tui

`--enable enable...` is a bad look

.codespellignore

@@ -1 +1,2 @@
 iTerm
+psuedo

.github/actions/linux-code-sign/action.yml

@@ -0,0 +1,44 @@
+name: linux-code-sign
+description: Sign Linux artifacts with cosign.
+inputs:
+  target:
+    description: Target triple for the artifacts to sign.
+    required: true
+  artifacts-dir:
+    description: Absolute path to the directory containing built binaries to sign.
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Install cosign
+      uses: sigstore/cosign-installer@v3.7.0
+
+    - name: Cosign Linux artifacts
+      shell: bash
+      env:
+        COSIGN_EXPERIMENTAL: "1"
+        COSIGN_YES: "true"
+        COSIGN_OIDC_CLIENT_ID: "sigstore"
+        COSIGN_OIDC_ISSUER: "https://oauth2.sigstore.dev/auth"
+      run: |
+        set -euo pipefail
+
+        dest="${{ inputs.artifacts-dir }}"
+        if [[ ! -d "$dest" ]]; then
+          echo "Destination $dest does not exist"
+          exit 1
+        fi
+
+        for binary in codex codex-responses-api-proxy; do
+          artifact="${dest}/${binary}"
+          if [[ ! -f "$artifact" ]]; then
+            echo "Binary $artifact not found"
+            exit 1
+          fi
+
+          cosign sign-blob \
+            --yes \
+            --bundle "${artifact}.sigstore" \
+            "$artifact"
+        done

.github/actions/windows-code-sign/action.yml

@@ -0,0 +1,57 @@
+name: windows-code-sign
+description: Sign Windows binaries with Azure Trusted Signing.
+inputs:
+  target:
+    description: Target triple for the artifacts to sign.
+    required: true
+  client-id:
+    description: Azure Trusted Signing client ID.
+    required: true
+  tenant-id:
+    description: Azure tenant ID for Trusted Signing.
+    required: true
+  subscription-id:
+    description: Azure subscription ID for Trusted Signing.
+    required: true
+  endpoint:
+    description: Azure Trusted Signing endpoint.
+    required: true
+  account-name:
+    description: Azure Trusted Signing account name.
+    required: true
+  certificate-profile-name:
+    description: Certificate profile name for signing.
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Azure login for Trusted Signing (OIDC)
+      uses: azure/login@v2
+      with:
+        client-id: ${{ inputs.client-id }}
+        tenant-id: ${{ inputs.tenant-id }}
+        subscription-id: ${{ inputs.subscription-id }}
+
+    - name: Sign Windows binaries with Azure Trusted Signing
+      uses: azure/trusted-signing-action@v0
+      with:
+        endpoint: ${{ inputs.endpoint }}
+        trusted-signing-account-name: ${{ inputs.account-name }}
+        certificate-profile-name: ${{ inputs.certificate-profile-name }}
+        exclude-environment-credential: true
+        exclude-workload-identity-credential: true
+        exclude-managed-identity-credential: true
+        exclude-shared-token-cache-credential: true
+        exclude-visual-studio-credential: true
+        exclude-visual-studio-code-credential: true
+        exclude-azure-cli-credential: false
+        exclude-azure-powershell-credential: true
+        exclude-azure-developer-cli-credential: true
+        exclude-interactive-browser-credential: true
+        cache-dependencies: false
+        files: |
+          ${{ github.workspace }}/codex-rs/target/${{ inputs.target }}/release/codex.exe
+          ${{ github.workspace }}/codex-rs/target/${{ inputs.target }}/release/codex-responses-api-proxy.exe
+          ${{ github.workspace }}/codex-rs/target/${{ inputs.target }}/release/codex-windows-sandbox-setup.exe
+          ${{ github.workspace }}/codex-rs/target/${{ inputs.target }}/release/codex-command-runner.exe

.github/codex/home/config.toml

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

.github/pull_request_template.md

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

.github/workflows/cargo-deny.yml

@@ -0,0 +1,26 @@
+name: cargo-deny
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+jobs:
+  cargo-deny:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ./codex-rs
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Run cargo-deny
+        uses: EmbarkStudios/cargo-deny-action@v1
+        with:
+          rust-version: stable
+          manifest-path: ./codex-rs/Cargo.toml

.github/workflows/ci.yml

@@ -12,7 +12,7 @@ jobs:
       NODE_OPTIONS: --max-old-space-size=4096
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Setup pnpm
         uses: pnpm/action-setup@v4
@@ -46,7 +46,7 @@ jobs:
           echo "pack_output=$PACK_OUTPUT" >> "$GITHUB_OUTPUT"
 
       - name: Upload staged npm package artifact
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: codex-npm-staging
           path: ${{ steps.stage_npm_package.outputs.pack_output }}

.github/workflows/cla.yml

@@ -13,17 +13,37 @@ permissions:
 
 jobs:
   cla:
+    # Only run the CLA assistant for the canonical openai repo so forks are not blocked
+    # and contributors who signed previously do not receive duplicate CLA notifications.
+    if: ${{ github.repository_owner == 'openai' }}
     runs-on: ubuntu-latest
     steps:
       - uses: contributor-assistant/github-action@v2.6.1
+        # Run on close only if the PR was merged. This will lock the PR to preserve
+        # the CLA agreement. We don't want to lock PRs that have been closed without
+        # merging because the contributor may want to respond with additional comments.
+        # This action has a "lock-pullrequest-aftermerge" option that can be set to false,
+        # but that would unconditionally skip locking even in cases where the PR was merged.
         if: |
-          github.event_name == 'pull_request_target' ||
-          github.event.comment.body == 'recheck' ||
-          github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA'
+          (
+            github.event_name == 'pull_request_target' &&
+            (
+              github.event.action == 'opened' ||
+              github.event.action == 'synchronize' ||
+              (github.event.action == 'closed' && github.event.pull_request.merged == true)
+            )
+          ) ||
+          (
+            github.event_name == 'issue_comment' &&
+            (
+              github.event.comment.body == 'recheck' ||
+              github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA'
+            )
+          )
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
           path-to-document: https://github.com/openai/codex/blob/main/docs/CLA.md
           path-to-signatures: signatures/cla.json
           branch: cla-signatures
-          allowlist: dependabot[bot]
+          allowlist: codex,dependabot,dependabot[bot],github-actions[bot]

.github/workflows/close-stale-contributor-prs.yml

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

.github/workflows/codespell.yml

@@ -18,10 +18,10 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
       - name: Annotate locations with typos
         uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
       - name: Codespell
-        uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2.1
+        uses: codespell-project/actions-codespell@8f01853be192eb0f849a5c7d721450e7a467c579 # v2.2
         with:
           ignore_words_file: .codespellignore

.github/workflows/issue-deduplicator.yml

@@ -16,7 +16,7 @@ jobs:
     outputs:
       codex_output: ${{ steps.codex.outputs.final-message }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
       - name: Prepare Codex inputs
         env:
@@ -46,7 +46,6 @@ jobs:
         with:
           openai-api-key: ${{ secrets.CODEX_OPENAI_API_KEY }}
           allow-users: "*"
-          model: gpt-5
           prompt: |
             You are an assistant that triages new GitHub issues by identifying potential duplicates.
 
@@ -87,7 +86,7 @@ jobs:
       issues: write
     steps:
       - name: Comment on issue
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         env:
           CODEX_OUTPUT: ${{ needs.gather-duplicates.outputs.codex_output }}
         with:

.github/workflows/issue-labeler.yml

@@ -16,7 +16,7 @@ jobs:
     outputs:
       codex_output: ${{ steps.codex.outputs.final-message }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
       - id: codex
         uses: openai/codex-action@main
@@ -26,21 +26,36 @@ jobs:
           prompt: |
             You are an assistant that reviews GitHub issues for the repository.
 
-            Your job is to choose the most appropriate existing labels for the issue described later in this prompt.
+            Your job is to choose the most appropriate labels for the issue described later in this prompt.
             Follow these rules:
-            - Only pick labels out of the list below.
-            - Prefer a small set of precise labels over many broad ones.
 
-            Labels to apply:
+            - Add one (and only one) of the following three labels to distinguish the type of issue. Default to "bug" if unsure.
             1. bug — Reproducible defects in Codex products (CLI, VS Code extension, web, auth).
             2. enhancement — Feature requests or usability improvements that ask for new capabilities, better ergonomics, or quality-of-life tweaks.
-            3. extension — VS Code (or other IDE) extension-specific issues.
-            4. windows-os — Bugs or friction specific to Windows environments (always when PowerShell is mentioned, path handling, copy/paste, OS-specific auth or tooling failures).
-            5. mcp — Topics involving Model Context Protocol servers/clients.
-            6. codex-web — Issues targeting the Codex web UI/Cloud experience.
-            8. azure — Problems or requests tied to Azure OpenAI deployments.
-            9. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
-            10. model-behavior — Undesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
+            3. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
+
+            - If applicable, add one of the following labels to specify which sub-product or product surface the issue relates to.
+            1. CLI — the Codex command line interface.
+            2. extension — VS Code (or other IDE) extension-specific issues.
+            3. codex-web — Issues targeting the Codex web UI/Cloud experience.
+            4. github-action — Issues with the Codex GitHub action.
+            5. iOS — Issues with the Codex iOS app.
+
+            - Additionally add zero or more of the following labels that are relevant to the issue content. Prefer a small set of precise labels over many broad ones.
+            1. windows-os — Bugs or friction specific to Windows environments (always when PowerShell is mentioned, path handling, copy/paste, OS-specific auth or tooling failures).
+            2. mcp — Topics involving Model Context Protocol servers/clients.
+            3. mcp-server — Problems related to the codex mcp-server command, where codex runs as an MCP server.
+            4. azure — Problems or requests tied to Azure OpenAI deployments.
+            5. model-behavior — Undesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
+            6. code-review — Issues related to the code review feature or functionality.
+            7. auth - Problems related to authentication, login, or access tokens.
+            8. codex-exec - Problems related to the "codex exec" command or functionality.
+            9. context-management - Problems related to compaction, context windows, or available context reporting.
+            10. custom-model - Problems that involve using custom model providers, local models, or OSS models.
+            11. rate-limits - Problems related to token limits, rate limits, or token usage reporting.
+            12. sandbox - Issues related to local sandbox environments or tool call approvals to override sandbox restrictions.
+            13. tool-calls - Problems related to specific tool call invocations including unexpected errors, failures, or hangs.
+            14. TUI - Problems with the terminal user interface (TUI) including keyboard shortcuts, copy & pasting, menus, or screen update issues.
 
             Issue number: ${{ github.event.issue.number }}
 

.github/workflows/rust-ci.yml

@@ -9,7 +9,7 @@ on:
 # CI builds in debug (dev) for faster signal.
 
 jobs:
-  # --- Detect what changed (always runs) -------------------------------------
+  # --- Detect what changed to detect which tests to run (always runs) -------------------------------------
   changed:
     name: Detect changed areas
     runs-on: ubuntu-24.04
@@ -17,7 +17,7 @@ jobs:
       codex: ${{ steps.detect.outputs.codex }}
       workflows: ${{ steps.detect.outputs.workflows }}
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Detect changed paths (no external action)
@@ -56,7 +56,7 @@ jobs:
       run:
         working-directory: codex-rs
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: dtolnay/rust-toolchain@1.90
         with:
           components: rustfmt
@@ -74,9 +74,9 @@ jobs:
       run:
         working-directory: codex-rs
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: dtolnay/rust-toolchain@1.90
-      - uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
+      - uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
         with:
           tool: cargo-shear
           version: 1.5.1
@@ -84,8 +84,8 @@ jobs:
         run: cargo shear
 
   # --- CI to validate on different os/targets --------------------------------
-  lint_build_test:
-    name: ${{ matrix.runner }} - ${{ matrix.target }}${{ matrix.profile == 'release' && ' (release)' || '' }}
+  lint_build:
+    name: Lint/Build — ${{ matrix.runner }} - ${{ matrix.target }}${{ matrix.profile == 'release' && ' (release)' || '' }}
     runs-on: ${{ matrix.runner }}
     timeout-minutes: 30
     needs: changed
@@ -94,6 +94,11 @@ jobs:
     defaults:
       run:
         working-directory: codex-rs
+    env:
+      # Speed up repeated builds across CI runs by caching compiled objects (non-Windows).
+      USE_SCCACHE: ${{ startsWith(matrix.runner, 'windows') && 'false' || 'true' }}
+      CARGO_INCREMENTAL: "0"
+      SCCACHE_CACHE_SIZE: 10G
 
     strategy:
       fail-fast: false
@@ -142,37 +147,116 @@ jobs:
             profile: release
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: dtolnay/rust-toolchain@1.90
         with:
           targets: ${{ matrix.target }}
           components: clippy
 
+      - name: Compute lockfile hash
+        id: lockhash
+        working-directory: codex-rs
+        shell: bash
+        run: |
+          set -euo pipefail
+          echo "hash=$(sha256sum Cargo.lock | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
+          echo "toolchain_hash=$(sha256sum rust-toolchain.toml | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
+
       # Explicit cache restore: split cargo home vs target, so we can
       # avoid caching the large target dir on the gnu-dev job.
       - name: Restore cargo home cache
         id: cache_cargo_home_restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@v5
         with:
           path: |
             ~/.cargo/bin/
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
-          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}
+          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 }}-
 
-      - name: Restore target cache (except gnu-dev)
-        id: cache_target_restore
-        if: ${{ !(matrix.target == 'x86_64-unknown-linux-gnu' && matrix.profile != 'release') }}
-        uses: actions/cache/restore@v4
+      # Install and restore sccache cache
+      - name: Install sccache
+        if: ${{ env.USE_SCCACHE == 'true' }}
+        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
         with:
-          path: ${{ github.workspace }}/codex-rs/target/
-          key: cargo-target-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}
+          tool: sccache
+          version: 0.7.5
+
+      - name: Configure sccache backend
+        if: ${{ env.USE_SCCACHE == 'true' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          if [[ -n "${ACTIONS_CACHE_URL:-}" && -n "${ACTIONS_RUNTIME_TOKEN:-}" ]]; then
+            echo "SCCACHE_GHA_ENABLED=true" >> "$GITHUB_ENV"
+            echo "Using sccache GitHub backend"
+          else
+            echo "SCCACHE_GHA_ENABLED=false" >> "$GITHUB_ENV"
+            echo "SCCACHE_DIR=${{ github.workspace }}/.sccache" >> "$GITHUB_ENV"
+            echo "Using sccache local disk + actions/cache fallback"
+          fi
+
+      - name: Enable sccache wrapper
+        if: ${{ env.USE_SCCACHE == 'true' }}
+        shell: bash
+        run: echo "RUSTC_WRAPPER=sccache" >> "$GITHUB_ENV"
+
+      - name: Restore sccache cache (fallback)
+        if: ${{ env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true' }}
+        id: cache_sccache_restore
+        uses: actions/cache/restore@v5
+        with:
+          path: ${{ github.workspace }}/.sccache/
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+          restore-keys: |
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
+
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Prepare APT cache directories (musl)
+        shell: bash
+        run: |
+          set -euo pipefail
+          sudo mkdir -p /var/cache/apt/archives /var/lib/apt/lists
+          sudo chown -R "$USER:$USER" /var/cache/apt /var/lib/apt/lists
+
+      - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Restore APT cache (musl)
+        id: cache_apt_restore
+        uses: actions/cache/restore@v5
+        with:
+          path: |
+            /var/cache/apt
+          key: apt-${{ matrix.runner }}-${{ matrix.target }}-v1
 
       - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
         name: Install musl build tools
+        env:
+          DEBIAN_FRONTEND: noninteractive
+        shell: bash
         run: |
-          sudo apt install -y musl-tools pkg-config && sudo rm -rf /var/lib/apt/lists/*
+          set -euo pipefail
+          sudo apt-get -y update -o Acquire::Retries=3
+          sudo apt-get -y install --no-install-recommends musl-tools pkg-config
+
+      - name: Install cargo-chef
+        if: ${{ matrix.profile == 'release' }}
+        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        with:
+          tool: cargo-chef
+          version: 0.1.71
+
+      - name: Pre-warm dependency cache (cargo-chef)
+        if: ${{ matrix.profile == 'release' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          RECIPE="${RUNNER_TEMP}/chef-recipe.json"
+          cargo chef prepare --recipe-path "$RECIPE"
+          cargo chef cook --recipe-path "$RECIPE" --target ${{ matrix.target }} --release --all-features
 
       - name: cargo clippy
         id: clippy
@@ -191,59 +275,265 @@ jobs:
           find . -name Cargo.toml -mindepth 2 -maxdepth 2 -print0 \
             | xargs -0 -n1 -I{} bash -c 'cd "$(dirname "{}")" && cargo check --profile ${{ matrix.profile }}'
 
-      - uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
-        with:
-          tool: nextest
-          version: 0.9.103
-
-      - name: tests
-        id: test
-        # Tests take too long for release builds to run them on every PR.
-        if: ${{ matrix.profile != 'release' }}
-        continue-on-error: true
-        run: cargo nextest run --all-features --no-fail-fast --target ${{ matrix.target }}
-        env:
-          RUST_BACKTRACE: 1
-
       # Save caches explicitly; make non-fatal so cache packaging
       # never fails the overall job. Only save when key wasn't hit.
       - name: Save cargo home cache
         if: always() && !cancelled() && steps.cache_cargo_home_restore.outputs.cache-hit != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@v5
         with:
           path: |
             ~/.cargo/bin/
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
-          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
 
-      - name: Save target cache (except gnu-dev)
-        if: >-
-          always() && !cancelled() &&
-          (steps.cache_target_restore.outputs.cache-hit != 'true') &&
-          !(matrix.target == 'x86_64-unknown-linux-gnu' && matrix.profile != 'release')
+      - name: Save sccache cache (fallback)
+        if: always() && !cancelled() && env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@v5
         with:
-          path: ${{ github.workspace }}/codex-rs/target/
-          key: cargo-target-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}
+          path: ${{ github.workspace }}/.sccache/
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+
+      - name: sccache stats
+        if: always() && env.USE_SCCACHE == 'true'
+        continue-on-error: true
+        run: sccache --show-stats || true
+
+      - name: sccache summary
+        if: always() && env.USE_SCCACHE == 'true'
+        shell: bash
+        run: |
+          {
+            echo "### sccache stats — ${{ matrix.target }} (${{ matrix.profile }})";
+            echo;
+            echo '```';
+            sccache --show-stats || true;
+            echo '```';
+          } >> "$GITHUB_STEP_SUMMARY"
+
+      - name: Save APT cache (musl)
+        if: always() && !cancelled() && (matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl') && steps.cache_apt_restore.outputs.cache-hit != 'true'
+        continue-on-error: true
+        uses: actions/cache/save@v5
+        with:
+          path: |
+            /var/cache/apt
+          key: apt-${{ matrix.runner }}-${{ matrix.target }}-v1
 
       # Fail the job if any of the previous steps failed.
       - name: verify all steps passed
         if: |
           steps.clippy.outcome == 'failure' ||
-          steps.cargo_check_all_crates.outcome == 'failure' ||
-          steps.test.outcome == 'failure'
+          steps.cargo_check_all_crates.outcome == 'failure'
         run: |
-          echo "One or more checks failed (clippy, cargo_check_all_crates, or test). See logs for details."
+          echo "One or more checks failed (clippy or cargo_check_all_crates). See logs for details."
+          exit 1
+
+  tests:
+    name: Tests — ${{ matrix.runner }} - ${{ matrix.target }}
+    runs-on: ${{ matrix.runner }}
+    timeout-minutes: 30
+    needs: changed
+    if: ${{ needs.changed.outputs.codex == 'true' || needs.changed.outputs.workflows == 'true' || github.event_name == 'push' }}
+    defaults:
+      run:
+        working-directory: codex-rs
+    env:
+      # Speed up repeated builds across CI runs by caching compiled objects (non-Windows).
+      USE_SCCACHE: ${{ startsWith(matrix.runner, 'windows') && 'false' || 'true' }}
+      CARGO_INCREMENTAL: "0"
+      SCCACHE_CACHE_SIZE: 10G
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: macos-14
+            target: aarch64-apple-darwin
+            profile: dev
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-gnu
+            profile: dev
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-gnu
+            profile: dev
+          - runner: windows-latest
+            target: x86_64-pc-windows-msvc
+            profile: dev
+          - runner: windows-11-arm
+            target: aarch64-pc-windows-msvc
+            profile: dev
+
+    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
+
+      # Ensure brew includes this fix so that brew's shellenv.sh loads
+      # cleanly in the Codex sandbox (it is frequently eval'd via .zprofile
+      # for Brew users, including the macOS runners on GitHub):
+      #
+      # https://github.com/Homebrew/brew/pull/21157
+      #
+      # Once brew 5.0.5 is released and is the default on macOS runners, this
+      # step can be removed.
+      - name: Upgrade brew
+        if: ${{ startsWith(matrix.runner, 'macos') }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          brew --version
+          git -C "$(brew --repo)" fetch origin
+          git -C "$(brew --repo)" checkout main
+          git -C "$(brew --repo)" reset --hard origin/main
+          export HOMEBREW_UPDATE_TO_TAG=0
+          brew update
+          brew upgrade
+          brew --version
+
+      # 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
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Compute lockfile hash
+        id: lockhash
+        working-directory: codex-rs
+        shell: bash
+        run: |
+          set -euo pipefail
+          echo "hash=$(sha256sum Cargo.lock | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
+          echo "toolchain_hash=$(sha256sum rust-toolchain.toml | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
+
+      - name: Restore cargo home cache
+        id: cache_cargo_home_restore
+        uses: actions/cache/restore@v5
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+          key: cargo-home-${{ 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 }}-
+
+      - name: Install sccache
+        if: ${{ env.USE_SCCACHE == 'true' }}
+        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        with:
+          tool: sccache
+          version: 0.7.5
+
+      - name: Configure sccache backend
+        if: ${{ env.USE_SCCACHE == 'true' }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          if [[ -n "${ACTIONS_CACHE_URL:-}" && -n "${ACTIONS_RUNTIME_TOKEN:-}" ]]; then
+            echo "SCCACHE_GHA_ENABLED=true" >> "$GITHUB_ENV"
+            echo "Using sccache GitHub backend"
+          else
+            echo "SCCACHE_GHA_ENABLED=false" >> "$GITHUB_ENV"
+            echo "SCCACHE_DIR=${{ github.workspace }}/.sccache" >> "$GITHUB_ENV"
+            echo "Using sccache local disk + actions/cache fallback"
+          fi
+
+      - name: Enable sccache wrapper
+        if: ${{ env.USE_SCCACHE == 'true' }}
+        shell: bash
+        run: echo "RUSTC_WRAPPER=sccache" >> "$GITHUB_ENV"
+
+      - name: Restore sccache cache (fallback)
+        if: ${{ env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true' }}
+        id: cache_sccache_restore
+        uses: actions/cache/restore@v5
+        with:
+          path: ${{ github.workspace }}/.sccache/
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+          restore-keys: |
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
+
+      - uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        with:
+          tool: nextest
+          version: 0.9.103
+
+      - name: tests
+        id: test
+        run: cargo nextest run --all-features --no-fail-fast --target ${{ matrix.target }} --cargo-profile ci-test
+        env:
+          RUST_BACKTRACE: 1
+          NEXTEST_STATUS_LEVEL: leak
+
+      - name: Save cargo home cache
+        if: always() && !cancelled() && steps.cache_cargo_home_restore.outputs.cache-hit != 'true'
+        continue-on-error: true
+        uses: actions/cache/save@v5
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
+
+      - name: Save sccache cache (fallback)
+        if: always() && !cancelled() && env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true'
+        continue-on-error: true
+        uses: actions/cache/save@v5
+        with:
+          path: ${{ github.workspace }}/.sccache/
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+
+      - name: sccache stats
+        if: always() && env.USE_SCCACHE == 'true'
+        continue-on-error: true
+        run: sccache --show-stats || true
+
+      - name: sccache summary
+        if: always() && env.USE_SCCACHE == 'true'
+        shell: bash
+        run: |
+          {
+            echo "### sccache stats — ${{ matrix.target }} (tests)";
+            echo;
+            echo '```';
+            sccache --show-stats || true;
+            echo '```';
+          } >> "$GITHUB_STEP_SUMMARY"
+
+      - name: verify tests passed
+        if: steps.test.outcome == 'failure'
+        run: |
+          echo "Tests failed. See logs for details."
           exit 1
 
   # --- Gatherer job that you mark as the ONLY required status -----------------
   results:
     name: CI results (required)
-    needs: [changed, general, cargo_shear, lint_build_test]
+    needs: [changed, general, cargo_shear, lint_build, tests]
     if: always()
     runs-on: ubuntu-24.04
     steps:
@@ -252,7 +542,8 @@ jobs:
         run: |
           echo "general: ${{ needs.general.result }}"
           echo "shear  : ${{ needs.cargo_shear.result }}"
-          echo "matrix : ${{ needs.lint_build_test.result }}"
+          echo "lint   : ${{ needs.lint_build.result }}"
+          echo "tests  : ${{ needs.tests.result }}"
 
           # If nothing relevant changed (PR touching only root README, etc.),
           # declare success regardless of other jobs.
@@ -264,4 +555,10 @@ jobs:
           # Otherwise require the jobs to have succeeded
           [[ '${{ needs.general.result }}' == 'success' ]] || { echo 'general failed'; exit 1; }
           [[ '${{ needs.cargo_shear.result }}' == 'success' ]] || { echo 'cargo_shear failed'; exit 1; }
-          [[ '${{ needs.lint_build_test.result }}' == 'success' ]] || { echo 'matrix failed'; exit 1; }
+          [[ '${{ needs.lint_build.result }}' == 'success' ]] || { echo 'lint_build failed'; exit 1; }
+          [[ '${{ needs.tests.result }}' == 'success' ]] || { echo 'tests failed'; exit 1; }
+
+      - name: sccache summary note
+        if: always()
+        run: |
+          echo "Per-job sccache stats are attached to each matrix job's Step Summary."

.github/workflows/rust-release.yml

@@ -19,7 +19,7 @@ jobs:
   tag-check:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
 
       - name: Validate tag matches Cargo.toml version
         shell: bash
@@ -50,6 +50,9 @@ jobs:
     name: Build - ${{ matrix.runner }} - ${{ matrix.target }}
     runs-on: ${{ matrix.runner }}
     timeout-minutes: 30
+    permissions:
+      contents: read
+      id-token: write
     defaults:
       run:
         working-directory: codex-rs
@@ -58,9 +61,9 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - runner: macos-14
+          - runner: macos-15-xlarge
             target: aarch64-apple-darwin
-          - runner: macos-14
+          - runner: macos-15-xlarge
             target: x86_64-apple-darwin
           - runner: ubuntu-24.04
             target: x86_64-unknown-linux-musl
@@ -76,12 +79,12 @@ jobs:
             target: aarch64-pc-windows-msvc
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: dtolnay/rust-toolchain@1.90
         with:
           targets: ${{ matrix.target }}
 
-      - uses: actions/cache@v4
+      - uses: actions/cache@v5
         with:
           path: |
             ~/.cargo/bin/
@@ -98,9 +101,34 @@ jobs:
           sudo apt-get install -y musl-tools pkg-config
 
       - name: Cargo build
-        run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
+        shell: bash
+        run: |
+          if [[ "${{ contains(matrix.target, 'windows') }}" == 'true' ]]; then
+            cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy --bin codex-windows-sandbox-setup --bin codex-command-runner
+          else
+            cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
+          fi
 
-      - if: ${{ matrix.runner == 'macos-14' }}
+      - if: ${{ contains(matrix.target, 'linux') }}
+        name: Cosign Linux artifacts
+        uses: ./.github/actions/linux-code-sign
+        with:
+          target: ${{ matrix.target }}
+          artifacts-dir: ${{ github.workspace }}/codex-rs/target/${{ matrix.target }}/release
+
+      - if: ${{ contains(matrix.target, 'windows') }}
+        name: Sign Windows binaries with Azure Trusted Signing
+        uses: ./.github/actions/windows-code-sign
+        with:
+          target: ${{ matrix.target }}
+          client-id: ${{ secrets.AZURE_TRUSTED_SIGNING_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TRUSTED_SIGNING_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_TRUSTED_SIGNING_SUBSCRIPTION_ID }}
+          endpoint: ${{ secrets.AZURE_TRUSTED_SIGNING_ENDPOINT }}
+          account-name: ${{ secrets.AZURE_TRUSTED_SIGNING_ACCOUNT_NAME }}
+          certificate-profile-name: ${{ secrets.AZURE_TRUSTED_SIGNING_CERTIFICATE_PROFILE_NAME }}
+
+      - if: ${{ matrix.runner == 'macos-15-xlarge' }}
         name: Configure Apple code signing
         shell: bash
         env:
@@ -185,7 +213,7 @@ jobs:
           echo "APPLE_CODESIGN_KEYCHAIN=$keychain_path" >> "$GITHUB_ENV"
           echo "::add-mask::$APPLE_CODESIGN_IDENTITY"
 
-      - if: ${{ matrix.runner == 'macos-14' }}
+      - if: ${{ matrix.runner == 'macos-15-xlarge' }}
         name: Sign macOS binaries
         shell: bash
         run: |
@@ -206,6 +234,69 @@ jobs:
             codesign --force --options runtime --timestamp --sign "$APPLE_CODESIGN_IDENTITY" "${keychain_args[@]}" "$path"
           done
 
+      - if: ${{ matrix.runner == 'macos-15-xlarge' }}
+        name: Notarize macOS binaries
+        shell: bash
+        env:
+          APPLE_NOTARIZATION_KEY_P8: ${{ secrets.APPLE_NOTARIZATION_KEY_P8 }}
+          APPLE_NOTARIZATION_KEY_ID: ${{ secrets.APPLE_NOTARIZATION_KEY_ID }}
+          APPLE_NOTARIZATION_ISSUER_ID: ${{ secrets.APPLE_NOTARIZATION_ISSUER_ID }}
+        run: |
+          set -euo pipefail
+
+          for var in APPLE_NOTARIZATION_KEY_P8 APPLE_NOTARIZATION_KEY_ID APPLE_NOTARIZATION_ISSUER_ID; do
+            if [[ -z "${!var:-}" ]]; then
+              echo "$var is required for notarization"
+              exit 1
+            fi
+          done
+
+          notary_key_path="${RUNNER_TEMP}/notarytool.key.p8"
+          echo "$APPLE_NOTARIZATION_KEY_P8" | base64 -d > "$notary_key_path"
+          cleanup_notary() {
+            rm -f "$notary_key_path"
+          }
+          trap cleanup_notary EXIT
+
+          notarize_binary() {
+            local binary="$1"
+            local source_path="target/${{ matrix.target }}/release/${binary}"
+            local archive_path="${RUNNER_TEMP}/${binary}.zip"
+
+            if [[ ! -f "$source_path" ]]; then
+              echo "Binary $source_path not found"
+              exit 1
+            fi
+
+            rm -f "$archive_path"
+            ditto -c -k --keepParent "$source_path" "$archive_path"
+
+            submission_json=$(xcrun notarytool submit "$archive_path" \
+              --key "$notary_key_path" \
+              --key-id "$APPLE_NOTARIZATION_KEY_ID" \
+              --issuer "$APPLE_NOTARIZATION_ISSUER_ID" \
+              --output-format json \
+              --wait)
+
+            status=$(printf '%s\n' "$submission_json" | jq -r '.status // "Unknown"')
+            submission_id=$(printf '%s\n' "$submission_json" | jq -r '.id // ""')
+
+            if [[ -z "$submission_id" ]]; then
+              echo "Failed to retrieve submission ID for $binary"
+              exit 1
+            fi
+
+            echo "::notice title=Notarization::$binary submission ${submission_id} completed with status ${status}"
+
+            if [[ "$status" != "Accepted" ]]; then
+              echo "Notarization failed for ${binary} (submission ${submission_id}, status ${status})"
+              exit 1
+            fi
+          }
+
+          notarize_binary "codex"
+          notarize_binary "codex-responses-api-proxy"
+
       - name: Stage artifacts
         shell: bash
         run: |
@@ -215,11 +306,18 @@ jobs:
           if [[ "${{ matrix.runner }}" == windows* ]]; then
             cp target/${{ matrix.target }}/release/codex.exe "$dest/codex-${{ matrix.target }}.exe"
             cp target/${{ matrix.target }}/release/codex-responses-api-proxy.exe "$dest/codex-responses-api-proxy-${{ matrix.target }}.exe"
+            cp target/${{ matrix.target }}/release/codex-windows-sandbox-setup.exe "$dest/codex-windows-sandbox-setup-${{ matrix.target }}.exe"
+            cp target/${{ matrix.target }}/release/codex-command-runner.exe "$dest/codex-command-runner-${{ matrix.target }}.exe"
           else
             cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
             cp target/${{ matrix.target }}/release/codex-responses-api-proxy "$dest/codex-responses-api-proxy-${{ matrix.target }}"
           fi
 
+          if [[ "${{ matrix.target }}" == *linux* ]]; then
+            cp target/${{ matrix.target }}/release/codex.sigstore "$dest/codex-${{ matrix.target }}.sigstore"
+            cp target/${{ matrix.target }}/release/codex-responses-api-proxy.sigstore "$dest/codex-responses-api-proxy-${{ matrix.target }}.sigstore"
+          fi
+
       - if: ${{ matrix.runner == 'windows-11-arm' }}
         name: Install zstd
         shell: powershell
@@ -232,6 +330,15 @@ jobs:
           # ${{ matrix.target }}
           dest="dist/${{ matrix.target }}"
 
+          # We want to ship the raw Windows executables in the GitHub Release
+          # in addition to the compressed archives. Keep the originals for
+          # Windows targets; remove them elsewhere to limit the number of
+          # artifacts that end up in the GitHub Release.
+          keep_originals=false
+          if [[ "${{ matrix.runner }}" == windows* ]]; then
+            keep_originals=true
+          fi
+
           # For compatibility with environments that lack the `zstd` tool we
           # additionally create a `.tar.gz` for all platforms and `.zip` for
           # Windows alongside every single binary that we publish. The end result is:
@@ -249,6 +356,11 @@ jobs:
               continue
             fi
 
+            # Don't try to compress signature bundles.
+            if [[ "$base" == *.sigstore ]]; then
+              continue
+            fi
+
             # Create per-binary tar.gz
             tar -C "$dest" -czf "$dest/${base}.tar.gz" "$base"
 
@@ -261,11 +373,15 @@ jobs:
 
             # Also create .zst (existing behaviour) *and* remove the original
             # uncompressed binary to keep the directory small.
-            zstd -T0 -19 --rm "$dest/$base"
+            zstd_args=(-T0 -19)
+            if [[ "${keep_originals}" == false ]]; then
+              zstd_args+=(--rm)
+            fi
+            zstd "${zstd_args[@]}" "$dest/$base"
           done
 
       - name: Remove signing keychain
-        if: ${{ always() && matrix.runner == 'macos-14' }}
+        if: ${{ always() && matrix.runner == 'macos-15-xlarge' }}
         shell: bash
         env:
           APPLE_CODESIGN_KEYCHAIN: ${{ env.APPLE_CODESIGN_KEYCHAIN }}
@@ -287,7 +403,7 @@ jobs:
             fi
           fi
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v6
         with:
           name: ${{ matrix.target }}
           # Upload the per-binary .zst files as well as the new .tar.gz
@@ -295,8 +411,19 @@ jobs:
           path: |
             codex-rs/dist/${{ matrix.target }}/*
 
+  shell-tool-mcp:
+    name: shell-tool-mcp
+    needs: tag-check
+    uses: ./.github/workflows/shell-tool-mcp.yml
+    with:
+      release-tag: ${{ github.ref_name }}
+      publish: true
+    secrets: inherit
+
   release:
-    needs: build
+    needs:
+      - build
+      - shell-tool-mcp
     name: release
     runs-on: ubuntu-latest
     permissions:
@@ -310,15 +437,23 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v7
         with:
           path: dist
 
       - name: List
         run: ls -R dist/
 
+      # This is a temporary fix: we should modify shell-tool-mcp.yml so these
+      # files do not end up in dist/ in the first place.
+      - name: Delete entries from dist/ that should not go in the release
+        run: |
+          rm -rf dist/shell-tool-mcp*
+
+          ls -R dist/
+
       - name: Define release name
         id: release_name
         run: |

.github/workflows/sdk.yml

@@ -11,7 +11,7 @@ jobs:
     timeout-minutes: 10
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Setup pnpm
         uses: pnpm/action-setup@v4

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

@@ -0,0 +1,48 @@
+name: shell-tool-mcp CI
+
+on:
+  push:
+    paths:
+      - "shell-tool-mcp/**"
+      - ".github/workflows/shell-tool-mcp-ci.yml"
+      - "pnpm-lock.yaml"
+      - "pnpm-workspace.yaml"
+  pull_request:
+    paths:
+      - "shell-tool-mcp/**"
+      - ".github/workflows/shell-tool-mcp-ci.yml"
+      - "pnpm-lock.yaml"
+      - "pnpm-workspace.yaml"
+
+env:
+  NODE_VERSION: 22
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          run_install: false
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v5
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          cache: "pnpm"
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Format check
+        run: pnpm --filter @openai/codex-shell-tool-mcp run format
+
+      - name: Run tests
+        run: pnpm --filter @openai/codex-shell-tool-mcp test
+
+      - name: Build
+        run: pnpm --filter @openai/codex-shell-tool-mcp run build

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

@@ -0,0 +1,405 @@
+name: shell-tool-mcp
+
+on:
+  workflow_call:
+    inputs:
+      release-version:
+        description: Version to publish (x.y.z or x.y.z-alpha.N). Defaults to GITHUB_REF_NAME when it starts with rust-v.
+        required: false
+        type: string
+      release-tag:
+        description: Tag name to use when downloading release artifacts (defaults to rust-v<version>).
+        required: false
+        type: string
+      publish:
+        description: Whether to publish to npm when the version is releasable.
+        required: false
+        default: true
+        type: boolean
+
+env:
+  NODE_VERSION: 22
+
+jobs:
+  metadata:
+    runs-on: ubuntu-latest
+    outputs:
+      version: ${{ steps.compute.outputs.version }}
+      release_tag: ${{ steps.compute.outputs.release_tag }}
+      should_publish: ${{ steps.compute.outputs.should_publish }}
+      npm_tag: ${{ steps.compute.outputs.npm_tag }}
+    steps:
+      - name: Compute version and tags
+        id: compute
+        run: |
+          set -euo pipefail
+
+          version="${{ inputs.release-version }}"
+          release_tag="${{ inputs.release-tag }}"
+
+          if [[ -z "$version" ]]; then
+            if [[ -n "$release_tag" && "$release_tag" =~ ^rust-v.+ ]]; then
+              version="${release_tag#rust-v}"
+            elif [[ "${GITHUB_REF_NAME:-}" =~ ^rust-v.+ ]]; then
+              version="${GITHUB_REF_NAME#rust-v}"
+              release_tag="${GITHUB_REF_NAME}"
+            else
+              echo "release-version is required when GITHUB_REF_NAME is not a rust-v tag."
+              exit 1
+            fi
+          fi
+
+          if [[ -z "$release_tag" ]]; then
+            release_tag="rust-v${version}"
+          fi
+
+          npm_tag=""
+          should_publish="false"
+          if [[ "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            should_publish="true"
+          elif [[ "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+-alpha\.[0-9]+$ ]]; then
+            should_publish="true"
+            npm_tag="alpha"
+          fi
+
+          echo "version=${version}" >> "$GITHUB_OUTPUT"
+          echo "release_tag=${release_tag}" >> "$GITHUB_OUTPUT"
+          echo "npm_tag=${npm_tag}" >> "$GITHUB_OUTPUT"
+          echo "should_publish=${should_publish}" >> "$GITHUB_OUTPUT"
+
+  rust-binaries:
+    name: Build Rust - ${{ matrix.target }}
+    needs: metadata
+    runs-on: ${{ matrix.runner }}
+    timeout-minutes: 30
+    defaults:
+      run:
+        working-directory: codex-rs
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: macos-15-xlarge
+            target: aarch64-apple-darwin
+          - runner: macos-15-xlarge
+            target: x86_64-apple-darwin
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+            install_musl: true
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            install_musl: true
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - uses: dtolnay/rust-toolchain@1.90
+        with:
+          targets: ${{ matrix.target }}
+
+      - if: ${{ matrix.install_musl }}
+        name: Install musl build dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y musl-tools pkg-config
+
+      - name: Build exec server binaries
+        run: cargo build --release --target ${{ matrix.target }} --bin codex-exec-mcp-server --bin codex-execve-wrapper
+
+      - name: Stage exec server binaries
+        run: |
+          dest="${GITHUB_WORKSPACE}/artifacts/vendor/${{ matrix.target }}"
+          mkdir -p "$dest"
+          cp "target/${{ matrix.target }}/release/codex-exec-mcp-server" "$dest/"
+          cp "target/${{ matrix.target }}/release/codex-execve-wrapper" "$dest/"
+
+      - uses: actions/upload-artifact@v6
+        with:
+          name: shell-tool-mcp-rust-${{ matrix.target }}
+          path: artifacts/**
+          if-no-files-found: error
+
+  bash-linux:
+    name: Build Bash (Linux) - ${{ matrix.variant }} - ${{ matrix.target }}
+    needs: metadata
+    runs-on: ${{ matrix.runner }}
+    timeout-minutes: 30
+    container:
+      image: ${{ matrix.image }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+            variant: ubuntu-24.04
+            image: ubuntu:24.04
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+            variant: ubuntu-22.04
+            image: ubuntu:22.04
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+            variant: debian-12
+            image: debian:12
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+            variant: debian-11
+            image: debian:11
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-musl
+            variant: centos-9
+            image: quay.io/centos/centos:stream9
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            variant: ubuntu-24.04
+            image: arm64v8/ubuntu:24.04
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            variant: ubuntu-22.04
+            image: arm64v8/ubuntu:22.04
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            variant: ubuntu-20.04
+            image: arm64v8/ubuntu:20.04
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            variant: debian-12
+            image: arm64v8/debian:12
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            variant: debian-11
+            image: arm64v8/debian:11
+          - runner: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-musl
+            variant: centos-9
+            image: quay.io/centos/centos:stream9
+    steps:
+      - name: Install build prerequisites
+        shell: bash
+        run: |
+          set -euo pipefail
+          if command -v apt-get >/dev/null 2>&1; then
+            apt-get update
+            DEBIAN_FRONTEND=noninteractive apt-get install -y git build-essential bison autoconf gettext
+          elif command -v dnf >/dev/null 2>&1; then
+            dnf install -y git gcc gcc-c++ make bison autoconf gettext
+          elif command -v yum >/dev/null 2>&1; then
+            yum install -y git gcc gcc-c++ make bison autoconf gettext
+          else
+            echo "Unsupported package manager in container"
+            exit 1
+          fi
+
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Build patched Bash
+        shell: bash
+        run: |
+          set -euo pipefail
+          git clone --depth 1 https://github.com/bminor/bash /tmp/bash
+          cd /tmp/bash
+          git fetch --depth 1 origin a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
+          git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
+          git apply "${GITHUB_WORKSPACE}/shell-tool-mcp/patches/bash-exec-wrapper.patch"
+          ./configure --without-bash-malloc
+          cores="$(command -v nproc >/dev/null 2>&1 && nproc || getconf _NPROCESSORS_ONLN)"
+          make -j"${cores}"
+
+          dest="${GITHUB_WORKSPACE}/artifacts/vendor/${{ matrix.target }}/bash/${{ matrix.variant }}"
+          mkdir -p "$dest"
+          cp bash "$dest/bash"
+
+      - uses: actions/upload-artifact@v6
+        with:
+          name: shell-tool-mcp-bash-${{ matrix.target }}-${{ matrix.variant }}
+          path: artifacts/**
+          if-no-files-found: error
+
+  bash-darwin:
+    name: Build Bash (macOS) - ${{ matrix.variant }} - ${{ matrix.target }}
+    needs: metadata
+    runs-on: ${{ matrix.runner }}
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: macos-15-xlarge
+            target: aarch64-apple-darwin
+            variant: macos-15
+          - runner: macos-14
+            target: aarch64-apple-darwin
+            variant: macos-14
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Build patched Bash
+        shell: bash
+        run: |
+          set -euo pipefail
+          git clone --depth 1 https://github.com/bminor/bash /tmp/bash
+          cd /tmp/bash
+          git fetch --depth 1 origin a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
+          git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
+          git apply "${GITHUB_WORKSPACE}/shell-tool-mcp/patches/bash-exec-wrapper.patch"
+          ./configure --without-bash-malloc
+          cores="$(getconf _NPROCESSORS_ONLN)"
+          make -j"${cores}"
+
+          dest="${GITHUB_WORKSPACE}/artifacts/vendor/${{ matrix.target }}/bash/${{ matrix.variant }}"
+          mkdir -p "$dest"
+          cp bash "$dest/bash"
+
+      - uses: actions/upload-artifact@v6
+        with:
+          name: shell-tool-mcp-bash-${{ matrix.target }}-${{ matrix.variant }}
+          path: artifacts/**
+          if-no-files-found: error
+
+  package:
+    name: Package npm module
+    needs:
+      - metadata
+      - rust-binaries
+      - bash-linux
+      - bash-darwin
+    runs-on: ubuntu-latest
+    env:
+      PACKAGE_VERSION: ${{ needs.metadata.outputs.version }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10.8.1
+          run_install: false
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v5
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Install JavaScript dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Build (shell-tool-mcp)
+        run: pnpm --filter @openai/codex-shell-tool-mcp run build
+
+      - name: Download build artifacts
+        uses: actions/download-artifact@v7
+        with:
+          path: artifacts
+
+      - name: Assemble staging directory
+        id: staging
+        shell: bash
+        run: |
+          set -euo pipefail
+          staging="${STAGING_DIR}"
+          mkdir -p "$staging" "$staging/vendor"
+          cp shell-tool-mcp/README.md "$staging/"
+          cp shell-tool-mcp/package.json "$staging/"
+          cp -R shell-tool-mcp/bin "$staging/"
+
+          found_vendor="false"
+          shopt -s nullglob
+          for vendor_dir in artifacts/*/vendor; do
+            rsync -av "$vendor_dir/" "$staging/vendor/"
+            found_vendor="true"
+          done
+          if [[ "$found_vendor" == "false" ]]; then
+            echo "No vendor payloads were downloaded."
+            exit 1
+          fi
+
+          node - <<'NODE'
+            import fs from "node:fs";
+            import path from "node:path";
+
+            const stagingDir = process.env.STAGING_DIR;
+            const version = process.env.PACKAGE_VERSION;
+            const pkgPath = path.join(stagingDir, "package.json");
+            const pkg = JSON.parse(fs.readFileSync(pkgPath, "utf8"));
+            pkg.version = version;
+            fs.writeFileSync(pkgPath, JSON.stringify(pkg, null, 2) + "\n");
+          NODE
+
+          echo "dir=$staging" >> "$GITHUB_OUTPUT"
+        env:
+          STAGING_DIR: ${{ runner.temp }}/shell-tool-mcp
+
+      - name: Ensure binaries are executable
+        run: |
+          set -euo pipefail
+          staging="${{ steps.staging.outputs.dir }}"
+          chmod +x \
+            "$staging"/vendor/*/codex-exec-mcp-server \
+            "$staging"/vendor/*/codex-execve-wrapper \
+            "$staging"/vendor/*/bash/*/bash
+
+      - name: Create npm tarball
+        shell: bash
+        run: |
+          set -euo pipefail
+          mkdir -p dist/npm
+          staging="${{ steps.staging.outputs.dir }}"
+          pack_info=$(cd "$staging" && npm pack --ignore-scripts --json --pack-destination "${GITHUB_WORKSPACE}/dist/npm")
+          filename=$(PACK_INFO="$pack_info" node -e 'const data = JSON.parse(process.env.PACK_INFO); console.log(data[0].filename);')
+          mv "dist/npm/${filename}" "dist/npm/codex-shell-tool-mcp-npm-${PACKAGE_VERSION}.tgz"
+
+      - uses: actions/upload-artifact@v6
+        with:
+          name: codex-shell-tool-mcp-npm
+          path: dist/npm/codex-shell-tool-mcp-npm-${{ env.PACKAGE_VERSION }}.tgz
+          if-no-files-found: error
+
+  publish:
+    name: Publish npm package
+    needs:
+      - metadata
+      - package
+    if: ${{ inputs.publish && needs.metadata.outputs.should_publish == 'true' }}
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      contents: read
+    steps:
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10.8.1
+          run_install: false
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v5
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          registry-url: https://registry.npmjs.org
+          scope: "@openai"
+
+      - name: Update npm
+        run: npm install -g npm@latest
+
+      - name: Download npm tarball
+        uses: actions/download-artifact@v7
+        with:
+          name: codex-shell-tool-mcp-npm
+          path: dist/npm
+
+      - name: Publish to npm
+        env:
+          NPM_TAG: ${{ needs.metadata.outputs.npm_tag }}
+          VERSION: ${{ needs.metadata.outputs.version }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          tag_args=()
+          if [[ -n "${NPM_TAG}" ]]; then
+            tag_args+=(--tag "${NPM_TAG}")
+          fi
+          npm publish "dist/npm/codex-shell-tool-mcp-npm-${VERSION}.tgz" "${tag_args[@]}"

.gitignore

@@ -30,6 +30,7 @@ result
 # cli tools
 CLAUDE.md
 .claude/
+AGENTS.override.md
 
 # caches
 .cache/
@@ -63,6 +64,9 @@ apply_patch/
 # coverage
 coverage/
 
+# personal files
+personal/
+
 # os
 .DS_Store
 Thumbs.db

.vscode/settings.json

@@ -3,6 +3,7 @@
     "rust-analyzer.check.command": "clippy",
     "rust-analyzer.check.extraArgs": ["--all-features", "--tests"],
     "rust-analyzer.rustfmt.extraArgs": ["--config", "imports_granularity=Item"],
+    "rust-analyzer.cargo.targetDir": "${workspaceFolder}/codex-rs/target/rust-analyzer",
     "[rust]": {
         "editor.defaultFormatter": "rust-lang.rust-analyzer",
         "editor.formatOnSave": true,

AGENTS.md

@@ -12,6 +12,7 @@ In the codex-rs folder where the rust code lives:
 - 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 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.
 
 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:
 
@@ -73,6 +74,7 @@ If you don’t have the tool:
 ### Test assertions
 
 - Tests should use pretty_assertions::assert_eq for clearer diffs. Import this at the top of the test module if it isn't already.
+- Prefer deep equals comparisons whenever possible. Perform `assert_eq!()` on entire objects, rather than individual fields.
 
 ### Integration tests (core)
 
@@ -82,6 +84,8 @@ If you don’t have the tool:
 - Use `ResponseMock::single_request()` when a test should only issue one POST, or `ResponseMock::requests()` to inspect every captured `ResponsesRequest`.
 - `ResponsesRequest` exposes helpers (`body_json`, `input`, `function_call_output`, `custom_tool_call_output`, `call_output`, `header`, `path`, `query_param`) so assertions can target structured payloads instead of manual JSON digging.
 - Build SSE payloads with the provided `ev_*` constructors and the `sse(...)`.
+- Prefer `wait_for_event` over `wait_for_event_with_timeout`.
+- Prefer `mount_sse_once` over `mount_sse_once_match` or `mount_sse_sequence`
 
 - Typical pattern:
 

CHANGELOG.md

@@ -1 +1 @@
-The changelog can be found on the [releases page](https://github.com/openai/codex/releases)
+The changelog can be found on the [releases page](https://github.com/openai/codex/releases).

README.md

@@ -1,4 +1,4 @@
-<p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>
+<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.
 </br>
@@ -24,7 +24,7 @@ npm install -g @openai/codex
 Alternatively, if you use Homebrew:
 
 ```shell
-brew install codex
+brew install --cask codex
 ```
 
 Then simply run `codex` to get started:
@@ -33,6 +33,8 @@ Then simply run `codex` to get started:
 codex
 ```
 
+If you're running into upgrade issues with Homebrew, see the [FAQ entry on brew upgrade codex](./docs/faq.md#brew-upgrade-codex-isnt-upgrading-me).
+
 <details>
 <summary>You can also go to the <a href="https://github.com/openai/codex/releases/latest">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>
 
@@ -67,17 +69,23 @@ Codex can access MCP servers. To configure them, refer to the [config docs](./do
 
 Codex CLI supports a rich set of configuration options, with preferences stored in `~/.codex/config.toml`. For full configuration options, see [Configuration](./docs/config.md).
 
----
+### Execpolicy
+
+See the [Execpolicy quickstart](./docs/execpolicy.md) to set up rules that govern what commands Codex can execute.
 
 ### Docs & FAQ
 
 - [**Getting started**](./docs/getting-started.md)
   - [CLI usage](./docs/getting-started.md#cli-usage)
+  - [Slash Commands](./docs/slash_commands.md)
   - [Running with a prompt as input](./docs/getting-started.md#running-with-a-prompt-as-input)
   - [Example prompts](./docs/getting-started.md#example-prompts)
+  - [Custom prompts](./docs/prompts.md)
   - [Memory with AGENTS.md](./docs/getting-started.md#memory-with-agentsmd)
-  - [Configuration](./docs/config.md)
+- [**Configuration**](./docs/config.md)
+  - [Example config](./docs/example-config.md)
 - [**Sandbox & approvals**](./docs/sandbox.md)
+- [**Execpolicy quickstart**](./docs/execpolicy.md)
 - [**Authentication**](./docs/authentication.md)
   - [Auth methods](./docs/authentication.md#forcing-a-specific-auth-method-advanced)
   - [Login on a "Headless" machine](./docs/authentication.md#connecting-on-a-headless-machine)

cliff.toml

@@ -4,7 +4,7 @@
 header = """
 # Changelog
 
-You can install any of these versions: `npm install -g codex@version`
+You can install any of these versions: `npm install -g @openai/codex@<version>`
 """
 
 body = """

codex-cli/bin/codex.js

@@ -95,14 +95,6 @@ function detectPackageManager() {
     return "bun";
   }
 
-  if (
-    process.env.BUN_INSTALL ||
-    process.env.BUN_INSTALL_GLOBAL_DIR ||
-    process.env.BUN_INSTALL_BIN_DIR
-  ) {
-    return "bun";
-  }
-
   return userAgent ? "npm" : null;
 }
 

codex-rs/.cargo/audit.toml

@@ -0,0 +1,6 @@
+[advisories]
+ignore = [
+    "RUSTSEC-2024-0388", # derivative 2.2.0 via starlark; upstream crate is unmaintained
+    "RUSTSEC-2025-0057", # fxhash 0.2.1 via starlark_map; upstream crate is unmaintained
+    "RUSTSEC-2024-0436", # paste 1.0.15 via starlark/ratatui; upstream crate is unmaintained
+]

codex-rs/.cargo/config.toml

@@ -0,0 +1,5 @@
+[target.'cfg(all(windows, target_env = "msvc"))']
+rustflags = ["-C", "link-arg=/STACK:8388608"]
+
+[target.'cfg(all(windows, target_env = "gnu"))']
+rustflags = ["-C", "link-arg=-Wl,--stack,8388608"]

codex-rs/.config/nextest.toml

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

codex-rs/.github/workflows/cargo-audit.yml

@@ -0,0 +1,26 @@
+name: Cargo audit
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+jobs:
+  audit:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: codex-rs
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+      - name: Install cargo-audit
+        uses: taiki-e/install-action@v2
+        with:
+          tool: cargo-audit
+      - name: Run cargo audit
+        run: cargo audit --deny warnings

codex-rs/.gitignore

@@ -1,4 +1,5 @@
 /target/
+/target-*/
 
 # Recommended value of CARGO_TARGET_DIR when using Docker as explained in .devcontainer/README.md.
 /target-amd64/

codex-rs/Cargo.toml

@@ -2,10 +2,13 @@
 members = [
     "backend-client",
     "ansi-escape",
+    "async-utils",
     "app-server",
     "app-server-protocol",
+    "app-server-test-client",
     "apply-patch",
     "arg0",
+    "feedback",
     "codex-backend-openapi-models",
     "cloud-tasks",
     "cloud-tasks-client",
@@ -13,26 +16,35 @@ members = [
     "common",
     "core",
     "exec",
+    "exec-server",
     "execpolicy",
+    "execpolicy-legacy",
+    "keyring-store",
     "file-search",
-    "git-tooling",
     "linux-sandbox",
+    "lmstudio",
     "login",
-    "mcp-client",
     "mcp-server",
     "mcp-types",
     "ollama",
     "process-hardening",
     "protocol",
-    "protocol-ts",
     "rmcp-client",
     "responses-api-proxy",
+    "stdio-to-uds",
     "otel",
     "tui",
-    "git-apply",
+    "tui2",
+    "utils/absolute-path",
+    "utils/git",
+    "utils/cache",
+    "utils/image",
     "utils/json-to-toml",
+    "utils/pty",
     "utils/readiness",
     "utils/string",
+    "codex-client",
+    "codex-api",
 ]
 resolver = "2"
 
@@ -43,37 +55,52 @@ version = "0.0.0"
 # crates created with `cargo new -w ...` automatically inherit the 2024
 # edition.
 edition = "2024"
+license = "Apache-2.0"
 
 [workspace.dependencies]
 # Internal
 app_test_support = { path = "app-server/tests/common" }
 codex-ansi-escape = { path = "ansi-escape" }
+codex-api = { path = "codex-api" }
 codex-app-server = { path = "app-server" }
 codex-app-server-protocol = { path = "app-server-protocol" }
 codex-apply-patch = { path = "apply-patch" }
 codex-arg0 = { path = "arg0" }
+codex-async-utils = { path = "async-utils" }
+codex-backend-client = { path = "backend-client" }
 codex-chatgpt = { path = "chatgpt" }
+codex-client = { path = "codex-client" }
 codex-common = { path = "common" }
 codex-core = { path = "core" }
 codex-exec = { path = "exec" }
+codex-execpolicy = { path = "execpolicy" }
+codex-feedback = { path = "feedback" }
 codex-file-search = { path = "file-search" }
-codex-git-tooling = { path = "git-tooling" }
+codex-git = { path = "utils/git" }
+codex-keyring-store = { path = "keyring-store" }
 codex-linux-sandbox = { path = "linux-sandbox" }
+codex-lmstudio = { path = "lmstudio" }
 codex-login = { path = "login" }
-codex-mcp-client = { path = "mcp-client" }
 codex-mcp-server = { path = "mcp-server" }
 codex-ollama = { path = "ollama" }
 codex-otel = { path = "otel" }
 codex-process-hardening = { path = "process-hardening" }
 codex-protocol = { path = "protocol" }
-codex-protocol-ts = { path = "protocol-ts" }
 codex-responses-api-proxy = { path = "responses-api-proxy" }
 codex-rmcp-client = { path = "rmcp-client" }
+codex-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-image = { path = "utils/image" }
 codex-utils-json-to-toml = { path = "utils/json-to-toml" }
+codex-utils-pty = { path = "utils/pty" }
 codex-utils-readiness = { path = "utils/readiness" }
 codex-utils-string = { path = "utils/string" }
+codex-windows-sandbox = { path = "windows-sandbox-rs" }
 core_test_support = { path = "core/tests/common" }
+exec_server_test_support = { path = "exec-server/tests/common" }
 mcp-types = { path = "mcp-types" }
 mcp_test_support = { path = "mcp-server/tests/common" }
 
@@ -81,16 +108,16 @@ mcp_test_support = { path = "mcp-server/tests/common" }
 allocative = "0.3.3"
 ansi-to-tui = "7.0.0"
 anyhow = "1"
-arboard = "3"
-askama = "0.12"
-assert_matches = "1.5.0"
+arboard = { version = "3", features = ["wayland-data-control"] }
 assert_cmd = "2"
+assert_matches = "1.5.0"
 async-channel = "2.3.1"
 async-stream = "0.3.6"
 async-trait = "0.1.89"
 axum = { version = "0.8", default-features = false }
 base64 = "0.22.1"
 bytes = "1.10.1"
+chardetng = "0.1.17"
 chrono = "0.4.42"
 clap = "4"
 clap_complete = "4"
@@ -102,39 +129,43 @@ diffy = "0.4.2"
 dirs = "6"
 dotenvy = "0.15.7"
 dunce = "1.0.4"
+encoding_rs = "0.8.35"
 env-flags = "0.1.1"
 env_logger = "0.11.5"
 escargot = "0.5"
 eventsource-stream = "0.2.3"
 futures = { version = "0.3", default-features = false }
-icu_decimal = "2.0.0"
-icu_locale_core = "2.0.0"
+http = "1.3.1"
+icu_decimal = "2.1"
+icu_locale_core = "2.1"
+icu_provider = { version = "2.1", features = ["sync"] }
 ignore = "0.4.23"
-image = { version = "^0.25.8", default-features = false }
-indexmap = "2.6.0"
-insta = "1.43.2"
+image = { version = "^0.25.9", default-features = false }
+indexmap = "2.12.0"
+insta = "1.44.3"
 itertools = "0.14.0"
-keyring = "3.6"
+keyring = { version = "3.6", default-features = false }
 landlock = "0.4.1"
 lazy_static = "1"
-libc = "0.2.175"
+libc = "0.2.177"
 log = "0.4"
+lru = "0.16.2"
 maplit = "1.0.2"
 mime_guess = "2.0.5"
 multimap = "0.10.0"
 notify = "8.2.0"
 nucleo-matcher = "0.3.1"
+once_cell = "1.20.2"
 openssl-sys = "*"
 opentelemetry = "0.30.0"
 opentelemetry-appender-tracing = "0.30.0"
 opentelemetry-otlp = "0.30.0"
 opentelemetry-semantic-conventions = "0.30.0"
 opentelemetry_sdk = "0.30.0"
+tracing-opentelemetry = "0.31.0"
 os_info = "3.12.0"
 owo-colors = "4.2.0"
-paste = "1.0.15"
 path-absolutize = "3.1.1"
-path-clean = "1.0.1"
 pathdiff = "0.2"
 portable-pty = "0.9.0"
 predicates = "3"
@@ -142,27 +173,33 @@ pretty_assertions = "1.4.1"
 pulldown-cmark = "0.10"
 rand = "0.9"
 ratatui = "0.29.0"
+ratatui-macros = "0.6.0"
+regex = "1.12.2"
 regex-lite = "0.1.7"
 reqwest = "0.12"
-rmcp = { version = "0.8.0", default-features = false }
+rmcp = { version = "0.10.0", default-features = false }
 schemars = "0.8.22"
 seccompiler = "0.5.0"
+sentry = "0.46.0"
 serde = "1"
 serde_json = "1"
-serde_with = "3.14"
+serde_with = "3.16"
+serde_yaml = "0.9"
 serial_test = "3.2.0"
 sha1 = "0.10.6"
 sha2 = "0.10"
 shlex = "1.3.0"
 similar = "2.7.0"
+socket2 = "0.6.1"
 starlark = "0.13.0"
 strum = "0.27.2"
 strum_macros = "0.27.2"
 supports-color = "3.0.2"
 sys-locale = "0.3.2"
 tempfile = "3.23.0"
+test-log = "0.2.18"
 textwrap = "0.16.2"
-thiserror = "2.0.16"
+thiserror = "2.0.17"
 time = "0.3"
 tiny_http = "0.12"
 tokio = "1"
@@ -170,9 +207,9 @@ tokio-stream = "0.1.17"
 tokio-test = "0.4"
 tokio-util = "0.7.16"
 toml = "0.9.5"
-toml_edit = "0.23.4"
+toml_edit = "0.23.5"
 tonic = "0.13.1"
-tracing = "0.1.41"
+tracing = "0.1.43"
 tracing-appender = "0.2.3"
 tracing-subscriber = "0.3.20"
 tracing-test = "0.2.5"
@@ -180,6 +217,7 @@ tree-sitter = "0.25.10"
 tree-sitter-bash = "0.25"
 tree-sitter-highlight = "0.25.10"
 ts-rs = "11"
+uds_windows = "1.1.0"
 unicode-segmentation = "1.12.0"
 unicode-width = "0.2"
 url = "2"
@@ -189,9 +227,10 @@ vt100 = "0.16.2"
 walkdir = "2.5.0"
 webbrowser = "1.0"
 which = "6"
-wildmatch = "2.5.0"
+wildmatch = "2.6.1"
+
 wiremock = "0.6"
-zeroize = "1.8.1"
+zeroize = "1.8.2"
 
 [workspace.lints]
 rust = {}
@@ -234,7 +273,7 @@ unwrap_used = "deny"
 # cargo-shear cannot see the platform-specific openssl-sys usage, so we
 # silence the false positive here instead of deleting a real dependency.
 [workspace.metadata.cargo-shear]
-ignored = ["openssl-sys", "codex-utils-readiness"]
+ignored = ["icu_provider", "openssl-sys", "codex-utils-readiness"]
 
 [profile.release]
 lto = "fat"
@@ -245,9 +284,15 @@ strip = "symbols"
 # See https://github.com/openai/codex/issues/1411 for details.
 codegen-units = 1
 
+[profile.ci-test]
+debug = 1         # Reduce debug symbol size
+inherits = "test"
+opt-level = 0
+
 [patch.crates-io]
 # Uncomment to debug local changes.
 # ratatui = { path = "../../ratatui" }
+crossterm = { git = "https://github.com/nornagon/crossterm", branch = "nornagon/color-query" }
 ratatui = { git = "https://github.com/nornagon/ratatui", branch = "nornagon-v0.29.0-patch" }
 
 # Uncomment to debug local changes.

codex-rs/README.md

@@ -11,7 +11,12 @@ npm i -g @openai/codex
 codex
 ```
 
-You can also install via Homebrew (`brew install codex`) or download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
+You can also install via Homebrew (`brew install --cask codex`) or download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
+
+## Documentation quickstart
+
+- First run with Codex? Follow the walkthrough in [`docs/getting-started.md`](../docs/getting-started.md) for prompts, keyboard shortcuts, and session management.
+- Already shipping with Codex and want deeper control? Jump to [`docs/advanced.md`](../docs/advanced.md) and the configuration reference at [`docs/config.md`](../docs/config.md).
 
 ## What's new in the Rust CLI
 
@@ -41,49 +46,28 @@ Use `codex mcp` to add/list/get/remove MCP server launchers defined in `config.t
 
 ### Notifications
 
-You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS.
+You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS. When Codex detects that it is running under WSL 2 inside Windows Terminal (`WT_SESSION` is set), the TUI automatically falls back to native Windows toast notifications so approval prompts and completed turns surface even though Windows Terminal does not implement OSC 9.
 
 ### `codex exec` to run Codex programmatically/non-interactively
 
 To run Codex non-interactively, run `codex exec PROMPT` (you can also pass the prompt via `stdin`) and Codex will work on your task until it decides that it is done and exits. Output is printed to the terminal directly. You can set the `RUST_LOG` environment variable to see more about what's going on.
 
-### Use `@` for file search
-
-Typing `@` triggers a fuzzy-filename search over the workspace root. Use up/down to select among the results and Tab or Enter to replace the `@` with the selected path. You can use Esc to cancel the search.
-
-### Esc–Esc to edit a previous message
-
-When the chat composer is empty, press Esc to prime “backtrack” mode. Press Esc again to open a transcript preview highlighting the last user message; press Esc repeatedly to step to older user messages. Press Enter to confirm and Codex will fork the conversation from that point, trim the visible transcript accordingly, and pre‑fill the composer with the selected user message so you can edit and resubmit it.
-
-In the transcript preview, the footer shows an `Esc edit prev` hint while editing is active.
-
-### `--cd`/`-C` flag
-
-Sometimes it is not convenient to `cd` to the directory you want Codex to use as the "working root" before running Codex. Fortunately, `codex` supports a `--cd` option so you can specify whatever folder you want. You can confirm that Codex is honoring `--cd` by double-checking the **workdir** it reports in the TUI at the start of a new session.
-
-### Shell completions
-
-Generate shell completion scripts via:
-
-```shell
-codex completion bash
-codex completion zsh
-codex completion fish
-```
-
 ### Experimenting with the Codex Sandbox
 
 To test to see what happens when a command is run under the sandbox provided by Codex, we provide the following subcommands in Codex CLI:
 
 ```
 # macOS
-codex sandbox macos [--full-auto] [COMMAND]...
+codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...
 
 # Linux
 codex sandbox linux [--full-auto] [COMMAND]...
 
+# Windows
+codex sandbox windows [--full-auto] [COMMAND]...
+
 # Legacy aliases
-codex debug seatbelt [--full-auto] [COMMAND]...
+codex debug seatbelt [--full-auto] [--log-denials] [COMMAND]...
 codex debug landlock [--full-auto] [COMMAND]...
 ```
 

codex-rs/ansi-escape/Cargo.toml

@@ -1,7 +1,8 @@
 [package]
-edition = "2024"
 name = "codex-ansi-escape"
-version = { workspace = true }
+version.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [lib]
 name = "codex_ansi_escape"

codex-rs/app-server-protocol/Cargo.toml

@@ -1,7 +1,8 @@
 [package]
-edition = "2024"
 name = "codex-app-server-protocol"
-version = { workspace = true }
+version.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [lib]
 name = "codex_app_server_protocol"
@@ -11,11 +12,16 @@ path = "src/lib.rs"
 workspace = true
 
 [dependencies]
+anyhow = { workspace = true }
+clap = { workspace = true, features = ["derive"] }
 codex-protocol = { workspace = true }
-paste = { workspace = true }
+codex-utils-absolute-path = { workspace = true }
+mcp-types = { workspace = true }
+schemars = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
 strum_macros = { workspace = true }
+thiserror = { workspace = true }
 ts-rs = { workspace = true }
 uuid = { workspace = true, features = ["serde", "v7"] }
 

codex-rs/app-server-protocol/src/bin/export.rs

@@ -3,18 +3,20 @@ use clap::Parser;
 use std::path::PathBuf;
 
 #[derive(Parser, Debug)]
-#[command(about = "Generate TypeScript bindings for the Codex protocol")]
+#[command(
+    about = "Generate TypeScript bindings and JSON Schemas for the Codex app-server protocol"
+)]
 struct Args {
-    /// Output directory where .ts files will be written
+    /// Output directory where generated files will be written
     #[arg(short = 'o', long = "out", value_name = "DIR")]
     out_dir: PathBuf,
 
-    /// Optional path to the Prettier executable to format generated files
+    /// Optional Prettier executable path to format generated TypeScript files
     #[arg(short = 'p', long = "prettier", value_name = "PRETTIER_BIN")]
     prettier: Option<PathBuf>,
 }
 
 fn main() -> Result<()> {
     let args = Args::parse();
-    codex_protocol_ts::generate_ts(&args.out_dir, args.prettier.as_deref())
+    codex_app_server_protocol::generate_types(&args.out_dir, args.prettier.as_deref())
 }

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

@@ -0,0 +1,946 @@
+use crate::ClientNotification;
+use crate::ClientRequest;
+use crate::ServerNotification;
+use crate::ServerRequest;
+use crate::export_client_notification_schemas;
+use crate::export_client_param_schemas;
+use crate::export_client_response_schemas;
+use crate::export_client_responses;
+use crate::export_server_notification_schemas;
+use crate::export_server_param_schemas;
+use crate::export_server_response_schemas;
+use crate::export_server_responses;
+use anyhow::Context;
+use anyhow::Result;
+use anyhow::anyhow;
+use codex_protocol::protocol::EventMsg;
+use schemars::JsonSchema;
+use schemars::schema_for;
+use serde::Serialize;
+use serde_json::Map;
+use serde_json::Value;
+use std::collections::HashMap;
+use std::collections::HashSet;
+use std::ffi::OsStr;
+use std::fs;
+use std::io::Read;
+use std::io::Write;
+use std::path::Path;
+use std::path::PathBuf;
+use std::process::Command;
+use ts_rs::TS;
+
+const HEADER: &str = "// GENERATED CODE! DO NOT MODIFY BY HAND!\n\n";
+const IGNORED_DEFINITIONS: &[&str] = &["Option<()>"];
+
+#[derive(Clone)]
+pub struct GeneratedSchema {
+    namespace: Option<String>,
+    logical_name: String,
+    value: Value,
+    in_v1_dir: bool,
+}
+
+impl GeneratedSchema {
+    fn namespace(&self) -> Option<&str> {
+        self.namespace.as_deref()
+    }
+
+    fn logical_name(&self) -> &str {
+        &self.logical_name
+    }
+
+    fn value(&self) -> &Value {
+        &self.value
+    }
+}
+
+type JsonSchemaEmitter = fn(&Path) -> Result<GeneratedSchema>;
+pub fn generate_types(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
+    generate_ts(out_dir, prettier)?;
+    generate_json(out_dir)?;
+    Ok(())
+}
+
+#[derive(Clone, Copy, Debug)]
+pub struct GenerateTsOptions {
+    pub generate_indices: bool,
+    pub ensure_headers: bool,
+    pub run_prettier: bool,
+}
+
+impl Default for GenerateTsOptions {
+    fn default() -> Self {
+        Self {
+            generate_indices: true,
+            ensure_headers: true,
+            run_prettier: true,
+        }
+    }
+}
+
+pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
+    generate_ts_with_options(out_dir, prettier, GenerateTsOptions::default())
+}
+
+pub fn generate_ts_with_options(
+    out_dir: &Path,
+    prettier: Option<&Path>,
+    options: GenerateTsOptions,
+) -> Result<()> {
+    let v2_out_dir = out_dir.join("v2");
+    ensure_dir(out_dir)?;
+    ensure_dir(&v2_out_dir)?;
+
+    ClientRequest::export_all_to(out_dir)?;
+    export_client_responses(out_dir)?;
+    ClientNotification::export_all_to(out_dir)?;
+
+    ServerRequest::export_all_to(out_dir)?;
+    export_server_responses(out_dir)?;
+    ServerNotification::export_all_to(out_dir)?;
+
+    if options.generate_indices {
+        generate_index_ts(out_dir)?;
+        generate_index_ts(&v2_out_dir)?;
+    }
+
+    // Ensure our header is present on all TS files (root + subdirs like v2/).
+    let mut ts_files = Vec::new();
+    let should_collect_ts_files =
+        options.ensure_headers || (options.run_prettier && prettier.is_some());
+    if should_collect_ts_files {
+        ts_files = ts_files_in_recursive(out_dir)?;
+    }
+
+    if options.ensure_headers {
+        for file in &ts_files {
+            prepend_header_if_missing(file)?;
+        }
+    }
+
+    // Optionally run Prettier on all generated TS files.
+    if options.run_prettier
+        && let Some(prettier_bin) = prettier
+        && !ts_files.is_empty()
+    {
+        let status = Command::new(prettier_bin)
+            .arg("--write")
+            .arg("--log-level")
+            .arg("warn")
+            .args(ts_files.iter().map(|p| p.as_os_str()))
+            .status()
+            .with_context(|| format!("Failed to invoke Prettier at {}", prettier_bin.display()))?;
+        if !status.success() {
+            return Err(anyhow!("Prettier failed with status {status}"));
+        }
+    }
+
+    Ok(())
+}
+
+pub fn generate_json(out_dir: &Path) -> Result<()> {
+    ensure_dir(out_dir)?;
+    let envelope_emitters: &[JsonSchemaEmitter] = &[
+        |d| write_json_schema_with_return::<crate::RequestId>(d, "RequestId"),
+        |d| write_json_schema_with_return::<crate::JSONRPCMessage>(d, "JSONRPCMessage"),
+        |d| write_json_schema_with_return::<crate::JSONRPCRequest>(d, "JSONRPCRequest"),
+        |d| write_json_schema_with_return::<crate::JSONRPCNotification>(d, "JSONRPCNotification"),
+        |d| write_json_schema_with_return::<crate::JSONRPCResponse>(d, "JSONRPCResponse"),
+        |d| write_json_schema_with_return::<crate::JSONRPCError>(d, "JSONRPCError"),
+        |d| write_json_schema_with_return::<crate::JSONRPCErrorError>(d, "JSONRPCErrorError"),
+        |d| write_json_schema_with_return::<crate::ClientRequest>(d, "ClientRequest"),
+        |d| write_json_schema_with_return::<crate::ServerRequest>(d, "ServerRequest"),
+        |d| write_json_schema_with_return::<crate::ClientNotification>(d, "ClientNotification"),
+        |d| write_json_schema_with_return::<crate::ServerNotification>(d, "ServerNotification"),
+        |d| write_json_schema_with_return::<EventMsg>(d, "EventMsg"),
+    ];
+
+    let mut schemas: Vec<GeneratedSchema> = Vec::new();
+    for emit in envelope_emitters {
+        schemas.push(emit(out_dir)?);
+    }
+
+    schemas.extend(export_client_param_schemas(out_dir)?);
+    schemas.extend(export_client_response_schemas(out_dir)?);
+    schemas.extend(export_server_param_schemas(out_dir)?);
+    schemas.extend(export_server_response_schemas(out_dir)?);
+    schemas.extend(export_client_notification_schemas(out_dir)?);
+    schemas.extend(export_server_notification_schemas(out_dir)?);
+
+    let bundle = build_schema_bundle(schemas)?;
+    write_pretty_json(
+        out_dir.join("codex_app_server_protocol.schemas.json"),
+        &bundle,
+    )?;
+
+    Ok(())
+}
+
+fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<Value> {
+    const SPECIAL_DEFINITIONS: &[&str] = &[
+        "ClientNotification",
+        "ClientRequest",
+        "EventMsg",
+        "ServerNotification",
+        "ServerRequest",
+    ];
+
+    let namespaced_types = collect_namespaced_types(&schemas);
+    let mut definitions = Map::new();
+
+    for schema in schemas {
+        let GeneratedSchema {
+            namespace,
+            logical_name,
+            mut value,
+            in_v1_dir,
+        } = schema;
+
+        if IGNORED_DEFINITIONS.contains(&logical_name.as_str()) {
+            continue;
+        }
+
+        if let Some(ref ns) = namespace {
+            rewrite_refs_to_namespace(&mut value, ns);
+        }
+
+        let mut forced_namespace_refs: Vec<(String, String)> = Vec::new();
+        if let Value::Object(ref mut obj) = value
+            && let Some(defs) = obj.remove("definitions")
+            && let Value::Object(defs_obj) = defs
+        {
+            for (def_name, mut def_schema) in defs_obj {
+                if IGNORED_DEFINITIONS.contains(&def_name.as_str()) {
+                    continue;
+                }
+                if SPECIAL_DEFINITIONS.contains(&def_name.as_str()) {
+                    continue;
+                }
+                annotate_schema(&mut def_schema, Some(def_name.as_str()));
+                let target_namespace = match namespace {
+                    Some(ref ns) => Some(ns.clone()),
+                    None => namespace_for_definition(&def_name, &namespaced_types)
+                        .cloned()
+                        .filter(|_| !in_v1_dir),
+                };
+                if let Some(ref ns) = target_namespace {
+                    if namespace.as_deref() == Some(ns.as_str()) {
+                        rewrite_refs_to_namespace(&mut def_schema, ns);
+                        insert_into_namespace(&mut definitions, ns, def_name.clone(), def_schema)?;
+                    } else if !forced_namespace_refs
+                        .iter()
+                        .any(|(name, existing_ns)| name == &def_name && existing_ns == ns)
+                    {
+                        forced_namespace_refs.push((def_name.clone(), ns.clone()));
+                    }
+                } else {
+                    definitions.insert(def_name, def_schema);
+                }
+            }
+        }
+
+        for (name, ns) in forced_namespace_refs {
+            rewrite_named_ref_to_namespace(&mut value, &ns, &name);
+        }
+
+        if let Some(ref ns) = namespace {
+            insert_into_namespace(&mut definitions, ns, logical_name.clone(), value)?;
+        } else {
+            definitions.insert(logical_name, value);
+        }
+    }
+
+    let mut root = Map::new();
+    root.insert(
+        "$schema".to_string(),
+        Value::String("http://json-schema.org/draft-07/schema#".into()),
+    );
+    root.insert(
+        "title".to_string(),
+        Value::String("CodexAppServerProtocol".into()),
+    );
+    root.insert("type".to_string(), Value::String("object".into()));
+    root.insert("definitions".to_string(), Value::Object(definitions));
+
+    Ok(Value::Object(root))
+}
+
+fn insert_into_namespace(
+    definitions: &mut Map<String, Value>,
+    namespace: &str,
+    name: String,
+    schema: Value,
+) -> Result<()> {
+    let entry = definitions
+        .entry(namespace.to_string())
+        .or_insert_with(|| Value::Object(Map::new()));
+    match entry {
+        Value::Object(map) => {
+            map.insert(name, schema);
+            Ok(())
+        }
+        _ => Err(anyhow!("expected namespace {namespace} to be an object")),
+    }
+}
+
+fn write_json_schema_with_return<T>(out_dir: &Path, name: &str) -> Result<GeneratedSchema>
+where
+    T: JsonSchema,
+{
+    let file_stem = name.trim();
+    let schema = schema_for!(T);
+    let mut schema_value = serde_json::to_value(schema)?;
+    annotate_schema(&mut schema_value, Some(file_stem));
+    // If the name looks like a namespaced path (e.g., "v2::Type"), mirror
+    // the TypeScript layout and write to out_dir/v2/Type.json. Otherwise
+    // write alongside the legacy files.
+    let (raw_namespace, logical_name) = split_namespace(file_stem);
+    let out_path = if let Some(ns) = raw_namespace {
+        let dir = out_dir.join(ns);
+        ensure_dir(&dir)?;
+        dir.join(format!("{logical_name}.json"))
+    } else {
+        out_dir.join(format!("{file_stem}.json"))
+    };
+
+    if !IGNORED_DEFINITIONS.contains(&logical_name) {
+        write_pretty_json(out_path, &schema_value)
+            .with_context(|| format!("Failed to write JSON schema for {file_stem}"))?;
+    }
+
+    let namespace = match raw_namespace {
+        Some("v1") | None => None,
+        Some(ns) => Some(ns.to_string()),
+    };
+    Ok(GeneratedSchema {
+        in_v1_dir: raw_namespace == Some("v1"),
+        namespace,
+        logical_name: logical_name.to_string(),
+        value: schema_value,
+    })
+}
+
+pub(crate) fn write_json_schema<T>(out_dir: &Path, name: &str) -> Result<GeneratedSchema>
+where
+    T: JsonSchema,
+{
+    write_json_schema_with_return::<T>(out_dir, name)
+}
+
+fn write_pretty_json(path: PathBuf, value: &impl Serialize) -> Result<()> {
+    let json = serde_json::to_vec_pretty(value)
+        .with_context(|| format!("Failed to serialize JSON schema to {}", path.display()))?;
+    fs::write(&path, json).with_context(|| format!("Failed to write {}", path.display()))?;
+    Ok(())
+}
+
+/// Split a fully-qualified type name like "v2::Type" into its namespace and logical name.
+fn split_namespace(name: &str) -> (Option<&str>, &str) {
+    name.split_once("::")
+        .map_or((None, name), |(ns, rest)| (Some(ns), rest))
+}
+
+/// Recursively rewrite $ref values that point at "#/definitions/..." so that
+/// they point to a namespaced location under the bundle.
+fn rewrite_refs_to_namespace(value: &mut Value, ns: &str) {
+    match value {
+        Value::Object(obj) => {
+            if let Some(Value::String(r)) = obj.get_mut("$ref")
+                && let Some(suffix) = r.strip_prefix("#/definitions/")
+            {
+                let prefix = format!("{ns}/");
+                if !suffix.starts_with(&prefix) {
+                    *r = format!("#/definitions/{ns}/{suffix}");
+                }
+            }
+            for v in obj.values_mut() {
+                rewrite_refs_to_namespace(v, ns);
+            }
+        }
+        Value::Array(items) => {
+            for v in items.iter_mut() {
+                rewrite_refs_to_namespace(v, ns);
+            }
+        }
+        _ => {}
+    }
+}
+
+fn collect_namespaced_types(schemas: &[GeneratedSchema]) -> HashMap<String, String> {
+    let mut types = HashMap::new();
+    for schema in schemas {
+        if let Some(ns) = schema.namespace() {
+            types
+                .entry(schema.logical_name().to_string())
+                .or_insert_with(|| ns.to_string());
+            if let Some(Value::Object(defs)) = schema.value().get("definitions") {
+                for key in defs.keys() {
+                    types.entry(key.clone()).or_insert_with(|| ns.to_string());
+                }
+            }
+            if let Some(Value::Object(defs)) = schema.value().get("$defs") {
+                for key in defs.keys() {
+                    types.entry(key.clone()).or_insert_with(|| ns.to_string());
+                }
+            }
+        }
+    }
+    types
+}
+
+fn namespace_for_definition<'a>(
+    name: &str,
+    types: &'a HashMap<String, String>,
+) -> Option<&'a String> {
+    if let Some(ns) = types.get(name) {
+        return Some(ns);
+    }
+    let trimmed = name.trim_end_matches(|c: char| c.is_ascii_digit());
+    if trimmed != name {
+        return types.get(trimmed);
+    }
+    None
+}
+
+fn variant_definition_name(base: &str, variant: &Value) -> Option<String> {
+    if let Some(props) = variant.get("properties").and_then(Value::as_object) {
+        if let Some(method_literal) = literal_from_property(props, "method") {
+            let pascal = to_pascal_case(method_literal);
+            return Some(match base {
+                "ClientRequest" | "ServerRequest" => format!("{pascal}Request"),
+                "ClientNotification" | "ServerNotification" => format!("{pascal}Notification"),
+                _ => format!("{pascal}{base}"),
+            });
+        }
+
+        if let Some(type_literal) = literal_from_property(props, "type") {
+            let pascal = to_pascal_case(type_literal);
+            return Some(match base {
+                "EventMsg" => format!("{pascal}EventMsg"),
+                _ => format!("{pascal}{base}"),
+            });
+        }
+
+        if props.len() == 1
+            && let Some(key) = props.keys().next()
+        {
+            let pascal = to_pascal_case(key);
+            return Some(format!("{pascal}{base}"));
+        }
+    }
+
+    if let Some(required) = variant.get("required").and_then(Value::as_array)
+        && required.len() == 1
+        && let Some(key) = required[0].as_str()
+    {
+        let pascal = to_pascal_case(key);
+        return Some(format!("{pascal}{base}"));
+    }
+
+    None
+}
+
+fn literal_from_property<'a>(props: &'a Map<String, Value>, key: &str) -> Option<&'a str> {
+    props.get(key).and_then(string_literal)
+}
+
+fn string_literal(value: &Value) -> Option<&str> {
+    value.get("const").and_then(Value::as_str).or_else(|| {
+        value
+            .get("enum")
+            .and_then(Value::as_array)
+            .and_then(|arr| arr.first())
+            .and_then(Value::as_str)
+    })
+}
+
+fn annotate_schema(value: &mut Value, base: Option<&str>) {
+    match value {
+        Value::Object(map) => annotate_object(map, base),
+        Value::Array(items) => {
+            for item in items {
+                annotate_schema(item, base);
+            }
+        }
+        _ => {}
+    }
+}
+
+fn annotate_object(map: &mut Map<String, Value>, base: Option<&str>) {
+    let owner = map.get("title").and_then(Value::as_str).map(str::to_owned);
+    if let Some(owner) = owner.as_deref()
+        && let Some(Value::Object(props)) = map.get_mut("properties")
+    {
+        set_discriminator_titles(props, owner);
+    }
+
+    if let Some(Value::Array(variants)) = map.get_mut("oneOf") {
+        annotate_variant_list(variants, base);
+    }
+    if let Some(Value::Array(variants)) = map.get_mut("anyOf") {
+        annotate_variant_list(variants, base);
+    }
+
+    if let Some(Value::Object(defs)) = map.get_mut("definitions") {
+        for (name, schema) in defs.iter_mut() {
+            annotate_schema(schema, Some(name.as_str()));
+        }
+    }
+
+    if let Some(Value::Object(defs)) = map.get_mut("$defs") {
+        for (name, schema) in defs.iter_mut() {
+            annotate_schema(schema, Some(name.as_str()));
+        }
+    }
+
+    if let Some(Value::Object(props)) = map.get_mut("properties") {
+        for value in props.values_mut() {
+            annotate_schema(value, base);
+        }
+    }
+
+    if let Some(items) = map.get_mut("items") {
+        annotate_schema(items, base);
+    }
+
+    if let Some(additional) = map.get_mut("additionalProperties") {
+        annotate_schema(additional, base);
+    }
+
+    for (key, child) in map.iter_mut() {
+        match key.as_str() {
+            "oneOf"
+            | "anyOf"
+            | "definitions"
+            | "$defs"
+            | "properties"
+            | "items"
+            | "additionalProperties" => {}
+            _ => annotate_schema(child, base),
+        }
+    }
+}
+
+fn annotate_variant_list(variants: &mut [Value], base: Option<&str>) {
+    let mut seen = HashSet::new();
+
+    for variant in variants.iter() {
+        if let Some(name) = variant_title(variant) {
+            seen.insert(name.to_owned());
+        }
+    }
+
+    for variant in variants.iter_mut() {
+        let mut variant_name = variant_title(variant).map(str::to_owned);
+
+        if variant_name.is_none()
+            && let Some(base_name) = base
+            && let Some(name) = variant_definition_name(base_name, variant)
+        {
+            let mut candidate = name.clone();
+            let mut index = 2;
+            while seen.contains(&candidate) {
+                candidate = format!("{name}{index}");
+                index += 1;
+            }
+            if let Some(obj) = variant.as_object_mut() {
+                obj.insert("title".into(), Value::String(candidate.clone()));
+            }
+            seen.insert(candidate.clone());
+            variant_name = Some(candidate);
+        }
+
+        if let Some(name) = variant_name.as_deref()
+            && let Some(obj) = variant.as_object_mut()
+            && let Some(Value::Object(props)) = obj.get_mut("properties")
+        {
+            set_discriminator_titles(props, name);
+        }
+
+        annotate_schema(variant, base);
+    }
+}
+
+const DISCRIMINATOR_KEYS: &[&str] = &["type", "method", "mode", "status", "role", "reason"];
+
+fn set_discriminator_titles(props: &mut Map<String, Value>, owner: &str) {
+    for key in DISCRIMINATOR_KEYS {
+        if let Some(prop_schema) = props.get_mut(*key)
+            && string_literal(prop_schema).is_some()
+            && let Value::Object(prop_obj) = prop_schema
+        {
+            if prop_obj.contains_key("title") {
+                continue;
+            }
+            let suffix = to_pascal_case(key);
+            prop_obj.insert("title".into(), Value::String(format!("{owner}{suffix}")));
+        }
+    }
+}
+
+fn variant_title(value: &Value) -> Option<&str> {
+    value
+        .as_object()
+        .and_then(|obj| obj.get("title"))
+        .and_then(Value::as_str)
+}
+
+fn to_pascal_case(input: &str) -> String {
+    let mut result = String::new();
+    let mut capitalize_next = true;
+
+    for c in input.chars() {
+        if c == '_' || c == '-' {
+            capitalize_next = true;
+            continue;
+        }
+
+        if capitalize_next {
+            result.extend(c.to_uppercase());
+            capitalize_next = false;
+        } else {
+            result.push(c);
+        }
+    }
+
+    result
+}
+
+fn ensure_dir(dir: &Path) -> Result<()> {
+    fs::create_dir_all(dir)
+        .with_context(|| format!("Failed to create output directory {}", dir.display()))
+}
+
+fn rewrite_named_ref_to_namespace(value: &mut Value, ns: &str, name: &str) {
+    let direct = format!("#/definitions/{name}");
+    let prefixed = format!("{direct}/");
+    let replacement = format!("#/definitions/{ns}/{name}");
+    let replacement_prefixed = format!("{replacement}/");
+    match value {
+        Value::Object(obj) => {
+            if let Some(Value::String(reference)) = obj.get_mut("$ref") {
+                if reference == &direct {
+                    *reference = replacement;
+                } else if let Some(rest) = reference.strip_prefix(&prefixed) {
+                    *reference = format!("{replacement_prefixed}{rest}");
+                }
+            }
+            for child in obj.values_mut() {
+                rewrite_named_ref_to_namespace(child, ns, name);
+            }
+        }
+        Value::Array(items) => {
+            for child in items {
+                rewrite_named_ref_to_namespace(child, ns, name);
+            }
+        }
+        _ => {}
+    }
+}
+
+fn prepend_header_if_missing(path: &Path) -> Result<()> {
+    let mut content = String::new();
+    {
+        let mut f = fs::File::open(path)
+            .with_context(|| format!("Failed to open {} for reading", path.display()))?;
+        f.read_to_string(&mut content)
+            .with_context(|| format!("Failed to read {}", path.display()))?;
+    }
+
+    if content.starts_with(HEADER) {
+        return Ok(());
+    }
+
+    let mut f = fs::File::create(path)
+        .with_context(|| format!("Failed to open {} for writing", path.display()))?;
+    f.write_all(HEADER.as_bytes())
+        .with_context(|| format!("Failed to write header to {}", path.display()))?;
+    f.write_all(content.as_bytes())
+        .with_context(|| format!("Failed to write content to {}", path.display()))?;
+    Ok(())
+}
+
+fn ts_files_in(dir: &Path) -> Result<Vec<PathBuf>> {
+    let mut files = Vec::new();
+    for entry in
+        fs::read_dir(dir).with_context(|| format!("Failed to read dir {}", dir.display()))?
+    {
+        let entry = entry?;
+        let path = entry.path();
+        if path.is_file() && path.extension() == Some(OsStr::new("ts")) {
+            files.push(path);
+        }
+    }
+    files.sort();
+    Ok(files)
+}
+
+fn ts_files_in_recursive(dir: &Path) -> Result<Vec<PathBuf>> {
+    let mut files = Vec::new();
+    let mut stack = vec![dir.to_path_buf()];
+    while let Some(d) = stack.pop() {
+        for entry in
+            fs::read_dir(&d).with_context(|| format!("Failed to read dir {}", d.display()))?
+        {
+            let entry = entry?;
+            let path = entry.path();
+            if path.is_dir() {
+                stack.push(path);
+            } else if path.is_file() && path.extension() == Some(OsStr::new("ts")) {
+                files.push(path);
+            }
+        }
+    }
+    files.sort();
+    Ok(files)
+}
+
+/// Generate an index.ts file that re-exports all generated types.
+/// This allows consumers to import all types from a single file.
+fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
+    let mut entries: Vec<String> = Vec::new();
+    let mut stems: Vec<String> = ts_files_in(out_dir)?
+        .into_iter()
+        .filter_map(|p| {
+            let stem = p.file_stem()?.to_string_lossy().into_owned();
+            if stem == "index" { None } else { Some(stem) }
+        })
+        .collect();
+    stems.sort();
+    stems.dedup();
+
+    for name in stems {
+        entries.push(format!("export type {{ {name} }} from \"./{name}\";\n"));
+    }
+
+    // If this is the root out_dir and a ./v2 folder exists with TS files,
+    // expose it as a namespace to avoid symbol collisions at the root.
+    let v2_dir = out_dir.join("v2");
+    let has_v2_ts = ts_files_in(&v2_dir).map(|v| !v.is_empty()).unwrap_or(false);
+    if has_v2_ts {
+        entries.push("export * as v2 from \"./v2\";\n".to_string());
+    }
+
+    let mut content =
+        String::with_capacity(HEADER.len() + entries.iter().map(String::len).sum::<usize>());
+    content.push_str(HEADER);
+    for line in &entries {
+        content.push_str(line);
+    }
+
+    let index_path = out_dir.join("index.ts");
+    let mut f = fs::File::create(&index_path)
+        .with_context(|| format!("Failed to create {}", index_path.display()))?;
+    f.write_all(content.as_bytes())
+        .with_context(|| format!("Failed to write {}", index_path.display()))?;
+    Ok(index_path)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use anyhow::Result;
+    use std::collections::BTreeSet;
+    use std::fs;
+    use std::path::PathBuf;
+    use uuid::Uuid;
+
+    #[test]
+    fn generated_ts_has_no_optional_nullable_fields() -> Result<()> {
+        // Assert that there are no types of the form "?: T | null" in the generated TS files.
+        let output_dir = std::env::temp_dir().join(format!("codex_ts_types_{}", Uuid::now_v7()));
+        fs::create_dir(&output_dir)?;
+
+        struct TempDirGuard(PathBuf);
+
+        impl Drop for TempDirGuard {
+            fn drop(&mut self) {
+                let _ = fs::remove_dir_all(&self.0);
+            }
+        }
+
+        let _guard = TempDirGuard(output_dir.clone());
+
+        // Avoid doing more work than necessary to keep the test from timing out.
+        let options = GenerateTsOptions {
+            generate_indices: false,
+            ensure_headers: false,
+            run_prettier: false,
+        };
+        generate_ts_with_options(&output_dir, None, options)?;
+
+        let mut undefined_offenders = Vec::new();
+        let mut optional_nullable_offenders = BTreeSet::new();
+        let mut stack = vec![output_dir];
+        while let Some(dir) = stack.pop() {
+            for entry in fs::read_dir(&dir)? {
+                let entry = entry?;
+                let path = entry.path();
+                if path.is_dir() {
+                    stack.push(path);
+                    continue;
+                }
+
+                if matches!(path.extension().and_then(|ext| ext.to_str()), Some("ts")) {
+                    let contents = fs::read_to_string(&path)?;
+                    if contents.contains("| undefined") {
+                        undefined_offenders.push(path.clone());
+                    }
+
+                    const SKIP_PREFIXES: &[&str] = &[
+                        "const ",
+                        "let ",
+                        "var ",
+                        "export const ",
+                        "export let ",
+                        "export var ",
+                    ];
+
+                    let mut search_start = 0;
+                    while let Some(idx) = contents[search_start..].find("| null") {
+                        let abs_idx = search_start + idx;
+                        // Find the property-colon for this field by scanning forward
+                        // from the start of the segment and ignoring nested braces,
+                        // brackets, and parens. This avoids colons inside nested
+                        // type literals like `{ [k in string]?: string }`.
+
+                        let line_start_idx =
+                            contents[..abs_idx].rfind('\n').map(|i| i + 1).unwrap_or(0);
+
+                        let mut segment_start_idx = line_start_idx;
+                        if let Some(rel_idx) = contents[line_start_idx..abs_idx].rfind(',') {
+                            segment_start_idx = segment_start_idx.max(line_start_idx + rel_idx + 1);
+                        }
+                        if let Some(rel_idx) = contents[line_start_idx..abs_idx].rfind('{') {
+                            segment_start_idx = segment_start_idx.max(line_start_idx + rel_idx + 1);
+                        }
+                        if let Some(rel_idx) = contents[line_start_idx..abs_idx].rfind('}') {
+                            segment_start_idx = segment_start_idx.max(line_start_idx + rel_idx + 1);
+                        }
+
+                        // Scan forward for the colon that separates the field name from its type.
+                        let mut level_brace = 0_i32;
+                        let mut level_brack = 0_i32;
+                        let mut level_paren = 0_i32;
+                        let mut in_single = false;
+                        let mut in_double = false;
+                        let mut escape = false;
+                        let mut prop_colon_idx = None;
+                        for (i, ch) in contents[segment_start_idx..abs_idx].char_indices() {
+                            let idx_abs = segment_start_idx + i;
+                            if escape {
+                                escape = false;
+                                continue;
+                            }
+                            match ch {
+                                '\\' => {
+                                    // Only treat as escape when inside a string.
+                                    if in_single || in_double {
+                                        escape = true;
+                                    }
+                                }
+                                '\'' => {
+                                    if !in_double {
+                                        in_single = !in_single;
+                                    }
+                                }
+                                '"' => {
+                                    if !in_single {
+                                        in_double = !in_double;
+                                    }
+                                }
+                                '{' if !in_single && !in_double => level_brace += 1,
+                                '}' if !in_single && !in_double => level_brace -= 1,
+                                '[' if !in_single && !in_double => level_brack += 1,
+                                ']' if !in_single && !in_double => level_brack -= 1,
+                                '(' if !in_single && !in_double => level_paren += 1,
+                                ')' if !in_single && !in_double => level_paren -= 1,
+                                ':' if !in_single
+                                    && !in_double
+                                    && level_brace == 0
+                                    && level_brack == 0
+                                    && level_paren == 0 =>
+                                {
+                                    prop_colon_idx = Some(idx_abs);
+                                    break;
+                                }
+                                _ => {}
+                            }
+                        }
+
+                        let Some(colon_idx) = prop_colon_idx else {
+                            search_start = abs_idx + 5;
+                            continue;
+                        };
+
+                        let mut field_prefix = contents[segment_start_idx..colon_idx].trim();
+                        if field_prefix.is_empty() {
+                            search_start = abs_idx + 5;
+                            continue;
+                        }
+
+                        if let Some(comment_idx) = field_prefix.rfind("*/") {
+                            field_prefix = field_prefix[comment_idx + 2..].trim_start();
+                        }
+
+                        if field_prefix.is_empty() {
+                            search_start = abs_idx + 5;
+                            continue;
+                        }
+
+                        if SKIP_PREFIXES
+                            .iter()
+                            .any(|prefix| field_prefix.starts_with(prefix))
+                        {
+                            search_start = abs_idx + 5;
+                            continue;
+                        }
+
+                        if field_prefix.contains('(') {
+                            search_start = abs_idx + 5;
+                            continue;
+                        }
+
+                        // If the last non-whitespace before ':' is '?', then this is an
+                        // optional field with a nullable type (i.e., "?: T | null"),
+                        // which we explicitly disallow.
+                        if field_prefix.chars().rev().find(|c| !c.is_whitespace()) == Some('?') {
+                            let line_number =
+                                contents[..abs_idx].chars().filter(|c| *c == '\n').count() + 1;
+                            let offending_line_end = contents[line_start_idx..]
+                                .find('\n')
+                                .map(|i| line_start_idx + i)
+                                .unwrap_or(contents.len());
+                            let offending_snippet =
+                                contents[line_start_idx..offending_line_end].trim();
+
+                            optional_nullable_offenders.insert(format!(
+                                "{}:{}: {offending_snippet}",
+                                path.display(),
+                                line_number
+                            ));
+                        }
+
+                        search_start = abs_idx + 5;
+                    }
+                }
+            }
+        }
+
+        assert!(
+            undefined_offenders.is_empty(),
+            "Generated TypeScript still includes unions with `undefined` in {undefined_offenders:?}"
+        );
+
+        // If this assertion fails, it means a field was generated as
+        // "?: T | null" — i.e., both optional (undefined) and nullable (null).
+        // We only want either "?: T" or ": T | null".
+        assert!(
+            optional_nullable_offenders.is_empty(),
+            "Generated TypeScript has optional fields with nullable types (disallowed '?: T | null'), add #[ts(optional)] to fix:\n{optional_nullable_offenders:?}"
+        );
+
+        Ok(())
+    }
+}

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

@@ -1,13 +1,14 @@
 //! We do not do true JSON-RPC 2.0, as we neither send nor expect the
 //! "jsonrpc": "2.0" field.
 
+use schemars::JsonSchema;
 use serde::Deserialize;
 use serde::Serialize;
 use ts_rs::TS;
 
 pub const JSONRPC_VERSION: &str = "2.0";
 
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, Hash, Eq, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, Hash, Eq, JsonSchema, TS)]
 #[serde(untagged)]
 pub enum RequestId {
     String(String),
@@ -18,7 +19,7 @@ pub enum RequestId {
 pub type Result = serde_json::Value;
 
 /// Refers to any valid JSON-RPC object that can be decoded off the wire, or encoded to be sent.
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, JsonSchema, TS)]
 #[serde(untagged)]
 pub enum JSONRPCMessage {
     Request(JSONRPCRequest),
@@ -28,40 +29,43 @@ pub enum JSONRPCMessage {
 }
 
 /// A request that expects a response.
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, JsonSchema, TS)]
 pub struct JSONRPCRequest {
     pub id: RequestId,
     pub method: String,
     #[serde(default, skip_serializing_if = "Option::is_none")]
+    #[ts(optional)]
     pub params: Option<serde_json::Value>,
 }
 
 /// A notification which does not expect a response.
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, JsonSchema, TS)]
 pub struct JSONRPCNotification {
     pub method: String,
     #[serde(default, skip_serializing_if = "Option::is_none")]
+    #[ts(optional)]
     pub params: Option<serde_json::Value>,
 }
 
 /// A successful (non-error) response to a request.
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, JsonSchema, TS)]
 pub struct JSONRPCResponse {
     pub id: RequestId,
     pub result: Result,
 }
 
 /// A response to a request that indicates an error occurred.
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, JsonSchema, TS)]
 pub struct JSONRPCError {
     pub error: JSONRPCErrorError,
     pub id: RequestId,
 }
 
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, TS)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, JsonSchema, TS)]
 pub struct JSONRPCErrorError {
     pub code: i64,
     #[serde(default, skip_serializing_if = "Option::is_none")]
+    #[ts(optional)]
     pub data: Option<serde_json::Value>,
     pub message: String,
 }

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

@@ -1,5 +1,12 @@
+mod export;
 mod jsonrpc_lite;
 mod protocol;
 
+pub use export::generate_json;
+pub use export::generate_ts;
+pub use export::generate_types;
 pub use jsonrpc_lite::*;
-pub use protocol::*;
+pub use protocol::common::*;
+pub use protocol::thread_history::*;
+pub use protocol::v1::*;
+pub use protocol::v2::*;

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

@@ -1,932 +0,0 @@
-use std::collections::HashMap;
-use std::path::PathBuf;
-
-use crate::JSONRPCNotification;
-use crate::JSONRPCRequest;
-use crate::RequestId;
-use codex_protocol::ConversationId;
-use codex_protocol::config_types::ReasoningEffort;
-use codex_protocol::config_types::ReasoningSummary;
-use codex_protocol::config_types::SandboxMode;
-use codex_protocol::config_types::Verbosity;
-use codex_protocol::protocol::AskForApproval;
-use codex_protocol::protocol::EventMsg;
-use codex_protocol::protocol::FileChange;
-use codex_protocol::protocol::ReviewDecision;
-use codex_protocol::protocol::SandboxPolicy;
-use codex_protocol::protocol::TurnAbortReason;
-use paste::paste;
-use serde::Deserialize;
-use serde::Serialize;
-use strum_macros::Display;
-use ts_rs::TS;
-use uuid::Uuid;
-
-#[derive(Serialize, Deserialize, Clone, Debug, PartialEq, TS)]
-#[ts(type = "string")]
-pub struct GitSha(pub String);
-
-impl GitSha {
-    pub fn new(sha: &str) -> Self {
-        Self(sha.to_string())
-    }
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, Display, TS)]
-#[serde(rename_all = "lowercase")]
-pub enum AuthMode {
-    ApiKey,
-    ChatGPT,
-}
-
-/// Generates an `enum ClientRequest` where each variant is a request that the
-/// client can send to the server. Each variant has associated `params` and
-/// `response` types. Also generates a `export_client_responses()` function to
-/// export all response types to TypeScript.
-macro_rules! client_request_definitions {
-    (
-        $(
-            $(#[$variant_meta:meta])*
-            $variant:ident {
-                params: $(#[$params_meta:meta])* $params:ty,
-                response: $response:ty,
-            }
-        ),* $(,)?
-    ) => {
-        /// Request from the client to the server.
-        #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-        #[serde(tag = "method", rename_all = "camelCase")]
-        pub enum ClientRequest {
-            $(
-                $(#[$variant_meta])*
-                $variant {
-                    #[serde(rename = "id")]
-                    request_id: RequestId,
-                    $(#[$params_meta])*
-                    params: $params,
-                },
-            )*
-        }
-
-        pub fn export_client_responses(
-            out_dir: &::std::path::Path,
-        ) -> ::std::result::Result<(), ::ts_rs::ExportError> {
-            $(
-                <$response as ::ts_rs::TS>::export_all_to(out_dir)?;
-            )*
-            Ok(())
-        }
-    };
-}
-
-client_request_definitions! {
-    Initialize {
-        params: InitializeParams,
-        response: InitializeResponse,
-    },
-    NewConversation {
-        params: NewConversationParams,
-        response: NewConversationResponse,
-    },
-    /// List recorded Codex conversations (rollouts) with optional pagination and search.
-    ListConversations {
-        params: ListConversationsParams,
-        response: ListConversationsResponse,
-    },
-    /// Resume a recorded Codex conversation from a rollout file.
-    ResumeConversation {
-        params: ResumeConversationParams,
-        response: ResumeConversationResponse,
-    },
-    ArchiveConversation {
-        params: ArchiveConversationParams,
-        response: ArchiveConversationResponse,
-    },
-    SendUserMessage {
-        params: SendUserMessageParams,
-        response: SendUserMessageResponse,
-    },
-    SendUserTurn {
-        params: SendUserTurnParams,
-        response: SendUserTurnResponse,
-    },
-    InterruptConversation {
-        params: InterruptConversationParams,
-        response: InterruptConversationResponse,
-    },
-    AddConversationListener {
-        params: AddConversationListenerParams,
-        response: AddConversationSubscriptionResponse,
-    },
-    RemoveConversationListener {
-        params: RemoveConversationListenerParams,
-        response: RemoveConversationSubscriptionResponse,
-    },
-    GitDiffToRemote {
-        params: GitDiffToRemoteParams,
-        response: GitDiffToRemoteResponse,
-    },
-    LoginApiKey {
-        params: LoginApiKeyParams,
-        response: LoginApiKeyResponse,
-    },
-    LoginChatGpt {
-        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
-        response: LoginChatGptResponse,
-    },
-    CancelLoginChatGpt {
-        params: CancelLoginChatGptParams,
-        response: CancelLoginChatGptResponse,
-    },
-    LogoutChatGpt {
-        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
-        response: LogoutChatGptResponse,
-    },
-    GetAuthStatus {
-        params: GetAuthStatusParams,
-        response: GetAuthStatusResponse,
-    },
-    GetUserSavedConfig {
-        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
-        response: GetUserSavedConfigResponse,
-    },
-    SetDefaultModel {
-        params: SetDefaultModelParams,
-        response: SetDefaultModelResponse,
-    },
-    GetUserAgent {
-        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
-        response: GetUserAgentResponse,
-    },
-    UserInfo {
-        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
-        response: UserInfoResponse,
-    },
-    FuzzyFileSearch {
-        params: FuzzyFileSearchParams,
-        response: FuzzyFileSearchResponse,
-    },
-    /// Execute a command (argv vector) under the server's sandbox.
-    ExecOneOffCommand {
-        params: ExecOneOffCommandParams,
-        response: ExecOneOffCommandResponse,
-    },
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct InitializeParams {
-    pub client_info: ClientInfo,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ClientInfo {
-    pub name: String,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub title: Option<String>,
-    pub version: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct InitializeResponse {
-    pub user_agent: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct NewConversationParams {
-    /// Optional override for the model name (e.g. "o3", "o4-mini").
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub model: Option<String>,
-
-    /// Configuration profile from config.toml to specify default options.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub profile: Option<String>,
-
-    /// Working directory for the session. If relative, it is resolved against
-    /// the server process's current working directory.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub cwd: Option<String>,
-
-    /// Approval policy for shell commands generated by the model:
-    /// `untrusted`, `on-failure`, `on-request`, `never`.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub approval_policy: Option<AskForApproval>,
-
-    /// Sandbox mode: `read-only`, `workspace-write`, or `danger-full-access`.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub sandbox: Option<SandboxMode>,
-
-    /// Individual config settings that will override what is in
-    /// CODEX_HOME/config.toml.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub config: Option<HashMap<String, serde_json::Value>>,
-
-    /// The set of instructions to use instead of the default ones.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub base_instructions: Option<String>,
-
-    /// Whether to include the plan tool in the conversation.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub include_plan_tool: Option<bool>,
-
-    /// Whether to include the apply patch tool in the conversation.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub include_apply_patch_tool: Option<bool>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct NewConversationResponse {
-    pub conversation_id: ConversationId,
-    pub model: String,
-    /// Note this could be ignored by the model.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub reasoning_effort: Option<ReasoningEffort>,
-    pub rollout_path: PathBuf,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ResumeConversationResponse {
-    pub conversation_id: ConversationId,
-    pub model: String,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub initial_messages: Option<Vec<EventMsg>>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ListConversationsParams {
-    /// Optional page size; defaults to a reasonable server-side value.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub page_size: Option<usize>,
-    /// Opaque pagination cursor returned by a previous call.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub cursor: Option<String>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ConversationSummary {
-    pub conversation_id: ConversationId,
-    pub path: PathBuf,
-    pub preview: String,
-    /// RFC3339 timestamp string for the session start, if available.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub timestamp: Option<String>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ListConversationsResponse {
-    pub items: Vec<ConversationSummary>,
-    /// Opaque cursor to pass to the next call to continue after the last item.
-    /// if None, there are no more items to return.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub next_cursor: Option<String>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ResumeConversationParams {
-    /// Absolute path to the rollout JSONL file.
-    pub path: PathBuf,
-    /// Optional overrides to apply when spawning the resumed session.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub overrides: Option<NewConversationParams>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct AddConversationSubscriptionResponse {
-    pub subscription_id: Uuid,
-}
-
-/// The [`ConversationId`] must match the `rollout_path`.
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ArchiveConversationParams {
-    pub conversation_id: ConversationId,
-    pub rollout_path: PathBuf,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ArchiveConversationResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct RemoveConversationSubscriptionResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct LoginApiKeyParams {
-    pub api_key: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct LoginApiKeyResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct LoginChatGptResponse {
-    pub login_id: Uuid,
-    /// URL the client should open in a browser to initiate the OAuth flow.
-    pub auth_url: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct GitDiffToRemoteResponse {
-    pub sha: GitSha,
-    pub diff: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct CancelLoginChatGptParams {
-    pub login_id: Uuid,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct GitDiffToRemoteParams {
-    pub cwd: PathBuf,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct CancelLoginChatGptResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct LogoutChatGptParams {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct LogoutChatGptResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct GetAuthStatusParams {
-    /// If true, include the current auth token (if available) in the response.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub include_token: Option<bool>,
-    /// If true, attempt to refresh the token before returning status.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub refresh_token: Option<bool>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ExecOneOffCommandParams {
-    /// Command argv to execute.
-    pub command: Vec<String>,
-    /// Timeout of the command in milliseconds.
-    /// If not specified, a sensible default is used server-side.
-    pub timeout_ms: Option<u64>,
-    /// Optional working directory for the process. Defaults to server config cwd.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub cwd: Option<PathBuf>,
-    /// Optional explicit sandbox policy overriding the server default.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub sandbox_policy: Option<SandboxPolicy>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ExecOneOffCommandResponse {
-    pub exit_code: i32,
-    pub stdout: String,
-    pub stderr: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct GetAuthStatusResponse {
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub auth_method: Option<AuthMode>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub auth_token: Option<String>,
-
-    // Indicates that auth method must be valid to use the server.
-    // This can be false if using a custom provider that is configured
-    // with requires_openai_auth == false.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub requires_openai_auth: Option<bool>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct GetUserAgentResponse {
-    pub user_agent: String,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct UserInfoResponse {
-    /// Note: `alleged_user_email` is not currently verified. We read it from
-    /// the local auth.json, which the user could theoretically modify. In the
-    /// future, we may add logic to verify the email against the server before
-    /// returning it.
-    pub alleged_user_email: Option<String>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct GetUserSavedConfigResponse {
-    pub config: UserSavedConfig,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SetDefaultModelParams {
-    /// If set to None, this means `model` should be cleared in config.toml.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub model: Option<String>,
-    /// If set to None, this means `model_reasoning_effort` should be cleared
-    /// in config.toml.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub reasoning_effort: Option<ReasoningEffort>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SetDefaultModelResponse {}
-
-/// UserSavedConfig contains a subset of the config. It is meant to expose mcp
-/// client-configurable settings that can be specified in the NewConversation
-/// and SendUserTurn requests.
-#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct UserSavedConfig {
-    /// Approvals
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub approval_policy: Option<AskForApproval>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub sandbox_mode: Option<SandboxMode>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub sandbox_settings: Option<SandboxSettings>,
-
-    /// Model-specific configuration
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub model: Option<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub model_reasoning_effort: Option<ReasoningEffort>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub model_reasoning_summary: Option<ReasoningSummary>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub model_verbosity: Option<Verbosity>,
-
-    /// Tools
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub tools: Option<Tools>,
-
-    /// Profiles
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub profile: Option<String>,
-    #[serde(default)]
-    pub profiles: HashMap<String, Profile>,
-}
-
-/// MCP representation of a [`codex_core::config_profile::ConfigProfile`].
-#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct Profile {
-    pub model: Option<String>,
-    /// The key in the `model_providers` map identifying the
-    /// [`ModelProviderInfo`] to use.
-    pub model_provider: Option<String>,
-    pub approval_policy: Option<AskForApproval>,
-    pub model_reasoning_effort: Option<ReasoningEffort>,
-    pub model_reasoning_summary: Option<ReasoningSummary>,
-    pub model_verbosity: Option<Verbosity>,
-    pub chatgpt_base_url: Option<String>,
-}
-/// MCP representation of a [`codex_core::config::ToolsToml`].
-#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct Tools {
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub web_search: Option<bool>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub view_image: Option<bool>,
-}
-
-/// MCP representation of a [`codex_core::config_types::SandboxWorkspaceWrite`].
-#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SandboxSettings {
-    #[serde(default)]
-    pub writable_roots: Vec<PathBuf>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub network_access: Option<bool>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub exclude_tmpdir_env_var: Option<bool>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub exclude_slash_tmp: Option<bool>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SendUserMessageParams {
-    pub conversation_id: ConversationId,
-    pub items: Vec<InputItem>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SendUserTurnParams {
-    pub conversation_id: ConversationId,
-    pub items: Vec<InputItem>,
-    pub cwd: PathBuf,
-    pub approval_policy: AskForApproval,
-    pub sandbox_policy: SandboxPolicy,
-    pub model: String,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub effort: Option<ReasoningEffort>,
-    pub summary: ReasoningSummary,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SendUserTurnResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct InterruptConversationParams {
-    pub conversation_id: ConversationId,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct InterruptConversationResponse {
-    pub abort_reason: TurnAbortReason,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SendUserMessageResponse {}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct AddConversationListenerParams {
-    pub conversation_id: ConversationId,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct RemoveConversationListenerParams {
-    pub subscription_id: Uuid,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-#[serde(tag = "type", content = "data")]
-pub enum InputItem {
-    Text {
-        text: String,
-    },
-    /// Pre‑encoded data: URI image.
-    Image {
-        image_url: String,
-    },
-
-    /// Local image path provided by the user.  This will be converted to an
-    /// `Image` variant (base64 data URL) during request serialization.
-    LocalImage {
-        path: PathBuf,
-    },
-}
-
-/// Generates an `enum ServerRequest` where each variant is a request that the
-/// server can send to the client along with the corresponding params and
-/// response types. It also generates helper types used by the app/server
-/// infrastructure (payload enum, request constructor, and export helpers).
-macro_rules! server_request_definitions {
-    (
-        $(
-            $(#[$variant_meta:meta])*
-            $variant:ident
-        ),* $(,)?
-    ) => {
-        paste! {
-            /// Request initiated from the server and sent to the client.
-            #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-            #[serde(tag = "method", rename_all = "camelCase")]
-            pub enum ServerRequest {
-                $(
-                    $(#[$variant_meta])*
-                    $variant {
-                        #[serde(rename = "id")]
-                        request_id: RequestId,
-                        params: [<$variant Params>],
-                    },
-                )*
-            }
-
-            #[derive(Debug, Clone, PartialEq)]
-            pub enum ServerRequestPayload {
-                $( $variant([<$variant Params>]), )*
-            }
-
-            impl ServerRequestPayload {
-                pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
-                    match self {
-                        $(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
-                    }
-                }
-            }
-        }
-
-        pub fn export_server_responses(
-            out_dir: &::std::path::Path,
-        ) -> ::std::result::Result<(), ::ts_rs::ExportError> {
-            paste! {
-                $(<[<$variant Response>] as ::ts_rs::TS>::export_all_to(out_dir)?;)*
-            }
-            Ok(())
-        }
-    };
-}
-
-impl TryFrom<JSONRPCRequest> for ServerRequest {
-    type Error = serde_json::Error;
-
-    fn try_from(value: JSONRPCRequest) -> Result<Self, Self::Error> {
-        serde_json::from_value(serde_json::to_value(value)?)
-    }
-}
-
-server_request_definitions! {
-    /// Request to approve a patch.
-    ApplyPatchApproval,
-    /// Request to exec a command.
-    ExecCommandApproval,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ApplyPatchApprovalParams {
-    pub conversation_id: ConversationId,
-    /// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
-    /// and [codex_core::protocol::PatchApplyEndEvent].
-    pub call_id: String,
-    pub file_changes: HashMap<PathBuf, FileChange>,
-    /// Optional explanatory reason (e.g. request for extra write access).
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub reason: Option<String>,
-    /// When set, the agent is asking the user to allow writes under this root
-    /// for the remainder of the session (unclear if this is honored today).
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub grant_root: Option<PathBuf>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ExecCommandApprovalParams {
-    pub conversation_id: ConversationId,
-    /// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
-    /// and [codex_core::protocol::ExecCommandEndEvent].
-    pub call_id: String,
-    pub command: Vec<String>,
-    pub cwd: PathBuf,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub reason: Option<String>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-pub struct ExecCommandApprovalResponse {
-    pub decision: ReviewDecision,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-pub struct ApplyPatchApprovalResponse {
-    pub decision: ReviewDecision,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-#[ts(rename_all = "camelCase")]
-pub struct FuzzyFileSearchParams {
-    pub query: String,
-    pub roots: Vec<String>,
-    // if provided, will cancel any previous request that used the same value
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub cancellation_token: Option<String>,
-}
-
-/// Superset of [`codex_file_search::FileMatch`]
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-pub struct FuzzyFileSearchResult {
-    pub root: String,
-    pub path: String,
-    pub file_name: String,
-    pub score: u32,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub indices: Option<Vec<u32>>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-pub struct FuzzyFileSearchResponse {
-    pub files: Vec<FuzzyFileSearchResult>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct LoginChatGptCompleteNotification {
-    pub login_id: Uuid,
-    pub success: bool,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub error: Option<String>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct SessionConfiguredNotification {
-    /// Name left as session_id instead of conversation_id for backwards compatibility.
-    pub session_id: ConversationId,
-
-    /// Tell the client what model is being queried.
-    pub model: String,
-
-    /// The effort the model is putting into reasoning about the user's request.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub reasoning_effort: Option<ReasoningEffort>,
-
-    /// Identifier of the history log file (inode on Unix, 0 otherwise).
-    pub history_log_id: u64,
-
-    /// Current number of entries in the history log.
-    #[ts(type = "number")]
-    pub history_entry_count: usize,
-
-    /// Optional initial messages (as events) for resumed sessions.
-    /// When present, UIs can use these to seed the history.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub initial_messages: Option<Vec<EventMsg>>,
-
-    pub rollout_path: PathBuf,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct AuthStatusChangeNotification {
-    /// Current authentication method; omitted if signed out.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub auth_method: Option<AuthMode>,
-}
-
-/// Notification sent from the server to the client.
-#[derive(Serialize, Deserialize, Debug, Clone, TS, Display)]
-#[serde(tag = "method", content = "params", rename_all = "camelCase")]
-#[strum(serialize_all = "camelCase")]
-pub enum ServerNotification {
-    /// Authentication status changed
-    AuthStatusChange(AuthStatusChangeNotification),
-
-    /// ChatGPT login flow completed
-    LoginChatGptComplete(LoginChatGptCompleteNotification),
-
-    /// The special session configured event for a new or resumed conversation.
-    SessionConfigured(SessionConfiguredNotification),
-}
-
-impl ServerNotification {
-    pub fn to_params(self) -> Result<serde_json::Value, serde_json::Error> {
-        match self {
-            ServerNotification::AuthStatusChange(params) => serde_json::to_value(params),
-            ServerNotification::LoginChatGptComplete(params) => serde_json::to_value(params),
-            ServerNotification::SessionConfigured(params) => serde_json::to_value(params),
-        }
-    }
-}
-
-impl TryFrom<JSONRPCNotification> for ServerNotification {
-    type Error = serde_json::Error;
-
-    fn try_from(value: JSONRPCNotification) -> Result<Self, Self::Error> {
-        serde_json::from_value(serde_json::to_value(value)?)
-    }
-}
-
-/// Notification sent from the client to the server.
-#[derive(Serialize, Deserialize, Debug, Clone, TS, Display)]
-#[serde(tag = "method", content = "params", rename_all = "camelCase")]
-#[strum(serialize_all = "camelCase")]
-pub enum ClientNotification {
-    Initialized,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use anyhow::Result;
-    use pretty_assertions::assert_eq;
-    use serde_json::json;
-
-    #[test]
-    fn serialize_new_conversation() -> Result<()> {
-        let request = ClientRequest::NewConversation {
-            request_id: RequestId::Integer(42),
-            params: NewConversationParams {
-                model: Some("gpt-5-codex".to_string()),
-                profile: None,
-                cwd: None,
-                approval_policy: Some(AskForApproval::OnRequest),
-                sandbox: None,
-                config: None,
-                base_instructions: None,
-                include_plan_tool: None,
-                include_apply_patch_tool: None,
-            },
-        };
-        assert_eq!(
-            json!({
-                "method": "newConversation",
-                "id": 42,
-                "params": {
-                    "model": "gpt-5-codex",
-                    "approvalPolicy": "on-request"
-                }
-            }),
-            serde_json::to_value(&request)?,
-        );
-        Ok(())
-    }
-
-    #[test]
-    fn conversation_id_serializes_as_plain_string() -> Result<()> {
-        let id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
-
-        assert_eq!(
-            json!("67e55044-10b1-426f-9247-bb680e5fe0c8"),
-            serde_json::to_value(id)?
-        );
-        Ok(())
-    }
-
-    #[test]
-    fn conversation_id_deserializes_from_plain_string() -> Result<()> {
-        let id: ConversationId =
-            serde_json::from_value(json!("67e55044-10b1-426f-9247-bb680e5fe0c8"))?;
-
-        assert_eq!(
-            ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?,
-            id,
-        );
-        Ok(())
-    }
-
-    #[test]
-    fn serialize_client_notification() -> Result<()> {
-        let notification = ClientNotification::Initialized;
-        // Note there is no "params" field for this notification.
-        assert_eq!(
-            json!({
-                "method": "initialized",
-            }),
-            serde_json::to_value(&notification)?,
-        );
-        Ok(())
-    }
-
-    #[test]
-    fn serialize_server_request() -> Result<()> {
-        let conversation_id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
-        let params = ExecCommandApprovalParams {
-            conversation_id,
-            call_id: "call-42".to_string(),
-            command: vec!["echo".to_string(), "hello".to_string()],
-            cwd: PathBuf::from("/tmp"),
-            reason: Some("because tests".to_string()),
-        };
-        let request = ServerRequest::ExecCommandApproval {
-            request_id: RequestId::Integer(7),
-            params: params.clone(),
-        };
-
-        assert_eq!(
-            json!({
-                "method": "execCommandApproval",
-                "id": 7,
-                "params": {
-                    "conversationId": "67e55044-10b1-426f-9247-bb680e5fe0c8",
-                    "callId": "call-42",
-                    "command": ["echo", "hello"],
-                    "cwd": "/tmp",
-                    "reason": "because tests",
-                }
-            }),
-            serde_json::to_value(&request)?,
-        );
-
-        let payload = ServerRequestPayload::ExecCommandApproval(params);
-        assert_eq!(payload.request_with_id(RequestId::Integer(7)), request);
-        Ok(())
-    }
-}

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

@@ -0,0 +1,835 @@
+use std::path::Path;
+
+use crate::JSONRPCNotification;
+use crate::JSONRPCRequest;
+use crate::RequestId;
+use crate::export::GeneratedSchema;
+use crate::export::write_json_schema;
+use crate::protocol::v1;
+use crate::protocol::v2;
+use schemars::JsonSchema;
+use serde::Deserialize;
+use serde::Serialize;
+use strum_macros::Display;
+use ts_rs::TS;
+
+#[derive(Serialize, Deserialize, Clone, Debug, PartialEq, JsonSchema, TS)]
+#[ts(type = "string")]
+pub struct GitSha(pub String);
+
+impl GitSha {
+    pub fn new(sha: &str) -> Self {
+        Self(sha.to_string())
+    }
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, Display, JsonSchema, TS)]
+#[serde(rename_all = "lowercase")]
+pub enum AuthMode {
+    ApiKey,
+    ChatGPT,
+}
+
+/// Generates an `enum ClientRequest` where each variant is a request that the
+/// client can send to the server. Each variant has associated `params` and
+/// `response` types. Also generates a `export_client_responses()` function to
+/// export all response types to TypeScript.
+macro_rules! client_request_definitions {
+    (
+        $(
+            $(#[$variant_meta:meta])*
+            $variant:ident $(=> $wire:literal)? {
+                params: $(#[$params_meta:meta])* $params:ty,
+                response: $response:ty,
+            }
+        ),* $(,)?
+    ) => {
+        /// Request from the client to the server.
+        #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+        #[serde(tag = "method", rename_all = "camelCase")]
+        pub enum ClientRequest {
+            $(
+                $(#[$variant_meta])*
+                $(#[serde(rename = $wire)] #[ts(rename = $wire)])?
+                $variant {
+                    #[serde(rename = "id")]
+                    request_id: RequestId,
+                    $(#[$params_meta])*
+                    params: $params,
+                },
+            )*
+        }
+
+        pub fn export_client_responses(
+            out_dir: &::std::path::Path,
+        ) -> ::std::result::Result<(), ::ts_rs::ExportError> {
+            $(
+                <$response as ::ts_rs::TS>::export_all_to(out_dir)?;
+            )*
+            Ok(())
+        }
+
+        #[allow(clippy::vec_init_then_push)]
+        pub fn export_client_response_schemas(
+            out_dir: &::std::path::Path,
+        ) -> ::anyhow::Result<Vec<GeneratedSchema>> {
+            let mut schemas = Vec::new();
+            $(
+                schemas.push(write_json_schema::<$response>(out_dir, stringify!($response))?);
+            )*
+            Ok(schemas)
+        }
+
+        #[allow(clippy::vec_init_then_push)]
+        pub fn export_client_param_schemas(
+            out_dir: &::std::path::Path,
+        ) -> ::anyhow::Result<Vec<GeneratedSchema>> {
+            let mut schemas = Vec::new();
+            $(
+                schemas.push(write_json_schema::<$params>(out_dir, stringify!($params))?);
+            )*
+            Ok(schemas)
+        }
+    };
+}
+
+client_request_definitions! {
+    Initialize {
+        params: v1::InitializeParams,
+        response: v1::InitializeResponse,
+    },
+
+    /// NEW APIs
+    // Thread lifecycle
+    ThreadStart => "thread/start" {
+        params: v2::ThreadStartParams,
+        response: v2::ThreadStartResponse,
+    },
+    ThreadResume => "thread/resume" {
+        params: v2::ThreadResumeParams,
+        response: v2::ThreadResumeResponse,
+    },
+    ThreadArchive => "thread/archive" {
+        params: v2::ThreadArchiveParams,
+        response: v2::ThreadArchiveResponse,
+    },
+    ThreadList => "thread/list" {
+        params: v2::ThreadListParams,
+        response: v2::ThreadListResponse,
+    },
+    ThreadCompact => "thread/compact" {
+        params: v2::ThreadCompactParams,
+        response: v2::ThreadCompactResponse,
+    },
+    SkillsList => "skills/list" {
+        params: v2::SkillsListParams,
+        response: v2::SkillsListResponse,
+    },
+    TurnStart => "turn/start" {
+        params: v2::TurnStartParams,
+        response: v2::TurnStartResponse,
+    },
+    TurnInterrupt => "turn/interrupt" {
+        params: v2::TurnInterruptParams,
+        response: v2::TurnInterruptResponse,
+    },
+    ReviewStart => "review/start" {
+        params: v2::ReviewStartParams,
+        response: v2::ReviewStartResponse,
+    },
+
+    ModelList => "model/list" {
+        params: v2::ModelListParams,
+        response: v2::ModelListResponse,
+    },
+
+    McpServerOauthLogin => "mcpServer/oauth/login" {
+        params: v2::McpServerOauthLoginParams,
+        response: v2::McpServerOauthLoginResponse,
+    },
+
+    McpServersList => "mcpServers/list" {
+        params: v2::ListMcpServersParams,
+        response: v2::ListMcpServersResponse,
+    },
+
+    LoginAccount => "account/login/start" {
+        params: v2::LoginAccountParams,
+        response: v2::LoginAccountResponse,
+    },
+
+    CancelLoginAccount => "account/login/cancel" {
+        params: v2::CancelLoginAccountParams,
+        response: v2::CancelLoginAccountResponse,
+    },
+
+    LogoutAccount => "account/logout" {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v2::LogoutAccountResponse,
+    },
+
+    GetAccountRateLimits => "account/rateLimits/read" {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v2::GetAccountRateLimitsResponse,
+    },
+
+    FeedbackUpload => "feedback/upload" {
+        params: v2::FeedbackUploadParams,
+        response: v2::FeedbackUploadResponse,
+    },
+
+    /// Execute a command (argv vector) under the server's sandbox.
+    OneOffCommandExec => "command/exec" {
+        params: v2::CommandExecParams,
+        response: v2::CommandExecResponse,
+    },
+
+    ConfigRead => "config/read" {
+        params: v2::ConfigReadParams,
+        response: v2::ConfigReadResponse,
+    },
+    ConfigValueWrite => "config/value/write" {
+        params: v2::ConfigValueWriteParams,
+        response: v2::ConfigWriteResponse,
+    },
+    ConfigBatchWrite => "config/batchWrite" {
+        params: v2::ConfigBatchWriteParams,
+        response: v2::ConfigWriteResponse,
+    },
+
+    GetAccount => "account/read" {
+        params: v2::GetAccountParams,
+        response: v2::GetAccountResponse,
+    },
+
+    /// DEPRECATED APIs below
+    NewConversation {
+        params: v1::NewConversationParams,
+        response: v1::NewConversationResponse,
+    },
+    GetConversationSummary {
+        params: v1::GetConversationSummaryParams,
+        response: v1::GetConversationSummaryResponse,
+    },
+    /// List recorded Codex conversations (rollouts) with optional pagination and search.
+    ListConversations {
+        params: v1::ListConversationsParams,
+        response: v1::ListConversationsResponse,
+    },
+    /// Resume a recorded Codex conversation from a rollout file.
+    ResumeConversation {
+        params: v1::ResumeConversationParams,
+        response: v1::ResumeConversationResponse,
+    },
+    ArchiveConversation {
+        params: v1::ArchiveConversationParams,
+        response: v1::ArchiveConversationResponse,
+    },
+    SendUserMessage {
+        params: v1::SendUserMessageParams,
+        response: v1::SendUserMessageResponse,
+    },
+    SendUserTurn {
+        params: v1::SendUserTurnParams,
+        response: v1::SendUserTurnResponse,
+    },
+    InterruptConversation {
+        params: v1::InterruptConversationParams,
+        response: v1::InterruptConversationResponse,
+    },
+    AddConversationListener {
+        params: v1::AddConversationListenerParams,
+        response: v1::AddConversationSubscriptionResponse,
+    },
+    RemoveConversationListener {
+        params: v1::RemoveConversationListenerParams,
+        response: v1::RemoveConversationSubscriptionResponse,
+    },
+    GitDiffToRemote {
+        params: v1::GitDiffToRemoteParams,
+        response: v1::GitDiffToRemoteResponse,
+    },
+    LoginApiKey {
+        params: v1::LoginApiKeyParams,
+        response: v1::LoginApiKeyResponse,
+    },
+    LoginChatGpt {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v1::LoginChatGptResponse,
+    },
+    // DEPRECATED in favor of CancelLoginAccount
+    CancelLoginChatGpt {
+        params: v1::CancelLoginChatGptParams,
+        response: v1::CancelLoginChatGptResponse,
+    },
+    LogoutChatGpt {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v1::LogoutChatGptResponse,
+    },
+    /// DEPRECATED in favor of GetAccount
+    GetAuthStatus {
+        params: v1::GetAuthStatusParams,
+        response: v1::GetAuthStatusResponse,
+    },
+    GetUserSavedConfig {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v1::GetUserSavedConfigResponse,
+    },
+    SetDefaultModel {
+        params: v1::SetDefaultModelParams,
+        response: v1::SetDefaultModelResponse,
+    },
+    GetUserAgent {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v1::GetUserAgentResponse,
+    },
+    UserInfo {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
+        response: v1::UserInfoResponse,
+    },
+    FuzzyFileSearch {
+        params: FuzzyFileSearchParams,
+        response: FuzzyFileSearchResponse,
+    },
+    /// Execute a command (argv vector) under the server's sandbox.
+    ExecOneOffCommand {
+        params: v1::ExecOneOffCommandParams,
+        response: v1::ExecOneOffCommandResponse,
+    },
+}
+
+/// Generates an `enum ServerRequest` where each variant is a request that the
+/// server can send to the client along with the corresponding params and
+/// response types. It also generates helper types used by the app/server
+/// infrastructure (payload enum, request constructor, and export helpers).
+macro_rules! server_request_definitions {
+    (
+        $(
+            $(#[$variant_meta:meta])*
+            $variant:ident $(=> $wire:literal)? {
+                params: $params:ty,
+                response: $response:ty,
+            }
+        ),* $(,)?
+    ) => {
+        /// Request initiated from the server and sent to the client.
+        #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+        #[serde(tag = "method", rename_all = "camelCase")]
+        pub enum ServerRequest {
+            $(
+                $(#[$variant_meta])*
+                $(#[serde(rename = $wire)] #[ts(rename = $wire)])?
+                $variant {
+                    #[serde(rename = "id")]
+                    request_id: RequestId,
+                    params: $params,
+                },
+            )*
+        }
+
+        #[derive(Debug, Clone, PartialEq, JsonSchema)]
+        pub enum ServerRequestPayload {
+            $( $variant($params), )*
+        }
+
+        impl ServerRequestPayload {
+            pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
+                match self {
+                    $(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
+                }
+            }
+        }
+
+        pub fn export_server_responses(
+            out_dir: &::std::path::Path,
+        ) -> ::std::result::Result<(), ::ts_rs::ExportError> {
+            $(
+                <$response as ::ts_rs::TS>::export_all_to(out_dir)?;
+            )*
+            Ok(())
+        }
+
+        #[allow(clippy::vec_init_then_push)]
+        pub fn export_server_response_schemas(
+            out_dir: &Path,
+        ) -> ::anyhow::Result<Vec<GeneratedSchema>> {
+            let mut schemas = Vec::new();
+            $(
+                schemas.push(crate::export::write_json_schema::<$response>(
+                    out_dir,
+                    concat!(stringify!($variant), "Response"),
+                )?);
+            )*
+            Ok(schemas)
+        }
+
+        #[allow(clippy::vec_init_then_push)]
+        pub fn export_server_param_schemas(
+            out_dir: &Path,
+        ) -> ::anyhow::Result<Vec<GeneratedSchema>> {
+            let mut schemas = Vec::new();
+            $(
+                schemas.push(crate::export::write_json_schema::<$params>(
+                    out_dir,
+                    concat!(stringify!($variant), "Params"),
+                )?);
+            )*
+            Ok(schemas)
+        }
+    };
+}
+
+/// Generates `ServerNotification` enum and helpers, including a JSON Schema
+/// exporter for each notification.
+macro_rules! server_notification_definitions {
+    (
+        $(
+            $(#[$variant_meta:meta])*
+            $variant:ident $(=> $wire:literal)? ( $payload:ty )
+        ),* $(,)?
+    ) => {
+        /// Notification sent from the server to the client.
+        #[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS, Display)]
+        #[serde(tag = "method", content = "params", rename_all = "camelCase")]
+        #[strum(serialize_all = "camelCase")]
+        pub enum ServerNotification {
+            $(
+                $(#[$variant_meta])*
+                $(#[serde(rename = $wire)] #[ts(rename = $wire)] #[strum(serialize = $wire)])?
+                $variant($payload),
+            )*
+        }
+
+        impl ServerNotification {
+            pub fn to_params(self) -> Result<serde_json::Value, serde_json::Error> {
+                match self {
+                    $(Self::$variant(params) => serde_json::to_value(params),)*
+                }
+            }
+        }
+
+        impl TryFrom<JSONRPCNotification> for ServerNotification {
+            type Error = serde_json::Error;
+
+            fn try_from(value: JSONRPCNotification) -> Result<Self, serde_json::Error> {
+                serde_json::from_value(serde_json::to_value(value)?)
+            }
+        }
+
+        #[allow(clippy::vec_init_then_push)]
+        pub fn export_server_notification_schemas(
+            out_dir: &::std::path::Path,
+        ) -> ::anyhow::Result<Vec<GeneratedSchema>> {
+            let mut schemas = Vec::new();
+            $(schemas.push(crate::export::write_json_schema::<$payload>(out_dir, stringify!($payload))?);)*
+            Ok(schemas)
+        }
+    };
+}
+/// Notifications sent from the client to the server.
+macro_rules! client_notification_definitions {
+    (
+        $(
+            $(#[$variant_meta:meta])*
+            $variant:ident $( ( $payload:ty ) )?
+        ),* $(,)?
+    ) => {
+        #[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS, Display)]
+        #[serde(tag = "method", content = "params", rename_all = "camelCase")]
+        #[strum(serialize_all = "camelCase")]
+        pub enum ClientNotification {
+            $(
+                $(#[$variant_meta])*
+                $variant $( ( $payload ) )?,
+            )*
+        }
+
+        pub fn export_client_notification_schemas(
+            _out_dir: &::std::path::Path,
+        ) -> ::anyhow::Result<Vec<GeneratedSchema>> {
+            let schemas = Vec::new();
+            $( $(schemas.push(crate::export::write_json_schema::<$payload>(_out_dir, stringify!($payload))?);)? )*
+            Ok(schemas)
+        }
+    };
+}
+
+impl TryFrom<JSONRPCRequest> for ServerRequest {
+    type Error = serde_json::Error;
+
+    fn try_from(value: JSONRPCRequest) -> Result<Self, Self::Error> {
+        serde_json::from_value(serde_json::to_value(value)?)
+    }
+}
+
+server_request_definitions! {
+    /// NEW APIs
+    /// Sent when approval is requested for a specific command execution.
+    /// This request is used for Turns started via turn/start.
+    CommandExecutionRequestApproval => "item/commandExecution/requestApproval" {
+        params: v2::CommandExecutionRequestApprovalParams,
+        response: v2::CommandExecutionRequestApprovalResponse,
+    },
+
+    /// Sent when approval is requested for a specific file change.
+    /// This request is used for Turns started via turn/start.
+    FileChangeRequestApproval => "item/fileChange/requestApproval" {
+        params: v2::FileChangeRequestApprovalParams,
+        response: v2::FileChangeRequestApprovalResponse,
+    },
+
+    /// DEPRECATED APIs below
+    /// Request to approve a patch.
+    /// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
+    ApplyPatchApproval {
+        params: v1::ApplyPatchApprovalParams,
+        response: v1::ApplyPatchApprovalResponse,
+    },
+    /// Request to exec a command.
+    /// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
+    ExecCommandApproval {
+        params: v1::ExecCommandApprovalParams,
+        response: v1::ExecCommandApprovalResponse,
+    },
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(rename_all = "camelCase")]
+pub struct FuzzyFileSearchParams {
+    pub query: String,
+    pub roots: Vec<String>,
+    // if provided, will cancel any previous request that used the same value
+    pub cancellation_token: Option<String>,
+}
+
+/// Superset of [`codex_file_search::FileMatch`]
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+pub struct FuzzyFileSearchResult {
+    pub root: String,
+    pub path: String,
+    pub file_name: String,
+    pub score: u32,
+    pub indices: Option<Vec<u32>>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+pub struct FuzzyFileSearchResponse {
+    pub files: Vec<FuzzyFileSearchResult>,
+}
+
+server_notification_definitions! {
+    /// NEW NOTIFICATIONS
+    Error => "error" (v2::ErrorNotification),
+    ThreadStarted => "thread/started" (v2::ThreadStartedNotification),
+    ThreadTokenUsageUpdated => "thread/tokenUsage/updated" (v2::ThreadTokenUsageUpdatedNotification),
+    TurnStarted => "turn/started" (v2::TurnStartedNotification),
+    TurnCompleted => "turn/completed" (v2::TurnCompletedNotification),
+    TurnDiffUpdated => "turn/diff/updated" (v2::TurnDiffUpdatedNotification),
+    TurnPlanUpdated => "turn/plan/updated" (v2::TurnPlanUpdatedNotification),
+    ItemStarted => "item/started" (v2::ItemStartedNotification),
+    ItemCompleted => "item/completed" (v2::ItemCompletedNotification),
+    AgentMessageDelta => "item/agentMessage/delta" (v2::AgentMessageDeltaNotification),
+    CommandExecutionOutputDelta => "item/commandExecution/outputDelta" (v2::CommandExecutionOutputDeltaNotification),
+    TerminalInteraction => "item/commandExecution/terminalInteraction" (v2::TerminalInteractionNotification),
+    FileChangeOutputDelta => "item/fileChange/outputDelta" (v2::FileChangeOutputDeltaNotification),
+    McpToolCallProgress => "item/mcpToolCall/progress" (v2::McpToolCallProgressNotification),
+    McpServerOauthLoginCompleted => "mcpServer/oauthLogin/completed" (v2::McpServerOauthLoginCompletedNotification),
+    AccountUpdated => "account/updated" (v2::AccountUpdatedNotification),
+    AccountRateLimitsUpdated => "account/rateLimits/updated" (v2::AccountRateLimitsUpdatedNotification),
+    ReasoningSummaryTextDelta => "item/reasoning/summaryTextDelta" (v2::ReasoningSummaryTextDeltaNotification),
+    ReasoningSummaryPartAdded => "item/reasoning/summaryPartAdded" (v2::ReasoningSummaryPartAddedNotification),
+    ReasoningTextDelta => "item/reasoning/textDelta" (v2::ReasoningTextDeltaNotification),
+    ContextCompacted => "thread/compacted" (v2::ContextCompactedNotification),
+
+    /// Notifies the user of world-writable directories on Windows, which cannot be protected by the sandbox.
+    WindowsWorldWritableWarning => "windows/worldWritableWarning" (v2::WindowsWorldWritableWarningNotification),
+
+    #[serde(rename = "account/login/completed")]
+    #[ts(rename = "account/login/completed")]
+    #[strum(serialize = "account/login/completed")]
+    AccountLoginCompleted(v2::AccountLoginCompletedNotification),
+
+    /// DEPRECATED NOTIFICATIONS below
+    AuthStatusChange(v1::AuthStatusChangeNotification),
+
+    /// Deprecated: use `account/login/completed` instead.
+    LoginChatGptComplete(v1::LoginChatGptCompleteNotification),
+    SessionConfigured(v1::SessionConfiguredNotification),
+}
+
+client_notification_definitions! {
+    Initialized,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use anyhow::Result;
+    use codex_protocol::ConversationId;
+    use codex_protocol::account::PlanType;
+    use codex_protocol::parse_command::ParsedCommand;
+    use codex_protocol::protocol::AskForApproval;
+    use pretty_assertions::assert_eq;
+    use serde_json::json;
+    use std::path::PathBuf;
+
+    #[test]
+    fn serialize_new_conversation() -> Result<()> {
+        let request = ClientRequest::NewConversation {
+            request_id: RequestId::Integer(42),
+            params: v1::NewConversationParams {
+                model: Some("gpt-5.1-codex-max".to_string()),
+                model_provider: None,
+                profile: None,
+                cwd: None,
+                approval_policy: Some(AskForApproval::OnRequest),
+                sandbox: None,
+                config: None,
+                base_instructions: None,
+                developer_instructions: None,
+                compact_prompt: None,
+                include_apply_patch_tool: None,
+            },
+        };
+        assert_eq!(
+            json!({
+                "method": "newConversation",
+                "id": 42,
+                "params": {
+                    "model": "gpt-5.1-codex-max",
+                    "modelProvider": null,
+                    "profile": null,
+                    "cwd": null,
+                    "approvalPolicy": "on-request",
+                    "sandbox": null,
+                    "config": null,
+                    "baseInstructions": null,
+                    "includeApplyPatchTool": null
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn conversation_id_serializes_as_plain_string() -> Result<()> {
+        let id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
+
+        assert_eq!(
+            json!("67e55044-10b1-426f-9247-bb680e5fe0c8"),
+            serde_json::to_value(id)?
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn conversation_id_deserializes_from_plain_string() -> Result<()> {
+        let id: ConversationId =
+            serde_json::from_value(json!("67e55044-10b1-426f-9247-bb680e5fe0c8"))?;
+
+        assert_eq!(
+            ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?,
+            id,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_client_notification() -> Result<()> {
+        let notification = ClientNotification::Initialized;
+        // Note there is no "params" field for this notification.
+        assert_eq!(
+            json!({
+                "method": "initialized",
+            }),
+            serde_json::to_value(&notification)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_server_request() -> Result<()> {
+        let conversation_id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
+        let params = v1::ExecCommandApprovalParams {
+            conversation_id,
+            call_id: "call-42".to_string(),
+            command: vec!["echo".to_string(), "hello".to_string()],
+            cwd: PathBuf::from("/tmp"),
+            reason: Some("because tests".to_string()),
+            parsed_cmd: vec![ParsedCommand::Unknown {
+                cmd: "echo hello".to_string(),
+            }],
+        };
+        let request = ServerRequest::ExecCommandApproval {
+            request_id: RequestId::Integer(7),
+            params: params.clone(),
+        };
+
+        assert_eq!(
+            json!({
+                "method": "execCommandApproval",
+                "id": 7,
+                "params": {
+                    "conversationId": "67e55044-10b1-426f-9247-bb680e5fe0c8",
+                    "callId": "call-42",
+                    "command": ["echo", "hello"],
+                    "cwd": "/tmp",
+                    "reason": "because tests",
+                    "parsedCmd": [
+                        {
+                            "type": "unknown",
+                            "cmd": "echo hello"
+                        }
+                    ]
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+
+        let payload = ServerRequestPayload::ExecCommandApproval(params);
+        assert_eq!(payload.request_with_id(RequestId::Integer(7)), request);
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_get_account_rate_limits() -> Result<()> {
+        let request = ClientRequest::GetAccountRateLimits {
+            request_id: RequestId::Integer(1),
+            params: None,
+        };
+        assert_eq!(
+            json!({
+                "method": "account/rateLimits/read",
+                "id": 1,
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_account_login_api_key() -> Result<()> {
+        let request = ClientRequest::LoginAccount {
+            request_id: RequestId::Integer(2),
+            params: v2::LoginAccountParams::ApiKey {
+                api_key: "secret".to_string(),
+            },
+        };
+        assert_eq!(
+            json!({
+                "method": "account/login/start",
+                "id": 2,
+                "params": {
+                    "type": "apiKey",
+                    "apiKey": "secret"
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_account_login_chatgpt() -> Result<()> {
+        let request = ClientRequest::LoginAccount {
+            request_id: RequestId::Integer(3),
+            params: v2::LoginAccountParams::Chatgpt,
+        };
+        assert_eq!(
+            json!({
+                "method": "account/login/start",
+                "id": 3,
+                "params": {
+                    "type": "chatgpt"
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_account_logout() -> Result<()> {
+        let request = ClientRequest::LogoutAccount {
+            request_id: RequestId::Integer(4),
+            params: None,
+        };
+        assert_eq!(
+            json!({
+                "method": "account/logout",
+                "id": 4,
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_get_account() -> Result<()> {
+        let request = ClientRequest::GetAccount {
+            request_id: RequestId::Integer(5),
+            params: v2::GetAccountParams {
+                refresh_token: false,
+            },
+        };
+        assert_eq!(
+            json!({
+                "method": "account/read",
+                "id": 5,
+                "params": {
+                    "refreshToken": false
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn account_serializes_fields_in_camel_case() -> Result<()> {
+        let api_key = v2::Account::ApiKey {};
+        assert_eq!(
+            json!({
+                "type": "apiKey",
+            }),
+            serde_json::to_value(&api_key)?,
+        );
+
+        let chatgpt = v2::Account::Chatgpt {
+            email: "user@example.com".to_string(),
+            plan_type: PlanType::Plus,
+        };
+        assert_eq!(
+            json!({
+                "type": "chatgpt",
+                "email": "user@example.com",
+                "planType": "plus",
+            }),
+            serde_json::to_value(&chatgpt)?,
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn serialize_list_models() -> Result<()> {
+        let request = ClientRequest::ModelList {
+            request_id: RequestId::Integer(6),
+            params: v2::ModelListParams::default(),
+        };
+        assert_eq!(
+            json!({
+                "method": "model/list",
+                "id": 6,
+                "params": {
+                    "limit": null,
+                    "cursor": null
+                }
+            }),
+            serde_json::to_value(&request)?,
+        );
+        Ok(())
+    }
+}

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

@@ -0,0 +1,15 @@
+use crate::protocol::v1;
+use crate::protocol::v2;
+
+impl From<v1::ExecOneOffCommandParams> for v2::CommandExecParams {
+    fn from(value: v1::ExecOneOffCommandParams) -> Self {
+        Self {
+            command: value.command,
+            timeout_ms: value
+                .timeout_ms
+                .map(|timeout| i64::try_from(timeout).unwrap_or(60_000)),
+            cwd: value.cwd,
+            sandbox_policy: value.sandbox_policy.map(std::convert::Into::into),
+        }
+    }
+}

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

@@ -0,0 +1,8 @@
+// Module declarations for the app-server protocol namespace.
+// Exposes protocol pieces used by `lib.rs` via `pub use protocol::common::*;`.
+
+pub mod common;
+mod mappers;
+pub mod thread_history;
+pub mod v1;
+pub mod v2;

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

@@ -0,0 +1,413 @@
+use crate::protocol::v2::ThreadItem;
+use crate::protocol::v2::Turn;
+use crate::protocol::v2::TurnError;
+use crate::protocol::v2::TurnStatus;
+use crate::protocol::v2::UserInput;
+use codex_protocol::protocol::AgentReasoningEvent;
+use codex_protocol::protocol::AgentReasoningRawContentEvent;
+use codex_protocol::protocol::EventMsg;
+use codex_protocol::protocol::TurnAbortedEvent;
+use codex_protocol::protocol::UserMessageEvent;
+
+/// Convert persisted [`EventMsg`] entries into a sequence of [`Turn`] values.
+///
+/// The purpose of this is to convert the EventMsgs persisted in a rollout file
+/// into a sequence of Turns and ThreadItems, which allows the client to render
+/// the historical messages when resuming a thread.
+pub fn build_turns_from_event_msgs(events: &[EventMsg]) -> Vec<Turn> {
+    let mut builder = ThreadHistoryBuilder::new();
+    for event in events {
+        builder.handle_event(event);
+    }
+    builder.finish()
+}
+
+struct ThreadHistoryBuilder {
+    turns: Vec<Turn>,
+    current_turn: Option<PendingTurn>,
+    next_turn_index: i64,
+    next_item_index: i64,
+}
+
+impl ThreadHistoryBuilder {
+    fn new() -> Self {
+        Self {
+            turns: Vec::new(),
+            current_turn: None,
+            next_turn_index: 1,
+            next_item_index: 1,
+        }
+    }
+
+    fn finish(mut self) -> Vec<Turn> {
+        self.finish_current_turn();
+        self.turns
+    }
+
+    /// This function should handle all EventMsg variants that can be persisted in a rollout file.
+    /// See `should_persist_event_msg` in `codex-rs/core/rollout/policy.rs`.
+    fn handle_event(&mut self, event: &EventMsg) {
+        match event {
+            EventMsg::UserMessage(payload) => self.handle_user_message(payload),
+            EventMsg::AgentMessage(payload) => self.handle_agent_message(payload.message.clone()),
+            EventMsg::AgentReasoning(payload) => self.handle_agent_reasoning(payload),
+            EventMsg::AgentReasoningRawContent(payload) => {
+                self.handle_agent_reasoning_raw_content(payload)
+            }
+            EventMsg::TokenCount(_) => {}
+            EventMsg::EnteredReviewMode(_) => {}
+            EventMsg::ExitedReviewMode(_) => {}
+            EventMsg::UndoCompleted(_) => {}
+            EventMsg::TurnAborted(payload) => self.handle_turn_aborted(payload),
+            _ => {}
+        }
+    }
+
+    fn handle_user_message(&mut self, payload: &UserMessageEvent) {
+        self.finish_current_turn();
+        let mut turn = self.new_turn();
+        let id = self.next_item_id();
+        let content = self.build_user_inputs(payload);
+        turn.items.push(ThreadItem::UserMessage { id, content });
+        self.current_turn = Some(turn);
+    }
+
+    fn handle_agent_message(&mut self, text: String) {
+        if text.is_empty() {
+            return;
+        }
+
+        let id = self.next_item_id();
+        self.ensure_turn()
+            .items
+            .push(ThreadItem::AgentMessage { id, text });
+    }
+
+    fn handle_agent_reasoning(&mut self, payload: &AgentReasoningEvent) {
+        if payload.text.is_empty() {
+            return;
+        }
+
+        // If the last item is a reasoning item, add the new text to the summary.
+        if let Some(ThreadItem::Reasoning { summary, .. }) = self.ensure_turn().items.last_mut() {
+            summary.push(payload.text.clone());
+            return;
+        }
+
+        // Otherwise, create a new reasoning item.
+        let id = self.next_item_id();
+        self.ensure_turn().items.push(ThreadItem::Reasoning {
+            id,
+            summary: vec![payload.text.clone()],
+            content: Vec::new(),
+        });
+    }
+
+    fn handle_agent_reasoning_raw_content(&mut self, payload: &AgentReasoningRawContentEvent) {
+        if payload.text.is_empty() {
+            return;
+        }
+
+        // If the last item is a reasoning item, add the new text to the content.
+        if let Some(ThreadItem::Reasoning { content, .. }) = self.ensure_turn().items.last_mut() {
+            content.push(payload.text.clone());
+            return;
+        }
+
+        // Otherwise, create a new reasoning item.
+        let id = self.next_item_id();
+        self.ensure_turn().items.push(ThreadItem::Reasoning {
+            id,
+            summary: Vec::new(),
+            content: vec![payload.text.clone()],
+        });
+    }
+
+    fn handle_turn_aborted(&mut self, _payload: &TurnAbortedEvent) {
+        let Some(turn) = self.current_turn.as_mut() else {
+            return;
+        };
+        turn.status = TurnStatus::Interrupted;
+    }
+
+    fn finish_current_turn(&mut self) {
+        if let Some(turn) = self.current_turn.take() {
+            if turn.items.is_empty() {
+                return;
+            }
+            self.turns.push(turn.into());
+        }
+    }
+
+    fn new_turn(&mut self) -> PendingTurn {
+        PendingTurn {
+            id: self.next_turn_id(),
+            items: Vec::new(),
+            error: None,
+            status: TurnStatus::Completed,
+        }
+    }
+
+    fn ensure_turn(&mut self) -> &mut PendingTurn {
+        if self.current_turn.is_none() {
+            let turn = self.new_turn();
+            return self.current_turn.insert(turn);
+        }
+
+        if let Some(turn) = self.current_turn.as_mut() {
+            return turn;
+        }
+
+        unreachable!("current turn must exist after initialization");
+    }
+
+    fn next_turn_id(&mut self) -> String {
+        let id = format!("turn-{}", self.next_turn_index);
+        self.next_turn_index += 1;
+        id
+    }
+
+    fn next_item_id(&mut self) -> String {
+        let id = format!("item-{}", self.next_item_index);
+        self.next_item_index += 1;
+        id
+    }
+
+    fn build_user_inputs(&self, payload: &UserMessageEvent) -> Vec<UserInput> {
+        let mut content = Vec::new();
+        if !payload.message.trim().is_empty() {
+            content.push(UserInput::Text {
+                text: payload.message.clone(),
+            });
+        }
+        if let Some(images) = &payload.images {
+            for image in images {
+                content.push(UserInput::Image { url: image.clone() });
+            }
+        }
+        content
+    }
+}
+
+struct PendingTurn {
+    id: String,
+    items: Vec<ThreadItem>,
+    error: Option<TurnError>,
+    status: TurnStatus,
+}
+
+impl From<PendingTurn> for Turn {
+    fn from(value: PendingTurn) -> Self {
+        Self {
+            id: value.id,
+            items: value.items,
+            error: value.error,
+            status: value.status,
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use codex_protocol::protocol::AgentMessageEvent;
+    use codex_protocol::protocol::AgentReasoningEvent;
+    use codex_protocol::protocol::AgentReasoningRawContentEvent;
+    use codex_protocol::protocol::TurnAbortReason;
+    use codex_protocol::protocol::TurnAbortedEvent;
+    use codex_protocol::protocol::UserMessageEvent;
+    use pretty_assertions::assert_eq;
+
+    #[test]
+    fn builds_multiple_turns_with_reasoning_items() {
+        let events = vec![
+            EventMsg::UserMessage(UserMessageEvent {
+                message: "First turn".into(),
+                images: Some(vec!["https://example.com/one.png".into()]),
+            }),
+            EventMsg::AgentMessage(AgentMessageEvent {
+                message: "Hi there".into(),
+            }),
+            EventMsg::AgentReasoning(AgentReasoningEvent {
+                text: "thinking".into(),
+            }),
+            EventMsg::AgentReasoningRawContent(AgentReasoningRawContentEvent {
+                text: "full reasoning".into(),
+            }),
+            EventMsg::UserMessage(UserMessageEvent {
+                message: "Second turn".into(),
+                images: None,
+            }),
+            EventMsg::AgentMessage(AgentMessageEvent {
+                message: "Reply two".into(),
+            }),
+        ];
+
+        let turns = build_turns_from_event_msgs(&events);
+        assert_eq!(turns.len(), 2);
+
+        let first = &turns[0];
+        assert_eq!(first.id, "turn-1");
+        assert_eq!(first.status, TurnStatus::Completed);
+        assert_eq!(first.items.len(), 3);
+        assert_eq!(
+            first.items[0],
+            ThreadItem::UserMessage {
+                id: "item-1".into(),
+                content: vec![
+                    UserInput::Text {
+                        text: "First turn".into(),
+                    },
+                    UserInput::Image {
+                        url: "https://example.com/one.png".into(),
+                    }
+                ],
+            }
+        );
+        assert_eq!(
+            first.items[1],
+            ThreadItem::AgentMessage {
+                id: "item-2".into(),
+                text: "Hi there".into(),
+            }
+        );
+        assert_eq!(
+            first.items[2],
+            ThreadItem::Reasoning {
+                id: "item-3".into(),
+                summary: vec!["thinking".into()],
+                content: vec!["full reasoning".into()],
+            }
+        );
+
+        let second = &turns[1];
+        assert_eq!(second.id, "turn-2");
+        assert_eq!(second.items.len(), 2);
+        assert_eq!(
+            second.items[0],
+            ThreadItem::UserMessage {
+                id: "item-4".into(),
+                content: vec![UserInput::Text {
+                    text: "Second turn".into()
+                }],
+            }
+        );
+        assert_eq!(
+            second.items[1],
+            ThreadItem::AgentMessage {
+                id: "item-5".into(),
+                text: "Reply two".into(),
+            }
+        );
+    }
+
+    #[test]
+    fn splits_reasoning_when_interleaved() {
+        let events = vec![
+            EventMsg::UserMessage(UserMessageEvent {
+                message: "Turn start".into(),
+                images: None,
+            }),
+            EventMsg::AgentReasoning(AgentReasoningEvent {
+                text: "first summary".into(),
+            }),
+            EventMsg::AgentReasoningRawContent(AgentReasoningRawContentEvent {
+                text: "first content".into(),
+            }),
+            EventMsg::AgentMessage(AgentMessageEvent {
+                message: "interlude".into(),
+            }),
+            EventMsg::AgentReasoning(AgentReasoningEvent {
+                text: "second summary".into(),
+            }),
+        ];
+
+        let turns = build_turns_from_event_msgs(&events);
+        assert_eq!(turns.len(), 1);
+        let turn = &turns[0];
+        assert_eq!(turn.items.len(), 4);
+
+        assert_eq!(
+            turn.items[1],
+            ThreadItem::Reasoning {
+                id: "item-2".into(),
+                summary: vec!["first summary".into()],
+                content: vec!["first content".into()],
+            }
+        );
+        assert_eq!(
+            turn.items[3],
+            ThreadItem::Reasoning {
+                id: "item-4".into(),
+                summary: vec!["second summary".into()],
+                content: Vec::new(),
+            }
+        );
+    }
+
+    #[test]
+    fn marks_turn_as_interrupted_when_aborted() {
+        let events = vec![
+            EventMsg::UserMessage(UserMessageEvent {
+                message: "Please do the thing".into(),
+                images: None,
+            }),
+            EventMsg::AgentMessage(AgentMessageEvent {
+                message: "Working...".into(),
+            }),
+            EventMsg::TurnAborted(TurnAbortedEvent {
+                reason: TurnAbortReason::Replaced,
+            }),
+            EventMsg::UserMessage(UserMessageEvent {
+                message: "Let's try again".into(),
+                images: None,
+            }),
+            EventMsg::AgentMessage(AgentMessageEvent {
+                message: "Second attempt complete.".into(),
+            }),
+        ];
+
+        let turns = build_turns_from_event_msgs(&events);
+        assert_eq!(turns.len(), 2);
+
+        let first_turn = &turns[0];
+        assert_eq!(first_turn.status, TurnStatus::Interrupted);
+        assert_eq!(first_turn.items.len(), 2);
+        assert_eq!(
+            first_turn.items[0],
+            ThreadItem::UserMessage {
+                id: "item-1".into(),
+                content: vec![UserInput::Text {
+                    text: "Please do the thing".into()
+                }],
+            }
+        );
+        assert_eq!(
+            first_turn.items[1],
+            ThreadItem::AgentMessage {
+                id: "item-2".into(),
+                text: "Working...".into(),
+            }
+        );
+
+        let second_turn = &turns[1];
+        assert_eq!(second_turn.status, TurnStatus::Completed);
+        assert_eq!(second_turn.items.len(), 2);
+        assert_eq!(
+            second_turn.items[0],
+            ThreadItem::UserMessage {
+                id: "item-3".into(),
+                content: vec![UserInput::Text {
+                    text: "Let's try again".into()
+                }],
+            }
+        );
+        assert_eq!(
+            second_turn.items[1],
+            ThreadItem::AgentMessage {
+                id: "item-4".into(),
+                text: "Second attempt complete.".into(),
+            }
+        );
+    }
+}

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

@@ -0,0 +1,461 @@
+use std::collections::HashMap;
+use std::path::PathBuf;
+
+use codex_protocol::ConversationId;
+use codex_protocol::config_types::ForcedLoginMethod;
+use codex_protocol::config_types::ReasoningSummary;
+use codex_protocol::config_types::SandboxMode;
+use codex_protocol::config_types::Verbosity;
+use codex_protocol::models::ResponseItem;
+use codex_protocol::openai_models::ReasoningEffort;
+use codex_protocol::parse_command::ParsedCommand;
+use codex_protocol::protocol::AskForApproval;
+use codex_protocol::protocol::EventMsg;
+use codex_protocol::protocol::FileChange;
+use codex_protocol::protocol::ReviewDecision;
+use codex_protocol::protocol::SandboxPolicy;
+use codex_protocol::protocol::SessionSource;
+use codex_protocol::protocol::TurnAbortReason;
+use codex_utils_absolute_path::AbsolutePathBuf;
+use schemars::JsonSchema;
+use serde::Deserialize;
+use serde::Serialize;
+use ts_rs::TS;
+use uuid::Uuid;
+
+// Reuse shared types defined in `common.rs`.
+use crate::protocol::common::AuthMode;
+use crate::protocol::common::GitSha;
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct InitializeParams {
+    pub client_info: ClientInfo,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ClientInfo {
+    pub name: String,
+    pub title: Option<String>,
+    pub version: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct InitializeResponse {
+    pub user_agent: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct NewConversationParams {
+    pub model: Option<String>,
+    pub model_provider: Option<String>,
+    pub profile: Option<String>,
+    pub cwd: Option<String>,
+    pub approval_policy: Option<AskForApproval>,
+    pub sandbox: Option<SandboxMode>,
+    pub config: Option<HashMap<String, serde_json::Value>>,
+    pub base_instructions: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub developer_instructions: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub compact_prompt: Option<String>,
+    pub include_apply_patch_tool: Option<bool>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct NewConversationResponse {
+    pub conversation_id: ConversationId,
+    pub model: String,
+    pub reasoning_effort: Option<ReasoningEffort>,
+    pub rollout_path: PathBuf,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ResumeConversationResponse {
+    pub conversation_id: ConversationId,
+    pub model: String,
+    pub initial_messages: Option<Vec<EventMsg>>,
+    pub rollout_path: PathBuf,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(untagged)]
+pub enum GetConversationSummaryParams {
+    RolloutPath {
+        #[serde(rename = "rolloutPath")]
+        rollout_path: PathBuf,
+    },
+    ConversationId {
+        #[serde(rename = "conversationId")]
+        conversation_id: ConversationId,
+    },
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GetConversationSummaryResponse {
+    pub summary: ConversationSummary,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ListConversationsParams {
+    pub page_size: Option<usize>,
+    pub cursor: Option<String>,
+    pub model_providers: Option<Vec<String>>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ConversationSummary {
+    pub conversation_id: ConversationId,
+    pub path: PathBuf,
+    pub preview: String,
+    pub timestamp: Option<String>,
+    pub model_provider: String,
+    pub cwd: PathBuf,
+    pub cli_version: String,
+    pub source: SessionSource,
+    pub git_info: Option<ConversationGitInfo>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "snake_case")]
+pub struct ConversationGitInfo {
+    pub sha: Option<String>,
+    pub branch: Option<String>,
+    pub origin_url: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ListConversationsResponse {
+    pub items: Vec<ConversationSummary>,
+    pub next_cursor: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ResumeConversationParams {
+    pub path: Option<PathBuf>,
+    pub conversation_id: Option<ConversationId>,
+    pub history: Option<Vec<ResponseItem>>,
+    pub overrides: Option<NewConversationParams>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct AddConversationSubscriptionResponse {
+    #[schemars(with = "String")]
+    pub subscription_id: Uuid,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ArchiveConversationParams {
+    pub conversation_id: ConversationId,
+    pub rollout_path: PathBuf,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ArchiveConversationResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct RemoveConversationSubscriptionResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct LoginApiKeyParams {
+    pub api_key: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct LoginApiKeyResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct LoginChatGptResponse {
+    #[schemars(with = "String")]
+    pub login_id: Uuid,
+    pub auth_url: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GitDiffToRemoteResponse {
+    pub sha: GitSha,
+    pub diff: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ApplyPatchApprovalParams {
+    pub conversation_id: ConversationId,
+    /// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
+    /// and [codex_core::protocol::PatchApplyEndEvent].
+    pub call_id: String,
+    pub file_changes: HashMap<PathBuf, FileChange>,
+    /// Optional explanatory reason (e.g. request for extra write access).
+    pub reason: Option<String>,
+    /// When set, the agent is asking the user to allow writes under this root
+    /// for the remainder of the session (unclear if this is honored today).
+    pub grant_root: Option<PathBuf>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ApplyPatchApprovalResponse {
+    pub decision: ReviewDecision,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ExecCommandApprovalParams {
+    pub conversation_id: ConversationId,
+    /// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
+    /// and [codex_core::protocol::ExecCommandEndEvent].
+    pub call_id: String,
+    pub command: Vec<String>,
+    pub cwd: PathBuf,
+    pub reason: Option<String>,
+    pub parsed_cmd: Vec<ParsedCommand>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+pub struct ExecCommandApprovalResponse {
+    pub decision: ReviewDecision,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct CancelLoginChatGptParams {
+    #[schemars(with = "String")]
+    pub login_id: Uuid,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GitDiffToRemoteParams {
+    pub cwd: PathBuf,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct CancelLoginChatGptResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct LogoutChatGptParams {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct LogoutChatGptResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GetAuthStatusParams {
+    pub include_token: Option<bool>,
+    pub refresh_token: Option<bool>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ExecOneOffCommandParams {
+    pub command: Vec<String>,
+    pub timeout_ms: Option<u64>,
+    pub cwd: Option<PathBuf>,
+    pub sandbox_policy: Option<SandboxPolicy>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ExecOneOffCommandResponse {
+    pub exit_code: i32,
+    pub stdout: String,
+    pub stderr: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GetAuthStatusResponse {
+    pub auth_method: Option<AuthMode>,
+    pub auth_token: Option<String>,
+    pub requires_openai_auth: Option<bool>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GetUserAgentResponse {
+    pub user_agent: String,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct UserInfoResponse {
+    pub alleged_user_email: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct GetUserSavedConfigResponse {
+    pub config: UserSavedConfig,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SetDefaultModelParams {
+    pub model: Option<String>,
+    pub reasoning_effort: Option<ReasoningEffort>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SetDefaultModelResponse {}
+
+#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct UserSavedConfig {
+    pub approval_policy: Option<AskForApproval>,
+    pub sandbox_mode: Option<SandboxMode>,
+    pub sandbox_settings: Option<SandboxSettings>,
+    pub forced_chatgpt_workspace_id: Option<String>,
+    pub forced_login_method: Option<ForcedLoginMethod>,
+    pub model: Option<String>,
+    pub model_reasoning_effort: Option<ReasoningEffort>,
+    pub model_reasoning_summary: Option<ReasoningSummary>,
+    pub model_verbosity: Option<Verbosity>,
+    pub tools: Option<Tools>,
+    pub profile: Option<String>,
+    pub profiles: HashMap<String, Profile>,
+}
+
+#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct Profile {
+    pub model: Option<String>,
+    pub model_provider: Option<String>,
+    pub approval_policy: Option<AskForApproval>,
+    pub model_reasoning_effort: Option<ReasoningEffort>,
+    pub model_reasoning_summary: Option<ReasoningSummary>,
+    pub model_verbosity: Option<Verbosity>,
+    pub chatgpt_base_url: Option<String>,
+}
+
+#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct Tools {
+    pub web_search: Option<bool>,
+    pub view_image: Option<bool>,
+}
+
+#[derive(Deserialize, Debug, Clone, PartialEq, Serialize, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SandboxSettings {
+    #[serde(default)]
+    pub writable_roots: Vec<AbsolutePathBuf>,
+    pub network_access: Option<bool>,
+    pub exclude_tmpdir_env_var: Option<bool>,
+    pub exclude_slash_tmp: Option<bool>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SendUserMessageParams {
+    pub conversation_id: ConversationId,
+    pub items: Vec<InputItem>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SendUserTurnParams {
+    pub conversation_id: ConversationId,
+    pub items: Vec<InputItem>,
+    pub cwd: PathBuf,
+    pub approval_policy: AskForApproval,
+    pub sandbox_policy: SandboxPolicy,
+    pub model: String,
+    pub effort: Option<ReasoningEffort>,
+    pub summary: ReasoningSummary,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SendUserTurnResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct InterruptConversationParams {
+    pub conversation_id: ConversationId,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct InterruptConversationResponse {
+    pub abort_reason: TurnAbortReason,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SendUserMessageResponse {}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct AddConversationListenerParams {
+    pub conversation_id: ConversationId,
+    #[serde(default)]
+    pub experimental_raw_events: bool,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct RemoveConversationListenerParams {
+    #[schemars(with = "String")]
+    pub subscription_id: Uuid,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[serde(tag = "type", content = "data")]
+pub enum InputItem {
+    Text { text: String },
+    Image { image_url: String },
+    LocalImage { path: PathBuf },
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+/// Deprecated in favor of AccountLoginCompletedNotification.
+pub struct LoginChatGptCompleteNotification {
+    #[schemars(with = "String")]
+    pub login_id: Uuid,
+    pub success: bool,
+    pub error: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct SessionConfiguredNotification {
+    pub session_id: ConversationId,
+    pub model: String,
+    pub reasoning_effort: Option<ReasoningEffort>,
+    pub history_log_id: u64,
+    #[ts(type = "number")]
+    pub history_entry_count: usize,
+    pub initial_messages: Option<Vec<EventMsg>>,
+    pub rollout_path: PathBuf,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+/// Deprecated notification. Use AccountUpdatedNotification instead.
+pub struct AuthStatusChangeNotification {
+    pub auth_method: Option<AuthMode>,
+}

codex-rs/app-server-test-client/Cargo.toml

@@ -0,0 +1,17 @@
+[package]
+name = "codex-app-server-test-client"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[lints]
+workspace = true
+
+[dependencies]
+anyhow = { workspace = true }
+clap = { workspace = true, features = ["derive", "env"] }
+codex-app-server-protocol = { workspace = true }
+codex-protocol = { workspace = true }
+serde = { workspace = true, features = ["derive"] }
+serde_json = { workspace = true }
+uuid = { workspace = true, features = ["v4"] }

codex-rs/app-server-test-client/README.md

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

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

@@ -0,0 +1,864 @@
+use std::collections::VecDeque;
+use std::io::BufRead;
+use std::io::BufReader;
+use std::io::Write;
+use std::process::Child;
+use std::process::ChildStdin;
+use std::process::ChildStdout;
+use std::process::Command;
+use std::process::Stdio;
+use std::thread;
+use std::time::Duration;
+
+use anyhow::Context;
+use anyhow::Result;
+use anyhow::bail;
+use clap::Parser;
+use clap::Subcommand;
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::AddConversationSubscriptionResponse;
+use codex_app_server_protocol::ApprovalDecision;
+use codex_app_server_protocol::AskForApproval;
+use codex_app_server_protocol::ClientInfo;
+use codex_app_server_protocol::ClientRequest;
+use codex_app_server_protocol::CommandExecutionRequestApprovalParams;
+use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
+use codex_app_server_protocol::FileChangeRequestApprovalParams;
+use codex_app_server_protocol::FileChangeRequestApprovalResponse;
+use codex_app_server_protocol::GetAccountRateLimitsResponse;
+use codex_app_server_protocol::InitializeParams;
+use codex_app_server_protocol::InitializeResponse;
+use codex_app_server_protocol::InputItem;
+use codex_app_server_protocol::JSONRPCMessage;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCRequest;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::LoginChatGptCompleteNotification;
+use codex_app_server_protocol::LoginChatGptResponse;
+use codex_app_server_protocol::NewConversationParams;
+use codex_app_server_protocol::NewConversationResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SandboxPolicy;
+use codex_app_server_protocol::SendUserMessageParams;
+use codex_app_server_protocol::SendUserMessageResponse;
+use codex_app_server_protocol::ServerNotification;
+use codex_app_server_protocol::ServerRequest;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnStartParams;
+use codex_app_server_protocol::TurnStartResponse;
+use codex_app_server_protocol::TurnStatus;
+use codex_app_server_protocol::UserInput as V2UserInput;
+use codex_protocol::ConversationId;
+use codex_protocol::protocol::Event;
+use codex_protocol::protocol::EventMsg;
+use serde::Serialize;
+use serde::de::DeserializeOwned;
+use serde_json::Value;
+use uuid::Uuid;
+
+/// Minimal launcher that initializes the Codex app-server and logs the handshake.
+#[derive(Parser)]
+#[command(author = "Codex", version, about = "Bootstrap Codex app-server", long_about = None)]
+struct Cli {
+    /// Path to the `codex` CLI binary.
+    #[arg(long, env = "CODEX_BIN", default_value = "codex")]
+    codex_bin: String,
+
+    #[command(subcommand)]
+    command: CliCommand,
+}
+
+#[derive(Subcommand)]
+enum CliCommand {
+    /// Send a user message through the Codex app-server.
+    SendMessage {
+        /// User message to send to Codex.
+        #[arg()]
+        user_message: String,
+    },
+    /// Send a user message through the app-server V2 thread/turn APIs.
+    SendMessageV2 {
+        /// User message to send to Codex.
+        #[arg()]
+        user_message: String,
+    },
+    /// Start a V2 turn that elicits an ExecCommand approval.
+    #[command(name = "trigger-cmd-approval")]
+    TriggerCmdApproval {
+        /// Optional prompt; defaults to a simple python command.
+        #[arg()]
+        user_message: Option<String>,
+    },
+    /// Start a V2 turn that elicits an ApplyPatch approval.
+    #[command(name = "trigger-patch-approval")]
+    TriggerPatchApproval {
+        /// Optional prompt; defaults to creating a file via apply_patch.
+        #[arg()]
+        user_message: Option<String>,
+    },
+    /// Start a V2 turn that should not elicit an ExecCommand approval.
+    #[command(name = "no-trigger-cmd-approval")]
+    NoTriggerCmdApproval,
+    /// Send two sequential V2 turns in the same thread to test follow-up behavior.
+    SendFollowUpV2 {
+        /// Initial user message for the first turn.
+        #[arg()]
+        first_message: String,
+        /// Follow-up user message for the second turn.
+        #[arg()]
+        follow_up_message: String,
+    },
+    /// Trigger the ChatGPT login flow and wait for completion.
+    TestLogin,
+    /// Fetch the current account rate limits from the Codex app-server.
+    GetAccountRateLimits,
+}
+
+fn main() -> Result<()> {
+    let Cli { codex_bin, command } = Cli::parse();
+
+    match command {
+        CliCommand::SendMessage { user_message } => send_message(codex_bin, user_message),
+        CliCommand::SendMessageV2 { user_message } => send_message_v2(codex_bin, user_message),
+        CliCommand::TriggerCmdApproval { user_message } => {
+            trigger_cmd_approval(codex_bin, user_message)
+        }
+        CliCommand::TriggerPatchApproval { user_message } => {
+            trigger_patch_approval(codex_bin, user_message)
+        }
+        CliCommand::NoTriggerCmdApproval => no_trigger_cmd_approval(codex_bin),
+        CliCommand::SendFollowUpV2 {
+            first_message,
+            follow_up_message,
+        } => send_follow_up_v2(codex_bin, first_message, follow_up_message),
+        CliCommand::TestLogin => test_login(codex_bin),
+        CliCommand::GetAccountRateLimits => get_account_rate_limits(codex_bin),
+    }
+}
+
+fn send_message(codex_bin: String, user_message: String) -> Result<()> {
+    let mut client = CodexClient::spawn(codex_bin)?;
+
+    let initialize = client.initialize()?;
+    println!("< initialize response: {initialize:?}");
+
+    let conversation = client.new_conversation()?;
+    println!("< newConversation response: {conversation:?}");
+
+    let subscription = client.add_conversation_listener(&conversation.conversation_id)?;
+    println!("< addConversationListener response: {subscription:?}");
+
+    let send_response = client.send_user_message(&conversation.conversation_id, &user_message)?;
+    println!("< sendUserMessage response: {send_response:?}");
+
+    client.stream_conversation(&conversation.conversation_id)?;
+
+    client.remove_conversation_listener(subscription.subscription_id)?;
+
+    Ok(())
+}
+
+fn send_message_v2(codex_bin: String, user_message: String) -> Result<()> {
+    send_message_v2_with_policies(codex_bin, user_message, None, None)
+}
+
+fn trigger_cmd_approval(codex_bin: String, user_message: Option<String>) -> Result<()> {
+    let default_prompt =
+        "Run `touch /tmp/should-trigger-approval` so I can confirm the file exists.";
+    let message = user_message.unwrap_or_else(|| default_prompt.to_string());
+    send_message_v2_with_policies(
+        codex_bin,
+        message,
+        Some(AskForApproval::OnRequest),
+        Some(SandboxPolicy::ReadOnly),
+    )
+}
+
+fn trigger_patch_approval(codex_bin: String, user_message: Option<String>) -> Result<()> {
+    let default_prompt =
+        "Create a file named APPROVAL_DEMO.txt containing a short hello message using apply_patch.";
+    let message = user_message.unwrap_or_else(|| default_prompt.to_string());
+    send_message_v2_with_policies(
+        codex_bin,
+        message,
+        Some(AskForApproval::OnRequest),
+        Some(SandboxPolicy::ReadOnly),
+    )
+}
+
+fn no_trigger_cmd_approval(codex_bin: String) -> Result<()> {
+    let prompt = "Run `touch should_not_trigger_approval.txt`";
+    send_message_v2_with_policies(codex_bin, prompt.to_string(), None, None)
+}
+
+fn send_message_v2_with_policies(
+    codex_bin: String,
+    user_message: String,
+    approval_policy: Option<AskForApproval>,
+    sandbox_policy: Option<SandboxPolicy>,
+) -> Result<()> {
+    let mut client = CodexClient::spawn(codex_bin)?;
+
+    let initialize = client.initialize()?;
+    println!("< initialize response: {initialize:?}");
+
+    let thread_response = client.thread_start(ThreadStartParams::default())?;
+    println!("< thread/start response: {thread_response:?}");
+    let mut turn_params = TurnStartParams {
+        thread_id: thread_response.thread.id.clone(),
+        input: vec![V2UserInput::Text { text: user_message }],
+        ..Default::default()
+    };
+    turn_params.approval_policy = approval_policy;
+    turn_params.sandbox_policy = sandbox_policy;
+
+    let turn_response = client.turn_start(turn_params)?;
+    println!("< turn/start response: {turn_response:?}");
+
+    client.stream_turn(&thread_response.thread.id, &turn_response.turn.id)?;
+
+    Ok(())
+}
+
+fn send_follow_up_v2(
+    codex_bin: String,
+    first_message: String,
+    follow_up_message: String,
+) -> Result<()> {
+    let mut client = CodexClient::spawn(codex_bin)?;
+
+    let initialize = client.initialize()?;
+    println!("< initialize response: {initialize:?}");
+
+    let thread_response = client.thread_start(ThreadStartParams::default())?;
+    println!("< thread/start response: {thread_response:?}");
+
+    let first_turn_params = TurnStartParams {
+        thread_id: thread_response.thread.id.clone(),
+        input: vec![V2UserInput::Text {
+            text: first_message,
+        }],
+        ..Default::default()
+    };
+    let first_turn_response = client.turn_start(first_turn_params)?;
+    println!("< turn/start response (initial): {first_turn_response:?}");
+    client.stream_turn(&thread_response.thread.id, &first_turn_response.turn.id)?;
+
+    let follow_up_params = TurnStartParams {
+        thread_id: thread_response.thread.id.clone(),
+        input: vec![V2UserInput::Text {
+            text: follow_up_message,
+        }],
+        ..Default::default()
+    };
+    let follow_up_response = client.turn_start(follow_up_params)?;
+    println!("< turn/start response (follow-up): {follow_up_response:?}");
+    client.stream_turn(&thread_response.thread.id, &follow_up_response.turn.id)?;
+
+    Ok(())
+}
+
+fn test_login(codex_bin: String) -> Result<()> {
+    let mut client = CodexClient::spawn(codex_bin)?;
+
+    let initialize = client.initialize()?;
+    println!("< initialize response: {initialize:?}");
+
+    let login_response = client.login_chat_gpt()?;
+    println!("< loginChatGpt response: {login_response:?}");
+    println!(
+        "Open the following URL in your browser to continue:\n{}",
+        login_response.auth_url
+    );
+
+    let completion = client.wait_for_login_completion(&login_response.login_id)?;
+    println!("< loginChatGptComplete notification: {completion:?}");
+
+    if completion.success {
+        println!("Login succeeded.");
+        Ok(())
+    } else {
+        bail!(
+            "login failed: {}",
+            completion
+                .error
+                .as_deref()
+                .unwrap_or("unknown error from loginChatGptComplete")
+        );
+    }
+}
+
+fn get_account_rate_limits(codex_bin: String) -> Result<()> {
+    let mut client = CodexClient::spawn(codex_bin)?;
+
+    let initialize = client.initialize()?;
+    println!("< initialize response: {initialize:?}");
+
+    let response = client.get_account_rate_limits()?;
+    println!("< account/rateLimits/read response: {response:?}");
+
+    Ok(())
+}
+
+struct CodexClient {
+    child: Child,
+    stdin: Option<ChildStdin>,
+    stdout: BufReader<ChildStdout>,
+    pending_notifications: VecDeque<JSONRPCNotification>,
+}
+
+impl CodexClient {
+    fn spawn(codex_bin: String) -> Result<Self> {
+        let mut codex_app_server = Command::new(&codex_bin)
+            .arg("app-server")
+            .stdin(Stdio::piped())
+            .stdout(Stdio::piped())
+            .stderr(Stdio::inherit())
+            .spawn()
+            .with_context(|| format!("failed to start `{codex_bin}` app-server"))?;
+
+        let stdin = codex_app_server
+            .stdin
+            .take()
+            .context("codex app-server stdin unavailable")?;
+        let stdout = codex_app_server
+            .stdout
+            .take()
+            .context("codex app-server stdout unavailable")?;
+
+        Ok(Self {
+            child: codex_app_server,
+            stdin: Some(stdin),
+            stdout: BufReader::new(stdout),
+            pending_notifications: VecDeque::new(),
+        })
+    }
+
+    fn initialize(&mut self) -> Result<InitializeResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::Initialize {
+            request_id: request_id.clone(),
+            params: InitializeParams {
+                client_info: ClientInfo {
+                    name: "codex-toy-app-server".to_string(),
+                    title: Some("Codex Toy App Server".to_string()),
+                    version: env!("CARGO_PKG_VERSION").to_string(),
+                },
+            },
+        };
+
+        self.send_request(request, request_id, "initialize")
+    }
+
+    fn new_conversation(&mut self) -> Result<NewConversationResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::NewConversation {
+            request_id: request_id.clone(),
+            params: NewConversationParams::default(),
+        };
+
+        self.send_request(request, request_id, "newConversation")
+    }
+
+    fn add_conversation_listener(
+        &mut self,
+        conversation_id: &ConversationId,
+    ) -> Result<AddConversationSubscriptionResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::AddConversationListener {
+            request_id: request_id.clone(),
+            params: AddConversationListenerParams {
+                conversation_id: *conversation_id,
+                experimental_raw_events: false,
+            },
+        };
+
+        self.send_request(request, request_id, "addConversationListener")
+    }
+
+    fn remove_conversation_listener(&mut self, subscription_id: Uuid) -> Result<()> {
+        let request_id = self.request_id();
+        let request = ClientRequest::RemoveConversationListener {
+            request_id: request_id.clone(),
+            params: codex_app_server_protocol::RemoveConversationListenerParams { subscription_id },
+        };
+
+        self.send_request::<codex_app_server_protocol::RemoveConversationSubscriptionResponse>(
+            request,
+            request_id,
+            "removeConversationListener",
+        )?;
+
+        Ok(())
+    }
+
+    fn send_user_message(
+        &mut self,
+        conversation_id: &ConversationId,
+        message: &str,
+    ) -> Result<SendUserMessageResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::SendUserMessage {
+            request_id: request_id.clone(),
+            params: SendUserMessageParams {
+                conversation_id: *conversation_id,
+                items: vec![InputItem::Text {
+                    text: message.to_string(),
+                }],
+            },
+        };
+
+        self.send_request(request, request_id, "sendUserMessage")
+    }
+
+    fn thread_start(&mut self, params: ThreadStartParams) -> Result<ThreadStartResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::ThreadStart {
+            request_id: request_id.clone(),
+            params,
+        };
+
+        self.send_request(request, request_id, "thread/start")
+    }
+
+    fn turn_start(&mut self, params: TurnStartParams) -> Result<TurnStartResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::TurnStart {
+            request_id: request_id.clone(),
+            params,
+        };
+
+        self.send_request(request, request_id, "turn/start")
+    }
+
+    fn login_chat_gpt(&mut self) -> Result<LoginChatGptResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::LoginChatGpt {
+            request_id: request_id.clone(),
+            params: None,
+        };
+
+        self.send_request(request, request_id, "loginChatGpt")
+    }
+
+    fn get_account_rate_limits(&mut self) -> Result<GetAccountRateLimitsResponse> {
+        let request_id = self.request_id();
+        let request = ClientRequest::GetAccountRateLimits {
+            request_id: request_id.clone(),
+            params: None,
+        };
+
+        self.send_request(request, request_id, "account/rateLimits/read")
+    }
+
+    fn stream_conversation(&mut self, conversation_id: &ConversationId) -> Result<()> {
+        loop {
+            let notification = self.next_notification()?;
+
+            if !notification.method.starts_with("codex/event/") {
+                continue;
+            }
+
+            if let Some(event) = self.extract_event(notification, conversation_id)? {
+                match &event.msg {
+                    EventMsg::AgentMessage(event) => {
+                        println!("{}", event.message);
+                    }
+                    EventMsg::AgentMessageDelta(event) => {
+                        print!("{}", event.delta);
+                        std::io::stdout().flush().ok();
+                    }
+                    EventMsg::TaskComplete(event) => {
+                        println!("\n[task complete: {event:?}]");
+                        break;
+                    }
+                    EventMsg::TurnAborted(event) => {
+                        println!("\n[turn aborted: {:?}]", event.reason);
+                        break;
+                    }
+                    EventMsg::Error(event) => {
+                        println!("[error] {event:?}");
+                    }
+                    _ => {
+                        println!("[UNKNOWN EVENT] {:?}", event.msg);
+                    }
+                }
+            }
+        }
+
+        Ok(())
+    }
+
+    fn wait_for_login_completion(
+        &mut self,
+        expected_login_id: &Uuid,
+    ) -> Result<LoginChatGptCompleteNotification> {
+        loop {
+            let notification = self.next_notification()?;
+
+            if let Ok(server_notification) = ServerNotification::try_from(notification) {
+                match server_notification {
+                    ServerNotification::LoginChatGptComplete(completion) => {
+                        if &completion.login_id == expected_login_id {
+                            return Ok(completion);
+                        }
+
+                        println!(
+                            "[ignoring loginChatGptComplete for unexpected login_id: {}]",
+                            completion.login_id
+                        );
+                    }
+                    ServerNotification::AuthStatusChange(status) => {
+                        println!("< authStatusChange notification: {status:?}");
+                    }
+                    ServerNotification::AccountRateLimitsUpdated(snapshot) => {
+                        println!("< accountRateLimitsUpdated notification: {snapshot:?}");
+                    }
+                    ServerNotification::SessionConfigured(_) => {
+                        // SessionConfigured notifications are unrelated to login; skip.
+                    }
+                    _ => {}
+                }
+            }
+
+            // Not a server notification (likely a conversation event); keep waiting.
+        }
+    }
+
+    fn stream_turn(&mut self, thread_id: &str, turn_id: &str) -> Result<()> {
+        loop {
+            let notification = self.next_notification()?;
+
+            let Ok(server_notification) = ServerNotification::try_from(notification) else {
+                continue;
+            };
+
+            match server_notification {
+                ServerNotification::ThreadStarted(payload) => {
+                    if payload.thread.id == thread_id {
+                        println!("< thread/started notification: {:?}", payload.thread);
+                    }
+                }
+                ServerNotification::TurnStarted(payload) => {
+                    if payload.turn.id == turn_id {
+                        println!("< turn/started notification: {:?}", payload.turn.status);
+                    }
+                }
+                ServerNotification::AgentMessageDelta(delta) => {
+                    print!("{}", delta.delta);
+                    std::io::stdout().flush().ok();
+                }
+                ServerNotification::CommandExecutionOutputDelta(delta) => {
+                    print!("{}", delta.delta);
+                    std::io::stdout().flush().ok();
+                }
+                ServerNotification::TerminalInteraction(delta) => {
+                    println!("[stdin sent: {}]", delta.stdin);
+                    std::io::stdout().flush().ok();
+                }
+                ServerNotification::ItemStarted(payload) => {
+                    println!("\n< item started: {:?}", payload.item);
+                }
+                ServerNotification::ItemCompleted(payload) => {
+                    println!("< item completed: {:?}", payload.item);
+                }
+                ServerNotification::TurnCompleted(payload) => {
+                    if payload.turn.id == turn_id {
+                        println!("\n< turn/completed notification: {:?}", payload.turn.status);
+                        if payload.turn.status == TurnStatus::Failed
+                            && let Some(error) = payload.turn.error
+                        {
+                            println!("[turn error] {}", error.message);
+                        }
+                        break;
+                    }
+                }
+                ServerNotification::McpToolCallProgress(payload) => {
+                    println!("< MCP tool progress: {}", payload.message);
+                }
+                _ => {
+                    println!("[UNKNOWN SERVER NOTIFICATION] {server_notification:?}");
+                }
+            }
+        }
+
+        Ok(())
+    }
+
+    fn extract_event(
+        &self,
+        notification: JSONRPCNotification,
+        conversation_id: &ConversationId,
+    ) -> Result<Option<Event>> {
+        let params = notification
+            .params
+            .context("event notification missing params")?;
+
+        let mut map = match params {
+            Value::Object(map) => map,
+            other => bail!("unexpected params shape: {other:?}"),
+        };
+
+        let conversation_value = map
+            .remove("conversationId")
+            .context("event missing conversationId")?;
+        let notification_conversation: ConversationId = serde_json::from_value(conversation_value)
+            .context("conversationId was not a valid UUID")?;
+
+        if &notification_conversation != conversation_id {
+            return Ok(None);
+        }
+
+        let event_value = Value::Object(map);
+        let event: Event =
+            serde_json::from_value(event_value).context("failed to decode event payload")?;
+        Ok(Some(event))
+    }
+
+    fn send_request<T>(
+        &mut self,
+        request: ClientRequest,
+        request_id: RequestId,
+        method: &str,
+    ) -> Result<T>
+    where
+        T: DeserializeOwned,
+    {
+        self.write_request(&request)?;
+        self.wait_for_response(request_id, method)
+    }
+
+    fn write_request(&mut self, request: &ClientRequest) -> Result<()> {
+        let request_json = serde_json::to_string(request)?;
+        let request_pretty = serde_json::to_string_pretty(request)?;
+        print_multiline_with_prefix("> ", &request_pretty);
+
+        if let Some(stdin) = self.stdin.as_mut() {
+            writeln!(stdin, "{request_json}")?;
+            stdin
+                .flush()
+                .context("failed to flush request to codex app-server")?;
+        } else {
+            bail!("codex app-server stdin closed");
+        }
+
+        Ok(())
+    }
+
+    fn wait_for_response<T>(&mut self, request_id: RequestId, method: &str) -> Result<T>
+    where
+        T: DeserializeOwned,
+    {
+        loop {
+            let message = self.read_jsonrpc_message()?;
+
+            match message {
+                JSONRPCMessage::Response(JSONRPCResponse { id, result }) => {
+                    if id == request_id {
+                        return serde_json::from_value(result)
+                            .with_context(|| format!("{method} response missing payload"));
+                    }
+                }
+                JSONRPCMessage::Error(err) => {
+                    if err.id == request_id {
+                        bail!("{method} failed: {err:?}");
+                    }
+                }
+                JSONRPCMessage::Notification(notification) => {
+                    self.pending_notifications.push_back(notification);
+                }
+                JSONRPCMessage::Request(request) => {
+                    self.handle_server_request(request)?;
+                }
+            }
+        }
+    }
+
+    fn next_notification(&mut self) -> Result<JSONRPCNotification> {
+        if let Some(notification) = self.pending_notifications.pop_front() {
+            return Ok(notification);
+        }
+
+        loop {
+            let message = self.read_jsonrpc_message()?;
+
+            match message {
+                JSONRPCMessage::Notification(notification) => return Ok(notification),
+                JSONRPCMessage::Response(_) | JSONRPCMessage::Error(_) => {
+                    // No outstanding requests, so ignore stray responses/errors for now.
+                    continue;
+                }
+                JSONRPCMessage::Request(request) => {
+                    self.handle_server_request(request)?;
+                }
+            }
+        }
+    }
+
+    fn read_jsonrpc_message(&mut self) -> Result<JSONRPCMessage> {
+        loop {
+            let mut response_line = String::new();
+            let bytes = self
+                .stdout
+                .read_line(&mut response_line)
+                .context("failed to read from codex app-server")?;
+
+            if bytes == 0 {
+                bail!("codex app-server closed stdout");
+            }
+
+            let trimmed = response_line.trim();
+            if trimmed.is_empty() {
+                continue;
+            }
+
+            let parsed: Value =
+                serde_json::from_str(trimmed).context("response was not valid JSON-RPC")?;
+            let pretty = serde_json::to_string_pretty(&parsed)?;
+            print_multiline_with_prefix("< ", &pretty);
+            let message: JSONRPCMessage = serde_json::from_value(parsed)
+                .context("response was not a valid JSON-RPC message")?;
+            return Ok(message);
+        }
+    }
+
+    fn request_id(&self) -> RequestId {
+        RequestId::String(Uuid::new_v4().to_string())
+    }
+
+    fn handle_server_request(&mut self, request: JSONRPCRequest) -> Result<()> {
+        let server_request = ServerRequest::try_from(request)
+            .context("failed to deserialize ServerRequest from JSONRPCRequest")?;
+
+        match server_request {
+            ServerRequest::CommandExecutionRequestApproval { request_id, params } => {
+                self.handle_command_execution_request_approval(request_id, params)?;
+            }
+            ServerRequest::FileChangeRequestApproval { request_id, params } => {
+                self.approve_file_change_request(request_id, params)?;
+            }
+            other => {
+                bail!("received unsupported server request: {other:?}");
+            }
+        }
+
+        Ok(())
+    }
+
+    fn handle_command_execution_request_approval(
+        &mut self,
+        request_id: RequestId,
+        params: CommandExecutionRequestApprovalParams,
+    ) -> Result<()> {
+        let CommandExecutionRequestApprovalParams {
+            thread_id,
+            turn_id,
+            item_id,
+            reason,
+            proposed_execpolicy_amendment,
+        } = params;
+
+        println!(
+            "\n< commandExecution approval requested for thread {thread_id}, turn {turn_id}, item {item_id}"
+        );
+        if let Some(reason) = reason.as_deref() {
+            println!("< reason: {reason}");
+        }
+        if let Some(execpolicy_amendment) = proposed_execpolicy_amendment.as_ref() {
+            println!("< proposed execpolicy amendment: {execpolicy_amendment:?}");
+        }
+
+        let response = CommandExecutionRequestApprovalResponse {
+            decision: ApprovalDecision::Accept,
+        };
+        self.send_server_request_response(request_id, &response)?;
+        println!("< approved commandExecution request for item {item_id}");
+        Ok(())
+    }
+
+    fn approve_file_change_request(
+        &mut self,
+        request_id: RequestId,
+        params: FileChangeRequestApprovalParams,
+    ) -> Result<()> {
+        let FileChangeRequestApprovalParams {
+            thread_id,
+            turn_id,
+            item_id,
+            reason,
+            grant_root,
+        } = params;
+
+        println!(
+            "\n< fileChange approval requested for thread {thread_id}, turn {turn_id}, item {item_id}"
+        );
+        if let Some(reason) = reason.as_deref() {
+            println!("< reason: {reason}");
+        }
+        if let Some(grant_root) = grant_root.as_deref() {
+            println!("< grant root: {}", grant_root.display());
+        }
+
+        let response = FileChangeRequestApprovalResponse {
+            decision: ApprovalDecision::Accept,
+        };
+        self.send_server_request_response(request_id, &response)?;
+        println!("< approved fileChange request for item {item_id}");
+        Ok(())
+    }
+
+    fn send_server_request_response<T>(&mut self, request_id: RequestId, response: &T) -> Result<()>
+    where
+        T: Serialize,
+    {
+        let message = JSONRPCMessage::Response(JSONRPCResponse {
+            id: request_id,
+            result: serde_json::to_value(response)?,
+        });
+        self.write_jsonrpc_message(message)
+    }
+
+    fn write_jsonrpc_message(&mut self, message: JSONRPCMessage) -> Result<()> {
+        let payload = serde_json::to_string(&message)?;
+        let pretty = serde_json::to_string_pretty(&message)?;
+        print_multiline_with_prefix("> ", &pretty);
+
+        if let Some(stdin) = self.stdin.as_mut() {
+            writeln!(stdin, "{payload}")?;
+            stdin
+                .flush()
+                .context("failed to flush response to codex app-server")?;
+            return Ok(());
+        }
+
+        bail!("codex app-server stdin closed")
+    }
+}
+
+fn print_multiline_with_prefix(prefix: &str, payload: &str) {
+    for line in payload.lines() {
+        println!("{prefix}{line}");
+    }
+}
+
+impl Drop for CodexClient {
+    fn drop(&mut self) {
+        let _ = self.stdin.take();
+
+        if let Ok(Some(status)) = self.child.try_wait() {
+            println!("[codex app-server exited: {status}]");
+            return;
+        }
+
+        thread::sleep(Duration::from_millis(100));
+
+        if let Ok(Some(status)) = self.child.try_wait() {
+            println!("[codex app-server exited: {status}]");
+            return;
+        }
+
+        let _ = self.child.kill();
+        let _ = self.child.wait();
+    }
+}

codex-rs/app-server/Cargo.toml

@@ -1,7 +1,8 @@
 [package]
-edition = "2024"
 name = "codex-app-server"
-version = { workspace = true }
+version.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [[bin]]
 name = "codex-app-server"
@@ -19,13 +20,20 @@ anyhow = { workspace = true }
 codex-arg0 = { workspace = true }
 codex-common = { workspace = true, features = ["cli"] }
 codex-core = { workspace = true }
+codex-backend-client = { workspace = true }
 codex-file-search = { workspace = true }
 codex-login = { workspace = true }
 codex-protocol = { workspace = true }
 codex-app-server-protocol = { workspace = true }
+codex-feedback = { workspace = true }
+codex-rmcp-client = { workspace = true }
 codex-utils-json-to-toml = { workspace = true }
+chrono = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
+mcp-types = { workspace = true }
+tempfile = { workspace = true }
+toml = { workspace = true }
 tokio = { workspace = true, features = [
     "io-std",
     "macros",
@@ -42,8 +50,9 @@ app_test_support = { workspace = true }
 assert_cmd = { workspace = true }
 base64 = { workspace = true }
 core_test_support = { workspace = true }
+mcp-types = { workspace = true }
 os_info = { workspace = true }
 pretty_assertions = { workspace = true }
-tempfile = { workspace = true }
-toml = { workspace = true }
+serial_test = { workspace = true }
 wiremock = { workspace = true }
+shlex = { workspace = true }

codex-rs/app-server/README.md

@@ -1,6 +1,16 @@
 # codex-app-server
 
-`codex app-server` is the harness Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt). The message schema is currently unstable, but those who wish to build experimental UIs on top of Codex may find it valuable.
+`codex app-server` is the interface Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt).
+
+## Table of Contents
+- [Protocol](#protocol)
+- [Message Schema](#message-schema)
+- [Core Primitives](#core-primitives)
+- [Lifecycle Overview](#lifecycle-overview)
+- [Initialization](#initialization)
+- [API Overview](#api-overview)
+- [Events](#events)
+- [Auth endpoints](#auth-endpoints)
 
 ## Protocol
 
@@ -8,8 +18,433 @@ Similar to [MCP](https://modelcontextprotocol.io/), `codex app-server` supports
 
 ## Message Schema
 
-Currently, you can dump a TypeScript version of the schema using `codex generate-ts`. It is specific to the version of Codex you used to run `generate-ts`, so the two are guaranteed to be compatible.
+Currently, you can dump a TypeScript version of the schema using `codex app-server generate-ts`, or a JSON Schema bundle via `codex app-server generate-json-schema`. Each output is specific to the version of Codex you used to run the command, so the generated artifacts are guaranteed to match that version.
 
 ```
-codex generate-ts --out DIR
+codex app-server generate-ts --out DIR
+codex app-server generate-json-schema --out DIR
 ```
+
+## Core Primitives
+
+The API exposes three top level primitives representing an interaction between a user and Codex:
+- **Thread**: A conversation between a user and the Codex agent. Each thread contains multiple turns.
+- **Turn**: One turn of the conversation, typically starting with a user message and finishing with an agent message. Each turn contains multiple items.
+- **Item**: Represents user inputs and agent outputs as part of the turn, persisted and used as the context for future conversations. Example items include user message, agent reasoning, agent message, shell command, file edit, etc.
+
+Use the thread APIs to create, list, or archive conversations. Drive a conversation with turn APIs and stream progress via turn notifications.
+
+## Lifecycle Overview
+
+- Initialize once: Immediately after launching the codex app-server process, send an `initialize` request with your client metadata, then emit an `initialized` notification. Any other request before this handshake gets rejected.
+- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead.
+- Begin a turn: To send user input, call `turn/start` with the target `threadId` and the user's input. Optional fields let you override model, cwd, sandbox policy, etc. This immediately returns the new turn object and triggers a `turn/started` notification.
+- Stream events: After `turn/start`, keep reading JSON-RPC notifications on stdout. You’ll see `item/started`, `item/completed`, deltas like `item/agentMessage/delta`, tool progress, etc. These represent streaming model output plus any side effects (commands, tool calls, reasoning notes).
+- Finish the turn: When the model is done (or the turn is interrupted via making the `turn/interrupt` call), the server sends `turn/completed` with the final turn state and token usage.
+
+## Initialization
+
+Clients must send a single `initialize` request before invoking any other method, then acknowledge with an `initialized` notification. The server returns the user agent string it will present to upstream services; subsequent requests issued before initialization receive a `"Not initialized"` error, and repeated `initialize` calls receive an `"Already initialized"` error.
+
+Applications building on top of `codex app-server` should identify themselves via the `clientInfo` parameter.
+
+Example (from OpenAI's official VSCode extension):
+```json
+{ "method": "initialize", "id": 0, "params": {
+    "clientInfo": { "name": "codex-vscode", "title": "Codex VS Code Extension", "version": "0.1.0" }
+} }
+```
+
+## API Overview
+- `thread/start` — create a new thread; emits `thread/started` and auto-subscribes you to turn/item events for that thread.
+- `thread/resume` — reopen an existing thread by id so subsequent `turn/start` calls append to it.
+- `thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
+- `thread/archive` — move a thread’s rollout file into the archived directory; returns `{}` on success.
+- `turn/start` — add user input to a thread and begin Codex generation; responds with the initial `turn` object and streams `turn/started`, `item/*`, and `turn/completed` notifications.
+- `turn/interrupt` — request cancellation of an in-flight turn by `(thread_id, turn_id)`; success is an empty `{}` response and the turn finishes with `status: "interrupted"`.
+- `review/start` — kick off 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).
+- `skills/list` — list skills for one or more `cwd` values.
+- `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.
+- `mcpServers/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.
+
+### Example: Start or resume a thread
+
+Start a fresh thread when you need a new Codex conversation.
+
+```json
+{ "method": "thread/start", "id": 10, "params": {
+    // Optionally set config settings. If not specified, will use the user's
+    // current config settings.
+    "model": "gpt-5.1-codex",
+    "cwd": "/Users/me/project",
+    "approvalPolicy": "never",
+    "sandbox": "workspaceWrite",
+} }
+{ "id": 10, "result": {
+    "thread": {
+        "id": "thr_123",
+        "preview": "",
+        "modelProvider": "openai",
+        "createdAt": 1730910000
+    }
+} }
+{ "method": "thread/started", "params": { "thread": { … } } }
+```
+
+To continue a stored session, call `thread/resume` with the `thread.id` you previously recorded. The response shape matches `thread/start`, and no additional notifications are emitted:
+
+```json
+{ "method": "thread/resume", "id": 11, "params": { "threadId": "thr_123" } }
+{ "id": 11, "result": { "thread": { "id": "thr_123", … } } }
+```
+
+### Example: List threads (with pagination & filters)
+
+`thread/list` lets you render a history UI. Pass any combination of:
+- `cursor` — opaque string from a prior response; omit for the first page.
+- `limit` — server defaults to a reasonable page size if unset.
+- `modelProviders` — restrict results to specific providers; unset, null, or an empty array will include all providers.
+
+Example:
+
+```json
+{ "method": "thread/list", "id": 20, "params": {
+    "cursor": null,
+    "limit": 25,
+} }
+{ "id": 20, "result": {
+    "data": [
+        { "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111 },
+        { "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000 }
+    ],
+    "nextCursor": "opaque-token-or-null"
+} }
+```
+
+When `nextCursor` is `null`, you’ve reached the final page.
+
+### Example: Archive a thread
+
+Use `thread/archive` to move the persisted rollout (stored as a JSONL file on disk) into the archived sessions directory.
+
+```json
+{ "method": "thread/archive", "id": 21, "params": { "threadId": "thr_b" } }
+{ "id": 21, "result": {} }
+```
+
+An archived thread will not appear in future calls to `thread/list`.
+
+### Example: Start a turn (send user input)
+
+Turns attach user input (text or images) to a thread and trigger Codex generation. The `input` field is a list of discriminated unions:
+
+- `{"type":"text","text":"Explain this diff"}`
+- `{"type":"image","url":"https://…png"}`
+- `{"type":"localImage","path":"/tmp/screenshot.png"}`
+
+You can optionally specify config overrides on the new turn. If specified, these settings become the default for subsequent turns on the same thread.
+
+```json
+{ "method": "turn/start", "id": 30, "params": {
+    "threadId": "thr_123",
+    "input": [ { "type": "text", "text": "Run tests" } ],
+    // Below are optional config overrides
+    "cwd": "/Users/me/project",
+    "approvalPolicy": "unlessTrusted",
+    "sandboxPolicy": {
+        "mode": "workspaceWrite",
+        "writableRoots": ["/Users/me/project"],
+        "networkAccess": true
+    },
+    "model": "gpt-5.1-codex",
+    "effort": "medium",
+    "summary": "concise"
+} }
+{ "id": 30, "result": { "turn": {
+    "id": "turn_456",
+    "status": "inProgress",
+    "items": [],
+    "error": null
+} } }
+```
+
+### Example: Interrupt an active turn
+
+You can cancel a running Turn with `turn/interrupt`.
+
+```json
+{ "method": "turn/interrupt", "id": 31, "params": {
+    "threadId": "thr_123",
+    "turnId": "turn_456"
+} }
+{ "id": 31, "result": {} }
+```
+
+The server requests cancellations for running subprocesses, then emits a `turn/completed` event with `status: "interrupted"`. Rely on the `turn/completed` to know when Codex-side cleanup is done.
+
+### Example: Request a code review
+
+Use `review/start` to run Codex’s reviewer on the currently checked-out project. The request takes the thread id plus a `target` describing what should be reviewed:
+
+- `{"type":"uncommittedChanges"}` — staged, unstaged, and untracked files.
+- `{"type":"baseBranch","branch":"main"}` — diff against the provided branch’s upstream (see prompt for the exact `git merge-base`/`git diff` instructions Codex will run).
+- `{"type":"commit","sha":"abc1234","title":"Optional subject"}` — review a specific commit.
+- `{"type":"custom","instructions":"Free-form reviewer instructions"}` — fallback prompt equivalent to the legacy manual review request.
+- `delivery` (`"inline"` or `"detached"`, default `"inline"`) — where the review runs:
+  - `"inline"`: run the review as a new turn on the existing thread. The response’s `reviewThreadId` equals the original `threadId`, and no new `thread/started` notification is emitted.
+  - `"detached"`: fork a new review thread from the parent conversation and run the review there. The response’s `reviewThreadId` is the id of this new review thread, and the server emits a `thread/started` notification for it before streaming review items.
+
+Example request/response:
+
+```json
+{ "method": "review/start", "id": 40, "params": {
+    "threadId": "thr_123",
+    "delivery": "inline",
+    "target": { "type": "commit", "sha": "1234567deadbeef", "title": "Polish tui colors" }
+} }
+{ "id": 40, "result": {
+    "turn": {
+        "id": "turn_900",
+        "status": "inProgress",
+        "items": [
+            { "type": "userMessage", "id": "turn_900", "content": [ { "type": "text", "text": "Review commit 1234567: Polish tui colors" } ] }
+        ],
+        "error": null
+    },
+    "reviewThreadId": "thr_123"
+} }
+```
+
+For a detached review, use `"delivery": "detached"`. The response is the same shape, but `reviewThreadId` will be the id of the new review thread (different from the original `threadId`). The server also emits a `thread/started` notification for that new thread before streaming the review turn.
+
+Codex streams the usual `turn/started` notification followed by an `item/started`
+with an `enteredReviewMode` item so clients can show progress:
+
+```json
+{ "method": "item/started", "params": { "item": {
+    "type": "enteredReviewMode",
+    "id": "turn_900",
+    "review": "current changes"
+} } }
+```
+
+When the reviewer finishes, the server emits `item/started` and `item/completed`
+containing an `exitedReviewMode` item with the final review text:
+
+```json
+{ "method": "item/completed", "params": { "item": {
+    "type": "exitedReviewMode",
+    "id": "turn_900",
+    "review": "Looks solid overall...\n\n- Prefer Stylize helpers — app.rs:10-20\n  ..."
+} } }
+```
+
+The `review` string is plain text that already bundles the overall explanation plus a bullet list for each structured finding (matching `ThreadItem::ExitedReviewMode` in the generated schema). Use this notification to render the reviewer output in your client.
+
+### Example: One-off command execution
+
+Run a standalone command (argv vector) in the server’s sandbox without creating a thread or turn:
+
+```json
+{ "method": "command/exec", "id": 32, "params": {
+    "command": ["ls", "-la"],
+    "cwd": "/Users/me/project",                    // optional; defaults to server cwd
+    "sandboxPolicy": { "type": "workspaceWrite" }, // optional; defaults to user config
+    "timeoutMs": 10000                             // optional; ms timeout; defaults to server timeout
+} }
+{ "id": 32, "result": { "exitCode": 0, "stdout": "...", "stderr": "" } }
+```
+
+Notes:
+- Empty `command` arrays are rejected.
+- `sandboxPolicy` accepts the same shape used by `turn/start` (e.g., `dangerFullAccess`, `readOnly`, `workspaceWrite` with flags).
+- When omitted, `timeoutMs` falls back to the server default.
+
+## Events
+
+Event notifications are the server-initiated event stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading stdout for `thread/started`, `turn/*`, and `item/*` notifications.
+
+### Turn events
+
+The app-server streams JSON-RPC notifications while a turn is running. Each turn starts with `turn/started` (initial `turn`) and ends with `turn/completed` (final `turn` status). Token usage events stream separately via `thread/tokenUsage/updated`. Clients subscribe to the events they care about, rendering each item incrementally as updates arrive. The per-item lifecycle is always: `item/started` → zero or more item-specific deltas → `item/completed`.
+
+- `turn/started` — `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.
+- `turn/completed` — `{ turn }` where `turn.status` is `completed`, `interrupted`, or `failed`; failures carry `{ error: { message, codexErrorInfo? } }`.
+- `turn/diff/updated` — `{ threadId, turnId, diff }` represents the up-to-date snapshot of the turn-level unified diff, emitted after every FileChange item. `diff` is the latest aggregated unified diff across every file change in the turn. UIs can render this to show the full "what changed" view without stitching individual `fileChange` items.
+- `turn/plan/updated` — `{ turnId, explanation?, plan }` whenever the agent shares or changes its plan; each `plan` entry is `{ step, status }` with `status` in `pending`, `inProgress`, or `completed`.
+
+Today both notifications carry an empty `items` array even when item events were streamed; rely on `item/*` notifications for the canonical item list until this is fixed.
+
+#### Items
+
+`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Currently we support events for the following items:
+- `userMessage` — `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).
+- `agentMessage` — `{id, text}` containing the accumulated agent reply.
+- `reasoning` — `{id, summary, content}` where `summary` holds streamed reasoning summaries (applicable for most OpenAI models) and `content` holds raw reasoning blocks (applicable for e.g. open source models).
+- `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.
+- `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.
+
+All items emit two shared lifecycle events:
+- `item/started` — emits the full `item` when a new unit of work begins so the UI can render it immediately; the `item.id` in this payload matches the `itemId` used by deltas.
+- `item/completed` — sends the final `item` once that work finishes (e.g., after a tool call or message completes); treat this as the authoritative state.
+
+There are additional item-specific events:
+#### agentMessage
+- `item/agentMessage/delta` — appends streamed text for the agent message; concatenate `delta` values for the same `itemId` in order to reconstruct the full reply.
+#### reasoning
+- `item/reasoning/summaryTextDelta` — streams readable reasoning summaries; `summaryIndex` increments when a new summary section opens.
+- `item/reasoning/summaryPartAdded` — marks the boundary between reasoning summary sections for an `itemId`; subsequent `summaryTextDelta` entries share the same `summaryIndex`.
+- `item/reasoning/textDelta` — streams raw reasoning text (only applicable for e.g. open source models); use `contentIndex` to group deltas that belong together before showing them in the UI.
+#### commandExecution
+- `item/commandExecution/outputDelta` — streams stdout/stderr for the command; append deltas in order to render live output alongside `aggregatedOutput` in the final item.
+Final `commandExecution` items include parsed `commandActions`, `status`, `exitCode`, and `durationMs` so the UI can summarize what ran and whether it succeeded.
+#### fileChange
+- `item/fileChange/outputDelta` - contains the tool call response of the underlying `apply_patch` tool call.
+
+### Errors
+`error` event is emitted whenever the server hits an error mid-turn (for example, upstream model errors or quota limits). Carries the same `{ error: { message, codexErrorInfo? } }` payload as `turn.status: "failed"` and may precede that terminal notification.
+
+  `codexErrorInfo` maps to the `CodexErrorInfo` enum. Common values:
+  - `ContextWindowExceeded`
+  - `UsageLimitExceeded`
+  - `HttpConnectionFailed { httpStatusCode? }`: upstream HTTP failures including 4xx/5xx
+  - `ResponseStreamConnectionFailed { httpStatusCode? }`: failure to connect to the response SSE stream
+  - `ResponseStreamDisconnected { httpStatusCode? }`: disconnect of the response SSE stream in the middle of a turn before completion
+  - `ResponseTooManyFailedAttempts { httpStatusCode? }`
+  - `BadRequest`
+  - `Unauthorized`
+  - `SandboxError`
+  - `InternalServerError`
+  - `Other`: all unclassified errors
+
+When an upstream HTTP status is available (for example, from the Responses API or a provider), it is forwarded in `httpStatusCode` on the relevant `codexErrorInfo` variant.
+
+## Approvals
+
+Certain actions (shell commands or modifying files) may require explicit user approval depending on the user's config. When `turn/start` is used, the app-server drives an approval flow by sending a server-initiated JSON-RPC request to the client. The client must respond to tell Codex whether to proceed. UIs should present these requests inline with the active turn so users can review the proposed command or diff before choosing.
+
+- Requests include `threadId` and `turnId`—use them to scope UI state to the active conversation.
+- Respond with a single `{ "decision": "accept" | "decline" }` payload (plus optional `acceptSettings` on command executions). The server resumes or declines the work and ends the item with `item/completed`.
+
+### Command execution approvals
+
+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.
+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.
+
+### File change approvals
+
+Order of messages:
+1. `item/started` — emits a `fileChange` item with `changes` (diff chunk summaries) and `status: "inProgress"`. Show the proposed edits and paths to the user.
+2. `item/fileChange/requestApproval` (request) — includes `itemId`, `threadId`, `turnId`, and an optional `reason`.
+3. Client response — `{ "decision": "accept" }` or `{ "decision": "decline" }`.
+4. `item/completed` — returns the same `fileChange` item with `status` updated to `completed`, `failed`, or `declined` after the patch attempt. Rely on this to show success/failure and finalize the diff state in your UI.
+
+UI guidance for IDEs: surface an approval dialog as soon as the request arrives. The turn will proceed after the server receives a response to the approval request. The terminal `item/completed` notification will be sent with the appropriate status.
+
+## 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.
+
+### API Overview
+- `account/read` — fetch current account info; optionally refresh tokens.
+- `account/login/start` — begin login (`apiKey` or `chatgpt`).
+- `account/login/completed` (notify) — emitted when a login attempt finishes (success or error).
+- `account/login/cancel` — cancel a pending ChatGPT login by `loginId`.
+- `account/logout` — sign out; triggers `account/updated`.
+- `account/updated` (notify) — emitted whenever auth mode changes (`authMode`: `apikey`, `chatgpt`, or `null`).
+- `account/rateLimits/read` — fetch ChatGPT rate limits; updates arrive via `account/rateLimits/updated` (notify).
+- `account/rateLimits/updated` (notify) — emitted whenever a user's ChatGPT rate limits change.
+- `mcpServer/oauthLogin/completed` (notify) — emitted after a `mcpServer/oauth/login` flow finishes for a server; payload includes `{ name, success, error? }`.
+
+### 1) Check auth state
+
+Request:
+```json
+{ "method": "account/read", "id": 1, "params": { "refreshToken": false } }
+```
+
+Response examples:
+```json
+{ "id": 1, "result": { "account": null, "requiresOpenaiAuth": false } } // No OpenAI auth needed (e.g., OSS/local models)
+{ "id": 1, "result": { "account": null, "requiresOpenaiAuth": true } }  // OpenAI auth required (typical for OpenAI-hosted models)
+{ "id": 1, "result": { "account": { "type": "apiKey" }, "requiresOpenaiAuth": true } }
+{ "id": 1, "result": { "account": { "type": "chatgpt", "email": "user@example.com", "planType": "pro" }, "requiresOpenaiAuth": true } }
+```
+
+Field notes:
+- `refreshToken` (bool): set `true` to force a token refresh.
+- `requiresOpenaiAuth` reflects the active provider; when `false`, Codex can run without OpenAI credentials.
+
+### 2) Log in with an API key
+
+1. Send:
+   ```json
+   { "method": "account/login/start", "id": 2, "params": { "type": "apiKey", "apiKey": "sk-…" } }
+   ```
+2. Expect:
+   ```json
+   { "id": 2, "result": { "type": "apiKey" } }
+   ```
+3. Notifications:
+   ```json
+   { "method": "account/login/completed", "params": { "loginId": null, "success": true, "error": null } }
+   { "method": "account/updated", "params": { "authMode": "apikey" } }
+   ```
+
+### 3) Log in with ChatGPT (browser flow)
+
+1. Start:
+   ```json
+   { "method": "account/login/start", "id": 3, "params": { "type": "chatgpt" } }
+   { "id": 3, "result": { "type": "chatgpt", "loginId": "<uuid>", "authUrl": "https://chatgpt.com/…&redirect_uri=http%3A%2F%2Flocalhost%3A<port>%2Fauth%2Fcallback" } }
+   ```
+2. Open `authUrl` in a browser; the app-server hosts the local callback.
+3. Wait for notifications:
+   ```json
+   { "method": "account/login/completed", "params": { "loginId": "<uuid>", "success": true, "error": null } }
+   { "method": "account/updated", "params": { "authMode": "chatgpt" } }
+   ```
+
+### 4) Cancel a ChatGPT login
+
+```json
+{ "method": "account/login/cancel", "id": 4, "params": { "loginId": "<uuid>" } }
+{ "method": "account/login/completed", "params": { "loginId": "<uuid>", "success": false, "error": "…" } }
+```
+
+### 5) Logout
+
+```json
+{ "method": "account/logout", "id": 5 }
+{ "id": 5, "result": {} }
+{ "method": "account/updated", "params": { "authMode": null } }
+```
+
+### 6) Rate limits (ChatGPT)
+
+```json
+{ "method": "account/rateLimits/read", "id": 6 }
+{ "id": 6, "result": { "rateLimits": { "primary": { "usedPercent": 25, "windowDurationMins": 15, "resetsAt": 1730947200 }, "secondary": null } } }
+{ "method": "account/rateLimits/updated", "params": { "rateLimits": { … } } }
+```
+
+Field notes:
+- `usedPercent` is current usage within the OpenAI quota window.
+- `windowDurationMins` is the quota window length.
+- `resetsAt` is a Unix timestamp (seconds) for the next reset.

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

@@ -0,0 +1,70 @@
+use crate::error_code::INTERNAL_ERROR_CODE;
+use crate::error_code::INVALID_REQUEST_ERROR_CODE;
+use codex_app_server_protocol::ConfigBatchWriteParams;
+use codex_app_server_protocol::ConfigReadParams;
+use codex_app_server_protocol::ConfigReadResponse;
+use codex_app_server_protocol::ConfigValueWriteParams;
+use codex_app_server_protocol::ConfigWriteErrorCode;
+use codex_app_server_protocol::ConfigWriteResponse;
+use codex_app_server_protocol::JSONRPCErrorError;
+use codex_core::config::ConfigService;
+use codex_core::config::ConfigServiceError;
+use serde_json::json;
+use std::path::PathBuf;
+use toml::Value as TomlValue;
+
+#[derive(Clone)]
+pub(crate) struct ConfigApi {
+    service: ConfigService,
+}
+
+impl ConfigApi {
+    pub(crate) fn new(codex_home: PathBuf, cli_overrides: Vec<(String, TomlValue)>) -> Self {
+        Self {
+            service: ConfigService::new(codex_home, cli_overrides),
+        }
+    }
+
+    pub(crate) async fn read(
+        &self,
+        params: ConfigReadParams,
+    ) -> Result<ConfigReadResponse, JSONRPCErrorError> {
+        self.service.read(params).await.map_err(map_error)
+    }
+
+    pub(crate) async fn write_value(
+        &self,
+        params: ConfigValueWriteParams,
+    ) -> Result<ConfigWriteResponse, JSONRPCErrorError> {
+        self.service.write_value(params).await.map_err(map_error)
+    }
+
+    pub(crate) async fn batch_write(
+        &self,
+        params: ConfigBatchWriteParams,
+    ) -> Result<ConfigWriteResponse, JSONRPCErrorError> {
+        self.service.batch_write(params).await.map_err(map_error)
+    }
+}
+
+fn map_error(err: ConfigServiceError) -> JSONRPCErrorError {
+    if let Some(code) = err.write_error_code() {
+        return config_write_error(code, err.to_string());
+    }
+
+    JSONRPCErrorError {
+        code: INTERNAL_ERROR_CODE,
+        message: err.to_string(),
+        data: None,
+    }
+}
+
+fn config_write_error(code: ConfigWriteErrorCode, message: impl Into<String>) -> JSONRPCErrorError {
+    JSONRPCErrorError {
+        code: INVALID_REQUEST_ERROR_CODE,
+        message: message.into(),
+        data: Some(json!({
+            "config_write_error_code": code,
+        })),
+    }
+}

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

@@ -19,6 +19,10 @@ pub(crate) async fn run_fuzzy_file_search(
     roots: Vec<String>,
     cancellation_flag: Arc<AtomicBool>,
 ) -> Vec<FuzzyFileSearchResult> {
+    if roots.is_empty() {
+        return Vec::new();
+    }
+
     #[expect(clippy::expect_used)]
     let limit_per_root =
         NonZero::new(LIMIT_PER_ROOT).expect("LIMIT_PER_ROOT should be a valid non-zero usize");
@@ -46,6 +50,7 @@ pub(crate) async fn run_fuzzy_file_search(
                 threads,
                 cancel_flag,
                 COMPUTE_INDICES,
+                true,
             ) {
                 Ok(res) => Ok((root, res)),
                 Err(err) => Err((root, err)),

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

@@ -1,32 +1,40 @@
 #![deny(clippy::print_stdout, clippy::print_stderr)]
 
-use std::io::ErrorKind;
-use std::io::Result as IoResult;
-use std::path::PathBuf;
-
 use codex_common::CliConfigOverrides;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
+use std::io::ErrorKind;
+use std::io::Result as IoResult;
+use std::path::PathBuf;
 
+use crate::message_processor::MessageProcessor;
+use crate::outgoing_message::OutgoingMessage;
+use crate::outgoing_message::OutgoingMessageSender;
 use codex_app_server_protocol::JSONRPCMessage;
+use codex_feedback::CodexFeedback;
 use tokio::io::AsyncBufReadExt;
 use tokio::io::AsyncWriteExt;
 use tokio::io::BufReader;
 use tokio::io::{self};
 use tokio::sync::mpsc;
+use toml::Value as TomlValue;
+use tracing::Level;
 use tracing::debug;
 use tracing::error;
 use tracing::info;
 use tracing_subscriber::EnvFilter;
+use tracing_subscriber::Layer;
+use tracing_subscriber::filter::Targets;
+use tracing_subscriber::layer::SubscriberExt;
+use tracing_subscriber::util::SubscriberInitExt;
 
-use crate::message_processor::MessageProcessor;
-use crate::outgoing_message::OutgoingMessage;
-use crate::outgoing_message::OutgoingMessageSender;
-
+mod bespoke_event_handling;
 mod codex_message_processor;
+mod config_api;
 mod error_code;
 mod fuzzy_file_search;
 mod message_processor;
+mod models;
 mod outgoing_message;
 
 /// Size of the bounded channels used to communicate between tasks. The value
@@ -38,16 +46,9 @@ pub async fn run_main(
     codex_linux_sandbox_exe: Option<PathBuf>,
     cli_config_overrides: CliConfigOverrides,
 ) -> IoResult<()> {
-    // Install a simple subscriber so `tracing` output is visible.  Users can
-    // control the log level with `RUST_LOG`.
-    tracing_subscriber::fmt()
-        .with_writer(std::io::stderr)
-        .with_env_filter(EnvFilter::from_default_env())
-        .init();
-
     // Set up channels.
     let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
-    let (outgoing_tx, mut outgoing_rx) = mpsc::unbounded_channel::<OutgoingMessage>();
+    let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(CHANNEL_CAPACITY);
 
     // Task: read from stdin, push to `incoming_tx`.
     let stdin_reader_handle = tokio::spawn({
@@ -80,19 +81,57 @@ pub async fn run_main(
             format!("error parsing -c overrides: {e}"),
         )
     })?;
-    let config = Config::load_with_cli_overrides(cli_kv_overrides, ConfigOverrides::default())
-        .await
-        .map_err(|e| {
-            std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
+    let config =
+        Config::load_with_cli_overrides(cli_kv_overrides.clone(), ConfigOverrides::default())
+            .await
+            .map_err(|e| {
+                std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
+            })?;
+
+    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}"),
+            )
         })?;
 
+    // Install a simple subscriber so `tracing` output is visible.  Users can
+    // control the log level with `RUST_LOG`.
+    let stderr_fmt = tracing_subscriber::fmt::layer()
+        .with_writer(std::io::stderr)
+        .with_span_events(tracing_subscriber::fmt::format::FmtSpan::FULL)
+        .with_filter(EnvFilter::from_default_env());
+
+    let feedback_layer = tracing_subscriber::fmt::layer()
+        .with_writer(feedback.make_writer())
+        .with_ansi(false)
+        .with_target(false)
+        .with_filter(Targets::new().with_default(Level::TRACE));
+
+    let otel_logger_layer = otel.as_ref().and_then(|o| o.logger_layer());
+
+    let otel_tracing_layer = otel.as_ref().and_then(|o| o.tracing_layer());
+
+    let _ = tracing_subscriber::registry()
+        .with(stderr_fmt)
+        .with(feedback_layer)
+        .with(otel_logger_layer)
+        .with(otel_tracing_layer)
+        .try_init();
+
     // 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 mut processor = MessageProcessor::new(
             outgoing_message_sender,
             codex_linux_sandbox_exe,
             std::sync::Arc::new(config),
+            cli_overrides,
+            feedback.clone(),
         );
         async move {
             while let Some(msg) = incoming_rx.recv().await {

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

@@ -1,28 +1,35 @@
 use std::path::PathBuf;
+use std::sync::Arc;
 
 use crate::codex_message_processor::CodexMessageProcessor;
+use crate::config_api::ConfigApi;
 use crate::error_code::INVALID_REQUEST_ERROR_CODE;
 use crate::outgoing_message::OutgoingMessageSender;
 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::InitializeResponse;
-
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCErrorError;
 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_core::AuthManager;
 use codex_core::ConversationManager;
 use codex_core::config::Config;
 use codex_core::default_client::USER_AGENT_SUFFIX;
 use codex_core::default_client::get_codex_user_agent;
+use codex_feedback::CodexFeedback;
 use codex_protocol::protocol::SessionSource;
-use std::sync::Arc;
+use toml::Value as TomlValue;
 
 pub(crate) struct MessageProcessor {
     outgoing: Arc<OutgoingMessageSender>,
     codex_message_processor: CodexMessageProcessor,
+    config_api: ConfigApi,
     initialized: bool,
 }
 
@@ -33,9 +40,15 @@ impl MessageProcessor {
         outgoing: OutgoingMessageSender,
         codex_linux_sandbox_exe: Option<PathBuf>,
         config: Arc<Config>,
+        cli_overrides: Vec<(String, TomlValue)>,
+        feedback: CodexFeedback,
     ) -> Self {
         let outgoing = Arc::new(outgoing);
-        let auth_manager = AuthManager::shared(config.codex_home.clone(), false);
+        let auth_manager = AuthManager::shared(
+            config.codex_home.clone(),
+            false,
+            config.cli_auth_credentials_store_mode,
+        );
         let conversation_manager = Arc::new(ConversationManager::new(
             auth_manager.clone(),
             SessionSource::VSCode,
@@ -45,75 +58,106 @@ impl MessageProcessor {
             conversation_manager,
             outgoing.clone(),
             codex_linux_sandbox_exe,
-            config,
+            Arc::clone(&config),
+            cli_overrides.clone(),
+            feedback,
         );
+        let config_api = ConfigApi::new(config.codex_home.clone(), cli_overrides);
 
         Self {
             outgoing,
             codex_message_processor,
+            config_api,
             initialized: false,
         }
     }
 
     pub(crate) async fn process_request(&mut self, request: JSONRPCRequest) {
         let request_id = request.id.clone();
-        if let Ok(request_json) = serde_json::to_value(request)
-            && let Ok(codex_request) = serde_json::from_value::<ClientRequest>(request_json)
-        {
-            match codex_request {
-                // Handle Initialize internally so CodexMessageProcessor does not have to concern
-                // itself with the `initialized` bool.
-                ClientRequest::Initialize { request_id, params } => {
-                    if self.initialized {
-                        let error = JSONRPCErrorError {
-                            code: INVALID_REQUEST_ERROR_CODE,
-                            message: "Already initialized".to_string(),
-                            data: None,
-                        };
-                        self.outgoing.send_error(request_id, error).await;
-                        return;
-                    } else {
-                        let ClientInfo {
-                            name,
-                            title: _title,
-                            version,
-                        } = params.client_info;
-                        let user_agent_suffix = format!("{name}; {version}");
-                        if let Ok(mut suffix) = USER_AGENT_SUFFIX.lock() {
-                            *suffix = Some(user_agent_suffix);
-                        }
+        let request_json = match serde_json::to_value(&request) {
+            Ok(request_json) => request_json,
+            Err(err) => {
+                let error = JSONRPCErrorError {
+                    code: INVALID_REQUEST_ERROR_CODE,
+                    message: format!("Invalid request: {err}"),
+                    data: None,
+                };
+                self.outgoing.send_error(request_id, error).await;
+                return;
+            }
+        };
 
-                        let user_agent = get_codex_user_agent();
-                        let response = InitializeResponse { user_agent };
-                        self.outgoing.send_response(request_id, response).await;
+        let codex_request = match serde_json::from_value::<ClientRequest>(request_json) {
+            Ok(codex_request) => codex_request,
+            Err(err) => {
+                let error = JSONRPCErrorError {
+                    code: INVALID_REQUEST_ERROR_CODE,
+                    message: format!("Invalid request: {err}"),
+                    data: None,
+                };
+                self.outgoing.send_error(request_id, error).await;
+                return;
+            }
+        };
 
-                        self.initialized = true;
-                        return;
-                    }
-                }
-                _ => {
-                    if !self.initialized {
-                        let error = JSONRPCErrorError {
-                            code: INVALID_REQUEST_ERROR_CODE,
-                            message: "Not initialized".to_string(),
-                            data: None,
-                        };
-                        self.outgoing.send_error(request_id, error).await;
-                        return;
+        match codex_request {
+            // Handle Initialize internally so CodexMessageProcessor does not have to concern
+            // itself with the `initialized` bool.
+            ClientRequest::Initialize { request_id, params } => {
+                if self.initialized {
+                    let error = JSONRPCErrorError {
+                        code: INVALID_REQUEST_ERROR_CODE,
+                        message: "Already initialized".to_string(),
+                        data: None,
+                    };
+                    self.outgoing.send_error(request_id, error).await;
+                    return;
+                } else {
+                    let ClientInfo {
+                        name,
+                        title: _title,
+                        version,
+                    } = params.client_info;
+                    let user_agent_suffix = format!("{name}; {version}");
+                    if let Ok(mut suffix) = USER_AGENT_SUFFIX.lock() {
+                        *suffix = Some(user_agent_suffix);
                     }
+
+                    let user_agent = get_codex_user_agent();
+                    let response = InitializeResponse { user_agent };
+                    self.outgoing.send_response(request_id, response).await;
+
+                    self.initialized = true;
+
+                    return;
                 }
             }
+            _ => {
+                if !self.initialized {
+                    let error = JSONRPCErrorError {
+                        code: INVALID_REQUEST_ERROR_CODE,
+                        message: "Not initialized".to_string(),
+                        data: None,
+                    };
+                    self.outgoing.send_error(request_id, error).await;
+                    return;
+                }
+            }
+        }
 
-            self.codex_message_processor
-                .process_request(codex_request)
-                .await;
-        } else {
-            let error = JSONRPCErrorError {
-                code: INVALID_REQUEST_ERROR_CODE,
-                message: "Invalid request".to_string(),
-                data: None,
-            };
-            self.outgoing.send_error(request_id, error).await;
+        match codex_request {
+            ClientRequest::ConfigRead { request_id, params } => {
+                self.handle_config_read(request_id, params).await;
+            }
+            ClientRequest::ConfigValueWrite { request_id, params } => {
+                self.handle_config_value_write(request_id, params).await;
+            }
+            ClientRequest::ConfigBatchWrite { request_id, params } => {
+                self.handle_config_batch_write(request_id, params).await;
+            }
+            other => {
+                self.codex_message_processor.process_request(other).await;
+            }
         }
     }
 
@@ -134,4 +178,33 @@ impl MessageProcessor {
     pub(crate) fn process_error(&mut self, err: JSONRPCError) {
         tracing::error!("<- error: {:?}", err);
     }
+
+    async fn handle_config_read(&self, request_id: RequestId, params: ConfigReadParams) {
+        match self.config_api.read(params).await {
+            Ok(response) => self.outgoing.send_response(request_id, response).await,
+            Err(error) => self.outgoing.send_error(request_id, error).await,
+        }
+    }
+
+    async fn handle_config_value_write(
+        &self,
+        request_id: RequestId,
+        params: ConfigValueWriteParams,
+    ) {
+        match self.config_api.write_value(params).await {
+            Ok(response) => self.outgoing.send_response(request_id, response).await,
+            Err(error) => self.outgoing.send_error(request_id, error).await,
+        }
+    }
+
+    async fn handle_config_batch_write(
+        &self,
+        request_id: RequestId,
+        params: ConfigBatchWriteParams,
+    ) {
+        match self.config_api.batch_write(params).await {
+            Ok(response) => self.outgoing.send_response(request_id, response).await,
+            Err(error) => self.outgoing.send_error(request_id, error).await,
+        }
+    }
 }

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

@@ -0,0 +1,46 @@
+use std::sync::Arc;
+
+use codex_app_server_protocol::Model;
+use codex_app_server_protocol::ReasoningEffortOption;
+use codex_core::ConversationManager;
+use codex_core::config::Config;
+use codex_protocol::openai_models::ModelPreset;
+use codex_protocol::openai_models::ReasoningEffortPreset;
+
+pub async fn supported_models(
+    conversation_manager: Arc<ConversationManager>,
+    config: &Config,
+) -> Vec<Model> {
+    conversation_manager
+        .list_models(config)
+        .await
+        .into_iter()
+        .map(model_from_preset)
+        .collect()
+}
+
+fn model_from_preset(preset: ModelPreset) -> Model {
+    Model {
+        id: preset.id.to_string(),
+        model: preset.model.to_string(),
+        display_name: preset.display_name.to_string(),
+        description: preset.description.to_string(),
+        supported_reasoning_efforts: reasoning_efforts_from_preset(
+            preset.supported_reasoning_efforts,
+        ),
+        default_reasoning_effort: preset.default_reasoning_effort,
+        is_default: preset.is_default,
+    }
+}
+
+fn reasoning_efforts_from_preset(
+    efforts: Vec<ReasoningEffortPreset>,
+) -> Vec<ReasoningEffortOption> {
+    efforts
+        .iter()
+        .map(|preset| ReasoningEffortOption {
+            reasoning_effort: preset.effort,
+            description: preset.description.to_string(),
+        })
+        .collect()
+}

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

@@ -16,15 +16,18 @@ use tracing::warn;
 
 use crate::error_code::INTERNAL_ERROR_CODE;
 
+#[cfg(test)]
+use codex_protocol::account::PlanType;
+
 /// Sends messages to the client and manages request callbacks.
 pub(crate) struct OutgoingMessageSender {
     next_request_id: AtomicI64,
-    sender: mpsc::UnboundedSender<OutgoingMessage>,
+    sender: mpsc::Sender<OutgoingMessage>,
     request_id_to_callback: Mutex<HashMap<RequestId, oneshot::Sender<Result>>>,
 }
 
 impl OutgoingMessageSender {
-    pub(crate) fn new(sender: mpsc::UnboundedSender<OutgoingMessage>) -> Self {
+    pub(crate) fn new(sender: mpsc::Sender<OutgoingMessage>) -> Self {
         Self {
             next_request_id: AtomicI64::new(0),
             sender,
@@ -45,8 +48,12 @@ impl OutgoingMessageSender {
         }
 
         let outgoing_message =
-            OutgoingMessage::Request(request.request_with_id(outgoing_message_id));
-        let _ = self.sender.send(outgoing_message);
+            OutgoingMessage::Request(request.request_with_id(outgoing_message_id.clone()));
+        if let Err(err) = self.sender.send(outgoing_message).await {
+            warn!("failed to send request {outgoing_message_id:?} to client: {err:?}");
+            let mut request_id_to_callback = self.request_id_to_callback.lock().await;
+            request_id_to_callback.remove(&outgoing_message_id);
+        }
         rx_approve
     }
 
@@ -72,7 +79,9 @@ impl OutgoingMessageSender {
         match serde_json::to_value(response) {
             Ok(result) => {
                 let outgoing_message = OutgoingMessage::Response(OutgoingResponse { id, result });
-                let _ = self.sender.send(outgoing_message);
+                if let Err(err) = self.sender.send(outgoing_message).await {
+                    warn!("failed to send response to client: {err:?}");
+                }
             }
             Err(err) => {
                 self.send_error(
@@ -89,21 +98,29 @@ impl OutgoingMessageSender {
     }
 
     pub(crate) async fn send_server_notification(&self, notification: ServerNotification) {
-        let _ = self
+        if let Err(err) = self
             .sender
-            .send(OutgoingMessage::AppServerNotification(notification));
+            .send(OutgoingMessage::AppServerNotification(notification))
+            .await
+        {
+            warn!("failed to send server notification to client: {err:?}");
+        }
     }
 
     /// All notifications should be migrated to [`ServerNotification`] and
     /// [`OutgoingMessage::Notification`] should be removed.
     pub(crate) async fn send_notification(&self, notification: OutgoingNotification) {
         let outgoing_message = OutgoingMessage::Notification(notification);
-        let _ = self.sender.send(outgoing_message);
+        if let Err(err) = self.sender.send(outgoing_message).await {
+            warn!("failed to send notification to client: {err:?}");
+        }
     }
 
     pub(crate) async fn send_error(&self, id: RequestId, error: JSONRPCErrorError) {
         let outgoing_message = OutgoingMessage::Error(OutgoingError { id, error });
-        let _ = self.sender.send(outgoing_message);
+        if let Err(err) = self.sender.send(outgoing_message).await {
+            warn!("failed to send error to client: {err:?}");
+        }
     }
 }
 
@@ -141,7 +158,13 @@ pub(crate) struct OutgoingError {
 
 #[cfg(test)]
 mod tests {
+    use codex_app_server_protocol::AccountLoginCompletedNotification;
+    use codex_app_server_protocol::AccountRateLimitsUpdatedNotification;
+    use codex_app_server_protocol::AccountUpdatedNotification;
+    use codex_app_server_protocol::AuthMode;
     use codex_app_server_protocol::LoginChatGptCompleteNotification;
+    use codex_app_server_protocol::RateLimitSnapshot;
+    use codex_app_server_protocol::RateLimitWindow;
     use pretty_assertions::assert_eq;
     use serde_json::json;
     use uuid::Uuid;
@@ -164,6 +187,7 @@ mod tests {
                 "params": {
                     "loginId": Uuid::nil(),
                     "success": true,
+                    "error": null,
                 },
             }),
             serde_json::to_value(jsonrpc_notification)
@@ -171,4 +195,88 @@ mod tests {
             "ensure the strum macros serialize the method field correctly"
         );
     }
+
+    #[test]
+    fn verify_account_login_completed_notification_serialization() {
+        let notification =
+            ServerNotification::AccountLoginCompleted(AccountLoginCompletedNotification {
+                login_id: Some(Uuid::nil().to_string()),
+                success: true,
+                error: None,
+            });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!({
+                "method": "account/login/completed",
+                "params": {
+                    "loginId": Uuid::nil().to_string(),
+                    "success": true,
+                    "error": null,
+                },
+            }),
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
+
+    #[test]
+    fn verify_account_rate_limits_notification_serialization() {
+        let notification =
+            ServerNotification::AccountRateLimitsUpdated(AccountRateLimitsUpdatedNotification {
+                rate_limits: RateLimitSnapshot {
+                    primary: Some(RateLimitWindow {
+                        used_percent: 25,
+                        window_duration_mins: Some(15),
+                        resets_at: Some(123),
+                    }),
+                    secondary: None,
+                    credits: None,
+                    plan_type: Some(PlanType::Plus),
+                },
+            });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!({
+                "method": "account/rateLimits/updated",
+                "params": {
+                    "rateLimits": {
+                        "primary": {
+                            "usedPercent": 25,
+                            "windowDurationMins": 15,
+                            "resetsAt": 123
+                        },
+                        "secondary": null,
+                        "credits": null,
+                        "planType": "plus"
+                    }
+                },
+            }),
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
+
+    #[test]
+    fn verify_account_updated_notification_serialization() {
+        let notification = ServerNotification::AccountUpdated(AccountUpdatedNotification {
+            auth_mode: Some(AuthMode::ApiKey),
+        });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!({
+                "method": "account/updated",
+                "params": {
+                    "authMode": "apikey"
+                },
+            }),
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
 }

codex-rs/app-server/tests/common/Cargo.toml

@@ -1,7 +1,8 @@
 [package]
-edition = "2024"
 name = "app_test_support"
-version = { workspace = true }
+version.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [lib]
 path = "lib.rs"
@@ -9,7 +10,11 @@ path = "lib.rs"
 [dependencies]
 anyhow = { workspace = true }
 assert_cmd = { workspace = true }
+base64 = { workspace = true }
+chrono = { workspace = true }
 codex-app-server-protocol = { workspace = true }
+codex-core = { workspace = true, features = ["test-support"] }
+codex-protocol = { workspace = true }
 serde = { workspace = true }
 serde_json = { workspace = true }
 tokio = { workspace = true, features = [
@@ -18,4 +23,7 @@ tokio = { workspace = true, features = [
     "process",
     "rt-multi-thread",
 ] }
+uuid = { workspace = true }
 wiremock = { workspace = true }
+core_test_support = { path = "../../../core/tests/common" }
+shlex = { workspace = true }

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

@@ -0,0 +1,135 @@
+use std::path::Path;
+
+use anyhow::Context;
+use anyhow::Result;
+use base64::Engine;
+use base64::engine::general_purpose::URL_SAFE_NO_PAD;
+use chrono::DateTime;
+use chrono::Utc;
+use codex_core::auth::AuthCredentialsStoreMode;
+use codex_core::auth::AuthDotJson;
+use codex_core::auth::save_auth;
+use codex_core::token_data::TokenData;
+use codex_core::token_data::parse_id_token;
+use serde_json::json;
+
+/// Builder for writing a fake ChatGPT auth.json in tests.
+#[derive(Debug, Clone)]
+pub struct ChatGptAuthFixture {
+    access_token: String,
+    refresh_token: String,
+    account_id: Option<String>,
+    claims: ChatGptIdTokenClaims,
+    last_refresh: Option<Option<DateTime<Utc>>>,
+}
+
+impl ChatGptAuthFixture {
+    pub fn new(access_token: impl Into<String>) -> Self {
+        Self {
+            access_token: access_token.into(),
+            refresh_token: "refresh-token".to_string(),
+            account_id: None,
+            claims: ChatGptIdTokenClaims::default(),
+            last_refresh: None,
+        }
+    }
+
+    pub fn refresh_token(mut self, refresh_token: impl Into<String>) -> Self {
+        self.refresh_token = refresh_token.into();
+        self
+    }
+
+    pub fn account_id(mut self, account_id: impl Into<String>) -> Self {
+        self.account_id = Some(account_id.into());
+        self
+    }
+
+    pub fn plan_type(mut self, plan_type: impl Into<String>) -> Self {
+        self.claims.plan_type = Some(plan_type.into());
+        self
+    }
+
+    pub fn email(mut self, email: impl Into<String>) -> Self {
+        self.claims.email = Some(email.into());
+        self
+    }
+
+    pub fn last_refresh(mut self, last_refresh: Option<DateTime<Utc>>) -> Self {
+        self.last_refresh = Some(last_refresh);
+        self
+    }
+
+    pub fn claims(mut self, claims: ChatGptIdTokenClaims) -> Self {
+        self.claims = claims;
+        self
+    }
+}
+
+#[derive(Debug, Clone, Default)]
+pub struct ChatGptIdTokenClaims {
+    pub email: Option<String>,
+    pub plan_type: Option<String>,
+}
+
+impl ChatGptIdTokenClaims {
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    pub fn email(mut self, email: impl Into<String>) -> Self {
+        self.email = Some(email.into());
+        self
+    }
+
+    pub fn plan_type(mut self, plan_type: impl Into<String>) -> Self {
+        self.plan_type = Some(plan_type.into());
+        self
+    }
+}
+
+pub fn encode_id_token(claims: &ChatGptIdTokenClaims) -> Result<String> {
+    let header = json!({ "alg": "none", "typ": "JWT" });
+    let mut payload = serde_json::Map::new();
+    if let Some(email) = &claims.email {
+        payload.insert("email".to_string(), json!(email));
+    }
+    if let Some(plan_type) = &claims.plan_type {
+        payload.insert(
+            "https://api.openai.com/auth".to_string(),
+            json!({ "chatgpt_plan_type": plan_type }),
+        );
+    }
+    let payload = serde_json::Value::Object(payload);
+
+    let header_b64 =
+        URL_SAFE_NO_PAD.encode(serde_json::to_vec(&header).context("serialize jwt header")?);
+    let payload_b64 =
+        URL_SAFE_NO_PAD.encode(serde_json::to_vec(&payload).context("serialize jwt payload")?);
+    let signature_b64 = URL_SAFE_NO_PAD.encode(b"signature");
+    Ok(format!("{header_b64}.{payload_b64}.{signature_b64}"))
+}
+
+pub fn write_chatgpt_auth(
+    codex_home: &Path,
+    fixture: ChatGptAuthFixture,
+    cli_auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> Result<()> {
+    let id_token_raw = encode_id_token(&fixture.claims)?;
+    let id_token = parse_id_token(&id_token_raw).context("parse id token")?;
+    let tokens = TokenData {
+        id_token,
+        access_token: fixture.access_token,
+        refresh_token: fixture.refresh_token,
+        account_id: fixture.account_id,
+    };
+
+    let last_refresh = fixture.last_refresh.unwrap_or_else(|| Some(Utc::now()));
+
+    let auth = AuthDotJson {
+        openai_api_key: None,
+        tokens: Some(tokens),
+        last_refresh,
+    };
+
+    save_auth(codex_home, &auth, cli_auth_credentials_store_mode).context("write auth.json")
+}

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

@@ -1,13 +1,32 @@
+mod auth_fixtures;
 mod mcp_process;
 mod mock_model_server;
+mod models_cache;
 mod responses;
+mod rollout;
 
+pub use auth_fixtures::ChatGptAuthFixture;
+pub use auth_fixtures::ChatGptIdTokenClaims;
+pub use auth_fixtures::encode_id_token;
+pub use auth_fixtures::write_chatgpt_auth;
 use codex_app_server_protocol::JSONRPCResponse;
+pub use core_test_support::format_with_current_shell;
+pub use core_test_support::format_with_current_shell_display;
+pub use core_test_support::format_with_current_shell_display_non_login;
+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::McpProcess;
 pub use mock_model_server::create_mock_chat_completions_server;
+pub use mock_model_server::create_mock_chat_completions_server_unchecked;
+pub use models_cache::write_models_cache;
+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_shell_sse_response;
+pub use responses::create_shell_command_sse_response;
+pub use rollout::create_fake_rollout;
 use serde::de::DeserializeOwned;
 
 pub fn to_response<T: DeserializeOwned>(response: JSONRPCResponse) -> anyhow::Result<T> {

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

@@ -14,28 +14,41 @@ use anyhow::Context;
 use assert_cmd::prelude::*;
 use codex_app_server_protocol::AddConversationListenerParams;
 use codex_app_server_protocol::ArchiveConversationParams;
+use codex_app_server_protocol::CancelLoginAccountParams;
 use codex_app_server_protocol::CancelLoginChatGptParams;
 use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::ClientNotification;
+use codex_app_server_protocol::ConfigBatchWriteParams;
+use codex_app_server_protocol::ConfigReadParams;
+use codex_app_server_protocol::ConfigValueWriteParams;
+use codex_app_server_protocol::FeedbackUploadParams;
+use codex_app_server_protocol::GetAccountParams;
 use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::InitializeParams;
 use codex_app_server_protocol::InterruptConversationParams;
-use codex_app_server_protocol::ListConversationsParams;
-use codex_app_server_protocol::LoginApiKeyParams;
-use codex_app_server_protocol::NewConversationParams;
-use codex_app_server_protocol::RemoveConversationListenerParams;
-use codex_app_server_protocol::ResumeConversationParams;
-use codex_app_server_protocol::SendUserMessageParams;
-use codex_app_server_protocol::SendUserTurnParams;
-use codex_app_server_protocol::ServerRequest;
-use codex_app_server_protocol::SetDefaultModelParams;
-
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCMessage;
 use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCRequest;
 use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::ListConversationsParams;
+use codex_app_server_protocol::LoginApiKeyParams;
+use codex_app_server_protocol::ModelListParams;
+use codex_app_server_protocol::NewConversationParams;
+use codex_app_server_protocol::RemoveConversationListenerParams;
 use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ResumeConversationParams;
+use codex_app_server_protocol::ReviewStartParams;
+use codex_app_server_protocol::SendUserMessageParams;
+use codex_app_server_protocol::SendUserTurnParams;
+use codex_app_server_protocol::ServerRequest;
+use codex_app_server_protocol::SetDefaultModelParams;
+use codex_app_server_protocol::ThreadArchiveParams;
+use codex_app_server_protocol::ThreadListParams;
+use codex_app_server_protocol::ThreadResumeParams;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::TurnInterruptParams;
+use codex_app_server_protocol::TurnStartParams;
 use std::process::Command as StdCommand;
 use tokio::process::Command;
 
@@ -236,6 +249,29 @@ impl McpProcess {
         self.send_request("getUserAgent", None).await
     }
 
+    /// Send an `account/rateLimits/read` JSON-RPC request.
+    pub async fn send_get_account_rate_limits_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("account/rateLimits/read", None).await
+    }
+
+    /// Send an `account/read` JSON-RPC request.
+    pub async fn send_get_account_request(
+        &mut self,
+        params: GetAccountParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/read", params).await
+    }
+
+    /// Send a `feedback/upload` JSON-RPC request.
+    pub async fn send_feedback_upload_request(
+        &mut self,
+        params: FeedbackUploadParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("feedback/upload", params).await
+    }
+
     /// Send a `userInfo` JSON-RPC request.
     pub async fn send_user_info_request(&mut self) -> anyhow::Result<i64> {
         self.send_request("userInfo", None).await
@@ -259,6 +295,51 @@ impl McpProcess {
         self.send_request("listConversations", params).await
     }
 
+    /// Send a `thread/start` JSON-RPC request.
+    pub async fn send_thread_start_request(
+        &mut self,
+        params: ThreadStartParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/start", params).await
+    }
+
+    /// Send a `thread/resume` JSON-RPC request.
+    pub async fn send_thread_resume_request(
+        &mut self,
+        params: ThreadResumeParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/resume", params).await
+    }
+
+    /// Send a `thread/archive` JSON-RPC request.
+    pub async fn send_thread_archive_request(
+        &mut self,
+        params: ThreadArchiveParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/archive", params).await
+    }
+
+    /// Send a `thread/list` JSON-RPC request.
+    pub async fn send_thread_list_request(
+        &mut self,
+        params: ThreadListParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/list", params).await
+    }
+
+    /// Send a `model/list` JSON-RPC request.
+    pub async fn send_list_models_request(
+        &mut self,
+        params: ModelListParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("model/list", params).await
+    }
+
     /// Send a `resumeConversation` JSON-RPC request.
     pub async fn send_resume_conversation_request(
         &mut self,
@@ -282,6 +363,33 @@ impl McpProcess {
         self.send_request("loginChatGpt", None).await
     }
 
+    /// Send a `turn/start` JSON-RPC request (v2).
+    pub async fn send_turn_start_request(
+        &mut self,
+        params: TurnStartParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("turn/start", params).await
+    }
+
+    /// Send a `turn/interrupt` JSON-RPC request (v2).
+    pub async fn send_turn_interrupt_request(
+        &mut self,
+        params: TurnInterruptParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("turn/interrupt", params).await
+    }
+
+    /// Send a `review/start` JSON-RPC request (v2).
+    pub async fn send_review_start_request(
+        &mut self,
+        params: ReviewStartParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("review/start", params).await
+    }
+
     /// Send a `cancelLoginChatGpt` JSON-RPC request.
     pub async fn send_cancel_login_chat_gpt_request(
         &mut self,
@@ -296,6 +404,64 @@ impl McpProcess {
         self.send_request("logoutChatGpt", None).await
     }
 
+    pub async fn send_config_read_request(
+        &mut self,
+        params: ConfigReadParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("config/read", params).await
+    }
+
+    pub async fn send_config_value_write_request(
+        &mut self,
+        params: ConfigValueWriteParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("config/value/write", params).await
+    }
+
+    pub async fn send_config_batch_write_request(
+        &mut self,
+        params: ConfigBatchWriteParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("config/batchWrite", params).await
+    }
+
+    /// Send an `account/logout` JSON-RPC request.
+    pub async fn send_logout_account_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("account/logout", None).await
+    }
+
+    /// Send an `account/login/start` JSON-RPC request for API key login.
+    pub async fn send_login_account_api_key_request(
+        &mut self,
+        api_key: &str,
+    ) -> anyhow::Result<i64> {
+        let params = serde_json::json!({
+            "type": "apiKey",
+            "apiKey": api_key,
+        });
+        self.send_request("account/login/start", Some(params)).await
+    }
+
+    /// Send an `account/login/start` JSON-RPC request for ChatGPT login.
+    pub async fn send_login_account_chatgpt_request(&mut self) -> anyhow::Result<i64> {
+        let params = serde_json::json!({
+            "type": "chatgpt"
+        });
+        self.send_request("account/login/start", Some(params)).await
+    }
+
+    /// Send an `account/login/cancel` JSON-RPC request.
+    pub async fn send_cancel_login_account_request(
+        &mut self,
+        params: CancelLoginAccountParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/login/cancel", params).await
+    }
+
     /// Send a `fuzzyFileSearch` JSON-RPC request.
     pub async fn send_fuzzy_file_search_request(
         &mut self,

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

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

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

@@ -0,0 +1,85 @@
+use chrono::DateTime;
+use chrono::Utc;
+use codex_core::openai_models::model_presets::all_model_presets;
+use codex_protocol::openai_models::ClientVersion;
+use codex_protocol::openai_models::ConfigShellToolType;
+use codex_protocol::openai_models::ModelInfo;
+use codex_protocol::openai_models::ModelPreset;
+use codex_protocol::openai_models::ModelVisibility;
+use codex_protocol::openai_models::ReasoningSummaryFormat;
+use codex_protocol::openai_models::TruncationPolicyConfig;
+use serde_json::json;
+use std::path::Path;
+
+/// Convert a ModelPreset to ModelInfo for cache storage.
+fn preset_to_info(preset: &ModelPreset, priority: i32) -> ModelInfo {
+    ModelInfo {
+        slug: preset.id.clone(),
+        display_name: preset.display_name.clone(),
+        description: Some(preset.description.clone()),
+        default_reasoning_level: preset.default_reasoning_effort,
+        supported_reasoning_levels: preset.supported_reasoning_efforts.clone(),
+        shell_type: ConfigShellToolType::ShellCommand,
+        visibility: if preset.show_in_picker {
+            ModelVisibility::List
+        } else {
+            ModelVisibility::Hide
+        },
+        minimal_client_version: ClientVersion(0, 1, 0),
+        supported_in_api: true,
+        priority,
+        upgrade: preset.upgrade.as_ref().map(|u| u.id.clone()),
+        base_instructions: None,
+        supports_reasoning_summaries: false,
+        support_verbosity: false,
+        default_verbosity: None,
+        apply_patch_tool_type: None,
+        truncation_policy: TruncationPolicyConfig::bytes(10_000),
+        supports_parallel_tool_calls: false,
+        context_window: None,
+        reasoning_summary_format: ReasoningSummaryFormat::None,
+        experimental_supported_tools: Vec::new(),
+    }
+}
+
+/// Write a models_cache.json file to the codex home directory.
+/// This prevents ModelsManager from making network requests to refresh models.
+/// The cache will be treated as fresh (within TTL) and used instead of fetching from the network.
+/// Uses the built-in model presets from ModelsManager, converted to ModelInfo format.
+pub fn write_models_cache(codex_home: &Path) -> std::io::Result<()> {
+    // Get all presets and filter for show_in_picker (same as builtin_model_presets does)
+    let presets: Vec<&ModelPreset> = all_model_presets()
+        .iter()
+        .filter(|preset| preset.show_in_picker)
+        .collect();
+    // Convert presets to ModelInfo, assigning priorities (higher = earlier in list)
+    // Priority is used for sorting, so first model gets highest priority
+    let models: Vec<ModelInfo> = presets
+        .iter()
+        .enumerate()
+        .map(|(idx, preset)| {
+            // Higher priority = earlier in list, so reverse the index
+            let priority = (presets.len() - idx) as i32;
+            preset_to_info(preset, priority)
+        })
+        .collect();
+
+    write_models_cache_with_models(codex_home, models)
+}
+
+/// Write a models_cache.json file with specific models.
+/// Useful when tests need specific models to be available.
+pub fn write_models_cache_with_models(
+    codex_home: &Path,
+    models: Vec<ModelInfo>,
+) -> std::io::Result<()> {
+    let cache_path = codex_home.join("models_cache.json");
+    // DateTime<Utc> serializes to RFC3339 format by default with serde
+    let fetched_at: DateTime<Utc> = Utc::now();
+    let cache = json!({
+        "fetched_at": fetched_at,
+        "etag": null,
+        "models": models
+    });
+    std::fs::write(cache_path, serde_json::to_string_pretty(&cache)?)
+}

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

@@ -1,17 +1,18 @@
 use serde_json::json;
 use std::path::Path;
 
-pub fn create_shell_sse_response(
+pub fn create_shell_command_sse_response(
     command: Vec<String>,
     workdir: Option<&Path>,
     timeout_ms: Option<u64>,
     call_id: &str,
 ) -> anyhow::Result<String> {
-    // The `arguments`` for the `shell` tool is a serialized JSON object.
+    // The `arguments` for the `shell_command` tool is a serialized JSON object.
+    let command_str = shlex::try_join(command.iter().map(String::as_str))?;
     let tool_call_arguments = serde_json::to_string(&json!({
-        "command": command,
+        "command": command_str,
         "workdir": workdir.map(|w| w.to_string_lossy()),
-        "timeout": timeout_ms
+        "timeout_ms": timeout_ms
     }))?;
     let tool_call = json!({
         "choices": [
@@ -21,7 +22,7 @@ pub fn create_shell_sse_response(
                         {
                             "id": call_id,
                             "function": {
-                                "name": "shell",
+                                "name": "shell_command",
                                 "arguments": tool_call_arguments
                             }
                         }
@@ -62,10 +63,10 @@ pub fn create_apply_patch_sse_response(
     patch_content: &str,
     call_id: &str,
 ) -> anyhow::Result<String> {
-    // Use shell command to call apply_patch with heredoc format
-    let shell_command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
+    // Use shell_command to call apply_patch with heredoc format
+    let command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
     let tool_call_arguments = serde_json::to_string(&json!({
-        "command": ["bash", "-lc", shell_command]
+        "command": command
     }))?;
 
     let tool_call = json!({
@@ -76,7 +77,46 @@ pub fn create_apply_patch_sse_response(
                         {
                             "id": call_id,
                             "function": {
-                                "name": "shell",
+                                "name": "shell_command",
+                                "arguments": tool_call_arguments
+                            }
+                        }
+                    ]
+                },
+                "finish_reason": "tool_calls"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&tool_call)?
+    );
+    Ok(sse)
+}
+
+pub fn create_exec_command_sse_response(call_id: &str) -> anyhow::Result<String> {
+    let (cmd, args) = if cfg!(windows) {
+        ("cmd.exe", vec!["/d", "/c", "echo hi"])
+    } else {
+        ("/bin/sh", vec!["-c", "echo hi"])
+    };
+    let command = std::iter::once(cmd.to_string())
+        .chain(args.into_iter().map(str::to_string))
+        .collect::<Vec<_>>();
+    let tool_call_arguments = serde_json::to_string(&json!({
+        "cmd": command.join(" "),
+        "yield_time_ms": 500
+    }))?;
+    let tool_call = json!({
+        "choices": [
+            {
+                "delta": {
+                    "tool_calls": [
+                        {
+                            "id": call_id,
+                            "function": {
+                                "name": "exec_command",
                                 "arguments": tool_call_arguments
                             }
                         }

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

@@ -0,0 +1,89 @@
+use anyhow::Result;
+use codex_protocol::ConversationId;
+use codex_protocol::protocol::GitInfo;
+use codex_protocol::protocol::SessionMeta;
+use codex_protocol::protocol::SessionMetaLine;
+use codex_protocol::protocol::SessionSource;
+use serde_json::json;
+use std::fs;
+use std::path::Path;
+use std::path::PathBuf;
+use uuid::Uuid;
+
+/// Create a minimal rollout file under `CODEX_HOME/sessions/YYYY/MM/DD/`.
+///
+/// - `filename_ts` is the filename timestamp component in `YYYY-MM-DDThh-mm-ss` format.
+/// - `meta_rfc3339` is the envelope timestamp used in JSON lines.
+/// - `preview` is the user message preview text.
+/// - `model_provider` optionally sets the provider in the session meta payload.
+///
+/// Returns the generated conversation/session UUID as a string.
+pub fn create_fake_rollout(
+    codex_home: &Path,
+    filename_ts: &str,
+    meta_rfc3339: &str,
+    preview: &str,
+    model_provider: Option<&str>,
+    git_info: Option<GitInfo>,
+) -> Result<String> {
+    let uuid = Uuid::new_v4();
+    let uuid_str = uuid.to_string();
+    let conversation_id = ConversationId::from_string(&uuid_str)?;
+
+    // sessions/YYYY/MM/DD derived from filename_ts (YYYY-MM-DDThh-mm-ss)
+    let year = &filename_ts[0..4];
+    let month = &filename_ts[5..7];
+    let day = &filename_ts[8..10];
+    let dir = codex_home.join("sessions").join(year).join(month).join(day);
+    fs::create_dir_all(&dir)?;
+
+    let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
+
+    // Build JSONL lines
+    let meta = SessionMeta {
+        id: conversation_id,
+        timestamp: meta_rfc3339.to_string(),
+        cwd: PathBuf::from("/"),
+        originator: "codex".to_string(),
+        cli_version: "0.0.0".to_string(),
+        instructions: None,
+        source: SessionSource::Cli,
+        model_provider: model_provider.map(str::to_string),
+    };
+    let 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,
+                "kind": "plain"
+            }
+        })
+        .to_string(),
+    ];
+
+    fs::write(file_path, lines.join("\n") + "\n")?;
+    Ok(uuid_str)
+}

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

@@ -1,5 +1,4 @@
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
 use codex_app_server_protocol::ArchiveConversationParams;
@@ -9,45 +8,37 @@ use codex_app_server_protocol::NewConversationParams;
 use codex_app_server_protocol::NewConversationResponse;
 use codex_app_server_protocol::RequestId;
 use codex_core::ARCHIVED_SESSIONS_SUBDIR;
+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 DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(20);
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn archive_conversation_moves_rollout_into_archived_directory() {
-    let codex_home = TempDir::new().expect("create temp dir");
-    create_config_toml(codex_home.path()).expect("write config.toml");
+async fn archive_conversation_moves_rollout_into_archived_directory() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("initialize timeout")
-        .expect("initialize request");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let new_request_id = mcp
         .send_new_conversation_request(NewConversationParams {
             model: Some("mock-model".to_string()),
             ..Default::default()
         })
-        .await
-        .expect("send newConversation");
+        .await?;
     let new_response: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(new_request_id)),
     )
-    .await
-    .expect("newConversation timeout")
-    .expect("newConversation response");
+    .await??;
 
     let NewConversationResponse {
         conversation_id,
         rollout_path,
         ..
-    } = to_response::<NewConversationResponse>(new_response)
-        .expect("deserialize newConversation response");
+    } = to_response::<NewConversationResponse>(new_response)?;
 
     assert!(
         rollout_path.exists(),
@@ -60,19 +51,15 @@ async fn archive_conversation_moves_rollout_into_archived_directory() {
             conversation_id,
             rollout_path: rollout_path.clone(),
         })
-        .await
-        .expect("send archiveConversation");
+        .await?;
     let archive_response: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(archive_request_id)),
     )
-    .await
-    .expect("archiveConversation timeout")
-    .expect("archiveConversation response");
+    .await??;
 
     let _: ArchiveConversationResponse =
-        to_response::<ArchiveConversationResponse>(archive_response)
-            .expect("deserialize archiveConversation response");
+        to_response::<ArchiveConversationResponse>(archive_response)?;
 
     let archived_directory = codex_home.path().join(ARCHIVED_SESSIONS_SUBDIR);
     let archived_rollout_path =
@@ -90,6 +77,8 @@ async fn archive_conversation_moves_rollout_into_archived_directory() {
         "expected archived rollout path {} to exist",
         archived_rollout_path.display()
     );
+
+    Ok(())
 }
 
 fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {

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

@@ -1,15 +1,16 @@
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
 use codex_app_server_protocol::AuthMode;
 use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::GetAuthStatusResponse;
+use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::LoginApiKeyParams;
 use codex_app_server_protocol::LoginApiKeyResponse;
 use codex_app_server_protocol::RequestId;
 use pretty_assertions::assert_eq;
+use std::path::Path;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
@@ -57,125 +58,112 @@ sandbox_mode = "danger-full-access"
     )
 }
 
-async fn login_with_api_key_via_request(mcp: &mut McpProcess, api_key: &str) {
+fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+forced_login_method = "{forced_method}"
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+async fn login_with_api_key_via_request(mcp: &mut McpProcess, api_key: &str) -> Result<()> {
     let request_id = mcp
         .send_login_api_key_request(LoginApiKeyParams {
             api_key: api_key.to_string(),
         })
-        .await
-        .unwrap_or_else(|e| panic!("send loginApiKey: {e}"));
+        .await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .unwrap_or_else(|e| panic!("loginApiKey timeout: {e}"))
-    .unwrap_or_else(|e| panic!("loginApiKey response: {e}"));
-    let _: LoginApiKeyResponse =
-        to_response(resp).unwrap_or_else(|e| panic!("deserialize login response: {e}"));
+    .await??;
+    let _: LoginApiKeyResponse = to_response(resp)?;
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn get_auth_status_no_auth() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
+async fn get_auth_status_no_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
 
-    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)])
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let request_id = mcp
         .send_get_auth_status_request(GetAuthStatusParams {
             include_token: Some(true),
             refresh_token: Some(false),
         })
-        .await
-        .expect("send getAuthStatus");
+        .await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getAuthStatus timeout")
-    .expect("getAuthStatus response");
-    let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
     assert_eq!(status.auth_method, None, "expected no auth method");
     assert_eq!(status.auth_token, None, "expected no token");
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn get_auth_status_with_api_key() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
+async fn get_auth_status_with_api_key() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    login_with_api_key_via_request(&mut mcp, "sk-test-key").await;
+    login_with_api_key_via_request(&mut mcp, "sk-test-key").await?;
 
     let request_id = mcp
         .send_get_auth_status_request(GetAuthStatusParams {
             include_token: Some(true),
             refresh_token: Some(false),
         })
-        .await
-        .expect("send getAuthStatus");
+        .await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getAuthStatus timeout")
-    .expect("getAuthStatus response");
-    let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
     assert_eq!(status.auth_method, Some(AuthMode::ApiKey));
     assert_eq!(status.auth_token, Some("sk-test-key".to_string()));
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn get_auth_status_with_api_key_when_auth_not_required() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml_custom_provider(codex_home.path(), false)
-        .unwrap_or_else(|err| panic!("write config.toml: {err}"));
+async fn get_auth_status_with_api_key_when_auth_not_required() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_custom_provider(codex_home.path(), false)?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    login_with_api_key_via_request(&mut mcp, "sk-test-key").await;
+    login_with_api_key_via_request(&mut mcp, "sk-test-key").await?;
 
     let request_id = mcp
         .send_get_auth_status_request(GetAuthStatusParams {
             include_token: Some(true),
             refresh_token: Some(false),
         })
-        .await
-        .expect("send getAuthStatus");
+        .await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getAuthStatus timeout")
-    .expect("getAuthStatus response");
-    let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
     assert_eq!(status.auth_method, None, "expected no auth method");
     assert_eq!(status.auth_token, None, "expected no token");
     assert_eq!(
@@ -183,41 +171,60 @@ async fn get_auth_status_with_api_key_when_auth_not_required() {
         Some(false),
         "requires_openai_auth should be false",
     );
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn get_auth_status_with_api_key_no_include_token() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
+async fn get_auth_status_with_api_key_no_include_token() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    login_with_api_key_via_request(&mut mcp, "sk-test-key").await;
+    login_with_api_key_via_request(&mut mcp, "sk-test-key").await?;
 
     // Build params via struct so None field is omitted in wire JSON.
     let params = GetAuthStatusParams {
         include_token: None,
         refresh_token: Some(false),
     };
-    let request_id = mcp
-        .send_get_auth_status_request(params)
-        .await
-        .expect("send getAuthStatus");
+    let request_id = mcp.send_get_auth_status_request(params).await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getAuthStatus timeout")
-    .expect("getAuthStatus response");
-    let status: GetAuthStatusResponse = to_response(resp).expect("deserialize status");
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
     assert_eq!(status.auth_method, Some(AuthMode::ApiKey));
     assert!(status.auth_token.is_none(), "token must be omitted");
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn login_api_key_rejected_when_forced_chatgpt() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_forced_login(codex_home.path(), "chatgpt")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_login_api_key_request(LoginApiKeyParams {
+            api_key: "sk-test-key".to_string(),
+        })
+        .await?;
+
+    let err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(
+        err.error.message,
+        "API key login is disabled. Use ChatGPT login instead."
+    );
+    Ok(())
 }

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

@@ -1,9 +1,9 @@
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_final_assistant_message_sse_response;
 use app_test_support::create_mock_chat_completions_server;
-use app_test_support::create_shell_sse_response;
+use app_test_support::create_shell_command_sse_response;
+use app_test_support::format_with_current_shell;
 use app_test_support::to_response;
 use codex_app_server_protocol::AddConversationListenerParams;
 use codex_app_server_protocol::AddConversationSubscriptionResponse;
@@ -23,58 +23,54 @@ use codex_app_server_protocol::SendUserTurnResponse;
 use codex_app_server_protocol::ServerRequest;
 use codex_core::protocol::AskForApproval;
 use codex_core::protocol::SandboxPolicy;
-use codex_core::protocol_config_types::ReasoningEffort;
 use codex_core::protocol_config_types::ReasoningSummary;
 use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
 use codex_protocol::config_types::SandboxMode;
+use codex_protocol::openai_models::ReasoningEffort;
+use codex_protocol::parse_command::ParsedCommand;
 use codex_protocol::protocol::Event;
 use codex_protocol::protocol::EventMsg;
-use codex_protocol::protocol::InputMessageKind;
 use pretty_assertions::assert_eq;
 use std::env;
+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(flavor = "multi_thread", worker_threads = 4)]
-async fn test_codex_jsonrpc_conversation_flow() {
+async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
     if env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
         println!(
             "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
         );
-        return;
+        return Ok(());
     }
 
-    let tmp = TempDir::new().expect("tmp dir");
+    let tmp = TempDir::new()?;
     // Temporary Codex home with config pointing at the mock server.
     let codex_home = tmp.path().join("codex_home");
-    std::fs::create_dir(&codex_home).expect("create codex home dir");
+    std::fs::create_dir(&codex_home)?;
     let working_directory = tmp.path().join("workdir");
-    std::fs::create_dir(&working_directory).expect("create working directory");
+    std::fs::create_dir(&working_directory)?;
 
     // Create a mock model server that immediately ends each turn.
     // Two turns are expected: initial session configure + one user message.
     let responses = vec![
-        create_shell_sse_response(
+        create_shell_command_sse_response(
             vec!["ls".to_string()],
             Some(&working_directory),
             Some(5000),
             "call1234",
-        )
-        .expect("create shell sse response"),
-        create_final_assistant_message_sse_response("Enjoy your new git repo!")
-            .expect("create final assistant message"),
+        )?,
+        create_final_assistant_message_sse_response("Enjoy your new git repo!")?,
     ];
     let server = create_mock_chat_completions_server(responses).await;
-    create_config_toml(&codex_home, &server.uri()).expect("write config");
+    create_config_toml(&codex_home, &server.uri())?;
 
     // Start MCP server and initialize.
-    let mut mcp = McpProcess::new(&codex_home).await.expect("spawn mcp");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init error");
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     // 1) newConversation
     let new_conv_id = mcp
@@ -82,17 +78,13 @@ async fn test_codex_jsonrpc_conversation_flow() {
             cwd: Some(working_directory.to_string_lossy().into_owned()),
             ..Default::default()
         })
-        .await
-        .expect("send newConversation");
+        .await?;
     let new_conv_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
     )
-    .await
-    .expect("newConversation timeout")
-    .expect("newConversation resp");
-    let new_conv_resp = to_response::<NewConversationResponse>(new_conv_resp)
-        .expect("deserialize newConversation response");
+    .await??;
+    let new_conv_resp = to_response::<NewConversationResponse>(new_conv_resp)?;
     let NewConversationResponse {
         conversation_id,
         model,
@@ -103,19 +95,18 @@ async fn test_codex_jsonrpc_conversation_flow() {
 
     // 2) addConversationListener
     let add_listener_id = mcp
-        .send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
-        .await
-        .expect("send addConversationListener");
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
     let add_listener_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
     )
-    .await
-    .expect("addConversationListener timeout")
-    .expect("addConversationListener resp");
+    .await??;
     let AddConversationSubscriptionResponse { subscription_id } =
-        to_response::<AddConversationSubscriptionResponse>(add_listener_resp)
-            .expect("deserialize addConversationListener response");
+        to_response::<AddConversationSubscriptionResponse>(add_listener_resp)?;
 
     // 3) sendUserMessage (should trigger notifications; we only validate an OK response)
     let send_user_id = mcp
@@ -125,17 +116,13 @@ async fn test_codex_jsonrpc_conversation_flow() {
                 text: "text".to_string(),
             }],
         })
-        .await
-        .expect("send sendUserMessage");
+        .await?;
     let send_user_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
     )
-    .await
-    .expect("sendUserMessage timeout")
-    .expect("sendUserMessage resp");
-    let SendUserMessageResponse {} = to_response::<SendUserMessageResponse>(send_user_resp)
-        .expect("deserialize sendUserMessage response");
+    .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.
@@ -143,9 +130,7 @@ async fn test_codex_jsonrpc_conversation_flow() {
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
-    .await
-    .expect("task_finished_notification timeout")
-    .expect("task_finished_notification resp");
+    .await??;
     let serde_json::Value::Object(map) = task_finished_notification
         .params
         .expect("notification should have params")
@@ -163,37 +148,35 @@ async fn test_codex_jsonrpc_conversation_flow() {
         .send_remove_conversation_listener_request(RemoveConversationListenerParams {
             subscription_id,
         })
-        .await
-        .expect("send removeConversationListener");
+        .await?;
     let remove_listener_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(remove_listener_id)),
     )
-    .await
-    .expect("removeConversationListener timeout")
-    .expect("removeConversationListener resp");
-    let RemoveConversationSubscriptionResponse {} =
-        to_response(remove_listener_resp).expect("deserialize removeConversationListener response");
+    .await??;
+    let RemoveConversationSubscriptionResponse {} = to_response(remove_listener_resp)?;
+
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 4)]
-async fn test_send_user_turn_changes_approval_policy_behavior() {
+async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
     if env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
         println!(
             "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
         );
-        return;
+        return Ok(());
     }
 
-    let tmp = TempDir::new().expect("tmp dir");
+    let tmp = TempDir::new()?;
     let codex_home = tmp.path().join("codex_home");
-    std::fs::create_dir(&codex_home).expect("create codex home dir");
+    std::fs::create_dir(&codex_home)?;
     let working_directory = tmp.path().join("workdir");
-    std::fs::create_dir(&working_directory).expect("create working directory");
+    std::fs::create_dir(&working_directory)?;
 
     // Mock server will request a python shell call for the first and second turn, then finish.
     let responses = vec![
-        create_shell_sse_response(
+        create_shell_command_sse_response(
             vec![
                 "python3".to_string(),
                 "-c".to_string(),
@@ -202,11 +185,9 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
             Some(&working_directory),
             Some(5000),
             "call1",
-        )
-        .expect("create first shell sse response"),
-        create_final_assistant_message_sse_response("done 1")
-            .expect("create final assistant message 1"),
-        create_shell_sse_response(
+        )?,
+        create_final_assistant_message_sse_response("done 1")?,
+        create_shell_command_sse_response(
             vec![
                 "python3".to_string(),
                 "-c".to_string(),
@@ -215,20 +196,15 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
             Some(&working_directory),
             Some(5000),
             "call2",
-        )
-        .expect("create second shell sse response"),
-        create_final_assistant_message_sse_response("done 2")
-            .expect("create final assistant message 2"),
+        )?,
+        create_final_assistant_message_sse_response("done 2")?,
     ];
     let server = create_mock_chat_completions_server(responses).await;
-    create_config_toml(&codex_home, &server.uri()).expect("write config");
+    create_config_toml(&codex_home, &server.uri())?;
 
     // Start MCP server and initialize.
-    let mut mcp = McpProcess::new(&codex_home).await.expect("spawn mcp");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init error");
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     // 1) Start conversation with approval_policy=untrusted
     let new_conv_id = mcp
@@ -236,36 +212,30 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
             cwd: Some(working_directory.to_string_lossy().into_owned()),
             ..Default::default()
         })
-        .await
-        .expect("send newConversation");
+        .await?;
     let new_conv_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
     )
-    .await
-    .expect("newConversation timeout")
-    .expect("newConversation resp");
+    .await??;
     let NewConversationResponse {
         conversation_id, ..
-    } = to_response::<NewConversationResponse>(new_conv_resp)
-        .expect("deserialize newConversation response");
+    } = to_response::<NewConversationResponse>(new_conv_resp)?;
 
     // 2) addConversationListener
     let add_listener_id = mcp
-        .send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
-        .await
-        .expect("send addConversationListener");
-    let _: AddConversationSubscriptionResponse =
-        to_response::<AddConversationSubscriptionResponse>(
-            timeout(
-                DEFAULT_READ_TIMEOUT,
-                mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
-            )
-            .await
-            .expect("addConversationListener timeout")
-            .expect("addConversationListener resp"),
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let _: AddConversationSubscriptionResponse = to_response::<AddConversationSubscriptionResponse>(
+        timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
         )
-        .expect("deserialize addConversationListener response");
+        .await??,
+    )?;
 
     // 3) sendUserMessage triggers a shell call; approval policy is Untrusted so we should get an elicitation
     let send_user_id = mcp
@@ -275,27 +245,21 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
                 text: "run python".to_string(),
             }],
         })
-        .await
-        .expect("send sendUserMessage");
+        .await?;
     let _send_user_resp: SendUserMessageResponse = to_response::<SendUserMessageResponse>(
         timeout(
             DEFAULT_READ_TIMEOUT,
             mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
         )
-        .await
-        .expect("sendUserMessage timeout")
-        .expect("sendUserMessage resp"),
-    )
-    .expect("deserialize sendUserMessage response");
+        .await??,
+    )?;
 
     // Expect an ExecCommandApproval request (elicitation)
     let request = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_request_message(),
     )
-    .await
-    .expect("waiting for exec approval request timeout")
-    .expect("exec approval request");
+    .await??;
     let ServerRequest::ExecCommandApproval { request_id, params } = request else {
         panic!("expected ExecCommandApproval request, got: {request:?}");
     };
@@ -304,13 +268,12 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
         ExecCommandApprovalParams {
             conversation_id,
             call_id: "call1".to_string(),
-            command: vec![
-                "python3".to_string(),
-                "-c".to_string(),
-                "print(42)".to_string(),
-            ],
+            command: format_with_current_shell("python3 -c 'print(42)'"),
             cwd: working_directory.clone(),
             reason: None,
+            parsed_cmd: vec![ParsedCommand::Unknown {
+                cmd: "python3 -c 'print(42)'".to_string()
+            }],
         },
         params
     );
@@ -320,17 +283,14 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
         request_id,
         serde_json::json!({ "decision": codex_core::protocol::ReviewDecision::Approved }),
     )
-    .await
-    .expect("send approval response");
+    .await?;
 
     // Wait for first TaskComplete
     let _ = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
-    .await
-    .expect("task_complete 1 timeout")
-    .expect("task_complete 1 notification");
+    .await??;
 
     // 4) sendUserTurn with approval_policy=never should run without elicitation
     let send_turn_id = mcp
@@ -346,19 +306,15 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
             effort: Some(ReasoningEffort::Medium),
             summary: ReasoningSummary::Auto,
         })
-        .await
-        .expect("send sendUserTurn");
+        .await?;
     // Acknowledge sendUserTurn
     let _send_turn_resp: SendUserTurnResponse = to_response::<SendUserTurnResponse>(
         timeout(
             DEFAULT_READ_TIMEOUT,
             mcp.read_stream_until_response_message(RequestId::Integer(send_turn_id)),
         )
-        .await
-        .expect("sendUserTurn timeout")
-        .expect("sendUserTurn resp"),
-    )
-    .expect("deserialize sendUserTurn response");
+        .await??,
+    )?;
 
     // Ensure we do NOT receive an ExecCommandApproval request before the task completes.
     // If any Request is seen while waiting for task_complete, the helper will error and the test fails.
@@ -366,70 +322,53 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
-    .await
-    .expect("task_complete 2 timeout")
-    .expect("task_complete 2 notification");
+    .await??;
+
+    Ok(())
 }
 
 // Helper: minimal config.toml pointing at mock provider.
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 4)]
-async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
+async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<()> {
     if env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
         println!(
             "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
         );
-        return;
+        return Ok(());
     }
 
-    let tmp = TempDir::new().expect("tmp dir");
+    let tmp = TempDir::new()?;
     let codex_home = tmp.path().join("codex_home");
-    std::fs::create_dir(&codex_home).expect("create codex home dir");
+    std::fs::create_dir(&codex_home)?;
     let workspace_root = tmp.path().join("workspace");
-    std::fs::create_dir(&workspace_root).expect("create workspace root");
+    std::fs::create_dir(&workspace_root)?;
     let first_cwd = workspace_root.join("turn1");
     let second_cwd = workspace_root.join("turn2");
-    std::fs::create_dir(&first_cwd).expect("create first cwd");
-    std::fs::create_dir(&second_cwd).expect("create second cwd");
+    std::fs::create_dir(&first_cwd)?;
+    std::fs::create_dir(&second_cwd)?;
 
     let responses = vec![
-        create_shell_sse_response(
-            vec![
-                "bash".to_string(),
-                "-lc".to_string(),
-                "echo first turn".to_string(),
-            ],
+        create_shell_command_sse_response(
+            vec!["echo".to_string(), "first".to_string(), "turn".to_string()],
             None,
             Some(5000),
             "call-first",
-        )
-        .expect("create first shell response"),
-        create_final_assistant_message_sse_response("done first")
-            .expect("create first final assistant message"),
-        create_shell_sse_response(
-            vec![
-                "bash".to_string(),
-                "-lc".to_string(),
-                "echo second turn".to_string(),
-            ],
+        )?,
+        create_final_assistant_message_sse_response("done first")?,
+        create_shell_command_sse_response(
+            vec!["echo".to_string(), "second".to_string(), "turn".to_string()],
             None,
             Some(5000),
             "call-second",
-        )
-        .expect("create second shell response"),
-        create_final_assistant_message_sse_response("done second")
-            .expect("create second final assistant message"),
+        )?,
+        create_final_assistant_message_sse_response("done second")?,
     ];
     let server = create_mock_chat_completions_server(responses).await;
-    create_config_toml(&codex_home, &server.uri()).expect("write config");
+    create_config_toml(&codex_home, &server.uri())?;
 
-    let mut mcp = McpProcess::new(&codex_home)
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let new_conv_id = mcp
         .send_new_conversation_request(NewConversationParams {
@@ -438,33 +377,29 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
             sandbox: Some(SandboxMode::WorkspaceWrite),
             ..Default::default()
         })
-        .await
-        .expect("send newConversation");
+        .await?;
     let new_conv_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
     )
-    .await
-    .expect("newConversation timeout")
-    .expect("newConversation resp");
+    .await??;
     let NewConversationResponse {
         conversation_id,
         model,
         ..
-    } = to_response::<NewConversationResponse>(new_conv_resp)
-        .expect("deserialize newConversation response");
+    } = to_response::<NewConversationResponse>(new_conv_resp)?;
 
     let add_listener_id = mcp
-        .send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
-        .await
-        .expect("send addConversationListener");
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
     timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
     )
-    .await
-    .expect("addConversationListener timeout")
-    .expect("addConversationListener resp");
+    .await??;
 
     let first_turn_id = mcp
         .send_send_user_turn_request(SendUserTurnParams {
@@ -475,7 +410,7 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
             cwd: first_cwd.clone(),
             approval_policy: AskForApproval::Never,
             sandbox_policy: SandboxPolicy::WorkspaceWrite {
-                writable_roots: vec![first_cwd.clone()],
+                writable_roots: vec![first_cwd.try_into()?],
                 network_access: false,
                 exclude_tmpdir_env_var: false,
                 exclude_slash_tmp: false,
@@ -484,22 +419,17 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
             effort: Some(ReasoningEffort::Medium),
             summary: ReasoningSummary::Auto,
         })
-        .await
-        .expect("send first sendUserTurn");
+        .await?;
     timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(first_turn_id)),
     )
-    .await
-    .expect("sendUserTurn 1 timeout")
-    .expect("sendUserTurn 1 resp");
+    .await??;
     timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
-    .await
-    .expect("task_complete 1 timeout")
-    .expect("task_complete 1 notification");
+    .await??;
 
     let second_turn_id = mcp
         .send_send_user_turn_request(SendUserTurnParams {
@@ -514,60 +444,18 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
             effort: Some(ReasoningEffort::Medium),
             summary: ReasoningSummary::Auto,
         })
-        .await
-        .expect("send second sendUserTurn");
+        .await?;
     timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(second_turn_id)),
     )
-    .await
-    .expect("sendUserTurn 2 timeout")
-    .expect("sendUserTurn 2 resp");
-
-    let mut env_message: Option<String> = None;
-    let second_cwd_str = second_cwd.to_string_lossy().into_owned();
-    for _ in 0..10 {
-        let notification = timeout(
-            DEFAULT_READ_TIMEOUT,
-            mcp.read_stream_until_notification_message("codex/event/user_message"),
-        )
-        .await
-        .expect("user_message timeout")
-        .expect("user_message notification");
-        let params = notification
-            .params
-            .clone()
-            .expect("user_message should include params");
-        let event: Event = serde_json::from_value(params).expect("deserialize user_message event");
-        if let EventMsg::UserMessage(user) = event.msg
-            && matches!(user.kind, Some(InputMessageKind::EnvironmentContext))
-            && user.message.contains(&second_cwd_str)
-        {
-            env_message = Some(user.message);
-            break;
-        }
-    }
-    let env_message = env_message.expect("expected environment context update");
-    assert!(
-        env_message.contains("<sandbox_mode>danger-full-access</sandbox_mode>"),
-        "env context should reflect new sandbox mode: {env_message}"
-    );
-    assert!(
-        env_message.contains("<network_access>enabled</network_access>"),
-        "env context should enable network access for danger-full-access policy: {env_message}"
-    );
-    assert!(
-        env_message.contains(&second_cwd_str),
-        "env context should include updated cwd: {env_message}"
-    );
+    .await??;
 
     let exec_begin_notification = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/exec_command_begin"),
     )
-    .await
-    .expect("exec_command_begin timeout")
-    .expect("exec_command_begin notification");
+    .await??;
     let params = exec_begin_notification
         .params
         .clone()
@@ -581,13 +469,9 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
         exec_begin.cwd, second_cwd,
         "exec turn should run from updated cwd"
     );
+    let expected_command = format_with_current_shell("echo second turn");
     assert_eq!(
-        exec_begin.command,
-        vec![
-            "bash".to_string(),
-            "-lc".to_string(),
-            "echo second turn".to_string()
-        ],
+        exec_begin.command, expected_command,
         "exec turn should run expected command"
     );
 
@@ -595,9 +479,9 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
-    .await
-    .expect("task_complete 2 timeout")
-    .expect("task_complete 2 notification");
+    .await??;
+
+    Ok(())
 }
 
 fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {

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

@@ -1,7 +1,6 @@
-use std::collections::HashMap;
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
+use app_test_support::test_tmp_path;
 use app_test_support::to_response;
 use codex_app_server_protocol::GetUserSavedConfigResponse;
 use codex_app_server_protocol::JSONRPCResponse;
@@ -11,31 +10,38 @@ use codex_app_server_protocol::SandboxSettings;
 use codex_app_server_protocol::Tools;
 use codex_app_server_protocol::UserSavedConfig;
 use codex_core::protocol::AskForApproval;
-use codex_protocol::config_types::ReasoningEffort;
+use codex_protocol::config_types::ForcedLoginMethod;
 use codex_protocol::config_types::ReasoningSummary;
 use codex_protocol::config_types::SandboxMode;
 use codex_protocol::config_types::Verbosity;
+use codex_protocol::openai_models::ReasoningEffort;
 use pretty_assertions::assert_eq;
+use std::collections::HashMap;
+use std::path::Path;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
 fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let writable_root = test_tmp_path();
     let config_toml = codex_home.join("config.toml");
     std::fs::write(
         config_toml,
-        r#"
-model = "gpt-5-codex"
+        format!(
+            r#"
+model = "gpt-5.1-codex-max"
 approval_policy = "on-request"
 sandbox_mode = "workspace-write"
 model_reasoning_summary = "detailed"
 model_reasoning_effort = "high"
 model_verbosity = "medium"
 profile = "test"
+forced_chatgpt_workspace_id = "12345678-0000-0000-0000-000000000000"
+forced_login_method = "chatgpt"
 
 [sandbox_workspace_write]
-writable_roots = ["/tmp"]
+writable_roots = [{}]
 network_access = true
 exclude_tmpdir_env_var = true
 exclude_slash_tmp = true
@@ -53,46 +59,41 @@ model_verbosity = "medium"
 model_provider = "openai"
 chatgpt_base_url = "https://api.chatgpt.com"
 "#,
+            serde_json::json!(writable_root)
+        ),
     )
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 4)]
-async fn get_config_toml_parses_all_fields() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml(codex_home.path()).expect("write config.toml");
+async fn get_config_toml_parses_all_fields() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let request_id = mcp
-        .send_get_user_saved_config_request()
-        .await
-        .expect("send getUserSavedConfig");
+    let request_id = mcp.send_get_user_saved_config_request().await?;
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getUserSavedConfig timeout")
-    .expect("getUserSavedConfig response");
+    .await??;
 
-    let config: GetUserSavedConfigResponse = to_response(resp).expect("deserialize config");
+    let config: GetUserSavedConfigResponse = to_response(resp)?;
+    let writable_root = test_tmp_path();
     let expected = GetUserSavedConfigResponse {
         config: UserSavedConfig {
             approval_policy: Some(AskForApproval::OnRequest),
             sandbox_mode: Some(SandboxMode::WorkspaceWrite),
             sandbox_settings: Some(SandboxSettings {
-                writable_roots: vec!["/tmp".into()],
+                writable_roots: vec![writable_root],
                 network_access: Some(true),
                 exclude_tmpdir_env_var: Some(true),
                 exclude_slash_tmp: Some(true),
             }),
-            model: Some("gpt-5-codex".into()),
+            forced_chatgpt_workspace_id: Some("12345678-0000-0000-0000-000000000000".into()),
+            forced_login_method: Some(ForcedLoginMethod::Chatgpt),
+            model: Some("gpt-5.1-codex-max".into()),
             model_reasoning_effort: Some(ReasoningEffort::High),
             model_reasoning_summary: Some(ReasoningSummary::Detailed),
             model_verbosity: Some(Verbosity::Medium),
@@ -117,38 +118,31 @@ async fn get_config_toml_parses_all_fields() {
     };
 
     assert_eq!(config, expected);
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn get_config_toml_empty() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
+async fn get_config_toml_empty() -> Result<()> {
+    let codex_home = TempDir::new()?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let request_id = mcp
-        .send_get_user_saved_config_request()
-        .await
-        .expect("send getUserSavedConfig");
+    let request_id = mcp.send_get_user_saved_config_request().await?;
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getUserSavedConfig timeout")
-    .expect("getUserSavedConfig response");
+    .await??;
 
-    let config: GetUserSavedConfigResponse = to_response(resp).expect("deserialize config");
+    let config: GetUserSavedConfigResponse = to_response(resp)?;
     let expected = GetUserSavedConfigResponse {
         config: UserSavedConfig {
             approval_policy: None,
             sandbox_mode: None,
             sandbox_settings: None,
+            forced_chatgpt_workspace_id: None,
+            forced_login_method: None,
             model: None,
             model_reasoning_effort: None,
             model_reasoning_summary: None,
@@ -160,4 +154,5 @@ async fn get_config_toml_empty() {
     };
 
     assert_eq!(config, expected);
+    Ok(())
 }

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

@@ -1,5 +1,4 @@
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_final_assistant_message_sse_response;
 use app_test_support::create_mock_chat_completions_server;
@@ -15,31 +14,25 @@ use codex_app_server_protocol::SendUserMessageParams;
 use codex_app_server_protocol::SendUserMessageResponse;
 use pretty_assertions::assert_eq;
 use serde_json::json;
+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(flavor = "multi_thread", worker_threads = 2)]
-async fn test_conversation_create_and_send_message_ok() {
+async fn test_conversation_create_and_send_message_ok() -> Result<()> {
     // Mock server – we won't strictly rely on it, but provide one to satisfy any model wiring.
-    let responses = vec![
-        create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
-    ];
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
     let server = create_mock_chat_completions_server(responses).await;
 
     // Temporary Codex home with config pointing at the mock server.
-    let codex_home = TempDir::new().expect("create temp dir");
-    create_config_toml(codex_home.path(), &server.uri()).expect("write config.toml");
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
 
     // Start MCP server process and initialize.
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     // Create a conversation via the new JSON-RPC API.
     let new_conv_id = mcp
@@ -47,40 +40,35 @@ async fn test_conversation_create_and_send_message_ok() {
             model: Some("o3".to_string()),
             ..Default::default()
         })
-        .await
-        .expect("send newConversation");
+        .await?;
     let new_conv_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
     )
-    .await
-    .expect("newConversation timeout")
-    .expect("newConversation resp");
+    .await??;
     let NewConversationResponse {
         conversation_id,
         model,
         reasoning_effort: _,
         rollout_path: _,
-    } = to_response::<NewConversationResponse>(new_conv_resp)
-        .expect("deserialize newConversation response");
+    } = to_response::<NewConversationResponse>(new_conv_resp)?;
     assert_eq!(model, "o3");
 
     // Add a listener so we receive notifications for this conversation (not strictly required for this test).
     let add_listener_id = mcp
-        .send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
-        .await
-        .expect("send addConversationListener");
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
     let _sub: AddConversationSubscriptionResponse =
         to_response::<AddConversationSubscriptionResponse>(
             timeout(
                 DEFAULT_READ_TIMEOUT,
                 mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
             )
-            .await
-            .expect("addConversationListener timeout")
-            .expect("addConversationListener resp"),
-        )
-        .expect("deserialize addConversationListener response");
+            .await??,
+        )?;
 
     // Now send a user message via the wire API and expect an OK (empty object) result.
     let send_id = mcp
@@ -90,36 +78,32 @@ async fn test_conversation_create_and_send_message_ok() {
                 text: "Hello".to_string(),
             }],
         })
-        .await
-        .expect("send sendUserMessage");
+        .await?;
     let send_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
     )
-    .await
-    .expect("sendUserMessage timeout")
-    .expect("sendUserMessage resp");
-    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(send_resp)
-        .expect("deserialize sendUserMessage response");
+    .await??;
+    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(send_resp)?;
 
     // avoid race condition by waiting for the mock server to receive the chat.completions request
     let deadline = std::time::Instant::now() + DEFAULT_READ_TIMEOUT;
-    loop {
+    let requests = loop {
         let requests = server.received_requests().await.unwrap_or_default();
         if !requests.is_empty() {
-            break;
+            break requests;
         }
         if std::time::Instant::now() >= deadline {
             panic!("mock server did not receive the chat.completions request in time");
         }
         tokio::time::sleep(std::time::Duration::from_millis(10)).await;
-    }
+    };
 
     // Verify the outbound request body matches expectations for Chat Completions.
-    let request = &server.received_requests().await.unwrap()[0];
-    let body = request
-        .body_json::<serde_json::Value>()
-        .expect("parse request body as JSON");
+    let request = requests
+        .first()
+        .expect("mock server should have received at least one request");
+    let body = request.body_json::<serde_json::Value>()?;
     assert_eq!(body["model"], json!("o3"));
     assert!(body["stream"].as_bool().unwrap_or(false));
     let messages = body["messages"]
@@ -130,6 +114,7 @@ async fn test_conversation_create_and_send_message_ok() {
     assert_eq!(last["content"], json!("Hello"));
 
     drop(server);
+    Ok(())
 }
 
 // Helper to create a config.toml pointing at the mock model server.

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

@@ -1,5 +1,5 @@
-use anyhow::Context;
 use anyhow::Result;
+use anyhow::anyhow;
 use app_test_support::McpProcess;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
@@ -13,48 +13,39 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn test_fuzzy_file_search_sorts_and_includes_indices() -> Result<()> {
     // Prepare a temporary Codex home and a separate root with test files.
-    let codex_home = TempDir::new().context("create temp codex home")?;
-    let root = TempDir::new().context("create temp search root")?;
+    let codex_home = TempDir::new()?;
+    let root = TempDir::new()?;
 
     // Create files designed to have deterministic ordering for query "abe".
-    std::fs::write(root.path().join("abc"), "x").context("write file abc")?;
-    std::fs::write(root.path().join("abcde"), "x").context("write file abcde")?;
-    std::fs::write(root.path().join("abexy"), "x").context("write file abexy")?;
-    std::fs::write(root.path().join("zzz.txt"), "x").context("write file zzz")?;
+    std::fs::write(root.path().join("abc"), "x")?;
+    std::fs::write(root.path().join("abcde"), "x")?;
+    std::fs::write(root.path().join("abexy"), "x")?;
+    std::fs::write(root.path().join("zzz.txt"), "x")?;
     let sub_dir = root.path().join("sub");
-    std::fs::create_dir_all(&sub_dir).context("create sub dir")?;
+    std::fs::create_dir_all(&sub_dir)?;
     let sub_abce_path = sub_dir.join("abce");
-    std::fs::write(&sub_abce_path, "x").context("write file sub/abce")?;
+    std::fs::write(&sub_abce_path, "x")?;
     let sub_abce_rel = sub_abce_path
-        .strip_prefix(root.path())
-        .context("strip root prefix from sub/abce")?
+        .strip_prefix(root.path())?
         .to_string_lossy()
         .to_string();
 
     // Start MCP server and initialize.
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .context("spawn mcp")?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .context("init timeout")?
-        .context("init failed")?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let root_path = root.path().to_string_lossy().to_string();
     // Send fuzzyFileSearch request.
     let request_id = mcp
         .send_fuzzy_file_search_request("abe", vec![root_path.clone()], None)
-        .await
-        .context("send fuzzyFileSearch")?;
+        .await?;
 
     // Read response and verify shape and ordering.
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .context("fuzzyFileSearch timeout")?
-    .context("fuzzyFileSearch resp")?;
+    .await??;
 
     let value = resp.result;
     // The path separator on Windows affects the score.
@@ -94,24 +85,18 @@ async fn test_fuzzy_file_search_sorts_and_includes_indices() -> Result<()> {
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn test_fuzzy_file_search_accepts_cancellation_token() -> Result<()> {
-    let codex_home = TempDir::new().context("create temp codex home")?;
-    let root = TempDir::new().context("create temp search root")?;
+    let codex_home = TempDir::new()?;
+    let root = TempDir::new()?;
 
-    std::fs::write(root.path().join("alpha.txt"), "contents").context("write alpha")?;
+    std::fs::write(root.path().join("alpha.txt"), "contents")?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .context("spawn mcp")?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .context("init timeout")?
-        .context("init failed")?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let root_path = root.path().to_string_lossy().to_string();
     let request_id = mcp
         .send_fuzzy_file_search_request("alp", vec![root_path.clone()], None)
-        .await
-        .context("send fuzzyFileSearch")?;
+        .await?;
 
     let request_id_2 = mcp
         .send_fuzzy_file_search_request(
@@ -119,23 +104,20 @@ async fn test_fuzzy_file_search_accepts_cancellation_token() -> Result<()> {
             vec![root_path.clone()],
             Some(request_id.to_string()),
         )
-        .await
-        .context("send fuzzyFileSearch")?;
+        .await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id_2)),
     )
-    .await
-    .context("fuzzyFileSearch timeout")?
-    .context("fuzzyFileSearch resp")?;
+    .await??;
 
     let files = resp
         .result
         .get("files")
-        .context("files key missing")?
+        .ok_or_else(|| anyhow!("files key missing"))?
         .as_array()
-        .context("files not array")?
+        .ok_or_else(|| anyhow!("files not array"))?
         .clone();
 
     assert_eq!(files.len(), 1);

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

@@ -19,7 +19,7 @@ use tokio::time::timeout;
 
 use app_test_support::McpProcess;
 use app_test_support::create_mock_chat_completions_server;
-use app_test_support::create_shell_sse_response;
+use app_test_support::create_shell_command_sse_response;
 use app_test_support::to_response;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
@@ -56,7 +56,7 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
     std::fs::create_dir(&working_directory)?;
 
     // Create mock server with a single SSE response: the long sleep command
-    let server = create_mock_chat_completions_server(vec![create_shell_sse_response(
+    let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
         shell_command.clone(),
         Some(&working_directory),
         Some(10_000), // 10 seconds timeout in ms
@@ -88,7 +88,10 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
 
     // 2) addConversationListener
     let add_listener_id = mcp
-        .send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
         .await?;
     let _add_listener_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
@@ -143,7 +146,7 @@ fn create_config_toml(codex_home: &Path, server_uri: String) -> std::io::Result<
             r#"
 model = "mock-model"
 approval_policy = "never"
-sandbox_mode = "danger-full-access"
+sandbox_mode = "read-only"
 
 model_provider = "mock_provider"
 

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

@@ -1,7 +1,6 @@
-use std::fs;
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
+use app_test_support::create_fake_rollout;
 use app_test_support::to_response;
 use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCResponse;
@@ -13,67 +12,69 @@ use codex_app_server_protocol::ResumeConversationParams;
 use codex_app_server_protocol::ResumeConversationResponse;
 use codex_app_server_protocol::ServerNotification;
 use codex_app_server_protocol::SessionConfiguredNotification;
+use codex_core::protocol::EventMsg;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
 use pretty_assertions::assert_eq;
-use serde_json::json;
 use tempfile::TempDir;
 use tokio::time::timeout;
-use uuid::Uuid;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn test_list_and_resume_conversations() {
+async fn test_list_and_resume_conversations() -> Result<()> {
     // Prepare a temporary CODEX_HOME with a few fake rollout files.
-    let codex_home = TempDir::new().expect("create temp dir");
+    let codex_home = TempDir::new()?;
     create_fake_rollout(
         codex_home.path(),
         "2025-01-02T12-00-00",
         "2025-01-02T12:00:00Z",
         "Hello A",
-    );
+        Some("openai"),
+        None,
+    )?;
     create_fake_rollout(
         codex_home.path(),
         "2025-01-01T13-00-00",
         "2025-01-01T13:00:00Z",
         "Hello B",
-    );
+        Some("openai"),
+        None,
+    )?;
     create_fake_rollout(
         codex_home.path(),
         "2025-01-01T12-00-00",
         "2025-01-01T12:00:00Z",
         "Hello C",
-    );
+        None,
+        None,
+    )?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     // Request first page with size 2
     let req_id = mcp
         .send_list_conversations_request(ListConversationsParams {
             page_size: Some(2),
             cursor: None,
+            model_providers: None,
         })
-        .await
-        .expect("send listConversations");
+        .await?;
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
     )
-    .await
-    .expect("listConversations timeout")
-    .expect("listConversations resp");
+    .await??;
     let ListConversationsResponse { items, next_cursor } =
-        to_response::<ListConversationsResponse>(resp).expect("deserialize response");
+        to_response::<ListConversationsResponse>(resp)?;
 
     assert_eq!(items.len(), 2);
     // Newest first; preview text should match
     assert_eq!(items[0].preview, "Hello A");
     assert_eq!(items[1].preview, "Hello B");
+    assert_eq!(items[0].model_provider, "openai");
+    assert_eq!(items[1].model_provider, "openai");
     assert!(items[0].path.is_absolute());
     assert!(next_cursor.is_some());
 
@@ -82,129 +83,356 @@ async fn test_list_and_resume_conversations() {
         .send_list_conversations_request(ListConversationsParams {
             page_size: Some(2),
             cursor: next_cursor,
+            model_providers: None,
         })
-        .await
-        .expect("send listConversations page 2");
+        .await?;
     let resp2: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(req_id2)),
     )
-    .await
-    .expect("listConversations page 2 timeout")
-    .expect("listConversations page 2 resp");
+    .await??;
     let ListConversationsResponse {
         items: items2,
         next_cursor: next2,
         ..
-    } = to_response::<ListConversationsResponse>(resp2).expect("deserialize response");
+    } = to_response::<ListConversationsResponse>(resp2)?;
     assert_eq!(items2.len(), 1);
     assert_eq!(items2[0].preview, "Hello C");
-    assert!(next2.is_some());
+    assert_eq!(items2[0].model_provider, "openai");
+    assert_eq!(next2, None);
 
-    // Now resume one of the sessions and expect a SessionConfigured notification and response.
+    // Add a conversation with an explicit non-OpenAI provider for filter tests.
+    create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T11-30-00",
+        "2025-01-01T11:30:00Z",
+        "Hello TP",
+        Some("test-provider"),
+        None,
+    )?;
+
+    // Filtering by model provider should return only matching sessions.
+    let filter_req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(10),
+            cursor: None,
+            model_providers: Some(vec!["test-provider".to_string()]),
+        })
+        .await?;
+    let filter_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(filter_req_id)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: filtered_items,
+        next_cursor: filtered_next,
+    } = to_response::<ListConversationsResponse>(filter_resp)?;
+    assert_eq!(filtered_items.len(), 1);
+    assert_eq!(filtered_next, None);
+    assert_eq!(filtered_items[0].preview, "Hello TP");
+    assert_eq!(filtered_items[0].model_provider, "test-provider");
+
+    // Empty filter should include every session regardless of provider metadata.
+    let unfiltered_req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(10),
+            cursor: None,
+            model_providers: Some(Vec::new()),
+        })
+        .await?;
+    let unfiltered_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(unfiltered_req_id)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: unfiltered_items,
+        next_cursor: unfiltered_next,
+    } = to_response::<ListConversationsResponse>(unfiltered_resp)?;
+    assert_eq!(unfiltered_items.len(), 4);
+    assert!(unfiltered_next.is_none());
+
+    let empty_req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(10),
+            cursor: None,
+            model_providers: Some(vec!["other".to_string()]),
+        })
+        .await?;
+    let empty_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(empty_req_id)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: empty_items,
+        next_cursor: empty_next,
+    } = to_response::<ListConversationsResponse>(empty_resp)?;
+    assert!(empty_items.is_empty());
+    assert!(empty_next.is_none());
+
+    let first_item = &items[0];
+
+    // Now resume one of the sessions from an explicit rollout path.
     let resume_req_id = mcp
         .send_resume_conversation_request(ResumeConversationParams {
-            path: items[0].path.clone(),
+            path: Some(first_item.path.clone()),
+            conversation_id: None,
+            history: None,
             overrides: Some(NewConversationParams {
                 model: Some("o3".to_string()),
                 ..Default::default()
             }),
         })
-        .await
-        .expect("send resumeConversation");
+        .await?;
 
     // Expect a codex/event notification with msg.type == sessionConfigured
     let notification: JSONRPCNotification = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("sessionConfigured"),
     )
-    .await
-    .expect("sessionConfigured notification timeout")
-    .expect("sessionConfigured notification");
-    let session_configured: ServerNotification = notification
-        .try_into()
-        .expect("deserialize sessionConfigured notification");
-    // Basic shape assertion: ensure event type is sessionConfigured
+    .await??;
+    let session_configured: ServerNotification = notification.try_into()?;
     let ServerNotification::SessionConfigured(SessionConfiguredNotification {
         model,
         rollout_path,
+        initial_messages: session_initial_messages,
         ..
     }) = session_configured
     else {
         unreachable!("expected sessionConfigured notification");
     };
     assert_eq!(model, "o3");
-    assert_eq!(items[0].path.clone(), rollout_path);
+    assert_eq!(rollout_path, first_item.path.clone());
+    let session_initial_messages = session_initial_messages
+        .expect("expected initial messages when resuming from rollout path");
+    match session_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => panic!("unexpected initial messages from rollout resume: {other:#?}"),
+    }
 
     // Then the response for resumeConversation
     let resume_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(resume_req_id)),
     )
-    .await
-    .expect("resumeConversation timeout")
-    .expect("resumeConversation resp");
+    .await??;
     let ResumeConversationResponse {
-        conversation_id, ..
-    } = to_response::<ResumeConversationResponse>(resume_resp)
-        .expect("deserialize resumeConversation response");
+        conversation_id,
+        model: resume_model,
+        initial_messages: response_initial_messages,
+        ..
+    } = to_response::<ResumeConversationResponse>(resume_resp)?;
     // conversation id should be a valid UUID
     assert!(!conversation_id.to_string().is_empty());
+    assert_eq!(resume_model, "o3");
+    let response_initial_messages =
+        response_initial_messages.expect("expected initial messages in resume response");
+    match response_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => panic!("unexpected initial messages in resume response: {other:#?}"),
+    }
+
+    // Resuming with only a conversation id should locate the rollout automatically.
+    let resume_by_id_req_id = mcp
+        .send_resume_conversation_request(ResumeConversationParams {
+            path: None,
+            conversation_id: Some(first_item.conversation_id),
+            history: None,
+            overrides: Some(NewConversationParams {
+                model: Some("o3".to_string()),
+                ..Default::default()
+            }),
+        })
+        .await?;
+    let notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("sessionConfigured"),
+    )
+    .await??;
+    let session_configured: ServerNotification = notification.try_into()?;
+    let ServerNotification::SessionConfigured(SessionConfiguredNotification {
+        model,
+        rollout_path,
+        initial_messages: session_initial_messages,
+        ..
+    }) = session_configured
+    else {
+        unreachable!("expected sessionConfigured notification");
+    };
+    assert_eq!(model, "o3");
+    assert_eq!(rollout_path, first_item.path.clone());
+    let session_initial_messages = session_initial_messages
+        .expect("expected initial messages when resuming from conversation id");
+    match session_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => panic!("unexpected initial messages from conversation id resume: {other:#?}"),
+    }
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_by_id_req_id)),
+    )
+    .await??;
+    let ResumeConversationResponse {
+        conversation_id: by_id_conversation_id,
+        model: by_id_model,
+        initial_messages: by_id_initial_messages,
+        ..
+    } = to_response::<ResumeConversationResponse>(resume_resp)?;
+    assert!(!by_id_conversation_id.to_string().is_empty());
+    assert_eq!(by_id_model, "o3");
+    let by_id_initial_messages = by_id_initial_messages
+        .expect("expected initial messages when resuming from conversation id response");
+    match by_id_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => {
+            panic!("unexpected initial messages in conversation id resume response: {other:#?}")
+        }
+    }
+
+    // Resuming with explicit history should succeed even without a stored rollout.
+    let fork_history_text = "Hello from history";
+    let history = vec![ResponseItem::Message {
+        id: None,
+        role: "user".to_string(),
+        content: vec![ContentItem::InputText {
+            text: fork_history_text.to_string(),
+        }],
+    }];
+    let resume_with_history_req_id = mcp
+        .send_resume_conversation_request(ResumeConversationParams {
+            path: None,
+            conversation_id: None,
+            history: Some(history),
+            overrides: Some(NewConversationParams {
+                model: Some("o3".to_string()),
+                ..Default::default()
+            }),
+        })
+        .await?;
+    let notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("sessionConfigured"),
+    )
+    .await??;
+    let session_configured: ServerNotification = notification.try_into()?;
+    let ServerNotification::SessionConfigured(SessionConfiguredNotification {
+        model,
+        initial_messages: session_initial_messages,
+        ..
+    }) = session_configured
+    else {
+        unreachable!("expected sessionConfigured notification");
+    };
+    assert_eq!(model, "o3");
+    assert!(
+        session_initial_messages.as_ref().is_none_or(Vec::is_empty),
+        "expected no initial messages when resuming from explicit history but got {session_initial_messages:#?}"
+    );
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_with_history_req_id)),
+    )
+    .await??;
+    let ResumeConversationResponse {
+        conversation_id: history_conversation_id,
+        model: history_model,
+        initial_messages: history_initial_messages,
+        ..
+    } = to_response::<ResumeConversationResponse>(resume_resp)?;
+    assert!(!history_conversation_id.to_string().is_empty());
+    assert_eq!(history_model, "o3");
+    assert!(
+        history_initial_messages.as_ref().is_none_or(Vec::is_empty),
+        "expected no initial messages in resume response when history is provided but got {history_initial_messages:#?}"
+    );
+
+    Ok(())
 }
 
-fn create_fake_rollout(codex_home: &Path, filename_ts: &str, meta_rfc3339: &str, preview: &str) {
-    let uuid = Uuid::new_v4();
-    // sessions/YYYY/MM/DD/ derived from filename_ts (YYYY-MM-DDThh-mm-ss)
-    let year = &filename_ts[0..4];
-    let month = &filename_ts[5..7];
-    let day = &filename_ts[8..10];
-    let dir = codex_home.join("sessions").join(year).join(month).join(day);
-    fs::create_dir_all(&dir).unwrap_or_else(|e| panic!("create sessions dir: {e}"));
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn list_conversations_fetches_through_filtered_pages() -> Result<()> {
+    let codex_home = TempDir::new()?;
 
-    let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
-    let mut lines = Vec::new();
-    // Meta line with timestamp (flattened meta in payload for new schema)
-    lines.push(
-        json!({
-            "timestamp": meta_rfc3339,
-            "type": "session_meta",
-            "payload": {
-                "id": uuid,
-                "timestamp": meta_rfc3339,
-                "cwd": "/",
-                "originator": "codex",
-                "cli_version": "0.0.0",
-                "instructions": null
-            }
+    // Only the last 3 conversations match the provider filter; request 3 and
+    // ensure pagination keeps fetching past non-matching pages.
+    let cases = [
+        (
+            "2025-03-04T12-00-00",
+            "2025-03-04T12:00:00Z",
+            "skip_provider",
+        ),
+        (
+            "2025-03-03T12-00-00",
+            "2025-03-03T12:00:00Z",
+            "skip_provider",
+        ),
+        (
+            "2025-03-02T12-00-00",
+            "2025-03-02T12:00:00Z",
+            "target_provider",
+        ),
+        (
+            "2025-03-01T12-00-00",
+            "2025-03-01T12:00:00Z",
+            "target_provider",
+        ),
+        (
+            "2025-02-28T12-00-00",
+            "2025-02-28T12:00:00Z",
+            "target_provider",
+        ),
+    ];
+
+    for (ts_file, ts_rfc, provider) in cases {
+        create_fake_rollout(
+            codex_home.path(),
+            ts_file,
+            ts_rfc,
+            "Hello",
+            Some(provider),
+            None,
+        )?;
+    }
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(3),
+            cursor: None,
+            model_providers: Some(vec!["target_provider".to_string()]),
         })
-        .to_string(),
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    let ListConversationsResponse { items, next_cursor } =
+        to_response::<ListConversationsResponse>(resp)?;
+
+    assert_eq!(
+        items.len(),
+        3,
+        "should fetch across pages to satisfy the limit"
     );
-    // Minimal user message entry as a persisted response item (with envelope timestamp)
-    lines.push(
-        json!({
-            "timestamp": meta_rfc3339,
-            "type":"response_item",
-            "payload": {
-                "type":"message",
-                "role":"user",
-                "content":[{"type":"input_text","text": preview}]
-            }
-        })
-        .to_string(),
+    assert!(
+        items
+            .iter()
+            .all(|item| item.model_provider == "target_provider")
     );
-    // Add a matching user message event line to satisfy filters
-    lines.push(
-        json!({
-            "timestamp": meta_rfc3339,
-            "type":"event_msg",
-            "payload": {
-                "type":"user_message",
-                "message": preview,
-                "kind": "plain"
-            }
-        })
-        .to_string(),
-    );
-    fs::write(file_path, lines.join("\n") + "\n")
-        .unwrap_or_else(|e| panic!("write rollout file: {e}"));
+    assert_eq!(next_cursor, None);
+
+    Ok(())
 }

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

@@ -1,17 +1,17 @@
-use std::path::Path;
-use std::time::Duration;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
-use codex_app_server_protocol::CancelLoginChatGptParams;
-use codex_app_server_protocol::CancelLoginChatGptResponse;
 use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::GetAuthStatusResponse;
+use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::LoginChatGptResponse;
 use codex_app_server_protocol::LogoutChatGptResponse;
 use codex_app_server_protocol::RequestId;
+use codex_core::auth::AuthCredentialsStoreMode;
 use codex_login::login_with_api_key;
+use serial_test::serial;
+use std::path::Path;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
@@ -40,32 +40,26 @@ stream_max_retries = 0
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn logout_chatgpt_removes_auth() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml(codex_home.path()).expect("write config.toml");
-    login_with_api_key(codex_home.path(), "sk-test-key").expect("seed api key");
+async fn logout_chatgpt_removes_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+    login_with_api_key(
+        codex_home.path(),
+        "sk-test-key",
+        AuthCredentialsStoreMode::File,
+    )?;
     assert!(codex_home.path().join("auth.json").exists());
 
-    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)])
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let id = mcp
-        .send_logout_chat_gpt_request()
-        .await
-        .expect("send logoutChatGpt");
+    let id = mcp.send_logout_chat_gpt_request().await?;
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(id)),
     )
-    .await
-    .expect("logoutChatGpt timeout")
-    .expect("logoutChatGpt response");
-    let _ok: LogoutChatGptResponse = to_response(resp).expect("deserialize logout response");
+    .await??;
+    let _ok: LogoutChatGptResponse = to_response(resp)?;
 
     assert!(
         !codex_home.path().join("auth.json").exists(),
@@ -78,69 +72,90 @@ async fn logout_chatgpt_removes_auth() {
             include_token: Some(true),
             refresh_token: Some(false),
         })
-        .await
-        .expect("send getAuthStatus");
+        .await?;
     let status_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(status_id)),
     )
-    .await
-    .expect("getAuthStatus timeout")
-    .expect("getAuthStatus response");
-    let status: GetAuthStatusResponse = to_response(status_resp).expect("deserialize status");
+    .await??;
+    let status: GetAuthStatusResponse = to_response(status_resp)?;
     assert_eq!(status.auth_method, None);
     assert_eq!(status.auth_token, None);
+    Ok(())
+}
+
+fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+forced_login_method = "{forced_method}"
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+fn create_config_toml_forced_workspace(
+    codex_home: &Path,
+    workspace_id: &str,
+) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+forced_chatgpt_workspace_id = "{workspace_id}"
+"#
+    );
+    std::fs::write(config_toml, contents)
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn login_and_cancel_chatgpt() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml(codex_home.path()).unwrap_or_else(|err| panic!("write config.toml: {err}"));
+async fn login_chatgpt_rejected_when_forced_api() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_forced_login(codex_home.path(), "api")?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let login_id = mcp
-        .send_login_chat_gpt_request()
-        .await
-        .expect("send loginChatGpt");
-    let login_resp: JSONRPCResponse = timeout(
+    let request_id = mcp.send_login_chat_gpt_request().await?;
+    let err: JSONRPCError = timeout(
         DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(login_id)),
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("loginChatGpt timeout")
-    .expect("loginChatGpt response");
-    let login: LoginChatGptResponse = to_response(login_resp).expect("deserialize login resp");
+    .await??;
 
-    let cancel_id = mcp
-        .send_cancel_login_chat_gpt_request(CancelLoginChatGptParams {
-            login_id: login.login_id,
-        })
-        .await
-        .expect("send cancelLoginChatGpt");
-    let cancel_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(cancel_id)),
-    )
-    .await
-    .expect("cancelLoginChatGpt timeout")
-    .expect("cancelLoginChatGpt response");
-    let _ok: CancelLoginChatGptResponse =
-        to_response(cancel_resp).expect("deserialize cancel response");
-
-    // Optionally observe the completion notification; do not fail if it races.
-    let maybe_note = timeout(
-        Duration::from_secs(2),
-        mcp.read_stream_until_notification_message("codex/event/login_chat_gpt_complete"),
-    )
-    .await;
-    if maybe_note.is_err() {
-        eprintln!("warning: did not observe login_chat_gpt_complete notification after cancel");
-    }
+    assert_eq!(
+        err.error.message,
+        "ChatGPT login is disabled. Use API key login instead."
+    );
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_chatgpt_includes_forced_workspace_query_param() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_forced_workspace(codex_home.path(), "ws-forced")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_login_chat_gpt_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let login: LoginChatGptResponse = to_response(resp)?;
+    assert!(
+        login.auth_url.contains("allowed_workspace_id=ws-forced"),
+        "auth URL should include forced workspace"
+    );
+    Ok(())
 }

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

@@ -11,3 +11,4 @@ mod send_message;
 mod set_default_model;
 mod user_agent;
 mod user_info;
+mod v2;

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

@@ -1,5 +1,4 @@
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_final_assistant_message_sse_response;
 use app_test_support::create_mock_chat_completions_server;
@@ -15,73 +14,76 @@ use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::SendUserMessageParams;
 use codex_app_server_protocol::SendUserMessageResponse;
 use codex_protocol::ConversationId;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
+use codex_protocol::protocol::RawResponseItemEvent;
 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 test_send_message_success() {
+async fn test_send_message_success() -> Result<()> {
     // Spin up a mock completions server that immediately ends the Codex turn.
     // Two Codex turns hit the mock model (session start + send-user-message). Provide two SSE responses.
     let responses = vec![
-        create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
-        create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
+        create_final_assistant_message_sse_response("Done")?,
+        create_final_assistant_message_sse_response("Done")?,
     ];
     let server = create_mock_chat_completions_server(responses).await;
 
     // Create a temporary Codex home with config pointing at the mock server.
-    let codex_home = TempDir::new().expect("create temp dir");
-    create_config_toml(codex_home.path(), &server.uri()).expect("write config.toml");
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
 
     // Start MCP server process and initialize.
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timed out")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     // Start a conversation using the new wire API.
     let new_conv_id = mcp
-        .send_new_conversation_request(NewConversationParams::default())
-        .await
-        .expect("send newConversation");
+        .send_new_conversation_request(NewConversationParams {
+            ..Default::default()
+        })
+        .await?;
     let new_conv_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
     )
-    .await
-    .expect("newConversation timeout")
-    .expect("newConversation resp");
+    .await??;
     let NewConversationResponse {
         conversation_id, ..
-    } = to_response::<_>(new_conv_resp).expect("deserialize newConversation response");
+    } = to_response::<_>(new_conv_resp)?;
 
     // 2) addConversationListener
     let add_listener_id = mcp
-        .send_add_conversation_listener_request(AddConversationListenerParams { conversation_id })
-        .await
-        .expect("send addConversationListener");
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
     let add_listener_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
     )
-    .await
-    .expect("addConversationListener timeout")
-    .expect("addConversationListener resp");
+    .await??;
     let AddConversationSubscriptionResponse { subscription_id: _ } =
-        to_response::<_>(add_listener_resp).expect("deserialize addConversationListener response");
+        to_response::<_>(add_listener_resp)?;
 
     // Now exercise sendUserMessage twice.
-    send_message("Hello", conversation_id, &mut mcp).await;
-    send_message("Hello again", conversation_id, &mut mcp).await;
+    send_message("Hello", conversation_id, &mut mcp).await?;
+    send_message("Hello again", conversation_id, &mut mcp).await?;
+    Ok(())
 }
 
 #[expect(clippy::expect_used)]
-async fn send_message(message: &str, conversation_id: ConversationId, mcp: &mut McpProcess) {
+async fn send_message(
+    message: &str,
+    conversation_id: ConversationId,
+    mcp: &mut McpProcess,
+) -> Result<()> {
     // Now exercise sendUserMessage.
     let send_id = mcp
         .send_send_user_message_request(SendUserMessageParams {
@@ -90,19 +92,15 @@ async fn send_message(message: &str, conversation_id: ConversationId, mcp: &mut
                 text: message.to_string(),
             }],
         })
-        .await
-        .expect("send sendUserMessage");
+        .await?;
 
     let response: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
     )
-    .await
-    .expect("sendUserMessage response timeout")
-    .expect("sendUserMessage response error");
+    .await??;
 
-    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(response)
-        .expect("deserialize sendUserMessage response");
+    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(response)?;
 
     // Verify the task_finished notification is received.
     // Note this also ensures that the final request to the server was made.
@@ -110,9 +108,7 @@ async fn send_message(message: &str, conversation_id: ConversationId, mcp: &mut
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
-    .await
-    .expect("task_finished_notification timeout")
-    .expect("task_finished_notification resp");
+    .await??;
     let serde_json::Value::Object(map) = task_finished_notification
         .params
         .expect("notification should have params")
@@ -124,17 +120,105 @@ async fn send_message(message: &str, conversation_id: ConversationId, mcp: &mut
             .expect("should have conversationId"),
         &serde_json::Value::String(conversation_id.to_string())
     );
+
+    let raw_attempt = tokio::time::timeout(
+        std::time::Duration::from_millis(200),
+        mcp.read_stream_until_notification_message("codex/event/raw_response_item"),
+    )
+    .await;
+    assert!(
+        raw_attempt.is_err(),
+        "unexpected raw item notification when not opted in"
+    );
+    Ok(())
 }
 
 #[tokio::test]
-async fn test_send_message_session_not_found() {
+async fn test_send_message_raw_notifications_opt_in() -> Result<()> {
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
+    let server = create_mock_chat_completions_server(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 new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            developer_instructions: Some("Use the test harness tools.".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let NewConversationResponse {
+        conversation_id, ..
+    } = to_response::<_>(new_conv_resp)?;
+
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: true,
+        })
+        .await?;
+    let add_listener_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+    )
+    .await??;
+    let AddConversationSubscriptionResponse { subscription_id: _ } =
+        to_response::<_>(add_listener_resp)?;
+
+    let send_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: "Hello".to_string(),
+            }],
+        })
+        .await?;
+
+    let developer = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_developer_message(&developer, "Use the test harness tools.");
+
+    let instructions = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_instructions_message(&instructions);
+
+    let environment = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_environment_message(&environment);
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
+    )
+    .await??;
+    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(response)?;
+
+    let user_message = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_user_message(&user_message, "Hello");
+
+    let assistant_message = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_assistant_message(&assistant_message, "Done");
+
+    let _ = tokio::time::timeout(
+        std::time::Duration::from_millis(250),
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await;
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn test_send_message_session_not_found() -> Result<()> {
     // Start MCP without creating a Codex session
-    let codex_home = TempDir::new().expect("tempdir");
-    let mut mcp = McpProcess::new(codex_home.path()).await.expect("spawn");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("timeout")
-        .expect("init");
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let unknown = ConversationId::new();
     let req_id = mcp
@@ -144,18 +228,16 @@ async fn test_send_message_session_not_found() {
                 text: "ping".to_string(),
             }],
         })
-        .await
-        .expect("send sendUserMessage");
+        .await?;
 
     // Expect an error response for unknown conversation.
     let err = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_error_message(RequestId::Integer(req_id)),
     )
-    .await
-    .expect("timeout")
-    .expect("error");
+    .await??;
     assert_eq!(err.id, RequestId::Integer(req_id));
+    Ok(())
 }
 
 // ---------------------------------------------------------------------------
@@ -184,3 +266,131 @@ stream_max_retries = 0
         ),
     )
 }
+
+#[expect(clippy::expect_used)]
+async fn read_raw_response_item(
+    mcp: &mut McpProcess,
+    conversation_id: ConversationId,
+) -> ResponseItem {
+    loop {
+        let raw_notification: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("codex/event/raw_response_item"),
+        )
+        .await
+        .expect("codex/event/raw_response_item notification timeout")
+        .expect("codex/event/raw_response_item notification resp");
+
+        let serde_json::Value::Object(params) = raw_notification
+            .params
+            .expect("codex/event/raw_response_item should have params")
+        else {
+            panic!("codex/event/raw_response_item should have params");
+        };
+
+        let conversation_id_value = params
+            .get("conversationId")
+            .and_then(|value| value.as_str())
+            .expect("raw response item should include conversationId");
+
+        assert_eq!(
+            conversation_id_value,
+            conversation_id.to_string(),
+            "raw response item conversation mismatch"
+        );
+
+        let msg_value = params
+            .get("msg")
+            .cloned()
+            .expect("raw response item should include msg payload");
+
+        // Ghost snapshots are produced concurrently and may arrive before the model reply.
+        let event: RawResponseItemEvent =
+            serde_json::from_value(msg_value).expect("deserialize raw response item");
+        if !matches!(event.item, ResponseItem::GhostSnapshot { .. }) {
+            return event.item;
+        }
+    }
+}
+
+fn assert_instructions_message(item: &ResponseItem) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "user");
+            let texts = content_texts(content);
+            let is_instructions = texts
+                .iter()
+                .any(|text| text.starts_with("# AGENTS.md instructions for "));
+            assert!(
+                is_instructions,
+                "expected instructions message, got {texts:?}"
+            );
+        }
+        other => panic!("expected instructions message, got {other:?}"),
+    }
+}
+
+fn assert_developer_message(item: &ResponseItem, expected_text: &str) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "developer");
+            let texts = content_texts(content);
+            assert_eq!(
+                texts,
+                vec![expected_text],
+                "expected developer instructions message, got {texts:?}"
+            );
+        }
+        other => panic!("expected developer instructions message, got {other:?}"),
+    }
+}
+
+fn assert_environment_message(item: &ResponseItem) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "user");
+            let texts = content_texts(content);
+            assert!(
+                texts
+                    .iter()
+                    .any(|text| text.contains("<environment_context>")),
+                "expected environment context message, got {texts:?}"
+            );
+        }
+        other => panic!("expected environment message, got {other:?}"),
+    }
+}
+
+fn assert_user_message(item: &ResponseItem, expected_text: &str) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "user");
+            let texts = content_texts(content);
+            assert_eq!(texts, vec![expected_text]);
+        }
+        other => panic!("expected user message, got {other:?}"),
+    }
+}
+
+fn assert_assistant_message(item: &ResponseItem, expected_text: &str) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "assistant");
+            let texts = content_texts(content);
+            assert_eq!(texts, vec![expected_text]);
+        }
+        other => panic!("expected assistant message, got {other:?}"),
+    }
+}
+
+fn content_texts(content: &[ContentItem]) -> Vec<&str> {
+    content
+        .iter()
+        .filter_map(|item| match item {
+            ContentItem::InputText { text } | ContentItem::OutputText { text } => {
+                Some(text.as_str())
+            }
+            _ => None,
+        })
+        .collect()
+}

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

@@ -1,5 +1,4 @@
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
 use codex_app_server_protocol::JSONRPCResponse;
@@ -8,50 +7,38 @@ use codex_app_server_protocol::SetDefaultModelParams;
 use codex_app_server_protocol::SetDefaultModelResponse;
 use codex_core::config::ConfigToml;
 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(flavor = "multi_thread", worker_threads = 2)]
-async fn set_default_model_persists_overrides() {
-    let codex_home = TempDir::new().expect("create tempdir");
-    create_config_toml(codex_home.path()).expect("write config.toml");
+async fn set_default_model_persists_overrides() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("init timeout")
-        .expect("init failed");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let params = SetDefaultModelParams {
         model: Some("gpt-4.1".to_string()),
         reasoning_effort: None,
     };
 
-    let request_id = mcp
-        .send_set_default_model_request(params)
-        .await
-        .expect("send setDefaultModel");
+    let request_id = mcp.send_set_default_model_request(params).await?;
 
     let resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("setDefaultModel timeout")
-    .expect("setDefaultModel response");
+    .await??;
 
-    let _: SetDefaultModelResponse =
-        to_response(resp).expect("deserialize setDefaultModel response");
+    let _: SetDefaultModelResponse = to_response(resp)?;
 
     let config_path = codex_home.path().join("config.toml");
-    let config_contents = tokio::fs::read_to_string(&config_path)
-        .await
-        .expect("read config.toml");
-    let config_toml: ConfigToml = toml::from_str(&config_contents).expect("parse config.toml");
+    let config_contents = tokio::fs::read_to_string(&config_path).await?;
+    let config_toml: ConfigToml = toml::from_str(&config_contents)?;
 
     assert_eq!(
         ConfigToml {
@@ -61,6 +48,7 @@ async fn set_default_model_persists_overrides() {
         },
         config_toml,
     );
+    Ok(())
 }
 
 // Helper to create a config.toml; mirrors create_conversation.rs
@@ -69,7 +57,7 @@ fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
     std::fs::write(
         config_toml,
         r#"
-model = "gpt-5-codex"
+model = "gpt-5.1-codex-max"
 model_reasoning_effort = "medium"
 "#,
     )

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

@@ -1,3 +1,4 @@
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
 use codex_app_server_protocol::GetUserAgentResponse;
@@ -10,28 +11,18 @@ use tokio::time::timeout;
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn get_user_agent_returns_current_codex_user_agent() {
-    let codex_home = TempDir::new().unwrap_or_else(|err| panic!("create tempdir: {err}"));
+async fn get_user_agent_returns_current_codex_user_agent() -> Result<()> {
+    let codex_home = TempDir::new()?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("initialize timeout")
-        .expect("initialize request");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let request_id = mcp
-        .send_get_user_agent_request()
-        .await
-        .expect("send getUserAgent");
+    let request_id = mcp.send_get_user_agent_request().await?;
     let response: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("getUserAgent timeout")
-    .expect("getUserAgent response");
+    .await??;
 
     let os_info = os_info::get();
     let user_agent = format!(
@@ -42,9 +33,9 @@ async fn get_user_agent_returns_current_codex_user_agent() {
         codex_core::terminal::user_agent()
     );
 
-    let received: GetUserAgentResponse =
-        to_response(response).expect("deserialize getUserAgent response");
+    let received: GetUserAgentResponse = to_response(response)?;
     let expected = GetUserAgentResponse { user_agent };
 
     assert_eq!(received, expected);
+    Ok(())
 }

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

@@ -1,78 +1,46 @@
-use std::time::Duration;
-
-use anyhow::Context;
+use anyhow::Result;
+use app_test_support::ChatGptAuthFixture;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
-use base64::Engine;
-use base64::engine::general_purpose::URL_SAFE_NO_PAD;
+use app_test_support::write_chatgpt_auth;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::UserInfoResponse;
-use codex_core::auth::AuthDotJson;
-use codex_core::auth::get_auth_file;
-use codex_core::auth::write_auth_json;
-use codex_core::token_data::IdTokenInfo;
-use codex_core::token_data::TokenData;
+use codex_core::auth::AuthCredentialsStoreMode;
 use pretty_assertions::assert_eq;
-use serde_json::json;
+use std::time::Duration;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
 const DEFAULT_READ_TIMEOUT: Duration = Duration::from_secs(10);
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn user_info_returns_email_from_auth_json() {
-    let codex_home = TempDir::new().expect("create tempdir");
+async fn user_info_returns_email_from_auth_json() -> Result<()> {
+    let codex_home = TempDir::new()?;
 
-    let auth_path = get_auth_file(codex_home.path());
-    let mut id_token = IdTokenInfo::default();
-    id_token.email = Some("user@example.com".to_string());
-    id_token.raw_jwt = encode_id_token_with_email("user@example.com").expect("encode id token");
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("access")
+            .refresh_token("refresh")
+            .email("user@example.com"),
+        AuthCredentialsStoreMode::File,
+    )?;
 
-    let auth = AuthDotJson {
-        openai_api_key: None,
-        tokens: Some(TokenData {
-            id_token,
-            access_token: "access".to_string(),
-            refresh_token: "refresh".to_string(),
-            account_id: None,
-        }),
-        last_refresh: None,
-    };
-    write_auth_json(&auth_path, &auth).expect("write auth.json");
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .expect("spawn mcp process");
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .expect("initialize timeout")
-        .expect("initialize request");
-
-    let request_id = mcp.send_user_info_request().await.expect("send userInfo");
+    let request_id = mcp.send_user_info_request().await?;
     let response: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("userInfo timeout")
-    .expect("userInfo response");
+    .await??;
 
-    let received: UserInfoResponse = to_response(response).expect("deserialize userInfo response");
+    let received: UserInfoResponse = to_response(response)?;
     let expected = UserInfoResponse {
         alleged_user_email: Some("user@example.com".to_string()),
     };
 
     assert_eq!(received, expected);
-}
-
-fn encode_id_token_with_email(email: &str) -> anyhow::Result<String> {
-    let header_b64 = URL_SAFE_NO_PAD.encode(
-        serde_json::to_vec(&json!({ "alg": "none", "typ": "JWT" }))
-            .context("serialize jwt header")?,
-    );
-    let payload =
-        serde_json::to_vec(&json!({ "email": email })).context("serialize jwt payload")?;
-    let payload_b64 = URL_SAFE_NO_PAD.encode(payload);
-    Ok(format!("{header_b64}.{payload_b64}.signature"))
+    Ok(())
 }

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

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

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

@@ -0,0 +1,421 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::test_path_buf_with_windows;
+use app_test_support::test_tmp_path_buf;
+use app_test_support::to_response;
+use codex_app_server_protocol::AskForApproval;
+use codex_app_server_protocol::ConfigBatchWriteParams;
+use codex_app_server_protocol::ConfigEdit;
+use codex_app_server_protocol::ConfigLayerName;
+use codex_app_server_protocol::ConfigReadParams;
+use codex_app_server_protocol::ConfigReadResponse;
+use codex_app_server_protocol::ConfigValueWriteParams;
+use codex_app_server_protocol::ConfigWriteResponse;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::MergeStrategy;
+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 pretty_assertions::assert_eq;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+fn write_config(codex_home: &TempDir, contents: &str) -> Result<()> {
+    Ok(std::fs::write(
+        codex_home.path().join("config.toml"),
+        contents,
+    )?)
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_read_returns_effective_and_layers() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_config(
+        &codex_home,
+        r#"
+model = "gpt-user"
+sandbox_mode = "workspace-write"
+"#,
+    )?;
+
+    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,
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ConfigReadResponse {
+        config,
+        origins,
+        layers,
+    } = to_response(resp)?;
+
+    assert_eq!(config.model.as_deref(), Some("gpt-user"));
+    assert_eq!(
+        origins.get("model").expect("origin").name,
+        ConfigLayerName::User
+    );
+    let layers = layers.expect("layers present");
+    assert_eq!(layers.len(), 2);
+    assert_eq!(layers[0].name, ConfigLayerName::SessionFlags);
+    assert_eq!(layers[1].name, ConfigLayerName::User);
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_read_includes_tools() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_config(
+        &codex_home,
+        r#"
+model = "gpt-user"
+
+[tools]
+web_search = true
+view_image = false
+"#,
+    )?;
+
+    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,
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ConfigReadResponse {
+        config,
+        origins,
+        layers,
+    } = to_response(resp)?;
+
+    let tools = config.tools.expect("tools present");
+    assert_eq!(
+        tools,
+        ToolsV2 {
+            web_search: Some(true),
+            view_image: Some(false),
+        }
+    );
+    assert_eq!(
+        origins.get("tools.web_search").expect("origin").name,
+        ConfigLayerName::User
+    );
+    assert_eq!(
+        origins.get("tools.view_image").expect("origin").name,
+        ConfigLayerName::User
+    );
+
+    let layers = layers.expect("layers present");
+    assert_eq!(layers.len(), 2);
+    assert_eq!(layers[0].name, ConfigLayerName::SessionFlags);
+    assert_eq!(layers[1].name, ConfigLayerName::User);
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_read_includes_system_layer_and_overrides() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let user_dir = test_path_buf_with_windows("/user", Some(r"C:\Users\user"));
+    let system_dir = test_path_buf_with_windows("/system", Some(r"C:\System"));
+    write_config(
+        &codex_home,
+        &format!(
+            r#"
+model = "gpt-user"
+approval_policy = "on-request"
+sandbox_mode = "workspace-write"
+
+[sandbox_workspace_write]
+writable_roots = [{}]
+network_access = true
+"#,
+            serde_json::json!(user_dir)
+        ),
+    )?;
+
+    let managed_path = codex_home.path().join("managed_config.toml");
+    std::fs::write(
+        &managed_path,
+        format!(
+            r#"
+model = "gpt-system"
+approval_policy = "never"
+
+[sandbox_workspace_write]
+writable_roots = [{}]
+"#,
+            serde_json::json!(system_dir.clone())
+        ),
+    )?;
+
+    let managed_path_str = managed_path.display().to_string();
+
+    let mut mcp = McpProcess::new_with_env(
+        codex_home.path(),
+        &[("CODEX_MANAGED_CONFIG_PATH", Some(&managed_path_str))],
+    )
+    .await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_config_read_request(ConfigReadParams {
+            include_layers: true,
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ConfigReadResponse {
+        config,
+        origins,
+        layers,
+    } = to_response(resp)?;
+
+    assert_eq!(config.model.as_deref(), Some("gpt-system"));
+    assert_eq!(
+        origins.get("model").expect("origin").name,
+        ConfigLayerName::System
+    );
+
+    assert_eq!(config.approval_policy, Some(AskForApproval::Never));
+    assert_eq!(
+        origins.get("approval_policy").expect("origin").name,
+        ConfigLayerName::System
+    );
+
+    assert_eq!(config.sandbox_mode, Some(SandboxMode::WorkspaceWrite));
+    assert_eq!(
+        origins.get("sandbox_mode").expect("origin").name,
+        ConfigLayerName::User
+    );
+
+    let sandbox = config
+        .sandbox_workspace_write
+        .as_ref()
+        .expect("sandbox workspace write");
+    assert_eq!(sandbox.writable_roots, vec![system_dir]);
+    assert_eq!(
+        origins
+            .get("sandbox_workspace_write.writable_roots.0")
+            .expect("origin")
+            .name,
+        ConfigLayerName::System
+    );
+
+    assert!(sandbox.network_access);
+    assert_eq!(
+        origins
+            .get("sandbox_workspace_write.network_access")
+            .expect("origin")
+            .name,
+        ConfigLayerName::User
+    );
+
+    let layers = layers.expect("layers present");
+    assert_eq!(layers.len(), 3);
+    assert_eq!(layers[0].name, ConfigLayerName::System);
+    assert_eq!(layers[1].name, ConfigLayerName::SessionFlags);
+    assert_eq!(layers[2].name, ConfigLayerName::User);
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_value_write_replaces_value() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_config(
+        &codex_home,
+        r#"
+model = "gpt-old"
+"#,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let read_id = mcp
+        .send_config_read_request(ConfigReadParams {
+            include_layers: false,
+        })
+        .await?;
+    let read_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
+    )
+    .await??;
+    let read: ConfigReadResponse = to_response(read_resp)?;
+    let expected_version = read.origins.get("model").map(|m| m.version.clone());
+
+    let write_id = mcp
+        .send_config_value_write_request(ConfigValueWriteParams {
+            file_path: None,
+            key_path: "model".to_string(),
+            value: json!("gpt-new"),
+            merge_strategy: MergeStrategy::Replace,
+            expected_version,
+        })
+        .await?;
+    let write_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(write_id)),
+    )
+    .await??;
+    let write: ConfigWriteResponse = to_response(write_resp)?;
+    let expected_file_path = codex_home
+        .path()
+        .join("config.toml")
+        .canonicalize()
+        .unwrap()
+        .display()
+        .to_string();
+
+    assert_eq!(write.status, WriteStatus::Ok);
+    assert_eq!(write.file_path, expected_file_path);
+    assert!(write.overridden_metadata.is_none());
+
+    let verify_id = mcp
+        .send_config_read_request(ConfigReadParams {
+            include_layers: false,
+        })
+        .await?;
+    let verify_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(verify_id)),
+    )
+    .await??;
+    let verify: ConfigReadResponse = to_response(verify_resp)?;
+    assert_eq!(verify.config.model.as_deref(), Some("gpt-new"));
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_value_write_rejects_version_conflict() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_config(
+        &codex_home,
+        r#"
+model = "gpt-old"
+"#,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let write_id = mcp
+        .send_config_value_write_request(ConfigValueWriteParams {
+            file_path: Some(codex_home.path().join("config.toml").display().to_string()),
+            key_path: "model".to_string(),
+            value: json!("gpt-new"),
+            merge_strategy: MergeStrategy::Replace,
+            expected_version: Some("sha256:stale".to_string()),
+        })
+        .await?;
+
+    let err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(write_id)),
+    )
+    .await??;
+    let code = err
+        .error
+        .data
+        .as_ref()
+        .and_then(|d| d.get("config_write_error_code"))
+        .and_then(|v| v.as_str());
+    assert_eq!(code, Some("configVersionConflict"));
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_batch_write_applies_multiple_edits() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_config(&codex_home, "")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let writable_root = test_tmp_path_buf();
+    let batch_id = mcp
+        .send_config_batch_write_request(ConfigBatchWriteParams {
+            file_path: Some(codex_home.path().join("config.toml").display().to_string()),
+            edits: vec![
+                ConfigEdit {
+                    key_path: "sandbox_mode".to_string(),
+                    value: json!("workspace-write"),
+                    merge_strategy: MergeStrategy::Replace,
+                },
+                ConfigEdit {
+                    key_path: "sandbox_workspace_write".to_string(),
+                    value: json!({
+                        "writable_roots": [writable_root.clone()],
+                        "network_access": false
+                    }),
+                    merge_strategy: MergeStrategy::Replace,
+                },
+            ],
+            expected_version: None,
+        })
+        .await?;
+    let batch_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(batch_id)),
+    )
+    .await??;
+    let batch_write: ConfigWriteResponse = to_response(batch_resp)?;
+    assert_eq!(batch_write.status, WriteStatus::Ok);
+    let expected_file_path = codex_home
+        .path()
+        .join("config.toml")
+        .canonicalize()
+        .unwrap()
+        .display()
+        .to_string();
+    assert_eq!(batch_write.file_path, expected_file_path);
+
+    let read_id = mcp
+        .send_config_read_request(ConfigReadParams {
+            include_layers: false,
+        })
+        .await?;
+    let read_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
+    )
+    .await??;
+    let read: ConfigReadResponse = to_response(read_resp)?;
+    assert_eq!(read.config.sandbox_mode, Some(SandboxMode::WorkspaceWrite));
+    let sandbox = read
+        .config
+        .sandbox_workspace_write
+        .as_ref()
+        .expect("sandbox workspace write");
+    assert_eq!(sandbox.writable_roots, vec![writable_root]);
+    assert!(!sandbox.network_access);
+
+    Ok(())
+}

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

@@ -0,0 +1,11 @@
+mod account;
+mod config_rpc;
+mod model_list;
+mod rate_limits;
+mod review;
+mod thread_archive;
+mod thread_list;
+mod thread_resume;
+mod thread_start;
+mod turn_interrupt;
+mod turn_start;

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

@@ -0,0 +1,331 @@
+use std::time::Duration;
+
+use anyhow::Result;
+use anyhow::anyhow;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use app_test_support::write_models_cache;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::Model;
+use codex_app_server_protocol::ModelListParams;
+use codex_app_server_protocol::ModelListResponse;
+use codex_app_server_protocol::ReasoningEffortOption;
+use codex_app_server_protocol::RequestId;
+use codex_protocol::openai_models::ReasoningEffort;
+use pretty_assertions::assert_eq;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_TIMEOUT: Duration = Duration::from_secs(10);
+const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
+
+#[tokio::test]
+async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_models_cache(codex_home.path())?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(100),
+            cursor: None,
+        })
+        .await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: items,
+        next_cursor,
+    } = to_response::<ModelListResponse>(response)?;
+
+    let expected_models = vec![
+        Model {
+            id: "gpt-5.1-codex-max".to_string(),
+            model: "gpt-5.1-codex-max".to_string(),
+            display_name: "gpt-5.1-codex-max".to_string(),
+            description: "Latest Codex-optimized flagship for deep and fast reasoning.".to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Fast responses with lighter reasoning".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Balances speed and reasoning depth for everyday tasks"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Greater reasoning depth for complex problems".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::XHigh,
+                    description: "Extra high reasoning depth for complex problems".to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: true,
+        },
+        Model {
+            id: "gpt-5.1-codex".to_string(),
+            model: "gpt-5.1-codex".to_string(),
+            display_name: "gpt-5.1-codex".to_string(),
+            description: "Optimized for codex.".to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Fastest responses with limited reasoning".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: false,
+        },
+        Model {
+            id: "gpt-5.1-codex-mini".to_string(),
+            model: "gpt-5.1-codex-mini".to_string(),
+            display_name: "gpt-5.1-codex-mini".to_string(),
+            description: "Optimized for codex. Cheaper, faster, but less capable.".to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: false,
+        },
+        Model {
+            id: "gpt-5.2".to_string(),
+            model: "gpt-5.2".to_string(),
+            display_name: "gpt-5.2".to_string(),
+            description:
+                "Latest frontier model with improvements across knowledge, reasoning and coding"
+                    .to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Balances speed with some reasoning; useful for straightforward \
+                                   queries and short explanations"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Provides a solid balance of reasoning depth and latency for \
+                         general-purpose tasks"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Greater reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::XHigh,
+                    description: "Extra high reasoning for complex problems".to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: false,
+        },
+        Model {
+            id: "gpt-5.1".to_string(),
+            model: "gpt-5.1".to_string(),
+            display_name: "gpt-5.1".to_string(),
+            description: "Broad world knowledge with strong general reasoning.".to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Balances speed with some reasoning; useful for straightforward \
+                                   queries and short explanations"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Provides a solid balance of reasoning depth and latency for \
+                         general-purpose tasks"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: false,
+        },
+    ];
+
+    assert_eq!(items, expected_models);
+    assert!(next_cursor.is_none());
+    Ok(())
+}
+
+#[tokio::test]
+async fn list_models_pagination_works() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_models_cache(codex_home.path())?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let first_request = mcp
+        .send_list_models_request(ModelListParams {
+            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 ModelListResponse {
+        data: first_items,
+        next_cursor: first_cursor,
+    } = to_response::<ModelListResponse>(first_response)?;
+
+    assert_eq!(first_items.len(), 1);
+    assert_eq!(first_items[0].id, "gpt-5.1-codex-max");
+    let next_cursor = first_cursor.ok_or_else(|| anyhow!("cursor for second page"))?;
+
+    let second_request = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(1),
+            cursor: Some(next_cursor.clone()),
+        })
+        .await?;
+
+    let second_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(second_request)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: second_items,
+        next_cursor: second_cursor,
+    } = to_response::<ModelListResponse>(second_response)?;
+
+    assert_eq!(second_items.len(), 1);
+    assert_eq!(second_items[0].id, "gpt-5.1-codex");
+    let third_cursor = second_cursor.ok_or_else(|| anyhow!("cursor for third page"))?;
+
+    let third_request = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(1),
+            cursor: Some(third_cursor.clone()),
+        })
+        .await?;
+
+    let third_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(third_request)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: third_items,
+        next_cursor: third_cursor,
+    } = to_response::<ModelListResponse>(third_response)?;
+
+    assert_eq!(third_items.len(), 1);
+    assert_eq!(third_items[0].id, "gpt-5.1-codex-mini");
+    let fourth_cursor = third_cursor.ok_or_else(|| anyhow!("cursor for fourth page"))?;
+
+    let fourth_request = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(1),
+            cursor: Some(fourth_cursor.clone()),
+        })
+        .await?;
+
+    let fourth_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(fourth_request)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: fourth_items,
+        next_cursor: fourth_cursor,
+    } = to_response::<ModelListResponse>(fourth_response)?;
+
+    assert_eq!(fourth_items.len(), 1);
+    assert_eq!(fourth_items[0].id, "gpt-5.2");
+    let fifth_cursor = fourth_cursor.ok_or_else(|| anyhow!("cursor for fifth page"))?;
+
+    let fifth_request = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(1),
+            cursor: Some(fifth_cursor.clone()),
+        })
+        .await?;
+
+    let fifth_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(fifth_request)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: fifth_items,
+        next_cursor: fifth_cursor,
+    } = to_response::<ModelListResponse>(fifth_response)?;
+
+    assert_eq!(fifth_items.len(), 1);
+    assert_eq!(fifth_items[0].id, "gpt-5.1");
+    assert!(fifth_cursor.is_none());
+    Ok(())
+}
+
+#[tokio::test]
+async fn list_models_rejects_invalid_cursor() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_models_cache(codex_home.path())?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_list_models_request(ModelListParams {
+            limit: None,
+            cursor: Some("invalid".to_string()),
+        })
+        .await?;
+
+    let error: JSONRPCError = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(error.id, RequestId::Integer(request_id));
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert_eq!(error.error.message, "invalid cursor: invalid");
+    Ok(())
+}

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

@@ -0,0 +1,184 @@
+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 codex_app_server_protocol::GetAccountRateLimitsResponse;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::LoginApiKeyParams;
+use codex_app_server_protocol::RateLimitSnapshot;
+use codex_app_server_protocol::RateLimitWindow;
+use codex_app_server_protocol::RequestId;
+use codex_core::auth::AuthCredentialsStoreMode;
+use codex_protocol::account::PlanType as AccountPlanType;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+use wiremock::Mock;
+use wiremock::MockServer;
+use wiremock::ResponseTemplate;
+use wiremock::matchers::header;
+use wiremock::matchers::method;
+use wiremock::matchers::path;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
+
+#[tokio::test]
+async fn get_account_rate_limits_requires_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_account_rate_limits_request().await?;
+
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(error.id, RequestId::Integer(request_id));
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert_eq!(
+        error.error.message,
+        "codex account authentication required to read rate limits"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    login_with_api_key(&mut mcp, "sk-test-key").await?;
+
+    let request_id = mcp.send_get_account_rate_limits_request().await?;
+
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(error.id, RequestId::Integer(request_id));
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert_eq!(
+        error.error.message,
+        "chatgpt authentication required to read rate limits"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("chatgpt-token")
+            .account_id("account-123")
+            .plan_type("pro"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let server = MockServer::start().await;
+    let server_url = server.uri();
+    write_chatgpt_base_url(codex_home.path(), &server_url)?;
+
+    let primary_reset_timestamp = chrono::DateTime::parse_from_rfc3339("2025-01-01T00:02:00Z")
+        .expect("parse primary reset timestamp")
+        .timestamp();
+    let secondary_reset_timestamp = chrono::DateTime::parse_from_rfc3339("2025-01-01T01:00:00Z")
+        .expect("parse secondary reset timestamp")
+        .timestamp();
+    let response_body = json!({
+        "plan_type": "pro",
+        "rate_limit": {
+            "allowed": true,
+            "limit_reached": false,
+            "primary_window": {
+                "used_percent": 42,
+                "limit_window_seconds": 3600,
+                "reset_after_seconds": 120,
+                "reset_at": primary_reset_timestamp,
+            },
+            "secondary_window": {
+                "used_percent": 5,
+                "limit_window_seconds": 86400,
+                "reset_after_seconds": 43200,
+                "reset_at": secondary_reset_timestamp,
+            }
+        }
+    });
+
+    Mock::given(method("GET"))
+        .and(path("/api/codex/usage"))
+        .and(header("authorization", "Bearer chatgpt-token"))
+        .and(header("chatgpt-account-id", "account-123"))
+        .respond_with(ResponseTemplate::new(200).set_body_json(response_body))
+        .mount(&server)
+        .await;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_account_rate_limits_request().await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let received: GetAccountRateLimitsResponse = to_response(response)?;
+
+    let expected = GetAccountRateLimitsResponse {
+        rate_limits: RateLimitSnapshot {
+            primary: Some(RateLimitWindow {
+                used_percent: 42,
+                window_duration_mins: Some(60),
+                resets_at: Some(primary_reset_timestamp),
+            }),
+            secondary: Some(RateLimitWindow {
+                used_percent: 5,
+                window_duration_mins: Some(1440),
+                resets_at: Some(secondary_reset_timestamp),
+            }),
+            credits: None,
+            plan_type: Some(AccountPlanType::Pro),
+        },
+    };
+    assert_eq!(received, expected);
+
+    Ok(())
+}
+
+async fn login_with_api_key(mcp: &mut McpProcess, api_key: &str) -> Result<()> {
+    let request_id = mcp
+        .send_login_api_key_request(LoginApiKeyParams {
+            api_key: api_key.to_string(),
+        })
+        .await?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    Ok(())
+}
+
+fn write_chatgpt_base_url(codex_home: &Path, base_url: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(config_toml, format!("chatgpt_base_url = \"{base_url}\"\n"))
+}

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

@@ -0,0 +1,329 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_chat_completions_server_unchecked;
+use app_test_support::to_response;
+use codex_app_server_protocol::ItemCompletedNotification;
+use codex_app_server_protocol::ItemStartedNotification;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ReviewDelivery;
+use codex_app_server_protocol::ReviewStartParams;
+use codex_app_server_protocol::ReviewStartResponse;
+use codex_app_server_protocol::ReviewTarget;
+use codex_app_server_protocol::ThreadItem;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnStatus;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
+
+#[tokio::test]
+async fn review_start_runs_review_turn_and_emits_code_review_item() -> Result<()> {
+    let review_payload = json!({
+        "findings": [
+            {
+                "title": "Prefer Stylize helpers",
+                "body": "Use .dim()/.bold() chaining instead of manual Style.",
+                "confidence_score": 0.9,
+                "priority": 1,
+                "code_location": {
+                    "absolute_file_path": "/tmp/file.rs",
+                    "line_range": {"start": 10, "end": 20}
+                }
+            }
+        ],
+        "overall_correctness": "good",
+        "overall_explanation": "Looks solid overall with minor polish suggested.",
+        "overall_confidence_score": 0.75
+    })
+    .to_string();
+    let responses = vec![create_final_assistant_message_sse_response(
+        &review_payload,
+    )?];
+    let server = create_mock_chat_completions_server_unchecked(responses).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let thread_id = start_default_thread(&mut mcp).await?;
+
+    let review_req = mcp
+        .send_review_start_request(ReviewStartParams {
+            thread_id: thread_id.clone(),
+            delivery: Some(ReviewDelivery::Inline),
+            target: ReviewTarget::Commit {
+                sha: "1234567deadbeef".to_string(),
+                title: Some("Tidy UI colors".to_string()),
+            },
+        })
+        .await?;
+    let review_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(review_req)),
+    )
+    .await??;
+    let ReviewStartResponse {
+        turn,
+        review_thread_id,
+    } = to_response::<ReviewStartResponse>(review_resp)?;
+    assert_eq!(review_thread_id, thread_id.clone());
+    let turn_id = turn.id.clone();
+    assert_eq!(turn.status, TurnStatus::InProgress);
+
+    // Confirm we see the EnteredReviewMode marker on the main thread.
+    let mut saw_entered_review_mode = false;
+    for _ in 0..10 {
+        let item_started: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("item/started"),
+        )
+        .await??;
+        let started: ItemStartedNotification =
+            serde_json::from_value(item_started.params.expect("params must be present"))?;
+        match started.item {
+            ThreadItem::EnteredReviewMode { id, review } => {
+                assert_eq!(id, turn_id);
+                assert_eq!(review, "commit 1234567: Tidy UI colors");
+                saw_entered_review_mode = true;
+                break;
+            }
+            _ => continue,
+        }
+    }
+    assert!(
+        saw_entered_review_mode,
+        "did not observe enteredReviewMode item"
+    );
+
+    // Confirm we see the ExitedReviewMode marker (with review text)
+    // on the same turn. Ignore any other items the stream surfaces.
+    let mut review_body: Option<String> = None;
+    for _ in 0..10 {
+        let review_notif: JSONRPCNotification = timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_notification_message("item/completed"),
+        )
+        .await??;
+        let completed: ItemCompletedNotification =
+            serde_json::from_value(review_notif.params.expect("params must be present"))?;
+        match completed.item {
+            ThreadItem::ExitedReviewMode { id, review } => {
+                assert_eq!(id, turn_id);
+                review_body = Some(review);
+                break;
+            }
+            _ => continue,
+        }
+    }
+
+    let review = review_body.expect("did not observe a code review item");
+    assert!(review.contains("Prefer Stylize helpers"));
+    assert!(review.contains("/tmp/file.rs:10-20"));
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn review_start_rejects_empty_base_branch() -> Result<()> {
+    let server = create_mock_chat_completions_server_unchecked(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+    let thread_id = start_default_thread(&mut mcp).await?;
+
+    let request_id = mcp
+        .send_review_start_request(ReviewStartParams {
+            thread_id,
+            delivery: Some(ReviewDelivery::Inline),
+            target: ReviewTarget::BaseBranch {
+                branch: "   ".to_string(),
+            },
+        })
+        .await?;
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert!(
+        error.error.message.contains("branch must not be empty"),
+        "unexpected message: {}",
+        error.error.message
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn review_start_with_detached_delivery_returns_new_thread_id() -> Result<()> {
+    let review_payload = json!({
+        "findings": [],
+        "overall_correctness": "ok",
+        "overall_explanation": "detached review",
+        "overall_confidence_score": 0.5
+    })
+    .to_string();
+    let responses = vec![create_final_assistant_message_sse_response(
+        &review_payload,
+    )?];
+    let server = create_mock_chat_completions_server_unchecked(responses).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let thread_id = start_default_thread(&mut mcp).await?;
+
+    let review_req = mcp
+        .send_review_start_request(ReviewStartParams {
+            thread_id: thread_id.clone(),
+            delivery: Some(ReviewDelivery::Detached),
+            target: ReviewTarget::Custom {
+                instructions: "detached review".to_string(),
+            },
+        })
+        .await?;
+    let review_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(review_req)),
+    )
+    .await??;
+    let ReviewStartResponse {
+        turn,
+        review_thread_id,
+    } = to_response::<ReviewStartResponse>(review_resp)?;
+
+    assert_eq!(turn.status, TurnStatus::InProgress);
+    assert_ne!(
+        review_thread_id, thread_id,
+        "detached review should run on a different thread"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn review_start_rejects_empty_commit_sha() -> Result<()> {
+    let server = create_mock_chat_completions_server_unchecked(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+    let thread_id = start_default_thread(&mut mcp).await?;
+
+    let request_id = mcp
+        .send_review_start_request(ReviewStartParams {
+            thread_id,
+            delivery: Some(ReviewDelivery::Inline),
+            target: ReviewTarget::Commit {
+                sha: "\t".to_string(),
+                title: None,
+            },
+        })
+        .await?;
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert!(
+        error.error.message.contains("sha must not be empty"),
+        "unexpected message: {}",
+        error.error.message
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn review_start_rejects_empty_custom_instructions() -> Result<()> {
+    let server = create_mock_chat_completions_server_unchecked(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+    let thread_id = start_default_thread(&mut mcp).await?;
+
+    let request_id = mcp
+        .send_review_start_request(ReviewStartParams {
+            thread_id,
+            delivery: Some(ReviewDelivery::Inline),
+            target: ReviewTarget::Custom {
+                instructions: "\n\n".to_string(),
+            },
+        })
+        .await?;
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert!(
+        error
+            .error
+            .message
+            .contains("instructions must not be empty"),
+        "unexpected message: {}",
+        error.error.message
+    );
+
+    Ok(())
+}
+
+async fn start_default_thread(mcp: &mut McpProcess) -> Result<String> {
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let thread_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
+    Ok(thread.id)
+}
+
+fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

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

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

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

@@ -0,0 +1,431 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_fake_rollout;
+use app_test_support::to_response;
+use codex_app_server_protocol::GitInfo as ApiGitInfo;
+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_protocol::protocol::GitInfo as CoreGitInfo;
+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);
+
+async fn init_mcp(codex_home: &Path) -> Result<McpProcess> {
+    let mut mcp = McpProcess::new(codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+    Ok(mcp)
+}
+
+async fn list_threads(
+    mcp: &mut McpProcess,
+    cursor: Option<String>,
+    limit: Option<u32>,
+    providers: Option<Vec<String>>,
+) -> Result<ThreadListResponse> {
+    let request_id = mcp
+        .send_thread_list_request(codex_app_server_protocol::ThreadListParams {
+            cursor,
+            limit,
+            model_providers: providers,
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    to_response::<ThreadListResponse>(resp)
+}
+
+fn create_fake_rollouts<F, G>(
+    codex_home: &Path,
+    count: usize,
+    provider_for_index: F,
+    timestamp_for_index: G,
+    preview: &str,
+) -> Result<Vec<String>>
+where
+    F: Fn(usize) -> &'static str,
+    G: Fn(usize) -> (String, String),
+{
+    let mut ids = Vec::with_capacity(count);
+    for i in 0..count {
+        let (ts_file, ts_rfc) = timestamp_for_index(i);
+        ids.push(create_fake_rollout(
+            codex_home,
+            &ts_file,
+            &ts_rfc,
+            preview,
+            Some(provider_for_index(i)),
+            None,
+        )?);
+    }
+    Ok(ids)
+}
+
+fn timestamp_at(
+    year: i32,
+    month: u32,
+    day: u32,
+    hour: u32,
+    minute: u32,
+    second: u32,
+) -> (String, String) {
+    (
+        format!("{year:04}-{month:02}-{day:02}T{hour:02}-{minute:02}-{second:02}"),
+        format!("{year:04}-{month:02}-{day:02}T{hour:02}:{minute:02}:{second:02}Z"),
+    )
+}
+
+#[tokio::test]
+async fn thread_list_basic_empty() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    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()]),
+    )
+    .await?;
+    assert!(data.is_empty());
+    assert_eq!(next_cursor, None);
+
+    Ok(())
+}
+
+// Minimal config.toml for listing.
+fn create_minimal_config(codex_home: &std::path::Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        r#"
+model = "mock-model"
+approval_policy = "never"
+"#,
+    )
+}
+
+#[tokio::test]
+async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    // Create three rollouts so we can paginate with limit=2.
+    let _a = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T12-00-00",
+        "2025-01-02T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let _b = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T13-00-00",
+        "2025-01-01T13:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+        None,
+    )?;
+    let _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?;
+
+    // Page 1: limit 2 → expect next_cursor Some.
+    let ThreadListResponse {
+        data: data1,
+        next_cursor: cursor1,
+    } = list_threads(
+        &mut mcp,
+        None,
+        Some(2),
+        Some(vec!["mock_provider".to_string()]),
+    )
+    .await?;
+    assert_eq!(data1.len(), 2);
+    for thread in &data1 {
+        assert_eq!(thread.preview, "Hello");
+        assert_eq!(thread.model_provider, "mock_provider");
+        assert!(thread.created_at > 0);
+        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);
+    }
+    let cursor1 = cursor1.expect("expected nextCursor on first page");
+
+    // Page 2: with cursor → expect next_cursor None when no more results.
+    let ThreadListResponse {
+        data: data2,
+        next_cursor: cursor2,
+    } = list_threads(
+        &mut mcp,
+        Some(cursor1),
+        Some(2),
+        Some(vec!["mock_provider".to_string()]),
+    )
+    .await?;
+    assert!(data2.len() <= 2);
+    for thread in &data2 {
+        assert_eq!(thread.preview, "Hello");
+        assert_eq!(thread.model_provider, "mock_provider");
+        assert!(thread.created_at > 0);
+        assert_eq!(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!(cursor2, None, "expected nextCursor to be null on last page");
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_respects_provider_filter() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    // Create rollouts under two providers.
+    let _a = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T10-00-00",
+        "2025-01-02T10:00:00Z",
+        "X",
+        Some("mock_provider"),
+        None,
+    )?; // mock_provider
+    let _b = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T11-00-00",
+        "2025-01-02T11:00:00Z",
+        "X",
+        Some("other_provider"),
+        None,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    // Filter to only other_provider; expect 1 item, nextCursor None.
+    let ThreadListResponse { data, next_cursor } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["other_provider".to_string()]),
+    )
+    .await?;
+    assert_eq!(data.len(), 1);
+    assert_eq!(next_cursor, None);
+    let thread = &data[0];
+    assert_eq!(thread.preview, "X");
+    assert_eq!(thread.model_provider, "other_provider");
+    let expected_ts = chrono::DateTime::parse_from_rfc3339("2025-01-02T11:00:00Z")?.timestamp();
+    assert_eq!(thread.created_at, expected_ts);
+    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);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_fetches_until_limit_or_exhausted() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    // Newest 16 conversations belong to a different provider; the older 8 are the
+    // only ones that match the filter. We request 8 so the server must keep
+    // paging past the first two pages to reach the desired count.
+    create_fake_rollouts(
+        codex_home.path(),
+        24,
+        |i| {
+            if i < 16 {
+                "skip_provider"
+            } else {
+                "target_provider"
+            }
+        },
+        |i| timestamp_at(2025, 3, 30 - i as u32, 12, 0, 0),
+        "Hello",
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    // Request 8 threads for the target provider; the matches only start on the
+    // third page so we rely on pagination to reach the limit.
+    let ThreadListResponse { data, next_cursor } = list_threads(
+        &mut mcp,
+        None,
+        Some(8),
+        Some(vec!["target_provider".to_string()]),
+    )
+    .await?;
+    assert_eq!(
+        data.len(),
+        8,
+        "should keep paging until the requested count is filled"
+    );
+    assert!(
+        data.iter()
+            .all(|thread| thread.model_provider == "target_provider"),
+        "all returned threads must match the requested provider"
+    );
+    assert_eq!(
+        next_cursor, None,
+        "once the requested count is satisfied on the final page, nextCursor should be None"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_enforces_max_limit() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    create_fake_rollouts(
+        codex_home.path(),
+        105,
+        |_| "mock_provider",
+        |i| {
+            let month = 5 + (i / 28);
+            let day = (i % 28) + 1;
+            timestamp_at(2025, month as u32, day as u32, 0, 0, 0)
+        },
+        "Hello",
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    let ThreadListResponse { data, next_cursor } = list_threads(
+        &mut mcp,
+        None,
+        Some(200),
+        Some(vec!["mock_provider".to_string()]),
+    )
+    .await?;
+    assert_eq!(
+        data.len(),
+        100,
+        "limit should be clamped to the maximum page size"
+    );
+    assert!(
+        next_cursor.is_some(),
+        "when more than the maximum exist, nextCursor should continue pagination"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_stops_when_not_enough_filtered_results_exist() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    // Only the last 7 conversations match the provider filter; we ask for 10 to
+    // ensure the server exhausts pagination without looping forever.
+    create_fake_rollouts(
+        codex_home.path(),
+        22,
+        |i| {
+            if i < 15 {
+                "skip_provider"
+            } else {
+                "target_provider"
+            }
+        },
+        |i| timestamp_at(2025, 4, 28 - i as u32, 8, 0, 0),
+        "Hello",
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+
+    // Request more threads than exist after filtering; expect all matches to be
+    // returned with nextCursor None.
+    let ThreadListResponse { data, next_cursor } = list_threads(
+        &mut mcp,
+        None,
+        Some(10),
+        Some(vec!["target_provider".to_string()]),
+    )
+    .await?;
+    assert_eq!(
+        data.len(),
+        7,
+        "all available filtered threads should be returned"
+    );
+    assert!(
+        data.iter()
+            .all(|thread| thread.model_provider == "target_provider"),
+        "results should still respect the provider filter"
+    );
+    assert_eq!(
+        next_cursor, None,
+        "when results are exhausted before reaching the limit, nextCursor should be None"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_includes_git_info() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let git_info = CoreGitInfo {
+        commit_hash: Some("abc123".to_string()),
+        branch: Some("main".to_string()),
+        repository_url: Some("https://example.com/repo.git".to_string()),
+    };
+    let conversation_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T09-00-00",
+        "2025-02-01T09:00:00Z",
+        "Git info preview",
+        Some("mock_provider"),
+        Some(git_info),
+    )?;
+
+    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()]),
+    )
+    .await?;
+    let thread = data
+        .iter()
+        .find(|t| t.id == conversation_id)
+        .expect("expected thread for created rollout");
+
+    let expected_git = ApiGitInfo {
+        sha: Some("abc123".to_string()),
+        branch: Some("main".to_string()),
+        origin_url: Some("https://example.com/repo.git".to_string()),
+    };
+    assert_eq!(thread.git_info, Some(expected_git));
+    assert_eq!(thread.source, SessionSource::Cli);
+    assert_eq!(thread.cwd, PathBuf::from("/"));
+    assert_eq!(thread.cli_version, "0.0.0");
+
+    Ok(())
+}

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

@@ -0,0 +1,256 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_fake_rollout;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SessionSource;
+use codex_app_server_protocol::ThreadItem;
+use codex_app_server_protocol::ThreadResumeParams;
+use codex_app_server_protocol::ThreadResumeResponse;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnStatus;
+use codex_app_server_protocol::UserInput;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
+use 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_resume_returns_original_thread() -> Result<()> {
+    let server = create_mock_chat_completions_server(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a thread.
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("gpt-5.1-codex-max".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    // Resume it via v2 API.
+    let resume_id = mcp
+        .send_thread_resume_request(ThreadResumeParams {
+            thread_id: thread.id.clone(),
+            ..Default::default()
+        })
+        .await?;
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+    )
+    .await??;
+    let ThreadResumeResponse {
+        thread: resumed, ..
+    } = to_response::<ThreadResumeResponse>(resume_resp)?;
+    assert_eq!(resumed, thread);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_resume_returns_rollout_history() -> Result<()> {
+    let server = create_mock_chat_completions_server(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let preview = "Saved user message";
+    let conversation_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-05T12-00-00",
+        "2025-01-05T12:00:00Z",
+        preview,
+        Some("mock_provider"),
+        None,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let resume_id = mcp
+        .send_thread_resume_request(ThreadResumeParams {
+            thread_id: conversation_id.clone(),
+            ..Default::default()
+        })
+        .await?;
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+    )
+    .await??;
+    let ThreadResumeResponse { thread, .. } = to_response::<ThreadResumeResponse>(resume_resp)?;
+
+    assert_eq!(thread.id, conversation_id);
+    assert_eq!(thread.preview, preview);
+    assert_eq!(thread.model_provider, "mock_provider");
+    assert!(thread.path.is_absolute());
+    assert_eq!(thread.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(),
+        1,
+        "expected rollouts to include one turn"
+    );
+    let turn = &thread.turns[0];
+    assert_eq!(turn.status, TurnStatus::Completed);
+    assert_eq!(turn.items.len(), 1, "expected user message item");
+    match &turn.items[0] {
+        ThreadItem::UserMessage { content, .. } => {
+            assert_eq!(
+                content,
+                &vec![UserInput::Text {
+                    text: preview.to_string()
+                }]
+            );
+        }
+        other => panic!("expected user message item, got {other:?}"),
+    }
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
+    let server = create_mock_chat_completions_server(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("gpt-5.1-codex-max".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    let thread_path = thread.path.clone();
+    let resume_id = mcp
+        .send_thread_resume_request(ThreadResumeParams {
+            thread_id: "not-a-valid-thread-id".to_string(),
+            path: Some(thread_path),
+            ..Default::default()
+        })
+        .await?;
+
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+    )
+    .await??;
+    let ThreadResumeResponse {
+        thread: resumed, ..
+    } = to_response::<ThreadResumeResponse>(resume_resp)?;
+    assert_eq!(resumed, thread);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_resume_supports_history_and_overrides() -> Result<()> {
+    let server = create_mock_chat_completions_server(vec![]).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a thread.
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("gpt-5.1-codex-max".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    let history_text = "Hello from history";
+    let history = vec![ResponseItem::Message {
+        id: None,
+        role: "user".to_string(),
+        content: vec![ContentItem::InputText {
+            text: history_text.to_string(),
+        }],
+    }];
+
+    // Resume with explicit history and override the model.
+    let resume_id = mcp
+        .send_thread_resume_request(ThreadResumeParams {
+            thread_id: thread.id,
+            history: Some(history),
+            model: Some("mock-model".to_string()),
+            model_provider: Some("mock_provider".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+    )
+    .await??;
+    let ThreadResumeResponse {
+        thread: resumed,
+        model_provider,
+        ..
+    } = to_response::<ThreadResumeResponse>(resume_resp)?;
+    assert!(!resumed.id.is_empty());
+    assert_eq!(model_provider, "mock_provider");
+    assert_eq!(resumed.preview, history_text);
+
+    Ok(())
+}
+
+// Helper to create a config.toml pointing at the mock model server.
+fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

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

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

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

@@ -0,0 +1,144 @@
+#![cfg(unix)]
+
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::create_shell_command_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnCompletedNotification;
+use codex_app_server_protocol::TurnInterruptParams;
+use codex_app_server_protocol::TurnInterruptResponse;
+use codex_app_server_protocol::TurnStartParams;
+use codex_app_server_protocol::TurnStartResponse;
+use codex_app_server_protocol::TurnStatus;
+use codex_app_server_protocol::UserInput as V2UserInput;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn turn_interrupt_aborts_running_turn() -> Result<()> {
+    // Use a portable sleep command to keep the turn running.
+    #[cfg(target_os = "windows")]
+    let shell_command = vec![
+        "powershell".to_string(),
+        "-Command".to_string(),
+        "Start-Sleep -Seconds 10".to_string(),
+    ];
+    #[cfg(not(target_os = "windows"))]
+    let shell_command = vec!["sleep".to_string(), "10".to_string()];
+
+    let tmp = TempDir::new()?;
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let working_directory = tmp.path().join("workdir");
+    std::fs::create_dir(&working_directory)?;
+
+    // Mock server: long-running shell command then (after abort) nothing else needed.
+    let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
+        shell_command.clone(),
+        Some(&working_directory),
+        Some(10_000),
+        "call_sleep",
+    )?])
+    .await;
+    create_config_toml(&codex_home, &server.uri())?;
+
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a v2 thread and capture its id.
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let thread_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
+
+    // Start a turn that triggers a long-running command.
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "run sleep".to_string(),
+            }],
+            cwd: Some(working_directory.clone()),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
+
+    // Give the command a brief moment to start.
+    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+
+    let thread_id = thread.id.clone();
+    // Interrupt the in-progress turn by id (v2 API).
+    let interrupt_id = mcp
+        .send_turn_interrupt_request(TurnInterruptParams {
+            thread_id: thread_id.clone(),
+            turn_id: turn.id,
+        })
+        .await?;
+    let interrupt_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(interrupt_id)),
+    )
+    .await??;
+    let _resp: TurnInterruptResponse = to_response::<TurnInterruptResponse>(interrupt_resp)?;
+
+    let completed_notif: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+    let completed: TurnCompletedNotification = serde_json::from_value(
+        completed_notif
+            .params
+            .expect("turn/completed params must be present"),
+    )?;
+    assert_eq!(completed.thread_id, thread_id);
+    assert_eq!(completed.turn.status, TurnStatus::Interrupted);
+
+    Ok(())
+}
+
+// Helper to create a config.toml pointing at the mock model server.
+fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "workspace-write"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/apply-patch/Cargo.toml

@@ -1,7 +1,8 @@
 [package]
-edition = "2024"
 name = "codex-apply-patch"
-version = { workspace = true }
+version.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [lib]
 name = "codex_apply_patch"

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

@@ -31,6 +31,13 @@ pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_too
 
 const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+enum ApplyPatchShell {
+    Unix,
+    PowerShell,
+    Cmd,
+}
+
 #[derive(Debug, Error, PartialEq)]
 pub enum ApplyPatchError {
     #[error(transparent)]
@@ -96,6 +103,57 @@ pub struct ApplyPatchArgs {
     pub workdir: Option<String>,
 }
 
+fn classify_shell_name(shell: &str) -> Option<String> {
+    std::path::Path::new(shell)
+        .file_stem()
+        .and_then(|name| name.to_str())
+        .map(str::to_ascii_lowercase)
+}
+
+fn classify_shell(shell: &str, flag: &str) -> Option<ApplyPatchShell> {
+    classify_shell_name(shell).and_then(|name| match name.as_str() {
+        "bash" | "zsh" | "sh" if matches!(flag, "-lc" | "-c") => Some(ApplyPatchShell::Unix),
+        "pwsh" | "powershell" if flag.eq_ignore_ascii_case("-command") => {
+            Some(ApplyPatchShell::PowerShell)
+        }
+        "cmd" if flag.eq_ignore_ascii_case("/c") => Some(ApplyPatchShell::Cmd),
+        _ => None,
+    })
+}
+
+fn can_skip_flag(shell: &str, flag: &str) -> bool {
+    classify_shell_name(shell).is_some_and(|name| {
+        matches!(name.as_str(), "pwsh" | "powershell") && flag.eq_ignore_ascii_case("-noprofile")
+    })
+}
+
+fn parse_shell_script(argv: &[String]) -> Option<(ApplyPatchShell, &str)> {
+    match argv {
+        [shell, flag, script] => classify_shell(shell, flag).map(|shell_type| {
+            let script = script.as_str();
+            (shell_type, script)
+        }),
+        [shell, skip_flag, flag, script] if can_skip_flag(shell, skip_flag) => {
+            classify_shell(shell, flag).map(|shell_type| {
+                let script = script.as_str();
+                (shell_type, script)
+            })
+        }
+        _ => None,
+    }
+}
+
+fn extract_apply_patch_from_shell(
+    shell: ApplyPatchShell,
+    script: &str,
+) -> std::result::Result<(String, Option<String>), ExtractHeredocError> {
+    match shell {
+        ApplyPatchShell::Unix | ApplyPatchShell::PowerShell | ApplyPatchShell::Cmd => {
+            extract_apply_patch_from_bash(script)
+        }
+    }
+}
+
 pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
     match argv {
         // Direct invocation: apply_patch <patch>
@@ -103,9 +161,9 @@ pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
             Ok(source) => MaybeApplyPatch::Body(source),
             Err(e) => MaybeApplyPatch::PatchParseError(e),
         },
-        // Bash heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
-        [bash, flag, script] if bash == "bash" && flag == "-lc" => {
-            match extract_apply_patch_from_bash(script) {
+        // Shell heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
+        _ => match parse_shell_script(argv) {
+            Some((shell, script)) => match extract_apply_patch_from_shell(shell, script) {
                 Ok((body, workdir)) => match parse_patch(&body) {
                     Ok(mut source) => {
                         source.workdir = workdir;
@@ -117,9 +175,9 @@ pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
                     MaybeApplyPatch::NotApplyPatch
                 }
                 Err(e) => MaybeApplyPatch::ShellParseError(e),
-            }
-        }
-        _ => MaybeApplyPatch::NotApplyPatch,
+            },
+            None => MaybeApplyPatch::NotApplyPatch,
+        },
     }
 }
 
@@ -214,24 +272,17 @@ impl ApplyPatchAction {
 /// cwd must be an absolute path so that we can resolve relative paths in the
 /// patch.
 pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApplyPatchVerified {
-    // Detect a raw patch body passed directly as the command or as the body of a bash -lc
+    // Detect a raw patch body passed directly as the command or as the body of a shell
     // script. In these cases, report an explicit error rather than applying the patch.
-    match argv {
-        [body] => {
-            if parse_patch(body).is_ok() {
-                return MaybeApplyPatchVerified::CorrectnessError(
-                    ApplyPatchError::ImplicitInvocation,
-                );
-            }
-        }
-        [bash, flag, script] if bash == "bash" && flag == "-lc" => {
-            if parse_patch(script).is_ok() {
-                return MaybeApplyPatchVerified::CorrectnessError(
-                    ApplyPatchError::ImplicitInvocation,
-                );
-            }
-        }
-        _ => {}
+    if let [body] = argv
+        && parse_patch(body).is_ok()
+    {
+        return MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation);
+    }
+    if let Some((_, script)) = parse_shell_script(argv)
+        && parse_patch(script).is_ok()
+    {
+        return MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation);
     }
 
     match maybe_parse_apply_patch(argv) {
@@ -288,7 +339,7 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
                             path,
                             ApplyPatchFileChange::Update {
                                 unified_diff,
-                                move_path: move_path.map(|p| cwd.join(p)),
+                                move_path: move_path.map(|p| effective_cwd.join(p)),
                                 new_content: contents,
                             },
                         );
@@ -863,6 +914,22 @@ mod tests {
         strs_to_strings(&["bash", "-lc", script])
     }
 
+    fn args_powershell(script: &str) -> Vec<String> {
+        strs_to_strings(&["powershell.exe", "-Command", script])
+    }
+
+    fn args_powershell_no_profile(script: &str) -> Vec<String> {
+        strs_to_strings(&["powershell.exe", "-NoProfile", "-Command", script])
+    }
+
+    fn args_pwsh(script: &str) -> Vec<String> {
+        strs_to_strings(&["pwsh", "-NoProfile", "-Command", script])
+    }
+
+    fn args_cmd(script: &str) -> Vec<String> {
+        strs_to_strings(&["cmd.exe", "/c", script])
+    }
+
     fn heredoc_script(prefix: &str) -> String {
         format!(
             "{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH"
@@ -882,8 +949,7 @@ mod tests {
         }]
     }
 
-    fn assert_match(script: &str, expected_workdir: Option<&str>) {
-        let args = args_bash(script);
+    fn assert_match_args(args: Vec<String>, expected_workdir: Option<&str>) {
         match maybe_parse_apply_patch(&args) {
             MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
                 assert_eq!(workdir.as_deref(), expected_workdir);
@@ -893,6 +959,11 @@ mod tests {
         }
     }
 
+    fn assert_match(script: &str, expected_workdir: Option<&str>) {
+        let args = args_bash(script);
+        assert_match_args(args, expected_workdir);
+    }
+
     fn assert_not_match(script: &str) {
         let args = args_bash(script);
         assert_matches!(
@@ -978,6 +1049,13 @@ mod tests {
         assert_match(&heredoc_script(""), None);
     }
 
+    #[test]
+    fn test_heredoc_non_login_shell() {
+        let script = heredoc_script("");
+        let args = strs_to_strings(&["bash", "-c", &script]);
+        assert_match_args(args, None);
+    }
+
     #[test]
     fn test_heredoc_applypatch() {
         let args = strs_to_strings(&[
@@ -1006,6 +1084,28 @@ PATCH"#,
         }
     }
 
+    #[test]
+    fn test_powershell_heredoc() {
+        let script = heredoc_script("");
+        assert_match_args(args_powershell(&script), None);
+    }
+    #[test]
+    fn test_powershell_heredoc_no_profile() {
+        let script = heredoc_script("");
+        assert_match_args(args_powershell_no_profile(&script), None);
+    }
+    #[test]
+    fn test_pwsh_heredoc() {
+        let script = heredoc_script("");
+        assert_match_args(args_pwsh(&script), None);
+    }
+
+    #[test]
+    fn test_cmd_heredoc_with_cd() {
+        let script = heredoc_script("cd foo && ");
+        assert_match_args(args_cmd(&script), Some("foo"));
+    }
+
     #[test]
     fn test_heredoc_with_leading_cd() {
         assert_match(&heredoc_script("cd foo && "), Some("foo"));
@@ -1603,6 +1703,53 @@ g
         );
     }
 
+    #[test]
+    fn test_apply_patch_resolves_move_path_with_effective_cwd() {
+        let session_dir = tempdir().unwrap();
+        let worktree_rel = "alt";
+        let worktree_dir = session_dir.path().join(worktree_rel);
+        fs::create_dir_all(&worktree_dir).unwrap();
+
+        let source_name = "old.txt";
+        let dest_name = "renamed.txt";
+        let source_path = worktree_dir.join(source_name);
+        fs::write(&source_path, "before\n").unwrap();
+
+        let patch = wrap_patch(&format!(
+            r#"*** Update File: {source_name}
+*** Move to: {dest_name}
+@@
+-before
++after"#
+        ));
+
+        let shell_script = format!("cd {worktree_rel} && apply_patch <<'PATCH'\n{patch}\nPATCH");
+        let argv = vec!["bash".into(), "-lc".into(), shell_script];
+
+        let result = maybe_parse_apply_patch_verified(&argv, session_dir.path());
+        let action = match result {
+            MaybeApplyPatchVerified::Body(action) => action,
+            other => panic!("expected verified body, got {other:?}"),
+        };
+
+        assert_eq!(action.cwd, worktree_dir);
+
+        let change = action
+            .changes()
+            .get(&worktree_dir.join(source_name))
+            .expect("source file change present");
+
+        match change {
+            ApplyPatchFileChange::Update { move_path, .. } => {
+                assert_eq!(
+                    move_path.as_deref(),
+                    Some(worktree_dir.join(dest_name).as_path())
+                );
+            }
+            other => panic!("expected update change, got {other:?}"),
+        }
+    }
+
     #[test]
     fn test_apply_patch_fails_on_write_error() {
         let dir = tempdir().unwrap();

codex-rs/apply-patch/tests/fixtures/scenarios/.gitattributes

@@ -0,0 +1 @@
+** text eol=lf

codex-rs/apply-patch/tests/fixtures/scenarios/001_add_file/expected/bar.md

@@ -0,0 +1 @@
+This is a new file

codex-rs/apply-patch/tests/fixtures/scenarios/001_add_file/patch.txt

@@ -0,0 +1,4 @@
+*** Begin Patch
+*** Add File: bar.md
++This is a new file
+*** End Patch

codex-rs/apply-patch/tests/fixtures/scenarios/002_multiple_operations/expected/modify.txt

@@ -0,0 +1,2 @@
+line1
+changed

codex-rs/apply-patch/tests/fixtures/scenarios/002_multiple_operations/expected/nested/new.txt

@@ -0,0 +1 @@
+created