_sequence;
+use app_test_support::create_request_user_input_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+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::UserInput as V2UserInput;
+use codex_protocol::config_types::CollaborationMode;
+use codex_protocol::config_types::ModeKind;
+use codex_protocol::config_types::Settings;
+use codex_protocol::openai_models::ReasoningEffort;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn request_user_input_round_trip() -> Result<()> {
+    let codex_home = tempfile::TempDir::new()?;
+    let responses = vec![
+        create_request_user_input_sse_response("call1")?,
+        create_final_assistant_message_sse_response("done")?,
+    ];
+    let server = create_mock_responses_server_sequence(responses).await;
+    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_start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let thread_start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(thread_start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response(thread_start_resp)?;
+
+    let turn_start_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "ask something".to_string(),
+                text_elements: Vec::new(),
+            }],
+            model: Some("mock-model".to_string()),
+            effort: Some(ReasoningEffort::Medium),
+            collaboration_mode: Some(CollaborationMode {
+                mode: ModeKind::Plan,
+                settings: Settings {
+                    model: "mock-model".to_string(),
+                    reasoning_effort: Some(ReasoningEffort::Medium),
+                    developer_instructions: None,
+                },
+            }),
+            ..Default::default()
+        })
+        .await?;
+    let turn_start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_start_id)),
+    )
+    .await??;
+    let TurnStartResponse { turn, .. } = to_response(turn_start_resp)?;
+
+    let server_req = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ToolRequestUserInput { request_id, params } = server_req else {
+        panic!("expected ToolRequestUserInput request, got: {server_req:?}");
+    };
+
+    assert_eq!(params.thread_id, thread.id);
+    assert_eq!(params.turn_id, turn.id);
+    assert_eq!(params.item_id, "call1");
+    assert_eq!(params.questions.len(), 1);
+
+    mcp.send_response(
+        request_id,
+        serde_json::json!({
+            "answers": {
+                "confirm_path": { "answers": ["yes"] }
+            }
+        }),
+    )
+    .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??;
+
+    Ok(())
+}
+
+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 = "untrusted"
+sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[features]
+collaboration_modes = true
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "responses"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/suite/v2/thread_fork.rs

@@ -77,8 +77,9 @@ async fn thread_fork_creates_new_thread_and_emits_started() -> Result<()> {
     assert_ne!(thread.id, conversation_id);
     assert_eq!(thread.preview, preview);
     assert_eq!(thread.model_provider, "mock_provider");
-    assert!(thread.path.is_absolute());
-    assert_ne!(thread.path, original_path);
+    let thread_path = thread.path.clone().expect("thread path");
+    assert!(thread_path.is_absolute());
+    assert_ne!(thread_path, original_path);
     assert!(thread.cwd.is_absolute());
     assert_eq!(thread.source, SessionSource::VsCode);
 
@@ -95,7 +96,8 @@ async fn thread_fork_creates_new_thread_and_emits_started() -> Result<()> {
             assert_eq!(
                 content,
                 &vec![UserInput::Text {
-                    text: preview.to_string()
+                    text: preview.to_string(),
+                    text_elements: Vec::new(),
                 }]
             );
         }

codex-rs/app-server/tests/suite/v2/thread_list.rs

@@ -1,17 +1,34 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_fake_rollout;
+use app_test_support::create_fake_rollout_with_source;
+use app_test_support::rollout_path;
 use app_test_support::to_response;
+use chrono::DateTime;
+use chrono::Utc;
 use codex_app_server_protocol::GitInfo as ApiGitInfo;
+use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::SessionSource;
 use codex_app_server_protocol::ThreadListResponse;
+use codex_app_server_protocol::ThreadSortKey;
+use codex_app_server_protocol::ThreadSourceKind;
+use codex_core::ARCHIVED_SESSIONS_SUBDIR;
+use codex_protocol::ThreadId;
 use codex_protocol::protocol::GitInfo as CoreGitInfo;
+use codex_protocol::protocol::SessionSource as CoreSessionSource;
+use codex_protocol::protocol::SubAgentSource;
+use pretty_assertions::assert_eq;
+use std::cmp::Reverse;
+use std::fs;
+use std::fs::FileTimes;
+use std::fs::OpenOptions;
 use std::path::Path;
 use std::path::PathBuf;
 use tempfile::TempDir;
 use tokio::time::timeout;
+use uuid::Uuid;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
@@ -26,12 +43,29 @@ async fn list_threads(
     cursor: Option<String>,
     limit: Option<u32>,
     providers: Option<Vec<String>>,
+    source_kinds: Option<Vec<ThreadSourceKind>>,
+    archived: Option<bool>,
+) -> Result<ThreadListResponse> {
+    list_threads_with_sort(mcp, cursor, limit, providers, source_kinds, None, archived).await
+}
+
+async fn list_threads_with_sort(
+    mcp: &mut McpProcess,
+    cursor: Option<String>,
+    limit: Option<u32>,
+    providers: Option<Vec<String>>,
+    source_kinds: Option<Vec<ThreadSourceKind>>,
+    sort_key: Option<ThreadSortKey>,
+    archived: Option<bool>,
 ) -> Result<ThreadListResponse> {
     let request_id = mcp
         .send_thread_list_request(codex_app_server_protocol::ThreadListParams {
             cursor,
             limit,
+            sort_key,
             model_providers: providers,
+            source_kinds,
+            archived,
         })
         .await?;
     let resp: JSONRPCResponse = timeout(
@@ -82,6 +116,16 @@ fn timestamp_at(
     )
 }
 
+fn set_rollout_mtime(path: &Path, updated_at_rfc3339: &str) -> Result<()> {
+    let parsed = DateTime::parse_from_rfc3339(updated_at_rfc3339)?.with_timezone(&Utc);
+    let times = FileTimes::new().set_modified(parsed.into());
+    OpenOptions::new()
+        .append(true)
+        .open(path)?
+        .set_times(times)?;
+    Ok(())
+}
+
 #[tokio::test]
 async fn thread_list_basic_empty() -> Result<()> {
     let codex_home = TempDir::new()?;
@@ -94,6 +138,8 @@ async fn thread_list_basic_empty() -> Result<()> {
         None,
         Some(10),
         Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert!(data.is_empty());
@@ -156,6 +202,8 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         None,
         Some(2),
         Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert_eq!(data1.len(), 2);
@@ -163,6 +211,7 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         assert_eq!(thread.preview, "Hello");
         assert_eq!(thread.model_provider, "mock_provider");
         assert!(thread.created_at > 0);
+        assert_eq!(thread.updated_at, thread.created_at);
         assert_eq!(thread.cwd, PathBuf::from("/"));
         assert_eq!(thread.cli_version, "0.0.0");
         assert_eq!(thread.source, SessionSource::Cli);
@@ -179,6 +228,8 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         Some(cursor1),
         Some(2),
         Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert!(data2.len() <= 2);
@@ -186,6 +237,7 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         assert_eq!(thread.preview, "Hello");
         assert_eq!(thread.model_provider, "mock_provider");
         assert!(thread.created_at > 0);
+        assert_eq!(thread.updated_at, thread.created_at);
         assert_eq!(thread.cwd, PathBuf::from("/"));
         assert_eq!(thread.cli_version, "0.0.0");
         assert_eq!(thread.source, SessionSource::Cli);
@@ -227,6 +279,8 @@ async fn thread_list_respects_provider_filter() -> Result<()> {
         None,
         Some(10),
         Some(vec!["other_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert_eq!(data.len(), 1);
@@ -236,6 +290,7 @@ async fn thread_list_respects_provider_filter() -> Result<()> {
     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);
+    assert_eq!(thread.updated_at, expected_ts);
     assert_eq!(thread.cwd, PathBuf::from("/"));
     assert_eq!(thread.cli_version, "0.0.0");
     assert_eq!(thread.source, SessionSource::Cli);
@@ -244,6 +299,207 @@ async fn thread_list_respects_provider_filter() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_list_empty_source_kinds_defaults_to_interactive_only() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let cli_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "CLI",
+        Some("mock_provider"),
+        None,
+    )?;
+    let exec_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-01T11-00-00",
+        "2025-02-01T11:00:00Z",
+        "Exec",
+        Some("mock_provider"),
+        None,
+        CoreSessionSource::Exec,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, next_cursor } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        Some(Vec::new()),
+        None,
+    )
+    .await?;
+
+    assert_eq!(next_cursor, None);
+    let ids: Vec<_> = data.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(ids, vec![cli_id.as_str()]);
+    assert_ne!(cli_id, exec_id);
+    assert_eq!(data[0].source, SessionSource::Cli);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_filters_by_source_kind_subagent_thread_spawn() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let cli_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "CLI",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let parent_thread_id = ThreadId::from_string(&Uuid::new_v4().to_string())?;
+    let subagent_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-01T11-00-00",
+        "2025-02-01T11:00:00Z",
+        "SubAgent",
+        Some("mock_provider"),
+        None,
+        CoreSessionSource::SubAgent(SubAgentSource::ThreadSpawn {
+            parent_thread_id,
+            depth: 1,
+        }),
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, next_cursor } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        Some(vec![ThreadSourceKind::SubAgentThreadSpawn]),
+        None,
+    )
+    .await?;
+
+    assert_eq!(next_cursor, None);
+    let ids: Vec<_> = data.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(ids, vec![subagent_id.as_str()]);
+    assert_ne!(cli_id, subagent_id);
+    assert!(matches!(data[0].source, SessionSource::SubAgent(_)));
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_filters_by_subagent_variant() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let parent_thread_id = ThreadId::from_string(&Uuid::new_v4().to_string())?;
+
+    let review_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-02T09-00-00",
+        "2025-02-02T09:00:00Z",
+        "Review",
+        Some("mock_provider"),
+        None,
+        CoreSessionSource::SubAgent(SubAgentSource::Review),
+    )?;
+    let compact_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-02T10-00-00",
+        "2025-02-02T10:00:00Z",
+        "Compact",
+        Some("mock_provider"),
+        None,
+        CoreSessionSource::SubAgent(SubAgentSource::Compact),
+    )?;
+    let spawn_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-02T11-00-00",
+        "2025-02-02T11:00:00Z",
+        "Spawn",
+        Some("mock_provider"),
+        None,
+        CoreSessionSource::SubAgent(SubAgentSource::ThreadSpawn {
+            parent_thread_id,
+            depth: 1,
+        }),
+    )?;
+    let other_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-02T12-00-00",
+        "2025-02-02T12:00:00Z",
+        "Other",
+        Some("mock_provider"),
+        None,
+        CoreSessionSource::SubAgent(SubAgentSource::Other("custom".to_string())),
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let review = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        Some(vec![ThreadSourceKind::SubAgentReview]),
+        None,
+    )
+    .await?;
+    let review_ids: Vec<_> = review
+        .data
+        .iter()
+        .map(|thread| thread.id.as_str())
+        .collect();
+    assert_eq!(review_ids, vec![review_id.as_str()]);
+
+    let compact = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        Some(vec![ThreadSourceKind::SubAgentCompact]),
+        None,
+    )
+    .await?;
+    let compact_ids: Vec<_> = compact
+        .data
+        .iter()
+        .map(|thread| thread.id.as_str())
+        .collect();
+    assert_eq!(compact_ids, vec![compact_id.as_str()]);
+
+    let spawn = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        Some(vec![ThreadSourceKind::SubAgentThreadSpawn]),
+        None,
+    )
+    .await?;
+    let spawn_ids: Vec<_> = spawn.data.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(spawn_ids, vec![spawn_id.as_str()]);
+
+    let other = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        Some(vec![ThreadSourceKind::SubAgentOther]),
+        None,
+    )
+    .await?;
+    let other_ids: Vec<_> = other.data.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(other_ids, vec![other_id.as_str()]);
+
+    Ok(())
+}
+
 #[tokio::test]
 async fn thread_list_fetches_until_limit_or_exhausted() -> Result<()> {
     let codex_home = TempDir::new()?;
@@ -275,6 +531,8 @@ async fn thread_list_fetches_until_limit_or_exhausted() -> Result<()> {
         None,
         Some(8),
         Some(vec!["target_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert_eq!(
@@ -319,6 +577,8 @@ async fn thread_list_enforces_max_limit() -> Result<()> {
         None,
         Some(200),
         Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert_eq!(
@@ -364,6 +624,8 @@ async fn thread_list_stops_when_not_enough_filtered_results_exist() -> Result<()
         None,
         Some(10),
         Some(vec!["target_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     assert_eq!(
@@ -410,6 +672,8 @@ async fn thread_list_includes_git_info() -> Result<()> {
         None,
         Some(10),
         Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
     )
     .await?;
     let thread = data
@@ -429,3 +693,428 @@ async fn thread_list_includes_git_info() -> Result<()> {
 
     Ok(())
 }
+
+#[tokio::test]
+async fn thread_list_default_sorts_by_created_at() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let id_a = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T12-00-00",
+        "2025-01-02T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_b = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T13-00-00",
+        "2025-01-01T13:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_c = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T12-00-00",
+        "2025-01-01T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, .. } = list_threads_with_sort(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
+        None,
+    )
+    .await?;
+
+    let ids: Vec<_> = data.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(ids, vec![id_a.as_str(), id_b.as_str(), id_c.as_str()]);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_sort_updated_at_orders_by_mtime() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let id_old = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T10-00-00",
+        "2025-01-01T10:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_mid = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T11-00-00",
+        "2025-01-01T11:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_new = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T12-00-00",
+        "2025-01-01T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-01-01T10-00-00", &id_old).as_path(),
+        "2025-01-03T00:00:00Z",
+    )?;
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-01-01T11-00-00", &id_mid).as_path(),
+        "2025-01-02T00:00:00Z",
+    )?;
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-01-01T12-00-00", &id_new).as_path(),
+        "2025-01-01T00:00:00Z",
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, .. } = list_threads_with_sort(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        Some(ThreadSortKey::UpdatedAt),
+        None,
+    )
+    .await?;
+
+    let ids: Vec<_> = data.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(ids, vec![id_old.as_str(), id_mid.as_str(), id_new.as_str()]);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_updated_at_paginates_with_cursor() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let id_a = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_b = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T11-00-00",
+        "2025-02-01T11:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_c = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T12-00-00",
+        "2025-02-01T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-02-01T10-00-00", &id_a).as_path(),
+        "2025-02-03T00:00:00Z",
+    )?;
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-02-01T11-00-00", &id_b).as_path(),
+        "2025-02-02T00:00:00Z",
+    )?;
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-02-01T12-00-00", &id_c).as_path(),
+        "2025-02-01T00:00:00Z",
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse {
+        data: page1,
+        next_cursor: cursor1,
+    } = list_threads_with_sort(
+        &mut mcp,
+        None,
+        Some(2),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        Some(ThreadSortKey::UpdatedAt),
+        None,
+    )
+    .await?;
+    let ids_page1: Vec<_> = page1.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(ids_page1, vec![id_a.as_str(), id_b.as_str()]);
+    let cursor1 = cursor1.expect("expected nextCursor on first page");
+
+    let ThreadListResponse {
+        data: page2,
+        next_cursor: cursor2,
+    } = list_threads_with_sort(
+        &mut mcp,
+        Some(cursor1),
+        Some(2),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        Some(ThreadSortKey::UpdatedAt),
+        None,
+    )
+    .await?;
+    let ids_page2: Vec<_> = page2.iter().map(|thread| thread.id.as_str()).collect();
+    assert_eq!(ids_page2, vec![id_c.as_str()]);
+    assert_eq!(cursor2, None);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_created_at_tie_breaks_by_uuid() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let id_a = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_b = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, .. } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
+    )
+    .await?;
+
+    let ids: Vec<_> = data.iter().map(|thread| thread.id.as_str()).collect();
+    let mut expected = [id_a, id_b];
+    expected.sort_by_key(|id| Reverse(Uuid::parse_str(id).expect("uuid should parse")));
+    let expected: Vec<_> = expected.iter().map(String::as_str).collect();
+    assert_eq!(ids, expected);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_updated_at_tie_breaks_by_uuid() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let id_a = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let id_b = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T11-00-00",
+        "2025-02-01T11:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let updated_at = "2025-02-03T00:00:00Z";
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-02-01T10-00-00", &id_a).as_path(),
+        updated_at,
+    )?;
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-02-01T11-00-00", &id_b).as_path(),
+        updated_at,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, .. } = list_threads_with_sort(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        Some(ThreadSortKey::UpdatedAt),
+        None,
+    )
+    .await?;
+
+    let ids: Vec<_> = data.iter().map(|thread| thread.id.as_str()).collect();
+    let mut expected = [id_a, id_b];
+    expected.sort_by_key(|id| Reverse(Uuid::parse_str(id).expect("uuid should parse")));
+    let expected: Vec<_> = expected.iter().map(String::as_str).collect();
+    assert_eq!(ids, expected);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_updated_at_uses_mtime() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let thread_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    set_rollout_mtime(
+        rollout_path(codex_home.path(), "2025-02-01T10-00-00", &thread_id).as_path(),
+        "2025-02-05T00:00:00Z",
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, .. } = list_threads_with_sort(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        Some(ThreadSortKey::UpdatedAt),
+        None,
+    )
+    .await?;
+
+    let thread = data
+        .iter()
+        .find(|item| item.id == thread_id)
+        .expect("expected thread for created rollout");
+    let expected_created =
+        chrono::DateTime::parse_from_rfc3339("2025-02-01T10:00:00Z")?.timestamp();
+    let expected_updated =
+        chrono::DateTime::parse_from_rfc3339("2025-02-05T00:00:00Z")?.timestamp();
+    assert_eq!(thread.created_at, expected_created);
+    assert_eq!(thread.updated_at, expected_updated);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_archived_filter() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let active_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-03-01T10-00-00",
+        "2025-03-01T10:00:00Z",
+        "Active",
+        Some("mock_provider"),
+        None,
+    )?;
+    let archived_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-03-01T09-00-00",
+        "2025-03-01T09:00:00Z",
+        "Archived",
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let archived_dir = codex_home.path().join(ARCHIVED_SESSIONS_SUBDIR);
+    fs::create_dir_all(&archived_dir)?;
+    let archived_source = rollout_path(codex_home.path(), "2025-03-01T09-00-00", &archived_id);
+    let archived_dest = archived_dir.join(
+        archived_source
+            .file_name()
+            .expect("archived rollout should have a file name"),
+    );
+    fs::rename(&archived_source, &archived_dest)?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, .. } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        None,
+    )
+    .await?;
+    assert_eq!(data.len(), 1);
+    assert_eq!(data[0].id, active_id);
+
+    let ThreadListResponse { data, .. } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["mock_provider".to_string()]),
+        None,
+        Some(true),
+    )
+    .await?;
+    assert_eq!(data.len(), 1);
+    assert_eq!(data[0].id, archived_id);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_invalid_cursor_returns_error() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let request_id = mcp
+        .send_thread_list_request(codex_app_server_protocol::ThreadListParams {
+            cursor: Some("not-a-cursor".to_string()),
+            limit: Some(2),
+            sort_key: None,
+            model_providers: Some(vec!["mock_provider".to_string()]),
+            source_kinds: None,
+            archived: 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, -32600);
+    assert_eq!(error.error.message, "invalid cursor: not-a-cursor");
+
+    Ok(())
+}

codex-rs/app-server/tests/suite/v2/thread_read.rs

@@ -0,0 +1,159 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_fake_rollout_with_text_elements;
+use app_test_support::create_mock_responses_server_repeating_assistant;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SessionSource;
+use codex_app_server_protocol::ThreadItem;
+use codex_app_server_protocol::ThreadReadParams;
+use codex_app_server_protocol::ThreadReadResponse;
+use codex_app_server_protocol::TurnStatus;
+use codex_app_server_protocol::UserInput;
+use codex_protocol::user_input::ByteRange;
+use codex_protocol::user_input::TextElement;
+use pretty_assertions::assert_eq;
+use std::path::Path;
+use std::path::PathBuf;
+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_read_returns_summary_without_turns() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let preview = "Saved user message";
+    let text_elements = [TextElement::new(
+        ByteRange { start: 0, end: 5 },
+        Some("<note>".into()),
+    )];
+    let conversation_id = create_fake_rollout_with_text_elements(
+        codex_home.path(),
+        "2025-01-05T12-00-00",
+        "2025-01-05T12:00:00Z",
+        preview,
+        text_elements
+            .iter()
+            .map(|elem| serde_json::to_value(elem).expect("serialize text element"))
+            .collect(),
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let read_id = mcp
+        .send_thread_read_request(ThreadReadParams {
+            thread_id: conversation_id.clone(),
+            include_turns: false,
+        })
+        .await?;
+    let read_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
+    )
+    .await??;
+    let ThreadReadResponse { thread } = to_response::<ThreadReadResponse>(read_resp)?;
+
+    assert_eq!(thread.id, conversation_id);
+    assert_eq!(thread.preview, preview);
+    assert_eq!(thread.model_provider, "mock_provider");
+    assert!(thread.path.as_ref().expect("thread path").is_absolute());
+    assert_eq!(thread.cwd, PathBuf::from("/"));
+    assert_eq!(thread.cli_version, "0.0.0");
+    assert_eq!(thread.source, SessionSource::Cli);
+    assert_eq!(thread.git_info, None);
+    assert_eq!(thread.turns.len(), 0);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_read_can_include_turns() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let preview = "Saved user message";
+    let text_elements = vec![TextElement::new(
+        ByteRange { start: 0, end: 5 },
+        Some("<note>".into()),
+    )];
+    let conversation_id = create_fake_rollout_with_text_elements(
+        codex_home.path(),
+        "2025-01-05T12-00-00",
+        "2025-01-05T12:00:00Z",
+        preview,
+        text_elements
+            .iter()
+            .map(|elem| serde_json::to_value(elem).expect("serialize text element"))
+            .collect(),
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let read_id = mcp
+        .send_thread_read_request(ThreadReadParams {
+            thread_id: conversation_id.clone(),
+            include_turns: true,
+        })
+        .await?;
+    let read_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
+    )
+    .await??;
+    let ThreadReadResponse { thread } = to_response::<ThreadReadResponse>(read_resp)?;
+
+    assert_eq!(thread.turns.len(), 1);
+    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(),
+                    text_elements: text_elements.clone().into_iter().map(Into::into).collect(),
+                }]
+            );
+        }
+        other => panic!("expected user message item, got {other:?}"),
+    }
+
+    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 = "responses"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/app-server/tests/suite/v2/thread_resume.rs

@@ -1,8 +1,10 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
-use app_test_support::create_fake_rollout;
+use app_test_support::create_fake_rollout_with_text_elements;
 use app_test_support::create_mock_responses_server_repeating_assistant;
+use app_test_support::rollout_path;
 use app_test_support::to_response;
+use chrono::Utc;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::SessionSource;
@@ -11,15 +13,25 @@ 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::TurnStartParams;
 use codex_app_server_protocol::TurnStatus;
 use codex_app_server_protocol::UserInput;
+use codex_protocol::config_types::Personality;
 use codex_protocol::models::ContentItem;
 use codex_protocol::models::ResponseItem;
+use codex_protocol::user_input::ByteRange;
+use codex_protocol::user_input::TextElement;
+use core_test_support::responses;
+use core_test_support::skip_if_no_network;
+use pretty_assertions::assert_eq;
+use std::fs::FileTimes;
+use std::path::Path;
 use std::path::PathBuf;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+const CODEX_5_2_INSTRUCTIONS_TEMPLATE_DEFAULT: &str = "You are Codex, a coding agent based on GPT-5. You and the user share the same workspace and collaborate to achieve the user's goals.";
 
 #[tokio::test]
 async fn thread_resume_returns_original_thread() -> Result<()> {
@@ -59,7 +71,9 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
     let ThreadResumeResponse {
         thread: resumed, ..
     } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    assert_eq!(resumed, thread);
+    let mut expected = thread;
+    expected.updated_at = resumed.updated_at;
+    assert_eq!(resumed, expected);
 
     Ok(())
 }
@@ -71,11 +85,19 @@ async fn thread_resume_returns_rollout_history() -> Result<()> {
     create_config_toml(codex_home.path(), &server.uri())?;
 
     let preview = "Saved user message";
-    let conversation_id = create_fake_rollout(
+    let text_elements = vec![TextElement::new(
+        ByteRange { start: 0, end: 5 },
+        Some("<note>".into()),
+    )];
+    let conversation_id = create_fake_rollout_with_text_elements(
         codex_home.path(),
         "2025-01-05T12-00-00",
         "2025-01-05T12:00:00Z",
         preview,
+        text_elements
+            .iter()
+            .map(|elem| serde_json::to_value(elem).expect("serialize text element"))
+            .collect(),
         Some("mock_provider"),
         None,
     )?;
@@ -99,7 +121,7 @@ async fn thread_resume_returns_rollout_history() -> Result<()> {
     assert_eq!(thread.id, conversation_id);
     assert_eq!(thread.preview, preview);
     assert_eq!(thread.model_provider, "mock_provider");
-    assert!(thread.path.is_absolute());
+    assert!(thread.path.as_ref().expect("thread path").is_absolute());
     assert_eq!(thread.cwd, PathBuf::from("/"));
     assert_eq!(thread.cli_version, "0.0.0");
     assert_eq!(thread.source, SessionSource::Cli);
@@ -118,7 +140,8 @@ async fn thread_resume_returns_rollout_history() -> Result<()> {
             assert_eq!(
                 content,
                 &vec![UserInput::Text {
-                    text: preview.to_string()
+                    text: preview.to_string(),
+                    text_elements: text_elements.clone().into_iter().map(Into::into).collect(),
                 }]
             );
         }
@@ -128,6 +151,116 @@ async fn thread_resume_returns_rollout_history() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_resume_without_overrides_does_not_change_updated_at_or_mtime() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    let rollout = setup_rollout_fixture(codex_home.path(), &server.uri())?;
+    let thread_id = rollout.conversation_id.clone();
+
+    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: 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, .. } = to_response::<ThreadResumeResponse>(resume_resp)?;
+
+    assert_eq!(thread.updated_at, rollout.expected_updated_at);
+
+    let after_modified = std::fs::metadata(&rollout.rollout_file_path)?.modified()?;
+    assert_eq!(after_modified, rollout.before_modified);
+
+    let turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id,
+            input: vec![UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let after_turn_modified = std::fs::metadata(&rollout.rollout_file_path)?.modified()?;
+    assert!(after_turn_modified > rollout.before_modified);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_resume_with_overrides_defers_updated_at_until_turn_start() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    let rollout = setup_rollout_fixture(codex_home.path(), &server.uri())?;
+
+    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: rollout.conversation_id.clone(),
+            model: Some("mock-model".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, .. } = to_response::<ThreadResumeResponse>(resume_resp)?;
+
+    assert_eq!(thread.updated_at, rollout.expected_updated_at);
+
+    let after_resume_modified = std::fs::metadata(&rollout.rollout_file_path)?.modified()?;
+    assert_eq!(after_resume_modified, rollout.before_modified);
+
+    let turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: rollout.conversation_id,
+            input: vec![UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let after_turn_modified = std::fs::metadata(&rollout.rollout_file_path)?.modified()?;
+    assert!(after_turn_modified > rollout.before_modified);
+
+    Ok(())
+}
+
 #[tokio::test]
 async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
     let server = create_mock_responses_server_repeating_assistant("Done").await;
@@ -150,7 +283,7 @@ async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
     .await??;
     let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
 
-    let thread_path = thread.path.clone();
+    let thread_path = thread.path.clone().expect("thread path");
     let resume_id = mcp
         .send_thread_resume_request(ThreadResumeParams {
             thread_id: "not-a-valid-thread-id".to_string(),
@@ -167,7 +300,9 @@ async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
     let ThreadResumeResponse {
         thread: resumed, ..
     } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    assert_eq!(resumed, thread);
+    let mut expected = thread;
+    expected.updated_at = resumed.updated_at;
+    assert_eq!(resumed, expected);
 
     Ok(())
 }
@@ -202,6 +337,7 @@ async fn thread_resume_supports_history_and_overrides() -> Result<()> {
         content: vec![ContentItem::InputText {
             text: history_text.to_string(),
         }],
+        end_turn: None,
     }];
 
     // Resume with explicit history and override the model.
@@ -231,6 +367,91 @@ async fn thread_resume_supports_history_and_overrides() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_resume_accepts_personality_override() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = responses::start_mock_server().await;
+    let body = responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_assistant_message("msg-1", "Done"),
+        responses::ev_completed("resp-1"),
+    ]);
+    let response_mock = responses::mount_sse_once(&server, body).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-5.2-codex".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 resume_id = mcp
+        .send_thread_resume_request(ThreadResumeParams {
+            thread_id: thread.id.clone(),
+            model: Some("gpt-5.2-codex".to_string()),
+            personality: Some(Personality::Pragmatic),
+            ..Default::default()
+        })
+        .await?;
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+    )
+    .await??;
+    let _resume: ThreadResumeResponse = to_response::<ThreadResumeResponse>(resume_resp)?;
+
+    let turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id,
+            input: vec![UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
+    )
+    .await??;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let request = response_mock.single_request();
+    let developer_texts = request.message_input_texts("developer");
+    assert!(
+        developer_texts
+            .iter()
+            .any(|text| text.contains("<personality_spec>")),
+        "expected a personality update message in developer input, got {developer_texts:?}"
+    );
+    let instructions_text = request.instructions_text();
+    assert!(
+        instructions_text.contains(CODEX_5_2_INSTRUCTIONS_TEMPLATE_DEFAULT),
+        "expected default base instructions from history, got {instructions_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");
@@ -238,12 +459,16 @@ fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io
         config_toml,
         format!(
             r#"
-model = "mock-model"
+model = "gpt-5.2-codex"
 approval_policy = "never"
 sandbox_mode = "read-only"
 
 model_provider = "mock_provider"
 
+[features]
+remote_models = false
+personality = true
+
 [model_providers.mock_provider]
 name = "Mock provider for test"
 base_url = "{server_uri}/v1"
@@ -254,3 +479,51 @@ stream_max_retries = 0
         ),
     )
 }
+
+fn set_rollout_mtime(path: &Path, updated_at_rfc3339: &str) -> Result<()> {
+    let parsed = chrono::DateTime::parse_from_rfc3339(updated_at_rfc3339)?.with_timezone(&Utc);
+    let times = FileTimes::new().set_modified(parsed.into());
+    std::fs::OpenOptions::new()
+        .append(true)
+        .open(path)?
+        .set_times(times)?;
+    Ok(())
+}
+
+struct RolloutFixture {
+    conversation_id: String,
+    rollout_file_path: PathBuf,
+    before_modified: std::time::SystemTime,
+    expected_updated_at: i64,
+}
+
+fn setup_rollout_fixture(codex_home: &Path, server_uri: &str) -> Result<RolloutFixture> {
+    create_config_toml(codex_home, server_uri)?;
+
+    let preview = "Saved user message";
+    let filename_ts = "2025-01-05T12-00-00";
+    let meta_rfc3339 = "2025-01-05T12:00:00Z";
+    let expected_updated_at_rfc3339 = "2025-01-07T00:00:00Z";
+    let conversation_id = create_fake_rollout_with_text_elements(
+        codex_home,
+        filename_ts,
+        meta_rfc3339,
+        preview,
+        Vec::new(),
+        Some("mock_provider"),
+        None,
+    )?;
+    let rollout_file_path = rollout_path(codex_home, filename_ts, &conversation_id);
+    set_rollout_mtime(rollout_file_path.as_path(), expected_updated_at_rfc3339)?;
+    let before_modified = std::fs::metadata(&rollout_file_path)?.modified()?;
+    let expected_updated_at = chrono::DateTime::parse_from_rfc3339(expected_updated_at_rfc3339)?
+        .with_timezone(&Utc)
+        .timestamp();
+
+    Ok(RolloutFixture {
+        conversation_id,
+        rollout_file_path,
+        before_modified,
+        expected_updated_at,
+    })
+}

codex-rs/app-server/tests/suite/v2/thread_rollback.rs

@@ -57,6 +57,7 @@ async fn thread_rollback_drops_last_turns_and_persists_to_rollout() -> Result<()
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: first_text.to_string(),
+                text_elements: Vec::new(),
             }],
             ..Default::default()
         })
@@ -77,6 +78,7 @@ async fn thread_rollback_drops_last_turns_and_persists_to_rollout() -> Result<()
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "Second".to_string(),
+                text_elements: Vec::new(),
             }],
             ..Default::default()
         })
@@ -115,7 +117,8 @@ async fn thread_rollback_drops_last_turns_and_persists_to_rollout() -> Result<()
             assert_eq!(
                 content,
                 &vec![V2UserInput::Text {
-                    text: first_text.to_string()
+                    text: first_text.to_string(),
+                    text_elements: Vec::new(),
                 }]
             );
         }
@@ -143,7 +146,8 @@ async fn thread_rollback_drops_last_turns_and_persists_to_rollout() -> Result<()
             assert_eq!(
                 content,
                 &vec![V2UserInput::Text {
-                    text: first_text.to_string()
+                    text: first_text.to_string(),
+                    text_elements: Vec::new(),
                 }]
             );
         }

codex-rs/app-server/tests/suite/v2/thread_start.rs

@@ -8,6 +8,9 @@ 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 codex_core::config::set_project_trust_level;
+use codex_protocol::config_types::TrustLevel;
+use codex_protocol::openai_models::ReasoningEffort;
 use std::path::Path;
 use tempfile::TempDir;
 use tokio::time::timeout;
@@ -69,6 +72,47 @@ async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_start_respects_project_config_from_cwd() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let workspace = TempDir::new()?;
+    let project_config_dir = workspace.path().join(".codex");
+    std::fs::create_dir_all(&project_config_dir)?;
+    std::fs::write(
+        project_config_dir.join("config.toml"),
+        r#"
+model_reasoning_effort = "high"
+"#,
+    )?;
+    set_project_trust_level(codex_home.path(), workspace.path(), TrustLevel::Trusted)?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let req_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            cwd: Some(workspace.path().to_string_lossy().into_owned()),
+            ..Default::default()
+        })
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    let ThreadStartResponse {
+        reasoning_effort, ..
+    } = to_response::<ThreadStartResponse>(resp)?;
+
+    assert_eq!(reasoning_effort, Some(ReasoningEffort::High));
+    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");

codex-rs/app-server/tests/suite/v2/thread_unarchive.rs

@@ -0,0 +1,121 @@
+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_app_server_protocol::ThreadUnarchiveParams;
+use codex_app_server_protocol::ThreadUnarchiveResponse;
+use codex_core::find_archived_thread_path_by_id_str;
+use codex_core::find_thread_path_by_id_str;
+use std::fs::FileTimes;
+use std::fs::OpenOptions;
+use std::path::Path;
+use std::time::Duration;
+use std::time::SystemTime;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(30);
+
+#[tokio::test]
+async fn thread_unarchive_moves_rollout_back_into_sessions_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??;
+
+    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 rollout_path = find_thread_path_by_id_str(codex_home.path(), &thread.id)
+        .await?
+        .expect("expected rollout path for thread id to exist");
+
+    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)?;
+
+    let archived_path = find_archived_thread_path_by_id_str(codex_home.path(), &thread.id)
+        .await?
+        .expect("expected archived rollout path for thread id to exist");
+    let archived_path_display = archived_path.display();
+    assert!(
+        archived_path.exists(),
+        "expected {archived_path_display} to exist"
+    );
+    let old_time = SystemTime::UNIX_EPOCH + Duration::from_secs(1);
+    let old_timestamp = old_time
+        .duration_since(SystemTime::UNIX_EPOCH)
+        .expect("old timestamp")
+        .as_secs() as i64;
+    let times = FileTimes::new().set_modified(old_time);
+    OpenOptions::new()
+        .append(true)
+        .open(&archived_path)?
+        .set_times(times)?;
+
+    let unarchive_id = mcp
+        .send_thread_unarchive_request(ThreadUnarchiveParams {
+            thread_id: thread.id.clone(),
+        })
+        .await?;
+    let unarchive_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(unarchive_id)),
+    )
+    .await??;
+    let ThreadUnarchiveResponse {
+        thread: unarchived_thread,
+    } = to_response::<ThreadUnarchiveResponse>(unarchive_resp)?;
+    assert!(
+        unarchived_thread.updated_at > old_timestamp,
+        "expected updated_at to be bumped on unarchive"
+    );
+
+    let rollout_path_display = rollout_path.display();
+    assert!(
+        rollout_path.exists(),
+        "expected rollout path {rollout_path_display} to be restored"
+    );
+    assert!(
+        !archived_path.exists(),
+        "expected archived rollout path {archived_path_display} to be moved"
+    );
+
+    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"
+"#
+}

codex-rs/app-server/tests/suite/v2/turn_interrupt.rs

@@ -73,6 +73,7 @@ async fn turn_interrupt_aborts_running_turn() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "run sleep".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(working_directory.clone()),
             ..Default::default()

codex-rs/app-server/tests/suite/v2/turn_start.rs

@@ -8,6 +8,8 @@ use app_test_support::create_mock_responses_server_sequence_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::ByteRange;
+use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::CommandExecutionApprovalDecision;
 use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
 use codex_app_server_protocol::CommandExecutionStatus;
@@ -22,6 +24,7 @@ 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::TextElement;
 use codex_app_server_protocol::ThreadItem;
 use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
@@ -31,15 +34,185 @@ 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::features::FEATURES;
+use codex_core::features::Feature;
 use codex_core::protocol_config_types::ReasoningSummary;
+use codex_protocol::config_types::CollaborationMode;
+use codex_protocol::config_types::ModeKind;
+use codex_protocol::config_types::Personality;
+use codex_protocol::config_types::Settings;
 use codex_protocol::openai_models::ReasoningEffort;
+use core_test_support::responses;
 use core_test_support::skip_if_no_network;
 use pretty_assertions::assert_eq;
+use std::collections::BTreeMap;
 use std::path::Path;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+const TEST_ORIGINATOR: &str = "codex_vscode";
+
+#[tokio::test]
+async fn turn_start_sends_originator_header() -> Result<()> {
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
+    let server = create_mock_responses_server_sequence_unchecked(responses).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::from([(Feature::Personality, true)]),
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.initialize_with_client_info(ClientInfo {
+            name: TEST_ORIGINATOR.to_string(),
+            title: Some("Codex VS Code Extension".to_string()),
+            version: "0.1.0".to_string(),
+        }),
+    )
+    .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 turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let requests = server
+        .received_requests()
+        .await
+        .expect("failed to fetch received requests");
+    assert!(!requests.is_empty());
+    for request in requests {
+        let originator = request
+            .headers
+            .get("originator")
+            .expect("originator header missing");
+        assert_eq!(originator.to_str()?, TEST_ORIGINATOR);
+    }
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn turn_start_emits_user_message_item_with_text_elements() -> Result<()> {
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
+    let server = create_mock_responses_server_sequence_unchecked(responses).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::from([(Feature::Personality, true)]),
+    )?;
+
+    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 text_elements = vec![TextElement::new(
+        ByteRange { start: 0, end: 5 },
+        Some("<note>".to_string()),
+    )];
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: text_elements.clone(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+
+    let user_message_item = timeout(DEFAULT_READ_TIMEOUT, async {
+        loop {
+            let notification = mcp
+                .read_stream_until_notification_message("item/started")
+                .await?;
+            let params = notification.params.expect("item/started params");
+            let item_started: ItemStartedNotification =
+                serde_json::from_value(params).expect("deserialize item/started notification");
+            if let ThreadItem::UserMessage { .. } = item_started.item {
+                return Ok::<ThreadItem, anyhow::Error>(item_started.item);
+            }
+        }
+    })
+    .await??;
+
+    match user_message_item {
+        ThreadItem::UserMessage { content, .. } => {
+            assert_eq!(
+                content,
+                vec![V2UserInput::Text {
+                    text: "Hello".to_string(),
+                    text_elements,
+                }]
+            );
+        }
+        other => panic!("expected user message item, got {other:?}"),
+    }
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    Ok(())
+}
 
 #[tokio::test]
 async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<()> {
@@ -53,7 +226,12 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
     let server = create_mock_responses_server_sequence_unchecked(responses).await;
 
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri(), "never")?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::from([(Feature::Personality, true)]),
+    )?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -78,6 +256,7 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "Hello".to_string(),
+                text_elements: Vec::new(),
             }],
             ..Default::default()
         })
@@ -110,6 +289,7 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "Second".to_string(),
+                text_elements: Vec::new(),
             }],
             model: Some("mock-model-override".to_string()),
             ..Default::default()
@@ -148,6 +328,273 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
     Ok(())
 }
 
+#[tokio::test]
+async fn turn_start_accepts_collaboration_mode_override_v2() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = responses::start_mock_server().await;
+    let body = responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_assistant_message("msg-1", "Done"),
+        responses::ev_completed("resp-1"),
+    ]);
+    let response_mock = responses::mount_sse_once(&server, body).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::default(),
+    )?;
+
+    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("gpt-5.2-codex".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 collaboration_mode = CollaborationMode {
+        mode: ModeKind::Custom,
+        settings: Settings {
+            model: "mock-model-collab".to_string(),
+            reasoning_effort: Some(ReasoningEffort::High),
+            developer_instructions: None,
+        },
+    };
+
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            model: Some("mock-model-override".to_string()),
+            effort: Some(ReasoningEffort::Low),
+            summary: Some(ReasoningSummary::Auto),
+            output_schema: None,
+            collaboration_mode: Some(collaboration_mode),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp)?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let request = response_mock.single_request();
+    let payload = request.body_json();
+    assert_eq!(payload["model"].as_str(), Some("mock-model-collab"));
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn turn_start_accepts_personality_override_v2() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = responses::start_mock_server().await;
+    let body = responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_assistant_message("msg-1", "Done"),
+        responses::ev_completed("resp-1"),
+    ]);
+    let response_mock = responses::mount_sse_once(&server, body).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::from([(Feature::Personality, true)]),
+    )?;
+
+    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("exp-codex-personality".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 turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            personality: Some(Personality::Pragmatic),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp)?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let request = response_mock.single_request();
+    let developer_texts = request.message_input_texts("developer");
+    if developer_texts.is_empty() {
+        eprintln!("request body: {}", request.body_json());
+    }
+
+    assert!(
+        developer_texts
+            .iter()
+            .any(|text| text.contains("<personality_spec>")),
+        "expected personality update message in developer input, got {developer_texts:?}"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn turn_start_change_personality_mid_thread_v2() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = responses::start_mock_server().await;
+    let sse1 = responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_assistant_message("msg-1", "Done"),
+        responses::ev_completed("resp-1"),
+    ]);
+    let sse2 = responses::sse(vec![
+        responses::ev_response_created("resp-2"),
+        responses::ev_assistant_message("msg-2", "Done"),
+        responses::ev_completed("resp-2"),
+    ]);
+    let response_mock = responses::mount_sse_sequence(&server, vec![sse1, sse2]).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::from([(Feature::Personality, true)]),
+    )?;
+
+    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("exp-codex-personality".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 turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+                text_elements: Vec::new(),
+            }],
+            personality: None,
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp)?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let turn_req2 = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello again".to_string(),
+                text_elements: Vec::new(),
+            }],
+            personality: Some(Personality::Pragmatic),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp2: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req2)),
+    )
+    .await??;
+    let _turn2: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp2)?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let requests = response_mock.requests();
+    assert_eq!(requests.len(), 2, "expected two requests");
+
+    let first_developer_texts = requests[0].message_input_texts("developer");
+    assert!(
+        first_developer_texts
+            .iter()
+            .all(|text| !text.contains("<personality_spec>")),
+        "expected no personality update message in first request, got {first_developer_texts:?}"
+    );
+
+    let second_developer_texts = requests[1].message_input_texts("developer");
+    assert!(
+        second_developer_texts
+            .iter()
+            .any(|text| text.contains("<personality_spec>")),
+        "expected personality update message in second request, got {second_developer_texts:?}"
+    );
+
+    Ok(())
+}
+
 #[tokio::test]
 async fn turn_start_accepts_local_image_input() -> Result<()> {
     // Two Codex turns hit the mock model (session start + turn/start).
@@ -160,7 +607,12 @@ async fn turn_start_accepts_local_image_input() -> Result<()> {
     let server = create_mock_responses_server_sequence_unchecked(responses).await;
 
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri(), "never")?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -235,7 +687,12 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
     ];
     let server = create_mock_responses_server_sequence(responses).await;
     // Default approval is untrusted to force elicitation on first turn.
-    create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
+    create_config_toml(
+        codex_home.as_path(),
+        &server.uri(),
+        "untrusted",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(codex_home.as_path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -260,6 +717,7 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "run python".to_string(),
+                text_elements: Vec::new(),
             }],
             ..Default::default()
         })
@@ -305,6 +763,7 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "run python again".to_string(),
+                text_elements: Vec::new(),
             }],
             approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
             sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::DangerFullAccess),
@@ -358,7 +817,12 @@ async fn turn_start_exec_approval_decline_v2() -> Result<()> {
         create_final_assistant_message_sse_response("done")?,
     ];
     let server = create_mock_responses_server_sequence(responses).await;
-    create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
+    create_config_toml(
+        codex_home.as_path(),
+        &server.uri(),
+        "untrusted",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(codex_home.as_path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -381,6 +845,7 @@ async fn turn_start_exec_approval_decline_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "run python".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(workspace.clone()),
             ..Default::default()
@@ -504,7 +969,12 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
         create_final_assistant_message_sse_response("done second")?,
     ];
     let server = create_mock_responses_server_sequence(responses).await;
-    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
+    create_config_toml(
+        &codex_home,
+        &server.uri(),
+        "untrusted",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(&codex_home).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -529,6 +999,7 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "first turn".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(first_cwd.clone()),
             approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
@@ -541,7 +1012,9 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             model: Some("mock-model".to_string()),
             effort: Some(ReasoningEffort::Medium),
             summary: Some(ReasoningSummary::Auto),
+            personality: None,
             output_schema: None,
+            collaboration_mode: None,
         })
         .await?;
     timeout(
@@ -562,6 +1035,7 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "second turn".to_string(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(second_cwd.clone()),
             approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
@@ -569,7 +1043,9 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             model: Some("mock-model".to_string()),
             effort: Some(ReasoningEffort::Medium),
             summary: Some(ReasoningSummary::Auto),
+            personality: None,
             output_schema: None,
+            collaboration_mode: None,
         })
         .await?;
     timeout(
@@ -638,7 +1114,12 @@ async fn turn_start_file_change_approval_v2() -> Result<()> {
         create_final_assistant_message_sse_response("patch applied")?,
     ];
     let server = create_mock_responses_server_sequence(responses).await;
-    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
+    create_config_toml(
+        &codex_home,
+        &server.uri(),
+        "untrusted",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(&codex_home).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -662,6 +1143,7 @@ async fn turn_start_file_change_approval_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "apply patch".into(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(workspace.clone()),
             ..Default::default()
@@ -814,7 +1296,12 @@ async fn turn_start_file_change_approval_accept_for_session_persists_v2() -> Res
         create_final_assistant_message_sse_response("patch 2 applied")?,
     ];
     let server = create_mock_responses_server_sequence(responses).await;
-    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
+    create_config_toml(
+        &codex_home,
+        &server.uri(),
+        "untrusted",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(&codex_home).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -839,6 +1326,7 @@ async fn turn_start_file_change_approval_accept_for_session_persists_v2() -> Res
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "apply patch 1".into(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(workspace.clone()),
             ..Default::default()
@@ -915,6 +1403,7 @@ async fn turn_start_file_change_approval_accept_for_session_persists_v2() -> Res
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "apply patch 2".into(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(workspace.clone()),
             ..Default::default()
@@ -988,7 +1477,12 @@ async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
         create_final_assistant_message_sse_response("patch declined")?,
     ];
     let server = create_mock_responses_server_sequence(responses).await;
-    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
+    create_config_toml(
+        &codex_home,
+        &server.uri(),
+        "untrusted",
+        &BTreeMap::default(),
+    )?;
 
     let mut mcp = McpProcess::new(&codex_home).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -1012,6 +1506,7 @@ async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "apply patch".into(),
+                text_elements: Vec::new(),
             }],
             cwd: Some(workspace.clone()),
             ..Default::default()
@@ -1127,16 +1622,12 @@ async fn command_execution_notifications_include_process_id() -> Result<()> {
     ];
     let server = create_mock_responses_server_sequence(responses).await;
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri(), "never")?;
-    let config_toml = codex_home.path().join("config.toml");
-    let mut config_contents = std::fs::read_to_string(&config_toml)?;
-    config_contents.push_str(
-        r#"
-[features]
-unified_exec = true
-"#,
-    );
-    std::fs::write(&config_toml, config_contents)?;
+    create_config_toml(
+        codex_home.path(),
+        &server.uri(),
+        "never",
+        &BTreeMap::from([(Feature::UnifiedExec, true)]),
+    )?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -1159,6 +1650,7 @@ unified_exec = true
             thread_id: thread.id.clone(),
             input: vec![V2UserInput::Text {
                 text: "run a command".to_string(),
+                text_elements: Vec::new(),
             }],
             ..Default::default()
         })
@@ -1228,8 +1720,18 @@ unified_exec = true
         unreachable!("loop ensures we break on command execution items");
     };
     assert_eq!(completed_id, "uexec-1");
-    assert_eq!(completed_status, CommandExecutionStatus::Completed);
-    assert_eq!(exit_code, Some(0));
+    assert!(
+        matches!(
+            completed_status,
+            CommandExecutionStatus::Completed | CommandExecutionStatus::Failed
+        ),
+        "unexpected command execution status: {completed_status:?}"
+    );
+    if completed_status == CommandExecutionStatus::Completed {
+        assert_eq!(exit_code, Some(0));
+    } else {
+        assert!(exit_code.is_some(), "expected exit_code for failed command");
+    }
     assert_eq!(
         completed_process_id.as_deref(),
         Some(started_process_id.as_str())
@@ -1249,7 +1751,24 @@ fn create_config_toml(
     codex_home: &Path,
     server_uri: &str,
     approval_policy: &str,
+    feature_flags: &BTreeMap<Feature, bool>,
 ) -> std::io::Result<()> {
+    let mut features = BTreeMap::from([(Feature::RemoteModels, false)]);
+    for (feature, enabled) in feature_flags {
+        features.insert(*feature, *enabled);
+    }
+    let feature_entries = features
+        .into_iter()
+        .map(|(feature, enabled)| {
+            let key = FEATURES
+                .iter()
+                .find(|spec| spec.id == feature)
+                .map(|spec| spec.key)
+                .unwrap_or_else(|| panic!("missing feature key for {feature:?}"));
+            format!("{key} = {enabled}")
+        })
+        .collect::<Vec<_>>()
+        .join("\n");
     let config_toml = codex_home.join("config.toml");
     std::fs::write(
         config_toml,
@@ -1261,6 +1780,9 @@ sandbox_mode = "read-only"
 
 model_provider = "mock_provider"
 
+[features]
+{feature_entries}
+
 [model_providers.mock_provider]
 name = "Mock provider for test"
 base_url = "{server_uri}/v1"

codex-rs/apply-patch/BUILD.bazel

@@ -0,0 +1,11 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+exports_files(["apply_patch_tool_instructions.md"])
+
+codex_rust_crate(
+    name = "apply-patch",
+    crate_name = "codex_apply_patch",
+    compile_data = [
+        "apply_patch_tool_instructions.md",
+    ],
+)

codex-rs/apply-patch/src/standalone_executable.rs

@@ -27,7 +27,7 @@ pub fn run_main() -> i32 {
             match std::io::stdin().read_to_string(&mut buf) {
                 Ok(_) => {
                     if buf.is_empty() {
-                        eprintln!("Usage: apply_patch 'PATCH'\n       echo 'PATCH' | apply-patch");
+                        eprintln!("Usage: apply_patch 'PATCH'\n       echo 'PATCH' | apply_patch");
                         return 2;
                     }
                     buf

codex-rs/arg0/BUILD.bazel

@@ -0,0 +1,6 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "arg0",
+    crate_name = "codex_arg0",
+)

codex-rs/arg0/src/lib.rs

@@ -145,11 +145,41 @@ where
 /// that `apply_patch` can be on the PATH without requiring the user to
 /// install a separate `apply_patch` executable, simplifying the deployment of
 /// Codex CLI.
+/// Note: In debug builds the temp-dir guard is disabled to ease local testing.
 ///
 /// 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> {
-    let temp_dir = TempDir::new()?;
+    let codex_home = codex_core::config::find_codex_home()?;
+    #[cfg(not(debug_assertions))]
+    {
+        // Guard against placing helpers in system temp directories outside debug builds.
+        let temp_root = std::env::temp_dir();
+        if codex_home.starts_with(&temp_root) {
+            return Err(std::io::Error::new(
+                std::io::ErrorKind::InvalidInput,
+                format!(
+                    "Refusing to create helper binaries under temporary dir {temp_root:?} (codex_home: {codex_home:?})"
+                ),
+            ));
+        }
+    }
+
+    std::fs::create_dir_all(&codex_home)?;
+    // Use a CODEX_HOME-scoped temp root to avoid cluttering the top-level directory.
+    let temp_root = codex_home.join("tmp").join("path");
+    std::fs::create_dir_all(&temp_root)?;
+    #[cfg(unix)]
+    {
+        use std::os::unix::fs::PermissionsExt;
+
+        // Ensure only the current user can access the temp directory.
+        std::fs::set_permissions(&temp_root, std::fs::Permissions::from_mode(0o700))?;
+    }
+
+    let temp_dir = tempfile::Builder::new()
+        .prefix("codex-arg0")
+        .tempdir_in(&temp_root)?;
     let path = temp_dir.path();
 
     for filename in &[

codex-rs/async-utils/BUILD.bazel

@@ -0,0 +1,6 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "async-utils",
+    crate_name = "codex_async_utils",
+)

codex-rs/backend-client/BUILD.bazel

@@ -0,0 +1,7 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "backend-client",
+    crate_name = "codex_backend_client",
+    compile_data = glob(["tests/fixtures/**"]),
+)

codex-rs/backend-client/src/client.rs

@@ -1,4 +1,5 @@
 use crate::types::CodeTaskDetailsResponse;
+use crate::types::ConfigFileResponse;
 use crate::types::CreditStatusDetails;
 use crate::types::PaginatedListTaskListItem;
 use crate::types::RateLimitStatusPayload;
@@ -174,6 +175,7 @@ impl Client {
         limit: Option<i32>,
         task_filter: Option<&str>,
         environment_id: Option<&str>,
+        cursor: Option<&str>,
     ) -> Result<PaginatedListTaskListItem> {
         let url = match self.path_style {
             PathStyle::CodexApi => format!("{}/api/codex/tasks/list", self.base_url),
@@ -190,6 +192,11 @@ impl Client {
         } else {
             req
         };
+        let req = if let Some(c) = cursor {
+            req.query(&[("cursor", c)])
+        } else {
+            req
+        };
         let req = if let Some(id) = environment_id {
             req.query(&[("environment_id", id)])
         } else {
@@ -238,6 +245,20 @@ impl Client {
         self.decode_json::<TurnAttemptsSiblingTurnsResponse>(&url, &ct, &body)
     }
 
+    /// Fetch the managed requirements file from codex-backend.
+    ///
+    /// `GET /api/codex/config/requirements` (Codex API style) or
+    /// `GET /wham/config/requirements` (ChatGPT backend-api style).
+    pub async fn get_config_requirements_file(&self) -> Result<ConfigFileResponse> {
+        let url = match self.path_style {
+            PathStyle::CodexApi => format!("{}/api/codex/config/requirements", self.base_url),
+            PathStyle::ChatGptApi => format!("{}/wham/config/requirements", self.base_url),
+        };
+        let req = self.http.get(&url).headers(self.headers());
+        let (body, ct) = self.exec_request(req, "GET", &url).await?;
+        self.decode_json::<ConfigFileResponse>(&url, &ct, &body)
+    }
+
     /// Create a new task (user turn) by POSTing to the appropriate backend path
     /// based on `path_style`. Returns the created task id.
     pub async fn create_task(&self, request_body: serde_json::Value) -> Result<String> {
@@ -330,6 +351,7 @@ impl Client {
     fn map_plan_type(plan_type: crate::types::PlanType) -> AccountPlanType {
         match plan_type {
             crate::types::PlanType::Free => AccountPlanType::Free,
+            crate::types::PlanType::Go => AccountPlanType::Go,
             crate::types::PlanType::Plus => AccountPlanType::Plus,
             crate::types::PlanType::Pro => AccountPlanType::Pro,
             crate::types::PlanType::Team => AccountPlanType::Team,
@@ -337,7 +359,6 @@ impl Client {
             crate::types::PlanType::Enterprise => AccountPlanType::Enterprise,
             crate::types::PlanType::Edu | crate::types::PlanType::Education => AccountPlanType::Edu,
             crate::types::PlanType::Guest
-            | crate::types::PlanType::Go
             | crate::types::PlanType::FreeWorkspace
             | crate::types::PlanType::Quorum
             | crate::types::PlanType::K12 => AccountPlanType::Unknown,

codex-rs/backend-client/src/lib.rs

@@ -4,6 +4,7 @@ pub mod types;
 pub use client::Client;
 pub use types::CodeTaskDetailsResponse;
 pub use types::CodeTaskDetailsResponseExt;
+pub use types::ConfigFileResponse;
 pub use types::PaginatedListTaskListItem;
 pub use types::TaskListItem;
 pub use types::TurnAttemptsSiblingTurnsResponse;

codex-rs/backend-client/src/types.rs

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

codex-rs/chatgpt/BUILD.bazel

@@ -0,0 +1,6 @@
+load("//:defs.bzl", "codex_rust_crate")
+
+codex_rust_crate(
+    name = "chatgpt",
+    crate_name = "codex_chatgpt",
+)

codex-rs/chatgpt/Cargo.toml

@@ -17,6 +17,8 @@ serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
 tokio = { workspace = true, features = ["full"] }
 codex-git = { workspace = true }
+urlencoding = { workspace = true }
 
 [dev-dependencies]
+pretty_assertions = { workspace = true }
 tempfile = { workspace = true }

codex-rs/chatgpt/src/chatgpt_client.rs

@@ -6,11 +6,20 @@ use crate::chatgpt_token::init_chatgpt_token_from_auth;
 
 use anyhow::Context;
 use serde::de::DeserializeOwned;
+use std::time::Duration;
 
 /// Make a GET request to the ChatGPT backend API.
 pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
     config: &Config,
     path: String,
+) -> anyhow::Result<T> {
+    chatgpt_get_request_with_timeout(config, path, None).await
+}
+
+pub(crate) async fn chatgpt_get_request_with_timeout<T: DeserializeOwned>(
+    config: &Config,
+    path: String,
+    timeout: Option<Duration>,
 ) -> anyhow::Result<T> {
     let chatgpt_base_url = &config.chatgpt_base_url;
     init_chatgpt_token_from_auth(&config.codex_home, config.cli_auth_credentials_store_mode)
@@ -27,14 +36,17 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
         anyhow::anyhow!("ChatGPT account ID not available, please re-run `codex login`")
     });
 
-    let response = client
+    let mut request = client
         .get(&url)
         .bearer_auth(&token.access_token)
         .header("chatgpt-account-id", account_id?)
-        .header("Content-Type", "application/json")
-        .send()
-        .await
-        .context("Failed to send request")?;
+        .header("Content-Type", "application/json");
+
+    if let Some(timeout) = timeout {
+        request = request.timeout(timeout);
+    }
+
+    let response = request.send().await.context("Failed to send request")?;
 
     if response.status().is_success() {
         let result: T = response