reconfig

## Summary
When incrementing the minor version, we should reset patch to 0, rather
than keeping it.

## Testing
- [x] tested locally with dry_run and `get_latest_release_version`
mocked out

---------

Co-authored-by: Michael Bolin <mbolin@openai.com>

.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/ci.yml

@@ -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@v5
         with:
           name: codex-npm-staging
           path: ${{ steps.stage_npm_package.outputs.pack_output }}

.github/workflows/cla.yml

@@ -13,17 +13,39 @@ 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[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

@@ -22,6 +22,6 @@ jobs:
       - name: Annotate locations with typos
         uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
       - name: Codespell
-        uses: codespell-project/actions-codespell@406322ec52dd7b488e48c1c4b82e2a8b3a1bf630 # v2.1
+        uses: codespell-project/actions-codespell@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@v5
 
       - 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@v5
 
       - 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
@@ -76,7 +76,7 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - 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
@@ -159,20 +164,90 @@ jobs:
             ~/.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 }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
+          restore-keys: |
+            cargo-home-${{ 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') }}
+      # Install and restore sccache cache
+      - 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@v4
         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 }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
+          restore-keys: |
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-
+            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: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
+        name: Restore APT cache (musl)
+        id: cache_apt_restore
+        uses: actions/cache/restore@v4
+        with:
+          path: |
+            /var/cache/apt
+          key: apt-${{ 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
@@ -191,20 +266,6 @@ 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 ${{ matrix.target }} --cargo-profile ci-test
-        env:
-          RUST_BACKTRACE: 1
-
       # Save caches explicitly; make non-fatal so cache packaging
       # never fails the overall job. Only save when key wasn't hit.
       - name: Save cargo home cache
@@ -217,33 +278,201 @@ jobs:
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
-          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
 
-      - 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
         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 }}-${{ hashFiles('**/Cargo.lock') }}-${{ 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 '```';
+          } >> "$GITHUB_STEP_SUMMARY"
+
+      - name: Save APT cache (musl)
+        if: always() && !cancelled() && (matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl') && steps.cache_apt_restore.outputs.cache-hit != 'true'
+        continue-on-error: true
+        uses: actions/cache/save@v4
+        with:
+          path: |
+            /var/cache/apt
+          key: apt-${{ 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@v5
+      - uses: dtolnay/rust-toolchain@1.90
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Restore cargo home cache
+        id: cache_cargo_home_restore
+        uses: actions/cache/restore@v4
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
+          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@v4
+        with:
+          path: ${{ github.workspace }}/.sccache/
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
+          restore-keys: |
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-
+            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 ${{ matrix.target }} --cargo-profile ci-test
+        env:
+          RUST_BACKTRACE: 1
+          NEXTEST_STATUS_LEVEL: leak
+
+      - name: Save cargo home cache
+        if: always() && !cancelled() && steps.cache_cargo_home_restore.outputs.cache-hit != 'true'
+        continue-on-error: true
+        uses: actions/cache/save@v4
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
+
+      - 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
+        with:
+          path: ${{ github.workspace }}/.sccache/
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ 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 +481,8 @@ 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 +494,10 @@ 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

@@ -295,6 +295,15 @@ 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:
@@ -324,7 +333,11 @@ 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
@@ -350,7 +363,7 @@ jobs:
             fi
           fi
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: ${{ matrix.target }}
           # Upload the per-binary .zst files as well as the new .tar.gz
@@ -358,8 +371,20 @@ jobs:
           path: |
             codex-rs/dist/${{ matrix.target }}/*
 
+  shell-tool-mcp:
+    name: shell-tool-mcp
+    needs: tag-check
+    uses: ./.github/workflows/shell-tool-mcp.yml
+    with:
+      release-tag: ${{ github.ref_name }}
+      # We are not ready to publish yet.
+      publish: false
+    secrets: inherit
+
   release:
-    needs: build
+    needs:
+      - build
+      - shell-tool-mcp
     name: release
     runs-on: ubuntu-latest
     permissions:
@@ -382,6 +407,14 @@ jobs:
       - name: List
         run: ls -R dist/
 
+      # This is a temporary fix: we should modify shell-tool-mcp.yml so these
+      # files do not end up in dist/ in the first place.
+      - name: Delete entries from dist/ that should not go in the release
+        run: |
+          rm -rf dist/shell-tool-mcp*
+
+          ls -R dist/
+
       - name: Define release name
         id: release_name
         run: |

.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@v5
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          run_install: false
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v5
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          cache: "pnpm"
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Format check
+        run: pnpm --filter @openai/codex-shell-tool-mcp run format
+
+      - name: Run tests
+        run: pnpm --filter @openai/codex-shell-tool-mcp test
+
+      - name: Build
+        run: pnpm --filter @openai/codex-shell-tool-mcp run build

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

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

.gitignore

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

AGENTS.md

@@ -84,6 +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

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

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/Cargo.toml

@@ -5,6 +5,7 @@ members = [
     "async-utils",
     "app-server",
     "app-server-protocol",
+    "app-server-test-client",
     "apply-patch",
     "arg0",
     "feedback",
@@ -15,28 +16,31 @@ members = [
     "common",
     "core",
     "exec",
+    "exec-server",
     "execpolicy",
+    "execpolicy-legacy",
+    "keyring-store",
     "file-search",
-    "git-tooling",
     "linux-sandbox",
+    "lmstudio",
     "login",
     "mcp-server",
     "mcp-types",
     "ollama",
     "process-hardening",
     "protocol",
-    "protocol-ts",
     "rmcp-client",
     "responses-api-proxy",
     "stdio-to-uds",
     "otel",
     "tui",
-    "git-apply",
+    "utils/git",
+    "utils/cache",
+    "utils/image",
     "utils/json-to-toml",
-    "utils/readiness",
     "utils/pty",
+    "utils/readiness",
     "utils/string",
-    "utils/tokenizer",
 ]
 resolver = "2"
 
@@ -62,26 +66,30 @@ codex-chatgpt = { path = "chatgpt" }
 codex-common = { path = "common" }
 codex-core = { path = "core" }
 codex-exec = { path = "exec" }
+codex-execpolicy = { path = "execpolicy" }
 codex-feedback = { path = "feedback" }
 codex-file-search = { path = "file-search" }
-codex-git-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-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-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-utils-tokenizer = { path = "utils/tokenizer" }
+codex-windows-sandbox = { path = "windows-sandbox-rs" }
 core_test_support = { path = "core/tests/common" }
 mcp-types = { path = "mcp-types" }
 mcp_test_support = { path = "mcp-server/tests/common" }
@@ -90,8 +98,8 @@ 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"
+arboard = { version = "3", features = ["wayland-data-control"] }
+askama = "0.14"
 assert_cmd = "2"
 assert_matches = "1.5.0"
 async-channel = "2.3.1"
@@ -101,6 +109,7 @@ axum = { version = "0.8", default-features = false }
 base64 = "0.22.1"
 bytes = "1.10.1"
 chrono = "0.4.42"
+chardetng = "0.1.17"
 clap = "4"
 clap_complete = "4"
 color-eyre = "0.6.3"
@@ -113,26 +122,31 @@ dotenvy = "0.15.7"
 dunce = "1.0.4"
 env-flags = "0.1.1"
 env_logger = "0.11.5"
+encoding_rs = "0.8.35"
 escargot = "0.5"
 eventsource-stream = "0.2.3"
 futures = { version = "0.3", default-features = false }
-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"
+indexmap = "2.12.0"
 insta = "1.43.2"
 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"
 log = "0.4"
+lru = "0.12.5"
 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"
 openssl-sys = "*"
 opentelemetry = "0.30.0"
 opentelemetry-appender-tracing = "0.30.0"
@@ -141,7 +155,6 @@ opentelemetry-semantic-conventions = "0.30.0"
 opentelemetry_sdk = "0.30.0"
 os_info = "3.12.0"
 owo-colors = "4.2.0"
-paste = "1.0.15"
 path-absolutize = "3.1.1"
 pathdiff = "0.2"
 portable-pty = "0.9.0"
@@ -153,10 +166,9 @@ ratatui = "0.29.0"
 ratatui-macros = "0.6.0"
 regex-lite = "0.1.7"
 reqwest = "0.12"
-rmcp = { version = "0.8.3", default-features = false }
+rmcp = { version = "0.8.5", default-features = false }
 schemars = "0.8.22"
 seccompiler = "0.5.0"
-sentry = "0.34.0"
 serde = "1"
 serde_json = "1"
 serde_with = "3.14"
@@ -165,6 +177,7 @@ sha1 = "0.10.6"
 sha2 = "0.10"
 shlex = "1.3.0"
 similar = "2.7.0"
+socket2 = "0.6.0"
 starlark = "0.13.0"
 strum = "0.27.2"
 strum_macros = "0.27.2"
@@ -173,7 +186,7 @@ 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"
@@ -202,8 +215,9 @@ walkdir = "2.5.0"
 webbrowser = "1.0"
 which = "6"
 wildmatch = "2.5.0"
+
 wiremock = "0.6"
-zeroize = "1.8.1"
+zeroize = "1.8.2"
 
 [workspace.lints]
 rust = {}
@@ -246,7 +260,11 @@ 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", "codex-utils-tokenizer"]
+ignored = [
+    "icu_provider",
+    "openssl-sys",
+    "codex-utils-readiness",
+]
 
 [profile.release]
 lto = "fat"
@@ -265,6 +283,7 @@ 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

@@ -58,13 +58,16 @@ To test to see what happens when a command is run under the sandbox provided by
 
 ```
 # 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/app-server-protocol/Cargo.toml

@@ -14,11 +14,12 @@ workspace = true
 anyhow = { workspace = true }
 clap = { workspace = true, features = ["derive"] }
 codex-protocol = { workspace = true }
-paste = { 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/export.rs

@@ -2,20 +2,25 @@ use crate::ClientNotification;
 use crate::ClientRequest;
 use crate::ServerNotification;
 use crate::ServerRequest;
+use crate::export_client_notification_schemas;
+use crate::export_client_param_schemas;
 use crate::export_client_response_schemas;
 use crate::export_client_responses;
+use crate::export_server_notification_schemas;
+use crate::export_server_param_schemas;
 use crate::export_server_response_schemas;
 use crate::export_server_responses;
 use anyhow::Context;
 use anyhow::Result;
 use anyhow::anyhow;
+use codex_protocol::protocol::EventMsg;
 use schemars::JsonSchema;
-use schemars::schema::RootSchema;
 use schemars::schema_for;
 use serde::Serialize;
 use serde_json::Map;
 use serde_json::Value;
-use std::collections::BTreeMap;
+use std::collections::HashMap;
+use std::collections::HashSet;
 use std::ffi::OsStr;
 use std::fs;
 use std::io::Read;
@@ -27,91 +32,64 @@ use ts_rs::TS;
 
 const HEADER: &str = "// GENERATED CODE! DO NOT MODIFY BY HAND!\n\n";
 
-macro_rules! for_each_schema_type {
-    ($macro:ident) => {
-        $macro!(crate::RequestId);
-        $macro!(crate::JSONRPCMessage);
-        $macro!(crate::JSONRPCRequest);
-        $macro!(crate::JSONRPCNotification);
-        $macro!(crate::JSONRPCResponse);
-        $macro!(crate::JSONRPCError);
-        $macro!(crate::JSONRPCErrorError);
-        $macro!(crate::AddConversationListenerParams);
-        $macro!(crate::AddConversationSubscriptionResponse);
-        $macro!(crate::ApplyPatchApprovalParams);
-        $macro!(crate::ApplyPatchApprovalResponse);
-        $macro!(crate::ArchiveConversationParams);
-        $macro!(crate::ArchiveConversationResponse);
-        $macro!(crate::AuthMode);
-        $macro!(crate::AuthStatusChangeNotification);
-        $macro!(crate::CancelLoginChatGptParams);
-        $macro!(crate::CancelLoginChatGptResponse);
-        $macro!(crate::ClientInfo);
-        $macro!(crate::ClientNotification);
-        $macro!(crate::ClientRequest);
-        $macro!(crate::ConversationSummary);
-        $macro!(crate::ExecCommandApprovalParams);
-        $macro!(crate::ExecCommandApprovalResponse);
-        $macro!(crate::ExecOneOffCommandParams);
-        $macro!(crate::ExecOneOffCommandResponse);
-        $macro!(crate::FuzzyFileSearchParams);
-        $macro!(crate::FuzzyFileSearchResponse);
-        $macro!(crate::FuzzyFileSearchResult);
-        $macro!(crate::GetAuthStatusParams);
-        $macro!(crate::GetAuthStatusResponse);
-        $macro!(crate::GetUserAgentResponse);
-        $macro!(crate::GetUserSavedConfigResponse);
-        $macro!(crate::GitDiffToRemoteParams);
-        $macro!(crate::GitDiffToRemoteResponse);
-        $macro!(crate::GitSha);
-        $macro!(crate::InitializeParams);
-        $macro!(crate::InitializeResponse);
-        $macro!(crate::InputItem);
-        $macro!(crate::InterruptConversationParams);
-        $macro!(crate::InterruptConversationResponse);
-        $macro!(crate::ListConversationsParams);
-        $macro!(crate::ListConversationsResponse);
-        $macro!(crate::LoginApiKeyParams);
-        $macro!(crate::LoginApiKeyResponse);
-        $macro!(crate::LoginChatGptCompleteNotification);
-        $macro!(crate::LoginChatGptResponse);
-        $macro!(crate::LogoutChatGptParams);
-        $macro!(crate::LogoutChatGptResponse);
-        $macro!(crate::NewConversationParams);
-        $macro!(crate::NewConversationResponse);
-        $macro!(crate::Profile);
-        $macro!(crate::RemoveConversationListenerParams);
-        $macro!(crate::RemoveConversationSubscriptionResponse);
-        $macro!(crate::ResumeConversationParams);
-        $macro!(crate::ResumeConversationResponse);
-        $macro!(crate::SandboxSettings);
-        $macro!(crate::SendUserMessageParams);
-        $macro!(crate::SendUserMessageResponse);
-        $macro!(crate::SendUserTurnParams);
-        $macro!(crate::SendUserTurnResponse);
-        $macro!(crate::ServerNotification);
-        $macro!(crate::ServerRequest);
-        $macro!(crate::SessionConfiguredNotification);
-        $macro!(crate::SetDefaultModelParams);
-        $macro!(crate::SetDefaultModelResponse);
-        $macro!(crate::Tools);
-        $macro!(crate::UserInfoResponse);
-        $macro!(crate::UserSavedConfig);
-        $macro!(codex_protocol::protocol::EventMsg);
-        $macro!(codex_protocol::protocol::FileChange);
-        $macro!(codex_protocol::parse_command::ParsedCommand);
-        $macro!(codex_protocol::protocol::SandboxPolicy);
-    };
+#[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)?;
@@ -121,18 +99,34 @@ pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
     export_server_responses(out_dir)?;
     ServerNotification::export_all_to(out_dir)?;
 
-    generate_index_ts(out_dir)?;
-
-    let ts_files = ts_files_in(out_dir)?;
-    for file in &ts_files {
-        prepend_header_if_missing(file)?;
+    if options.generate_indices {
+        generate_index_ts(out_dir)?;
+        generate_index_ts(&v2_out_dir)?;
     }
 
-    if let Some(prettier_bin) = prettier
+    // 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()))?;
@@ -146,59 +140,115 @@ pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
 
 pub fn generate_json(out_dir: &Path) -> Result<()> {
     ensure_dir(out_dir)?;
-    let mut bundle: BTreeMap<String, RootSchema> = BTreeMap::new();
+    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"),
+    ];
 
-    macro_rules! add_schema {
-        ($ty:path) => {{
-            let name = type_basename(stringify!($ty));
-            let schema = write_json_schema_with_return::<$ty>(out_dir, &name)?;
-            bundle.insert(name, schema);
-        }};
+    let mut schemas: Vec<GeneratedSchema> = Vec::new();
+    for emit in envelope_emitters {
+        schemas.push(emit(out_dir)?);
     }
 
-    for_each_schema_type!(add_schema);
+    schemas.extend(export_client_param_schemas(out_dir)?);
+    schemas.extend(export_client_response_schemas(out_dir)?);
+    schemas.extend(export_server_param_schemas(out_dir)?);
+    schemas.extend(export_server_response_schemas(out_dir)?);
+    schemas.extend(export_client_notification_schemas(out_dir)?);
+    schemas.extend(export_server_notification_schemas(out_dir)?);
 
-    export_client_response_schemas(out_dir)?;
-    export_server_response_schemas(out_dir)?;
+    let bundle = build_schema_bundle(schemas)?;
+    write_pretty_json(
+        out_dir.join("codex_app_server_protocol.schemas.json"),
+        &bundle,
+    )?;
 
-    let mut definitions = Map::new();
+    Ok(())
+}
 
+fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<Value> {
     const SPECIAL_DEFINITIONS: &[&str] = &[
         "ClientNotification",
         "ClientRequest",
         "EventMsg",
-        "FileChange",
-        "InputItem",
-        "ParsedCommand",
-        "SandboxPolicy",
         "ServerNotification",
         "ServerRequest",
     ];
+    const IGNORED_DEFINITIONS: &[&str] = &["Option<()>"];
 
-    for (name, schema) in bundle {
-        let mut schema_value = serde_json::to_value(schema)?;
-        if let Value::Object(ref mut obj) = schema_value {
-            if let Some(defs) = obj.remove("definitions")
-                && let Value::Object(defs_obj) = defs
-            {
-                for (def_name, def_schema) in defs_obj {
-                    if !SPECIAL_DEFINITIONS.contains(&def_name.as_str()) {
-                        definitions.insert(def_name, def_schema);
-                    }
+    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 let Some(Value::Array(one_of)) = obj.get_mut("oneOf") {
-                for variant in one_of.iter_mut() {
-                    if let Some(variant_name) = variant_definition_name(&name, variant)
-                        && let Value::Object(variant_obj) = variant
+                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)
                     {
-                        variant_obj.insert("title".into(), Value::String(variant_name));
+                        forced_namespace_refs.push((def_name.clone(), ns.clone()));
                     }
+                } else {
+                    definitions.insert(def_name, def_schema);
                 }
             }
         }
-        definitions.insert(name, schema_value);
+
+        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();
@@ -213,30 +263,66 @@ pub fn generate_json(out_dir: &Path) -> Result<()> {
     root.insert("type".to_string(), Value::String("object".into()));
     root.insert("definitions".to_string(), Value::Object(definitions));
 
-    write_pretty_json(
-        out_dir.join("codex_app_server_protocol.schemas.json"),
-        &Value::Object(root),
-    )?;
-
-    Ok(())
+    Ok(Value::Object(root))
 }
 
-fn write_json_schema_with_return<T>(out_dir: &Path, name: &str) -> Result<RootSchema>
+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);
-    write_pretty_json(out_dir.join(format!("{file_stem}.json")), &schema)
+    let mut schema_value = serde_json::to_value(schema)?;
+    annotate_schema(&mut schema_value, Some(file_stem));
+    // If the name looks like a namespaced path (e.g., "v2::Type"), mirror
+    // the TypeScript layout and write to out_dir/v2/Type.json. Otherwise
+    // write alongside the legacy files.
+    let (raw_namespace, logical_name) = split_namespace(file_stem);
+    let out_path = if let Some(ns) = raw_namespace {
+        let dir = out_dir.join(ns);
+        ensure_dir(&dir)?;
+        dir.join(format!("{logical_name}.json"))
+    } else {
+        out_dir.join(format!("{file_stem}.json"))
+    };
+
+    write_pretty_json(out_path, &schema_value)
         .with_context(|| format!("Failed to write JSON schema for {file_stem}"))?;
-    Ok(schema)
+    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<()>
+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).map(|_| ())
+    write_json_schema_with_return::<T>(out_dir, name)
 }
 
 fn write_pretty_json(path: PathBuf, value: &impl Serialize) -> Result<()> {
@@ -245,13 +331,73 @@ fn write_pretty_json(path: PathBuf, value: &impl Serialize) -> Result<()> {
     fs::write(&path, json).with_context(|| format!("Failed to write {}", path.display()))?;
     Ok(())
 }
-fn type_basename(type_path: &str) -> String {
-    type_path
-        .rsplit_once("::")
-        .map(|(_, name)| name)
-        .unwrap_or(type_path)
-        .trim()
-        .to_string()
+
+/// 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> {
@@ -273,14 +419,6 @@ fn variant_definition_name(base: &str, variant: &Value) -> Option<String> {
             });
         }
 
-        if let Some(mode_literal) = literal_from_property(props, "mode") {
-            let pascal = to_pascal_case(mode_literal);
-            return Some(match base {
-                "SandboxPolicy" => format!("{pascal}SandboxPolicy"),
-                _ => format!("{pascal}{base}"),
-            });
-        }
-
         if props.len() == 1
             && let Some(key) = props.keys().next()
         {
@@ -301,11 +439,147 @@ fn variant_definition_name(base: &str, variant: &Value) -> Option<String> {
 }
 
 fn literal_from_property<'a>(props: &'a Map<String, Value>, key: &str) -> Option<&'a str> {
-    props
-        .get(key)
-        .and_then(|value| value.get("enum"))
-        .and_then(Value::as_array)
-        .and_then(|arr| arr.first())
+    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)
 }
 
@@ -335,6 +609,33 @@ fn ensure_dir(dir: &Path) -> Result<()> {
         .with_context(|| format!("Failed to create output directory {}", dir.display()))
 }
 
+fn rewrite_named_ref_to_namespace(value: &mut Value, ns: &str, name: &str) {
+    let direct = format!("#/definitions/{name}");
+    let prefixed = format!("{direct}/");
+    let replacement = format!("#/definitions/{ns}/{name}");
+    let replacement_prefixed = format!("{replacement}/");
+    match value {
+        Value::Object(obj) => {
+            if let Some(Value::String(reference)) = obj.get_mut("$ref") {
+                if reference == &direct {
+                    *reference = replacement;
+                } else if let Some(rest) = reference.strip_prefix(&prefixed) {
+                    *reference = format!("{replacement_prefixed}{rest}");
+                }
+            }
+            for child in obj.values_mut() {
+                rewrite_named_ref_to_namespace(child, ns, name);
+            }
+        }
+        Value::Array(items) => {
+            for child in items {
+                rewrite_named_ref_to_namespace(child, ns, name);
+            }
+        }
+        _ => {}
+    }
+}
+
 fn prepend_header_if_missing(path: &Path) -> Result<()> {
     let mut content = String::new();
     {
@@ -372,6 +673,28 @@ fn ts_files_in(dir: &Path) -> Result<Vec<PathBuf>> {
     Ok(files)
 }
 
+fn ts_files_in_recursive(dir: &Path) -> Result<Vec<PathBuf>> {
+    let mut files = Vec::new();
+    let mut stack = vec![dir.to_path_buf()];
+    while let Some(d) = stack.pop() {
+        for entry in
+            fs::read_dir(&d).with_context(|| format!("Failed to read dir {}", d.display()))?
+        {
+            let entry = entry?;
+            let path = entry.path();
+            if path.is_dir() {
+                stack.push(path);
+            } else if path.is_file() && path.extension() == Some(OsStr::new("ts")) {
+                files.push(path);
+            }
+        }
+    }
+    files.sort();
+    Ok(files)
+}
+
+/// Generate an index.ts file that re-exports all generated types.
+/// This allows consumers to import all types from a single file.
 fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
     let mut entries: Vec<String> = Vec::new();
     let mut stems: Vec<String> = ts_files_in(out_dir)?
@@ -388,6 +711,14 @@ fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
         entries.push(format!("export type {{ {name} }} from \"./{name}\";\n"));
     }
 
+    // If this is the root out_dir and a ./v2 folder exists with TS files,
+    // expose it as a namespace to avoid symbol collisions at the root.
+    let v2_dir = out_dir.join("v2");
+    let has_v2_ts = ts_files_in(&v2_dir).map(|v| !v.is_empty()).unwrap_or(false);
+    if has_v2_ts {
+        entries.push("export * as v2 from \"./v2\";\n".to_string());
+    }
+
     let mut content =
         String::with_capacity(HEADER.len() + entries.iter().map(String::len).sum::<usize>());
     content.push_str(HEADER);
@@ -402,3 +733,211 @@ fn generate_index_ts(out_dir: &Path) -> Result<PathBuf> {
         .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

@@ -34,6 +34,7 @@ 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>,
 }
 
@@ -42,6 +43,7 @@ pub struct JSONRPCRequest {
 pub struct JSONRPCNotification {
     pub method: String,
     #[serde(default, skip_serializing_if = "Option::is_none")]
+    #[ts(optional)]
     pub params: Option<serde_json::Value>,
 }
 
@@ -63,6 +65,7 @@ pub struct JSONRPCError {
 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

@@ -6,4 +6,7 @@ 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/common.rs

@@ -0,0 +1,797 @@
+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,
+    },
+    TurnStart => "turn/start" {
+        params: v2::TurnStartParams,
+        response: v2::TurnStartResponse,
+    },
+    TurnInterrupt => "turn/interrupt" {
+        params: v2::TurnInterruptParams,
+        response: v2::TurnInterruptResponse,
+    },
+    ReviewStart => "review/start" {
+        params: v2::ReviewStartParams,
+        response: v2::TurnStartResponse,
+    },
+
+    ModelList => "model/list" {
+        params: v2::ModelListParams,
+        response: v2::ModelListResponse,
+    },
+
+    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,
+    },
+
+    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),
+    TurnStarted => "turn/started" (v2::TurnStartedNotification),
+    TurnCompleted => "turn/completed" (v2::TurnCompletedNotification),
+    ItemStarted => "item/started" (v2::ItemStartedNotification),
+    ItemCompleted => "item/completed" (v2::ItemCompletedNotification),
+    AgentMessageDelta => "item/agentMessage/delta" (v2::AgentMessageDeltaNotification),
+    CommandExecutionOutputDelta => "item/commandExecution/outputDelta" (v2::CommandExecutionOutputDeltaNotification),
+    McpToolCallProgress => "item/mcpToolCall/progress" (v2::McpToolCallProgressNotification),
+    AccountUpdated => "account/updated" (v2::AccountUpdatedNotification),
+    AccountRateLimitsUpdated => "account/rateLimits/updated" (v2::AccountRateLimitsUpdatedNotification),
+    ReasoningSummaryTextDelta => "item/reasoning/summaryTextDelta" (v2::ReasoningSummaryTextDeltaNotification),
+    ReasoningSummaryPartAdded => "item/reasoning/summaryPartAdded" (v2::ReasoningSummaryPartAddedNotification),
+    ReasoningTextDelta => "item/reasoning/textDelta" (v2::ReasoningTextDeltaNotification),
+
+    /// Notifies the user of world-writable directories on Windows, which cannot be protected by the sandbox.
+    WindowsWorldWritableWarning => "windows/worldWritableWarning" (v2::WindowsWorldWritableWarningNotification),
+
+    #[serde(rename = "account/login/completed")]
+    #[ts(rename = "account/login/completed")]
+    #[strum(serialize = "account/login/completed")]
+    AccountLoginCompleted(v2::AccountLoginCompletedNotification),
+
+    /// 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()),
+            risk: None,
+            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",
+                    "risk": null,
+                    "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/mod.rs

@@ -0,0 +1,7 @@
+// Module declarations for the app-server protocol namespace.
+// Exposes protocol pieces used by `lib.rs` via `pub use protocol::common::*;`.
+
+pub mod common;
+pub mod thread_history;
+pub mod v1;
+pub mod v2;

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

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

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

@@ -0,0 +1,462 @@
+use std::collections::HashMap;
+use std::path::PathBuf;
+
+use codex_protocol::ConversationId;
+use codex_protocol::config_types::ForcedLoginMethod;
+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::models::ResponseItem;
+use codex_protocol::parse_command::ParsedCommand;
+use codex_protocol::protocol::AskForApproval;
+use codex_protocol::protocol::EventMsg;
+use codex_protocol::protocol::FileChange;
+use codex_protocol::protocol::ReviewDecision;
+use codex_protocol::protocol::SandboxCommandAssessment;
+use codex_protocol::protocol::SandboxPolicy;
+use codex_protocol::protocol::SessionSource;
+use codex_protocol::protocol::TurnAbortReason;
+use schemars::JsonSchema;
+use serde::Deserialize;
+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 risk: Option<SandboxCommandAssessment>,
+    pub parsed_cmd: Vec<ParsedCommand>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+pub struct ExecCommandApprovalResponse {
+    pub decision: ReviewDecision,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct CancelLoginChatGptParams {
+    #[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<PathBuf>,
+    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 +1,16 @@
+[package]
+name = "codex-app-server-test-client"
+version = { workspace = true }
+edition = "2024"
+
+[lints]
+workspace = true
+
+[dependencies]
+anyhow = { workspace = true }
+clap = { workspace = true, features = ["derive", "env"] }
+codex-app-server-protocol = { workspace = true }
+codex-protocol = { workspace = true }
+serde = { workspace = true, features = ["derive"] }
+serde_json = { workspace = true }
+uuid = { workspace = true, features = ["v4"] }

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

codex-rs/app-server/Cargo.toml

@@ -24,6 +24,7 @@ codex-file-search = { workspace = true }
 codex-login = { workspace = true }
 codex-protocol = { workspace = true }
 codex-app-server-protocol = { workspace = true }
+codex-feedback = { workspace = true }
 codex-utils-json-to-toml = { workspace = true }
 chrono = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
@@ -45,8 +46,11 @@ app_test_support = { workspace = true }
 assert_cmd = { workspace = true }
 base64 = { workspace = true }
 core_test_support = { workspace = true }
+mcp-types = { workspace = true }
 os_info = { workspace = true }
 pretty_assertions = { workspace = true }
+serial_test = { workspace = true }
 tempfile = { workspace = true }
 toml = { workspace = true }
 wiremock = { workspace = true }
+shlex = { workspace = true }

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

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");

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

@@ -12,19 +12,23 @@ 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 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;
 
+mod bespoke_event_handling;
 mod codex_message_processor;
 mod error_code;
 mod fuzzy_file_search;
@@ -43,7 +47,7 @@ pub async fn run_main(
 ) -> IoResult<()> {
     // Set up channels.
     let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
-    let (outgoing_tx, mut outgoing_rx) = mpsc::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({
@@ -82,6 +86,8 @@ pub async fn run_main(
             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(
@@ -96,8 +102,15 @@ pub async fn run_main(
         .with_writer(std::io::stderr)
         .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 _ = tracing_subscriber::registry()
         .with(stderr_fmt)
+        .with(feedback_layer)
         .with(otel.as_ref().map(|provider| {
             OpenTelemetryTracingBridge::new(&provider.logger).with_filter(
                 tracing_subscriber::filter::filter_fn(codex_core::otel_init::codex_export_filter),
@@ -112,6 +125,7 @@ pub async fn run_main(
             outgoing_message_sender,
             codex_linux_sandbox_exe,
             std::sync::Arc::new(config),
+            feedback.clone(),
         );
         async move {
             while let Some(msg) = incoming_rx.recv().await {

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

@@ -6,7 +6,6 @@ use crate::outgoing_message::OutgoingMessageSender;
 use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::ClientRequest;
 use codex_app_server_protocol::InitializeResponse;
-
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCErrorError;
 use codex_app_server_protocol::JSONRPCNotification;
@@ -17,6 +16,7 @@ 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;
 
@@ -33,9 +33,14 @@ impl MessageProcessor {
         outgoing: OutgoingMessageSender,
         codex_linux_sandbox_exe: Option<PathBuf>,
         config: Arc<Config>,
+        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,
@@ -46,6 +51,7 @@ impl MessageProcessor {
             outgoing.clone(),
             codex_linux_sandbox_exe,
             config,
+            feedback,
         );
 
         Self {
@@ -57,64 +63,80 @@ impl MessageProcessor {
 
     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;
         }
+
+        self.codex_message_processor
+            .process_request(codex_request)
+            .await;
     }
 
     pub(crate) async fn process_notification(&self, notification: JSONRPCNotification) {

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

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

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

@@ -19,12 +19,12 @@ use crate::error_code::INTERNAL_ERROR_CODE;
 /// Sends messages to the client and manages request callbacks.
 pub(crate) struct OutgoingMessageSender {
     next_request_id: AtomicI64,
-    sender: mpsc::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 +45,12 @@ 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 +76,9 @@ 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 +95,29 @@ 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:?}");
+        }
     }
 }
 
@@ -141,9 +155,13 @@ 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_protocol::protocol::RateLimitSnapshot;
-    use codex_protocol::protocol::RateLimitWindow;
+    use codex_app_server_protocol::RateLimitSnapshot;
+    use codex_app_server_protocol::RateLimitWindow;
     use pretty_assertions::assert_eq;
     use serde_json::json;
     use uuid::Uuid;
@@ -166,6 +184,7 @@ mod tests {
                 "params": {
                     "loginId": Uuid::nil(),
                     "success": true,
+                    "error": null,
                 },
             }),
             serde_json::to_value(jsonrpc_notification)
@@ -175,27 +194,79 @@ mod tests {
     }
 
     #[test]
-    fn verify_account_rate_limits_notification_serialization() {
-        let notification = ServerNotification::AccountRateLimitsUpdated(RateLimitSnapshot {
-            primary: Some(RateLimitWindow {
-                used_percent: 25.0,
-                window_minutes: Some(15),
-                resets_at: Some(123),
+    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,
+                },
             }),
-            secondary: None,
-        });
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
+
+    #[test]
+    fn verify_account_rate_limits_notification_serialization() {
+        let notification =
+            ServerNotification::AccountRateLimitsUpdated(AccountRateLimitsUpdatedNotification {
+                rate_limits: RateLimitSnapshot {
+                    primary: Some(RateLimitWindow {
+                        used_percent: 25,
+                        window_duration_mins: Some(15),
+                        resets_at: Some(123),
+                    }),
+                    secondary: None,
+                    credits: None,
+                },
+            });
 
         let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
         assert_eq!(
             json!({
                 "method": "account/rateLimits/updated",
                 "params": {
-                    "primary": {
-                        "used_percent": 25.0,
-                        "window_minutes": 15,
-                        "resets_at": 123,
-                    },
-                    "secondary": null,
+                    "rateLimits": {
+                        "primary": {
+                            "usedPercent": 25,
+                            "windowDurationMins": 15,
+                            "resetsAt": 123
+                        },
+                        "secondary": null,
+                        "credits": null
+                    }
+                },
+            }),
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
+
+    #[test]
+    fn verify_account_updated_notification_serialization() {
+        let notification = ServerNotification::AccountUpdated(AccountUpdatedNotification {
+            auth_mode: Some(AuthMode::ApiKey),
+        });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!({
+                "method": "account/updated",
+                "params": {
+                    "authMode": "apikey"
                 },
             }),
             serde_json::to_value(jsonrpc_notification)

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

@@ -13,6 +13,7 @@ base64 = { workspace = true }
 chrono = { workspace = true }
 codex-app-server-protocol = { workspace = true }
 codex-core = { workspace = true }
+codex-protocol = { workspace = true }
 serde = { workspace = true }
 serde_json = { workspace = true }
 tokio = { workspace = true, features = [
@@ -21,4 +22,7 @@ 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

@@ -6,9 +6,9 @@ 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::get_auth_file;
-use codex_core::auth::write_auth_json;
+use codex_core::auth::save_auth;
 use codex_core::token_data::TokenData;
 use codex_core::token_data::parse_id_token;
 use serde_json::json;
@@ -109,7 +109,11 @@ pub fn encode_id_token(claims: &ChatGptIdTokenClaims) -> Result<String> {
     Ok(format!("{header_b64}.{payload_b64}.{signature_b64}"))
 }
 
-pub fn write_chatgpt_auth(codex_home: &Path, fixture: ChatGptAuthFixture) -> Result<()> {
+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 {
@@ -127,5 +131,5 @@ pub fn write_chatgpt_auth(codex_home: &Path, fixture: ChatGptAuthFixture) -> Res
         last_refresh,
     };
 
-    write_auth_json(&get_auth_file(codex_home), &auth).context("write auth.json")
+    save_auth(codex_home, &auth, cli_auth_credentials_store_mode).context("write auth.json")
 }

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

@@ -2,17 +2,22 @@ mod auth_fixtures;
 mod mcp_process;
 mod mock_model_server;
 mod responses;
+mod rollout;
 
 pub use auth_fixtures::ChatGptAuthFixture;
 pub use auth_fixtures::ChatGptIdTokenClaims;
 pub use auth_fixtures::encode_id_token;
 pub use auth_fixtures::write_chatgpt_auth;
 use codex_app_server_protocol::JSONRPCResponse;
+pub use core_test_support::format_with_current_shell;
+pub use core_test_support::format_with_current_shell_display;
 pub use mcp_process::McpProcess;
 pub use mock_model_server::create_mock_chat_completions_server;
+pub use mock_model_server::create_mock_chat_completions_server_unchecked;
 pub use responses::create_apply_patch_sse_response;
 pub use responses::create_final_assistant_message_sse_response;
-pub use responses::create_shell_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

@@ -14,29 +14,38 @@ use anyhow::Context;
 use assert_cmd::prelude::*;
 use codex_app_server_protocol::AddConversationListenerParams;
 use codex_app_server_protocol::ArchiveConversationParams;
+use codex_app_server_protocol::CancelLoginAccountParams;
 use codex_app_server_protocol::CancelLoginChatGptParams;
 use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::ClientNotification;
+use codex_app_server_protocol::FeedbackUploadParams;
+use codex_app_server_protocol::GetAccountParams;
 use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::InitializeParams;
 use codex_app_server_protocol::InterruptConversationParams;
-use codex_app_server_protocol::ListConversationsParams;
-use codex_app_server_protocol::ListModelsParams;
-use codex_app_server_protocol::LoginApiKeyParams;
-use codex_app_server_protocol::NewConversationParams;
-use codex_app_server_protocol::RemoveConversationListenerParams;
-use codex_app_server_protocol::ResumeConversationParams;
-use codex_app_server_protocol::SendUserMessageParams;
-use codex_app_server_protocol::SendUserTurnParams;
-use codex_app_server_protocol::ServerRequest;
-use codex_app_server_protocol::SetDefaultModelParams;
-
 use codex_app_server_protocol::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;
 
@@ -242,6 +251,24 @@ impl McpProcess {
         self.send_request("account/rateLimits/read", None).await
     }
 
+    /// Send an `account/read` JSON-RPC request.
+    pub async fn send_get_account_request(
+        &mut self,
+        params: GetAccountParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/read", params).await
+    }
+
+    /// Send a `feedback/upload` JSON-RPC request.
+    pub async fn send_feedback_upload_request(
+        &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
@@ -265,10 +292,46 @@ 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: ListModelsParams,
+        params: ModelListParams,
     ) -> anyhow::Result<i64> {
         let params = Some(serde_json::to_value(params)?);
         self.send_request("model/list", params).await
@@ -297,6 +360,33 @@ 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,
@@ -311,6 +401,40 @@ impl McpProcess {
         self.send_request("logoutChatGpt", None).await
     }
 
+    /// Send an `account/logout` JSON-RPC request.
+    pub async fn send_logout_account_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("account/logout", None).await
+    }
+
+    /// Send an `account/login/start` JSON-RPC request for API key login.
+    pub async fn send_login_account_api_key_request(
+        &mut self,
+        api_key: &str,
+    ) -> anyhow::Result<i64> {
+        let params = serde_json::json!({
+            "type": "apiKey",
+            "apiKey": api_key,
+        });
+        self.send_request("account/login/start", Some(params)).await
+    }
+
+    /// Send an `account/login/start` JSON-RPC request for ChatGPT login.
+    pub async fn send_login_account_chatgpt_request(&mut self) -> anyhow::Result<i64> {
+        let params = serde_json::json!({
+            "type": "chatgpt"
+        });
+        self.send_request("account/login/start", Some(params)).await
+    }
+
+    /// Send an `account/login/cancel` JSON-RPC request.
+    pub async fn send_cancel_login_account_request(
+        &mut self,
+        params: CancelLoginAccountParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/login/cancel", params).await
+    }
+
     /// Send a `fuzzyFileSearch` JSON-RPC request.
     pub async fn send_fuzzy_file_search_request(
         &mut self,

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/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 +77,7 @@ pub fn create_apply_patch_sse_response(
                         {
                             "id": call_id,
                             "function": {
-                                "name": "shell",
+                                "name": "shell_command",
                                 "arguments": tool_call_arguments
                             }
                         }

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

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

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

@@ -1,5 +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::AuthMode;
@@ -11,6 +10,7 @@ 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;
 
@@ -71,125 +71,99 @@ 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) {
+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!(
@@ -197,76 +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() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml_forced_login(codex_home.path(), "chatgpt")
-        .unwrap_or_else(|err| panic!("write config.toml: {err}"));
+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
-        .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_login_api_key_request(LoginApiKeyParams {
             api_key: "sk-test-key".to_string(),
         })
-        .await
-        .expect("send loginApiKey");
+        .await?;
 
     let err: JSONRPCError = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("loginApiKey error timeout")
-    .expect("loginApiKey error");
+    .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;
@@ -32,49 +32,45 @@ use codex_protocol::protocol::Event;
 use codex_protocol::protocol::EventMsg;
 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 +268,10 @@ 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,
+            risk: None,
             parsed_cmd: vec![ParsedCommand::Unknown {
                 cmd: "python3 -c 'print(42)'".to_string()
             }],
@@ -323,17 +284,14 @@ 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
@@ -349,19 +307,15 @@ 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.
@@ -369,70 +323,53 @@ 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 {
@@ -441,33 +378,29 @@ 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 {
@@ -487,22 +420,17 @@ 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 {
@@ -517,23 +445,18 @@ 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");
+    .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()
@@ -547,13 +470,9 @@ 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"
     );
 
@@ -561,9 +480,9 @@ 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

@@ -1,6 +1,4 @@
-use std::collections::HashMap;
-use std::path::Path;
-
+use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
 use codex_app_server_protocol::GetUserSavedConfigResponse;
@@ -17,6 +15,8 @@ use codex_protocol::config_types::ReasoningSummary;
 use codex_protocol::config_types::SandboxMode;
 use codex_protocol::config_types::Verbosity;
 use pretty_assertions::assert_eq;
+use std::collections::HashMap;
+use std::path::Path;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
@@ -27,7 +27,7 @@ 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"
 approval_policy = "on-request"
 sandbox_mode = "workspace-write"
 model_reasoning_summary = "detailed"
@@ -60,31 +60,21 @@ chatgpt_base_url = "https://api.chatgpt.com"
 }
 
 #[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 expected = GetUserSavedConfigResponse {
         config: UserSavedConfig {
             approval_policy: Some(AskForApproval::OnRequest),
@@ -97,7 +87,7 @@ async fn get_config_toml_parses_all_fields() {
             }),
             forced_chatgpt_workspace_id: Some("12345678-0000-0000-0000-000000000000".into()),
             forced_login_method: Some(ForcedLoginMethod::Chatgpt),
-            model: Some("gpt-5-codex".into()),
+            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),
@@ -122,33 +112,24 @@ 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,
@@ -167,4 +148,5 @@ 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 +12,66 @@ 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"),
+    )?;
     create_fake_rollout(
         codex_home.path(),
         "2025-01-01T13-00-00",
         "2025-01-01T13:00:00Z",
         "Hello B",
-    );
+        Some("openai"),
+    )?;
     create_fake_rollout(
         codex_home.path(),
         "2025-01-01T12-00-00",
         "2025-01-01T12:00:00Z",
         "Hello C",
-    );
+        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 +80,277 @@ 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"),
+    )?;
+
+    // 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:#?}"),
+    }
 
-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}"));
+    // 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:#?}")
+        }
+    }
 
-    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
-            }
+    // 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()
+            }),
         })
-        .to_string(),
+        .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:#?}"
     );
-    // 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(),
+    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:#?}"
     );
-    // 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}"));
+
+    Ok(())
 }

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

@@ -1,6 +1,4 @@
-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;
@@ -12,7 +10,11 @@ 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 std::time::Duration;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
@@ -41,32 +43,26 @@ 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(),
@@ -79,61 +75,47 @@ 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(())
 }
 
 #[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}"));
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_and_cancel_chatgpt() -> 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 login_id = mcp
-        .send_login_chat_gpt_request()
-        .await
-        .expect("send loginChatGpt");
+    let login_id = mcp.send_login_chat_gpt_request().await?;
     let login_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(login_id)),
     )
-    .await
-    .expect("loginChatGpt timeout")
-    .expect("loginChatGpt response");
-    let login: LoginChatGptResponse = to_response(login_resp).expect("deserialize login resp");
+    .await??;
+    let login: LoginChatGptResponse = to_response(login_resp)?;
 
     let cancel_id = mcp
         .send_cancel_login_chat_gpt_request(CancelLoginChatGptParams {
             login_id: login.login_id,
         })
-        .await
-        .expect("send cancelLoginChatGpt");
+        .await?;
     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");
+    .await??;
+    let _ok: CancelLoginChatGptResponse = to_response(cancel_resp)?;
 
     // Optionally observe the completion notification; do not fail if it races.
     let maybe_note = timeout(
@@ -144,6 +126,7 @@ async fn login_and_cancel_chatgpt() {
     if maybe_note.is_err() {
         eprintln!("warning: did not observe login_chat_gpt_complete notification after cancel");
     }
+    Ok(())
 }
 
 fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
@@ -176,66 +159,48 @@ forced_chatgpt_workspace_id = "{workspace_id}"
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn login_chatgpt_rejected_when_forced_api() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml_forced_login(codex_home.path(), "api")
-        .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 request_id = mcp
-        .send_login_chat_gpt_request()
-        .await
-        .expect("send loginChatGpt");
+    let request_id = mcp.send_login_chat_gpt_request().await?;
     let err: JSONRPCError = timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
     )
-    .await
-    .expect("loginChatGpt error timeout")
-    .expect("loginChatGpt error");
+    .await??;
 
     assert_eq!(
         err.error.message,
         "ChatGPT login is disabled. Use API key login instead."
     );
+    Ok(())
 }
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn login_chatgpt_includes_forced_workspace_query_param() {
-    let codex_home = TempDir::new().unwrap_or_else(|e| panic!("create tempdir: {e}"));
-    create_config_toml_forced_workspace(codex_home.path(), "ws-forced")
-        .unwrap_or_else(|err| panic!("write config.toml: {err}"));
+// 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
-        .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_login_chat_gpt_request()
-        .await
-        .expect("send loginChatGpt");
+    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
-    .expect("loginChatGpt timeout")
-    .expect("loginChatGpt response");
+    .await??;
 
-    let login: LoginChatGptResponse = to_response(resp).expect("deserialize login resp");
+    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

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

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 +266,126 @@ stream_max_retries = 0
         ),
     )
 }
+
+#[expect(clippy::expect_used)]
+async fn read_raw_response_item(
+    mcp: &mut McpProcess,
+    conversation_id: ConversationId,
+) -> ResponseItem {
+    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");
+
+    let event: RawResponseItemEvent =
+        serde_json::from_value(msg_value).expect("deserialize raw response item");
+    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

@@ -1,5 +1,4 @@
-use std::time::Duration;
-
+use anyhow::Result;
 use app_test_support::ChatGptAuthFixture;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
@@ -7,45 +6,41 @@ 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::AuthCredentialsStoreMode;
 use pretty_assertions::assert_eq;
+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()?;
 
     write_chatgpt_auth(
         codex_home.path(),
         ChatGptAuthFixture::new("access")
             .refresh_token("refresh")
             .email("user@example.com"),
-    )
-    .expect("write chatgpt auth");
+        AuthCredentialsStoreMode::File,
+    )?;
 
-    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_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);
+    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() -> 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/mod.rs

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

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

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

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

@@ -1,4 +1,3 @@
-use anyhow::Context;
 use anyhow::Result;
 use app_test_support::ChatGptAuthFixture;
 use app_test_support::McpProcess;
@@ -8,9 +7,10 @@ use codex_app_server_protocol::GetAccountRateLimitsResponse;
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::LoginApiKeyParams;
+use codex_app_server_protocol::RateLimitSnapshot;
+use codex_app_server_protocol::RateLimitWindow;
 use codex_app_server_protocol::RequestId;
-use codex_protocol::protocol::RateLimitSnapshot;
-use codex_protocol::protocol::RateLimitWindow;
+use codex_core::auth::AuthCredentialsStoreMode;
 use pretty_assertions::assert_eq;
 use serde_json::json;
 use std::path::Path;
@@ -26,30 +26,20 @@ 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(flavor = "multi_thread", worker_threads = 2)]
+#[tokio::test]
 async fn get_account_rate_limits_requires_auth() -> Result<()> {
-    let codex_home = TempDir::new().context("create codex home tempdir")?;
+    let codex_home = TempDir::new()?;
 
-    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)])
-        .await
-        .context("spawn mcp process")?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .context("initialize timeout")?
-        .context("initialize request")?;
+    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
-        .context("send account/rateLimits/read")?;
+    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
-    .context("account/rateLimits/read timeout")?
-    .context("account/rateLimits/read error")?;
+    .await??;
 
     assert_eq!(error.id, RequestId::Integer(request_id));
     assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
@@ -61,32 +51,22 @@ async fn get_account_rate_limits_requires_auth() -> Result<()> {
     Ok(())
 }
 
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+#[tokio::test]
 async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
-    let codex_home = TempDir::new().context("create codex home tempdir")?;
+    let codex_home = TempDir::new()?;
 
-    let mut mcp = McpProcess::new(codex_home.path())
-        .await
-        .context("spawn mcp process")?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .context("initialize timeout")?
-        .context("initialize request")?;
+    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
-        .context("send account/rateLimits/read")?;
+    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
-    .context("account/rateLimits/read timeout")?
-    .context("account/rateLimits/read error")?;
+    .await??;
 
     assert_eq!(error.id, RequestId::Integer(request_id));
     assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
@@ -98,20 +78,20 @@ async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
     Ok(())
 }
 
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+#[tokio::test]
 async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
-    let codex_home = TempDir::new().context("create codex home tempdir")?;
+    let codex_home = TempDir::new()?;
     write_chatgpt_auth(
         codex_home.path(),
         ChatGptAuthFixture::new("chatgpt-token")
             .account_id("account-123")
             .plan_type("pro"),
-    )
-    .context("write chatgpt auth")?;
+        AuthCredentialsStoreMode::File,
+    )?;
 
     let server = MockServer::start().await;
     let server_url = server.uri();
-    write_chatgpt_base_url(codex_home.path(), &server_url).context("write chatgpt base url")?;
+    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")
@@ -147,42 +127,32 @@ async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
         .mount(&server)
         .await;
 
-    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)])
-        .await
-        .context("spawn mcp process")?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
-        .await
-        .context("initialize timeout")?
-        .context("initialize request")?;
+    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
-        .context("send account/rateLimits/read")?;
+    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
-    .context("account/rateLimits/read timeout")?
-    .context("account/rateLimits/read response")?;
+    .await??;
 
-    let received: GetAccountRateLimitsResponse =
-        to_response(response).context("deserialize rate limit response")?;
+    let received: GetAccountRateLimitsResponse = to_response(response)?;
 
     let expected = GetAccountRateLimitsResponse {
         rate_limits: RateLimitSnapshot {
             primary: Some(RateLimitWindow {
-                used_percent: 42.0,
-                window_minutes: Some(60),
+                used_percent: 42,
+                window_duration_mins: Some(60),
                 resets_at: Some(primary_reset_timestamp),
             }),
             secondary: Some(RateLimitWindow {
-                used_percent: 5.0,
-                window_minutes: Some(1440),
+                used_percent: 5,
+                window_duration_mins: Some(1440),
                 resets_at: Some(secondary_reset_timestamp),
             }),
+            credits: None,
         },
     };
     assert_eq!(received, expected);
@@ -195,16 +165,13 @@ async fn login_with_api_key(mcp: &mut McpProcess, api_key: &str) -> Result<()> {
         .send_login_api_key_request(LoginApiKeyParams {
             api_key: api_key.to_string(),
         })
-        .await
-        .context("send loginApiKey")?;
+        .await?;
 
     timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
     )
-    .await
-    .context("loginApiKey timeout")?
-    .context("loginApiKey response")?;
+    .await??;
 
     Ok(())
 }

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

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

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

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

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

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

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

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

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

@@ -30,6 +30,7 @@ pub use standalone_executable::main;
 pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_tool_instructions.md");
 
 const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
+const APPLY_PATCH_SHELLS: [&str; 3] = ["bash", "zsh", "sh"];
 
 #[derive(Debug, Error, PartialEq)]
 pub enum ApplyPatchError {
@@ -96,6 +97,13 @@ pub struct ApplyPatchArgs {
     pub workdir: Option<String>,
 }
 
+fn shell_supports_apply_patch(shell: &str) -> bool {
+    std::path::Path::new(shell)
+        .file_name()
+        .and_then(|name| name.to_str())
+        .is_some_and(|name| APPLY_PATCH_SHELLS.contains(&name))
+}
+
 pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
     match argv {
         // Direct invocation: apply_patch <patch>
@@ -104,7 +112,7 @@ pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
             Err(e) => MaybeApplyPatch::PatchParseError(e),
         },
         // Bash heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
-        [bash, flag, script] if bash == "bash" && flag == "-lc" => {
+        [shell, flag, script] if shell_supports_apply_patch(shell) && flag == "-lc" => {
             match extract_apply_patch_from_bash(script) {
                 Ok((body, workdir)) => match parse_patch(&body) {
                     Ok(mut source) => {
@@ -224,12 +232,12 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
                 );
             }
         }
-        [bash, flag, script] if bash == "bash" && flag == "-lc" => {
-            if parse_patch(script).is_ok() {
-                return MaybeApplyPatchVerified::CorrectnessError(
-                    ApplyPatchError::ImplicitInvocation,
-                );
-            }
+        [shell, flag, script]
+            if shell_supports_apply_patch(shell)
+                && flag == "-lc"
+                && parse_patch(script).is_ok() =>
+        {
+            return MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation);
         }
         _ => {}
     }
@@ -288,7 +296,7 @@ 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,
                             },
                         );
@@ -1603,6 +1611,53 @@ 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/arg0/src/lib.rs

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

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

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

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

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

codex-rs/chatgpt/Cargo.toml

@@ -14,7 +14,7 @@ codex-core = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
 tokio = { workspace = true, features = ["full"] }
-codex-git-apply = { path = "../git-apply" }
+codex-git = { workspace = true }
 
 [dev-dependencies]
 tempfile = { workspace = true }

codex-rs/chatgpt/src/apply_command.rs

@@ -32,7 +32,8 @@ pub async fn run_apply_command(
     )
     .await?;
 
-    init_chatgpt_token_from_auth(&config.codex_home).await?;
+    init_chatgpt_token_from_auth(&config.codex_home, config.cli_auth_credentials_store_mode)
+        .await?;
 
     let task_response = get_task(&config, apply_cli.task_id).await?;
     apply_diff_from_task(task_response, cwd).await
@@ -58,13 +59,13 @@ pub async fn apply_diff_from_task(
 
 async fn apply_diff(diff: &str, cwd: Option<PathBuf>) -> anyhow::Result<()> {
     let cwd = cwd.unwrap_or(std::env::current_dir().unwrap_or_else(|_| std::env::temp_dir()));
-    let req = codex_git_apply::ApplyGitRequest {
+    let req = codex_git::ApplyGitRequest {
         cwd,
         diff: diff.to_string(),
         revert: false,
         preflight: false,
     };
-    let res = codex_git_apply::apply_git_patch(&req)?;
+    let res = codex_git::apply_git_patch(&req)?;
     if res.exit_code != 0 {
         anyhow::bail!(
             "Git apply failed (applied={}, skipped={}, conflicts={})\nstdout:\n{}\nstderr:\n{}",

codex-rs/chatgpt/src/chatgpt_client.rs

@@ -13,7 +13,8 @@ pub(crate) async fn chatgpt_get_request<T: DeserializeOwned>(
     path: String,
 ) -> anyhow::Result<T> {
     let chatgpt_base_url = &config.chatgpt_base_url;
-    init_chatgpt_token_from_auth(&config.codex_home).await?;
+    init_chatgpt_token_from_auth(&config.codex_home, config.cli_auth_credentials_store_mode)
+        .await?;
 
     // Make direct HTTP request to ChatGPT backend API with the token
     let client = create_client();

codex-rs/chatgpt/src/chatgpt_token.rs

@@ -3,6 +3,7 @@ use std::path::Path;
 use std::sync::LazyLock;
 use std::sync::RwLock;
 
+use codex_core::auth::AuthCredentialsStoreMode;
 use codex_core::token_data::TokenData;
 
 static CHATGPT_TOKEN: LazyLock<RwLock<Option<TokenData>>> = LazyLock::new(|| RwLock::new(None));
@@ -18,8 +19,11 @@ pub fn set_chatgpt_token_data(value: TokenData) {
 }
 
 /// Initialize the ChatGPT token from auth.json file
-pub async fn init_chatgpt_token_from_auth(codex_home: &Path) -> std::io::Result<()> {
-    let auth = CodexAuth::from_codex_home(codex_home)?;
+pub async fn init_chatgpt_token_from_auth(
+    codex_home: &Path,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> std::io::Result<()> {
+    let auth = CodexAuth::from_auth_storage(codex_home, auth_credentials_store_mode)?;
     if let Some(auth) = auth {
         let token_data = auth.get_token_data().await?;
         set_chatgpt_token_data(token_data);

codex-rs/cli/Cargo.toml

@@ -26,19 +26,22 @@ codex-cloud-tasks = { path = "../cloud-tasks" }
 codex-common = { workspace = true, features = ["cli"] }
 codex-core = { workspace = true }
 codex-exec = { workspace = true }
+codex-execpolicy = { workspace = true }
 codex-login = { workspace = true }
 codex-mcp-server = { workspace = true }
 codex-process-hardening = { workspace = true }
 codex-protocol = { workspace = true }
-codex-protocol-ts = { workspace = true }
 codex-responses-api-proxy = { workspace = true }
 codex-rmcp-client = { workspace = true }
 codex-stdio-to-uds = { workspace = true }
 codex-tui = { workspace = true }
 ctor = { workspace = true }
+libc = { workspace = true }
 owo-colors = { workspace = true }
+regex-lite = { workspace = true}
 serde_json = { workspace = true }
 supports-color = { workspace = true }
+toml = { workspace = true }
 tokio = { workspace = true, features = [
     "io-std",
     "macros",
@@ -46,6 +49,10 @@ tokio = { workspace = true, features = [
     "rt-multi-thread",
     "signal",
 ] }
+tracing = { workspace = true }
+
+[target.'cfg(target_os = "windows")'.dependencies]
+codex_windows_sandbox = { package = "codex-windows-sandbox", path = "../windows-sandbox-rs" }
 
 [dev-dependencies]
 assert_cmd = { workspace = true }

codex-rs/cli/src/debug_sandbox.rs

@@ -1,3 +1,8 @@
+#[cfg(target_os = "macos")]
+mod pid_tracker;
+#[cfg(target_os = "macos")]
+mod seatbelt;
+
 use std::path::PathBuf;
 
 use codex_common::CliConfigOverrides;
@@ -5,20 +10,27 @@ use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
 use codex_core::exec_env::create_env;
 use codex_core::landlock::spawn_command_under_linux_sandbox;
+#[cfg(target_os = "macos")]
 use codex_core::seatbelt::spawn_command_under_seatbelt;
 use codex_core::spawn::StdioPolicy;
 use codex_protocol::config_types::SandboxMode;
 
 use crate::LandlockCommand;
 use crate::SeatbeltCommand;
+use crate::WindowsCommand;
 use crate::exit_status::handle_exit_status;
 
+#[cfg(target_os = "macos")]
+use seatbelt::DenialLogger;
+
+#[cfg(target_os = "macos")]
 pub async fn run_command_under_seatbelt(
     command: SeatbeltCommand,
     codex_linux_sandbox_exe: Option<PathBuf>,
 ) -> anyhow::Result<()> {
     let SeatbeltCommand {
         full_auto,
+        log_denials,
         config_overrides,
         command,
     } = command;
@@ -28,10 +40,19 @@ pub async fn run_command_under_seatbelt(
         config_overrides,
         codex_linux_sandbox_exe,
         SandboxType::Seatbelt,
+        log_denials,
     )
     .await
 }
 
+#[cfg(not(target_os = "macos"))]
+pub async fn run_command_under_seatbelt(
+    _command: SeatbeltCommand,
+    _codex_linux_sandbox_exe: Option<PathBuf>,
+) -> anyhow::Result<()> {
+    anyhow::bail!("Seatbelt sandbox is only available on macOS");
+}
+
 pub async fn run_command_under_landlock(
     command: LandlockCommand,
     codex_linux_sandbox_exe: Option<PathBuf>,
@@ -47,13 +68,36 @@ pub async fn run_command_under_landlock(
         config_overrides,
         codex_linux_sandbox_exe,
         SandboxType::Landlock,
+        false,
+    )
+    .await
+}
+
+pub async fn run_command_under_windows(
+    command: WindowsCommand,
+    codex_linux_sandbox_exe: Option<PathBuf>,
+) -> anyhow::Result<()> {
+    let WindowsCommand {
+        full_auto,
+        config_overrides,
+        command,
+    } = command;
+    run_command_under_sandbox(
+        full_auto,
+        command,
+        config_overrides,
+        codex_linux_sandbox_exe,
+        SandboxType::Windows,
+        false,
     )
     .await
 }
 
 enum SandboxType {
+    #[cfg(target_os = "macos")]
     Seatbelt,
     Landlock,
+    Windows,
 }
 
 async fn run_command_under_sandbox(
@@ -62,6 +106,7 @@ async fn run_command_under_sandbox(
     config_overrides: CliConfigOverrides,
     codex_linux_sandbox_exe: Option<PathBuf>,
     sandbox_type: SandboxType,
+    log_denials: bool,
 ) -> anyhow::Result<()> {
     let sandbox_mode = create_sandbox_mode(full_auto);
     let config = Config::load_with_cli_overrides(
@@ -87,7 +132,70 @@ async fn run_command_under_sandbox(
     let stdio_policy = StdioPolicy::Inherit;
     let env = create_env(&config.shell_environment_policy);
 
+    // Special-case Windows sandbox: execute and exit the process to emulate inherited stdio.
+    if let SandboxType::Windows = sandbox_type {
+        #[cfg(target_os = "windows")]
+        {
+            use codex_windows_sandbox::run_windows_sandbox_capture;
+
+            let policy_str = serde_json::to_string(&config.sandbox_policy)?;
+
+            let sandbox_cwd = sandbox_policy_cwd.clone();
+            let cwd_clone = cwd.clone();
+            let env_map = env.clone();
+            let command_vec = command.clone();
+            let base_dir = config.codex_home.clone();
+
+            // Preflight audit is invoked elsewhere at the appropriate times.
+            let res = tokio::task::spawn_blocking(move || {
+                run_windows_sandbox_capture(
+                    policy_str.as_str(),
+                    &sandbox_cwd,
+                    base_dir.as_path(),
+                    command_vec,
+                    &cwd_clone,
+                    env_map,
+                    None,
+                )
+            })
+            .await;
+
+            let capture = match res {
+                Ok(Ok(v)) => v,
+                Ok(Err(err)) => {
+                    eprintln!("windows sandbox failed: {err}");
+                    std::process::exit(1);
+                }
+                Err(join_err) => {
+                    eprintln!("windows sandbox join error: {join_err}");
+                    std::process::exit(1);
+                }
+            };
+
+            if !capture.stdout.is_empty() {
+                use std::io::Write;
+                let _ = std::io::stdout().write_all(&capture.stdout);
+            }
+            if !capture.stderr.is_empty() {
+                use std::io::Write;
+                let _ = std::io::stderr().write_all(&capture.stderr);
+            }
+
+            std::process::exit(capture.exit_code);
+        }
+        #[cfg(not(target_os = "windows"))]
+        {
+            anyhow::bail!("Windows sandbox is only available on Windows");
+        }
+    }
+
+    #[cfg(target_os = "macos")]
+    let mut denial_logger = log_denials.then(DenialLogger::new).flatten();
+    #[cfg(not(target_os = "macos"))]
+    let _ = log_denials;
+
     let mut child = match sandbox_type {
+        #[cfg(target_os = "macos")]
         SandboxType::Seatbelt => {
             spawn_command_under_seatbelt(
                 command,
@@ -115,9 +223,31 @@ async fn run_command_under_sandbox(
             )
             .await?
         }
+        SandboxType::Windows => {
+            unreachable!("Windows sandbox should have been handled above");
+        }
     };
+
+    #[cfg(target_os = "macos")]
+    if let Some(denial_logger) = &mut denial_logger {
+        denial_logger.on_child_spawn(&child);
+    }
+
     let status = child.wait().await?;
 
+    #[cfg(target_os = "macos")]
+    if let Some(denial_logger) = denial_logger {
+        let denials = denial_logger.finish().await;
+        eprintln!("\n=== Sandbox denials ===");
+        if denials.is_empty() {
+            eprintln!("None found.");
+        } else {
+            for seatbelt::SandboxDenial { name, capability } in denials {
+                eprintln!("({name}) {capability}");
+            }
+        }
+    }
+
     handle_exit_status(status);
 }
 

codex-rs/cli/src/debug_sandbox/pid_tracker.rs

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

codex-rs/cli/src/debug_sandbox/seatbelt.rs

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

codex-rs/cli/src/lib.rs

@@ -11,6 +11,10 @@ pub struct SeatbeltCommand {
     #[arg(long = "full-auto", default_value_t = false)]
     pub full_auto: bool,
 
+    /// While the command runs, capture macOS sandbox denials via `log stream` and print them after exit
+    #[arg(long = "log-denials", default_value_t = false)]
+    pub log_denials: bool,
+
     #[clap(skip)]
     pub config_overrides: CliConfigOverrides,
 
@@ -32,3 +36,17 @@ pub struct LandlockCommand {
     #[arg(trailing_var_arg = true)]
     pub command: Vec<String>,
 }
+
+#[derive(Debug, Parser)]
+pub struct WindowsCommand {
+    /// Convenience alias for low-friction sandboxed automatic execution (network-disabled sandbox that can write to cwd and TMPDIR)
+    #[arg(long = "full-auto", default_value_t = false)]
+    pub full_auto: bool,
+
+    #[clap(skip)]
+    pub config_overrides: CliConfigOverrides,
+
+    /// Full command args to run under Windows restricted token sandbox.
+    #[arg(trailing_var_arg = true)]
+    pub command: Vec<String>,
+}

codex-rs/cli/src/login.rs

@@ -1,6 +1,7 @@
 use codex_app_server_protocol::AuthMode;
 use codex_common::CliConfigOverrides;
 use codex_core::CodexAuth;
+use codex_core::auth::AuthCredentialsStoreMode;
 use codex_core::auth::CLIENT_ID;
 use codex_core::auth::login_with_api_key;
 use codex_core::auth::logout;
@@ -17,11 +18,13 @@ use std::path::PathBuf;
 pub async fn login_with_chatgpt(
     codex_home: PathBuf,
     forced_chatgpt_workspace_id: Option<String>,
+    cli_auth_credentials_store_mode: AuthCredentialsStoreMode,
 ) -> std::io::Result<()> {
     let opts = ServerOptions::new(
         codex_home,
         CLIENT_ID.to_string(),
         forced_chatgpt_workspace_id,
+        cli_auth_credentials_store_mode,
     );
     let server = run_login_server(opts)?;
 
@@ -43,7 +46,13 @@ pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) ->
 
     let forced_chatgpt_workspace_id = config.forced_chatgpt_workspace_id.clone();
 
-    match login_with_chatgpt(config.codex_home, forced_chatgpt_workspace_id).await {
+    match login_with_chatgpt(
+        config.codex_home,
+        forced_chatgpt_workspace_id,
+        config.cli_auth_credentials_store_mode,
+    )
+    .await
+    {
         Ok(_) => {
             eprintln!("Successfully logged in");
             std::process::exit(0);
@@ -66,7 +75,11 @@ pub async fn run_login_with_api_key(
         std::process::exit(1);
     }
 
-    match login_with_api_key(&config.codex_home, &api_key) {
+    match login_with_api_key(
+        &config.codex_home,
+        &api_key,
+        config.cli_auth_credentials_store_mode,
+    ) {
         Ok(_) => {
             eprintln!("Successfully logged in");
             std::process::exit(0);
@@ -121,6 +134,7 @@ pub async fn run_login_with_device_code(
         config.codex_home,
         client_id.unwrap_or(CLIENT_ID.to_string()),
         forced_chatgpt_workspace_id,
+        config.cli_auth_credentials_store_mode,
     );
     if let Some(iss) = issuer_base_url {
         opts.issuer = iss;
@@ -140,7 +154,7 @@ pub async fn run_login_with_device_code(
 pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
     let config = load_config_or_exit(cli_config_overrides).await;
 
-    match CodexAuth::from_codex_home(&config.codex_home) {
+    match CodexAuth::from_auth_storage(&config.codex_home, config.cli_auth_credentials_store_mode) {
         Ok(Some(auth)) => match auth.mode {
             AuthMode::ApiKey => match auth.get_token().await {
                 Ok(api_key) => {
@@ -171,7 +185,7 @@ pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
 pub async fn run_logout(cli_config_overrides: CliConfigOverrides) -> ! {
     let config = load_config_or_exit(cli_config_overrides).await;
 
-    match logout(&config.codex_home) {
+    match logout(&config.codex_home, config.cli_auth_credentials_store_mode) {
         Ok(true) => {
             eprintln!("Successfully logged out");
             std::process::exit(0);

codex-rs/cli/src/main.rs

@@ -1,3 +1,4 @@
+use clap::Args;
 use clap::CommandFactory;
 use clap::Parser;
 use clap_complete::Shell;
@@ -7,6 +8,7 @@ use codex_chatgpt::apply_command::ApplyCommand;
 use codex_chatgpt::apply_command::run_apply_command;
 use codex_cli::LandlockCommand;
 use codex_cli::SeatbeltCommand;
+use codex_cli::WindowsCommand;
 use codex_cli::login::read_api_key_from_stdin;
 use codex_cli::login::run_login_status;
 use codex_cli::login::run_login_with_api_key;
@@ -16,19 +18,24 @@ use codex_cli::login::run_logout;
 use codex_cloud_tasks::Cli as CloudTasksCli;
 use codex_common::CliConfigOverrides;
 use codex_exec::Cli as ExecCli;
+use codex_execpolicy::ExecPolicyCheckCommand;
 use codex_responses_api_proxy::Args as ResponsesApiProxyArgs;
 use codex_tui::AppExitInfo;
 use codex_tui::Cli as TuiCli;
-use codex_tui::updates::UpdateAction;
+use codex_tui::update_action::UpdateAction;
 use owo_colors::OwoColorize;
 use std::path::PathBuf;
 use supports_color::Stream;
 
 mod mcp_cmd;
+#[cfg(not(windows))]
+mod wsl_paths;
 
 use crate::mcp_cmd::McpCli;
+
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
+use codex_core::features::is_known_feature_key;
 
 /// Codex CLI
 ///
@@ -77,8 +84,8 @@ enum Subcommand {
     /// [experimental] Run the Codex MCP server (stdio transport).
     McpServer,
 
-    /// [experimental] Run the app server.
-    AppServer,
+    /// [experimental] Run the app server or related tooling.
+    AppServer(AppServerCommand),
 
     /// Generate shell completion scripts.
     Completion(CompletionCommand),
@@ -87,6 +94,10 @@ enum Subcommand {
     #[clap(visible_alias = "debug")]
     Sandbox(SandboxArgs),
 
+    /// Execpolicy tooling.
+    #[clap(hide = true)]
+    Execpolicy(ExecpolicyCommand),
+
     /// Apply the latest diff produced by Codex agent as a `git apply` to your local working tree.
     #[clap(visible_alias = "a")]
     Apply(ApplyCommand),
@@ -94,9 +105,6 @@ enum Subcommand {
     /// Resume a previous interactive session (picker by default; use --last to continue the most recent).
     Resume(ResumeCommand),
 
-    /// Internal: generate TypeScript protocol bindings.
-    #[clap(hide = true)]
-    GenerateTs(GenerateTsCommand),
     /// [EXPERIMENTAL] Browse tasks from Codex Cloud and apply changes locally.
     #[clap(name = "cloud", alias = "cloud-tasks")]
     Cloud(CloudTasksCli),
@@ -131,6 +139,10 @@ struct ResumeCommand {
     #[arg(long = "last", default_value_t = false, conflicts_with = "session_id")]
     last: bool,
 
+    /// Show all sessions (disables cwd filtering and shows CWD column).
+    #[arg(long = "all", default_value_t = false)]
+    all: bool,
+
     #[clap(flatten)]
     config_overrides: TuiCli,
 }
@@ -150,6 +162,22 @@ enum SandboxCommand {
     /// Run a command under Landlock+seccomp (Linux only).
     #[clap(visible_alias = "landlock")]
     Linux(LandlockCommand),
+
+    /// Run a command under Windows restricted token (Windows only).
+    Windows(WindowsCommand),
+}
+
+#[derive(Debug, Parser)]
+struct ExecpolicyCommand {
+    #[command(subcommand)]
+    sub: ExecpolicySubcommand,
+}
+
+#[derive(Debug, clap::Subcommand)]
+enum ExecpolicySubcommand {
+    /// Check execpolicy files against a command.
+    #[clap(name = "check")]
+    Check(ExecPolicyCheckCommand),
 }
 
 #[derive(Debug, Parser)]
@@ -200,6 +228,22 @@ struct LogoutCommand {
 }
 
 #[derive(Debug, Parser)]
+struct AppServerCommand {
+    /// Omit to run the app server; specify a subcommand for tooling.
+    #[command(subcommand)]
+    subcommand: Option<AppServerSubcommand>,
+}
+
+#[derive(Debug, clap::Subcommand)]
+enum AppServerSubcommand {
+    /// [experimental] Generate TypeScript bindings for the app server protocol.
+    GenerateTs(GenerateTsCommand),
+
+    /// [experimental] Generate JSON Schema for the app server protocol.
+    GenerateJsonSchema(GenerateJsonSchemaCommand),
+}
+
+#[derive(Debug, Args)]
 struct GenerateTsCommand {
     /// Output directory where .ts files will be written
     #[arg(short = 'o', long = "out", value_name = "DIR")]
@@ -210,6 +254,13 @@ struct GenerateTsCommand {
     prettier: Option<PathBuf>,
 }
 
+#[derive(Debug, Args)]
+struct GenerateJsonSchemaCommand {
+    /// Output directory where the schema bundle will be written
+    #[arg(short = 'o', long = "out", value_name = "DIR")]
+    out_dir: PathBuf,
+}
+
 #[derive(Debug, Parser)]
 struct StdioToUdsCommand {
     /// Path to the Unix domain socket to connect to.
@@ -262,10 +313,30 @@ fn handle_app_exit(exit_info: AppExitInfo) -> anyhow::Result<()> {
 /// Run the update action and print the result.
 fn run_update_action(action: UpdateAction) -> anyhow::Result<()> {
     println!();
-    let (cmd, args) = action.command_args();
     let cmd_str = action.command_str();
     println!("Updating Codex via `{cmd_str}`...");
-    let status = std::process::Command::new(cmd).args(args).status()?;
+
+    let status = {
+        #[cfg(windows)]
+        {
+            // On Windows, run via cmd.exe so .CMD/.BAT are correctly resolved (PATHEXT semantics).
+            std::process::Command::new("cmd")
+                .args(["/C", &cmd_str])
+                .status()?
+        }
+        #[cfg(not(windows))]
+        {
+            let (cmd, args) = action.command_args();
+            let command_path = crate::wsl_paths::normalize_for_wsl(cmd);
+            let normalized_args: Vec<String> = args
+                .iter()
+                .map(crate::wsl_paths::normalize_for_wsl)
+                .collect();
+            std::process::Command::new(&command_path)
+                .args(&normalized_args)
+                .status()?
+        }
+    };
     if !status.success() {
         anyhow::bail!("`{cmd_str}` failed with status {status}");
     }
@@ -274,6 +345,10 @@ fn run_update_action(action: UpdateAction) -> anyhow::Result<()> {
     Ok(())
 }
 
+fn run_execpolicycheck(cmd: ExecPolicyCheckCommand) -> anyhow::Result<()> {
+    cmd.run()
+}
+
 #[derive(Debug, Default, Parser, Clone)]
 struct FeatureToggles {
     /// Enable a feature (repeatable). Equivalent to `-c features.<name>=true`.
@@ -286,15 +361,25 @@ struct FeatureToggles {
 }
 
 impl FeatureToggles {
-    fn to_overrides(&self) -> Vec<String> {
+    fn to_overrides(&self) -> anyhow::Result<Vec<String>> {
         let mut v = Vec::new();
-        for k in &self.enable {
-            v.push(format!("features.{k}=true"));
+        for feature in &self.enable {
+            Self::validate_feature(feature)?;
+            v.push(format!("features.{feature}=true"));
         }
-        for k in &self.disable {
-            v.push(format!("features.{k}=false"));
+        for feature in &self.disable {
+            Self::validate_feature(feature)?;
+            v.push(format!("features.{feature}=false"));
+        }
+        Ok(v)
+    }
+
+    fn validate_feature(feature: &str) -> anyhow::Result<()> {
+        if is_known_feature_key(feature) {
+            Ok(())
+        } else {
+            anyhow::bail!("Unknown feature flag: {feature}")
         }
-        v
     }
 }
 
@@ -345,9 +430,8 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
     } = MultitoolCli::parse();
 
     // Fold --enable/--disable into config overrides so they flow to all subcommands.
-    root_config_overrides
-        .raw_overrides
-        .extend(feature_toggles.to_overrides());
+    let toggle_overrides = feature_toggles.to_overrides()?;
+    root_config_overrides.raw_overrides.extend(toggle_overrides);
 
     match subcommand {
         None => {
@@ -373,12 +457,24 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
             prepend_config_flags(&mut mcp_cli.config_overrides, root_config_overrides.clone());
             mcp_cli.run().await?;
         }
-        Some(Subcommand::AppServer) => {
-            codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
-        }
+        Some(Subcommand::AppServer(app_server_cli)) => match app_server_cli.subcommand {
+            None => {
+                codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
+            }
+            Some(AppServerSubcommand::GenerateTs(gen_cli)) => {
+                codex_app_server_protocol::generate_ts(
+                    &gen_cli.out_dir,
+                    gen_cli.prettier.as_deref(),
+                )?;
+            }
+            Some(AppServerSubcommand::GenerateJsonSchema(gen_cli)) => {
+                codex_app_server_protocol::generate_json(&gen_cli.out_dir)?;
+            }
+        },
         Some(Subcommand::Resume(ResumeCommand {
             session_id,
             last,
+            all,
             config_overrides,
         })) => {
             interactive = finalize_resume_interactive(
@@ -386,6 +482,7 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
                 root_config_overrides.clone(),
                 session_id,
                 last,
+                all,
                 config_overrides,
             );
             let exit_info = codex_tui::run_main(interactive, codex_linux_sandbox_exe).await?;
@@ -462,6 +559,20 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
                 )
                 .await?;
             }
+            SandboxCommand::Windows(mut windows_cli) => {
+                prepend_config_flags(
+                    &mut windows_cli.config_overrides,
+                    root_config_overrides.clone(),
+                );
+                codex_cli::debug_sandbox::run_command_under_windows(
+                    windows_cli,
+                    codex_linux_sandbox_exe,
+                )
+                .await?;
+            }
+        },
+        Some(Subcommand::Execpolicy(ExecpolicyCommand { sub })) => match sub {
+            ExecpolicySubcommand::Check(cmd) => run_execpolicycheck(cmd)?,
         },
         Some(Subcommand::Apply(mut apply_cli)) => {
             prepend_config_flags(
@@ -479,21 +590,24 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
             tokio::task::spawn_blocking(move || codex_stdio_to_uds::run(socket_path.as_path()))
                 .await??;
         }
-        Some(Subcommand::GenerateTs(gen_cli)) => {
-            codex_protocol_ts::generate_ts(&gen_cli.out_dir, gen_cli.prettier.as_deref())?;
-        }
         Some(Subcommand::Features(FeaturesCli { sub })) => match sub {
             FeaturesSubcommand::List => {
                 // Respect root-level `-c` overrides plus top-level flags like `--profile`.
-                let cli_kv_overrides = root_config_overrides
+                let mut cli_kv_overrides = root_config_overrides
                     .parse_overrides()
-                    .map_err(|e| anyhow::anyhow!(e))?;
+                    .map_err(anyhow::Error::msg)?;
+
+                // Honor `--search` via the new feature toggle.
+                if interactive.web_search {
+                    cli_kv_overrides.push((
+                        "features.web_search_request".to_string(),
+                        toml::Value::Boolean(true),
+                    ));
+                }
 
                 // Thread through relevant top-level flags (at minimum, `--profile`).
-                // Also honor `--search` since it maps to a feature toggle.
                 let overrides = ConfigOverrides {
                     config_profile: interactive.config_profile.clone(),
-                    tools_web_search_request: interactive.web_search.then_some(true),
                     ..Default::default()
                 };
 
@@ -528,6 +642,7 @@ fn finalize_resume_interactive(
     root_config_overrides: CliConfigOverrides,
     session_id: Option<String>,
     last: bool,
+    show_all: bool,
     resume_cli: TuiCli,
 ) -> TuiCli {
     // Start with the parsed interactive CLI so resume shares the same
@@ -536,6 +651,7 @@ fn finalize_resume_interactive(
     interactive.resume_picker = resume_session_id.is_none() && !last;
     interactive.resume_last = last;
     interactive.resume_session_id = resume_session_id;
+    interactive.resume_show_all = show_all;
 
     // Merge resume-scoped flags and overrides with highest precedence.
     merge_resume_cli_flags(&mut interactive, resume_cli);
@@ -605,6 +721,7 @@ mod tests {
     use assert_matches::assert_matches;
     use codex_core::protocol::TokenUsage;
     use codex_protocol::ConversationId;
+    use pretty_assertions::assert_eq;
 
     fn finalize_from_args(args: &[&str]) -> TuiCli {
         let cli = MultitoolCli::try_parse_from(args).expect("parse");
@@ -618,13 +735,21 @@ mod tests {
         let Subcommand::Resume(ResumeCommand {
             session_id,
             last,
+            all,
             config_overrides: resume_cli,
         }) = subcommand.expect("resume present")
         else {
             unreachable!()
         };
 
-        finalize_resume_interactive(interactive, root_overrides, session_id, last, resume_cli)
+        finalize_resume_interactive(
+            interactive,
+            root_overrides,
+            session_id,
+            last,
+            all,
+            resume_cli,
+        )
     }
 
     fn sample_exit_info(conversation: Option<&str>) -> AppExitInfo {
@@ -677,9 +802,9 @@ mod tests {
 
     #[test]
     fn resume_model_flag_applies_when_no_root_flags() {
-        let interactive = finalize_from_args(["codex", "resume", "-m", "gpt-5-test"].as_ref());
+        let interactive = finalize_from_args(["codex", "resume", "-m", "gpt-5.1-test"].as_ref());
 
-        assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
+        assert_eq!(interactive.model.as_deref(), Some("gpt-5.1-test"));
         assert!(interactive.resume_picker);
         assert!(!interactive.resume_last);
         assert_eq!(interactive.resume_session_id, None);
@@ -691,6 +816,7 @@ mod tests {
         assert!(interactive.resume_picker);
         assert!(!interactive.resume_last);
         assert_eq!(interactive.resume_session_id, None);
+        assert!(!interactive.resume_show_all);
     }
 
     #[test]
@@ -699,6 +825,7 @@ mod tests {
         assert!(!interactive.resume_picker);
         assert!(interactive.resume_last);
         assert_eq!(interactive.resume_session_id, None);
+        assert!(!interactive.resume_show_all);
     }
 
     #[test]
@@ -707,6 +834,14 @@ mod tests {
         assert!(!interactive.resume_picker);
         assert!(!interactive.resume_last);
         assert_eq!(interactive.resume_session_id.as_deref(), Some("1234"));
+        assert!(!interactive.resume_show_all);
+    }
+
+    #[test]
+    fn resume_all_flag_sets_show_all() {
+        let interactive = finalize_from_args(["codex", "resume", "--all"].as_ref());
+        assert!(interactive.resume_picker);
+        assert!(interactive.resume_show_all);
     }
 
     #[test]
@@ -724,7 +859,7 @@ mod tests {
                 "--ask-for-approval",
                 "on-request",
                 "-m",
-                "gpt-5-test",
+                "gpt-5.1-test",
                 "-p",
                 "my-profile",
                 "-C",
@@ -735,7 +870,7 @@ mod tests {
             .as_ref(),
         );
 
-        assert_eq!(interactive.model.as_deref(), Some("gpt-5-test"));
+        assert_eq!(interactive.model.as_deref(), Some("gpt-5.1-test"));
         assert!(interactive.oss);
         assert_eq!(interactive.config_profile.as_deref(), Some("my-profile"));
         assert_matches!(
@@ -781,4 +916,32 @@ mod tests {
         assert!(!interactive.resume_last);
         assert_eq!(interactive.resume_session_id, None);
     }
+
+    #[test]
+    fn feature_toggles_known_features_generate_overrides() {
+        let toggles = FeatureToggles {
+            enable: vec!["web_search_request".to_string()],
+            disable: vec!["unified_exec".to_string()],
+        };
+        let overrides = toggles.to_overrides().expect("valid features");
+        assert_eq!(
+            overrides,
+            vec![
+                "features.web_search_request=true".to_string(),
+                "features.unified_exec=false".to_string(),
+            ]
+        );
+    }
+
+    #[test]
+    fn feature_toggles_unknown_feature_errors() {
+        let toggles = FeatureToggles {
+            enable: vec!["does_not_exist".to_string()],
+            disable: Vec::new(),
+        };
+        let err = toggles
+            .to_overrides()
+            .expect_err("feature should be rejected");
+        assert_eq!(err.to_string(), "Unknown feature flag: does_not_exist");
+    }
 }

codex-rs/cli/src/mcp_cmd.rs

@@ -9,11 +9,11 @@ use codex_common::CliConfigOverrides;
 use codex_common::format_env_display::format_env_display;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
+use codex_core::config::edit::ConfigEditsBuilder;
 use codex_core::config::find_codex_home;
 use codex_core::config::load_global_mcp_servers;
-use codex_core::config::write_global_mcp_servers;
-use codex_core::config_types::McpServerConfig;
-use codex_core::config_types::McpServerTransportConfig;
+use codex_core::config::types::McpServerConfig;
+use codex_core::config::types::McpServerTransportConfig;
 use codex_core::features::Feature;
 use codex_core::mcp::auth::compute_auth_statuses;
 use codex_core::protocol::McpAuthStatus;
@@ -79,6 +79,7 @@ pub struct GetArgs {
 }
 
 #[derive(Debug, clap::Parser)]
+#[command(override_usage = "codex mcp add [OPTIONS] <NAME> (--url <URL> | -- <COMMAND>...)")]
 pub struct AddArgs {
     /// Name for the MCP server configuration.
     pub name: String,
@@ -196,7 +197,9 @@ impl McpCli {
 
 async fn run_add(config_overrides: &CliConfigOverrides, add_args: AddArgs) -> Result<()> {
     // Validate any provided overrides even though they are not currently applied.
-    let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
+    let overrides = config_overrides
+        .parse_overrides()
+        .map_err(anyhow::Error::msg)?;
     let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
         .await
         .context("failed to load configuration")?;
@@ -263,7 +266,10 @@ async fn run_add(config_overrides: &CliConfigOverrides, add_args: AddArgs) -> Re
 
     servers.insert(name.clone(), new_entry);
 
-    write_global_mcp_servers(&codex_home, &servers)
+    ConfigEditsBuilder::new(&codex_home)
+        .replace_mcp_servers(&servers)
+        .apply()
+        .await
         .with_context(|| format!("failed to write MCP servers to {}", codex_home.display()))?;
 
     println!("Added global MCP server '{name}'.");
@@ -274,26 +280,42 @@ async fn run_add(config_overrides: &CliConfigOverrides, add_args: AddArgs) -> Re
         http_headers,
         env_http_headers,
     } = transport
-        && matches!(supports_oauth_login(&url).await, Ok(true))
     {
-        println!("Detected OAuth support. Starting OAuth flow…");
-        perform_oauth_login(
-            &name,
-            &url,
-            config.mcp_oauth_credentials_store_mode,
-            http_headers.clone(),
-            env_http_headers.clone(),
-            &Vec::new(),
-        )
-        .await?;
-        println!("Successfully logged in.");
+        match supports_oauth_login(&url).await {
+            Ok(true) => {
+                if !config.features.enabled(Feature::RmcpClient) {
+                    println!(
+                        "MCP server supports login. Add `experimental_use_rmcp_client = true` \
+                         to your config.toml and run `codex mcp login {name}` to login."
+                    );
+                } else {
+                    println!("Detected OAuth support. Starting OAuth flow…");
+                    perform_oauth_login(
+                        &name,
+                        &url,
+                        config.mcp_oauth_credentials_store_mode,
+                        http_headers.clone(),
+                        env_http_headers.clone(),
+                        &Vec::new(),
+                    )
+                    .await?;
+                    println!("Successfully logged in.");
+                }
+            }
+            Ok(false) => {}
+            Err(_) => println!(
+                "MCP server may or may not require login. Run `codex mcp login {name}` to login."
+            ),
+        }
     }
 
     Ok(())
 }
 
 async fn run_remove(config_overrides: &CliConfigOverrides, remove_args: RemoveArgs) -> Result<()> {
-    config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
+    config_overrides
+        .parse_overrides()
+        .map_err(anyhow::Error::msg)?;
 
     let RemoveArgs { name } = remove_args;
 
@@ -307,7 +329,10 @@ async fn run_remove(config_overrides: &CliConfigOverrides, remove_args: RemoveAr
     let removed = servers.remove(&name).is_some();
 
     if removed {
-        write_global_mcp_servers(&codex_home, &servers)
+        ConfigEditsBuilder::new(&codex_home)
+            .replace_mcp_servers(&servers)
+            .apply()
+            .await
             .with_context(|| format!("failed to write MCP servers to {}", codex_home.display()))?;
     }
 
@@ -321,14 +346,16 @@ async fn run_remove(config_overrides: &CliConfigOverrides, remove_args: RemoveAr
 }
 
 async fn run_login(config_overrides: &CliConfigOverrides, login_args: LoginArgs) -> Result<()> {
-    let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
+    let overrides = config_overrides
+        .parse_overrides()
+        .map_err(anyhow::Error::msg)?;
     let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
         .await
         .context("failed to load configuration")?;
 
     if !config.features.enabled(Feature::RmcpClient) {
         bail!(
-            "OAuth login is only supported when experimental_use_rmcp_client is true in config.toml."
+            "OAuth login is only supported when [features].rmcp_client is true in config.toml. See https://github.com/openai/codex/blob/main/docs/config.md#feature-flags for details."
         );
     }
 
@@ -362,7 +389,9 @@ async fn run_login(config_overrides: &CliConfigOverrides, login_args: LoginArgs)
 }
 
 async fn run_logout(config_overrides: &CliConfigOverrides, logout_args: LogoutArgs) -> Result<()> {
-    let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
+    let overrides = config_overrides
+        .parse_overrides()
+        .map_err(anyhow::Error::msg)?;
     let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
         .await
         .context("failed to load configuration")?;
@@ -389,7 +418,9 @@ async fn run_logout(config_overrides: &CliConfigOverrides, logout_args: LogoutAr
 }
 
 async fn run_list(config_overrides: &CliConfigOverrides, list_args: ListArgs) -> Result<()> {
-    let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
+    let overrides = config_overrides
+        .parse_overrides()
+        .map_err(anyhow::Error::msg)?;
     let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
         .await
         .context("failed to load configuration")?;
@@ -523,10 +554,12 @@ async fn run_list(config_overrides: &CliConfigOverrides, list_args: ListArgs) ->
                     .map(|entry| entry.auth_status)
                     .unwrap_or(McpAuthStatus::Unsupported)
                     .to_string();
+                let bearer_token_display =
+                    bearer_token_env_var.as_deref().unwrap_or("-").to_string();
                 http_rows.push([
                     name.clone(),
                     url.clone(),
-                    bearer_token_env_var.clone().unwrap_or("-".to_string()),
+                    bearer_token_display,
                     status,
                     auth_status,
                 ]);
@@ -642,7 +675,9 @@ async fn run_list(config_overrides: &CliConfigOverrides, list_args: ListArgs) ->
 }
 
 async fn run_get(config_overrides: &CliConfigOverrides, get_args: GetArgs) -> Result<()> {
-    let overrides = config_overrides.parse_overrides().map_err(|e| anyhow!(e))?;
+    let overrides = config_overrides
+        .parse_overrides()
+        .map_err(anyhow::Error::msg)?;
     let config = Config::load_with_cli_overrides(overrides, ConfigOverrides::default())
         .await
         .context("failed to load configuration")?;
@@ -752,15 +787,15 @@ async fn run_get(config_overrides: &CliConfigOverrides, get_args: GetArgs) -> Re
         } => {
             println!("  transport: streamable_http");
             println!("  url: {url}");
-            let env_var = bearer_token_env_var.as_deref().unwrap_or("-");
-            println!("  bearer_token_env_var: {env_var}");
+            let bearer_token_display = bearer_token_env_var.as_deref().unwrap_or("-");
+            println!("  bearer_token_env_var: {bearer_token_display}");
             let headers_display = match http_headers {
                 Some(map) if !map.is_empty() => {
                     let mut pairs: Vec<_> = map.iter().collect();
                     pairs.sort_by(|(a, _), (b, _)| a.cmp(b));
                     pairs
                         .into_iter()
-                        .map(|(k, v)| format!("{k}={v}"))
+                        .map(|(k, _)| format!("{k}=*****"))
                         .collect::<Vec<_>>()
                         .join(", ")
                 }
@@ -773,7 +808,7 @@ async fn run_get(config_overrides: &CliConfigOverrides, get_args: GetArgs) -> Re
                     pairs.sort_by(|(a, _), (b, _)| a.cmp(b));
                     pairs
                         .into_iter()
-                        .map(|(k, v)| format!("{k}={v}"))
+                        .map(|(k, var)| format!("{k}={var}"))
                         .collect::<Vec<_>>()
                         .join(", ")
                 }

codex-rs/cli/src/wsl_paths.rs

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

codex-rs/cli/tests/execpolicy.rs

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

codex-rs/cli/tests/mcp_add_remove.rs

@@ -2,7 +2,7 @@ use std::path::Path;
 
 use anyhow::Result;
 use codex_core::config::load_global_mcp_servers;
-use codex_core::config_types::McpServerTransportConfig;
+use codex_core::config::types::McpServerTransportConfig;
 use predicates::str::contains;
 use pretty_assertions::assert_eq;
 use tempfile::TempDir;

codex-rs/cli/tests/mcp_list.rs

@@ -1,9 +1,9 @@
 use std::path::Path;
 
 use anyhow::Result;
+use codex_core::config::edit::ConfigEditsBuilder;
 use codex_core::config::load_global_mcp_servers;
-use codex_core::config::write_global_mcp_servers;
-use codex_core::config_types::McpServerTransportConfig;
+use codex_core::config::types::McpServerTransportConfig;
 use predicates::prelude::PredicateBooleanExt;
 use predicates::str::contains;
 use pretty_assertions::assert_eq;
@@ -59,7 +59,9 @@ async fn list_and_get_render_expected_output() -> Result<()> {
         }
         other => panic!("unexpected transport: {other:?}"),
     }
-    write_global_mcp_servers(codex_home.path(), &servers)?;
+    ConfigEditsBuilder::new(codex_home.path())
+        .replace_mcp_servers(&servers)
+        .apply_blocking()?;
 
     let mut list_cmd = codex_command(codex_home.path())?;
     let list_output = list_cmd.args(["mcp", "list"]).output()?;
@@ -68,9 +70,9 @@ async fn list_and_get_render_expected_output() -> Result<()> {
     assert!(stdout.contains("Name"));
     assert!(stdout.contains("docs"));
     assert!(stdout.contains("docs-server"));
-    assert!(stdout.contains("TOKEN=secret"));
-    assert!(stdout.contains("APP_TOKEN=$APP_TOKEN"));
-    assert!(stdout.contains("WORKSPACE_ID=$WORKSPACE_ID"));
+    assert!(stdout.contains("TOKEN=*****"));
+    assert!(stdout.contains("APP_TOKEN=*****"));
+    assert!(stdout.contains("WORKSPACE_ID=*****"));
     assert!(stdout.contains("Status"));
     assert!(stdout.contains("Auth"));
     assert!(stdout.contains("enabled"));
@@ -119,9 +121,9 @@ async fn list_and_get_render_expected_output() -> Result<()> {
     assert!(stdout.contains("transport: stdio"));
     assert!(stdout.contains("command: docs-server"));
     assert!(stdout.contains("args: --port 4000"));
-    assert!(stdout.contains("env: TOKEN=secret"));
-    assert!(stdout.contains("APP_TOKEN=$APP_TOKEN"));
-    assert!(stdout.contains("WORKSPACE_ID=$WORKSPACE_ID"));
+    assert!(stdout.contains("env: TOKEN=*****"));
+    assert!(stdout.contains("APP_TOKEN=*****"));
+    assert!(stdout.contains("WORKSPACE_ID=*****"));
     assert!(stdout.contains("enabled: true"));
     assert!(stdout.contains("remove: codex mcp remove docs"));
 
@@ -149,7 +151,9 @@ async fn get_disabled_server_shows_single_line() -> Result<()> {
         .get_mut("docs")
         .expect("docs server should exist after add");
     docs.enabled = false;
-    write_global_mcp_servers(codex_home.path(), &servers)?;
+    ConfigEditsBuilder::new(codex_home.path())
+        .replace_mcp_servers(&servers)
+        .apply_blocking()?;
 
     let mut get_cmd = codex_command(codex_home.path())?;
     let get_output = get_cmd.args(["mcp", "get", "docs"]).output()?;

codex-rs/cloud-tasks-client/Cargo.toml

@@ -22,6 +22,6 @@ chrono = { version = "0.4", features = ["serde"] }
 diffy = "0.4.2"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
-thiserror = "2.0.12"
+thiserror = "2.0.17"
 codex-backend-client = { path = "../backend-client", optional = true }
-codex-git-apply = { path = "../git-apply" }
+codex-git = { workspace = true }

codex-rs/cloud-tasks-client/src/http.rs

@@ -362,13 +362,13 @@ mod api {
                 });
             }
 
-            let req = codex_git_apply::ApplyGitRequest {
+            let req = codex_git::ApplyGitRequest {
                 cwd: std::env::current_dir().unwrap_or_else(|_| std::env::temp_dir()),
                 diff: diff.clone(),
                 revert: false,
                 preflight,
             };
-            let r = codex_git_apply::apply_git_patch(&req)
+            let r = codex_git::apply_git_patch(&req)
                 .map_err(|e| CloudTaskError::Io(format!("git apply failed to run: {e}")))?;
 
             let status = if r.exit_code == 0 {

codex-rs/cloud-tasks-client/src/lib.rs

@@ -26,4 +26,4 @@ pub use mock::MockClient;
 #[cfg(feature = "online")]
 pub use http::HttpClient;
 
-// Reusable apply engine now lives in the shared crate `codex-git-apply`.
+// Reusable apply engine now lives in the shared crate `codex-git`.

codex-rs/cloud-tasks/src/lib.rs

@@ -8,6 +8,7 @@ pub mod util;
 pub use cli::Cli;
 
 use anyhow::anyhow;
+use codex_login::AuthManager;
 use std::io::IsTerminal;
 use std::io::Read;
 use std::path::PathBuf;
@@ -56,11 +57,8 @@ async fn init_backend(user_agent_suffix: &str) -> anyhow::Result<BackendContext>
     };
     append_error_log(format!("startup: base_url={base_url} path_style={style}"));
 
-    let auth = match codex_core::config::find_codex_home()
-        .ok()
-        .map(|home| codex_login::AuthManager::new(home, false))
-        .and_then(|am| am.auth())
-    {
+    let auth_manager = util::load_auth_manager().await;
+    let auth = match auth_manager.as_ref().and_then(AuthManager::auth) {
         Some(auth) => auth,
         None => {
             eprintln!(
@@ -1035,7 +1033,7 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
                             // Close task modal/pending apply if present before opening env modal
                             app.diff_overlay = None;
                             app.env_modal = Some(app::EnvModalState { query: String::new(), selected: 0 });
-                            // Cache environments until user explicitly refreshes with 'r' inside the modal.
+                            // Cache environments while the modal is open to avoid repeated fetches.
                             let should_fetch = app.environments.is_empty();
                             if should_fetch {
                                 app.env_loading = true;
@@ -1086,7 +1084,19 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
                                                 let backend = Arc::clone(&backend);
                                                 let best_of_n = page.best_of_n;
                                                 tokio::spawn(async move {
-                                                    let result = codex_cloud_tasks_client::CloudBackend::create_task(&*backend, &env, &text, "main", false, best_of_n).await;
+                                                    let git_ref = if let Ok(cwd) = std::env::current_dir() {
+                                                        if let Some(branch) = codex_core::git_info::default_branch_name(&cwd).await {
+                                                            branch
+                                                        } else if let Some(branch) = codex_core::git_info::current_branch_name(&cwd).await {
+                                                            branch
+                                                        } else {
+                                                            "main".to_string()
+                                                        }
+                                                    } else {
+                                                        "main".to_string()
+                                                    };
+
+                                                    let result = codex_cloud_tasks_client::CloudBackend::create_task(&*backend, &env, &text, &git_ref, false, best_of_n).await;
                                                     let evt = match result {
                                                         Ok(ok) => app::AppEvent::NewTaskSubmitted(Ok(ok)),
                                                         Err(e) => app::AppEvent::NewTaskSubmitted(Err(format!("{e}"))),
@@ -1094,7 +1104,7 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
                                                     let _ = tx.send(evt);
                                                 });
                                             } else {
-                                                app.status = "No environment selected (press 'e' to choose)".to_string();
+                                                app.status = "No environment selected".to_string();
                                             }
                                     }
                                     needs_redraw = true;
@@ -1292,18 +1302,6 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
                             // Environment modal key handling
                             match key.code {
                                 KeyCode::Esc => { app.env_modal = None; needs_redraw = true; }
-                                KeyCode::Char('r') | KeyCode::Char('R') => {
-                                    // Trigger refresh of environments
-                                    app.env_loading = true; app.env_error = None; needs_redraw = true;
-                                    let _ = frame_tx.send(Instant::now() + Duration::from_millis(100));
-                                    let tx = tx.clone();
-                                    tokio::spawn(async move {
-            let base_url = crate::util::normalize_base_url(&std::env::var("CODEX_CLOUD_TASKS_BASE_URL").unwrap_or_else(|_| "https://chatgpt.com/backend-api".to_string()));
-            let headers = crate::util::build_chatgpt_headers().await;
-                                        let res = crate::env_detect::list_environments(&base_url, &headers).await;
-                                        let _ = tx.send(app::AppEvent::EnvironmentsLoaded(res));
-                                    });
-                                }
                                 KeyCode::Char(ch) if !key.modifiers.contains(KeyModifiers::CONTROL) && !key.modifiers.contains(KeyModifiers::ALT) => {
                                     if let Some(m) = app.env_modal.as_mut() { m.query.push(ch); }
                                     needs_redraw = true;
@@ -1410,7 +1408,7 @@ pub async fn run_main(cli: Cli, _codex_linux_sandbox_exe: Option<PathBuf>) -> an
                                 }
                                 KeyCode::Char('o') | KeyCode::Char('O') => {
                                     app.env_modal = Some(app::EnvModalState { query: String::new(), selected: 0 });
-                                    // Cache environments until user explicitly refreshes with 'r' inside the modal.
+                                    // Cache environments while the modal is open to avoid repeated fetches.
                                     let should_fetch = app.environments.is_empty();
                                     if should_fetch { app.env_loading = true; app.env_error = None; }
                                     needs_redraw = true;
@@ -1723,6 +1721,7 @@ mod tests {
     use ratatui::layout::Rect;
 
     #[test]
+    #[ignore = "very slow"]
     fn composer_input_renders_typed_characters() {
         let mut composer = ComposerInput::new();
         let key = KeyEvent::new(KeyCode::Char('a'), KeyModifiers::NONE);