clean up types

A partner is consuming our generated JSON schema bundle for app-server
and identified a few issues:
- not all polymorphic / one-of types have a type descriminator
- `"$ref": "#/definitions/v2/SandboxPolicy"` is missing
- "Option<>" is an invalid schema name, and also unnecessary

This PR:
- adds the type descriminator to the various types that are missing it
except for `SessionSource` and `SubAgentSource` because they are
serialized to disk (adding this would break backwards compat for
resume), and they should not be necessary to consume for an integration
with app-server.
- removes the special handling in `export.rs` of various types like
SandboxPolicy, which turned out to be unnecessary and incorrect
- filters out `Option<>` which was auto-generated for request params
that don't need a body

For context, we currently pull in wayyy more types than we need through
the `EventMsg` god object which we are **not** planning to expose in API
v2 (this is how I suspect `SessionSource` and `SubAgentSource` are being
pulled in). But until we have all the necessary v2 notifications in
place that will allow us to remove `EventMsg`, we will keep exporting it
for now.

.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

@@ -16,10 +16,27 @@ jobs:
     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:

.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@v7
+        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:
@@ -87,7 +87,7 @@ 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.
+      RUSTC_WRAPPER: sccache
+      CARGO_INCREMENTAL: "0"
+      SCCACHE_CACHE_SIZE: 10G
 
     strategy:
       fail-fast: false
@@ -159,20 +164,83 @@ 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: ${{ !(matrix.target == 'x86_64-unknown-linux-gnu' && matrix.profile != 'release') }}
+      # Install and restore sccache cache
+      - name: Install sccache
+        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        with:
+          tool: sccache
+          version: 0.7.5
+
+      - name: Configure sccache backend
+        shell: bash
+        run: |
+          set -euo pipefail
+          if [[ -n "${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: Restore sccache cache (fallback)
+        if: ${{ 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 +259,6 @@ 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 ${{ matrix.target }} --cargo-profile ci-test
-        env:
-          RUST_BACKTRACE: 1
-
       # Save caches explicitly; make non-fatal so cache packaging
       # never fails the overall job. Only save when key wasn't hit.
       - name: Save cargo home cache
@@ -217,33 +271,193 @@ jobs:
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
-          key: cargo-home-${{ 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.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()
+        continue-on-error: true
+        run: sccache --show-stats || true
+
+      - name: sccache summary
+        if: always()
+        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:
+      RUSTC_WRAPPER: sccache
+      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 }}-${{ matrix.profile }}-
+
+      - name: Install sccache
+        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        with:
+          tool: sccache
+          version: 0.7.5
+
+      - name: Configure sccache backend
+        shell: bash
+        run: |
+          set -euo pipefail
+          if [[ -n "${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: Restore sccache cache (fallback)
+        if: ${{ 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.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()
+        continue-on-error: true
+        run: sccache --show-stats || true
+
+      - name: sccache summary
+        if: always()
+        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 +466,8 @@ 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 +479,10 @@ 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

AGENTS.md

@@ -84,6 +84,7 @@ 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`.
 
 - 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>
 
@@ -73,11 +75,13 @@ Codex CLI supports a rich set of configuration options, with preferences stored
 
 - [**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/Cargo.toml

@@ -16,8 +16,8 @@ members = [
     "core",
     "exec",
     "execpolicy",
+    "keyring-store",
     "file-search",
-    "git-tooling",
     "linux-sandbox",
     "login",
     "mcp-server",
@@ -25,16 +25,17 @@ members = [
     "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",
 ]
@@ -64,7 +65,8 @@ codex-core = { path = "core" }
 codex-exec = { path = "exec" }
 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-login = { path = "login" }
 codex-mcp-server = { path = "mcp-server" }
@@ -72,16 +74,18 @@ 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 +94,8 @@ 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"
@@ -116,11 +120,13 @@ env_logger = "0.11.5"
 escargot = "0.5"
 eventsource-stream = "0.2.3"
 futures = { version = "0.3", default-features = false }
-icu_decimal = "2.0.0"
-icu_locale_core = "2.0.0"
+http = "1.3.1"
+icu_decimal = "2.1"
+icu_locale_core = "2.1"
+icu_provider = { version = "2.1", features = ["sync"] }
 ignore = "0.4.23"
 image = { version = "^0.25.8", default-features = false }
-indexmap = "2.6.0"
+indexmap = "2.12.0"
 insta = "1.43.2"
 itertools = "0.14.0"
 keyring = "3.6"
@@ -128,11 +134,13 @@ 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 +149,6 @@ 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"
@@ -153,7 +160,7 @@ ratatui = "0.29.0"
 ratatui-macros = "0.6.0"
 regex-lite = "0.1.7"
 reqwest = "0.12"
-rmcp = { version = "0.8.2", default-features = false }
+rmcp = { version = "0.8.5", default-features = false }
 schemars = "0.8.22"
 seccompiler = "0.5.0"
 sentry = "0.34.0"
@@ -173,7 +180,7 @@ 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 +209,9 @@ 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 +254,12 @@ 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",
+    "codex-utils-tokenizer",
+]
 
 [profile.release]
 lto = "fat"
@@ -265,6 +278,7 @@ 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

@@ -14,7 +14,7 @@ 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 }

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;
@@ -27,83 +32,29 @@ 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)?;
@@ -111,7 +62,9 @@ pub fn generate_types(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
 }
 
 pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> 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)?;
@@ -122,17 +75,22 @@ pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
     ServerNotification::export_all_to(out_dir)?;
 
     generate_index_ts(out_dir)?;
+    generate_index_ts(&v2_out_dir)?;
 
-    let ts_files = ts_files_in(out_dir)?;
+    // Ensure our header is present on all TS files (root + subdirs like v2/).
+    let ts_files = ts_files_in_recursive(out_dir)?;
     for file in &ts_files {
         prepend_header_if_missing(file)?;
     }
 
+    // Optionally run Prettier on all generated TS files.
     if let Some(prettier_bin) = prettier
         && !ts_files.is_empty()
     {
         let status = Command::new(prettier_bin)
             .arg("--write")
+            .arg("--log-level")
+            .arg("warn")
             .args(ts_files.iter().map(|p| p.as_os_str()))
             .status()
             .with_context(|| format!("Failed to invoke Prettier at {}", prettier_bin.display()))?;
@@ -146,59 +104,115 @@ 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 +227,66 @@ 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 +295,73 @@ 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 +383,6 @@ 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 +403,147 @@ 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 +573,33 @@ 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 +637,28 @@ 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 +675,14 @@ 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 +697,205 @@ 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());
+
+        generate_ts(&output_dir, None)?;
+
+        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 +6,6 @@ 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::v1::*;
+pub use protocol::v2::*;

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

@@ -0,0 +1,789 @@
+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,
+    },
+
+    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, Self::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
+    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),
+
+    #[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-codex".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-codex",
+                    "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 +1,6 @@
+// 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 v1;
+pub mod v2;

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/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"] }
@@ -47,6 +48,7 @@ base64 = { workspace = true }
 core_test_support = { workspace = true }
 os_info = { workspace = true }
 pretty_assertions = { workspace = true }
+serial_test = { workspace = true }
 tempfile = { workspace = true }
 toml = { workspace = true }
 wiremock = { workspace = true }

codex-rs/app-server/README.md

@@ -1,6 +1,6 @@
 # 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.
 
 ## Protocol
 
@@ -8,8 +8,253 @@ 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
 ```
+
+## 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"`.
+
+### 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-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-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.
+
+## 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.

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

@@ -46,6 +46,7 @@ pub(crate) async fn run_fuzzy_file_search(
                 threads,
                 cancel_flag,
                 COMPUTE_INDICES,
+                true,
             ) {
                 Ok(res) => Ok((root, res)),
                 Err(err) => Err((root, err)),

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

@@ -12,16 +12,19 @@ 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;
 
@@ -82,6 +85,8 @@ 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 +101,15 @@ 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 +124,7 @@ 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

@@ -17,6 +17,7 @@ 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 +34,14 @@ 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 +52,7 @@ impl MessageProcessor {
             outgoing.clone(),
             codex_linux_sandbox_exe,
             config,
+            feedback,
         );
 
         Self {
@@ -57,64 +64,79 @@ 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

@@ -141,7 +141,13 @@ pub(crate) struct OutgoingError {
 
 #[cfg(test)]
 mod tests {
+    use codex_app_server_protocol::AccountLoginCompletedNotification;
+    use codex_app_server_protocol::AccountRateLimitsUpdatedNotification;
+    use codex_app_server_protocol::AccountUpdatedNotification;
+    use codex_app_server_protocol::AuthMode;
     use codex_app_server_protocol::LoginChatGptCompleteNotification;
+    use codex_app_server_protocol::RateLimitSnapshot;
+    use codex_app_server_protocol::RateLimitWindow;
     use pretty_assertions::assert_eq;
     use serde_json::json;
     use uuid::Uuid;
@@ -164,6 +170,7 @@ mod tests {
                 "params": {
                     "loginId": Uuid::nil(),
                     "success": true,
+                    "error": null,
                 },
             }),
             serde_json::to_value(jsonrpc_notification)
@@ -171,4 +178,84 @@ mod tests {
             "ensure the strum macros serialize the method field correctly"
         );
     }
+
+    #[test]
+    fn verify_account_login_completed_notification_serialization() {
+        let notification =
+            ServerNotification::AccountLoginCompleted(AccountLoginCompletedNotification {
+                login_id: Some(Uuid::nil().to_string()),
+                success: true,
+                error: None,
+            });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!({
+                "method": "account/login/completed",
+                "params": {
+                    "loginId": Uuid::nil().to_string(),
+                    "success": true,
+                    "error": null,
+                },
+            }),
+            serde_json::to_value(jsonrpc_notification)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
+
+    #[test]
+    fn verify_account_rate_limits_notification_serialization() {
+        let notification =
+            ServerNotification::AccountRateLimitsUpdated(AccountRateLimitsUpdatedNotification {
+                rate_limits: RateLimitSnapshot {
+                    primary: Some(RateLimitWindow {
+                        used_percent: 25,
+                        window_duration_mins: Some(15),
+                        resets_at: Some(123),
+                    }),
+                    secondary: None,
+                },
+            });
+
+        let jsonrpc_notification = OutgoingMessage::AppServerNotification(notification);
+        assert_eq!(
+            json!({
+                "method": "account/rateLimits/updated",
+                "params": {
+                    "rateLimits": {
+                        "primary": {
+                            "usedPercent": 25,
+                            "windowDurationMins": 15,
+                            "resetsAt": 123
+                        },
+                        "secondary": 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)
+                .expect("ensure the notification serializes correctly"),
+            "ensure the notification serializes correctly"
+        );
+    }
 }

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 +22,5 @@ tokio = { workspace = true, features = [
     "process",
     "rt-multi-thread",
 ] }
+uuid = { workspace = true }
 wiremock = { 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

@@ -2,6 +2,7 @@ mod auth_fixtures;
 mod mcp_process;
 mod mock_model_server;
 mod responses;
+mod rollout;
 
 pub use auth_fixtures::ChatGptAuthFixture;
 pub use auth_fixtures::ChatGptIdTokenClaims;
@@ -10,9 +11,11 @@ pub use auth_fixtures::write_chatgpt_auth;
 use codex_app_server_protocol::JSONRPCResponse;
 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 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 +14,37 @@ 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::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 +250,24 @@ 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 +291,46 @@ 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 +359,24 @@ 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 `cancelLoginChatGpt` JSON-RPC request.
     pub async fn send_cancel_login_chat_gpt_request(
         &mut self,
@@ -311,6 +391,40 @@ 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/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

@@ -1,5 +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;
@@ -32,26 +31,27 @@ 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.
@@ -61,20 +61,15 @@ async fn test_codex_jsonrpc_conversation_flow() {
             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 +77,13 @@ 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 +94,18 @@ 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 +115,13 @@ 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 +129,7 @@ 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")
@@ -163,33 +147,31 @@ 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![
@@ -202,10 +184,8 @@ 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_final_assistant_message_sse_response("done 1")?,
         create_shell_sse_response(
             vec![
                 "python3".to_string(),
@@ -215,20 +195,15 @@ 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 +211,30 @@ 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 +244,21 @@ 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:?}");
     };
@@ -311,6 +274,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
             ],
             cwd: working_directory.clone(),
             reason: None,
+            risk: None,
             parsed_cmd: vec![ParsedCommand::Unknown {
                 cmd: "python3 -c 'print(42)'".to_string()
             }],
@@ -323,17 +287,14 @@ 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 +310,15 @@ 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.
@@ -369,31 +326,31 @@ 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(
@@ -405,10 +362,8 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
             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_final_assistant_message_sse_response("done first")?,
         create_shell_sse_response(
             vec![
                 "bash".to_string(),
@@ -418,21 +373,14 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
             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 +389,29 @@ 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 +431,17 @@ 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 +456,18 @@ 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()
@@ -561,9 +495,9 @@ 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;
 
@@ -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),
@@ -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

@@ -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

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 +1,9 @@
+mod account;
+mod model_list;
+mod rate_limits;
+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 +39,17 @@ 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".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,
@@ -66,15 +69,30 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
             is_default: true,
         },
         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 +121,7 @@ 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 +129,8 @@ 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 +141,18 @@ 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");
     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 +163,40 @@ 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-mini");
+    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");
+    assert!(third_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 +204,8 @@ 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")
@@ -147,40 +127,29 @@ 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),
             }),
         },
@@ -195,16 +164,13 @@ 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/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 +1,181 @@
+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::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+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_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-codex".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    // 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_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-codex".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    let 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-codex".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    let 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 } =
+        to_response::<ThreadResumeResponse>(resume_resp)?;
+    assert!(!resumed.id.is_empty());
+    assert_eq!(resumed.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 +1,90 @@
+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".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 } = 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!(thread.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 +1,128 @@
+#![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_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+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::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_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)?;
+
+    // No fields to assert on; successful deserialization confirms proper response shape.
+    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 +1,491 @@
+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_mock_chat_completions_server_unchecked;
+use app_test_support::create_shell_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::CommandExecutionStatus;
+use codex_app_server_protocol::ItemStartedNotification;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::ParsedCommand;
+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::TurnStartParams;
+use codex_app_server_protocol::TurnStartResponse;
+use codex_app_server_protocol::TurnStartedNotification;
+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??;
+
+    // And we should ultimately get a task_complete without having to add a
+    // legacy conversation listener explicitly (auto-attached by thread/start).
+    let _task_complete: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    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_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_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");
+    assert_eq!(
+        params.metadata.parsed_cmd,
+        vec![ParsedCommand::Unknown {
+            cmd: "python3 -c 'print(42)'".to_string(),
+        }]
+    );
+
+    // 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??;
+
+    // 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??;
+
+    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_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo first turn".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call-first",
+        )?,
+        create_final_assistant_message_sse_response("done first")?,
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo second 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);
+    assert_eq!(command, "bash -lc echo second turn");
+    assert_eq!(status, CommandExecutionStatus::InProgress);
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    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

@@ -288,7 +288,7 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
                             path,
                             ApplyPatchFileChange::Update {
                                 unified_diff,
-                                move_path: move_path.map(|p| cwd.join(p)),
+                                move_path: move_path.map(|p| effective_cwd.join(p)),
                                 new_content: contents,
                             },
                         );
@@ -1603,6 +1603,53 @@ g
         );
     }
 
+    #[test]
+    fn test_apply_patch_resolves_move_path_with_effective_cwd() {
+        let session_dir = tempdir().unwrap();
+        let worktree_rel = "alt";
+        let worktree_dir = session_dir.path().join(worktree_rel);
+        fs::create_dir_all(&worktree_dir).unwrap();
+
+        let source_name = "old.txt";
+        let dest_name = "renamed.txt";
+        let source_path = worktree_dir.join(source_name);
+        fs::write(&source_path, "before\n").unwrap();
+
+        let patch = wrap_patch(&format!(
+            r#"*** Update File: {source_name}
+*** Move to: {dest_name}
+@@
+-before
++after"#
+        ));
+
+        let shell_script = format!("cd {worktree_rel} && apply_patch <<'PATCH'\n{patch}\nPATCH");
+        let argv = vec!["bash".into(), "-lc".into(), shell_script];
+
+        let result = maybe_parse_apply_patch_verified(&argv, session_dir.path());
+        let action = match result {
+            MaybeApplyPatchVerified::Body(action) => action,
+            other => panic!("expected verified body, got {other:?}"),
+        };
+
+        assert_eq!(action.cwd, worktree_dir);
+
+        let change = action
+            .changes()
+            .get(&worktree_dir.join(source_name))
+            .expect("source file change present");
+
+        match change {
+            ApplyPatchFileChange::Update { move_path, .. } => {
+                assert_eq!(
+                    move_path.as_deref(),
+                    Some(worktree_dir.join(dest_name).as_path())
+                );
+            }
+            other => panic!("expected update change, got {other:?}"),
+        }
+    }
+
     #[test]
     fn test_apply_patch_fails_on_write_error() {
         let dir = tempdir().unwrap();

codex-rs/apply-patch/tests/suite/mod.rs

@@ -1 +1,3 @@
 mod cli;
+#[cfg(not(target_os = "windows"))]
+mod tool;

codex-rs/apply-patch/tests/suite/tool.rs

@@ -0,0 +1,257 @@
+use assert_cmd::Command;
+use pretty_assertions::assert_eq;
+use std::fs;
+use std::path::Path;
+use tempfile::tempdir;
+
+fn run_apply_patch_in_dir(dir: &Path, patch: &str) -> anyhow::Result<assert_cmd::assert::Assert> {
+    let mut cmd = Command::cargo_bin("apply_patch")?;
+    cmd.current_dir(dir);
+    Ok(cmd.arg(patch).assert())
+}
+
+fn apply_patch_command(dir: &Path) -> anyhow::Result<Command> {
+    let mut cmd = Command::cargo_bin("apply_patch")?;
+    cmd.current_dir(dir);
+    Ok(cmd)
+}
+
+#[test]
+fn test_apply_patch_cli_applies_multiple_operations() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let modify_path = tmp.path().join("modify.txt");
+    let delete_path = tmp.path().join("delete.txt");
+
+    fs::write(&modify_path, "line1\nline2\n")?;
+    fs::write(&delete_path, "obsolete\n")?;
+
+    let patch = "*** Begin Patch\n*** Add File: nested/new.txt\n+created\n*** Delete File: delete.txt\n*** Update File: modify.txt\n@@\n-line2\n+changed\n*** End Patch";
+
+    run_apply_patch_in_dir(tmp.path(), patch)?.success().stdout(
+        "Success. Updated the following files:\nA nested/new.txt\nM modify.txt\nD delete.txt\n",
+    );
+
+    assert_eq!(
+        fs::read_to_string(tmp.path().join("nested/new.txt"))?,
+        "created\n"
+    );
+    assert_eq!(fs::read_to_string(&modify_path)?, "line1\nchanged\n");
+    assert!(!delete_path.exists());
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_applies_multiple_chunks() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let target_path = tmp.path().join("multi.txt");
+    fs::write(&target_path, "line1\nline2\nline3\nline4\n")?;
+
+    let patch = "*** Begin Patch\n*** Update File: multi.txt\n@@\n-line2\n+changed2\n@@\n-line4\n+changed4\n*** End Patch";
+
+    run_apply_patch_in_dir(tmp.path(), patch)?
+        .success()
+        .stdout("Success. Updated the following files:\nM multi.txt\n");
+
+    assert_eq!(
+        fs::read_to_string(&target_path)?,
+        "line1\nchanged2\nline3\nchanged4\n"
+    );
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_moves_file_to_new_directory() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let original_path = tmp.path().join("old/name.txt");
+    let new_path = tmp.path().join("renamed/dir/name.txt");
+    fs::create_dir_all(original_path.parent().expect("parent should exist"))?;
+    fs::write(&original_path, "old content\n")?;
+
+    let patch = "*** Begin Patch\n*** Update File: old/name.txt\n*** Move to: renamed/dir/name.txt\n@@\n-old content\n+new content\n*** End Patch";
+
+    run_apply_patch_in_dir(tmp.path(), patch)?
+        .success()
+        .stdout("Success. Updated the following files:\nM renamed/dir/name.txt\n");
+
+    assert!(!original_path.exists());
+    assert_eq!(fs::read_to_string(&new_path)?, "new content\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_rejects_empty_patch() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr("No files were modified.\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_reports_missing_context() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let target_path = tmp.path().join("modify.txt");
+    fs::write(&target_path, "line1\nline2\n")?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Update File: modify.txt\n@@\n-missing\n+changed\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr("Failed to find expected lines in modify.txt:\nmissing\n");
+    assert_eq!(fs::read_to_string(&target_path)?, "line1\nline2\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_rejects_missing_file_delete() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Delete File: missing.txt\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr("Failed to delete file missing.txt\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_rejects_empty_update_hunk() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Update File: foo.txt\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr("Invalid patch hunk on line 2: Update file hunk for path 'foo.txt' is empty\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_requires_existing_file_for_update() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Update File: missing.txt\n@@\n-old\n+new\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr(
+            "Failed to read file to update missing.txt: No such file or directory (os error 2)\n",
+        );
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_move_overwrites_existing_destination() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let original_path = tmp.path().join("old/name.txt");
+    let destination = tmp.path().join("renamed/dir/name.txt");
+    fs::create_dir_all(original_path.parent().expect("parent should exist"))?;
+    fs::create_dir_all(destination.parent().expect("parent should exist"))?;
+    fs::write(&original_path, "from\n")?;
+    fs::write(&destination, "existing\n")?;
+
+    run_apply_patch_in_dir(
+        tmp.path(),
+        "*** Begin Patch\n*** Update File: old/name.txt\n*** Move to: renamed/dir/name.txt\n@@\n-from\n+new\n*** End Patch",
+    )?
+    .success()
+    .stdout("Success. Updated the following files:\nM renamed/dir/name.txt\n");
+
+    assert!(!original_path.exists());
+    assert_eq!(fs::read_to_string(&destination)?, "new\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_add_overwrites_existing_file() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let path = tmp.path().join("duplicate.txt");
+    fs::write(&path, "old content\n")?;
+
+    run_apply_patch_in_dir(
+        tmp.path(),
+        "*** Begin Patch\n*** Add File: duplicate.txt\n+new content\n*** End Patch",
+    )?
+    .success()
+    .stdout("Success. Updated the following files:\nA duplicate.txt\n");
+
+    assert_eq!(fs::read_to_string(&path)?, "new content\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_delete_directory_fails() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    fs::create_dir(tmp.path().join("dir"))?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Delete File: dir\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr("Failed to delete file dir\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_rejects_invalid_hunk_header() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Frobnicate File: foo\n*** End Patch")
+        .assert()
+        .failure()
+        .stderr("Invalid patch hunk on line 2: '*** Frobnicate File: foo' is not a valid hunk header. Valid hunk headers: '*** Add File: {path}', '*** Delete File: {path}', '*** Update File: {path}'\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_updates_file_appends_trailing_newline() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let target_path = tmp.path().join("no_newline.txt");
+    fs::write(&target_path, "no newline at end")?;
+
+    run_apply_patch_in_dir(
+        tmp.path(),
+        "*** Begin Patch\n*** Update File: no_newline.txt\n@@\n-no newline at end\n+first line\n+second line\n*** End Patch",
+    )?
+    .success()
+    .stdout("Success. Updated the following files:\nM no_newline.txt\n");
+
+    let contents = fs::read_to_string(&target_path)?;
+    assert!(contents.ends_with('\n'));
+    assert_eq!(contents, "first line\nsecond line\n");
+
+    Ok(())
+}
+
+#[test]
+fn test_apply_patch_cli_failure_after_partial_success_leaves_changes() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let new_file = tmp.path().join("created.txt");
+
+    apply_patch_command(tmp.path())?
+        .arg("*** Begin Patch\n*** Add File: created.txt\n+hello\n*** Update File: missing.txt\n@@\n-old\n+new\n*** End Patch")
+        .assert()
+        .failure()
+        .stdout("")
+        .stderr("Failed to read file to update missing.txt: No such file or directory (os error 2)\n");
+
+    assert_eq!(fs::read_to_string(&new_file)?, "hello\n");
+
+    Ok(())
+}

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/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

@@ -30,15 +30,17 @@ 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 +48,10 @@ 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 +132,74 @@ 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 = match &config.sandbox_policy {
+                codex_core::protocol::SandboxPolicy::DangerFullAccess => "workspace-write",
+                codex_core::protocol::SandboxPolicy::ReadOnly => "read-only",
+                codex_core::protocol::SandboxPolicy::WorkspaceWrite { .. } => "workspace-write",
+            };
+
+            let sandbox_cwd = sandbox_policy_cwd.clone();
+            let cwd_clone = cwd.clone();
+            let env_map = env.clone();
+            let command_vec = command.clone();
+            let base_dir = config.codex_home.clone();
+
+            // Preflight audit is invoked elsewhere at the appropriate times.
+            let res = tokio::task::spawn_blocking(move || {
+                run_windows_sandbox_capture(
+                    policy_str,
+                    &sandbox_cwd,
+                    command_vec,
+                    &cwd_clone,
+                    env_map,
+                    None,
+                    Some(base_dir.as_path()),
+                )
+            })
+            .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 +227,31 @@ 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;
@@ -19,16 +21,20 @@ use codex_exec::Cli as ExecCli;
 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 +83,8 @@ 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),
@@ -94,9 +100,6 @@ 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),
@@ -150,6 +153,9 @@ 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)]
@@ -200,6 +206,22 @@ 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 +232,13 @@ 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 +291,30 @@ 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}");
     }
@@ -286,15 +335,25 @@ 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 +404,8 @@ 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 => {
@@ -373,9 +431,20 @@ 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,
@@ -462,6 +531,17 @@ 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::Apply(mut apply_cli)) => {
             prepend_config_flags(
@@ -479,21 +559,24 @@ 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()
                 };
 
@@ -605,6 +688,7 @@ 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");
@@ -781,4 +865,32 @@ 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;
@@ -196,7 +196,9 @@ 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 +265,10 @@ 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 +279,42 @@ 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 +328,10 @@ 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 +345,16 @@ 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 +388,9 @@ 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 +417,9 @@ 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 +553,12 @@ 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 +674,9 @@ 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 +786,15 @@ 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 +807,7 @@ 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/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;

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

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

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

@@ -2,6 +2,10 @@ use base64::Engine as _;
 use chrono::Utc;
 use reqwest::header::HeaderMap;
 
+use codex_core::config::Config;
+use codex_core::config::ConfigOverrides;
+use codex_login::AuthManager;
+
 pub fn set_user_agent_suffix(suffix: &str) {
     if let Ok(mut guard) = codex_core::default_client::USER_AGENT_SUFFIX.lock() {
         guard.replace(suffix.to_string());
@@ -54,6 +58,18 @@ pub fn extract_chatgpt_account_id(token: &str) -> Option<String> {
         .map(str::to_string)
 }
 
+pub async fn load_auth_manager() -> Option<AuthManager> {
+    // TODO: pass in cli overrides once cloud tasks properly support them.
+    let config = Config::load_with_cli_overrides(Vec::new(), ConfigOverrides::default())
+        .await
+        .ok()?;
+    Some(AuthManager::new(
+        config.codex_home,
+        false,
+        config.cli_auth_credentials_store_mode,
+    ))
+}
+
 /// Build headers for ChatGPT-backed requests: `User-Agent`, optional `Authorization`,
 /// and optional `ChatGPT-Account-Id`.
 pub async fn build_chatgpt_headers() -> HeaderMap {
@@ -69,24 +85,22 @@ pub async fn build_chatgpt_headers() -> HeaderMap {
         USER_AGENT,
         HeaderValue::from_str(&ua).unwrap_or(HeaderValue::from_static("codex-cli")),
     );
-    if let Ok(home) = codex_core::config::find_codex_home() {
-        let am = codex_login::AuthManager::new(home, false);
-        if let Some(auth) = am.auth()
-            && let Ok(tok) = auth.get_token().await
-            && !tok.is_empty()
+    if let Some(am) = load_auth_manager().await
+        && let Some(auth) = am.auth()
+        && let Ok(tok) = auth.get_token().await
+        && !tok.is_empty()
+    {
+        let v = format!("Bearer {tok}");
+        if let Ok(hv) = HeaderValue::from_str(&v) {
+            headers.insert(AUTHORIZATION, hv);
+        }
+        if let Some(acc) = auth
+            .get_account_id()
+            .or_else(|| extract_chatgpt_account_id(&tok))
+            && let Ok(name) = HeaderName::from_bytes(b"ChatGPT-Account-Id")
+            && let Ok(hv) = HeaderValue::from_str(&acc)
         {
-            let v = format!("Bearer {tok}");
-            if let Ok(hv) = HeaderValue::from_str(&v) {
-                headers.insert(AUTHORIZATION, hv);
-            }
-            if let Some(acc) = auth
-                .get_account_id()
-                .or_else(|| extract_chatgpt_account_id(&tok))
-                && let Ok(name) = HeaderName::from_bytes(b"ChatGPT-Account-Id")
-                && let Ok(hv) = HeaderValue::from_str(&acc)
-            {
-                headers.insert(name, hv);
-            }
+            headers.insert(name, hv);
         }
     }
     headers

codex-rs/codex-backend-openapi-models/Cargo.toml

@@ -16,3 +16,6 @@ path = "src/lib.rs"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
 serde_with = "3"
+
+[package.metadata.cargo-shear]
+ignored = ["serde_with"]

codex-rs/common/Cargo.toml

@@ -8,9 +8,10 @@ workspace = true
 
 [dependencies]
 clap = { workspace = true, features = ["derive", "wrap_help"], optional = true }
+codex-app-server-protocol = { workspace = true }
 codex-core = { workspace = true }
 codex-protocol = { workspace = true }
-codex-app-server-protocol = { workspace = true }
+once_cell = { workspace = true }
 serde = { workspace = true, optional = true }
 toml = { workspace = true, optional = true }
 

codex-rs/common/src/approval_presets.rs

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

codex-rs/common/src/config_override.rs

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

codex-rs/common/src/format_env_display.rs

@@ -6,15 +6,11 @@ pub fn format_env_display(env: Option<&HashMap<String, String>>, env_vars: &[Str
     if let Some(map) = env {
         let mut pairs: Vec<_> = map.iter().collect();
         pairs.sort_by(|(a, _), (b, _)| a.cmp(b));
-        parts.extend(
-            pairs
-                .into_iter()
-                .map(|(key, value)| format!("{key}={value}")),
-        );
+        parts.extend(pairs.into_iter().map(|(key, _)| format!("{key}=*****")));
     }
 
     if !env_vars.is_empty() {
-        parts.extend(env_vars.iter().map(|var| format!("{var}=${var}")));
+        parts.extend(env_vars.iter().map(|var| format!("{var}=*****")));
     }
 
     if parts.is_empty() {
@@ -42,14 +38,14 @@ mod tests {
         env.insert("B".to_string(), "two".to_string());
         env.insert("A".to_string(), "one".to_string());
 
-        assert_eq!(format_env_display(Some(&env), &[]), "A=one, B=two");
+        assert_eq!(format_env_display(Some(&env), &[]), "A=*****, B=*****");
     }
 
     #[test]
     fn formats_env_vars_with_dollar_prefix() {
         let vars = vec!["TOKEN".to_string(), "PATH".to_string()];
 
-        assert_eq!(format_env_display(None, &vars), "TOKEN=$TOKEN, PATH=$PATH");
+        assert_eq!(format_env_display(None, &vars), "TOKEN=*****, PATH=*****");
     }
 
     #[test]
@@ -60,7 +56,7 @@ mod tests {
 
         assert_eq!(
             format_env_display(Some(&env), &vars),
-            "HOME=/tmp, TOKEN=$TOKEN"
+            "HOME=*****, TOKEN=*****"
         );
     }
 }

codex-rs/common/src/model_presets.rs

@@ -1,5 +1,8 @@
+use std::collections::HashMap;
+
 use codex_app_server_protocol::AuthMode;
 use codex_core::protocol_config_types::ReasoningEffort;
+use once_cell::sync::Lazy;
 
 /// A reasoning effort option that can be surfaced for a model.
 #[derive(Debug, Clone, Copy)]
@@ -10,8 +13,14 @@ pub struct ReasoningEffortPreset {
     pub description: &'static str,
 }
 
+#[derive(Debug, Clone)]
+pub struct ModelUpgrade {
+    pub id: &'static str,
+    pub reasoning_effort_mapping: Option<HashMap<ReasoningEffort, ReasoningEffort>>,
+}
+
 /// Metadata describing a Codex-supported model.
-#[derive(Debug, Clone, Copy)]
+#[derive(Debug, Clone)]
 pub struct ModelPreset {
     /// Stable identifier for the preset.
     pub id: &'static str,
@@ -27,61 +36,173 @@ pub struct ModelPreset {
     pub supported_reasoning_efforts: &'static [ReasoningEffortPreset],
     /// Whether this is the default model for new users.
     pub is_default: bool,
+    /// recommended upgrade model
+    pub upgrade: Option<ModelUpgrade>,
 }
 
-const PRESETS: &[ModelPreset] = &[
-    ModelPreset {
-        id: "gpt-5-codex",
-        model: "gpt-5-codex",
-        display_name: "gpt-5-codex",
-        description: "Optimized for coding tasks with many tools.",
-        default_reasoning_effort: ReasoningEffort::Medium,
-        supported_reasoning_efforts: &[
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::Low,
-                description: "Fastest responses with limited reasoning",
-            },
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::Medium,
-                description: "Dynamically adjusts reasoning based on the task",
-            },
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::High,
-                description: "Maximizes reasoning depth for complex or ambiguous problems",
-            },
-        ],
-        is_default: true,
-    },
-    ModelPreset {
-        id: "gpt-5",
-        model: "gpt-5",
-        display_name: "gpt-5",
-        description: "Broad world knowledge with strong general reasoning.",
-        default_reasoning_effort: ReasoningEffort::Medium,
-        supported_reasoning_efforts: &[
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::Minimal,
-                description: "Fastest responses with little reasoning",
-            },
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::Low,
-                description: "Balances speed with some reasoning; useful for straightforward queries and short explanations",
-            },
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::Medium,
-                description: "Provides a solid balance of reasoning depth and latency for general-purpose tasks",
-            },
-            ReasoningEffortPreset {
-                effort: ReasoningEffort::High,
-                description: "Maximizes reasoning depth for complex or ambiguous problems",
-            },
-        ],
-        is_default: false,
-    },
-];
+static PRESETS: Lazy<Vec<ModelPreset>> = Lazy::new(|| {
+    vec![
+        ModelPreset {
+            id: "gpt-5.1-codex",
+            model: "gpt-5.1-codex",
+            display_name: "gpt-5.1-codex",
+            description: "Optimized for codex.",
+            default_reasoning_effort: ReasoningEffort::Medium,
+            supported_reasoning_efforts: &[
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Low,
+                    description: "Fastest responses with limited reasoning",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems",
+                },
+            ],
+            is_default: true,
+            upgrade: None,
+        },
+        ModelPreset {
+            id: "gpt-5.1-codex-mini",
+            model: "gpt-5.1-codex-mini",
+            display_name: "gpt-5.1-codex-mini",
+            description: "Optimized for codex. Cheaper, faster, but less capable.",
+            default_reasoning_effort: ReasoningEffort::Medium,
+            supported_reasoning_efforts: &[
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems",
+                },
+            ],
+            is_default: false,
+            upgrade: None,
+        },
+        ModelPreset {
+            id: "gpt-5.1",
+            model: "gpt-5.1",
+            display_name: "gpt-5.1",
+            description: "Broad world knowledge with strong general reasoning.",
+            default_reasoning_effort: ReasoningEffort::Medium,
+            supported_reasoning_efforts: &[
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Low,
+                    description: "Balances speed with some reasoning; useful for straightforward queries and short explanations",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Medium,
+                    description: "Provides a solid balance of reasoning depth and latency for general-purpose tasks",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems",
+                },
+            ],
+            is_default: false,
+            upgrade: None,
+        },
+        // Deprecated models.
+        ModelPreset {
+            id: "gpt-5-codex",
+            model: "gpt-5-codex",
+            display_name: "gpt-5-codex",
+            description: "Optimized for codex.",
+            default_reasoning_effort: ReasoningEffort::Medium,
+            supported_reasoning_efforts: &[
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Low,
+                    description: "Fastest responses with limited reasoning",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems",
+                },
+            ],
+            is_default: false,
+            upgrade: Some(ModelUpgrade {
+                id: "gpt-5.1-codex",
+                reasoning_effort_mapping: None,
+            }),
+        },
+        ModelPreset {
+            id: "gpt-5-codex-mini",
+            model: "gpt-5-codex-mini",
+            display_name: "gpt-5-codex-mini",
+            description: "Optimized for codex. Cheaper, faster, but less capable.",
+            default_reasoning_effort: ReasoningEffort::Medium,
+            supported_reasoning_efforts: &[
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems",
+                },
+            ],
+            is_default: false,
+            upgrade: Some(ModelUpgrade {
+                id: "gpt-5.1-codex-mini",
+                reasoning_effort_mapping: None,
+            }),
+        },
+        ModelPreset {
+            id: "gpt-5",
+            model: "gpt-5",
+            display_name: "gpt-5",
+            description: "Broad world knowledge with strong general reasoning.",
+            default_reasoning_effort: ReasoningEffort::Medium,
+            supported_reasoning_efforts: &[
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Minimal,
+                    description: "Fastest responses with little reasoning",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Low,
+                    description: "Balances speed with some reasoning; useful for straightforward queries and short explanations",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::Medium,
+                    description: "Provides a solid balance of reasoning depth and latency for general-purpose tasks",
+                },
+                ReasoningEffortPreset {
+                    effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems",
+                },
+            ],
+            is_default: false,
+            upgrade: Some(ModelUpgrade {
+                id: "gpt-5.1",
+                reasoning_effort_mapping: Some(HashMap::from([(
+                    ReasoningEffort::Minimal,
+                    ReasoningEffort::Low,
+                )])),
+            }),
+        },
+    ]
+});
 
 pub fn builtin_model_presets(_auth_mode: Option<AuthMode>) -> Vec<ModelPreset> {
-    PRESETS.to_vec()
+    // leave auth mode for later use
+    PRESETS
+        .iter()
+        .filter(|preset| preset.upgrade.is_none())
+        .cloned()
+        .collect()
+}
+
+pub fn all_model_presets() -> &'static Vec<ModelPreset> {
+    &PRESETS
 }
 
 #[cfg(test)]

codex-rs/core/Cargo.toml

@@ -21,19 +21,31 @@ bytes = { workspace = true }
 chrono = { workspace = true, features = ["serde"] }
 codex-app-server-protocol = { workspace = true }
 codex-apply-patch = { workspace = true }
+codex-async-utils = { workspace = true }
 codex-file-search = { workspace = true }
+codex-git = { workspace = true }
+codex-keyring-store = { workspace = true }
 codex-otel = { workspace = true, features = ["otel"] }
 codex-protocol = { workspace = true }
 codex-rmcp-client = { workspace = true }
-codex-async-utils = { workspace = true }
-codex-utils-string = { workspace = true }
 codex-utils-pty = { workspace = true }
+codex-utils-readiness = { workspace = true }
+codex-utils-string = { workspace = true }
+codex-utils-tokenizer = { workspace = true }
+codex-windows-sandbox = { package = "codex-windows-sandbox", path = "../windows-sandbox-rs" }
 dirs = { workspace = true }
 dunce = { workspace = true }
 env-flags = { workspace = true }
 eventsource-stream = { workspace = true }
 futures = { workspace = true }
+http = { workspace = true }
 indexmap = { workspace = true }
+keyring = { workspace = true, features = [
+    "apple-native",
+    "crypto-rust",
+    "linux-native-async-persistent",
+    "windows-native",
+] }
 libc = { workspace = true }
 mcp-types = { workspace = true }
 os_info = { workspace = true }
@@ -43,10 +55,12 @@ reqwest = { workspace = true, features = ["json", "stream"] }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
 sha1 = { workspace = true }
+sha2 = { workspace = true }
 shlex = { workspace = true }
 similar = { workspace = true }
 strum_macros = { workspace = true }
 tempfile = { workspace = true }
+test-case = "3.3.1"
 test-log = { workspace = true }
 thiserror = { workspace = true }
 time = { workspace = true, features = [
@@ -68,7 +82,7 @@ toml_edit = { workspace = true }
 tracing = { workspace = true, features = ["log"] }
 tree-sitter = { workspace = true }
 tree-sitter-bash = { workspace = true }
-uuid = { workspace = true, features = ["serde", "v4"] }
+uuid = { workspace = true, features = ["serde", "v4", "v5"] }
 which = { workspace = true }
 wildmatch = { workspace = true }
 
@@ -91,8 +105,11 @@ openssl-sys = { workspace = true, features = ["vendored"] }
 [dev-dependencies]
 assert_cmd = { workspace = true }
 assert_matches = { workspace = true }
+codex-arg0 = { workspace = true }
 core_test_support = { workspace = true }
+ctor = { workspace = true }
 escargot = { workspace = true }
+image = { workspace = true, features = ["jpeg", "png"] }
 maplit = { workspace = true }
 predicates = { workspace = true }
 pretty_assertions = { workspace = true }

codex-rs/core/gpt_5_1_prompt.md

@@ -0,0 +1,370 @@
+You are GPT-5.1 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.
+
+Your capabilities:
+
+- Receive user prompts and other context provided by the harness, such as files in the workspace.
+- Communicate with the user by streaming thinking & responses, and by making & updating plans.
+- Emit function calls to run terminal commands and apply patches. Depending on how this specific run is configured, you can request that these function calls be escalated to the user for approval before running. More on this in the "Sandbox and approvals" section.
+
+Within this context, Codex refers to the open-source agentic coding interface (not the old Codex language model built by OpenAI).
+
+# How you work
+
+## Personality
+
+Your default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
+
+# AGENTS.md spec
+- Repos often contain AGENTS.md files. These files can appear anywhere within the repository.
+- These files are a way for humans to give you (the agent) instructions or tips for working within the container.
+- Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.
+- Instructions in AGENTS.md files:
+    - The scope of an AGENTS.md file is the entire directory tree rooted at the folder that contains it.
+    - For every file you touch in the final patch, you must obey instructions in any AGENTS.md file whose scope includes that file.
+    - Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the file states otherwise.
+    - More-deeply-nested AGENTS.md files take precedence in the case of conflicting instructions.
+    - Direct system/developer/user instructions (as part of a prompt) take precedence over AGENTS.md instructions.
+- The contents of the AGENTS.md file at the root of the repo and any directories from the CWD up to the root are included with the developer message and don't need to be re-read. When working in a subdirectory of CWD, or a directory outside the CWD, check for any AGENTS.md files that may be applicable.
+
+## Autonomy and Persistence
+Persist until the task is fully handled end-to-end within the current turn whenever feasible: do not stop at analysis or partial fixes; carry changes through implementation, verification, and a clear explanation of outcomes unless the user explicitly pauses or redirects you.
+
+Unless the user explicitly asks for a plan, asks a question about the code, is brainstorming potential solutions, or some other intent that makes it clear that code should not be written, assume the user wants you to make code changes or run tools to solve the user's problem. In these cases, it's bad to output your proposed solution in a message, you should go ahead and actually implement the change. If you encounter challenges or blockers, you should attempt to resolve them yourself.
+
+## Responsiveness
+
+### User Updates Spec
+You'll work for stretches with tool calls — it's critical to keep the user updated as you work.
+
+Frequency & Length:
+- Send short updates (1–2 sentences) whenever there is a meaningful, important insight you need to share with the user to keep them informed.
+- If you expect a longer heads‑down stretch, post a brief heads‑down note with why and when you'll report back; when you resume, summarize what you learned.
+- Only the initial plan, plan updates, and final recap can be longer, with multiple bullets and paragraphs
+
+Tone:
+- Friendly, confident, senior-engineer energy. Positive, collaborative, humble; fix mistakes quickly.
+
+Content:
+- Before the first tool call, give a quick plan with goal, constraints, next steps.
+- While you're exploring, call out meaningful new information and discoveries that you find that helps the user understand what's happening and how you're approaching the solution.
+- If you change the plan (e.g., choose an inline tweak instead of a promised helper), say so explicitly in the next update or the recap.
+
+**Examples:**
+
+- “I’ve explored the repo; now checking the API route definitions.”
+- “Next, I’ll patch the config and update the related tests.”
+- “I’m about to scaffold the CLI commands and helper functions.”
+- “Ok cool, so I’ve wrapped my head around the repo. Now digging into the API routes.”
+- “Config’s looking tidy. Next up is patching helpers to keep things in sync.”
+- “Finished poking at the DB gateway. I will now chase down error handling.”
+- “Alright, build pipeline order is interesting. Checking how it reports failures.”
+- “Spotted a clever caching util; now hunting where it gets used.”
+
+## Planning
+
+You have access to an `update_plan` tool which tracks steps and progress and renders them to the user. Using the tool helps demonstrate that you've understood the task and convey how you're approaching it. Plans can help to make complex, ambiguous, or multi-phase work clearer and more collaborative for the user. A good plan should break the task into meaningful, logically ordered steps that are easy to verify as you go.
+
+Note that plans are not for padding out simple work with filler steps or stating the obvious. The content of your plan should not involve doing anything that you aren't capable of doing (i.e. don't try to test things that you can't test). Do not use plans for simple or single-step queries that you can just do or answer immediately.
+
+Do not repeat the full contents of the plan after an `update_plan` call — the harness already displays it. Instead, summarize the change made and highlight any important context or next step.
+
+Before running a command, consider whether or not you have completed the previous step, and make sure to mark it as completed before moving on to the next step. It may be the case that you complete all steps in your plan after a single pass of implementation. If this is the case, you can simply mark all the planned steps as completed. Sometimes, you may need to change plans in the middle of a task: call `update_plan` with the updated plan and make sure to provide an `explanation` of the rationale when doing so.
+
+Maintain statuses in the tool: exactly one item in_progress at a time; mark items complete when done; post timely status transitions. Do not jump an item from pending to completed: always set it to in_progress first. Do not batch-complete multiple items after the fact. Finish with all items completed or explicitly canceled/deferred before ending the turn. Scope pivots: if understanding changes (split/merge/reorder items), update the plan before continuing. Do not let the plan go stale while coding.
+
+Use a plan when:
+
+- The task is non-trivial and will require multiple actions over a long time horizon.
+- There are logical phases or dependencies where sequencing matters.
+- The work has ambiguity that benefits from outlining high-level goals.
+- You want intermediate checkpoints for feedback and validation.
+- When the user asked you to do more than one thing in a single prompt
+- The user has asked you to use the plan tool (aka "TODOs")
+- You generate additional steps while working, and plan to do them before yielding to the user
+
+### Examples
+
+**High-quality plans**
+
+Example 1:
+
+1. Add CLI entry with file args
+2. Parse Markdown via CommonMark library
+3. Apply semantic HTML template
+4. Handle code blocks, images, links
+5. Add error handling for invalid files
+
+Example 2:
+
+1. Define CSS variables for colors
+2. Add toggle with localStorage state
+3. Refactor components to use variables
+4. Verify all views for readability
+5. Add smooth theme-change transition
+
+Example 3:
+
+1. Set up Node.js + WebSocket server
+2. Add join/leave broadcast events
+3. Implement messaging with timestamps
+4. Add usernames + mention highlighting
+5. Persist messages in lightweight DB
+6. Add typing indicators + unread count
+
+**Low-quality plans**
+
+Example 1:
+
+1. Create CLI tool
+2. Add Markdown parser
+3. Convert to HTML
+
+Example 2:
+
+1. Add dark mode toggle
+2. Save preference
+3. Make styles look good
+
+Example 3:
+
+1. Create single-file HTML game
+2. Run quick sanity check
+3. Summarize usage instructions
+
+If you need to write a plan, only write high quality plans, not low quality ones.
+
+## Task execution
+
+You are a coding agent. You must keep going until the query or task is completely resolved, before ending your turn and yielding back to the user. Persist until the task is fully handled end-to-end within the current turn whenever feasible and persevere even when function calls fail. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability, using the tools available to you, before coming back to the user. Do NOT guess or make up an answer.
+
+You MUST adhere to the following criteria when solving queries:
+
+- Working on the repo(s) in the current environment is allowed, even if they are proprietary.
+- Analyzing code for vulnerabilities is allowed.
+- Showing user code and tool call details is allowed.
+- Use the `apply_patch` tool to edit files (NEVER try `applypatch` or `apply-patch`, only `apply_patch`). This is a FREEFORM tool, so do not wrap the patch in JSON.
+
+If completing the user's task requires writing or modifying files, your code and final answer should follow these coding guidelines, though user instructions (i.e. AGENTS.md) may override these guidelines:
+
+- Fix the problem at the root cause rather than applying surface-level patches, when possible.
+- Avoid unneeded complexity in your solution.
+- Do not attempt to fix unrelated bugs or broken tests. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
+- Update documentation as necessary.
+- Keep changes consistent with the style of the existing codebase. Changes should be minimal and focused on the task.
+- Use `git log` and `git blame` to search the history of the codebase if additional context is required.
+- NEVER add copyright or license headers unless specifically requested.
+- Do not waste tokens by re-reading files after calling `apply_patch` on them. The tool call will fail if it didn't work. The same goes for making folders, deleting folders, etc.
+- Do not `git commit` your changes or create new git branches unless explicitly requested.
+- Do not add inline comments within code unless explicitly requested.
+- Do not use one-letter variable names unless explicitly requested.
+- NEVER output inline citations like "【F:README.md†L5-L14】" in your outputs. The CLI is not able to render these so they will just be broken in the UI. Instead, if you output valid filepaths, users will be able to click on them to open the files in their editor.
+
+## Codex CLI harness, sandboxing, and approvals
+
+The Codex CLI harness supports several different configurations for sandboxing and escalation approvals that the user can choose from.
+
+Filesystem sandboxing defines which files can be read or written. The options for `sandbox_mode` are:
+- **read-only**: The sandbox only permits reading files.
+- **workspace-write**: The sandbox permits reading files, and editing files in `cwd` and `writable_roots`. Editing files in other directories requires approval.
+- **danger-full-access**: No filesystem sandboxing - all commands are permitted.
+
+Network sandboxing defines whether network can be accessed without approval. Options for `network_access` are:
+- **restricted**: Requires approval
+- **enabled**: No approval needed
+
+Approvals are your mechanism to get user consent to run shell commands without the sandbox. Possible configuration options for `approval_policy` are
+- **untrusted**: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
+- **on-failure**: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
+- **on-request**: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for escalating in the tool definition.)
+- **never**: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is paired with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
+
+When you are running with `approval_policy == on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
+- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /var)
+- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
+- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
+- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval. ALWAYS proceed to use the `with_escalated_permissions` and `justification` parameters. Within this harness, prefer requesting approval via the tool over asking in natural language.
+- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
+- (for all of these, you should weigh alternative paths that do not require approval)
+
+When `sandbox_mode` is set to read-only, you'll need to request approval for any command that isn't a read.
+
+You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing enabled, and approval on-failure.
+
+Although they introduce friction to the user because your work is paused until the user responds, you should leverage them when necessary to accomplish important work. If the completing the task requires escalated permissions, Do not let these settings or the sandbox deter you from attempting to accomplish the user's task unless it is set to "never", in which case never ask for approvals.
+
+When requesting approval to execute a command that will require escalated privileges:
+  - Provide the `with_escalated_permissions` parameter with the boolean value true
+  - Include a short, 1 sentence explanation for why you need to enable `with_escalated_permissions` in the justification parameter
+
+## Validating your work
+
+If the codebase has tests or the ability to build or run, consider using them to verify changes once your work is complete.
+
+When testing, your philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests.
+
+Similarly, once you're confident in correctness, you can suggest or use formatting commands to ensure that your code is well formatted. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.
+
+For all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
+
+Be mindful of whether to run validation commands proactively. In the absence of behavioral guidance:
+
+- When running in non-interactive approval modes like **never** or **on-failure**, you can proactively run tests, lint and do whatever you need to ensure you've completed the task. If you are unable to run tests, you must still do your utmost best to complete the task.
+- When working in interactive approval modes like **untrusted**, or **on-request**, hold off on running tests or lint commands until the user is ready for you to finalize your output, because these commands take time to run and slow down iteration. Instead suggest what you want to do next, and let the user confirm first.
+- When working on test-related tasks, such as adding tests, fixing tests, or reproducing a bug to verify behavior, you may proactively run tests regardless of approval mode. Use your judgement to decide whether this is a test-related task.
+
+## Ambition vs. precision
+
+For tasks that have no prior context (i.e. the user is starting something brand new), you should feel free to be ambitious and demonstrate creativity with your implementation.
+
+If you're operating in an existing codebase, you should make sure you do exactly what the user asks with surgical precision. Treat the surrounding codebase with respect, and don't overstep (i.e. changing filenames or variables unnecessarily). You should balance being sufficiently ambitious and proactive when completing tasks of this nature.
+
+You should use judicious initiative to decide on the right level of detail and complexity to deliver based on the user's needs. This means showing good judgment that you're capable of doing the right extras without gold-plating. This might be demonstrated by high-value, creative touches when scope of the task is vague; while being surgical and targeted when scope is tightly specified.
+
+## Sharing progress updates
+
+For especially longer tasks that you work on (i.e. requiring many tool calls, or a plan with multiple steps), you should provide progress updates back to the user at reasonable intervals. These updates should be structured as a concise sentence or two (no more than 8-10 words long) recapping progress so far in plain language: this update demonstrates your understanding of what needs to be done, progress so far (i.e. files explores, subtasks complete), and where you're going next.
+
+Before doing large chunks of work that may incur latency as experienced by the user (i.e. writing a new file), you should send a concise message to the user with an update indicating what you're about to do to ensure they know what you're spending time on. Don't start editing or writing large files before informing the user what you are doing and why.
+
+The messages you send before tool calls should describe what is immediately about to be done next in very concise language. If there was previous work done, this preamble message should also include a note about the work done so far to bring the user along.
+
+## Presenting your work and final message
+
+Your final message should read naturally, like an update from a concise teammate. For casual conversation, brainstorming tasks, or quick questions from the user, respond in a friendly, conversational tone. You should ask questions, suggest ideas, and adapt to the user’s style. If you've finished a large amount of work, when describing what you've done to the user, you should follow the final answer formatting guidelines to communicate substantive changes. You don't need to add structured formatting for one-word answers, greetings, or purely conversational exchanges.
+
+You can skip heavy formatting for single, simple actions or confirmations. In these cases, respond in plain sentences with any relevant next step or quick option. Reserve multi-section structured responses for results that need grouping or explanation.
+
+The user is working on the same computer as you, and has access to your work. As such there's no need to show the contents of files you have already written unless the user explicitly asks for them. Similarly, if you've created or modified files using `apply_patch`, there's no need to tell users to "save the file" or "copy the code into a file"—just reference the file path.
+
+If there's something that you think you could help with as a logical next step, concisely ask the user if they want you to do so. Good examples of this are running tests, committing changes, or building out the next logical component. If there’s something that you couldn't do (even with approval) but that the user might want to do (such as verifying changes by running the app), include those instructions succinctly.
+
+Brevity is very important as a default. You should be very concise (i.e. no more than 10 lines), but can relax this requirement for tasks where additional detail and comprehensiveness is important for the user's understanding.
+
+### Final answer structure and style guidelines
+
+You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
+
+**Section Headers**
+
+- Use only when they improve clarity — they are not mandatory for every answer.
+- Choose descriptive names that fit the content
+- Keep headers short (1–3 words) and in `**Title Case**`. Always start headers with `**` and end with `**`
+- Leave no blank line before the first bullet under a header.
+- Section headers should only be used where they genuinely improve scanability; avoid fragmenting the answer.
+
+**Bullets**
+
+- Use `-` followed by a space for every bullet.
+- Merge related points when possible; avoid a bullet for every trivial detail.
+- Keep bullets to one line unless breaking for clarity is unavoidable.
+- Group into short lists (4–6 bullets) ordered by importance.
+- Use consistent keyword phrasing and formatting across sections.
+
+**Monospace**
+
+- Wrap all commands, file paths, env vars, code identifiers, and code samples in backticks (`` `...` ``).
+- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.
+- Never mix monospace and bold markers; choose one based on whether it’s a keyword (`**`) or inline code/path (`` ` ``).
+
+**File References**
+When referencing files in your response, make sure to include the relevant start line and always follow the below rules:
+  * Use inline code to make file paths clickable.
+  * Each reference should have a stand alone path. Even if it's the same file.
+  * Accepted: absolute, workspace‑relative, a/ or b/ diff prefixes, or bare filename/suffix.
+  * Line/column (1‑based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
+  * Do not use URIs like file://, vscode://, or https://.
+  * Do not provide range of lines
+  * Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5
+
+**Structure**
+
+- Place related bullets together; don’t mix unrelated concepts in the same section.
+- Order sections from general → specific → supporting info.
+- For subsections (e.g., “Binaries” under “Rust Workspace”), introduce with a bolded keyword bullet, then list items under it.
+- Match structure to complexity:
+  - Multi-part or detailed results → use clear headers and grouped bullets.
+  - Simple results → minimal headers, possibly just a short list or paragraph.
+
+**Tone**
+
+- Keep the voice collaborative and natural, like a coding partner handing off work.
+- Be concise and factual — no filler or conversational commentary and avoid unnecessary repetition
+- Use present tense and active voice (e.g., “Runs tests” not “This will run tests”).
+- Keep descriptions self-contained; don’t refer to “above” or “below”.
+- Use parallel structure in lists for consistency.
+
+**Verbosity**
+- Final answer compactness rules (enforced):
+  - Tiny/small single-file change (≤ ~10 lines): 2–5 sentences or ≤3 bullets. No headings. 0–1 short snippet (≤3 lines) only if essential.
+  - Medium change (single area or a few files): ≤6 bullets or 6–10 sentences. At most 1–2 short snippets total (≤8 lines each).
+  - Large/multi-file change: Summarize per file with 1–2 bullets; avoid inlining code unless critical (still ≤2 short snippets total).
+  - Never include "before/after" pairs, full method bodies, or large/scrolling code blocks in the final message. Prefer referencing file/symbol names instead.
+
+**Don’t**
+
+- Don’t use literal words “bold” or “monospace” in the content.
+- Don’t nest bullets or create deep hierarchies.
+- Don’t output ANSI escape codes directly — the CLI renderer applies them.
+- Don’t cram unrelated keywords into a single bullet; split for clarity.
+- Don’t let keyword lists run long — wrap or reformat for scanability.
+
+Generally, ensure your final answers adapt their shape and depth to the request. For example, answers to code explanations should have a precise, structured explanation with code references that answer the question directly. For tasks with a simple implementation, lead with the outcome and supplement only with what’s needed for clarity. Larger changes can be presented as a logical walkthrough of your approach, grouping related steps, explaining rationale where it adds value, and highlighting next actions to accelerate the user. Your answers should provide the right level of detail while being easily scannable.
+
+For casual greetings, acknowledgements, or other one-off conversational messages that are not delivering substantive information or structured results, respond naturally without section headers or bullet formatting.
+
+# Tool Guidelines
+
+## Shell commands
+
+When using the shell, you must adhere to the following guidelines:
+
+- The arguments to `shell` will be passed to execvp().
+- Always set the `workdir` param when using the shell function. Do not use `cd` unless absolutely necessary.
+- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
+- Read files in chunks with a max chunk size of 250 lines. Do not use python scripts to attempt to output larger chunks of a file. Command line output will be truncated after 10 kilobytes or 256 lines of output, regardless of the command used.
+
+## apply_patch
+
+Use the `apply_patch` tool to edit files. Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
+
+*** Begin Patch
+[ one or more file sections ]
+*** End Patch
+
+Within that envelope, you get a sequence of file operations.
+You MUST include a header to specify the action you are taking.
+Each operation starts with one of three headers:
+
+*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
+*** Delete File: <path> - remove an existing file. Nothing follows.
+*** Update File: <path> - patch an existing file in place (optionally with a rename).
+
+Example patch:
+
+```
+*** Begin Patch
+*** Add File: hello.txt
++Hello world
+*** Update File: src/app.py
+*** Move to: src/main.py
+@@ def greet():
+-print("Hi")
++print("Hello, world!")
+*** Delete File: obsolete.txt
+*** End Patch
+```
+
+It is important to remember:
+
+- You must include a header with your intended action (Add/Delete/Update)
+- You must prefix new lines with `+` even when creating a new file
+
+## `update_plan`
+
+A tool named `update_plan` is available to you. You can use it to keep an up‑to‑date, step‑by‑step plan for the task.
+
+To create a new plan, call `update_plan` with a short list of 1‑sentence steps (no more than 5-7 words each) with a `status` for each step (`pending`, `in_progress`, or `completed`).
+
+When steps have been completed, use `update_plan` to mark each finished step as `completed` and the next step you are working on as `in_progress`. There should always be exactly one `in_progress` step until everything is done. You can mark multiple items as complete in a single `update_plan` call.
+
+If all steps are complete, ensure you call `update_plan` to mark all steps as `completed`.

codex-rs/core/gpt_5_codex_prompt.md

@@ -16,6 +16,7 @@ You are Codex, based on GPT-5. You are running as a coding agent in the Codex CL
     * If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, don't revert those changes.
     * If the changes are in files you've touched recently, you should read carefully and understand how you can work with the changes rather than reverting them.
     * If the changes are in unrelated files, just ignore them and don't revert them.
+- Do not amend a commit unless explicitly requested to do so.
 - While you are working, you might notice unexpected changes that you didn't make. If this happens, STOP IMMEDIATELY and ask the user how they would like to proceed.
 - **NEVER** use destructive commands like `git reset --hard` or `git checkout --` unless specifically requested or approved by the user.
 

codex-rs/core/review_prompt.md

@@ -82,6 +82,6 @@ OUTPUT FORMAT:
 
 * **Do not** wrap the JSON in markdown fences or extra prose.
 * The code_location field is required and must include absolute_file_path and line_range.
-*Line ranges must be as short as possible for interpreting the issue (avoid ranges over 5–10 lines; pick the most suitable subrange).
+* Line ranges must be as short as possible for interpreting the issue (avoid ranges over 5–10 lines; pick the most suitable subrange).
 * The code_location should overlap with the diff.
-* Do not generate a PR fix.
+* Do not generate a PR fix.

codex-rs/core/src/apply_patch.rs

@@ -61,7 +61,13 @@ pub(crate) async fn apply_patch(
             // that similar patches can be auto-approved in the future during
             // this session.
             let rx_approve = sess
-                .request_patch_approval(turn_context, call_id.to_owned(), &action, None, None)
+                .request_patch_approval(
+                    turn_context,
+                    call_id.to_owned(),
+                    convert_apply_patch_to_protocol(&action),
+                    None,
+                    None,
+                )
                 .await;
             match rx_approve.await.unwrap_or_default() {
                 ReviewDecision::Approved | ReviewDecision::ApprovedForSession => {

codex-rs/core/src/auth.rs

@@ -1,16 +1,14 @@
-use chrono::DateTime;
+mod storage;
+
 use chrono::Utc;
+use reqwest::StatusCode;
 use serde::Deserialize;
 use serde::Serialize;
 #[cfg(test)]
 use serial_test::serial;
 use std::env;
-use std::fs::File;
-use std::fs::OpenOptions;
-use std::io::Read;
-use std::io::Write;
-#[cfg(unix)]
-use std::os::unix::fs::OpenOptionsExt;
+use std::fmt::Debug;
+use std::io::ErrorKind;
 use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Arc;
@@ -20,10 +18,22 @@ use std::time::Duration;
 use codex_app_server_protocol::AuthMode;
 use codex_protocol::config_types::ForcedLoginMethod;
 
+pub use crate::auth::storage::AuthCredentialsStoreMode;
+pub use crate::auth::storage::AuthDotJson;
+use crate::auth::storage::AuthStorageBackend;
+use crate::auth::storage::create_auth_storage;
 use crate::config::Config;
-use crate::token_data::PlanType;
+use crate::default_client::CodexHttpClient;
+use crate::error::RefreshTokenFailedError;
+use crate::error::RefreshTokenFailedReason;
+use crate::token_data::KnownPlan as InternalKnownPlan;
+use crate::token_data::PlanType as InternalPlanType;
 use crate::token_data::TokenData;
 use crate::token_data::parse_id_token;
+use crate::util::try_parse_error_message;
+use codex_protocol::account::PlanType as AccountPlanType;
+use serde_json::Value;
+use thiserror::Error;
 
 #[derive(Debug, Clone)]
 pub struct CodexAuth {
@@ -31,8 +41,8 @@ pub struct CodexAuth {
 
     pub(crate) api_key: Option<String>,
     pub(crate) auth_dot_json: Arc<Mutex<Option<AuthDotJson>>>,
-    pub(crate) auth_file: PathBuf,
-    pub(crate) client: reqwest::Client,
+    storage: Arc<dyn AuthStorageBackend>,
+    pub(crate) client: CodexHttpClient,
 }
 
 impl PartialEq for CodexAuth {
@@ -41,24 +51,66 @@ impl PartialEq for CodexAuth {
     }
 }
 
+// TODO(pakrym): use token exp field to check for expiration instead
+const TOKEN_REFRESH_INTERVAL: i64 = 8;
+
+const REFRESH_TOKEN_EXPIRED_MESSAGE: &str = "Your access token could not be refreshed because your refresh token has expired. Please log out and sign in again.";
+const REFRESH_TOKEN_REUSED_MESSAGE: &str = "Your access token could not be refreshed because your refresh token was already used. Please log out and sign in again.";
+const REFRESH_TOKEN_INVALIDATED_MESSAGE: &str = "Your access token could not be refreshed because your refresh token was revoked. Please log out and sign in again.";
+const REFRESH_TOKEN_UNKNOWN_MESSAGE: &str =
+    "Your access token could not be refreshed. Please log out and sign in again.";
+const REFRESH_TOKEN_URL: &str = "https://auth.openai.com/oauth/token";
+pub const REFRESH_TOKEN_URL_OVERRIDE_ENV_VAR: &str = "CODEX_REFRESH_TOKEN_URL_OVERRIDE";
+
+#[derive(Debug, Error)]
+pub enum RefreshTokenError {
+    #[error("{0}")]
+    Permanent(#[from] RefreshTokenFailedError),
+    #[error(transparent)]
+    Transient(#[from] std::io::Error),
+}
+
+impl RefreshTokenError {
+    pub fn failed_reason(&self) -> Option<RefreshTokenFailedReason> {
+        match self {
+            Self::Permanent(error) => Some(error.reason),
+            Self::Transient(_) => None,
+        }
+    }
+
+    fn other_with_message(message: impl Into<String>) -> Self {
+        Self::Transient(std::io::Error::other(message.into()))
+    }
+}
+
+impl From<RefreshTokenError> for std::io::Error {
+    fn from(err: RefreshTokenError) -> Self {
+        match err {
+            RefreshTokenError::Permanent(failed) => std::io::Error::other(failed),
+            RefreshTokenError::Transient(inner) => inner,
+        }
+    }
+}
+
 impl CodexAuth {
-    pub async fn refresh_token(&self) -> Result<String, std::io::Error> {
-        let token_data = self
-            .get_current_token_data()
-            .ok_or(std::io::Error::other("Token data is not available."))?;
+    pub async fn refresh_token(&self) -> Result<String, RefreshTokenError> {
+        tracing::info!("Refreshing token");
+
+        let token_data = self.get_current_token_data().ok_or_else(|| {
+            RefreshTokenError::Transient(std::io::Error::other("Token data is not available."))
+        })?;
         let token = token_data.refresh_token;
 
-        let refresh_response = try_refresh_token(token, &self.client)
-            .await
-            .map_err(std::io::Error::other)?;
+        let refresh_response = try_refresh_token(token, &self.client).await?;
 
         let updated = update_tokens(
-            &self.auth_file,
+            &self.storage,
             refresh_response.id_token,
             refresh_response.access_token,
             refresh_response.refresh_token,
         )
-        .await?;
+        .await
+        .map_err(RefreshTokenError::from)?;
 
         if let Ok(mut auth_lock) = self.auth_dot_json.lock() {
             *auth_lock = Some(updated.clone());
@@ -67,7 +119,7 @@ impl CodexAuth {
         let access = match updated.tokens {
             Some(t) => t.access_token,
             None => {
-                return Err(std::io::Error::other(
+                return Err(RefreshTokenError::other_with_message(
                     "Token data is not available after refresh.",
                 ));
             }
@@ -75,9 +127,12 @@ impl CodexAuth {
         Ok(access)
     }
 
-    /// Loads the available auth information from the auth.json.
-    pub fn from_codex_home(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
-        load_auth(codex_home, false)
+    /// Loads the available auth information from auth storage.
+    pub fn from_auth_storage(
+        codex_home: &Path,
+        auth_credentials_store_mode: AuthCredentialsStoreMode,
+    ) -> std::io::Result<Option<CodexAuth>> {
+        load_auth(codex_home, false, auth_credentials_store_mode)
     }
 
     pub async fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
@@ -88,19 +143,25 @@ impl CodexAuth {
                 last_refresh: Some(last_refresh),
                 ..
             }) => {
-                if last_refresh < Utc::now() - chrono::Duration::days(28) {
-                    let refresh_response = tokio::time::timeout(
+                if last_refresh < Utc::now() - chrono::Duration::days(TOKEN_REFRESH_INTERVAL) {
+                    let refresh_result = tokio::time::timeout(
                         Duration::from_secs(60),
                         try_refresh_token(tokens.refresh_token.clone(), &self.client),
                     )
-                    .await
-                    .map_err(|_| {
-                        std::io::Error::other("timed out while refreshing OpenAI API key")
-                    })?
-                    .map_err(std::io::Error::other)?;
+                    .await;
+                    let refresh_response = match refresh_result {
+                        Ok(Ok(response)) => response,
+                        Ok(Err(err)) => return Err(err.into()),
+                        Err(_) => {
+                            return Err(std::io::Error::new(
+                                ErrorKind::TimedOut,
+                                "timed out while refreshing OpenAI API key",
+                            ));
+                        }
+                    };
 
                     let updated_auth_dot_json = update_tokens(
-                        &self.auth_file,
+                        &self.storage,
                         refresh_response.id_token,
                         refresh_response.access_token,
                         refresh_response.refresh_token,
@@ -143,7 +204,42 @@ impl CodexAuth {
         self.get_current_token_data().and_then(|t| t.id_token.email)
     }
 
-    pub(crate) fn get_plan_type(&self) -> Option<PlanType> {
+    /// Account-facing plan classification derived from the current token.
+    /// Returns a high-level `AccountPlanType` (e.g., Free/Plus/Pro/Team/…)
+    /// mapped from the ID token's internal plan value. Prefer this when you
+    /// need to make UI or product decisions based on the user's subscription.
+    pub fn account_plan_type(&self) -> Option<AccountPlanType> {
+        let map_known = |kp: &InternalKnownPlan| match kp {
+            InternalKnownPlan::Free => AccountPlanType::Free,
+            InternalKnownPlan::Plus => AccountPlanType::Plus,
+            InternalKnownPlan::Pro => AccountPlanType::Pro,
+            InternalKnownPlan::Team => AccountPlanType::Team,
+            InternalKnownPlan::Business => AccountPlanType::Business,
+            InternalKnownPlan::Enterprise => AccountPlanType::Enterprise,
+            InternalKnownPlan::Edu => AccountPlanType::Edu,
+        };
+
+        self.get_current_token_data()
+            .and_then(|t| t.id_token.chatgpt_plan_type)
+            .map(|pt| match pt {
+                InternalPlanType::Known(k) => map_known(&k),
+                InternalPlanType::Unknown(_) => AccountPlanType::Unknown,
+            })
+    }
+
+    /// Raw plan string from the ID token (including unknown/new plan types).
+    pub fn raw_plan_type(&self) -> Option<String> {
+        self.get_plan_type().map(|plan| match plan {
+            InternalPlanType::Known(k) => format!("{k:?}"),
+            InternalPlanType::Unknown(raw) => raw,
+        })
+    }
+
+    /// Raw internal plan value from the ID token.
+    /// Exposes the underlying `token_data::PlanType` without mapping it to the
+    /// public `AccountPlanType`. Use this when downstream code needs to inspect
+    /// internal/unknown plan strings exactly as issued in the token.
+    pub(crate) fn get_plan_type(&self) -> Option<InternalPlanType> {
         self.get_current_token_data()
             .and_then(|t| t.id_token.chatgpt_plan_type)
     }
@@ -174,17 +270,17 @@ impl CodexAuth {
         Self {
             api_key: None,
             mode: AuthMode::ChatGPT,
-            auth_file: PathBuf::new(),
+            storage: create_auth_storage(PathBuf::new(), AuthCredentialsStoreMode::File),
             auth_dot_json,
             client: crate::default_client::create_client(),
         }
     }
 
-    fn from_api_key_with_client(api_key: &str, client: reqwest::Client) -> Self {
+    fn from_api_key_with_client(api_key: &str, client: CodexHttpClient) -> Self {
         Self {
             api_key: Some(api_key.to_owned()),
             mode: AuthMode::ApiKey,
-            auth_file: PathBuf::new(),
+            storage: create_auth_storage(PathBuf::new(), AuthCredentialsStoreMode::File),
             auth_dot_json: Arc::new(Mutex::new(None)),
             client,
         }
@@ -212,33 +308,60 @@ pub fn read_codex_api_key_from_env() -> Option<String> {
         .filter(|value| !value.is_empty())
 }
 
-pub fn get_auth_file(codex_home: &Path) -> PathBuf {
-    codex_home.join("auth.json")
-}
-
 /// Delete the auth.json file inside `codex_home` if it exists. Returns `Ok(true)`
 /// if a file was removed, `Ok(false)` if no auth file was present.
-pub fn logout(codex_home: &Path) -> std::io::Result<bool> {
-    let auth_file = get_auth_file(codex_home);
-    match std::fs::remove_file(&auth_file) {
-        Ok(_) => Ok(true),
-        Err(err) if err.kind() == std::io::ErrorKind::NotFound => Ok(false),
-        Err(err) => Err(err),
-    }
+pub fn logout(
+    codex_home: &Path,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> std::io::Result<bool> {
+    let storage = create_auth_storage(codex_home.to_path_buf(), auth_credentials_store_mode);
+    storage.delete()
 }
 
 /// Writes an `auth.json` that contains only the API key.
-pub fn login_with_api_key(codex_home: &Path, api_key: &str) -> std::io::Result<()> {
+pub fn login_with_api_key(
+    codex_home: &Path,
+    api_key: &str,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> std::io::Result<()> {
     let auth_dot_json = AuthDotJson {
         openai_api_key: Some(api_key.to_string()),
         tokens: None,
         last_refresh: None,
     };
-    write_auth_json(&get_auth_file(codex_home), &auth_dot_json)
+    save_auth(codex_home, &auth_dot_json, auth_credentials_store_mode)
+}
+
+/// Persist the provided auth payload using the specified backend.
+pub fn save_auth(
+    codex_home: &Path,
+    auth: &AuthDotJson,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> std::io::Result<()> {
+    let storage = create_auth_storage(codex_home.to_path_buf(), auth_credentials_store_mode);
+    storage.save(auth)
+}
+
+/// Load CLI auth data using the configured credential store backend.
+/// Returns `None` when no credentials are stored. This function is
+/// provided only for tests. Production code should not directly load
+/// from the auth.json storage. It should use the AuthManager abstraction
+/// instead.
+pub fn load_auth_dot_json(
+    codex_home: &Path,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> std::io::Result<Option<AuthDotJson>> {
+    let storage = create_auth_storage(codex_home.to_path_buf(), auth_credentials_store_mode);
+    storage.load()
 }
 
 pub async fn enforce_login_restrictions(config: &Config) -> std::io::Result<()> {
-    let Some(auth) = load_auth(&config.codex_home, true)? else {
+    let Some(auth) = load_auth(
+        &config.codex_home,
+        true,
+        config.cli_auth_credentials_store_mode,
+    )?
+    else {
         return Ok(());
     };
 
@@ -257,7 +380,11 @@ pub async fn enforce_login_restrictions(config: &Config) -> std::io::Result<()>
         };
 
         if let Some(message) = method_violation {
-            return logout_with_message(&config.codex_home, message);
+            return logout_with_message(
+                &config.codex_home,
+                message,
+                config.cli_auth_credentials_store_mode,
+            );
         }
     }
 
@@ -274,6 +401,7 @@ pub async fn enforce_login_restrictions(config: &Config) -> std::io::Result<()>
                     format!(
                         "Failed to load ChatGPT credentials while enforcing workspace restrictions: {err}. Logging out."
                     ),
+                    config.cli_auth_credentials_store_mode,
                 );
             }
         };
@@ -289,15 +417,23 @@ pub async fn enforce_login_restrictions(config: &Config) -> std::io::Result<()>
                     "Login is restricted to workspace {expected_account_id}, but current credentials lack a workspace identifier. Logging out."
                 ),
             };
-            return logout_with_message(&config.codex_home, message);
+            return logout_with_message(
+                &config.codex_home,
+                message,
+                config.cli_auth_credentials_store_mode,
+            );
         }
     }
 
     Ok(())
 }
 
-fn logout_with_message(codex_home: &Path, message: String) -> std::io::Result<()> {
-    match logout(codex_home) {
+fn logout_with_message(
+    codex_home: &Path,
+    message: String,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> std::io::Result<()> {
+    match logout(codex_home, auth_credentials_store_mode) {
         Ok(_) => Err(std::io::Error::other(message)),
         Err(err) => Err(std::io::Error::other(format!(
             "{message}. Failed to remove auth.json: {err}"
@@ -308,6 +444,7 @@ fn logout_with_message(codex_home: &Path, message: String) -> std::io::Result<()
 fn load_auth(
     codex_home: &Path,
     enable_codex_api_key_env: bool,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
 ) -> std::io::Result<Option<CodexAuth>> {
     if enable_codex_api_key_env && let Some(api_key) = read_codex_api_key_from_env() {
         let client = crate::default_client::create_client();
@@ -317,12 +454,12 @@ fn load_auth(
         )));
     }
 
-    let auth_file = get_auth_file(codex_home);
+    let storage = create_auth_storage(codex_home.to_path_buf(), auth_credentials_store_mode);
+
     let client = crate::default_client::create_client();
-    let auth_dot_json = match try_read_auth_json(&auth_file) {
-        Ok(auth) => auth,
-        Err(err) if err.kind() == std::io::ErrorKind::NotFound => return Ok(None),
-        Err(err) => return Err(err),
+    let auth_dot_json = match storage.load()? {
+        Some(auth) => auth,
+        None => return Ok(None),
     };
 
     let AuthDotJson {
@@ -339,7 +476,7 @@ fn load_auth(
     Ok(Some(CodexAuth {
         api_key: None,
         mode: AuthMode::ChatGPT,
-        auth_file,
+        storage: storage.clone(),
         auth_dot_json: Arc::new(Mutex::new(Some(AuthDotJson {
             openai_api_key: None,
             tokens,
@@ -349,44 +486,20 @@ fn load_auth(
     }))
 }
 
-/// Attempt to read and refresh the `auth.json` file in the given `CODEX_HOME` directory.
-/// Returns the full AuthDotJson structure after refreshing if necessary.
-pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
-    let mut file = File::open(auth_file)?;
-    let mut contents = String::new();
-    file.read_to_string(&mut contents)?;
-    let auth_dot_json: AuthDotJson = serde_json::from_str(&contents)?;
-
-    Ok(auth_dot_json)
-}
-
-pub fn write_auth_json(auth_file: &Path, auth_dot_json: &AuthDotJson) -> std::io::Result<()> {
-    if let Some(parent) = auth_file.parent() {
-        std::fs::create_dir_all(parent)?;
-    }
-    let json_data = serde_json::to_string_pretty(auth_dot_json)?;
-    let mut options = OpenOptions::new();
-    options.truncate(true).write(true).create(true);
-    #[cfg(unix)]
-    {
-        options.mode(0o600);
-    }
-    let mut file = options.open(auth_file)?;
-    file.write_all(json_data.as_bytes())?;
-    file.flush()?;
-    Ok(())
-}
-
 async fn update_tokens(
-    auth_file: &Path,
-    id_token: String,
+    storage: &Arc<dyn AuthStorageBackend>,
+    id_token: Option<String>,
     access_token: Option<String>,
     refresh_token: Option<String>,
 ) -> std::io::Result<AuthDotJson> {
-    let mut auth_dot_json = try_read_auth_json(auth_file)?;
+    let mut auth_dot_json = storage
+        .load()?
+        .ok_or(std::io::Error::other("Token data is not available."))?;
 
     let tokens = auth_dot_json.tokens.get_or_insert_with(TokenData::default);
-    tokens.id_token = parse_id_token(&id_token).map_err(std::io::Error::other)?;
+    if let Some(id_token) = id_token {
+        tokens.id_token = parse_id_token(&id_token).map_err(std::io::Error::other)?;
+    }
     if let Some(access_token) = access_token {
         tokens.access_token = access_token;
     }
@@ -394,14 +507,14 @@ async fn update_tokens(
         tokens.refresh_token = refresh_token;
     }
     auth_dot_json.last_refresh = Some(Utc::now());
-    write_auth_json(auth_file, &auth_dot_json)?;
+    storage.save(&auth_dot_json)?;
     Ok(auth_dot_json)
 }
 
 async fn try_refresh_token(
     refresh_token: String,
-    client: &reqwest::Client,
-) -> std::io::Result<RefreshResponse> {
+    client: &CodexHttpClient,
+) -> Result<RefreshResponse, RefreshTokenError> {
     let refresh_request = RefreshRequest {
         client_id: CLIENT_ID,
         grant_type: "refresh_token",
@@ -409,29 +522,93 @@ async fn try_refresh_token(
         scope: "openid profile email",
     };
 
+    let endpoint = refresh_token_endpoint();
+
     // Use shared client factory to include standard headers
     let response = client
-        .post("https://auth.openai.com/oauth/token")
+        .post(endpoint.as_str())
         .header("Content-Type", "application/json")
         .json(&refresh_request)
         .send()
         .await
-        .map_err(std::io::Error::other)?;
+        .map_err(|err| RefreshTokenError::Transient(std::io::Error::other(err)))?;
 
-    if response.status().is_success() {
+    let status = response.status();
+    if status.is_success() {
         let refresh_response = response
             .json::<RefreshResponse>()
             .await
-            .map_err(std::io::Error::other)?;
+            .map_err(|err| RefreshTokenError::Transient(std::io::Error::other(err)))?;
         Ok(refresh_response)
     } else {
-        Err(std::io::Error::other(format!(
-            "Failed to refresh token: {}",
-            response.status()
-        )))
+        let body = response.text().await.unwrap_or_default();
+        if status == StatusCode::UNAUTHORIZED {
+            let failed = classify_refresh_token_failure(&body);
+            Err(RefreshTokenError::Permanent(failed))
+        } else {
+            let message = try_parse_error_message(&body);
+            Err(RefreshTokenError::Transient(std::io::Error::other(
+                format!("Failed to refresh token: {status}: {message}"),
+            )))
+        }
     }
 }
 
+fn classify_refresh_token_failure(body: &str) -> RefreshTokenFailedError {
+    let code = extract_refresh_token_error_code(body);
+
+    let normalized_code = code.as_deref().map(str::to_ascii_lowercase);
+    let reason = match normalized_code.as_deref() {
+        Some("refresh_token_expired") => RefreshTokenFailedReason::Expired,
+        Some("refresh_token_reused") => RefreshTokenFailedReason::Exhausted,
+        Some("refresh_token_invalidated") => RefreshTokenFailedReason::Revoked,
+        _ => RefreshTokenFailedReason::Other,
+    };
+
+    if reason == RefreshTokenFailedReason::Other {
+        tracing::warn!(
+            backend_code = normalized_code.as_deref(),
+            backend_body = body,
+            "Encountered unknown 401 response while refreshing token"
+        );
+    }
+
+    let message = match reason {
+        RefreshTokenFailedReason::Expired => REFRESH_TOKEN_EXPIRED_MESSAGE.to_string(),
+        RefreshTokenFailedReason::Exhausted => REFRESH_TOKEN_REUSED_MESSAGE.to_string(),
+        RefreshTokenFailedReason::Revoked => REFRESH_TOKEN_INVALIDATED_MESSAGE.to_string(),
+        RefreshTokenFailedReason::Other => REFRESH_TOKEN_UNKNOWN_MESSAGE.to_string(),
+    };
+
+    RefreshTokenFailedError::new(reason, message)
+}
+
+fn extract_refresh_token_error_code(body: &str) -> Option<String> {
+    if body.trim().is_empty() {
+        return None;
+    }
+
+    let Value::Object(map) = serde_json::from_str::<Value>(body).ok()? else {
+        return None;
+    };
+
+    if let Some(error_value) = map.get("error") {
+        match error_value {
+            Value::Object(obj) => {
+                if let Some(code) = obj.get("code").and_then(Value::as_str) {
+                    return Some(code.to_string());
+                }
+            }
+            Value::String(code) => {
+                return Some(code.to_string());
+            }
+            _ => {}
+        }
+    }
+
+    map.get("code").and_then(Value::as_str).map(str::to_string)
+}
+
 #[derive(Serialize)]
 struct RefreshRequest {
     client_id: &'static str,
@@ -442,27 +619,19 @@ struct RefreshRequest {
 
 #[derive(Deserialize, Clone)]
 struct RefreshResponse {
-    id_token: String,
+    id_token: Option<String>,
     access_token: Option<String>,
     refresh_token: Option<String>,
 }
 
-/// Expected structure for $CODEX_HOME/auth.json.
-#[derive(Deserialize, Serialize, Clone, Debug, PartialEq)]
-pub struct AuthDotJson {
-    #[serde(rename = "OPENAI_API_KEY")]
-    pub openai_api_key: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub tokens: Option<TokenData>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub last_refresh: Option<DateTime<Utc>>,
-}
-
 // Shared constant for token refresh (client id used for oauth token refresh flow)
 pub const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
 
+fn refresh_token_endpoint() -> String {
+    std::env::var(REFRESH_TOKEN_URL_OVERRIDE_ENV_VAR)
+        .unwrap_or_else(|_| REFRESH_TOKEN_URL.to_string())
+}
+
 use std::sync::RwLock;
 
 /// Internal cached auth state.
@@ -474,12 +643,16 @@ struct CachedAuth {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::auth::storage::FileAuthStorage;
+    use crate::auth::storage::get_auth_file;
     use crate::config::Config;
     use crate::config::ConfigOverrides;
     use crate::config::ConfigToml;
     use crate::token_data::IdTokenInfo;
-    use crate::token_data::KnownPlan;
-    use crate::token_data::PlanType;
+    use crate::token_data::KnownPlan as InternalKnownPlan;
+    use crate::token_data::PlanType as InternalPlanType;
+    use codex_protocol::account::PlanType as AccountPlanType;
+
     use base64::Engine;
     use codex_protocol::config_types::ForcedLoginMethod;
     use pretty_assertions::assert_eq;
@@ -488,9 +661,9 @@ mod tests {
     use tempfile::tempdir;
 
     #[tokio::test]
-    async fn roundtrip_auth_dot_json() {
+    async fn refresh_without_id_token() {
         let codex_home = tempdir().unwrap();
-        let _ = write_auth_file(
+        let fake_jwt = write_auth_file(
             AuthFileParams {
                 openai_api_key: None,
                 chatgpt_plan_type: "pro".to_string(),
@@ -500,12 +673,23 @@ mod tests {
         )
         .expect("failed to write auth file");
 
-        let file = get_auth_file(codex_home.path());
-        let auth_dot_json = try_read_auth_json(&file).unwrap();
-        write_auth_json(&file, &auth_dot_json).unwrap();
+        let storage = create_auth_storage(
+            codex_home.path().to_path_buf(),
+            AuthCredentialsStoreMode::File,
+        );
+        let updated = super::update_tokens(
+            &storage,
+            None,
+            Some("new-access-token".to_string()),
+            Some("new-refresh-token".to_string()),
+        )
+        .await
+        .expect("update_tokens should succeed");
 
-        let same_auth_dot_json = try_read_auth_json(&file).unwrap();
-        assert_eq!(auth_dot_json, same_auth_dot_json);
+        let tokens = updated.tokens.expect("tokens should exist");
+        assert_eq!(tokens.id_token.raw_jwt, fake_jwt);
+        assert_eq!(tokens.access_token, "new-access-token");
+        assert_eq!(tokens.refresh_token, "new-refresh-token");
     }
 
     #[test]
@@ -527,9 +711,13 @@ mod tests {
         )
         .unwrap();
 
-        super::login_with_api_key(dir.path(), "sk-new").expect("login_with_api_key should succeed");
+        super::login_with_api_key(dir.path(), "sk-new", AuthCredentialsStoreMode::File)
+            .expect("login_with_api_key should succeed");
 
-        let auth = super::try_read_auth_json(&auth_path).expect("auth.json should parse");
+        let storage = FileAuthStorage::new(dir.path().to_path_buf());
+        let auth = storage
+            .try_read_auth_json(&auth_path)
+            .expect("auth.json should parse");
         assert_eq!(auth.openai_api_key.as_deref(), Some("sk-new"));
         assert!(auth.tokens.is_none(), "tokens should be cleared");
     }
@@ -537,7 +725,8 @@ mod tests {
     #[test]
     fn missing_auth_json_returns_none() {
         let dir = tempdir().unwrap();
-        let auth = CodexAuth::from_codex_home(dir.path()).expect("call should succeed");
+        let auth = CodexAuth::from_auth_storage(dir.path(), AuthCredentialsStoreMode::File)
+            .expect("call should succeed");
         assert_eq!(auth, None);
     }
 
@@ -559,9 +748,11 @@ mod tests {
             api_key,
             mode,
             auth_dot_json,
-            auth_file: _,
+            storage: _,
             ..
-        } = super::load_auth(codex_home.path(), false).unwrap().unwrap();
+        } = super::load_auth(codex_home.path(), false, AuthCredentialsStoreMode::File)
+            .unwrap()
+            .unwrap();
         assert_eq!(None, api_key);
         assert_eq!(AuthMode::ChatGPT, mode);
 
@@ -577,7 +768,7 @@ mod tests {
                 tokens: Some(TokenData {
                     id_token: IdTokenInfo {
                         email: Some("user@example.com".to_string()),
-                        chatgpt_plan_type: Some(PlanType::Known(KnownPlan::Pro)),
+                        chatgpt_plan_type: Some(InternalPlanType::Known(InternalKnownPlan::Pro)),
                         chatgpt_account_id: None,
                         raw_jwt: fake_jwt,
                     },
@@ -602,7 +793,9 @@ mod tests {
         )
         .unwrap();
 
-        let auth = super::load_auth(dir.path(), false).unwrap().unwrap();
+        let auth = super::load_auth(dir.path(), false, AuthCredentialsStoreMode::File)
+            .unwrap()
+            .unwrap();
         assert_eq!(auth.mode, AuthMode::ApiKey);
         assert_eq!(auth.api_key, Some("sk-test-key".to_string()));
 
@@ -617,11 +810,11 @@ mod tests {
             tokens: None,
             last_refresh: None,
         };
-        write_auth_json(&get_auth_file(dir.path()), &auth_dot_json)?;
-        assert!(dir.path().join("auth.json").exists());
-        let removed = logout(dir.path())?;
-        assert!(removed);
-        assert!(!dir.path().join("auth.json").exists());
+        super::save_auth(dir.path(), &auth_dot_json, AuthCredentialsStoreMode::File)?;
+        let auth_file = get_auth_file(dir.path());
+        assert!(auth_file.exists());
+        assert!(logout(dir.path(), AuthCredentialsStoreMode::File)?);
+        assert!(!auth_file.exists());
         Ok(())
     }
 
@@ -729,7 +922,8 @@ mod tests {
     #[tokio::test]
     async fn enforce_login_restrictions_logs_out_for_method_mismatch() {
         let codex_home = tempdir().unwrap();
-        login_with_api_key(codex_home.path(), "sk-test").expect("seed api key");
+        login_with_api_key(codex_home.path(), "sk-test", AuthCredentialsStoreMode::File)
+            .expect("seed api key");
 
         let config = build_config(codex_home.path(), Some(ForcedLoginMethod::Chatgpt), None);
 
@@ -798,7 +992,8 @@ mod tests {
     async fn enforce_login_restrictions_allows_api_key_if_login_method_not_set_but_forced_chatgpt_workspace_id_is_set()
      {
         let codex_home = tempdir().unwrap();
-        login_with_api_key(codex_home.path(), "sk-test").expect("seed api key");
+        login_with_api_key(codex_home.path(), "sk-test", AuthCredentialsStoreMode::File)
+            .expect("seed api key");
 
         let config = build_config(codex_home.path(), None, Some("org_mine".to_string()));
 
@@ -827,6 +1022,54 @@ mod tests {
                 .contains("ChatGPT login is required, but an API key is currently being used.")
         );
     }
+
+    #[test]
+    fn plan_type_maps_known_plan() {
+        let codex_home = tempdir().unwrap();
+        let _jwt = write_auth_file(
+            AuthFileParams {
+                openai_api_key: None,
+                chatgpt_plan_type: "pro".to_string(),
+                chatgpt_account_id: None,
+            },
+            codex_home.path(),
+        )
+        .expect("failed to write auth file");
+
+        let auth = super::load_auth(codex_home.path(), false, AuthCredentialsStoreMode::File)
+            .expect("load auth")
+            .expect("auth available");
+
+        pretty_assertions::assert_eq!(auth.account_plan_type(), Some(AccountPlanType::Pro));
+        pretty_assertions::assert_eq!(
+            auth.get_plan_type(),
+            Some(InternalPlanType::Known(InternalKnownPlan::Pro))
+        );
+    }
+
+    #[test]
+    fn plan_type_maps_unknown_to_unknown() {
+        let codex_home = tempdir().unwrap();
+        let _jwt = write_auth_file(
+            AuthFileParams {
+                openai_api_key: None,
+                chatgpt_plan_type: "mystery-tier".to_string(),
+                chatgpt_account_id: None,
+            },
+            codex_home.path(),
+        )
+        .expect("failed to write auth file");
+
+        let auth = super::load_auth(codex_home.path(), false, AuthCredentialsStoreMode::File)
+            .expect("load auth")
+            .expect("auth available");
+
+        pretty_assertions::assert_eq!(auth.account_plan_type(), Some(AccountPlanType::Unknown));
+        pretty_assertions::assert_eq!(
+            auth.get_plan_type(),
+            Some(InternalPlanType::Unknown("mystery-tier".to_string()))
+        );
+    }
 }
 
 /// Central manager providing a single source of truth for auth.json derived
@@ -842,6 +1085,7 @@ pub struct AuthManager {
     codex_home: PathBuf,
     inner: RwLock<CachedAuth>,
     enable_codex_api_key_env: bool,
+    auth_credentials_store_mode: AuthCredentialsStoreMode,
 }
 
 impl AuthManager {
@@ -849,14 +1093,23 @@ impl AuthManager {
     /// preferred auth method. Errors loading auth are swallowed; `auth()` will
     /// simply return `None` in that case so callers can treat it as an
     /// unauthenticated state.
-    pub fn new(codex_home: PathBuf, enable_codex_api_key_env: bool) -> Self {
-        let auth = load_auth(&codex_home, enable_codex_api_key_env)
-            .ok()
-            .flatten();
+    pub fn new(
+        codex_home: PathBuf,
+        enable_codex_api_key_env: bool,
+        auth_credentials_store_mode: AuthCredentialsStoreMode,
+    ) -> Self {
+        let auth = load_auth(
+            &codex_home,
+            enable_codex_api_key_env,
+            auth_credentials_store_mode,
+        )
+        .ok()
+        .flatten();
         Self {
             codex_home,
             inner: RwLock::new(CachedAuth { auth }),
             enable_codex_api_key_env,
+            auth_credentials_store_mode,
         }
     }
 
@@ -867,6 +1120,7 @@ impl AuthManager {
             codex_home: PathBuf::new(),
             inner: RwLock::new(cached),
             enable_codex_api_key_env: false,
+            auth_credentials_store_mode: AuthCredentialsStoreMode::File,
         })
     }
 
@@ -878,9 +1132,13 @@ impl AuthManager {
     /// Force a reload of the auth information from auth.json. Returns
     /// whether the auth value changed.
     pub fn reload(&self) -> bool {
-        let new_auth = load_auth(&self.codex_home, self.enable_codex_api_key_env)
-            .ok()
-            .flatten();
+        let new_auth = load_auth(
+            &self.codex_home,
+            self.enable_codex_api_key_env,
+            self.auth_credentials_store_mode,
+        )
+        .ok()
+        .flatten();
         if let Ok(mut guard) = self.inner.write() {
             let changed = !AuthManager::auths_equal(&guard.auth, &new_auth);
             guard.auth = new_auth;
@@ -899,13 +1157,23 @@ impl AuthManager {
     }
 
     /// Convenience constructor returning an `Arc` wrapper.
-    pub fn shared(codex_home: PathBuf, enable_codex_api_key_env: bool) -> Arc<Self> {
-        Arc::new(Self::new(codex_home, enable_codex_api_key_env))
+    pub fn shared(
+        codex_home: PathBuf,
+        enable_codex_api_key_env: bool,
+        auth_credentials_store_mode: AuthCredentialsStoreMode,
+    ) -> Arc<Self> {
+        Arc::new(Self::new(
+            codex_home,
+            enable_codex_api_key_env,
+            auth_credentials_store_mode,
+        ))
     }
 
     /// Attempt to refresh the current auth token (if any). On success, reload
     /// the auth state from disk so other components observe refreshed token.
-    pub async fn refresh_token(&self) -> std::io::Result<Option<String>> {
+    /// If the token refresh fails in a permanent (non‑transient) way, logs out
+    /// to clear invalid auth state.
+    pub async fn refresh_token(&self) -> Result<Option<String>, RefreshTokenError> {
         let auth = match self.auth() {
             Some(a) => a,
             None => return Ok(None),
@@ -916,7 +1184,10 @@ impl AuthManager {
                 self.reload();
                 Ok(Some(token))
             }
-            Err(e) => Err(e),
+            Err(e) => {
+                tracing::error!("Failed to refresh token: {}", e);
+                Err(e)
+            }
         }
     }
 
@@ -925,7 +1196,7 @@ impl AuthManager {
     /// reloads the in‑memory auth cache so callers immediately observe the
     /// unauthenticated state.
     pub fn logout(&self) -> std::io::Result<bool> {
-        let removed = super::auth::logout(&self.codex_home)?;
+        let removed = super::auth::logout(&self.codex_home, self.auth_credentials_store_mode)?;
         // Always reload to clear any cached auth (even if file absent).
         self.reload();
         Ok(removed)