Merge branch 'fix-timeout' of https://github.com/openai/codex into fix-timeout

.codespellignore

@@ -1,3 +1 @@
 iTerm
-iTerm2
-psuedo

.codespellrc

@@ -3,4 +3,4 @@
 skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl,frame*.txt
 check-hidden = true
 ignore-regex = ^\s*"image/\S+": ".*|\b(afterAll)\b
-ignore-words-list = ratatui,ser,iTerm,iterm2,iterm
+ignore-words-list = ratatui,ser

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

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

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

@@ -1,246 +0,0 @@
-name: macos-code-sign
-description: Configure, sign, notarize, and clean up macOS code signing artifacts.
-inputs:
-  target:
-    description: Rust compilation target triple (e.g. aarch64-apple-darwin).
-    required: true
-  sign-binaries:
-    description: Whether to sign and notarize the macOS binaries.
-    required: false
-    default: "true"
-  sign-dmg:
-    description: Whether to sign and notarize the macOS dmg.
-    required: false
-    default: "true"
-  apple-certificate:
-    description: Base64-encoded Apple signing certificate (P12).
-    required: true
-  apple-certificate-password:
-    description: Password for the signing certificate.
-    required: true
-  apple-notarization-key-p8:
-    description: Base64-encoded Apple notarization key (P8).
-    required: true
-  apple-notarization-key-id:
-    description: Apple notarization key ID.
-    required: true
-  apple-notarization-issuer-id:
-    description: Apple notarization issuer ID.
-    required: true
-runs:
-  using: composite
-  steps:
-    - name: Configure Apple code signing
-      shell: bash
-      env:
-        KEYCHAIN_PASSWORD: actions
-        APPLE_CERTIFICATE: ${{ inputs.apple-certificate }}
-        APPLE_CERTIFICATE_PASSWORD: ${{ inputs.apple-certificate-password }}
-      run: |
-        set -euo pipefail
-
-        if [[ -z "${APPLE_CERTIFICATE:-}" ]]; then
-          echo "APPLE_CERTIFICATE is required for macOS signing"
-          exit 1
-        fi
-
-        if [[ -z "${APPLE_CERTIFICATE_PASSWORD:-}" ]]; then
-          echo "APPLE_CERTIFICATE_PASSWORD is required for macOS signing"
-          exit 1
-        fi
-
-        cert_path="${RUNNER_TEMP}/apple_signing_certificate.p12"
-        echo "$APPLE_CERTIFICATE" | base64 -d > "$cert_path"
-
-        keychain_path="${RUNNER_TEMP}/codex-signing.keychain-db"
-        security create-keychain -p "$KEYCHAIN_PASSWORD" "$keychain_path"
-        security set-keychain-settings -lut 21600 "$keychain_path"
-        security unlock-keychain -p "$KEYCHAIN_PASSWORD" "$keychain_path"
-
-        keychain_args=()
-        cleanup_keychain() {
-          if ((${#keychain_args[@]} > 0)); then
-            security list-keychains -s "${keychain_args[@]}" || true
-            security default-keychain -s "${keychain_args[0]}" || true
-          else
-            security list-keychains -s || true
-          fi
-          if [[ -f "$keychain_path" ]]; then
-            security delete-keychain "$keychain_path" || true
-          fi
-        }
-
-        while IFS= read -r keychain; do
-          [[ -n "$keychain" ]] && keychain_args+=("$keychain")
-        done < <(security list-keychains | sed 's/^[[:space:]]*//;s/[[:space:]]*$//;s/"//g')
-
-        if ((${#keychain_args[@]} > 0)); then
-          security list-keychains -s "$keychain_path" "${keychain_args[@]}"
-        else
-          security list-keychains -s "$keychain_path"
-        fi
-
-        security default-keychain -s "$keychain_path"
-        security import "$cert_path" -k "$keychain_path" -P "$APPLE_CERTIFICATE_PASSWORD" -T /usr/bin/codesign -T /usr/bin/security
-        security set-key-partition-list -S apple-tool:,apple: -s -k "$KEYCHAIN_PASSWORD" "$keychain_path" > /dev/null
-
-        codesign_hashes=()
-        while IFS= read -r hash; do
-          [[ -n "$hash" ]] && codesign_hashes+=("$hash")
-        done < <(security find-identity -v -p codesigning "$keychain_path" \
-          | sed -n 's/.*\([0-9A-F]\{40\}\).*/\1/p' \
-          | sort -u)
-
-        if ((${#codesign_hashes[@]} == 0)); then
-          echo "No signing identities found in $keychain_path"
-          cleanup_keychain
-          rm -f "$cert_path"
-          exit 1
-        fi
-
-        if ((${#codesign_hashes[@]} > 1)); then
-          echo "Multiple signing identities found in $keychain_path:"
-          printf '  %s\n' "${codesign_hashes[@]}"
-          cleanup_keychain
-          rm -f "$cert_path"
-          exit 1
-        fi
-
-        APPLE_CODESIGN_IDENTITY="${codesign_hashes[0]}"
-
-        rm -f "$cert_path"
-
-        echo "APPLE_CODESIGN_IDENTITY=$APPLE_CODESIGN_IDENTITY" >> "$GITHUB_ENV"
-        echo "APPLE_CODESIGN_KEYCHAIN=$keychain_path" >> "$GITHUB_ENV"
-        echo "::add-mask::$APPLE_CODESIGN_IDENTITY"
-
-    - name: Sign macOS binaries
-      if: ${{ inputs.sign-binaries == 'true' }}
-      shell: bash
-      run: |
-        set -euo pipefail
-
-        if [[ -z "${APPLE_CODESIGN_IDENTITY:-}" ]]; then
-          echo "APPLE_CODESIGN_IDENTITY is required for macOS signing"
-          exit 1
-        fi
-
-        keychain_args=()
-        if [[ -n "${APPLE_CODESIGN_KEYCHAIN:-}" && -f "${APPLE_CODESIGN_KEYCHAIN}" ]]; then
-          keychain_args+=(--keychain "${APPLE_CODESIGN_KEYCHAIN}")
-        fi
-
-        for binary in codex codex-responses-api-proxy; do
-          path="codex-rs/target/${{ inputs.target }}/release/${binary}"
-          codesign --force --options runtime --timestamp --sign "$APPLE_CODESIGN_IDENTITY" "${keychain_args[@]}" "$path"
-        done
-
-    - name: Notarize macOS binaries
-      if: ${{ inputs.sign-binaries == 'true' }}
-      shell: bash
-      env:
-        APPLE_NOTARIZATION_KEY_P8: ${{ inputs.apple-notarization-key-p8 }}
-        APPLE_NOTARIZATION_KEY_ID: ${{ inputs.apple-notarization-key-id }}
-        APPLE_NOTARIZATION_ISSUER_ID: ${{ inputs.apple-notarization-issuer-id }}
-      run: |
-        set -euo pipefail
-
-        for var in APPLE_NOTARIZATION_KEY_P8 APPLE_NOTARIZATION_KEY_ID APPLE_NOTARIZATION_ISSUER_ID; do
-          if [[ -z "${!var:-}" ]]; then
-            echo "$var is required for notarization"
-            exit 1
-          fi
-        done
-
-        notary_key_path="${RUNNER_TEMP}/notarytool.key.p8"
-        echo "$APPLE_NOTARIZATION_KEY_P8" | base64 -d > "$notary_key_path"
-        cleanup_notary() {
-          rm -f "$notary_key_path"
-        }
-        trap cleanup_notary EXIT
-
-        source "$GITHUB_ACTION_PATH/notary_helpers.sh"
-
-        notarize_binary() {
-          local binary="$1"
-          local source_path="codex-rs/target/${{ inputs.target }}/release/${binary}"
-          local archive_path="${RUNNER_TEMP}/${binary}.zip"
-
-          if [[ ! -f "$source_path" ]]; then
-            echo "Binary $source_path not found"
-            exit 1
-          fi
-
-          rm -f "$archive_path"
-          ditto -c -k --keepParent "$source_path" "$archive_path"
-
-          notarize_submission "$binary" "$archive_path" "$notary_key_path"
-        }
-
-        notarize_binary "codex"
-        notarize_binary "codex-responses-api-proxy"
-
-    - name: Sign and notarize macOS dmg
-      if: ${{ inputs.sign-dmg == 'true' }}
-      shell: bash
-      env:
-        APPLE_NOTARIZATION_KEY_P8: ${{ inputs.apple-notarization-key-p8 }}
-        APPLE_NOTARIZATION_KEY_ID: ${{ inputs.apple-notarization-key-id }}
-        APPLE_NOTARIZATION_ISSUER_ID: ${{ inputs.apple-notarization-issuer-id }}
-      run: |
-        set -euo pipefail
-
-        for var in APPLE_CODESIGN_IDENTITY APPLE_NOTARIZATION_KEY_P8 APPLE_NOTARIZATION_KEY_ID APPLE_NOTARIZATION_ISSUER_ID; do
-          if [[ -z "${!var:-}" ]]; then
-            echo "$var is required"
-            exit 1
-          fi
-        done
-
-        notary_key_path="${RUNNER_TEMP}/notarytool.key.p8"
-        echo "$APPLE_NOTARIZATION_KEY_P8" | base64 -d > "$notary_key_path"
-        cleanup_notary() {
-          rm -f "$notary_key_path"
-        }
-        trap cleanup_notary EXIT
-
-        source "$GITHUB_ACTION_PATH/notary_helpers.sh"
-
-        dmg_path="codex-rs/target/${{ inputs.target }}/release/codex-${{ inputs.target }}.dmg"
-
-        if [[ ! -f "$dmg_path" ]]; then
-          echo "dmg $dmg_path not found"
-          exit 1
-        fi
-
-        keychain_args=()
-        if [[ -n "${APPLE_CODESIGN_KEYCHAIN:-}" && -f "${APPLE_CODESIGN_KEYCHAIN}" ]]; then
-          keychain_args+=(--keychain "${APPLE_CODESIGN_KEYCHAIN}")
-        fi
-
-        codesign --force --timestamp --sign "$APPLE_CODESIGN_IDENTITY" "${keychain_args[@]}" "$dmg_path"
-        notarize_submission "codex-${{ inputs.target }}.dmg" "$dmg_path" "$notary_key_path"
-        xcrun stapler staple "$dmg_path"
-
-    - name: Remove signing keychain
-      if: ${{ always() }}
-      shell: bash
-      env:
-        APPLE_CODESIGN_KEYCHAIN: ${{ env.APPLE_CODESIGN_KEYCHAIN }}
-      run: |
-        set -euo pipefail
-        if [[ -n "${APPLE_CODESIGN_KEYCHAIN:-}" ]]; then
-          keychain_args=()
-          while IFS= read -r keychain; do
-            [[ "$keychain" == "$APPLE_CODESIGN_KEYCHAIN" ]] && continue
-            [[ -n "$keychain" ]] && keychain_args+=("$keychain")
-          done < <(security list-keychains | sed 's/^[[:space:]]*//;s/[[:space:]]*$//;s/"//g')
-          if ((${#keychain_args[@]} > 0)); then
-            security list-keychains -s "${keychain_args[@]}"
-            security default-keychain -s "${keychain_args[0]}"
-          fi
-
-          if [[ -f "$APPLE_CODESIGN_KEYCHAIN" ]]; then
-            security delete-keychain "$APPLE_CODESIGN_KEYCHAIN"
-          fi
-        fi

.github/actions/macos-code-sign/notary_helpers.sh

@@ -1,46 +0,0 @@
-#!/usr/bin/env bash
-
-notarize_submission() {
-  local label="$1"
-  local path="$2"
-  local notary_key_path="$3"
-
-  if [[ -z "${APPLE_NOTARIZATION_KEY_ID:-}" || -z "${APPLE_NOTARIZATION_ISSUER_ID:-}" ]]; then
-    echo "APPLE_NOTARIZATION_KEY_ID and APPLE_NOTARIZATION_ISSUER_ID are required for notarization"
-    exit 1
-  fi
-
-  if [[ -z "$notary_key_path" || ! -f "$notary_key_path" ]]; then
-    echo "Notary key file $notary_key_path not found"
-    exit 1
-  fi
-
-  if [[ ! -f "$path" ]]; then
-    echo "Notarization payload $path not found"
-    exit 1
-  fi
-
-  local submission_json
-  submission_json=$(xcrun notarytool submit "$path" \
-    --key "$notary_key_path" \
-    --key-id "$APPLE_NOTARIZATION_KEY_ID" \
-    --issuer "$APPLE_NOTARIZATION_ISSUER_ID" \
-    --output-format json \
-    --wait)
-
-  local status submission_id
-  status=$(printf '%s\n' "$submission_json" | jq -r '.status // "Unknown"')
-  submission_id=$(printf '%s\n' "$submission_json" | jq -r '.id // ""')
-
-  if [[ -z "$submission_id" ]]; then
-    echo "Failed to retrieve submission ID for $label"
-    exit 1
-  fi
-
-  echo "::notice title=Notarization::$label submission ${submission_id} completed with status ${status}"
-
-  if [[ "$status" != "Accepted" ]]; then
-    echo "Notarization failed for ${label} (submission ${submission_id}, status ${status})"
-    exit 1
-  fi
-}

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

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

.github/codex/home/config.toml

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

.github/dotslash-config.json

@@ -55,30 +55,6 @@
           "path": "codex-responses-api-proxy.exe"
         }
       }
-    },
-    "codex-command-runner": {
-      "platforms": {
-        "windows-x86_64": {
-          "regex": "^codex-command-runner-x86_64-pc-windows-msvc\\.exe\\.zst$",
-          "path": "codex-command-runner.exe"
-        },
-        "windows-aarch64": {
-          "regex": "^codex-command-runner-aarch64-pc-windows-msvc\\.exe\\.zst$",
-          "path": "codex-command-runner.exe"
-        }
-      }
-    },
-    "codex-windows-sandbox-setup": {
-      "platforms": {
-        "windows-x86_64": {
-          "regex": "^codex-windows-sandbox-setup-x86_64-pc-windows-msvc\\.exe\\.zst$",
-          "path": "codex-windows-sandbox-setup.exe"
-        },
-        "windows-aarch64": {
-          "regex": "^codex-windows-sandbox-setup-aarch64-pc-windows-msvc\\.exe\\.zst$",
-          "path": "codex-windows-sandbox-setup.exe"
-        }
-      }
     }
   }
 }

.github/pull_request_template.md

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

.github/workflows/cargo-deny.yml

@@ -1,26 +0,0 @@
-name: cargo-deny
-
-on:
-  pull_request:
-  push:
-    branches:
-      - main
-
-jobs:
-  cargo-deny:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ./codex-rs
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Install Rust toolchain
-        uses: dtolnay/rust-toolchain@stable
-
-      - name: Run cargo-deny
-        uses: EmbarkStudios/cargo-deny-action@v2
-        with:
-          rust-version: stable
-          manifest-path: ./codex-rs/Cargo.toml

.github/workflows/ci.yml

@@ -12,7 +12,7 @@ jobs:
       NODE_OPTIONS: --max-old-space-size=4096
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v5
 
       - name: Setup pnpm
         uses: pnpm/action-setup@v4
@@ -20,7 +20,7 @@ jobs:
           run_install: false
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v5
         with:
           node-version: 22
 
@@ -36,8 +36,7 @@ jobs:
           GH_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
-          # Use a rust-release version that includes all native binaries.
-          CODEX_VERSION=0.74.0
+          CODEX_VERSION=0.40.0
           OUTPUT_DIR="${RUNNER_TEMP}"
           python3 ./scripts/stage_npm_packages.py \
             --release-version "$CODEX_VERSION" \
@@ -47,7 +46,7 @@ jobs:
           echo "pack_output=$PACK_OUTPUT" >> "$GITHUB_OUTPUT"
 
       - name: Upload staged npm package artifact
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v5
         with:
           name: codex-npm-staging
           path: ${{ steps.stage_npm_package.outputs.pack_output }}

.github/workflows/cla.yml

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

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

@@ -1,107 +0,0 @@
-name: Close stale contributor PRs
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 6 * * *"
-
-permissions:
-  contents: read
-  issues: write
-  pull-requests: write
-
-jobs:
-  close-stale-contributor-prs:
-    # Prevent scheduled runs on forks
-    if: github.repository == 'openai/codex'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Close inactive PRs from contributors
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const DAYS_INACTIVE = 14;
-            const cutoff = new Date(Date.now() - DAYS_INACTIVE * 24 * 60 * 60 * 1000);
-            const { owner, repo } = context.repo;
-            const dryRun = false;
-            const stalePrs = [];
-
-            core.info(`Dry run mode: ${dryRun}`);
-
-            const prs = await github.paginate(github.rest.pulls.list, {
-              owner,
-              repo,
-              state: "open",
-              per_page: 100,
-              sort: "updated",
-              direction: "asc",
-            });
-
-            for (const pr of prs) {
-              const lastUpdated = new Date(pr.updated_at);
-              if (lastUpdated > cutoff) {
-                core.info(`PR ${pr.number} is fresh`);
-                continue;
-              }
-
-              if (!pr.user || pr.user.type !== "User") {
-                core.info(`PR ${pr.number} wasn't created by a user`);
-                continue;
-              }
-
-              let permission;
-              try {
-                const permissionResponse = await github.rest.repos.getCollaboratorPermissionLevel({
-                  owner,
-                  repo,
-                  username: pr.user.login,
-                });
-                permission = permissionResponse.data.permission;
-              } catch (error) {
-                if (error.status === 404) {
-                  core.info(`Author ${pr.user.login} is not a collaborator; skipping #${pr.number}`);
-                  continue;
-                }
-                throw error;
-              }
-
-              const hasContributorAccess = ["admin", "maintain", "write"].includes(permission);
-              if (!hasContributorAccess) {
-                core.info(`Author ${pr.user.login} has ${permission} access; skipping #${pr.number}`);
-                continue;
-              }
-
-              stalePrs.push(pr);
-            }
-
-            if (!stalePrs.length) {
-              core.info("No stale contributor pull requests found.");
-              return;
-            }
-
-            for (const pr of stalePrs) {
-              const issue_number = pr.number;
-              const closeComment = `Closing this pull request because it has had no updates for more than ${DAYS_INACTIVE} days. If you plan to continue working on it, feel free to reopen or open a new PR.`;
-
-              if (dryRun) {
-                core.info(`[dry-run] Would close contributor PR #${issue_number} from ${pr.user.login}`);
-                continue;
-              }
-
-              await github.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number,
-                body: closeComment,
-              });
-
-              await github.rest.pulls.update({
-                owner,
-                repo,
-                pull_number: issue_number,
-                state: "closed",
-              });
-
-              core.info(`Closed contributor PR #${issue_number} from ${pr.user.login}`);
-            }

.github/workflows/codespell.yml

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

.github/workflows/issue-deduplicator.yml

@@ -9,15 +9,14 @@ on:
 jobs:
   gather-duplicates:
     name: Identify potential duplicates
-    # Prevent runs on forks (requires OpenAI API key, wastes Actions minutes)
-    if: github.repository == 'openai/codex' && (github.event.action == 'opened' || (github.event.action == 'labeled' && github.event.label.name == 'codex-deduplicate'))
+    if: ${{ github.event.action == 'opened' || (github.event.action == 'labeled' && github.event.label.name == 'codex-deduplicate') }}
     runs-on: ubuntu-latest
     permissions:
       contents: read
     outputs:
       codex_output: ${{ steps.codex.outputs.final-message }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
 
       - name: Prepare Codex inputs
         env:
@@ -47,6 +46,7 @@ jobs:
         with:
           openai-api-key: ${{ secrets.CODEX_OPENAI_API_KEY }}
           allow-users: "*"
+          model: gpt-5
           prompt: |
             You are an assistant that triages new GitHub issues by identifying potential duplicates.
 

.github/workflows/issue-labeler.yml

@@ -9,15 +9,14 @@ on:
 jobs:
   gather-labels:
     name: Generate label suggestions
-    # Prevent runs on forks (requires OpenAI API key, wastes Actions minutes)
-    if: github.repository == 'openai/codex' && (github.event.action == 'opened' || (github.event.action == 'labeled' && github.event.label.name == 'codex-label'))
+    if: ${{ github.event.action == 'opened' || (github.event.action == 'labeled' && github.event.label.name == 'codex-label') }}
     runs-on: ubuntu-latest
     permissions:
       contents: read
     outputs:
       codex_output: ${{ steps.codex.outputs.final-message }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
 
       - id: codex
         uses: openai/codex-action@main
@@ -27,36 +26,21 @@ jobs:
           prompt: |
             You are an assistant that reviews GitHub issues for the repository.
 
-            Your job is to choose the most appropriate labels for the issue described later in this prompt.
+            Your job is to choose the most appropriate existing labels for the issue described later in this prompt.
             Follow these rules:
+            - Only pick labels out of the list below.
+            - Prefer a small set of precise labels over many broad ones.
 
-            - Add one (and only one) of the following three labels to distinguish the type of issue. Default to "bug" if unsure.
+            Labels to apply:
             1. bug — Reproducible defects in Codex products (CLI, VS Code extension, web, auth).
             2. enhancement — Feature requests or usability improvements that ask for new capabilities, better ergonomics, or quality-of-life tweaks.
-            3. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
-
-            - If applicable, add one of the following labels to specify which sub-product or product surface the issue relates to.
-            1. CLI — the Codex command line interface.
-            2. extension — VS Code (or other IDE) extension-specific issues.
-            3. codex-web — Issues targeting the Codex web UI/Cloud experience.
-            4. github-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.
+            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.
 
             Issue number: ${{ github.event.issue.number }}
 

.github/workflows/rust-ci.yml

@@ -17,7 +17,7 @@ jobs:
       codex: ${{ steps.detect.outputs.codex }}
       workflows: ${{ steps.detect.outputs.workflows }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
       - name: Detect changed paths (no external action)
@@ -28,11 +28,9 @@ jobs:
 
           if [[ "${{ github.event_name }}" == "pull_request" ]]; then
             BASE_SHA='${{ github.event.pull_request.base.sha }}'
-            HEAD_SHA='${{ github.event.pull_request.head.sha }}'
             echo "Base SHA: $BASE_SHA"
-            echo "Head SHA: $HEAD_SHA"
-            # List files changed between base and PR head
-            mapfile -t files < <(git diff --name-only --no-renames "$BASE_SHA" "$HEAD_SHA")
+            # List files changed between base and current HEAD (merge-base aware)
+            mapfile -t files < <(git diff --name-only --no-renames "$BASE_SHA"...HEAD)
           else
             # On push / manual runs, default to running everything
             files=("codex-rs/force" ".github/force")
@@ -58,7 +56,7 @@ jobs:
       run:
         working-directory: codex-rs
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.90
         with:
           components: rustfmt
@@ -76,9 +74,9 @@ jobs:
       run:
         working-directory: codex-rs
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.90
-      - uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+      - uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
         with:
           tool: cargo-shear
           version: 1.5.1
@@ -97,8 +95,8 @@ jobs:
       run:
         working-directory: codex-rs
     env:
-      # Speed up repeated builds across CI runs by caching compiled objects (non-Windows).
-      USE_SCCACHE: ${{ startsWith(matrix.runner, 'windows') && 'false' || 'true' }}
+      # Speed up repeated builds across CI runs by caching compiled objects.
+      RUSTC_WRAPPER: sccache
       CARGO_INCREMENTAL: "0"
       SCCACHE_CACHE_SIZE: 10G
 
@@ -149,46 +147,35 @@ jobs:
             profile: release
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.90
         with:
           targets: ${{ matrix.target }}
           components: clippy
 
-      - name: Compute lockfile hash
-        id: lockhash
-        working-directory: codex-rs
-        shell: bash
-        run: |
-          set -euo pipefail
-          echo "hash=$(sha256sum Cargo.lock | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
-          echo "toolchain_hash=$(sha256sum rust-toolchain.toml | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
-
       # Explicit cache restore: split cargo home vs target, so we can
       # avoid caching the large target dir on the gnu-dev job.
       - name: Restore cargo home cache
         id: cache_cargo_home_restore
-        uses: actions/cache/restore@v5
+        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 }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
+          key: cargo-home-${{ 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 }}-
 
       # Install and restore sccache cache
       - name: Install sccache
-        if: ${{ env.USE_SCCACHE == 'true' }}
-        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
         with:
           tool: sccache
           version: 0.7.5
 
       - name: Configure sccache backend
-        if: ${{ env.USE_SCCACHE == 'true' }}
         shell: bash
         run: |
           set -euo pipefail
@@ -201,20 +188,15 @@ jobs:
             echo "Using sccache local disk + actions/cache fallback"
           fi
 
-      - name: Enable sccache wrapper
-        if: ${{ env.USE_SCCACHE == 'true' }}
-        shell: bash
-        run: echo "RUSTC_WRAPPER=sccache" >> "$GITHUB_ENV"
-
       - name: Restore sccache cache (fallback)
-        if: ${{ env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true' }}
+        if: ${{ env.SCCACHE_GHA_ENABLED != 'true' }}
         id: cache_sccache_restore
-        uses: actions/cache/restore@v5
+        uses: actions/cache/restore@v4
         with:
           path: ${{ github.workspace }}/.sccache/
-          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
           restore-keys: |
-            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-
+            sccache-${{ 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'}}
@@ -228,7 +210,7 @@ jobs:
       - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
         name: Restore APT cache (musl)
         id: cache_apt_restore
-        uses: actions/cache/restore@v5
+        uses: actions/cache/restore@v4
         with:
           path: |
             /var/cache/apt
@@ -246,7 +228,7 @@ jobs:
 
       - name: Install cargo-chef
         if: ${{ matrix.profile == 'release' }}
-        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
         with:
           tool: cargo-chef
           version: 0.1.71
@@ -282,30 +264,30 @@ jobs:
       - name: Save cargo home cache
         if: always() && !cancelled() && steps.cache_cargo_home_restore.outputs.cache-hit != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v5
+        uses: actions/cache/save@v4
         with:
           path: |
             ~/.cargo/bin/
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
-          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
 
       - name: Save sccache cache (fallback)
-        if: always() && !cancelled() && env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true'
+        if: always() && !cancelled() && env.SCCACHE_GHA_ENABLED != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v5
+        uses: actions/cache/save@v4
         with:
           path: ${{ github.workspace }}/.sccache/
-          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
 
       - name: sccache stats
-        if: always() && env.USE_SCCACHE == 'true'
+        if: always()
         continue-on-error: true
         run: sccache --show-stats || true
 
       - name: sccache summary
-        if: always() && env.USE_SCCACHE == 'true'
+        if: always()
         shell: bash
         run: |
           {
@@ -319,7 +301,7 @@ jobs:
       - name: Save APT cache (musl)
         if: always() && !cancelled() && (matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl') && steps.cache_apt_restore.outputs.cache-hit != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v5
+        uses: actions/cache/save@v4
         with:
           path: |
             /var/cache/apt
@@ -344,8 +326,7 @@ jobs:
       run:
         working-directory: codex-rs
     env:
-      # Speed up repeated builds across CI runs by caching compiled objects (non-Windows).
-      USE_SCCACHE: ${{ startsWith(matrix.runner, 'windows') && 'false' || 'true' }}
+      RUSTC_WRAPPER: sccache
       CARGO_INCREMENTAL: "0"
       SCCACHE_CACHE_SIZE: 10G
 
@@ -370,63 +351,31 @@ jobs:
             profile: dev
 
     steps:
-      - uses: actions/checkout@v6
-
-      # We have been running out of space when running this job on Linux for
-      # x86_64-unknown-linux-gnu, so remove some unnecessary dependencies.
-      - name: Remove unnecessary dependencies to save space
-        if: ${{ startsWith(matrix.runner, 'ubuntu') }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          sudo rm -rf \
-            /usr/local/lib/android \
-            /usr/share/dotnet \
-            /usr/local/share/boost \
-            /usr/local/lib/node_modules \
-            /opt/ghc
-          sudo apt-get remove -y docker.io docker-compose podman buildah
-
-      # Some integration tests rely on DotSlash being installed.
-      # See https://github.com/openai/codex/pull/7617.
-      - name: Install DotSlash
-        uses: facebook/install-dotslash@v2
-
+      - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.90
         with:
           targets: ${{ matrix.target }}
 
-      - name: Compute lockfile hash
-        id: lockhash
-        working-directory: codex-rs
-        shell: bash
-        run: |
-          set -euo pipefail
-          echo "hash=$(sha256sum Cargo.lock | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
-          echo "toolchain_hash=$(sha256sum rust-toolchain.toml | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
-
       - name: Restore cargo home cache
         id: cache_cargo_home_restore
-        uses: actions/cache/restore@v5
+        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 }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
           restore-keys: |
             cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
 
       - name: Install sccache
-        if: ${{ env.USE_SCCACHE == 'true' }}
-        uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+        uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
         with:
           tool: sccache
           version: 0.7.5
 
       - name: Configure sccache backend
-        if: ${{ env.USE_SCCACHE == 'true' }}
         shell: bash
         run: |
           set -euo pipefail
@@ -439,61 +388,56 @@ jobs:
             echo "Using sccache local disk + actions/cache fallback"
           fi
 
-      - name: Enable sccache wrapper
-        if: ${{ env.USE_SCCACHE == 'true' }}
-        shell: bash
-        run: echo "RUSTC_WRAPPER=sccache" >> "$GITHUB_ENV"
-
       - name: Restore sccache cache (fallback)
-        if: ${{ env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true' }}
+        if: ${{ env.SCCACHE_GHA_ENABLED != 'true' }}
         id: cache_sccache_restore
-        uses: actions/cache/restore@v5
+        uses: actions/cache/restore@v4
         with:
           path: ${{ github.workspace }}/.sccache/
-          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
           restore-keys: |
-            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-
+            sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-
             sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-
 
-      - uses: taiki-e/install-action@44c6d64aa62cd779e873306675c7a58e86d6d532 # v2
+      - uses: taiki-e/install-action@0c5db7f7f897c03b771660e91d065338615679f4 # v2
         with:
           tool: nextest
           version: 0.9.103
 
       - name: tests
         id: test
+        continue-on-error: true
         run: cargo nextest run --all-features --no-fail-fast --target ${{ matrix.target }} --cargo-profile ci-test
         env:
           RUST_BACKTRACE: 1
-          NEXTEST_STATUS_LEVEL: leak
 
       - name: Save cargo home cache
         if: always() && !cancelled() && steps.cache_cargo_home_restore.outputs.cache-hit != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v5
+        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 }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ steps.lockhash.outputs.toolchain_hash }}
+          key: cargo-home-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ hashFiles('codex-rs/rust-toolchain.toml') }}
 
       - name: Save sccache cache (fallback)
-        if: always() && !cancelled() && env.USE_SCCACHE == 'true' && env.SCCACHE_GHA_ENABLED != 'true'
+        if: always() && !cancelled() && env.SCCACHE_GHA_ENABLED != 'true'
         continue-on-error: true
-        uses: actions/cache/save@v5
+        uses: actions/cache/save@v4
         with:
           path: ${{ github.workspace }}/.sccache/
-          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ steps.lockhash.outputs.hash }}-${{ github.run_id }}
+          key: sccache-${{ matrix.runner }}-${{ matrix.target }}-${{ matrix.profile }}-${{ hashFiles('**/Cargo.lock') }}-${{ github.run_id }}
 
       - name: sccache stats
-        if: always() && env.USE_SCCACHE == 'true'
+        if: always()
         continue-on-error: true
         run: sccache --show-stats || true
 
       - name: sccache summary
-        if: always() && env.USE_SCCACHE == 'true'
+        if: always()
         shell: bash
         run: |
           {

.github/workflows/rust-release-prepare.yml

@@ -1,53 +0,0 @@
-name: rust-release-prepare
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 */4 * * *"
-
-concurrency:
-  group: ${{ github.workflow }}
-  cancel-in-progress: false
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  prepare:
-    # Prevent scheduled runs on forks (no secrets, wastes Actions minutes)
-    if: github.repository == 'openai/codex'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          ref: main
-          fetch-depth: 0
-
-      - name: Update models.json
-        env:
-          OPENAI_API_KEY: ${{ secrets.CODEX_OPENAI_API_KEY }}
-        run: |
-          set -euo pipefail
-
-          client_version="99.99.99"
-          terminal_info="github-actions"
-          user_agent="codex_cli_rs/99.99.99 (Linux $(uname -r); $(uname -m)) ${terminal_info}"
-          base_url="${OPENAI_BASE_URL:-https://chatgpt.com/backend-api/codex}"
-
-          headers=(
-            -H "Authorization: Bearer ${OPENAI_API_KEY}"
-            -H "User-Agent: ${user_agent}"
-          )
-
-          url="${base_url%/}/models?client_version=${client_version}"
-          curl --http1.1 --fail --show-error --location "${headers[@]}" "${url}" | jq '.' > codex-rs/core/models.json
-
-      - name: Open pull request (if changed)
-        uses: peter-evans/create-pull-request@v8
-        with:
-          commit-message: "Update models.json"
-          title: "Update models.json"
-          body: "Automated update of models.json."
-          branch: "bot/update-models-json"
-          reviewers: "pakrym-oai,aibrahim-oai"
-          delete-branch: true

.github/workflows/rust-release.yml

@@ -19,7 +19,7 @@ jobs:
   tag-check:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
 
       - name: Validate tag matches Cargo.toml version
         shell: bash
@@ -50,9 +50,6 @@ jobs:
     name: Build - ${{ matrix.runner }} - ${{ matrix.target }}
     runs-on: ${{ matrix.runner }}
     timeout-minutes: 30
-    permissions:
-      contents: read
-      id-token: write
     defaults:
       run:
         working-directory: codex-rs
@@ -79,12 +76,12 @@ jobs:
             target: aarch64-pc-windows-msvc
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.90
         with:
           targets: ${{ matrix.target }}
 
-      - uses: actions/cache@v5
+      - uses: actions/cache@v4
         with:
           path: |
             ~/.cargo/bin/
@@ -101,104 +98,176 @@ jobs:
           sudo apt-get install -y musl-tools pkg-config
 
       - name: Cargo build
+        run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
+
+      - if: ${{ matrix.runner == 'macos-15-xlarge' }}
+        name: Configure Apple code signing
         shell: bash
+        env:
+          KEYCHAIN_PASSWORD: actions
+          APPLE_CERTIFICATE: ${{ secrets.APPLE_CERTIFICATE_P12 }}
+          APPLE_CERTIFICATE_PASSWORD: ${{ secrets.APPLE_CERTIFICATE_PASSWORD }}
         run: |
-          if [[ "${{ contains(matrix.target, 'windows') }}" == 'true' ]]; then
-            cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy --bin codex-windows-sandbox-setup --bin codex-command-runner
-          else
-            cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-responses-api-proxy
+          set -euo pipefail
+
+          if [[ -z "${APPLE_CERTIFICATE:-}" ]]; then
+            echo "APPLE_CERTIFICATE is required for macOS signing"
+            exit 1
           fi
 
-      - if: ${{ contains(matrix.target, 'linux') }}
-        name: Cosign Linux artifacts
-        uses: ./.github/actions/linux-code-sign
-        with:
-          target: ${{ matrix.target }}
-          artifacts-dir: ${{ github.workspace }}/codex-rs/target/${{ matrix.target }}/release
+          if [[ -z "${APPLE_CERTIFICATE_PASSWORD:-}" ]]; then
+            echo "APPLE_CERTIFICATE_PASSWORD is required for macOS signing"
+            exit 1
+          fi
 
-      - if: ${{ contains(matrix.target, 'windows') }}
-        name: Sign Windows binaries with Azure Trusted Signing
-        uses: ./.github/actions/windows-code-sign
-        with:
-          target: ${{ matrix.target }}
-          client-id: ${{ secrets.AZURE_TRUSTED_SIGNING_CLIENT_ID }}
-          tenant-id: ${{ secrets.AZURE_TRUSTED_SIGNING_TENANT_ID }}
-          subscription-id: ${{ secrets.AZURE_TRUSTED_SIGNING_SUBSCRIPTION_ID }}
-          endpoint: ${{ secrets.AZURE_TRUSTED_SIGNING_ENDPOINT }}
-          account-name: ${{ secrets.AZURE_TRUSTED_SIGNING_ACCOUNT_NAME }}
-          certificate-profile-name: ${{ secrets.AZURE_TRUSTED_SIGNING_CERTIFICATE_PROFILE_NAME }}
+          cert_path="${RUNNER_TEMP}/apple_signing_certificate.p12"
+          echo "$APPLE_CERTIFICATE" | base64 -d > "$cert_path"
 
-      - if: ${{ runner.os == 'macOS' }}
-        name: MacOS code signing (binaries)
-        uses: ./.github/actions/macos-code-sign
-        with:
-          target: ${{ matrix.target }}
-          sign-binaries: "true"
-          sign-dmg: "false"
-          apple-certificate: ${{ secrets.APPLE_CERTIFICATE_P12 }}
-          apple-certificate-password: ${{ secrets.APPLE_CERTIFICATE_PASSWORD }}
-          apple-notarization-key-p8: ${{ secrets.APPLE_NOTARIZATION_KEY_P8 }}
-          apple-notarization-key-id: ${{ secrets.APPLE_NOTARIZATION_KEY_ID }}
-          apple-notarization-issuer-id: ${{ secrets.APPLE_NOTARIZATION_ISSUER_ID }}
+          keychain_path="${RUNNER_TEMP}/codex-signing.keychain-db"
+          security create-keychain -p "$KEYCHAIN_PASSWORD" "$keychain_path"
+          security set-keychain-settings -lut 21600 "$keychain_path"
+          security unlock-keychain -p "$KEYCHAIN_PASSWORD" "$keychain_path"
 
-      - if: ${{ runner.os == 'macOS' }}
-        name: Build macOS dmg
+          keychain_args=()
+          cleanup_keychain() {
+            if ((${#keychain_args[@]} > 0)); then
+              security list-keychains -s "${keychain_args[@]}" || true
+              security default-keychain -s "${keychain_args[0]}" || true
+            else
+              security list-keychains -s || true
+            fi
+            if [[ -f "$keychain_path" ]]; then
+              security delete-keychain "$keychain_path" || true
+            fi
+          }
+
+          while IFS= read -r keychain; do
+            [[ -n "$keychain" ]] && keychain_args+=("$keychain")
+          done < <(security list-keychains | sed 's/^[[:space:]]*//;s/[[:space:]]*$//;s/"//g')
+
+          if ((${#keychain_args[@]} > 0)); then
+            security list-keychains -s "$keychain_path" "${keychain_args[@]}"
+          else
+            security list-keychains -s "$keychain_path"
+          fi
+
+          security default-keychain -s "$keychain_path"
+          security import "$cert_path" -k "$keychain_path" -P "$APPLE_CERTIFICATE_PASSWORD" -T /usr/bin/codesign -T /usr/bin/security
+          security set-key-partition-list -S apple-tool:,apple: -s -k "$KEYCHAIN_PASSWORD" "$keychain_path" > /dev/null
+
+          codesign_hashes=()
+          while IFS= read -r hash; do
+            [[ -n "$hash" ]] && codesign_hashes+=("$hash")
+          done < <(security find-identity -v -p codesigning "$keychain_path" \
+            | sed -n 's/.*\([0-9A-F]\{40\}\).*/\1/p' \
+            | sort -u)
+
+          if ((${#codesign_hashes[@]} == 0)); then
+            echo "No signing identities found in $keychain_path"
+            cleanup_keychain
+            rm -f "$cert_path"
+            exit 1
+          fi
+
+          if ((${#codesign_hashes[@]} > 1)); then
+            echo "Multiple signing identities found in $keychain_path:"
+            printf '  %s\n' "${codesign_hashes[@]}"
+            cleanup_keychain
+            rm -f "$cert_path"
+            exit 1
+          fi
+
+          APPLE_CODESIGN_IDENTITY="${codesign_hashes[0]}"
+
+          rm -f "$cert_path"
+
+          echo "APPLE_CODESIGN_IDENTITY=$APPLE_CODESIGN_IDENTITY" >> "$GITHUB_ENV"
+          echo "APPLE_CODESIGN_KEYCHAIN=$keychain_path" >> "$GITHUB_ENV"
+          echo "::add-mask::$APPLE_CODESIGN_IDENTITY"
+
+      - if: ${{ matrix.runner == 'macos-15-xlarge' }}
+        name: Sign macOS binaries
         shell: bash
         run: |
           set -euo pipefail
 
-          target="${{ matrix.target }}"
-          release_dir="target/${target}/release"
-          dmg_root="${RUNNER_TEMP}/codex-dmg-root"
-          volname="Codex (${target})"
-          dmg_path="${release_dir}/codex-${target}.dmg"
-
-          # The previous "MacOS code signing (binaries)" step signs + notarizes the
-          # built artifacts in `${release_dir}`. This step packages *those same*
-          # signed binaries into a dmg.
-          codex_binary_path="${release_dir}/codex"
-          proxy_binary_path="${release_dir}/codex-responses-api-proxy"
-
-          rm -rf "$dmg_root"
-          mkdir -p "$dmg_root"
-
-          if [[ ! -f "$codex_binary_path" ]]; then
-            echo "Binary $codex_binary_path not found"
-            exit 1
-          fi
-          if [[ ! -f "$proxy_binary_path" ]]; then
-            echo "Binary $proxy_binary_path not found"
+          if [[ -z "${APPLE_CODESIGN_IDENTITY:-}" ]]; then
+            echo "APPLE_CODESIGN_IDENTITY is required for macOS signing"
             exit 1
           fi
 
-          ditto "$codex_binary_path" "${dmg_root}/codex"
-          ditto "$proxy_binary_path" "${dmg_root}/codex-responses-api-proxy"
-
-          rm -f "$dmg_path"
-          hdiutil create \
-            -volname "$volname" \
-            -srcfolder "$dmg_root" \
-            -format UDZO \
-            -ov \
-            "$dmg_path"
-
-          if [[ ! -f "$dmg_path" ]]; then
-            echo "dmg $dmg_path not found after build"
-            exit 1
+          keychain_args=()
+          if [[ -n "${APPLE_CODESIGN_KEYCHAIN:-}" && -f "${APPLE_CODESIGN_KEYCHAIN}" ]]; then
+            keychain_args+=(--keychain "${APPLE_CODESIGN_KEYCHAIN}")
           fi
 
-      - if: ${{ runner.os == 'macOS' }}
-        name: MacOS code signing (dmg)
-        uses: ./.github/actions/macos-code-sign
-        with:
-          target: ${{ matrix.target }}
-          sign-binaries: "false"
-          sign-dmg: "true"
-          apple-certificate: ${{ secrets.APPLE_CERTIFICATE_P12 }}
-          apple-certificate-password: ${{ secrets.APPLE_CERTIFICATE_PASSWORD }}
-          apple-notarization-key-p8: ${{ secrets.APPLE_NOTARIZATION_KEY_P8 }}
-          apple-notarization-key-id: ${{ secrets.APPLE_NOTARIZATION_KEY_ID }}
-          apple-notarization-issuer-id: ${{ secrets.APPLE_NOTARIZATION_ISSUER_ID }}
+          for binary in codex codex-responses-api-proxy; do
+            path="target/${{ matrix.target }}/release/${binary}"
+            codesign --force --options runtime --timestamp --sign "$APPLE_CODESIGN_IDENTITY" "${keychain_args[@]}" "$path"
+          done
+
+      - if: ${{ matrix.runner == 'macos-15-xlarge' }}
+        name: Notarize macOS binaries
+        shell: bash
+        env:
+          APPLE_NOTARIZATION_KEY_P8: ${{ secrets.APPLE_NOTARIZATION_KEY_P8 }}
+          APPLE_NOTARIZATION_KEY_ID: ${{ secrets.APPLE_NOTARIZATION_KEY_ID }}
+          APPLE_NOTARIZATION_ISSUER_ID: ${{ secrets.APPLE_NOTARIZATION_ISSUER_ID }}
+        run: |
+          set -euo pipefail
+
+          for var in APPLE_NOTARIZATION_KEY_P8 APPLE_NOTARIZATION_KEY_ID APPLE_NOTARIZATION_ISSUER_ID; do
+            if [[ -z "${!var:-}" ]]; then
+              echo "$var is required for notarization"
+              exit 1
+            fi
+          done
+
+          notary_key_path="${RUNNER_TEMP}/notarytool.key.p8"
+          echo "$APPLE_NOTARIZATION_KEY_P8" | base64 -d > "$notary_key_path"
+          cleanup_notary() {
+            rm -f "$notary_key_path"
+          }
+          trap cleanup_notary EXIT
+
+          notarize_binary() {
+            local binary="$1"
+            local source_path="target/${{ matrix.target }}/release/${binary}"
+            local archive_path="${RUNNER_TEMP}/${binary}.zip"
+
+            if [[ ! -f "$source_path" ]]; then
+              echo "Binary $source_path not found"
+              exit 1
+            fi
+
+            rm -f "$archive_path"
+            ditto -c -k --keepParent "$source_path" "$archive_path"
+
+            submission_json=$(xcrun notarytool submit "$archive_path" \
+              --key "$notary_key_path" \
+              --key-id "$APPLE_NOTARIZATION_KEY_ID" \
+              --issuer "$APPLE_NOTARIZATION_ISSUER_ID" \
+              --output-format json \
+              --wait)
+
+            status=$(printf '%s\n' "$submission_json" | jq -r '.status // "Unknown"')
+            submission_id=$(printf '%s\n' "$submission_json" | jq -r '.id // ""')
+
+            if [[ -z "$submission_id" ]]; then
+              echo "Failed to retrieve submission ID for $binary"
+              exit 1
+            fi
+
+            echo "::notice title=Notarization::$binary submission ${submission_id} completed with status ${status}"
+
+            if [[ "$status" != "Accepted" ]]; then
+              echo "Notarization failed for ${binary} (submission ${submission_id}, status ${status})"
+              exit 1
+            fi
+          }
+
+          notarize_binary "codex"
+          notarize_binary "codex-responses-api-proxy"
 
       - name: Stage artifacts
         shell: bash
@@ -209,22 +278,11 @@ jobs:
           if [[ "${{ matrix.runner }}" == windows* ]]; then
             cp target/${{ matrix.target }}/release/codex.exe "$dest/codex-${{ matrix.target }}.exe"
             cp target/${{ matrix.target }}/release/codex-responses-api-proxy.exe "$dest/codex-responses-api-proxy-${{ matrix.target }}.exe"
-            cp target/${{ matrix.target }}/release/codex-windows-sandbox-setup.exe "$dest/codex-windows-sandbox-setup-${{ matrix.target }}.exe"
-            cp target/${{ matrix.target }}/release/codex-command-runner.exe "$dest/codex-command-runner-${{ matrix.target }}.exe"
           else
             cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
             cp target/${{ matrix.target }}/release/codex-responses-api-proxy "$dest/codex-responses-api-proxy-${{ matrix.target }}"
           fi
 
-          if [[ "${{ matrix.target }}" == *linux* ]]; then
-            cp target/${{ matrix.target }}/release/codex.sigstore "$dest/codex-${{ matrix.target }}.sigstore"
-            cp target/${{ matrix.target }}/release/codex-responses-api-proxy.sigstore "$dest/codex-responses-api-proxy-${{ matrix.target }}.sigstore"
-          fi
-
-          if [[ "${{ matrix.target }}" == *apple-darwin ]]; then
-            cp target/${{ matrix.target }}/release/codex-${{ matrix.target }}.dmg "$dest/codex-${{ matrix.target }}.dmg"
-          fi
-
       - if: ${{ matrix.runner == 'windows-11-arm' }}
         name: Install zstd
         shell: powershell
@@ -237,15 +295,6 @@ jobs:
           # ${{ matrix.target }}
           dest="dist/${{ matrix.target }}"
 
-          # We want to ship the raw Windows executables in the GitHub Release
-          # in addition to the compressed archives. Keep the originals for
-          # Windows targets; remove them elsewhere to limit the number of
-          # artifacts that end up in the GitHub Release.
-          keep_originals=false
-          if [[ "${{ matrix.runner }}" == windows* ]]; then
-            keep_originals=true
-          fi
-
           # For compatibility with environments that lack the `zstd` tool we
           # additionally create a `.tar.gz` for all platforms and `.zip` for
           # Windows alongside every single binary that we publish. The end result is:
@@ -259,12 +308,7 @@ jobs:
             base="$(basename "$f")"
             # Skip files that are already archives (shouldn't happen, but be
             # safe).
-            if [[ "$base" == *.tar.gz || "$base" == *.zip || "$base" == *.dmg ]]; then
-              continue
-            fi
-
-            # Don't try to compress signature bundles.
-            if [[ "$base" == *.sigstore ]]; then
+            if [[ "$base" == *.tar.gz || "$base" == *.zip ]]; then
               continue
             fi
 
@@ -280,14 +324,33 @@ jobs:
 
             # Also create .zst (existing behaviour) *and* remove the original
             # uncompressed binary to keep the directory small.
-            zstd_args=(-T0 -19)
-            if [[ "${keep_originals}" == false ]]; then
-              zstd_args+=(--rm)
-            fi
-            zstd "${zstd_args[@]}" "$dest/$base"
+            zstd -T0 -19 --rm "$dest/$base"
           done
 
-      - uses: actions/upload-artifact@v6
+      - name: Remove signing keychain
+        if: ${{ always() && matrix.runner == 'macos-15-xlarge' }}
+        shell: bash
+        env:
+          APPLE_CODESIGN_KEYCHAIN: ${{ env.APPLE_CODESIGN_KEYCHAIN }}
+        run: |
+          set -euo pipefail
+          if [[ -n "${APPLE_CODESIGN_KEYCHAIN:-}" ]]; then
+            keychain_args=()
+            while IFS= read -r keychain; do
+              [[ "$keychain" == "$APPLE_CODESIGN_KEYCHAIN" ]] && continue
+              [[ -n "$keychain" ]] && keychain_args+=("$keychain")
+            done < <(security list-keychains | sed 's/^[[:space:]]*//;s/[[:space:]]*$//;s/"//g')
+            if ((${#keychain_args[@]} > 0)); then
+              security list-keychains -s "${keychain_args[@]}"
+              security default-keychain -s "${keychain_args[0]}"
+            fi
+
+            if [[ -f "$APPLE_CODESIGN_KEYCHAIN" ]]; then
+              security delete-keychain "$APPLE_CODESIGN_KEYCHAIN"
+            fi
+          fi
+
+      - uses: actions/upload-artifact@v5
         with:
           name: ${{ matrix.target }}
           # Upload the per-binary .zst files as well as the new .tar.gz
@@ -295,19 +358,8 @@ jobs:
           path: |
             codex-rs/dist/${{ matrix.target }}/*
 
-  shell-tool-mcp:
-    name: shell-tool-mcp
-    needs: tag-check
-    uses: ./.github/workflows/shell-tool-mcp.yml
-    with:
-      release-tag: ${{ github.ref_name }}
-      publish: true
-    secrets: inherit
-
   release:
-    needs:
-      - build
-      - shell-tool-mcp
+    needs: build
     name: release
     runs-on: ubuntu-latest
     permissions:
@@ -321,23 +373,15 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v5
 
-      - uses: actions/download-artifact@v7
+      - uses: actions/download-artifact@v4
         with:
           path: dist
 
       - name: List
         run: ls -R dist/
 
-      # This is a temporary fix: we should modify shell-tool-mcp.yml so these
-      # files do not end up in dist/ in the first place.
-      - name: Delete entries from dist/ that should not go in the release
-        run: |
-          rm -rf dist/shell-tool-mcp*
-
-          ls -R dist/
-
       - name: Define release name
         id: release_name
         run: |
@@ -371,7 +415,7 @@ jobs:
           run_install: false
 
       - name: Setup Node.js for npm packaging
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v5
         with:
           node-version: 22
 
@@ -422,7 +466,7 @@ jobs:
 
     steps:
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v5
         with:
           node-version: 22
           registry-url: "https://registry.npmjs.org"

.github/workflows/sdk.yml

@@ -11,7 +11,7 @@ jobs:
     timeout-minutes: 10
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v5
 
       - name: Setup pnpm
         uses: pnpm/action-setup@v4
@@ -19,7 +19,7 @@ jobs:
           run_install: false
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v5
         with:
           node-version: 22
           cache: pnpm

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

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

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

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

.gitignore

@@ -64,9 +64,6 @@ apply_patch/
 # coverage
 coverage/
 
-# personal files
-personal/
-
 # os
 .DS_Store
 Thumbs.db
@@ -85,8 +82,3 @@ CHANGELOG.ignore.md
 # nix related
 .direnv
 .envrc
-
-# Python bytecode files
-__pycache__/
-*.pyc
-

AGENTS.md

@@ -11,6 +11,7 @@ In the codex-rs folder where the rust code lives:
 - Always collapse if statements per https://rust-lang.github.io/rust-clippy/master/index.html#collapsible_if
 - Always inline format! args when possible per https://rust-lang.github.io/rust-clippy/master/index.html#uninlined_format_args
 - Use method references over closures when possible per https://rust-lang.github.io/rust-clippy/master/index.html#redundant_closure_for_method_calls
+- Do not use unsigned integer even if the number cannot be negative.
 - When writing tests, prefer comparing the equality of entire objects over fields one by one.
 - When making a change that adds or changes an API, ensure that the documentation in the `docs/` folder is up to date if applicable.
 
@@ -74,14 +75,6 @@ If you don’t have the tool:
 ### Test assertions
 
 - Tests should use pretty_assertions::assert_eq for clearer diffs. Import this at the top of the test module if it isn't already.
-- Prefer deep equals comparisons whenever possible. Perform `assert_eq!()` on entire objects, rather than individual fields.
-- Avoid mutating process environment in tests; prefer passing environment-derived flags or dependencies from above.
-
-### Spawning workspace binaries in tests (Cargo vs Buck2)
-
-- Prefer `codex_utils_cargo_bin::cargo_bin("...")` over `assert_cmd::Command::cargo_bin(...)` or `escargot` when tests need to spawn first-party binaries.
-  - Under Buck2, `CARGO_BIN_EXE_*` may be project-relative (e.g. `buck-out/...`), which breaks if a test changes its working directory. `codex_utils_cargo_bin::cargo_bin` resolves to an absolute path first.
-- When locating fixture files under Buck2, avoid `env!("CARGO_MANIFEST_DIR")` (Buck codegen sets it to `"."`). Prefer deriving paths from `codex_utils_cargo_bin::buck_project_root()` when needed.
 
 ### Integration tests (core)
 
@@ -91,8 +84,6 @@ If you don’t have the tool:
 - Use `ResponseMock::single_request()` when a test should only issue one POST, or `ResponseMock::requests()` to inspect every captured `ResponsesRequest`.
 - `ResponsesRequest` exposes helpers (`body_json`, `input`, `function_call_output`, `custom_tool_call_output`, `call_output`, `header`, `path`, `query_param`) so assertions can target structured payloads instead of manual JSON digging.
 - Build SSE payloads with the provided `ev_*` constructors and the `sse(...)`.
-- Prefer `wait_for_event` over `wait_for_event_with_timeout`.
-- Prefer `mount_sse_once` over `mount_sse_once_match` or `mount_sse_sequence`
 
 - Typical pattern:
 

README.md

@@ -1,11 +1,13 @@
 <p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install --cask codex</code></p>
+
 <p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.
+</br>
+</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href="https://developers.openai.com/codex/ide">install in your IDE</a>
+</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href="https://chatgpt.com/codex">chatgpt.com/codex</a></p>
+
 <p align="center">
   <img src="./.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" />
-</p>
-</br>
-If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href="https://developers.openai.com/codex/ide">install in your IDE.</a>
-</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href="https://chatgpt.com/codex">chatgpt.com/codex</a>.</p>
+  </p>
 
 ---
 
@@ -13,19 +15,25 @@ If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href="http
 
 ### Installing and running Codex CLI
 
-Install globally with your preferred package manager:
+Install globally with your preferred package manager. If you use npm:
 
 ```shell
-# Install using npm
 npm install -g @openai/codex
 ```
 
+Alternatively, if you use Homebrew:
+
 ```shell
-# Install using Homebrew
 brew install --cask codex
 ```
 
-Then simply run `codex` to get started.
+Then simply run `codex` to get started:
+
+```shell
+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>
@@ -45,15 +53,57 @@ Each archive contains a single entry with the platform baked into the name (e.g.
 
 ### Using Codex with your ChatGPT plan
 
+<p align="center">
+  <img src="./.github/codex-cli-login.png" alt="Codex CLI login" width="80%" />
+  </p>
+
 Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan. [Learn more about what's included in your ChatGPT plan](https://help.openai.com/en/articles/11369540-codex-in-chatgpt).
 
-You can also use Codex with an API key, but this requires [additional setup](https://developers.openai.com/codex/auth#sign-in-with-an-api-key).
+You can also use Codex with an API key, but this requires [additional setup](./docs/authentication.md#usage-based-billing-alternative-use-an-openai-api-key). If you previously used an API key for usage-based billing, see the [migration steps](./docs/authentication.md#migrating-from-usage-based-billing-api-key). If you're having trouble with login, please comment on [this issue](https://github.com/openai/codex/issues/1243).
 
-## Docs
+### Model Context Protocol (MCP)
 
-- [**Codex Documentation**](https://developers.openai.com/codex)
+Codex can access MCP servers. To configure them, refer to the [config docs](./docs/config.md#mcp_servers).
+
+### Configuration
+
+Codex CLI supports a rich set of configuration options, with preferences stored in `~/.codex/config.toml`. For full configuration options, see [Configuration](./docs/config.md).
+
+---
+
+### Docs & FAQ
+
+- [**Getting started**](./docs/getting-started.md)
+  - [CLI usage](./docs/getting-started.md#cli-usage)
+  - [Slash Commands](./docs/slash_commands.md)
+  - [Running with a prompt as input](./docs/getting-started.md#running-with-a-prompt-as-input)
+  - [Example prompts](./docs/getting-started.md#example-prompts)
+  - [Custom prompts](./docs/prompts.md)
+  - [Memory with AGENTS.md](./docs/getting-started.md#memory-with-agentsmd)
+- [**Configuration**](./docs/config.md)
+  - [Example config](./docs/example-config.md)
+- [**Sandbox & approvals**](./docs/sandbox.md)
+- [**Authentication**](./docs/authentication.md)
+  - [Auth methods](./docs/authentication.md#forcing-a-specific-auth-method-advanced)
+  - [Login on a "Headless" machine](./docs/authentication.md#connecting-on-a-headless-machine)
+- **Automating Codex**
+  - [GitHub Action](https://github.com/openai/codex-action)
+  - [TypeScript SDK](./sdk/typescript/README.md)
+  - [Non-interactive mode (`codex exec`)](./docs/exec.md)
+- [**Advanced**](./docs/advanced.md)
+  - [Tracing / verbose logging](./docs/advanced.md#tracing--verbose-logging)
+  - [Model Context Protocol (MCP)](./docs/advanced.md#model-context-protocol-mcp)
+- [**Zero data retention (ZDR)**](./docs/zdr.md)
 - [**Contributing**](./docs/contributing.md)
-- [**Installing & building**](./docs/install.md)
+- [**Install & build**](./docs/install.md)
+  - [System Requirements](./docs/install.md#system-requirements)
+  - [DotSlash](./docs/install.md#dotslash)
+  - [Build from source](./docs/install.md#build-from-source)
+- [**FAQ**](./docs/faq.md)
 - [**Open source fund**](./docs/open-source-fund.md)
 
+---
+
+## License
+
 This repository is licensed under the [Apache-2.0 License](LICENSE).

codex-cli/bin/codex.js

@@ -95,10 +95,10 @@ function detectPackageManager() {
     return "bun";
   }
 
-
   if (
-    __dirname.includes(".bun/install/global") ||
-    __dirname.includes(".bun\\install\\global")
+    process.env.BUN_INSTALL ||
+    process.env.BUN_INSTALL_GLOBAL_DIR ||
+    process.env.BUN_INSTALL_BIN_DIR
   ) {
     return "bun";
   }

codex-cli/scripts/build_npm_package.py

@@ -20,14 +20,9 @@ PACKAGE_NATIVE_COMPONENTS: dict[str, list[str]] = {
     "codex-responses-api-proxy": ["codex-responses-api-proxy"],
     "codex-sdk": ["codex"],
 }
-WINDOWS_ONLY_COMPONENTS: dict[str, list[str]] = {
-    "codex": ["codex-windows-sandbox-setup", "codex-command-runner"],
-}
 COMPONENT_DEST_DIR: dict[str, str] = {
     "codex": "codex",
     "codex-responses-api-proxy": "codex-responses-api-proxy",
-    "codex-windows-sandbox-setup": "codex",
-    "codex-command-runner": "codex",
     "rg": "path",
 }
 
@@ -108,7 +103,7 @@ def main() -> int:
                     "pointing to a directory containing pre-installed binaries."
                 )
 
-            copy_native_binaries(vendor_src, staging_dir, package, native_components)
+            copy_native_binaries(vendor_src, staging_dir, native_components)
 
         if release_version:
             staging_dir_str = str(staging_dir)
@@ -237,12 +232,7 @@ def stage_codex_sdk_sources(staging_dir: Path) -> None:
         shutil.copy2(license_src, staging_dir / "LICENSE")
 
 
-def copy_native_binaries(
-    vendor_src: Path,
-    staging_dir: Path,
-    package: str,
-    components: list[str],
-) -> None:
+def copy_native_binaries(vendor_src: Path, staging_dir: Path, components: list[str]) -> None:
     vendor_src = vendor_src.resolve()
     if not vendor_src.exists():
         raise RuntimeError(f"Vendor source directory not found: {vendor_src}")
@@ -260,9 +250,6 @@ def copy_native_binaries(
         if not target_dir.is_dir():
             continue
 
-        if "windows" in target_dir.name:
-            components_set.update(WINDOWS_ONLY_COMPONENTS.get(package, []))
-
         dest_target_dir = vendor_dest / target_dir.name
         dest_target_dir.mkdir(parents=True, exist_ok=True)
 

codex-cli/scripts/install_native_deps.py

@@ -2,7 +2,6 @@
 """Install Codex native binaries (Rust CLI plus ripgrep helpers)."""
 
 import argparse
-from contextlib import contextmanager
 import json
 import os
 import shutil
@@ -13,7 +12,6 @@ import zipfile
 from dataclasses import dataclass
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from pathlib import Path
-import sys
 from typing import Iterable, Sequence
 from urllib.parse import urlparse
 from urllib.request import urlopen
@@ -38,11 +36,8 @@ class BinaryComponent:
     artifact_prefix: str  # matches the artifact filename prefix (e.g. codex-<target>.zst)
     dest_dir: str  # directory under vendor/<target>/ where the binary is installed
     binary_basename: str  # executable name inside dest_dir (before optional .exe)
-    targets: tuple[str, ...] | None = None  # limit installation to specific targets
 
 
-WINDOWS_TARGETS = tuple(target for target in BINARY_TARGETS if "windows" in target)
-
 BINARY_COMPONENTS = {
     "codex": BinaryComponent(
         artifact_prefix="codex",
@@ -54,18 +49,6 @@ BINARY_COMPONENTS = {
         dest_dir="codex-responses-api-proxy",
         binary_basename="codex-responses-api-proxy",
     ),
-    "codex-windows-sandbox-setup": BinaryComponent(
-        artifact_prefix="codex-windows-sandbox-setup",
-        dest_dir="codex",
-        binary_basename="codex-windows-sandbox-setup",
-        targets=WINDOWS_TARGETS,
-    ),
-    "codex-command-runner": BinaryComponent(
-        artifact_prefix="codex-command-runner",
-        dest_dir="codex",
-        binary_basename="codex-command-runner",
-        targets=WINDOWS_TARGETS,
-    ),
 }
 
 RG_TARGET_PLATFORM_PAIRS: list[tuple[str, str]] = [
@@ -79,45 +62,6 @@ RG_TARGET_PLATFORM_PAIRS: list[tuple[str, str]] = [
 RG_TARGET_TO_PLATFORM = {target: platform for target, platform in RG_TARGET_PLATFORM_PAIRS}
 DEFAULT_RG_TARGETS = [target for target, _ in RG_TARGET_PLATFORM_PAIRS]
 
-# urllib.request.urlopen() defaults to no timeout (can hang indefinitely), which is painful in CI.
-DOWNLOAD_TIMEOUT_SECS = 60
-
-
-def _gha_enabled() -> bool:
-    # GitHub Actions supports "workflow commands" (e.g. ::group:: / ::error::) that make logs
-    # much easier to scan: groups collapse noisy sections and error annotations surface the
-    # failure in the UI without changing the actual exception/traceback output.
-    return os.environ.get("GITHUB_ACTIONS") == "true"
-
-
-def _gha_escape(value: str) -> str:
-    # Workflow commands require percent/newline escaping.
-    return value.replace("%", "%25").replace("\r", "%0D").replace("\n", "%0A")
-
-
-def _gha_error(*, title: str, message: str) -> None:
-    # Emit a GitHub Actions error annotation. This does not replace stdout/stderr logs; it just
-    # adds a prominent summary line to the job UI so the root cause is easier to spot.
-    if not _gha_enabled():
-        return
-    print(
-        f"::error title={_gha_escape(title)}::{_gha_escape(message)}",
-        flush=True,
-    )
-
-
-@contextmanager
-def _gha_group(title: str):
-    # Wrap a block in a collapsible log group on GitHub Actions. Outside of GHA this is a no-op
-    # so local output remains unchanged.
-    if _gha_enabled():
-        print(f"::group::{_gha_escape(title)}", flush=True)
-    try:
-        yield
-    finally:
-        if _gha_enabled():
-            print("::endgroup::", flush=True)
-
 
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Install native Codex binaries.")
@@ -135,8 +79,7 @@ def parse_args() -> argparse.Namespace:
         choices=tuple(list(BINARY_COMPONENTS) + ["rg"]),
         help=(
             "Limit installation to the specified components."
-            " May be repeated. Defaults to codex, codex-windows-sandbox-setup,"
-            " codex-command-runner, and rg."
+            " May be repeated. Defaults to 'codex' and 'rg'."
         ),
     )
     parser.add_argument(
@@ -158,12 +101,7 @@ def main() -> int:
     vendor_dir = codex_cli_root / VENDOR_DIR_NAME
     vendor_dir.mkdir(parents=True, exist_ok=True)
 
-    components = args.components or [
-        "codex",
-        "codex-windows-sandbox-setup",
-        "codex-command-runner",
-        "rg",
-    ]
+    components = args.components or ["codex", "rg"]
 
     workflow_url = (args.workflow_url or DEFAULT_WORKFLOW_URL).strip()
     if not workflow_url:
@@ -172,20 +110,19 @@ def main() -> int:
     workflow_id = workflow_url.rstrip("/").split("/")[-1]
     print(f"Downloading native artifacts from workflow {workflow_id}...")
 
-    with _gha_group(f"Download native artifacts from workflow {workflow_id}"):
-        with tempfile.TemporaryDirectory(prefix="codex-native-artifacts-") as artifacts_dir_str:
-            artifacts_dir = Path(artifacts_dir_str)
-            _download_artifacts(workflow_id, artifacts_dir)
-            install_binary_components(
-                artifacts_dir,
-                vendor_dir,
-                [BINARY_COMPONENTS[name] for name in components if name in BINARY_COMPONENTS],
-            )
+    with tempfile.TemporaryDirectory(prefix="codex-native-artifacts-") as artifacts_dir_str:
+        artifacts_dir = Path(artifacts_dir_str)
+        _download_artifacts(workflow_id, artifacts_dir)
+        install_binary_components(
+            artifacts_dir,
+            vendor_dir,
+            BINARY_TARGETS,
+            [name for name in components if name in BINARY_COMPONENTS],
+        )
 
     if "rg" in components:
-        with _gha_group("Fetch ripgrep binaries"):
-            print("Fetching ripgrep binaries...")
-            fetch_rg(vendor_dir, DEFAULT_RG_TARGETS, manifest_path=RG_MANIFEST)
+        print("Fetching ripgrep binaries...")
+        fetch_rg(vendor_dir, DEFAULT_RG_TARGETS, manifest_path=RG_MANIFEST)
 
     print(f"Installed native dependencies into {vendor_dir}")
     return 0
@@ -246,14 +183,7 @@ def fetch_rg(
 
         for future in as_completed(future_map):
             target = future_map[future]
-            try:
-                results[target] = future.result()
-            except Exception as exc:
-                _gha_error(
-                    title="ripgrep install failed",
-                    message=f"target={target} error={exc!r}",
-                )
-                raise RuntimeError(f"Failed to install ripgrep for target {target}.") from exc
+            results[target] = future.result()
             print(f"  installed ripgrep for {target}")
 
     return [results[target] for target in targets]
@@ -276,19 +206,23 @@ def _download_artifacts(workflow_id: str, dest_dir: Path) -> None:
 def install_binary_components(
     artifacts_dir: Path,
     vendor_dir: Path,
-    selected_components: Sequence[BinaryComponent],
+    targets: Iterable[str],
+    component_names: Sequence[str],
 ) -> None:
+    selected_components = [BINARY_COMPONENTS[name] for name in component_names if name in BINARY_COMPONENTS]
     if not selected_components:
         return
 
-    for component in selected_components:
-        component_targets = list(component.targets or BINARY_TARGETS)
+    targets = list(targets)
+    if not targets:
+        return
 
+    for component in selected_components:
         print(
             f"Installing {component.binary_basename} binaries for targets: "
-            + ", ".join(component_targets)
+            + ", ".join(targets)
         )
-        max_workers = min(len(component_targets), max(1, (os.cpu_count() or 1)))
+        max_workers = min(len(targets), max(1, (os.cpu_count() or 1)))
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             futures = {
                 executor.submit(
@@ -298,7 +232,7 @@ def install_binary_components(
                     target,
                     component,
                 ): target
-                for target in component_targets
+                for target in targets
             }
             for future in as_completed(futures):
                 installed_path = future.result()
@@ -351,8 +285,6 @@ def _fetch_single_rg(
     url = providers[0]["url"]
     archive_format = platform_info.get("format", "zst")
     archive_member = platform_info.get("path")
-    digest = platform_info.get("digest")
-    expected_size = platform_info.get("size")
 
     dest_dir = vendor_dir / target / "path"
     dest_dir.mkdir(parents=True, exist_ok=True)
@@ -365,32 +297,10 @@ def _fetch_single_rg(
         tmp_dir = Path(tmp_dir_str)
         archive_filename = os.path.basename(urlparse(url).path)
         download_path = tmp_dir / archive_filename
-        print(
-            f"  downloading ripgrep for {target} ({platform_key}) from {url}",
-            flush=True,
-        )
-        try:
-            _download_file(url, download_path)
-        except Exception as exc:
-            _gha_error(
-                title="ripgrep download failed",
-                message=f"target={target} platform={platform_key} url={url} error={exc!r}",
-            )
-            raise RuntimeError(
-                "Failed to download ripgrep "
-                f"(target={target}, platform={platform_key}, format={archive_format}, "
-                f"expected_size={expected_size!r}, digest={digest!r}, url={url}, dest={download_path})."
-            ) from exc
+        _download_file(url, download_path)
 
         dest.unlink(missing_ok=True)
-        try:
-            extract_archive(download_path, archive_format, archive_member, dest)
-        except Exception as exc:
-            raise RuntimeError(
-                "Failed to extract ripgrep "
-                f"(target={target}, platform={platform_key}, format={archive_format}, "
-                f"member={archive_member!r}, url={url}, archive={download_path})."
-            ) from exc
+        extract_archive(download_path, archive_format, archive_member, dest)
 
     if not is_windows:
         dest.chmod(0o755)
@@ -400,9 +310,7 @@ def _fetch_single_rg(
 
 def _download_file(url: str, dest: Path) -> None:
     dest.parent.mkdir(parents=True, exist_ok=True)
-    dest.unlink(missing_ok=True)
-
-    with urlopen(url, timeout=DOWNLOAD_TIMEOUT_SECS) as response, open(dest, "wb") as out:
+    with urlopen(url) as response, open(dest, "wb") as out:
         shutil.copyfileobj(response, out)
 
 

codex-rs/.cargo/audit.toml

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

codex-rs/.config/nextest.toml

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

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

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

codex-rs/Cargo.toml

@@ -5,7 +5,6 @@ members = [
     "async-utils",
     "app-server",
     "app-server-protocol",
-    "app-server-test-client",
     "apply-patch",
     "arg0",
     "feedback",
@@ -16,27 +15,22 @@ members = [
     "common",
     "core",
     "exec",
-    "exec-server",
     "execpolicy",
-    "execpolicy-legacy",
     "keyring-store",
     "file-search",
     "linux-sandbox",
-    "lmstudio",
     "login",
     "mcp-server",
     "mcp-types",
     "ollama",
     "process-hardening",
     "protocol",
+    "protocol-ts",
     "rmcp-client",
     "responses-api-proxy",
     "stdio-to-uds",
     "otel",
     "tui",
-    "tui2",
-    "utils/absolute-path",
-    "utils/cargo-bin",
     "utils/git",
     "utils/cache",
     "utils/image",
@@ -44,8 +38,7 @@ members = [
     "utils/pty",
     "utils/readiness",
     "utils/string",
-    "codex-client",
-    "codex-api",
+    "utils/tokenizer",
 ]
 resolver = "2"
 
@@ -56,13 +49,11 @@ version = "0.0.0"
 # crates created with `cargo new -w ...` automatically inherit the 2024
 # edition.
 edition = "2024"
-license = "Apache-2.0"
 
 [workspace.dependencies]
 # Internal
 app_test_support = { path = "app-server/tests/common" }
 codex-ansi-escape = { path = "ansi-escape" }
-codex-api = { path = "codex-api" }
 codex-app-server = { path = "app-server" }
 codex-app-server-protocol = { path = "app-server-protocol" }
 codex-apply-patch = { path = "apply-patch" }
@@ -70,39 +61,34 @@ codex-arg0 = { path = "arg0" }
 codex-async-utils = { path = "async-utils" }
 codex-backend-client = { path = "backend-client" }
 codex-chatgpt = { path = "chatgpt" }
-codex-client = { path = "codex-client" }
 codex-common = { path = "common" }
 codex-core = { path = "core" }
 codex-exec = { path = "exec" }
-codex-execpolicy = { path = "execpolicy" }
 codex-feedback = { path = "feedback" }
 codex-file-search = { path = "file-search" }
 codex-git = { path = "utils/git" }
 codex-keyring-store = { path = "keyring-store" }
 codex-linux-sandbox = { path = "linux-sandbox" }
-codex-lmstudio = { path = "lmstudio" }
 codex-login = { path = "login" }
 codex-mcp-server = { path = "mcp-server" }
 codex-ollama = { path = "ollama" }
 codex-otel = { path = "otel" }
 codex-process-hardening = { path = "process-hardening" }
 codex-protocol = { path = "protocol" }
+codex-protocol-ts = { path = "protocol-ts" }
 codex-responses-api-proxy = { path = "responses-api-proxy" }
 codex-rmcp-client = { path = "rmcp-client" }
 codex-stdio-to-uds = { path = "stdio-to-uds" }
 codex-tui = { path = "tui" }
-codex-tui2 = { path = "tui2" }
-codex-utils-absolute-path = { path = "utils/absolute-path" }
 codex-utils-cache = { path = "utils/cache" }
-codex-utils-cargo-bin = { path = "utils/cargo-bin" }
 codex-utils-image = { path = "utils/image" }
 codex-utils-json-to-toml = { path = "utils/json-to-toml" }
 codex-utils-pty = { path = "utils/pty" }
 codex-utils-readiness = { path = "utils/readiness" }
 codex-utils-string = { path = "utils/string" }
-codex-windows-sandbox = { path = "windows-sandbox-rs" }
+codex-utils-tokenizer = { path = "utils/tokenizer" }
+codex-windows-sandbox = { path = "windows-sandbox" }
 core_test_support = { path = "core/tests/common" }
-exec_server_test_support = { path = "exec-server/tests/common" }
 mcp-types = { path = "mcp-types" }
 mcp_test_support = { path = "mcp-server/tests/common" }
 
@@ -110,7 +96,8 @@ mcp_test_support = { path = "mcp-server/tests/common" }
 allocative = "0.3.3"
 ansi-to-tui = "7.0.0"
 anyhow = "1"
-arboard = { version = "3", features = ["wayland-data-control"] }
+arboard = "3"
+askama = "0.12"
 assert_cmd = "2"
 assert_matches = "1.5.0"
 async-channel = "2.3.1"
@@ -119,7 +106,6 @@ async-trait = "0.1.89"
 axum = { version = "0.8", default-features = false }
 base64 = "0.22.1"
 bytes = "1.10.1"
-chardetng = "0.1.17"
 chrono = "0.4.42"
 clap = "4"
 clap_complete = "4"
@@ -131,7 +117,6 @@ diffy = "0.4.2"
 dirs = "6"
 dotenvy = "0.15.7"
 dunce = "1.0.4"
-encoding_rs = "0.8.35"
 env-flags = "0.1.1"
 env_logger = "0.11.5"
 escargot = "0.5"
@@ -139,35 +124,33 @@ eventsource-stream = "0.2.3"
 futures = { version = "0.3", default-features = false }
 http = "1.3.1"
 icu_decimal = "2.1"
-icu_locale_core = "2.1"
 icu_provider = { version = "2.1", features = ["sync"] }
+icu_locale_core = "2.1"
 ignore = "0.4.23"
-image = { version = "^0.25.9", default-features = false }
-include_dir = "0.7.4"
+image = { version = "^0.25.8", default-features = false }
 indexmap = "2.12.0"
-insta = "1.46.0"
+insta = "1.43.2"
 itertools = "0.14.0"
-keyring = { version = "3.6", default-features = false }
-landlock = "0.4.4"
+keyring = "3.6"
+landlock = "0.4.1"
 lazy_static = "1"
-libc = "0.2.177"
+libc = "0.2.175"
 log = "0.4"
-lru = "0.16.2"
+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 = "1.20.2"
 openssl-sys = "*"
-opentelemetry = "0.31.0"
-opentelemetry-appender-tracing = "0.31.0"
-opentelemetry-otlp = "0.31.0"
-opentelemetry-semantic-conventions = "0.31.0"
-opentelemetry_sdk = "0.31.0"
-tracing-opentelemetry = "0.32.0"
+opentelemetry = "0.30.0"
+opentelemetry-appender-tracing = "0.30.0"
+opentelemetry-otlp = "0.30.0"
+opentelemetry-semantic-conventions = "0.30.0"
+opentelemetry_sdk = "0.30.0"
 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"
@@ -176,51 +159,47 @@ pretty_assertions = "1.4.1"
 pulldown-cmark = "0.10"
 rand = "0.9"
 ratatui = "0.29.0"
-ratatui-core = "0.1.0"
 ratatui-macros = "0.6.0"
-regex = "1.12.2"
-regex-lite = "0.1.8"
+regex-lite = "0.1.7"
 reqwest = "0.12"
-rmcp = { version = "0.12.0", default-features = false }
+rmcp = { version = "0.8.5", default-features = false }
 schemars = "0.8.22"
 seccompiler = "0.5.0"
-sentry = "0.46.0"
+sentry = "0.34.0"
 serde = "1"
 serde_json = "1"
-serde_with = "3.16"
-serde_yaml = "0.9"
+serde_with = "3.14"
 serial_test = "3.2.0"
 sha1 = "0.10.6"
 sha2 = "0.10"
 shlex = "1.3.0"
 similar = "2.7.0"
-socket2 = "0.6.1"
 starlark = "0.13.0"
 strum = "0.27.2"
 strum_macros = "0.27.2"
 supports-color = "3.0.2"
 sys-locale = "0.3.2"
 tempfile = "3.23.0"
-test-log = "0.2.19"
+test-log = "0.2.18"
 textwrap = "0.16.2"
 thiserror = "2.0.17"
 time = "0.3"
 tiny_http = "0.12"
 tokio = "1"
-tokio-stream = "0.1.18"
+tokio-stream = "0.1.17"
 tokio-test = "0.4"
 tokio-util = "0.7.16"
 toml = "0.9.5"
-toml_edit = "0.24.0"
-tracing = "0.1.43"
+toml_edit = "0.23.4"
+tonic = "0.13.1"
+tracing = "0.1.41"
 tracing-appender = "0.2.3"
-tracing-subscriber = "0.3.22"
+tracing-subscriber = "0.3.20"
 tracing-test = "0.2.5"
 tree-sitter = "0.25.10"
 tree-sitter-bash = "0.25"
 tree-sitter-highlight = "0.25.10"
 ts-rs = "11"
-tui-scrollbar = "0.2.1"
 uds_windows = "1.1.0"
 unicode-segmentation = "1.12.0"
 unicode-width = "0.2"
@@ -231,10 +210,10 @@ vt100 = "0.16.2"
 walkdir = "2.5.0"
 webbrowser = "1.0"
 which = "6"
-wildmatch = "2.6.1"
+wildmatch = "2.5.0"
 
 wiremock = "0.6"
-zeroize = "1.8.2"
+zeroize = "1.8.1"
 
 [workspace.lints]
 rust = {}
@@ -277,7 +256,12 @@ 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 = ["icu_provider", "openssl-sys", "codex-utils-readiness"]
+ignored = [
+    "icu_provider",
+    "openssl-sys",
+    "codex-utils-readiness",
+    "codex-utils-tokenizer",
+]
 
 [profile.release]
 lto = "fat"
@@ -296,8 +280,8 @@ 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" }
+crossterm = { git = "https://github.com/nornagon/crossterm", branch = "nornagon/color-query" }
 
 # Uncomment to debug local changes.
 # rmcp = { path = "../../rust-sdk/crates/rmcp" }

codex-rs/README.md

@@ -15,8 +15,8 @@ You can also install via Homebrew (`brew install --cask codex`) or download a pl
 
 ## Documentation quickstart
 
-- First run with Codex? Start with [`docs/getting-started.md`](../docs/getting-started.md) (links to the walkthrough for prompts, keyboard shortcuts, and session management).
-- Want deeper control? See [`docs/config.md`](../docs/config.md) and [`docs/install.md`](../docs/install.md).
+- First run with Codex? Follow the walkthrough in [`docs/getting-started.md`](../docs/getting-started.md) for prompts, keyboard shortcuts, and session management.
+- Already shipping with Codex and want deeper control? Jump to [`docs/advanced.md`](../docs/advanced.md) and the configuration reference at [`docs/config.md`](../docs/config.md).
 
 ## What's new in the Rust CLI
 
@@ -30,7 +30,7 @@ Codex supports a rich set of configuration options. Note that the Rust CLI uses
 
 #### MCP client
 
-Codex CLI functions as an MCP client that allows the Codex CLI and IDE extension to connect to MCP servers on startup. See the [`configuration documentation`](../docs/config.md#connecting-to-mcp-servers) for details.
+Codex CLI functions as an MCP client that allows the Codex CLI and IDE extension to connect to MCP servers on startup. See the [`configuration documentation`](../docs/config.md#mcp_servers) for details.
 
 #### MCP server (experimental)
 
@@ -46,7 +46,7 @@ Use `codex mcp` to add/list/get/remove MCP server launchers defined in `config.t
 
 ### Notifications
 
-You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS. When Codex detects that it is running under WSL 2 inside Windows Terminal (`WT_SESSION` is set), the TUI automatically falls back to native Windows toast notifications so approval prompts and completed turns surface even though Windows Terminal does not implement OSC 9.
+You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The [notify documentation](../docs/config.md#notify) includes a detailed example that explains how to get desktop notifications via [terminal-notifier](https://github.com/julienXX/terminal-notifier) on macOS.
 
 ### `codex exec` to run Codex programmatically/non-interactively
 
@@ -58,7 +58,7 @@ To test to see what happens when a command is run under the sandbox provided by
 
 ```
 # macOS
-codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...
+codex sandbox macos [--full-auto] [COMMAND]...
 
 # Linux
 codex sandbox linux [--full-auto] [COMMAND]...
@@ -67,7 +67,7 @@ codex sandbox linux [--full-auto] [COMMAND]...
 codex sandbox windows [--full-auto] [COMMAND]...
 
 # Legacy aliases
-codex debug seatbelt [--full-auto] [--log-denials] [COMMAND]...
+codex debug seatbelt [--full-auto] [COMMAND]...
 codex debug landlock [--full-auto] [COMMAND]...
 ```
 

codex-rs/ansi-escape/Cargo.toml

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

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

@@ -1,8 +1,7 @@
 [package]
+edition = "2024"
 name = "codex-app-server-protocol"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
+version = { workspace = true }
 
 [lib]
 name = "codex_app_server_protocol"
@@ -15,13 +14,12 @@ workspace = true
 anyhow = { workspace = true }
 clap = { workspace = true, features = ["derive"] }
 codex-protocol = { workspace = true }
-codex-utils-absolute-path = { workspace = true }
 mcp-types = { workspace = true }
+paste = { workspace = true }
 schemars = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
 strum_macros = { workspace = true }
-thiserror = { workspace = true }
 ts-rs = { workspace = true }
 uuid = { workspace = true, features = ["serde", "v7"] }
 

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

@@ -13,7 +13,10 @@ use crate::export_server_responses;
 use anyhow::Context;
 use anyhow::Result;
 use anyhow::anyhow;
+use codex_protocol::parse_command::ParsedCommand;
 use codex_protocol::protocol::EventMsg;
+use codex_protocol::protocol::FileChange;
+use codex_protocol::protocol::SandboxPolicy;
 use schemars::JsonSchema;
 use schemars::schema_for;
 use serde::Serialize;
@@ -31,7 +34,6 @@ use std::process::Command;
 use ts_rs::TS;
 
 const HEADER: &str = "// GENERATED CODE! DO NOT MODIFY BY HAND!\n\n";
-const IGNORED_DEFINITIONS: &[&str] = &["Option<()>"];
 
 #[derive(Clone)]
 pub struct GeneratedSchema {
@@ -62,32 +64,7 @@ pub fn generate_types(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
     Ok(())
 }
 
-#[derive(Clone, Copy, Debug)]
-pub struct GenerateTsOptions {
-    pub generate_indices: bool,
-    pub ensure_headers: bool,
-    pub run_prettier: bool,
-}
-
-impl Default for GenerateTsOptions {
-    fn default() -> Self {
-        Self {
-            generate_indices: true,
-            ensure_headers: true,
-            run_prettier: true,
-        }
-    }
-}
-
 pub fn generate_ts(out_dir: &Path, prettier: Option<&Path>) -> Result<()> {
-    generate_ts_with_options(out_dir, prettier, GenerateTsOptions::default())
-}
-
-pub fn generate_ts_with_options(
-    out_dir: &Path,
-    prettier: Option<&Path>,
-    options: GenerateTsOptions,
-) -> Result<()> {
     let v2_out_dir = out_dir.join("v2");
     ensure_dir(out_dir)?;
     ensure_dir(&v2_out_dir)?;
@@ -100,34 +77,21 @@ pub fn generate_ts_with_options(
     export_server_responses(out_dir)?;
     ServerNotification::export_all_to(out_dir)?;
 
-    if options.generate_indices {
-        generate_index_ts(out_dir)?;
-        generate_index_ts(&v2_out_dir)?;
-    }
+    generate_index_ts(out_dir)?;
+    generate_index_ts(&v2_out_dir)?;
 
     // Ensure our header is present on all TS files (root + subdirs like v2/).
-    let mut ts_files = Vec::new();
-    let should_collect_ts_files =
-        options.ensure_headers || (options.run_prettier && prettier.is_some());
-    if should_collect_ts_files {
-        ts_files = ts_files_in_recursive(out_dir)?;
-    }
-
-    if options.ensure_headers {
-        for file in &ts_files {
-            prepend_header_if_missing(file)?;
-        }
+    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 options.run_prettier
-        && let Some(prettier_bin) = prettier
+    if let Some(prettier_bin) = prettier
         && !ts_files.is_empty()
     {
         let status = Command::new(prettier_bin)
             .arg("--write")
-            .arg("--log-level")
-            .arg("warn")
             .args(ts_files.iter().map(|p| p.as_os_str()))
             .status()
             .with_context(|| format!("Failed to invoke Prettier at {}", prettier_bin.display()))?;
@@ -154,6 +118,10 @@ pub fn generate_json(out_dir: &Path) -> Result<()> {
         |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"),
+        |d| write_json_schema_with_return::<FileChange>(d, "FileChange"),
+        |d| write_json_schema_with_return::<crate::protocol::v1::InputItem>(d, "InputItem"),
+        |d| write_json_schema_with_return::<ParsedCommand>(d, "ParsedCommand"),
+        |d| write_json_schema_with_return::<SandboxPolicy>(d, "SandboxPolicy"),
     ];
 
     let mut schemas: Vec<GeneratedSchema> = Vec::new();
@@ -182,6 +150,10 @@ fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<Value> {
         "ClientNotification",
         "ClientRequest",
         "EventMsg",
+        "FileChange",
+        "InputItem",
+        "ParsedCommand",
+        "SandboxPolicy",
         "ServerNotification",
         "ServerRequest",
     ];
@@ -197,10 +169,6 @@ fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<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);
         }
@@ -211,9 +179,6 @@ fn build_schema_bundle(schemas: Vec<GeneratedSchema>) -> Result<Value> {
             && let Value::Object(defs_obj) = defs
         {
             for (def_name, mut def_schema) in defs_obj {
-                if IGNORED_DEFINITIONS.contains(&def_name.as_str()) {
-                    continue;
-                }
                 if SPECIAL_DEFINITIONS.contains(&def_name.as_str()) {
                     continue;
                 }
@@ -304,11 +269,8 @@ where
         out_dir.join(format!("{file_stem}.json"))
     };
 
-    if !IGNORED_DEFINITIONS.contains(&logical_name) {
-        write_pretty_json(out_path, &schema_value)
-            .with_context(|| format!("Failed to write JSON schema for {file_stem}"))?;
-    }
-
+    write_pretty_json(out_path, &schema_value)
+        .with_context(|| format!("Failed to write JSON schema for {file_stem}"))?;
     let namespace = match raw_namespace {
         Some("v1") | None => None,
         Some(ns) => Some(ns.to_string()),
@@ -422,6 +384,14 @@ fn variant_definition_name(base: &str, variant: &Value) -> Option<String> {
             });
         }
 
+        if let Some(mode_literal) = literal_from_property(props, "mode") {
+            let pascal = to_pascal_case(mode_literal);
+            return Some(match base {
+                "SandboxPolicy" => format!("{pascal}SandboxPolicy"),
+                _ => format!("{pascal}{base}"),
+            });
+        }
+
         if props.len() == 1
             && let Some(key) = props.keys().next()
         {
@@ -696,8 +666,6 @@ fn ts_files_in_recursive(dir: &Path) -> Result<Vec<PathBuf>> {
     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)?
@@ -762,13 +730,7 @@ mod tests {
 
         let _guard = TempDirGuard(output_dir.clone());
 
-        // Avoid doing more work than necessary to keep the test from timing out.
-        let options = GenerateTsOptions {
-            generate_indices: false,
-            ensure_headers: false,
-            run_prettier: false,
-        };
-        generate_ts_with_options(&output_dir, None, options)?;
+        generate_ts(&output_dir, None)?;
 
         let mut undefined_offenders = Vec::new();
         let mut optional_nullable_offenders = BTreeSet::new();

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

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

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

@@ -1,4 +1,6 @@
+use std::collections::HashMap;
 use std::path::Path;
+use std::path::PathBuf;
 
 use crate::JSONRPCNotification;
 use crate::JSONRPCRequest;
@@ -7,6 +9,12 @@ use crate::export::GeneratedSchema;
 use crate::export::write_json_schema;
 use crate::protocol::v1;
 use crate::protocol::v2;
+use codex_protocol::ConversationId;
+use codex_protocol::parse_command::ParsedCommand;
+use codex_protocol::protocol::FileChange;
+use codex_protocol::protocol::ReviewDecision;
+use codex_protocol::protocol::SandboxCommandAssessment;
+use paste::paste;
 use schemars::JsonSchema;
 use serde::Deserialize;
 use serde::Serialize;
@@ -38,7 +46,7 @@ macro_rules! client_request_definitions {
     (
         $(
             $(#[$variant_meta:meta])*
-            $variant:ident $(=> $wire:literal)? {
+            $variant:ident {
                 params: $(#[$params_meta:meta])* $params:ty,
                 response: $response:ty,
             }
@@ -50,7 +58,6 @@ macro_rules! client_request_definitions {
         pub enum ClientRequest {
             $(
                 $(#[$variant_meta])*
-                $(#[serde(rename = $wire)] #[ts(rename = $wire)])?
                 $variant {
                     #[serde(rename = "id")]
                     request_id: RequestId,
@@ -94,111 +101,105 @@ macro_rules! client_request_definitions {
 }
 
 client_request_definitions! {
-    Initialize {
-        params: v1::InitializeParams,
-        response: v1::InitializeResponse,
-    },
-
     /// NEW APIs
     // Thread lifecycle
-    ThreadStart => "thread/start" {
+    #[serde(rename = "thread/start")]
+    #[ts(rename = "thread/start")]
+    ThreadStart {
         params: v2::ThreadStartParams,
         response: v2::ThreadStartResponse,
     },
-    ThreadResume => "thread/resume" {
+    #[serde(rename = "thread/resume")]
+    #[ts(rename = "thread/resume")]
+    ThreadResume {
         params: v2::ThreadResumeParams,
         response: v2::ThreadResumeResponse,
     },
-    ThreadArchive => "thread/archive" {
+    #[serde(rename = "thread/archive")]
+    #[ts(rename = "thread/archive")]
+    ThreadArchive {
         params: v2::ThreadArchiveParams,
         response: v2::ThreadArchiveResponse,
     },
-    ThreadList => "thread/list" {
+    #[serde(rename = "thread/list")]
+    #[ts(rename = "thread/list")]
+    ThreadList {
         params: v2::ThreadListParams,
         response: v2::ThreadListResponse,
     },
-    SkillsList => "skills/list" {
-        params: v2::SkillsListParams,
-        response: v2::SkillsListResponse,
+    #[serde(rename = "thread/compact")]
+    #[ts(rename = "thread/compact")]
+    ThreadCompact {
+        params: v2::ThreadCompactParams,
+        response: v2::ThreadCompactResponse,
     },
-    TurnStart => "turn/start" {
+    #[serde(rename = "turn/start")]
+    #[ts(rename = "turn/start")]
+    TurnStart {
         params: v2::TurnStartParams,
         response: v2::TurnStartResponse,
     },
-    TurnInterrupt => "turn/interrupt" {
+    #[serde(rename = "turn/interrupt")]
+    #[ts(rename = "turn/interrupt")]
+    TurnInterrupt {
         params: v2::TurnInterruptParams,
         response: v2::TurnInterruptResponse,
     },
-    ReviewStart => "review/start" {
-        params: v2::ReviewStartParams,
-        response: v2::ReviewStartResponse,
-    },
 
-    ModelList => "model/list" {
+    #[serde(rename = "model/list")]
+    #[ts(rename = "model/list")]
+    ModelList {
         params: v2::ModelListParams,
         response: v2::ModelListResponse,
     },
 
-    McpServerOauthLogin => "mcpServer/oauth/login" {
-        params: v2::McpServerOauthLoginParams,
-        response: v2::McpServerOauthLoginResponse,
-    },
-
-    McpServerStatusList => "mcpServerStatus/list" {
-        params: v2::ListMcpServerStatusParams,
-        response: v2::ListMcpServerStatusResponse,
-    },
-
-    LoginAccount => "account/login/start" {
+    #[serde(rename = "account/login/start")]
+    #[ts(rename = "account/login/start")]
+    LoginAccount {
         params: v2::LoginAccountParams,
         response: v2::LoginAccountResponse,
     },
 
-    CancelLoginAccount => "account/login/cancel" {
+    #[serde(rename = "account/login/cancel")]
+    #[ts(rename = "account/login/cancel")]
+    CancelLoginAccount {
         params: v2::CancelLoginAccountParams,
         response: v2::CancelLoginAccountResponse,
     },
 
-    LogoutAccount => "account/logout" {
+    #[serde(rename = "account/logout")]
+    #[ts(rename = "account/logout")]
+    LogoutAccount {
         params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
         response: v2::LogoutAccountResponse,
     },
 
-    GetAccountRateLimits => "account/rateLimits/read" {
+    #[serde(rename = "account/rateLimits/read")]
+    #[ts(rename = "account/rateLimits/read")]
+    GetAccountRateLimits {
         params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
         response: v2::GetAccountRateLimitsResponse,
     },
 
-    FeedbackUpload => "feedback/upload" {
+    #[serde(rename = "feedback/upload")]
+    #[ts(rename = "feedback/upload")]
+    FeedbackUpload {
         params: v2::FeedbackUploadParams,
         response: v2::FeedbackUploadResponse,
     },
 
-    /// Execute a command (argv vector) under the server's sandbox.
-    OneOffCommandExec => "command/exec" {
-        params: v2::CommandExecParams,
-        response: v2::CommandExecResponse,
-    },
-
-    ConfigRead => "config/read" {
-        params: v2::ConfigReadParams,
-        response: v2::ConfigReadResponse,
-    },
-    ConfigValueWrite => "config/value/write" {
-        params: v2::ConfigValueWriteParams,
-        response: v2::ConfigWriteResponse,
-    },
-    ConfigBatchWrite => "config/batchWrite" {
-        params: v2::ConfigBatchWriteParams,
-        response: v2::ConfigWriteResponse,
-    },
-
-    GetAccount => "account/read" {
-        params: v2::GetAccountParams,
+    #[serde(rename = "account/read")]
+    #[ts(rename = "account/read")]
+    GetAccount {
+        params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
         response: v2::GetAccountResponse,
     },
 
     /// DEPRECATED APIs below
+    Initialize {
+        params: v1::InitializeParams,
+        response: v1::InitializeResponse,
+    },
     NewConversation {
         params: v1::NewConversationParams,
         response: v1::NewConversationResponse,
@@ -262,7 +263,6 @@ client_request_definitions! {
         params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
         response: v1::LogoutChatGptResponse,
     },
-    /// DEPRECATED in favor of GetAccount
     GetAuthStatus {
         params: v1::GetAuthStatusParams,
         response: v1::GetAuthStatusResponse,
@@ -302,36 +302,34 @@ macro_rules! server_request_definitions {
     (
         $(
             $(#[$variant_meta:meta])*
-            $variant:ident $(=> $wire:literal)? {
-                params: $params:ty,
-                response: $response:ty,
-            }
+            $variant:ident
         ),* $(,)?
     ) => {
-        /// Request initiated from the server and sent to the client.
-        #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
-        #[serde(tag = "method", rename_all = "camelCase")]
-        pub enum ServerRequest {
-            $(
-                $(#[$variant_meta])*
-                $(#[serde(rename = $wire)] #[ts(rename = $wire)])?
-                $variant {
-                    #[serde(rename = "id")]
-                    request_id: RequestId,
-                    params: $params,
-                },
-            )*
-        }
+        paste! {
+            /// Request initiated from the server and sent to the client.
+            #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+            #[serde(tag = "method", rename_all = "camelCase")]
+            pub enum ServerRequest {
+                $(
+                    $(#[$variant_meta])*
+                    $variant {
+                        #[serde(rename = "id")]
+                        request_id: RequestId,
+                        params: [<$variant Params>],
+                    },
+                )*
+            }
 
-        #[derive(Debug, Clone, PartialEq, JsonSchema)]
-        pub enum ServerRequestPayload {
-            $( $variant($params), )*
-        }
+            #[derive(Debug, Clone, PartialEq, JsonSchema)]
+            pub enum ServerRequestPayload {
+                $( $variant([<$variant Params>]), )*
+            }
 
-        impl ServerRequestPayload {
-            pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
-                match self {
-                    $(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
+            impl ServerRequestPayload {
+                pub fn request_with_id(self, request_id: RequestId) -> ServerRequest {
+                    match self {
+                        $(Self::$variant(params) => ServerRequest::$variant { request_id, params },)*
+                    }
                 }
             }
         }
@@ -339,9 +337,9 @@ macro_rules! server_request_definitions {
         pub fn export_server_responses(
             out_dir: &::std::path::Path,
         ) -> ::std::result::Result<(), ::ts_rs::ExportError> {
-            $(
-                <$response as ::ts_rs::TS>::export_all_to(out_dir)?;
-            )*
+            paste! {
+                $(<[<$variant Response>] as ::ts_rs::TS>::export_all_to(out_dir)?;)*
+            }
             Ok(())
         }
 
@@ -350,12 +348,9 @@ macro_rules! server_request_definitions {
             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"),
-                )?);
-            )*
+            paste! {
+                $(schemas.push(crate::export::write_json_schema::<[<$variant Response>]>(out_dir, stringify!([<$variant Response>]))?);)*
+            }
             Ok(schemas)
         }
 
@@ -364,12 +359,9 @@ macro_rules! server_request_definitions {
             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"),
-                )?);
-            )*
+            paste! {
+                $(schemas.push(crate::export::write_json_schema::<[<$variant Params>]>(out_dir, stringify!([<$variant Params>]))?);)*
+            }
             Ok(schemas)
         }
     };
@@ -407,7 +399,7 @@ macro_rules! server_notification_definitions {
         impl TryFrom<JSONRPCNotification> for ServerNotification {
             type Error = serde_json::Error;
 
-            fn try_from(value: JSONRPCNotification) -> Result<Self, serde_json::Error> {
+            fn try_from(value: JSONRPCNotification) -> Result<Self, Self::Error> {
                 serde_json::from_value(serde_json::to_value(value)?)
             }
         }
@@ -459,34 +451,49 @@ impl TryFrom<JSONRPCRequest> for ServerRequest {
 }
 
 server_request_definitions! {
-    /// NEW APIs
-    /// Sent when approval is requested for a specific command execution.
-    /// This request is used for Turns started via turn/start.
-    CommandExecutionRequestApproval => "item/commandExecution/requestApproval" {
-        params: v2::CommandExecutionRequestApprovalParams,
-        response: v2::CommandExecutionRequestApprovalResponse,
-    },
-
-    /// Sent when approval is requested for a specific file change.
-    /// This request is used for Turns started via turn/start.
-    FileChangeRequestApproval => "item/fileChange/requestApproval" {
-        params: v2::FileChangeRequestApprovalParams,
-        response: v2::FileChangeRequestApprovalResponse,
-    },
-
-    /// DEPRECATED APIs below
     /// Request to approve a patch.
-    /// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
-    ApplyPatchApproval {
-        params: v1::ApplyPatchApprovalParams,
-        response: v1::ApplyPatchApprovalResponse,
-    },
+    ApplyPatchApproval,
     /// Request to exec a command.
-    /// This request is used for Turns started via the legacy APIs (i.e. SendUserTurn, SendUserMessage).
-    ExecCommandApproval {
-        params: v1::ExecCommandApprovalParams,
-        response: v1::ExecCommandApprovalResponse,
-    },
+    ExecCommandApproval,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ApplyPatchApprovalParams {
+    pub conversation_id: ConversationId,
+    /// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
+    /// and [codex_core::protocol::PatchApplyEndEvent].
+    pub call_id: String,
+    pub file_changes: HashMap<PathBuf, FileChange>,
+    /// Optional explanatory reason (e.g. request for extra write access).
+    pub reason: Option<String>,
+    /// When set, the agent is asking the user to allow writes under this root
+    /// for the remainder of the session (unclear if this is honored today).
+    pub grant_root: Option<PathBuf>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ExecCommandApprovalParams {
+    pub conversation_id: ConversationId,
+    /// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
+    /// and [codex_core::protocol::ExecCommandEndEvent].
+    pub call_id: String,
+    pub command: Vec<String>,
+    pub cwd: PathBuf,
+    pub reason: Option<String>,
+    pub risk: Option<SandboxCommandAssessment>,
+    pub parsed_cmd: Vec<ParsedCommand>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+pub struct ExecCommandApprovalResponse {
+    pub decision: ReviewDecision,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+pub struct ApplyPatchApprovalResponse {
+    pub decision: ReviewDecision,
 }
 
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
@@ -516,33 +523,16 @@ pub struct FuzzyFileSearchResponse {
 
 server_notification_definitions! {
     /// NEW NOTIFICATIONS
-    Error => "error" (v2::ErrorNotification),
     ThreadStarted => "thread/started" (v2::ThreadStartedNotification),
-    ThreadTokenUsageUpdated => "thread/tokenUsage/updated" (v2::ThreadTokenUsageUpdatedNotification),
     TurnStarted => "turn/started" (v2::TurnStartedNotification),
     TurnCompleted => "turn/completed" (v2::TurnCompletedNotification),
-    TurnDiffUpdated => "turn/diff/updated" (v2::TurnDiffUpdatedNotification),
-    TurnPlanUpdated => "turn/plan/updated" (v2::TurnPlanUpdatedNotification),
     ItemStarted => "item/started" (v2::ItemStartedNotification),
     ItemCompleted => "item/completed" (v2::ItemCompletedNotification),
-    /// This event is internal-only. Used by Codex Cloud.
-    RawResponseItemCompleted => "rawResponseItem/completed" (v2::RawResponseItemCompletedNotification),
     AgentMessageDelta => "item/agentMessage/delta" (v2::AgentMessageDeltaNotification),
     CommandExecutionOutputDelta => "item/commandExecution/outputDelta" (v2::CommandExecutionOutputDeltaNotification),
-    TerminalInteraction => "item/commandExecution/terminalInteraction" (v2::TerminalInteractionNotification),
-    FileChangeOutputDelta => "item/fileChange/outputDelta" (v2::FileChangeOutputDeltaNotification),
     McpToolCallProgress => "item/mcpToolCall/progress" (v2::McpToolCallProgressNotification),
-    McpServerOauthLoginCompleted => "mcpServer/oauthLogin/completed" (v2::McpServerOauthLoginCompletedNotification),
     AccountUpdated => "account/updated" (v2::AccountUpdatedNotification),
     AccountRateLimitsUpdated => "account/rateLimits/updated" (v2::AccountRateLimitsUpdatedNotification),
-    ReasoningSummaryTextDelta => "item/reasoning/summaryTextDelta" (v2::ReasoningSummaryTextDeltaNotification),
-    ReasoningSummaryPartAdded => "item/reasoning/summaryPartAdded" (v2::ReasoningSummaryPartAddedNotification),
-    ReasoningTextDelta => "item/reasoning/textDelta" (v2::ReasoningTextDeltaNotification),
-    ContextCompacted => "thread/compacted" (v2::ContextCompactedNotification),
-    DeprecationNotice => "deprecationNotice" (v2::DeprecationNoticeNotification),
-
-    /// Notifies the user of world-writable directories on Windows, which cannot be protected by the sandbox.
-    WindowsWorldWritableWarning => "windows/worldWritableWarning" (v2::WindowsWorldWritableWarningNotification),
 
     #[serde(rename = "account/login/completed")]
     #[ts(rename = "account/login/completed")]
@@ -565,20 +555,17 @@ client_notification_definitions! {
 mod tests {
     use super::*;
     use anyhow::Result;
-    use codex_protocol::ConversationId;
     use codex_protocol::account::PlanType;
-    use codex_protocol::parse_command::ParsedCommand;
     use codex_protocol::protocol::AskForApproval;
     use pretty_assertions::assert_eq;
     use serde_json::json;
-    use std::path::PathBuf;
 
     #[test]
     fn serialize_new_conversation() -> Result<()> {
         let request = ClientRequest::NewConversation {
             request_id: RequestId::Integer(42),
             params: v1::NewConversationParams {
-                model: Some("gpt-5.1-codex-max".to_string()),
+                model: Some("gpt-5-codex".to_string()),
                 model_provider: None,
                 profile: None,
                 cwd: None,
@@ -596,7 +583,7 @@ mod tests {
                 "method": "newConversation",
                 "id": 42,
                 "params": {
-                    "model": "gpt-5.1-codex-max",
+                    "model": "gpt-5-codex",
                     "modelProvider": null,
                     "profile": null,
                     "cwd": null,
@@ -651,12 +638,13 @@ mod tests {
     #[test]
     fn serialize_server_request() -> Result<()> {
         let conversation_id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
-        let params = v1::ExecCommandApprovalParams {
+        let params = ExecCommandApprovalParams {
             conversation_id,
             call_id: "call-42".to_string(),
             command: vec!["echo".to_string(), "hello".to_string()],
             cwd: PathBuf::from("/tmp"),
             reason: Some("because tests".to_string()),
+            risk: None,
             parsed_cmd: vec![ParsedCommand::Unknown {
                 cmd: "echo hello".to_string(),
             }],
@@ -676,6 +664,7 @@ mod tests {
                     "command": ["echo", "hello"],
                     "cwd": "/tmp",
                     "reason": "because tests",
+                    "risk": null,
                     "parsedCmd": [
                         {
                             "type": "unknown",
@@ -769,17 +758,12 @@ mod tests {
     fn serialize_get_account() -> Result<()> {
         let request = ClientRequest::GetAccount {
             request_id: RequestId::Integer(5),
-            params: v2::GetAccountParams {
-                refresh_token: false,
-            },
+            params: None,
         };
         assert_eq!(
             json!({
                 "method": "account/read",
                 "id": 5,
-                "params": {
-                    "refreshToken": false
-                }
             }),
             serde_json::to_value(&request)?,
         );
@@ -788,16 +772,19 @@ mod tests {
 
     #[test]
     fn account_serializes_fields_in_camel_case() -> Result<()> {
-        let api_key = v2::Account::ApiKey {};
+        let api_key = v2::Account::ApiKey {
+            api_key: "secret".to_string(),
+        };
         assert_eq!(
             json!({
                 "type": "apiKey",
+                "apiKey": "secret",
             }),
             serde_json::to_value(&api_key)?,
         );
 
         let chatgpt = v2::Account::Chatgpt {
-            email: "user@example.com".to_string(),
+            email: Some("user@example.com".to_string()),
             plan_type: PlanType::Plus,
         };
         assert_eq!(

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

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

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

@@ -2,7 +2,5 @@
 // Exposes protocol pieces used by `lib.rs` via `pub use protocol::common::*;`.
 
 pub mod common;
-mod mappers;
-pub mod thread_history;
 pub mod v1;
 pub mod v2;

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

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

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

@@ -3,20 +3,15 @@ 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::openai_models::ReasoningEffort;
-use codex_protocol::parse_command::ParsedCommand;
 use codex_protocol::protocol::AskForApproval;
 use codex_protocol::protocol::EventMsg;
-use codex_protocol::protocol::FileChange;
-use codex_protocol::protocol::ReviewDecision;
 use codex_protocol::protocol::SandboxPolicy;
-use codex_protocol::protocol::SessionSource;
 use codex_protocol::protocol::TurnAbortReason;
-use codex_utils_absolute_path::AbsolutePathBuf;
 use schemars::JsonSchema;
 use serde::Deserialize;
 use serde::Serialize;
@@ -118,18 +113,6 @@ pub struct ConversationSummary {
     pub preview: String,
     pub timestamp: Option<String>,
     pub model_provider: String,
-    pub cwd: PathBuf,
-    pub cli_version: String,
-    pub source: SessionSource,
-    pub git_info: Option<ConversationGitInfo>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
-#[serde(rename_all = "snake_case")]
-pub struct ConversationGitInfo {
-    pub sha: Option<String>,
-    pub branch: Option<String>,
-    pub origin_url: Option<String>,
 }
 
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
@@ -195,45 +178,6 @@ pub struct GitDiffToRemoteResponse {
     pub diff: String,
 }
 
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ApplyPatchApprovalParams {
-    pub conversation_id: ConversationId,
-    /// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
-    /// and [codex_core::protocol::PatchApplyEndEvent].
-    pub call_id: String,
-    pub file_changes: HashMap<PathBuf, FileChange>,
-    /// Optional explanatory reason (e.g. request for extra write access).
-    pub reason: Option<String>,
-    /// When set, the agent is asking the user to allow writes under this root
-    /// for the remainder of the session (unclear if this is honored today).
-    pub grant_root: Option<PathBuf>,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ApplyPatchApprovalResponse {
-    pub decision: ReviewDecision,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
-#[serde(rename_all = "camelCase")]
-pub struct ExecCommandApprovalParams {
-    pub conversation_id: ConversationId,
-    /// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
-    /// and [codex_core::protocol::ExecCommandEndEvent].
-    pub call_id: String,
-    pub command: Vec<String>,
-    pub cwd: PathBuf,
-    pub reason: Option<String>,
-    pub 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 {
@@ -360,7 +304,7 @@ pub struct Tools {
 #[serde(rename_all = "camelCase")]
 pub struct SandboxSettings {
     #[serde(default)]
-    pub writable_roots: Vec<AbsolutePathBuf>,
+    pub writable_roots: Vec<PathBuf>,
     pub network_access: Option<bool>,
     pub exclude_tmpdir_env_var: Option<bool>,
     pub exclude_slash_tmp: Option<bool>,
@@ -384,8 +328,6 @@ pub struct SendUserTurnParams {
     pub model: String,
     pub effort: Option<ReasoningEffort>,
     pub summary: ReasoningSummary,
-    /// Optional JSON Schema used to constrain the final assistant message for this turn.
-    pub output_schema: Option<serde_json::Value>,
 }
 
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]

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

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

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

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

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

@@ -1,911 +0,0 @@
-use std::collections::VecDeque;
-use std::io::BufRead;
-use std::io::BufReader;
-use std::io::Write;
-use std::process::Child;
-use std::process::ChildStdin;
-use std::process::ChildStdout;
-use std::process::Command;
-use std::process::Stdio;
-use std::thread;
-use std::time::Duration;
-
-use anyhow::Context;
-use anyhow::Result;
-use anyhow::bail;
-use clap::ArgAction;
-use clap::Parser;
-use clap::Subcommand;
-use codex_app_server_protocol::AddConversationListenerParams;
-use codex_app_server_protocol::AddConversationSubscriptionResponse;
-use codex_app_server_protocol::ApprovalDecision;
-use codex_app_server_protocol::AskForApproval;
-use codex_app_server_protocol::ClientInfo;
-use codex_app_server_protocol::ClientRequest;
-use codex_app_server_protocol::CommandExecutionRequestApprovalParams;
-use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
-use codex_app_server_protocol::FileChangeRequestApprovalParams;
-use codex_app_server_protocol::FileChangeRequestApprovalResponse;
-use codex_app_server_protocol::GetAccountRateLimitsResponse;
-use codex_app_server_protocol::InitializeParams;
-use codex_app_server_protocol::InitializeResponse;
-use codex_app_server_protocol::InputItem;
-use codex_app_server_protocol::JSONRPCMessage;
-use codex_app_server_protocol::JSONRPCNotification;
-use codex_app_server_protocol::JSONRPCRequest;
-use codex_app_server_protocol::JSONRPCResponse;
-use codex_app_server_protocol::LoginChatGptCompleteNotification;
-use codex_app_server_protocol::LoginChatGptResponse;
-use codex_app_server_protocol::NewConversationParams;
-use codex_app_server_protocol::NewConversationResponse;
-use codex_app_server_protocol::RequestId;
-use codex_app_server_protocol::SandboxPolicy;
-use codex_app_server_protocol::SendUserMessageParams;
-use codex_app_server_protocol::SendUserMessageResponse;
-use codex_app_server_protocol::ServerNotification;
-use codex_app_server_protocol::ServerRequest;
-use codex_app_server_protocol::ThreadStartParams;
-use codex_app_server_protocol::ThreadStartResponse;
-use codex_app_server_protocol::TurnStartParams;
-use codex_app_server_protocol::TurnStartResponse;
-use codex_app_server_protocol::TurnStatus;
-use codex_app_server_protocol::UserInput as V2UserInput;
-use codex_protocol::ConversationId;
-use codex_protocol::protocol::Event;
-use codex_protocol::protocol::EventMsg;
-use serde::Serialize;
-use serde::de::DeserializeOwned;
-use serde_json::Value;
-use uuid::Uuid;
-
-/// Minimal launcher that initializes the Codex app-server and logs the handshake.
-#[derive(Parser)]
-#[command(author = "Codex", version, about = "Bootstrap Codex app-server", long_about = None)]
-struct Cli {
-    /// Path to the `codex` CLI binary.
-    #[arg(long, env = "CODEX_BIN", default_value = "codex")]
-    codex_bin: String,
-
-    /// Forwarded to the `codex` CLI as `--config key=value`. Repeatable.
-    ///
-    /// Example:
-    ///   `--config 'model_providers.mock.base_url="http://localhost:4010/v2"'`
-    #[arg(
-        short = 'c',
-        long = "config",
-        value_name = "key=value",
-        action = ArgAction::Append,
-        global = true
-    )]
-    config_overrides: Vec<String>,
-
-    #[command(subcommand)]
-    command: CliCommand,
-}
-
-#[derive(Subcommand)]
-enum CliCommand {
-    /// Send a user message through the Codex app-server.
-    SendMessage {
-        /// User message to send to Codex.
-        #[arg()]
-        user_message: String,
-    },
-    /// Send a user message through the app-server V2 thread/turn APIs.
-    SendMessageV2 {
-        /// User message to send to Codex.
-        #[arg()]
-        user_message: String,
-    },
-    /// Start a V2 turn that elicits an ExecCommand approval.
-    #[command(name = "trigger-cmd-approval")]
-    TriggerCmdApproval {
-        /// Optional prompt; defaults to a simple python command.
-        #[arg()]
-        user_message: Option<String>,
-    },
-    /// Start a V2 turn that elicits an ApplyPatch approval.
-    #[command(name = "trigger-patch-approval")]
-    TriggerPatchApproval {
-        /// Optional prompt; defaults to creating a file via apply_patch.
-        #[arg()]
-        user_message: Option<String>,
-    },
-    /// Start a V2 turn that should not elicit an ExecCommand approval.
-    #[command(name = "no-trigger-cmd-approval")]
-    NoTriggerCmdApproval,
-    /// Send two sequential V2 turns in the same thread to test follow-up behavior.
-    SendFollowUpV2 {
-        /// Initial user message for the first turn.
-        #[arg()]
-        first_message: String,
-        /// Follow-up user message for the second turn.
-        #[arg()]
-        follow_up_message: String,
-    },
-    /// Trigger the ChatGPT login flow and wait for completion.
-    TestLogin,
-    /// Fetch the current account rate limits from the Codex app-server.
-    GetAccountRateLimits,
-}
-
-fn main() -> Result<()> {
-    let Cli {
-        codex_bin,
-        config_overrides,
-        command,
-    } = Cli::parse();
-
-    match command {
-        CliCommand::SendMessage { user_message } => {
-            send_message(&codex_bin, &config_overrides, user_message)
-        }
-        CliCommand::SendMessageV2 { user_message } => {
-            send_message_v2(&codex_bin, &config_overrides, user_message)
-        }
-        CliCommand::TriggerCmdApproval { user_message } => {
-            trigger_cmd_approval(&codex_bin, &config_overrides, user_message)
-        }
-        CliCommand::TriggerPatchApproval { user_message } => {
-            trigger_patch_approval(&codex_bin, &config_overrides, user_message)
-        }
-        CliCommand::NoTriggerCmdApproval => no_trigger_cmd_approval(&codex_bin, &config_overrides),
-        CliCommand::SendFollowUpV2 {
-            first_message,
-            follow_up_message,
-        } => send_follow_up_v2(
-            &codex_bin,
-            &config_overrides,
-            first_message,
-            follow_up_message,
-        ),
-        CliCommand::TestLogin => test_login(&codex_bin, &config_overrides),
-        CliCommand::GetAccountRateLimits => get_account_rate_limits(&codex_bin, &config_overrides),
-    }
-}
-
-fn send_message(codex_bin: &str, config_overrides: &[String], user_message: String) -> Result<()> {
-    let mut client = CodexClient::spawn(codex_bin, config_overrides)?;
-
-    let initialize = client.initialize()?;
-    println!("< initialize response: {initialize:?}");
-
-    let conversation = client.new_conversation()?;
-    println!("< newConversation response: {conversation:?}");
-
-    let subscription = client.add_conversation_listener(&conversation.conversation_id)?;
-    println!("< addConversationListener response: {subscription:?}");
-
-    let send_response = client.send_user_message(&conversation.conversation_id, &user_message)?;
-    println!("< sendUserMessage response: {send_response:?}");
-
-    client.stream_conversation(&conversation.conversation_id)?;
-
-    client.remove_conversation_listener(subscription.subscription_id)?;
-
-    Ok(())
-}
-
-fn send_message_v2(
-    codex_bin: &str,
-    config_overrides: &[String],
-    user_message: String,
-) -> Result<()> {
-    send_message_v2_with_policies(codex_bin, config_overrides, user_message, None, None)
-}
-
-fn trigger_cmd_approval(
-    codex_bin: &str,
-    config_overrides: &[String],
-    user_message: Option<String>,
-) -> Result<()> {
-    let default_prompt =
-        "Run `touch /tmp/should-trigger-approval` so I can confirm the file exists.";
-    let message = user_message.unwrap_or_else(|| default_prompt.to_string());
-    send_message_v2_with_policies(
-        codex_bin,
-        config_overrides,
-        message,
-        Some(AskForApproval::OnRequest),
-        Some(SandboxPolicy::ReadOnly),
-    )
-}
-
-fn trigger_patch_approval(
-    codex_bin: &str,
-    config_overrides: &[String],
-    user_message: Option<String>,
-) -> Result<()> {
-    let default_prompt =
-        "Create a file named APPROVAL_DEMO.txt containing a short hello message using apply_patch.";
-    let message = user_message.unwrap_or_else(|| default_prompt.to_string());
-    send_message_v2_with_policies(
-        codex_bin,
-        config_overrides,
-        message,
-        Some(AskForApproval::OnRequest),
-        Some(SandboxPolicy::ReadOnly),
-    )
-}
-
-fn no_trigger_cmd_approval(codex_bin: &str, config_overrides: &[String]) -> Result<()> {
-    let prompt = "Run `touch should_not_trigger_approval.txt`";
-    send_message_v2_with_policies(codex_bin, config_overrides, prompt.to_string(), None, None)
-}
-
-fn send_message_v2_with_policies(
-    codex_bin: &str,
-    config_overrides: &[String],
-    user_message: String,
-    approval_policy: Option<AskForApproval>,
-    sandbox_policy: Option<SandboxPolicy>,
-) -> Result<()> {
-    let mut client = CodexClient::spawn(codex_bin, config_overrides)?;
-
-    let initialize = client.initialize()?;
-    println!("< initialize response: {initialize:?}");
-
-    let thread_response = client.thread_start(ThreadStartParams::default())?;
-    println!("< thread/start response: {thread_response:?}");
-    let mut turn_params = TurnStartParams {
-        thread_id: thread_response.thread.id.clone(),
-        input: vec![V2UserInput::Text { text: user_message }],
-        ..Default::default()
-    };
-    turn_params.approval_policy = approval_policy;
-    turn_params.sandbox_policy = sandbox_policy;
-
-    let turn_response = client.turn_start(turn_params)?;
-    println!("< turn/start response: {turn_response:?}");
-
-    client.stream_turn(&thread_response.thread.id, &turn_response.turn.id)?;
-
-    Ok(())
-}
-
-fn send_follow_up_v2(
-    codex_bin: &str,
-    config_overrides: &[String],
-    first_message: String,
-    follow_up_message: String,
-) -> Result<()> {
-    let mut client = CodexClient::spawn(codex_bin, config_overrides)?;
-
-    let initialize = client.initialize()?;
-    println!("< initialize response: {initialize:?}");
-
-    let thread_response = client.thread_start(ThreadStartParams::default())?;
-    println!("< thread/start response: {thread_response:?}");
-
-    let first_turn_params = TurnStartParams {
-        thread_id: thread_response.thread.id.clone(),
-        input: vec![V2UserInput::Text {
-            text: first_message,
-        }],
-        ..Default::default()
-    };
-    let first_turn_response = client.turn_start(first_turn_params)?;
-    println!("< turn/start response (initial): {first_turn_response:?}");
-    client.stream_turn(&thread_response.thread.id, &first_turn_response.turn.id)?;
-
-    let follow_up_params = TurnStartParams {
-        thread_id: thread_response.thread.id.clone(),
-        input: vec![V2UserInput::Text {
-            text: follow_up_message,
-        }],
-        ..Default::default()
-    };
-    let follow_up_response = client.turn_start(follow_up_params)?;
-    println!("< turn/start response (follow-up): {follow_up_response:?}");
-    client.stream_turn(&thread_response.thread.id, &follow_up_response.turn.id)?;
-
-    Ok(())
-}
-
-fn test_login(codex_bin: &str, config_overrides: &[String]) -> Result<()> {
-    let mut client = CodexClient::spawn(codex_bin, config_overrides)?;
-
-    let initialize = client.initialize()?;
-    println!("< initialize response: {initialize:?}");
-
-    let login_response = client.login_chat_gpt()?;
-    println!("< loginChatGpt response: {login_response:?}");
-    println!(
-        "Open the following URL in your browser to continue:\n{}",
-        login_response.auth_url
-    );
-
-    let completion = client.wait_for_login_completion(&login_response.login_id)?;
-    println!("< loginChatGptComplete notification: {completion:?}");
-
-    if completion.success {
-        println!("Login succeeded.");
-        Ok(())
-    } else {
-        bail!(
-            "login failed: {}",
-            completion
-                .error
-                .as_deref()
-                .unwrap_or("unknown error from loginChatGptComplete")
-        );
-    }
-}
-
-fn get_account_rate_limits(codex_bin: &str, config_overrides: &[String]) -> Result<()> {
-    let mut client = CodexClient::spawn(codex_bin, config_overrides)?;
-
-    let initialize = client.initialize()?;
-    println!("< initialize response: {initialize:?}");
-
-    let response = client.get_account_rate_limits()?;
-    println!("< account/rateLimits/read response: {response:?}");
-
-    Ok(())
-}
-
-struct CodexClient {
-    child: Child,
-    stdin: Option<ChildStdin>,
-    stdout: BufReader<ChildStdout>,
-    pending_notifications: VecDeque<JSONRPCNotification>,
-}
-
-impl CodexClient {
-    fn spawn(codex_bin: &str, config_overrides: &[String]) -> Result<Self> {
-        let mut cmd = Command::new(codex_bin);
-        for override_kv in config_overrides {
-            cmd.arg("--config").arg(override_kv);
-        }
-        let mut codex_app_server = cmd
-            .arg("app-server")
-            .stdin(Stdio::piped())
-            .stdout(Stdio::piped())
-            .stderr(Stdio::inherit())
-            .spawn()
-            .with_context(|| format!("failed to start `{codex_bin}` app-server"))?;
-
-        let stdin = codex_app_server
-            .stdin
-            .take()
-            .context("codex app-server stdin unavailable")?;
-        let stdout = codex_app_server
-            .stdout
-            .take()
-            .context("codex app-server stdout unavailable")?;
-
-        Ok(Self {
-            child: codex_app_server,
-            stdin: Some(stdin),
-            stdout: BufReader::new(stdout),
-            pending_notifications: VecDeque::new(),
-        })
-    }
-
-    fn initialize(&mut self) -> Result<InitializeResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::Initialize {
-            request_id: request_id.clone(),
-            params: InitializeParams {
-                client_info: ClientInfo {
-                    name: "codex-toy-app-server".to_string(),
-                    title: Some("Codex Toy App Server".to_string()),
-                    version: env!("CARGO_PKG_VERSION").to_string(),
-                },
-            },
-        };
-
-        self.send_request(request, request_id, "initialize")
-    }
-
-    fn new_conversation(&mut self) -> Result<NewConversationResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::NewConversation {
-            request_id: request_id.clone(),
-            params: NewConversationParams::default(),
-        };
-
-        self.send_request(request, request_id, "newConversation")
-    }
-
-    fn add_conversation_listener(
-        &mut self,
-        conversation_id: &ConversationId,
-    ) -> Result<AddConversationSubscriptionResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::AddConversationListener {
-            request_id: request_id.clone(),
-            params: AddConversationListenerParams {
-                conversation_id: *conversation_id,
-                experimental_raw_events: false,
-            },
-        };
-
-        self.send_request(request, request_id, "addConversationListener")
-    }
-
-    fn remove_conversation_listener(&mut self, subscription_id: Uuid) -> Result<()> {
-        let request_id = self.request_id();
-        let request = ClientRequest::RemoveConversationListener {
-            request_id: request_id.clone(),
-            params: codex_app_server_protocol::RemoveConversationListenerParams { subscription_id },
-        };
-
-        self.send_request::<codex_app_server_protocol::RemoveConversationSubscriptionResponse>(
-            request,
-            request_id,
-            "removeConversationListener",
-        )?;
-
-        Ok(())
-    }
-
-    fn send_user_message(
-        &mut self,
-        conversation_id: &ConversationId,
-        message: &str,
-    ) -> Result<SendUserMessageResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::SendUserMessage {
-            request_id: request_id.clone(),
-            params: SendUserMessageParams {
-                conversation_id: *conversation_id,
-                items: vec![InputItem::Text {
-                    text: message.to_string(),
-                }],
-            },
-        };
-
-        self.send_request(request, request_id, "sendUserMessage")
-    }
-
-    fn thread_start(&mut self, params: ThreadStartParams) -> Result<ThreadStartResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::ThreadStart {
-            request_id: request_id.clone(),
-            params,
-        };
-
-        self.send_request(request, request_id, "thread/start")
-    }
-
-    fn turn_start(&mut self, params: TurnStartParams) -> Result<TurnStartResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::TurnStart {
-            request_id: request_id.clone(),
-            params,
-        };
-
-        self.send_request(request, request_id, "turn/start")
-    }
-
-    fn login_chat_gpt(&mut self) -> Result<LoginChatGptResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::LoginChatGpt {
-            request_id: request_id.clone(),
-            params: None,
-        };
-
-        self.send_request(request, request_id, "loginChatGpt")
-    }
-
-    fn get_account_rate_limits(&mut self) -> Result<GetAccountRateLimitsResponse> {
-        let request_id = self.request_id();
-        let request = ClientRequest::GetAccountRateLimits {
-            request_id: request_id.clone(),
-            params: None,
-        };
-
-        self.send_request(request, request_id, "account/rateLimits/read")
-    }
-
-    fn stream_conversation(&mut self, conversation_id: &ConversationId) -> Result<()> {
-        loop {
-            let notification = self.next_notification()?;
-
-            if !notification.method.starts_with("codex/event/") {
-                continue;
-            }
-
-            if let Some(event) = self.extract_event(notification, conversation_id)? {
-                match &event.msg {
-                    EventMsg::AgentMessage(event) => {
-                        println!("{}", event.message);
-                    }
-                    EventMsg::AgentMessageDelta(event) => {
-                        print!("{}", event.delta);
-                        std::io::stdout().flush().ok();
-                    }
-                    EventMsg::TaskComplete(event) => {
-                        println!("\n[task complete: {event:?}]");
-                        break;
-                    }
-                    EventMsg::TurnAborted(event) => {
-                        println!("\n[turn aborted: {:?}]", event.reason);
-                        break;
-                    }
-                    EventMsg::Error(event) => {
-                        println!("[error] {event:?}");
-                    }
-                    _ => {
-                        println!("[UNKNOWN EVENT] {:?}", event.msg);
-                    }
-                }
-            }
-        }
-
-        Ok(())
-    }
-
-    fn wait_for_login_completion(
-        &mut self,
-        expected_login_id: &Uuid,
-    ) -> Result<LoginChatGptCompleteNotification> {
-        loop {
-            let notification = self.next_notification()?;
-
-            if let Ok(server_notification) = ServerNotification::try_from(notification) {
-                match server_notification {
-                    ServerNotification::LoginChatGptComplete(completion) => {
-                        if &completion.login_id == expected_login_id {
-                            return Ok(completion);
-                        }
-
-                        println!(
-                            "[ignoring loginChatGptComplete for unexpected login_id: {}]",
-                            completion.login_id
-                        );
-                    }
-                    ServerNotification::AuthStatusChange(status) => {
-                        println!("< authStatusChange notification: {status:?}");
-                    }
-                    ServerNotification::AccountRateLimitsUpdated(snapshot) => {
-                        println!("< accountRateLimitsUpdated notification: {snapshot:?}");
-                    }
-                    ServerNotification::SessionConfigured(_) => {
-                        // SessionConfigured notifications are unrelated to login; skip.
-                    }
-                    _ => {}
-                }
-            }
-
-            // Not a server notification (likely a conversation event); keep waiting.
-        }
-    }
-
-    fn stream_turn(&mut self, thread_id: &str, turn_id: &str) -> Result<()> {
-        loop {
-            let notification = self.next_notification()?;
-
-            let Ok(server_notification) = ServerNotification::try_from(notification) else {
-                continue;
-            };
-
-            match server_notification {
-                ServerNotification::ThreadStarted(payload) => {
-                    if payload.thread.id == thread_id {
-                        println!("< thread/started notification: {:?}", payload.thread);
-                    }
-                }
-                ServerNotification::TurnStarted(payload) => {
-                    if payload.turn.id == turn_id {
-                        println!("< turn/started notification: {:?}", payload.turn.status);
-                    }
-                }
-                ServerNotification::AgentMessageDelta(delta) => {
-                    print!("{}", delta.delta);
-                    std::io::stdout().flush().ok();
-                }
-                ServerNotification::CommandExecutionOutputDelta(delta) => {
-                    print!("{}", delta.delta);
-                    std::io::stdout().flush().ok();
-                }
-                ServerNotification::TerminalInteraction(delta) => {
-                    println!("[stdin sent: {}]", delta.stdin);
-                    std::io::stdout().flush().ok();
-                }
-                ServerNotification::ItemStarted(payload) => {
-                    println!("\n< item started: {:?}", payload.item);
-                }
-                ServerNotification::ItemCompleted(payload) => {
-                    println!("< item completed: {:?}", payload.item);
-                }
-                ServerNotification::TurnCompleted(payload) => {
-                    if payload.turn.id == turn_id {
-                        println!("\n< turn/completed notification: {:?}", payload.turn.status);
-                        if payload.turn.status == TurnStatus::Failed
-                            && let Some(error) = payload.turn.error
-                        {
-                            println!("[turn error] {}", error.message);
-                        }
-                        break;
-                    }
-                }
-                ServerNotification::McpToolCallProgress(payload) => {
-                    println!("< MCP tool progress: {}", payload.message);
-                }
-                _ => {
-                    println!("[UNKNOWN SERVER NOTIFICATION] {server_notification:?}");
-                }
-            }
-        }
-
-        Ok(())
-    }
-
-    fn extract_event(
-        &self,
-        notification: JSONRPCNotification,
-        conversation_id: &ConversationId,
-    ) -> Result<Option<Event>> {
-        let params = notification
-            .params
-            .context("event notification missing params")?;
-
-        let mut map = match params {
-            Value::Object(map) => map,
-            other => bail!("unexpected params shape: {other:?}"),
-        };
-
-        let conversation_value = map
-            .remove("conversationId")
-            .context("event missing conversationId")?;
-        let notification_conversation: ConversationId = serde_json::from_value(conversation_value)
-            .context("conversationId was not a valid UUID")?;
-
-        if &notification_conversation != conversation_id {
-            return Ok(None);
-        }
-
-        let event_value = Value::Object(map);
-        let event: Event =
-            serde_json::from_value(event_value).context("failed to decode event payload")?;
-        Ok(Some(event))
-    }
-
-    fn send_request<T>(
-        &mut self,
-        request: ClientRequest,
-        request_id: RequestId,
-        method: &str,
-    ) -> Result<T>
-    where
-        T: DeserializeOwned,
-    {
-        self.write_request(&request)?;
-        self.wait_for_response(request_id, method)
-    }
-
-    fn write_request(&mut self, request: &ClientRequest) -> Result<()> {
-        let request_json = serde_json::to_string(request)?;
-        let request_pretty = serde_json::to_string_pretty(request)?;
-        print_multiline_with_prefix("> ", &request_pretty);
-
-        if let Some(stdin) = self.stdin.as_mut() {
-            writeln!(stdin, "{request_json}")?;
-            stdin
-                .flush()
-                .context("failed to flush request to codex app-server")?;
-        } else {
-            bail!("codex app-server stdin closed");
-        }
-
-        Ok(())
-    }
-
-    fn wait_for_response<T>(&mut self, request_id: RequestId, method: &str) -> Result<T>
-    where
-        T: DeserializeOwned,
-    {
-        loop {
-            let message = self.read_jsonrpc_message()?;
-
-            match message {
-                JSONRPCMessage::Response(JSONRPCResponse { id, result }) => {
-                    if id == request_id {
-                        return serde_json::from_value(result)
-                            .with_context(|| format!("{method} response missing payload"));
-                    }
-                }
-                JSONRPCMessage::Error(err) => {
-                    if err.id == request_id {
-                        bail!("{method} failed: {err:?}");
-                    }
-                }
-                JSONRPCMessage::Notification(notification) => {
-                    self.pending_notifications.push_back(notification);
-                }
-                JSONRPCMessage::Request(request) => {
-                    self.handle_server_request(request)?;
-                }
-            }
-        }
-    }
-
-    fn next_notification(&mut self) -> Result<JSONRPCNotification> {
-        if let Some(notification) = self.pending_notifications.pop_front() {
-            return Ok(notification);
-        }
-
-        loop {
-            let message = self.read_jsonrpc_message()?;
-
-            match message {
-                JSONRPCMessage::Notification(notification) => return Ok(notification),
-                JSONRPCMessage::Response(_) | JSONRPCMessage::Error(_) => {
-                    // No outstanding requests, so ignore stray responses/errors for now.
-                    continue;
-                }
-                JSONRPCMessage::Request(request) => {
-                    self.handle_server_request(request)?;
-                }
-            }
-        }
-    }
-
-    fn read_jsonrpc_message(&mut self) -> Result<JSONRPCMessage> {
-        loop {
-            let mut response_line = String::new();
-            let bytes = self
-                .stdout
-                .read_line(&mut response_line)
-                .context("failed to read from codex app-server")?;
-
-            if bytes == 0 {
-                bail!("codex app-server closed stdout");
-            }
-
-            let trimmed = response_line.trim();
-            if trimmed.is_empty() {
-                continue;
-            }
-
-            let parsed: Value =
-                serde_json::from_str(trimmed).context("response was not valid JSON-RPC")?;
-            let pretty = serde_json::to_string_pretty(&parsed)?;
-            print_multiline_with_prefix("< ", &pretty);
-            let message: JSONRPCMessage = serde_json::from_value(parsed)
-                .context("response was not a valid JSON-RPC message")?;
-            return Ok(message);
-        }
-    }
-
-    fn request_id(&self) -> RequestId {
-        RequestId::String(Uuid::new_v4().to_string())
-    }
-
-    fn handle_server_request(&mut self, request: JSONRPCRequest) -> Result<()> {
-        let server_request = ServerRequest::try_from(request)
-            .context("failed to deserialize ServerRequest from JSONRPCRequest")?;
-
-        match server_request {
-            ServerRequest::CommandExecutionRequestApproval { request_id, params } => {
-                self.handle_command_execution_request_approval(request_id, params)?;
-            }
-            ServerRequest::FileChangeRequestApproval { request_id, params } => {
-                self.approve_file_change_request(request_id, params)?;
-            }
-            other => {
-                bail!("received unsupported server request: {other:?}");
-            }
-        }
-
-        Ok(())
-    }
-
-    fn handle_command_execution_request_approval(
-        &mut self,
-        request_id: RequestId,
-        params: CommandExecutionRequestApprovalParams,
-    ) -> Result<()> {
-        let CommandExecutionRequestApprovalParams {
-            thread_id,
-            turn_id,
-            item_id,
-            reason,
-            proposed_execpolicy_amendment,
-        } = params;
-
-        println!(
-            "\n< commandExecution approval requested for thread {thread_id}, turn {turn_id}, item {item_id}"
-        );
-        if let Some(reason) = reason.as_deref() {
-            println!("< reason: {reason}");
-        }
-        if let Some(execpolicy_amendment) = proposed_execpolicy_amendment.as_ref() {
-            println!("< proposed execpolicy amendment: {execpolicy_amendment:?}");
-        }
-
-        let response = CommandExecutionRequestApprovalResponse {
-            decision: ApprovalDecision::Accept,
-        };
-        self.send_server_request_response(request_id, &response)?;
-        println!("< approved commandExecution request for item {item_id}");
-        Ok(())
-    }
-
-    fn approve_file_change_request(
-        &mut self,
-        request_id: RequestId,
-        params: FileChangeRequestApprovalParams,
-    ) -> Result<()> {
-        let FileChangeRequestApprovalParams {
-            thread_id,
-            turn_id,
-            item_id,
-            reason,
-            grant_root,
-        } = params;
-
-        println!(
-            "\n< fileChange approval requested for thread {thread_id}, turn {turn_id}, item {item_id}"
-        );
-        if let Some(reason) = reason.as_deref() {
-            println!("< reason: {reason}");
-        }
-        if let Some(grant_root) = grant_root.as_deref() {
-            println!("< grant root: {}", grant_root.display());
-        }
-
-        let response = FileChangeRequestApprovalResponse {
-            decision: ApprovalDecision::Accept,
-        };
-        self.send_server_request_response(request_id, &response)?;
-        println!("< approved fileChange request for item {item_id}");
-        Ok(())
-    }
-
-    fn send_server_request_response<T>(&mut self, request_id: RequestId, response: &T) -> Result<()>
-    where
-        T: Serialize,
-    {
-        let message = JSONRPCMessage::Response(JSONRPCResponse {
-            id: request_id,
-            result: serde_json::to_value(response)?,
-        });
-        self.write_jsonrpc_message(message)
-    }
-
-    fn write_jsonrpc_message(&mut self, message: JSONRPCMessage) -> Result<()> {
-        let payload = serde_json::to_string(&message)?;
-        let pretty = serde_json::to_string_pretty(&message)?;
-        print_multiline_with_prefix("> ", &pretty);
-
-        if let Some(stdin) = self.stdin.as_mut() {
-            writeln!(stdin, "{payload}")?;
-            stdin
-                .flush()
-                .context("failed to flush response to codex app-server")?;
-            return Ok(());
-        }
-
-        bail!("codex app-server stdin closed")
-    }
-}
-
-fn print_multiline_with_prefix(prefix: &str, payload: &str) {
-    for line in payload.lines() {
-        println!("{prefix}{line}");
-    }
-}
-
-impl Drop for CodexClient {
-    fn drop(&mut self) {
-        let _ = self.stdin.take();
-
-        if let Ok(Some(status)) = self.child.try_wait() {
-            println!("[codex app-server exited: {status}]");
-            return;
-        }
-
-        thread::sleep(Duration::from_millis(100));
-
-        if let Ok(Some(status)) = self.child.try_wait() {
-            println!("[codex app-server exited: {status}]");
-            return;
-        }
-
-        let _ = self.child.kill();
-        let _ = self.child.wait();
-    }
-}

codex-rs/app-server/Cargo.toml

@@ -1,8 +1,7 @@
 [package]
+edition = "2024"
 name = "codex-app-server"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
+version = { workspace = true }
 
 [[bin]]
 name = "codex-app-server"
@@ -26,15 +25,10 @@ codex-login = { workspace = true }
 codex-protocol = { workspace = true }
 codex-app-server-protocol = { workspace = true }
 codex-feedback = { workspace = true }
-codex-rmcp-client = { workspace = true }
-codex-utils-absolute-path = { workspace = true }
 codex-utils-json-to-toml = { workspace = true }
 chrono = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
-mcp-types = { workspace = true }
-tempfile = { workspace = true }
-toml = { workspace = true }
 tokio = { workspace = true, features = [
     "io-std",
     "macros",
@@ -44,15 +38,17 @@ tokio = { workspace = true, features = [
 ] }
 tracing = { workspace = true, features = ["log"] }
 tracing-subscriber = { workspace = true, features = ["env-filter", "fmt"] }
+opentelemetry-appender-tracing = { workspace = true }
 uuid = { workspace = true, features = ["serde", "v7"] }
 
 [dev-dependencies]
 app_test_support = { workspace = true }
+assert_cmd = { workspace = true }
 base64 = { workspace = true }
 core_test_support = { workspace = true }
-mcp-types = { workspace = true }
 os_info = { workspace = true }
 pretty_assertions = { workspace = true }
 serial_test = { workspace = true }
+tempfile = { workspace = true }
+toml = { workspace = true }
 wiremock = { workspace = true }
-shlex = { workspace = true }

codex-rs/app-server/README.md

@@ -1,17 +1,6 @@
 # codex-app-server
 
-`codex app-server` is the interface Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt).
-
-## Table of Contents
-
-- [Protocol](#protocol)
-- [Message Schema](#message-schema)
-- [Core Primitives](#core-primitives)
-- [Lifecycle Overview](#lifecycle-overview)
-- [Initialization](#initialization)
-- [API Overview](#api-overview)
-- [Events](#events)
-- [Auth endpoints](#auth-endpoints)
+`codex app-server` is the harness Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt). The message schema is currently unstable, but those who wish to build experimental UIs on top of Codex may find it valuable.
 
 ## Protocol
 
@@ -19,488 +8,8 @@ Similar to [MCP](https://modelcontextprotocol.io/), `codex app-server` supports
 
 ## Message Schema
 
-Currently, you can dump a TypeScript version of the schema using `codex app-server generate-ts`, or a JSON Schema bundle via `codex app-server generate-json-schema`. Each output is specific to the version of Codex you used to run the command, so the generated artifacts are guaranteed to match that version.
+Currently, you can dump a TypeScript version of the schema using `codex generate-ts`. It is specific to the version of Codex you used to run `generate-ts`, so the two are guaranteed to be compatible.
 
 ```
-codex app-server generate-ts --out DIR
-codex app-server generate-json-schema --out DIR
+codex generate-ts --out DIR
 ```
-
-## Core Primitives
-
-The API exposes three top level primitives representing an interaction between a user and Codex:
-
-- **Thread**: A conversation between a user and the Codex agent. Each thread contains multiple turns.
-- **Turn**: One turn of the conversation, typically starting with a user message and finishing with an agent message. Each turn contains multiple items.
-- **Item**: Represents user inputs and agent outputs as part of the turn, persisted and used as the context for future conversations. Example items include user message, agent reasoning, agent message, shell command, file edit, etc.
-
-Use the thread APIs to create, list, or archive conversations. Drive a conversation with turn APIs and stream progress via turn notifications.
-
-## Lifecycle Overview
-
-- Initialize once: Immediately after launching the codex app-server process, send an `initialize` request with your client metadata, then emit an `initialized` notification. Any other request before this handshake gets rejected.
-- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead.
-- Begin a turn: To send user input, call `turn/start` with the target `threadId` and the user's input. Optional fields let you override model, cwd, sandbox policy, etc. This immediately returns the new turn object and triggers a `turn/started` notification.
-- Stream events: After `turn/start`, keep reading JSON-RPC notifications on stdout. You’ll see `item/started`, `item/completed`, deltas like `item/agentMessage/delta`, tool progress, etc. These represent streaming model output plus any side effects (commands, tool calls, reasoning notes).
-- Finish the turn: When the model is done (or the turn is interrupted via making the `turn/interrupt` call), the server sends `turn/completed` with the final turn state and token usage.
-
-## Initialization
-
-Clients must send a single `initialize` request before invoking any other method, then acknowledge with an `initialized` notification. The server returns the user agent string it will present to upstream services; subsequent requests issued before initialization receive a `"Not initialized"` error, and repeated `initialize` calls receive an `"Already initialized"` error.
-
-Applications building on top of `codex app-server` should identify themselves via the `clientInfo` parameter.
-
-Example (from OpenAI's official VSCode extension):
-
-```json
-{
-  "method": "initialize",
-  "id": 0,
-  "params": {
-    "clientInfo": {
-      "name": "codex-vscode",
-      "title": "Codex VS Code Extension",
-      "version": "0.1.0"
-    }
-  }
-}
-```
-
-## API Overview
-
-- `thread/start` — create a new thread; emits `thread/started` and auto-subscribes you to turn/item events for that thread.
-- `thread/resume` — reopen an existing thread by id so subsequent `turn/start` calls append to it.
-- `thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
-- `thread/archive` — move a thread’s rollout file into the archived directory; returns `{}` on success.
-- `turn/start` — add user input to a thread and begin Codex generation; responds with the initial `turn` object and streams `turn/started`, `item/*`, and `turn/completed` notifications.
-- `turn/interrupt` — request cancellation of an in-flight turn by `(thread_id, turn_id)`; success is an empty `{}` response and the turn finishes with `status: "interrupted"`.
-- `review/start` — kick off Codex’s automated reviewer for a thread; responds like `turn/start` and emits `item/started`/`item/completed` notifications with `enteredReviewMode` and `exitedReviewMode` items, plus a final assistant `agentMessage` containing the review.
-- `command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
-- `model/list` — list available models (with reasoning effort options).
-- `skills/list` — list skills for one or more `cwd` values (optional `forceReload`).
-- `mcpServer/oauth/login` — start an OAuth login for a configured MCP server; returns an `authorization_url` and later emits `mcpServer/oauthLogin/completed` once the browser flow finishes.
-- `mcpServerStatus/list` — enumerate configured MCP servers with their tools, resources, resource templates, and auth status; supports cursor+limit pagination.
-- `feedback/upload` — submit a feedback report (classification + optional reason/logs and conversation_id); returns the tracking thread id.
-- `command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
-- `config/read` — fetch the effective config on disk after resolving config layering (thread-agnostic; does not include in-repo `.codex/` layers).
-- `config/value/write` — write a single config key/value to the user's config.toml on disk.
-- `config/batchWrite` — apply multiple config edits atomically to the user's config.toml on disk.
-
-### Example: Start or resume a thread
-
-Start a fresh thread when you need a new Codex conversation.
-
-```json
-{ "method": "thread/start", "id": 10, "params": {
-    // Optionally set config settings. If not specified, will use the user's
-    // current config settings.
-    "model": "gpt-5.1-codex",
-    "cwd": "/Users/me/project",
-    "approvalPolicy": "never",
-    "sandbox": "workspaceWrite",
-} }
-{ "id": 10, "result": {
-    "thread": {
-        "id": "thr_123",
-        "preview": "",
-        "modelProvider": "openai",
-        "createdAt": 1730910000
-    }
-} }
-{ "method": "thread/started", "params": { "thread": { … } } }
-```
-
-To continue a stored session, call `thread/resume` with the `thread.id` you previously recorded. The response shape matches `thread/start`, and no additional notifications are emitted:
-
-```json
-{ "method": "thread/resume", "id": 11, "params": { "threadId": "thr_123" } }
-{ "id": 11, "result": { "thread": { "id": "thr_123", … } } }
-```
-
-### Example: List threads (with pagination & filters)
-
-`thread/list` lets you render a history UI. Pass any combination of:
-
-- `cursor` — opaque string from a prior response; omit for the first page.
-- `limit` — server defaults to a reasonable page size if unset.
-- `modelProviders` — restrict results to specific providers; unset, null, or an empty array will include all providers.
-
-Example:
-
-```json
-{ "method": "thread/list", "id": 20, "params": {
-    "cursor": null,
-    "limit": 25,
-} }
-{ "id": 20, "result": {
-    "data": [
-        { "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111 },
-        { "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000 }
-    ],
-    "nextCursor": "opaque-token-or-null"
-} }
-```
-
-When `nextCursor` is `null`, you’ve reached the final page.
-
-### Example: Archive a thread
-
-Use `thread/archive` to move the persisted rollout (stored as a JSONL file on disk) into the archived sessions directory.
-
-```json
-{ "method": "thread/archive", "id": 21, "params": { "threadId": "thr_b" } }
-{ "id": 21, "result": {} }
-```
-
-An archived thread will not appear in future calls to `thread/list`.
-
-### Example: Start a turn (send user input)
-
-Turns attach user input (text or images) to a thread and trigger Codex generation. The `input` field is a list of discriminated unions:
-
-- `{"type":"text","text":"Explain this diff"}`
-- `{"type":"image","url":"https://…png"}`
-- `{"type":"localImage","path":"/tmp/screenshot.png"}`
-
-You can optionally specify config overrides on the new turn. If specified, these settings become the default for subsequent turns on the same thread. `outputSchema` applies only to the current turn.
-
-```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": {
-        "type": "workspaceWrite",
-        "writableRoots": ["/Users/me/project"],
-        "networkAccess": true
-    },
-    "model": "gpt-5.1-codex",
-    "effort": "medium",
-    "summary": "concise",
-    // Optional JSON Schema to constrain the final assistant message for this turn.
-    "outputSchema": {
-        "type": "object",
-        "properties": { "answer": { "type": "string" } },
-        "required": ["answer"],
-        "additionalProperties": false
-    }
-} }
-{ "id": 30, "result": { "turn": {
-    "id": "turn_456",
-    "status": "inProgress",
-    "items": [],
-    "error": null
-} } }
-```
-
-### Example: Interrupt an active turn
-
-You can cancel a running Turn with `turn/interrupt`.
-
-```json
-{ "method": "turn/interrupt", "id": 31, "params": {
-    "threadId": "thr_123",
-    "turnId": "turn_456"
-} }
-{ "id": 31, "result": {} }
-```
-
-The server requests cancellations for running subprocesses, then emits a `turn/completed` event with `status: "interrupted"`. Rely on the `turn/completed` to know when Codex-side cleanup is done.
-
-### Example: Request a code review
-
-Use `review/start` to run Codex’s reviewer on the currently checked-out project. The request takes the thread id plus a `target` describing what should be reviewed:
-
-- `{"type":"uncommittedChanges"}` — staged, unstaged, and untracked files.
-- `{"type":"baseBranch","branch":"main"}` — diff against the provided branch’s upstream (see prompt for the exact `git merge-base`/`git diff` instructions Codex will run).
-- `{"type":"commit","sha":"abc1234","title":"Optional subject"}` — review a specific commit.
-- `{"type":"custom","instructions":"Free-form reviewer instructions"}` — fallback prompt equivalent to the legacy manual review request.
-- `delivery` (`"inline"` or `"detached"`, default `"inline"`) — where the review runs:
-  - `"inline"`: run the review as a new turn on the existing thread. The response’s `reviewThreadId` equals the original `threadId`, and no new `thread/started` notification is emitted.
-  - `"detached"`: fork a new review thread from the parent conversation and run the review there. The response’s `reviewThreadId` is the id of this new review thread, and the server emits a `thread/started` notification for it before streaming review items.
-
-Example request/response:
-
-```json
-{ "method": "review/start", "id": 40, "params": {
-    "threadId": "thr_123",
-    "delivery": "inline",
-    "target": { "type": "commit", "sha": "1234567deadbeef", "title": "Polish tui colors" }
-} }
-{ "id": 40, "result": {
-    "turn": {
-        "id": "turn_900",
-        "status": "inProgress",
-        "items": [
-            { "type": "userMessage", "id": "turn_900", "content": [ { "type": "text", "text": "Review commit 1234567: Polish tui colors" } ] }
-        ],
-        "error": null
-    },
-    "reviewThreadId": "thr_123"
-} }
-```
-
-For a detached review, use `"delivery": "detached"`. The response is the same shape, but `reviewThreadId` will be the id of the new review thread (different from the original `threadId`). The server also emits a `thread/started` notification for that new thread before streaming the review turn.
-
-Codex streams the usual `turn/started` notification followed by an `item/started`
-with an `enteredReviewMode` item so clients can show progress:
-
-```json
-{
-  "method": "item/started",
-  "params": {
-    "item": {
-      "type": "enteredReviewMode",
-      "id": "turn_900",
-      "review": "current changes"
-    }
-  }
-}
-```
-
-When the reviewer finishes, the server emits `item/started` and `item/completed`
-containing an `exitedReviewMode` item with the final review text:
-
-```json
-{
-  "method": "item/completed",
-  "params": {
-    "item": {
-      "type": "exitedReviewMode",
-      "id": "turn_900",
-      "review": "Looks solid overall...\n\n- Prefer Stylize helpers — app.rs:10-20\n  ..."
-    }
-  }
-}
-```
-
-The `review` string is plain text that already bundles the overall explanation plus a bullet list for each structured finding (matching `ThreadItem::ExitedReviewMode` in the generated schema). Use this notification to render the reviewer output in your client.
-
-### Example: One-off command execution
-
-Run a standalone command (argv vector) in the server’s sandbox without creating a thread or turn:
-
-```json
-{ "method": "command/exec", "id": 32, "params": {
-    "command": ["ls", "-la"],
-    "cwd": "/Users/me/project",                    // optional; defaults to server cwd
-    "sandboxPolicy": { "type": "workspaceWrite" }, // optional; defaults to user config
-    "timeoutMs": 10000                             // optional; ms timeout; defaults to server timeout
-} }
-{ "id": 32, "result": { "exitCode": 0, "stdout": "...", "stderr": "" } }
-```
-
-- For clients that are already sandboxed externally, set `sandboxPolicy` to `{"type":"externalSandbox","networkAccess":"enabled"}` (or omit `networkAccess` to keep it restricted). Codex will not enforce its own sandbox in this mode; it tells the model it has full file-system access and passes the `networkAccess` state through `environment_context`.
-
-Notes:
-
-- Empty `command` arrays are rejected.
-- `sandboxPolicy` accepts the same shape used by `turn/start` (e.g., `dangerFullAccess`, `readOnly`, `workspaceWrite` with flags, `externalSandbox` with `networkAccess` `restricted|enabled`).
-- When omitted, `timeoutMs` falls back to the server default.
-
-## Events
-
-Event notifications are the server-initiated event stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading stdout for `thread/started`, `turn/*`, and `item/*` notifications.
-
-### Turn events
-
-The app-server streams JSON-RPC notifications while a turn is running. Each turn starts with `turn/started` (initial `turn`) and ends with `turn/completed` (final `turn` status). Token usage events stream separately via `thread/tokenUsage/updated`. Clients subscribe to the events they care about, rendering each item incrementally as updates arrive. The per-item lifecycle is always: `item/started` → zero or more item-specific deltas → `item/completed`.
-
-- `turn/started` — `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.
-- `turn/completed` — `{ turn }` where `turn.status` is `completed`, `interrupted`, or `failed`; failures carry `{ error: { message, codexErrorInfo?, additionalDetails? } }`.
-- `turn/diff/updated` — `{ threadId, turnId, diff }` represents the up-to-date snapshot of the turn-level unified diff, emitted after every FileChange item. `diff` is the latest aggregated unified diff across every file change in the turn. UIs can render this to show the full "what changed" view without stitching individual `fileChange` items.
-- `turn/plan/updated` — `{ turnId, explanation?, plan }` whenever the agent shares or changes its plan; each `plan` entry is `{ step, status }` with `status` in `pending`, `inProgress`, or `completed`.
-
-Today both notifications carry an empty `items` array even when item events were streamed; rely on `item/*` notifications for the canonical item list until this is fixed.
-
-#### Items
-
-`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Currently we support events for the following items:
-
-- `userMessage` — `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).
-- `agentMessage` — `{id, text}` containing the accumulated agent reply.
-- `reasoning` — `{id, summary, content}` where `summary` holds streamed reasoning summaries (applicable for most OpenAI models) and `content` holds raw reasoning blocks (applicable for e.g. open source models).
-- `commandExecution` — `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}` for sandboxed commands; `status` is `inProgress`, `completed`, `failed`, or `declined`.
-- `fileChange` — `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}` and `status` is `inProgress`, `completed`, `failed`, or `declined`.
-- `mcpToolCall` — `{id, server, tool, status, arguments, result?, error?}` describing MCP calls; `status` is `inProgress`, `completed`, or `failed`.
-- `webSearch` — `{id, query}` for a web search request issued by the agent.
-- `imageView` — `{id, path}` emitted when the agent invokes the image viewer tool.
-- `enteredReviewMode` — `{id, review}` sent when the reviewer starts; `review` is a short user-facing label such as `"current changes"` or the requested target description.
-- `exitedReviewMode` — `{id, review}` emitted when the reviewer finishes; `review` is the full plain-text review (usually, overall notes plus bullet point findings).
-- `compacted` - `{threadId, turnId}` when codex compacts the conversation history. This can happen automatically.
-
-All items emit two shared lifecycle events:
-
-- `item/started` — emits the full `item` when a new unit of work begins so the UI can render it immediately; the `item.id` in this payload matches the `itemId` used by deltas.
-- `item/completed` — sends the final `item` once that work finishes (e.g., after a tool call or message completes); treat this as the authoritative state.
-
-There are additional item-specific events:
-
-#### agentMessage
-
-- `item/agentMessage/delta` — appends streamed text for the agent message; concatenate `delta` values for the same `itemId` in order to reconstruct the full reply.
-
-#### reasoning
-
-- `item/reasoning/summaryTextDelta` — streams readable reasoning summaries; `summaryIndex` increments when a new summary section opens.
-- `item/reasoning/summaryPartAdded` — marks the boundary between reasoning summary sections for an `itemId`; subsequent `summaryTextDelta` entries share the same `summaryIndex`.
-- `item/reasoning/textDelta` — streams raw reasoning text (only applicable for e.g. open source models); use `contentIndex` to group deltas that belong together before showing them in the UI.
-
-#### commandExecution
-
-- `item/commandExecution/outputDelta` — streams stdout/stderr for the command; append deltas in order to render live output alongside `aggregatedOutput` in the final item.
-  Final `commandExecution` items include parsed `commandActions`, `status`, `exitCode`, and `durationMs` so the UI can summarize what ran and whether it succeeded.
-
-#### fileChange
-
-- `item/fileChange/outputDelta` - contains the tool call response of the underlying `apply_patch` tool call.
-
-### Errors
-
-`error` event is emitted whenever the server hits an error mid-turn (for example, upstream model errors or quota limits). Carries the same `{ error: { message, codexErrorInfo?, additionalDetails? } }` payload as `turn.status: "failed"` and may precede that terminal notification.
-
-`codexErrorInfo` maps to the `CodexErrorInfo` enum. Common values:
-
-- `ContextWindowExceeded`
-- `UsageLimitExceeded`
-- `HttpConnectionFailed { httpStatusCode? }`: upstream HTTP failures including 4xx/5xx
-- `ResponseStreamConnectionFailed { httpStatusCode? }`: failure to connect to the response SSE stream
-- `ResponseStreamDisconnected { httpStatusCode? }`: disconnect of the response SSE stream in the middle of a turn before completion
-- `ResponseTooManyFailedAttempts { httpStatusCode? }`
-- `BadRequest`
-- `Unauthorized`
-- `SandboxError`
-- `InternalServerError`
-- `Other`: all unclassified errors
-
-When an upstream HTTP status is available (for example, from the Responses API or a provider), it is forwarded in `httpStatusCode` on the relevant `codexErrorInfo` variant.
-
-## Approvals
-
-Certain actions (shell commands or modifying files) may require explicit user approval depending on the user's config. When `turn/start` is used, the app-server drives an approval flow by sending a server-initiated JSON-RPC request to the client. The client must respond to tell Codex whether to proceed. UIs should present these requests inline with the active turn so users can review the proposed command or diff before choosing.
-
-- Requests include `threadId` and `turnId`—use them to scope UI state to the active conversation.
-- Respond with a single `{ "decision": "accept" | "decline" }` payload (plus optional `acceptSettings` on command executions). The server resumes or declines the work and ends the item with `item/completed`.
-
-### Command execution approvals
-
-Order of messages:
-
-1. `item/started` — shows the pending `commandExecution` item with `command`, `cwd`, and other fields so you can render the proposed action.
-2. `item/commandExecution/requestApproval` (request) — carries the same `itemId`, `threadId`, `turnId`, optionally `reason` or `risk`, plus `parsedCmd` for friendly display.
-3. Client response — `{ "decision": "accept", "acceptSettings": { "forSession": false } }` or `{ "decision": "decline" }`.
-4. `item/completed` — final `commandExecution` item with `status: "completed" | "failed" | "declined"` and execution output. Render this as the authoritative result.
-
-### File change approvals
-
-Order of messages:
-
-1. `item/started` — emits a `fileChange` item with `changes` (diff chunk summaries) and `status: "inProgress"`. Show the proposed edits and paths to the user.
-2. `item/fileChange/requestApproval` (request) — includes `itemId`, `threadId`, `turnId`, and an optional `reason`.
-3. Client response — `{ "decision": "accept" }` or `{ "decision": "decline" }`.
-4. `item/completed` — returns the same `fileChange` item with `status` updated to `completed`, `failed`, or `declined` after the patch attempt. Rely on this to show success/failure and finalize the diff state in your UI.
-
-UI guidance for IDEs: surface an approval dialog as soon as the request arrives. The turn will proceed after the server receives a response to the approval request. The terminal `item/completed` notification will be sent with the appropriate status.
-
-## Auth endpoints
-
-The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.
-
-### API Overview
-
-- `account/read` — fetch current account info; optionally refresh tokens.
-- `account/login/start` — begin login (`apiKey` or `chatgpt`).
-- `account/login/completed` (notify) — emitted when a login attempt finishes (success or error).
-- `account/login/cancel` — cancel a pending ChatGPT login by `loginId`.
-- `account/logout` — sign out; triggers `account/updated`.
-- `account/updated` (notify) — emitted whenever auth mode changes (`authMode`: `apikey`, `chatgpt`, or `null`).
-- `account/rateLimits/read` — fetch ChatGPT rate limits; updates arrive via `account/rateLimits/updated` (notify).
-- `account/rateLimits/updated` (notify) — emitted whenever a user's ChatGPT rate limits change.
-- `mcpServer/oauthLogin/completed` (notify) — emitted after a `mcpServer/oauth/login` flow finishes for a server; payload includes `{ name, success, error? }`.
-
-### 1) Check auth state
-
-Request:
-
-```json
-{ "method": "account/read", "id": 1, "params": { "refreshToken": false } }
-```
-
-Response examples:
-
-```json
-{ "id": 1, "result": { "account": null, "requiresOpenaiAuth": false } } // No OpenAI auth needed (e.g., OSS/local models)
-{ "id": 1, "result": { "account": null, "requiresOpenaiAuth": true } }  // OpenAI auth required (typical for OpenAI-hosted models)
-{ "id": 1, "result": { "account": { "type": "apiKey" }, "requiresOpenaiAuth": true } }
-{ "id": 1, "result": { "account": { "type": "chatgpt", "email": "user@example.com", "planType": "pro" }, "requiresOpenaiAuth": true } }
-```
-
-Field notes:
-
-- `refreshToken` (bool): set `true` to force a token refresh.
-- `requiresOpenaiAuth` reflects the active provider; when `false`, Codex can run without OpenAI credentials.
-
-### 2) Log in with an API key
-
-1. Send:
-   ```json
-   {
-     "method": "account/login/start",
-     "id": 2,
-     "params": { "type": "apiKey", "apiKey": "sk-…" }
-   }
-   ```
-2. Expect:
-   ```json
-   { "id": 2, "result": { "type": "apiKey" } }
-   ```
-3. Notifications:
-   ```json
-   { "method": "account/login/completed", "params": { "loginId": null, "success": true, "error": null } }
-   { "method": "account/updated", "params": { "authMode": "apikey" } }
-   ```
-
-### 3) Log in with ChatGPT (browser flow)
-
-1. Start:
-   ```json
-   { "method": "account/login/start", "id": 3, "params": { "type": "chatgpt" } }
-   { "id": 3, "result": { "type": "chatgpt", "loginId": "<uuid>", "authUrl": "https://chatgpt.com/…&redirect_uri=http%3A%2F%2Flocalhost%3A<port>%2Fauth%2Fcallback" } }
-   ```
-2. Open `authUrl` in a browser; the app-server hosts the local callback.
-3. Wait for notifications:
-   ```json
-   { "method": "account/login/completed", "params": { "loginId": "<uuid>", "success": true, "error": null } }
-   { "method": "account/updated", "params": { "authMode": "chatgpt" } }
-   ```
-
-### 4) Cancel a ChatGPT login
-
-```json
-{ "method": "account/login/cancel", "id": 4, "params": { "loginId": "<uuid>" } }
-{ "method": "account/login/completed", "params": { "loginId": "<uuid>", "success": false, "error": "…" } }
-```
-
-### 5) Logout
-
-```json
-{ "method": "account/logout", "id": 5 }
-{ "id": 5, "result": {} }
-{ "method": "account/updated", "params": { "authMode": null } }
-```
-
-### 6) Rate limits (ChatGPT)
-
-```json
-{ "method": "account/rateLimits/read", "id": 6 }
-{ "id": 6, "result": { "rateLimits": { "primary": { "usedPercent": 25, "windowDurationMins": 15, "resetsAt": 1730947200 }, "secondary": null } } }
-{ "method": "account/rateLimits/updated", "params": { "rateLimits": { … } } }
-```
-
-Field notes:
-
-- `usedPercent` is current usage within the OpenAI quota window.
-- `windowDurationMins` is the quota window length.
-- `resetsAt` is a Unix timestamp (seconds) for the next reset.

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

@@ -1,113 +0,0 @@
-use crate::error_code::INTERNAL_ERROR_CODE;
-use crate::error_code::INVALID_REQUEST_ERROR_CODE;
-use codex_app_server_protocol::ConfigBatchWriteParams;
-use codex_app_server_protocol::ConfigReadParams;
-use codex_app_server_protocol::ConfigReadResponse;
-use codex_app_server_protocol::ConfigValueWriteParams;
-use codex_app_server_protocol::ConfigWriteErrorCode;
-use codex_app_server_protocol::ConfigWriteResponse;
-use codex_app_server_protocol::JSONRPCErrorError;
-use codex_core::config::Config;
-use codex_core::config::ConfigBuilder;
-use codex_core::config::ConfigService;
-use codex_core::config::ConfigServiceError;
-use codex_utils_json_to_toml::json_to_toml;
-use serde_json::json;
-use std::path::PathBuf;
-use toml::Value as TomlValue;
-
-#[derive(Clone)]
-pub(crate) struct ConfigApi {
-    codex_home: PathBuf,
-    cli_overrides: Vec<(String, TomlValue)>,
-    service: ConfigService,
-}
-
-impl ConfigApi {
-    pub(crate) fn new(codex_home: PathBuf, cli_overrides: Vec<(String, TomlValue)>) -> Self {
-        Self {
-            service: ConfigService::new(codex_home.clone(), cli_overrides.clone()),
-            codex_home,
-            cli_overrides,
-        }
-    }
-
-    pub(crate) async fn read(
-        &self,
-        params: ConfigReadParams,
-    ) -> Result<ConfigReadResponse, JSONRPCErrorError> {
-        self.service.read(params).await.map_err(map_error)
-    }
-
-    pub(crate) async fn load_thread_agnostic_config(
-        &self,
-        overrides: codex_core::config::ConfigOverrides,
-        request_cli_overrides: Option<std::collections::HashMap<String, serde_json::Value>>,
-    ) -> std::io::Result<Config> {
-        // Apply the app server's startup `--config` overrides, then apply request-scoped overrides
-        // with higher precedence.
-        let mut merged_cli_overrides = self.cli_overrides.clone();
-        merged_cli_overrides.extend(
-            request_cli_overrides
-                .unwrap_or_default()
-                .into_iter()
-                .map(|(k, v)| (k, json_to_toml(v))),
-        );
-
-        ConfigBuilder::default()
-            .codex_home(self.codex_home.clone())
-            .cli_overrides(merged_cli_overrides)
-            .harness_overrides(overrides)
-            .thread_agnostic()
-            .build()
-            .await
-    }
-
-    pub(crate) async fn write_value(
-        &self,
-        params: ConfigValueWriteParams,
-    ) -> Result<ConfigWriteResponse, JSONRPCErrorError> {
-        self.service.write_value(params).await.map_err(map_error)
-    }
-
-    pub(crate) async fn batch_write(
-        &self,
-        params: ConfigBatchWriteParams,
-    ) -> Result<ConfigWriteResponse, JSONRPCErrorError> {
-        self.service.batch_write(params).await.map_err(map_error)
-    }
-
-    pub(crate) async fn load_latest_thread_agnostic_config(
-        &self,
-    ) -> Result<Config, JSONRPCErrorError> {
-        self.load_thread_agnostic_config(codex_core::config::ConfigOverrides::default(), None)
-            .await
-            .map_err(|err| JSONRPCErrorError {
-                code: INTERNAL_ERROR_CODE,
-                message: format!("failed to reload config: {err}"),
-                data: None,
-            })
-    }
-}
-
-fn map_error(err: ConfigServiceError) -> JSONRPCErrorError {
-    if let Some(code) = err.write_error_code() {
-        return config_write_error(code, err.to_string());
-    }
-
-    JSONRPCErrorError {
-        code: INTERNAL_ERROR_CODE,
-        message: err.to_string(),
-        data: None,
-    }
-}
-
-fn config_write_error(code: ConfigWriteErrorCode, message: impl Into<String>) -> JSONRPCErrorError {
-    JSONRPCErrorError {
-        code: INVALID_REQUEST_ERROR_CODE,
-        message: message.into(),
-        data: Some(json!({
-            "config_write_error_code": code,
-        })),
-    }
-}

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

@@ -1,5 +1,6 @@
 use std::num::NonZero;
 use std::num::NonZeroUsize;
+use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Arc;
 use std::sync::atomic::AtomicBool;
@@ -18,10 +19,6 @@ pub(crate) async fn run_fuzzy_file_search(
     roots: Vec<String>,
     cancellation_flag: Arc<AtomicBool>,
 ) -> Vec<FuzzyFileSearchResult> {
-    if roots.is_empty() {
-        return Vec::new();
-    }
-
     #[expect(clippy::expect_used)]
     let limit_per_root =
         NonZero::new(LIMIT_PER_ROOT).expect("LIMIT_PER_ROOT should be a valid non-zero usize");
@@ -62,7 +59,11 @@ pub(crate) async fn run_fuzzy_file_search(
             Ok(Ok((root, res))) => {
                 for m in res.matches {
                     let path = m.path;
-                    let file_name = file_search::file_name_from_path(&path);
+                    //TODO(shijie): Move file name generation to file_search lib.
+                    let file_name = Path::new(&path)
+                        .file_name()
+                        .map(|name| name.to_string_lossy().into_owned())
+                        .unwrap_or_else(|| path.clone());
                     let result = FuzzyFileSearchResult {
                         root: root.clone(),
                         path,

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

@@ -2,6 +2,8 @@
 
 use codex_common::CliConfigOverrides;
 use codex_core::config::Config;
+use codex_core::config::ConfigOverrides;
+use opentelemetry_appender_tracing::layer::OpenTelemetryTracingBridge;
 use std::io::ErrorKind;
 use std::io::Result as IoResult;
 use std::path::PathBuf;
@@ -16,18 +18,17 @@ use tokio::io::AsyncWriteExt;
 use tokio::io::BufReader;
 use tokio::io::{self};
 use tokio::sync::mpsc;
-use toml::Value as TomlValue;
+use tracing::Level;
 use tracing::debug;
 use tracing::error;
 use tracing::info;
 use tracing_subscriber::EnvFilter;
 use tracing_subscriber::Layer;
+use tracing_subscriber::filter::Targets;
 use tracing_subscriber::layer::SubscriberExt;
 use tracing_subscriber::util::SubscriberInitExt;
 
-mod bespoke_event_handling;
 mod codex_message_processor;
-mod config_api;
 mod error_code;
 mod fuzzy_file_search;
 mod message_processor;
@@ -45,7 +46,7 @@ pub async fn run_main(
 ) -> IoResult<()> {
     // Set up channels.
     let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
-    let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(CHANNEL_CAPACITY);
+    let (outgoing_tx, mut outgoing_rx) = mpsc::unbounded_channel::<OutgoingMessage>();
 
     // Task: read from stdin, push to `incoming_tx`.
     let stdin_reader_handle = tokio::spawn({
@@ -78,7 +79,7 @@ pub async fn run_main(
             format!("error parsing -c overrides: {e}"),
         )
     })?;
-    let config = Config::load_with_cli_overrides(cli_kv_overrides.clone())
+    let config = Config::load_with_cli_overrides(cli_kv_overrides, ConfigOverrides::default())
         .await
         .map_err(|e| {
             std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
@@ -98,33 +99,31 @@ pub async fn run_main(
     // control the log level with `RUST_LOG`.
     let stderr_fmt = tracing_subscriber::fmt::layer()
         .with_writer(std::io::stderr)
-        .with_span_events(tracing_subscriber::fmt::format::FmtSpan::FULL)
         .with_filter(EnvFilter::from_default_env());
 
-    let feedback_layer = feedback.logger_layer();
-    let feedback_metadata_layer = feedback.metadata_layer();
-
-    let otel_logger_layer = otel.as_ref().and_then(|o| o.logger_layer());
-
-    let otel_tracing_layer = otel.as_ref().and_then(|o| o.tracing_layer());
+    let 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(feedback_metadata_layer)
-        .with(otel_logger_layer)
-        .with(otel_tracing_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),
+            )
+        }))
         .try_init();
 
     // Task: process incoming messages.
     let processor_handle = tokio::spawn({
         let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
-        let cli_overrides: Vec<(String, TomlValue)> = cli_kv_overrides.clone();
         let mut processor = MessageProcessor::new(
             outgoing_message_sender,
             codex_linux_sandbox_exe,
             std::sync::Arc::new(config),
-            cli_overrides,
             feedback.clone(),
         );
         async move {

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

@@ -1,22 +1,17 @@
 use std::path::PathBuf;
-use std::sync::Arc;
 
 use crate::codex_message_processor::CodexMessageProcessor;
-use crate::config_api::ConfigApi;
 use crate::error_code::INVALID_REQUEST_ERROR_CODE;
 use crate::outgoing_message::OutgoingMessageSender;
 use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::ClientRequest;
-use codex_app_server_protocol::ConfigBatchWriteParams;
-use codex_app_server_protocol::ConfigReadParams;
-use codex_app_server_protocol::ConfigValueWriteParams;
 use codex_app_server_protocol::InitializeResponse;
+
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCErrorError;
 use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCRequest;
 use codex_app_server_protocol::JSONRPCResponse;
-use codex_app_server_protocol::RequestId;
 use codex_core::AuthManager;
 use codex_core::ConversationManager;
 use codex_core::config::Config;
@@ -24,12 +19,11 @@ 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 toml::Value as TomlValue;
+use std::sync::Arc;
 
 pub(crate) struct MessageProcessor {
     outgoing: Arc<OutgoingMessageSender>,
     codex_message_processor: CodexMessageProcessor,
-    config_api: ConfigApi,
     initialized: bool,
 }
 
@@ -40,7 +34,6 @@ impl MessageProcessor {
         outgoing: OutgoingMessageSender,
         codex_linux_sandbox_exe: Option<PathBuf>,
         config: Arc<Config>,
-        cli_overrides: Vec<(String, TomlValue)>,
         feedback: CodexFeedback,
     ) -> Self {
         let outgoing = Arc::new(outgoing);
@@ -58,16 +51,13 @@ impl MessageProcessor {
             conversation_manager,
             outgoing.clone(),
             codex_linux_sandbox_exe,
-            Arc::clone(&config),
-            cli_overrides.clone(),
+            config,
             feedback,
         );
-        let config_api = ConfigApi::new(config.codex_home.clone(), cli_overrides);
 
         Self {
             outgoing,
             codex_message_processor,
-            config_api,
             initialized: false,
         }
     }
@@ -128,7 +118,6 @@ impl MessageProcessor {
                     self.outgoing.send_response(request_id, response).await;
 
                     self.initialized = true;
-
                     return;
                 }
             }
@@ -145,20 +134,9 @@ impl MessageProcessor {
             }
         }
 
-        match codex_request {
-            ClientRequest::ConfigRead { request_id, params } => {
-                self.handle_config_read(request_id, params).await;
-            }
-            ClientRequest::ConfigValueWrite { request_id, params } => {
-                self.handle_config_value_write(request_id, params).await;
-            }
-            ClientRequest::ConfigBatchWrite { request_id, params } => {
-                self.handle_config_batch_write(request_id, params).await;
-            }
-            other => {
-                self.codex_message_processor.process_request(other).await;
-            }
-        }
+        self.codex_message_processor
+            .process_request(codex_request)
+            .await;
     }
 
     pub(crate) async fn process_notification(&self, notification: JSONRPCNotification) {
@@ -178,33 +156,4 @@ impl MessageProcessor {
     pub(crate) fn process_error(&mut self, err: JSONRPCError) {
         tracing::error!("<- error: {:?}", err);
     }
-
-    async fn handle_config_read(&self, request_id: RequestId, params: ConfigReadParams) {
-        match self.config_api.read(params).await {
-            Ok(response) => self.outgoing.send_response(request_id, response).await,
-            Err(error) => self.outgoing.send_error(request_id, error).await,
-        }
-    }
-
-    async fn handle_config_value_write(
-        &self,
-        request_id: RequestId,
-        params: ConfigValueWriteParams,
-    ) {
-        match self.config_api.write_value(params).await {
-            Ok(response) => self.outgoing.send_response(request_id, response).await,
-            Err(error) => self.outgoing.send_error(request_id, error).await,
-        }
-    }
-
-    async fn handle_config_batch_write(
-        &self,
-        request_id: RequestId,
-        params: ConfigBatchWriteParams,
-    ) {
-        match self.config_api.batch_write(params).await {
-            Ok(response) => self.outgoing.send_response(request_id, response).await,
-            Err(error) => self.outgoing.send_error(request_id, error).await,
-        }
-    }
 }

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

@@ -1,19 +1,12 @@
-use std::sync::Arc;
-
+use codex_app_server_protocol::AuthMode;
 use codex_app_server_protocol::Model;
 use codex_app_server_protocol::ReasoningEffortOption;
-use codex_core::ConversationManager;
-use codex_core::config::Config;
-use codex_protocol::openai_models::ModelPreset;
-use codex_protocol::openai_models::ReasoningEffortPreset;
+use codex_common::model_presets::ModelPreset;
+use codex_common::model_presets::ReasoningEffortPreset;
+use codex_common::model_presets::builtin_model_presets;
 
-pub async fn supported_models(
-    conversation_manager: Arc<ConversationManager>,
-    config: &Config,
-) -> Vec<Model> {
-    conversation_manager
-        .list_models(config)
-        .await
+pub fn supported_models(auth_mode: Option<AuthMode>) -> Vec<Model> {
+    builtin_model_presets(auth_mode)
         .into_iter()
         .map(model_from_preset)
         .collect()
@@ -34,7 +27,7 @@ fn model_from_preset(preset: ModelPreset) -> Model {
 }
 
 fn reasoning_efforts_from_preset(
-    efforts: Vec<ReasoningEffortPreset>,
+    efforts: &'static [ReasoningEffortPreset],
 ) -> Vec<ReasoningEffortOption> {
     efforts
         .iter()

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

@@ -16,18 +16,15 @@ use tracing::warn;
 
 use crate::error_code::INTERNAL_ERROR_CODE;
 
-#[cfg(test)]
-use codex_protocol::account::PlanType;
-
 /// Sends messages to the client and manages request callbacks.
 pub(crate) struct OutgoingMessageSender {
     next_request_id: AtomicI64,
-    sender: mpsc::Sender<OutgoingMessage>,
+    sender: mpsc::UnboundedSender<OutgoingMessage>,
     request_id_to_callback: Mutex<HashMap<RequestId, oneshot::Sender<Result>>>,
 }
 
 impl OutgoingMessageSender {
-    pub(crate) fn new(sender: mpsc::Sender<OutgoingMessage>) -> Self {
+    pub(crate) fn new(sender: mpsc::UnboundedSender<OutgoingMessage>) -> Self {
         Self {
             next_request_id: AtomicI64::new(0),
             sender,
@@ -48,12 +45,8 @@ impl OutgoingMessageSender {
         }
 
         let outgoing_message =
-            OutgoingMessage::Request(request.request_with_id(outgoing_message_id.clone()));
-        if let Err(err) = self.sender.send(outgoing_message).await {
-            warn!("failed to send request {outgoing_message_id:?} to client: {err:?}");
-            let mut request_id_to_callback = self.request_id_to_callback.lock().await;
-            request_id_to_callback.remove(&outgoing_message_id);
-        }
+            OutgoingMessage::Request(request.request_with_id(outgoing_message_id));
+        let _ = self.sender.send(outgoing_message);
         rx_approve
     }
 
@@ -79,9 +72,7 @@ impl OutgoingMessageSender {
         match serde_json::to_value(response) {
             Ok(result) => {
                 let outgoing_message = OutgoingMessage::Response(OutgoingResponse { id, result });
-                if let Err(err) = self.sender.send(outgoing_message).await {
-                    warn!("failed to send response to client: {err:?}");
-                }
+                let _ = self.sender.send(outgoing_message);
             }
             Err(err) => {
                 self.send_error(
@@ -98,29 +89,21 @@ impl OutgoingMessageSender {
     }
 
     pub(crate) async fn send_server_notification(&self, notification: ServerNotification) {
-        if let Err(err) = self
+        let _ = self
             .sender
-            .send(OutgoingMessage::AppServerNotification(notification))
-            .await
-        {
-            warn!("failed to send server notification to client: {err:?}");
-        }
+            .send(OutgoingMessage::AppServerNotification(notification));
     }
 
     /// All notifications should be migrated to [`ServerNotification`] and
     /// [`OutgoingMessage::Notification`] should be removed.
     pub(crate) async fn send_notification(&self, notification: OutgoingNotification) {
         let outgoing_message = OutgoingMessage::Notification(notification);
-        if let Err(err) = self.sender.send(outgoing_message).await {
-            warn!("failed to send notification to client: {err:?}");
-        }
+        let _ = self.sender.send(outgoing_message);
     }
 
     pub(crate) async fn send_error(&self, id: RequestId, error: JSONRPCErrorError) {
         let outgoing_message = OutgoingMessage::Error(OutgoingError { id, error });
-        if let Err(err) = self.sender.send(outgoing_message).await {
-            warn!("failed to send error to client: {err:?}");
-        }
+        let _ = self.sender.send(outgoing_message);
     }
 }
 
@@ -232,8 +215,6 @@ mod tests {
                         resets_at: Some(123),
                     }),
                     secondary: None,
-                    credits: None,
-                    plan_type: Some(PlanType::Plus),
                 },
             });
 
@@ -248,9 +229,7 @@ mod tests {
                             "windowDurationMins": 15,
                             "resetsAt": 123
                         },
-                        "secondary": null,
-                        "credits": null,
-                        "planType": "plus"
+                        "secondary": null
                     }
                 },
             }),

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

@@ -1,20 +1,19 @@
 [package]
+edition = "2024"
 name = "app_test_support"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
+version = { workspace = true }
 
 [lib]
 path = "lib.rs"
 
 [dependencies]
 anyhow = { workspace = true }
+assert_cmd = { workspace = true }
 base64 = { workspace = true }
 chrono = { workspace = true }
 codex-app-server-protocol = { workspace = true }
-codex-core = { workspace = true, features = ["test-support"] }
+codex-core = { workspace = true }
 codex-protocol = { workspace = true }
-codex-utils-cargo-bin = { workspace = true }
 serde = { workspace = true }
 serde_json = { workspace = true }
 tokio = { workspace = true, features = [
@@ -25,5 +24,3 @@ tokio = { workspace = true, features = [
 ] }
 uuid = { workspace = true }
 wiremock = { workspace = true }
-core_test_support = { path = "../../../core/tests/common" }
-shlex = { workspace = true }

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

@@ -1,7 +1,6 @@
 mod auth_fixtures;
 mod mcp_process;
 mod mock_model_server;
-mod models_cache;
 mod responses;
 mod rollout;
 
@@ -10,22 +9,12 @@ pub use auth_fixtures::ChatGptIdTokenClaims;
 pub use auth_fixtures::encode_id_token;
 pub use auth_fixtures::write_chatgpt_auth;
 use codex_app_server_protocol::JSONRPCResponse;
-pub use core_test_support::format_with_current_shell;
-pub use core_test_support::format_with_current_shell_display;
-pub use core_test_support::format_with_current_shell_display_non_login;
-pub use core_test_support::format_with_current_shell_non_login;
-pub use core_test_support::test_path_buf_with_windows;
-pub use core_test_support::test_tmp_path;
-pub use core_test_support::test_tmp_path_buf;
 pub use mcp_process::McpProcess;
 pub use mock_model_server::create_mock_chat_completions_server;
 pub use mock_model_server::create_mock_chat_completions_server_unchecked;
-pub use models_cache::write_models_cache;
-pub use models_cache::write_models_cache_with_models;
 pub use responses::create_apply_patch_sse_response;
-pub use responses::create_exec_command_sse_response;
 pub use responses::create_final_assistant_message_sse_response;
-pub use responses::create_shell_command_sse_response;
+pub use responses::create_shell_sse_response;
 pub use rollout::create_fake_rollout;
 use serde::de::DeserializeOwned;
 

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

@@ -11,17 +11,14 @@ use tokio::process::ChildStdin;
 use tokio::process::ChildStdout;
 
 use anyhow::Context;
+use assert_cmd::prelude::*;
 use codex_app_server_protocol::AddConversationListenerParams;
 use codex_app_server_protocol::ArchiveConversationParams;
 use codex_app_server_protocol::CancelLoginAccountParams;
 use codex_app_server_protocol::CancelLoginChatGptParams;
 use codex_app_server_protocol::ClientInfo;
 use codex_app_server_protocol::ClientNotification;
-use codex_app_server_protocol::ConfigBatchWriteParams;
-use codex_app_server_protocol::ConfigReadParams;
-use codex_app_server_protocol::ConfigValueWriteParams;
 use codex_app_server_protocol::FeedbackUploadParams;
-use codex_app_server_protocol::GetAccountParams;
 use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::InitializeParams;
 use codex_app_server_protocol::InterruptConversationParams;
@@ -37,7 +34,6 @@ use codex_app_server_protocol::NewConversationParams;
 use codex_app_server_protocol::RemoveConversationListenerParams;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::ResumeConversationParams;
-use codex_app_server_protocol::ReviewStartParams;
 use codex_app_server_protocol::SendUserMessageParams;
 use codex_app_server_protocol::SendUserTurnParams;
 use codex_app_server_protocol::ServerRequest;
@@ -48,6 +44,7 @@ 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;
 
 pub struct McpProcess {
@@ -76,8 +73,12 @@ impl McpProcess {
         codex_home: &Path,
         env_overrides: &[(&str, Option<&str>)],
     ) -> anyhow::Result<Self> {
-        let program = codex_utils_cargo_bin::cargo_bin("codex-app-server")
-            .context("should find binary for codex-app-server")?;
+        // Use assert_cmd to locate the binary path and then switch to tokio::process::Command
+        let std_cmd = StdCommand::cargo_bin("codex-app-server")
+            .context("should find binary for codex-mcp-server")?;
+
+        let program = std_cmd.get_program().to_owned();
+
         let mut cmd = Command::new(program);
 
         cmd.stdin(Stdio::piped());
@@ -248,15 +249,6 @@ 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,
@@ -375,15 +367,6 @@ impl McpProcess {
         self.send_request("turn/interrupt", params).await
     }
 
-    /// Send a `review/start` JSON-RPC request (v2).
-    pub async fn send_review_start_request(
-        &mut self,
-        params: ReviewStartParams,
-    ) -> anyhow::Result<i64> {
-        let params = Some(serde_json::to_value(params)?);
-        self.send_request("review/start", params).await
-    }
-
     /// Send a `cancelLoginChatGpt` JSON-RPC request.
     pub async fn send_cancel_login_chat_gpt_request(
         &mut self,
@@ -398,30 +381,6 @@ impl McpProcess {
         self.send_request("logoutChatGpt", None).await
     }
 
-    pub async fn send_config_read_request(
-        &mut self,
-        params: ConfigReadParams,
-    ) -> anyhow::Result<i64> {
-        let params = Some(serde_json::to_value(params)?);
-        self.send_request("config/read", params).await
-    }
-
-    pub async fn send_config_value_write_request(
-        &mut self,
-        params: ConfigValueWriteParams,
-    ) -> anyhow::Result<i64> {
-        let params = Some(serde_json::to_value(params)?);
-        self.send_request("config/value/write", params).await
-    }
-
-    pub async fn send_config_batch_write_request(
-        &mut self,
-        params: ConfigBatchWriteParams,
-    ) -> anyhow::Result<i64> {
-        let params = Some(serde_json::to_value(params)?);
-        self.send_request("config/batchWrite", params).await
-    }
-
     /// Send an `account/logout` JSON-RPC request.
     pub async fn send_logout_account_request(&mut self) -> anyhow::Result<i64> {
         self.send_request("account/logout", None).await

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

@@ -1,82 +0,0 @@
-use chrono::DateTime;
-use chrono::Utc;
-use codex_core::models_manager::model_presets::all_model_presets;
-use codex_protocol::openai_models::ConfigShellToolType;
-use codex_protocol::openai_models::ModelInfo;
-use codex_protocol::openai_models::ModelPreset;
-use codex_protocol::openai_models::ModelVisibility;
-use codex_protocol::openai_models::TruncationPolicyConfig;
-use serde_json::json;
-use std::path::Path;
-
-/// Convert a ModelPreset to ModelInfo for cache storage.
-fn preset_to_info(preset: &ModelPreset, priority: i32) -> ModelInfo {
-    ModelInfo {
-        slug: preset.id.clone(),
-        display_name: preset.display_name.clone(),
-        description: Some(preset.description.clone()),
-        default_reasoning_level: preset.default_reasoning_effort,
-        supported_reasoning_levels: preset.supported_reasoning_efforts.clone(),
-        shell_type: ConfigShellToolType::ShellCommand,
-        visibility: if preset.show_in_picker {
-            ModelVisibility::List
-        } else {
-            ModelVisibility::Hide
-        },
-        supported_in_api: true,
-        priority,
-        upgrade: preset.upgrade.as_ref().map(|u| u.id.clone()),
-        base_instructions: None,
-        supports_reasoning_summaries: false,
-        support_verbosity: false,
-        default_verbosity: None,
-        apply_patch_tool_type: None,
-        truncation_policy: TruncationPolicyConfig::bytes(10_000),
-        supports_parallel_tool_calls: false,
-        context_window: None,
-        experimental_supported_tools: Vec::new(),
-    }
-}
-
-// todo(aibrahim): fix the priorities to be the opposite here.
-/// Write a models_cache.json file to the codex home directory.
-/// This prevents ModelsManager from making network requests to refresh models.
-/// The cache will be treated as fresh (within TTL) and used instead of fetching from the network.
-/// Uses the built-in model presets from ModelsManager, converted to ModelInfo format.
-pub fn write_models_cache(codex_home: &Path) -> std::io::Result<()> {
-    // Get all presets and filter for show_in_picker (same as builtin_model_presets does)
-    let presets: Vec<&ModelPreset> = all_model_presets()
-        .iter()
-        .filter(|preset| preset.show_in_picker)
-        .collect();
-    // Convert presets to ModelInfo, assigning priorities (higher = earlier in list)
-    // Priority is used for sorting, so first model gets highest priority
-    let models: Vec<ModelInfo> = presets
-        .iter()
-        .enumerate()
-        .map(|(idx, preset)| {
-            // Higher priority = earlier in list, so reverse the index
-            let priority = (presets.len() - idx) as i32;
-            preset_to_info(preset, priority)
-        })
-        .collect();
-
-    write_models_cache_with_models(codex_home, models)
-}
-
-/// Write a models_cache.json file with specific models.
-/// Useful when tests need specific models to be available.
-pub fn write_models_cache_with_models(
-    codex_home: &Path,
-    models: Vec<ModelInfo>,
-) -> std::io::Result<()> {
-    let cache_path = codex_home.join("models_cache.json");
-    // DateTime<Utc> serializes to RFC3339 format by default with serde
-    let fetched_at: DateTime<Utc> = Utc::now();
-    let cache = json!({
-        "fetched_at": fetched_at,
-        "etag": null,
-        "models": models
-    });
-    std::fs::write(cache_path, serde_json::to_string_pretty(&cache)?)
-}

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

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

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

@@ -1,8 +1,6 @@
 use anyhow::Result;
 use codex_protocol::ConversationId;
-use codex_protocol::protocol::GitInfo;
 use codex_protocol::protocol::SessionMeta;
-use codex_protocol::protocol::SessionMetaLine;
 use codex_protocol::protocol::SessionSource;
 use serde_json::json;
 use std::fs;
@@ -24,7 +22,6 @@ pub fn create_fake_rollout(
     meta_rfc3339: &str,
     preview: &str,
     model_provider: Option<&str>,
-    git_info: Option<GitInfo>,
 ) -> Result<String> {
     let uuid = Uuid::new_v4();
     let uuid_str = uuid.to_string();
@@ -40,7 +37,7 @@ pub fn create_fake_rollout(
     let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
 
     // Build JSONL lines
-    let meta = SessionMeta {
+    let payload = serde_json::to_value(SessionMeta {
         id: conversation_id,
         timestamp: meta_rfc3339.to_string(),
         cwd: PathBuf::from("/"),
@@ -49,10 +46,6 @@ pub fn create_fake_rollout(
         instructions: None,
         source: SessionSource::Cli,
         model_provider: model_provider.map(str::to_string),
-    };
-    let payload = serde_json::to_value(SessionMetaLine {
-        meta,
-        git: git_info,
     })?;
 
     let lines = [

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

@@ -2,8 +2,7 @@ use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_final_assistant_message_sse_response;
 use app_test_support::create_mock_chat_completions_server;
-use app_test_support::create_shell_command_sse_response;
-use app_test_support::format_with_current_shell;
+use app_test_support::create_shell_sse_response;
 use app_test_support::to_response;
 use codex_app_server_protocol::AddConversationListenerParams;
 use codex_app_server_protocol::AddConversationSubscriptionResponse;
@@ -23,10 +22,10 @@ use codex_app_server_protocol::SendUserTurnResponse;
 use codex_app_server_protocol::ServerRequest;
 use codex_core::protocol::AskForApproval;
 use codex_core::protocol::SandboxPolicy;
+use codex_core::protocol_config_types::ReasoningEffort;
 use codex_core::protocol_config_types::ReasoningSummary;
 use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
 use codex_protocol::config_types::SandboxMode;
-use codex_protocol::openai_models::ReasoningEffort;
 use codex_protocol::parse_command::ParsedCommand;
 use codex_protocol::protocol::Event;
 use codex_protocol::protocol::EventMsg;
@@ -57,7 +56,7 @@ async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
     // Create a mock model server that immediately ends each turn.
     // Two turns are expected: initial session configure + one user message.
     let responses = vec![
-        create_shell_command_sse_response(
+        create_shell_sse_response(
             vec!["ls".to_string()],
             Some(&working_directory),
             Some(5000),
@@ -176,7 +175,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
 
     // Mock server will request a python shell call for the first and second turn, then finish.
     let responses = vec![
-        create_shell_command_sse_response(
+        create_shell_sse_response(
             vec![
                 "python3".to_string(),
                 "-c".to_string(),
@@ -187,7 +186,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
             "call1",
         )?,
         create_final_assistant_message_sse_response("done 1")?,
-        create_shell_command_sse_response(
+        create_shell_sse_response(
             vec![
                 "python3".to_string(),
                 "-c".to_string(),
@@ -268,9 +267,14 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
         ExecCommandApprovalParams {
             conversation_id,
             call_id: "call1".to_string(),
-            command: format_with_current_shell("python3 -c 'print(42)'"),
+            command: vec![
+                "python3".to_string(),
+                "-c".to_string(),
+                "print(42)".to_string(),
+            ],
             cwd: working_directory.clone(),
             reason: None,
+            risk: None,
             parsed_cmd: vec![ParsedCommand::Unknown {
                 cmd: "python3 -c 'print(42)'".to_string()
             }],
@@ -305,7 +309,6 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
             model: "mock-model".to_string(),
             effort: Some(ReasoningEffort::Medium),
             summary: ReasoningSummary::Auto,
-            output_schema: None,
         })
         .await?;
     // Acknowledge sendUserTurn
@@ -350,15 +353,23 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
     std::fs::create_dir(&second_cwd)?;
 
     let responses = vec![
-        create_shell_command_sse_response(
-            vec!["echo".to_string(), "first".to_string(), "turn".to_string()],
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo first turn".to_string(),
+            ],
             None,
             Some(5000),
             "call-first",
         )?,
         create_final_assistant_message_sse_response("done first")?,
-        create_shell_command_sse_response(
-            vec!["echo".to_string(), "second".to_string(), "turn".to_string()],
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo second turn".to_string(),
+            ],
             None,
             Some(5000),
             "call-second",
@@ -411,7 +422,7 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
             cwd: first_cwd.clone(),
             approval_policy: AskForApproval::Never,
             sandbox_policy: SandboxPolicy::WorkspaceWrite {
-                writable_roots: vec![first_cwd.try_into()?],
+                writable_roots: vec![first_cwd.clone()],
                 network_access: false,
                 exclude_tmpdir_env_var: false,
                 exclude_slash_tmp: false,
@@ -419,7 +430,6 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
             model: model.clone(),
             effort: Some(ReasoningEffort::Medium),
             summary: ReasoningSummary::Auto,
-            output_schema: None,
         })
         .await?;
     timeout(
@@ -445,7 +455,6 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
             model: model.clone(),
             effort: Some(ReasoningEffort::Medium),
             summary: ReasoningSummary::Auto,
-            output_schema: None,
         })
         .await?;
     timeout(
@@ -472,9 +481,13 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
         exec_begin.cwd, second_cwd,
         "exec turn should run from updated cwd"
     );
-    let expected_command = format_with_current_shell("echo second turn");
     assert_eq!(
-        exec_begin.command, expected_command,
+        exec_begin.command,
+        vec![
+            "bash".to_string(),
+            "-lc".to_string(),
+            "echo second turn".to_string()
+        ],
         "exec turn should run expected command"
     );
 

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

@@ -1,6 +1,5 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
-use app_test_support::test_tmp_path;
 use app_test_support::to_response;
 use codex_app_server_protocol::GetUserSavedConfigResponse;
 use codex_app_server_protocol::JSONRPCResponse;
@@ -11,10 +10,10 @@ use codex_app_server_protocol::Tools;
 use codex_app_server_protocol::UserSavedConfig;
 use codex_core::protocol::AskForApproval;
 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::openai_models::ReasoningEffort;
 use pretty_assertions::assert_eq;
 use std::collections::HashMap;
 use std::path::Path;
@@ -24,13 +23,11 @@ use tokio::time::timeout;
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
 fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
-    let writable_root = test_tmp_path();
     let config_toml = codex_home.join("config.toml");
     std::fs::write(
         config_toml,
-        format!(
-            r#"
-model = "gpt-5.1-codex-max"
+        r#"
+model = "gpt-5-codex"
 approval_policy = "on-request"
 sandbox_mode = "workspace-write"
 model_reasoning_summary = "detailed"
@@ -41,7 +38,7 @@ forced_chatgpt_workspace_id = "12345678-0000-0000-0000-000000000000"
 forced_login_method = "chatgpt"
 
 [sandbox_workspace_write]
-writable_roots = [{}]
+writable_roots = ["/tmp"]
 network_access = true
 exclude_tmpdir_env_var = true
 exclude_slash_tmp = true
@@ -59,8 +56,6 @@ model_verbosity = "medium"
 model_provider = "openai"
 chatgpt_base_url = "https://api.chatgpt.com"
 "#,
-            serde_json::json!(writable_root)
-        ),
     )
 }
 
@@ -80,20 +75,19 @@ async fn get_config_toml_parses_all_fields() -> Result<()> {
     .await??;
 
     let config: GetUserSavedConfigResponse = to_response(resp)?;
-    let writable_root = test_tmp_path();
     let expected = GetUserSavedConfigResponse {
         config: UserSavedConfig {
             approval_policy: Some(AskForApproval::OnRequest),
             sandbox_mode: Some(SandboxMode::WorkspaceWrite),
             sandbox_settings: Some(SandboxSettings {
-                writable_roots: vec![writable_root],
+                writable_roots: vec!["/tmp".into()],
                 network_access: Some(true),
                 exclude_tmpdir_env_var: Some(true),
                 exclude_slash_tmp: Some(true),
             }),
             forced_chatgpt_workspace_id: Some("12345678-0000-0000-0000-000000000000".into()),
             forced_login_method: Some(ForcedLoginMethod::Chatgpt),
-            model: Some("gpt-5.1-codex-max".into()),
+            model: Some("gpt-5-codex".into()),
             model_reasoning_effort: Some(ReasoningEffort::High),
             model_reasoning_summary: Some(ReasoningSummary::Detailed),
             model_verbosity: Some(Verbosity::Medium),

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

@@ -19,7 +19,7 @@ use tokio::time::timeout;
 
 use app_test_support::McpProcess;
 use app_test_support::create_mock_chat_completions_server;
-use app_test_support::create_shell_command_sse_response;
+use app_test_support::create_shell_sse_response;
 use app_test_support::to_response;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
@@ -56,7 +56,7 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
     std::fs::create_dir(&working_directory)?;
 
     // Create mock server with a single SSE response: the long sleep command
-    let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
+    let server = create_mock_chat_completions_server(vec![create_shell_sse_response(
         shell_command.clone(),
         Some(&working_directory),
         Some(10_000), // 10 seconds timeout in ms

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

@@ -31,7 +31,6 @@ async fn test_list_and_resume_conversations() -> Result<()> {
         "2025-01-02T12:00:00Z",
         "Hello A",
         Some("openai"),
-        None,
     )?;
     create_fake_rollout(
         codex_home.path(),
@@ -39,7 +38,6 @@ async fn test_list_and_resume_conversations() -> Result<()> {
         "2025-01-01T13:00:00Z",
         "Hello B",
         Some("openai"),
-        None,
     )?;
     create_fake_rollout(
         codex_home.path(),
@@ -47,7 +45,6 @@ async fn test_list_and_resume_conversations() -> Result<()> {
         "2025-01-01T12:00:00Z",
         "Hello C",
         None,
-        None,
     )?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
@@ -108,7 +105,6 @@ async fn test_list_and_resume_conversations() -> Result<()> {
         "2025-01-01T11:30:00Z",
         "Hello TP",
         Some("test-provider"),
-        None,
     )?;
 
     // Filtering by model provider should return only matching sessions.
@@ -358,81 +354,3 @@ async fn test_list_and_resume_conversations() -> Result<()> {
 
     Ok(())
 }
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn list_conversations_fetches_through_filtered_pages() -> Result<()> {
-    let codex_home = TempDir::new()?;
-
-    // Only the last 3 conversations match the provider filter; request 3 and
-    // ensure pagination keeps fetching past non-matching pages.
-    let cases = [
-        (
-            "2025-03-04T12-00-00",
-            "2025-03-04T12:00:00Z",
-            "skip_provider",
-        ),
-        (
-            "2025-03-03T12-00-00",
-            "2025-03-03T12:00:00Z",
-            "skip_provider",
-        ),
-        (
-            "2025-03-02T12-00-00",
-            "2025-03-02T12:00:00Z",
-            "target_provider",
-        ),
-        (
-            "2025-03-01T12-00-00",
-            "2025-03-01T12:00:00Z",
-            "target_provider",
-        ),
-        (
-            "2025-02-28T12-00-00",
-            "2025-02-28T12:00:00Z",
-            "target_provider",
-        ),
-    ];
-
-    for (ts_file, ts_rfc, provider) in cases {
-        create_fake_rollout(
-            codex_home.path(),
-            ts_file,
-            ts_rfc,
-            "Hello",
-            Some(provider),
-            None,
-        )?;
-    }
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let req_id = mcp
-        .send_list_conversations_request(ListConversationsParams {
-            page_size: Some(3),
-            cursor: None,
-            model_providers: Some(vec!["target_provider".to_string()]),
-        })
-        .await?;
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
-    )
-    .await??;
-    let ListConversationsResponse { items, next_cursor } =
-        to_response::<ListConversationsResponse>(resp)?;
-
-    assert_eq!(
-        items.len(),
-        3,
-        "should fetch across pages to satisfy the limit"
-    );
-    assert!(
-        items
-            .iter()
-            .all(|item| item.model_provider == "target_provider")
-    );
-    assert_eq!(next_cursor, None);
-
-    Ok(())
-}

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

@@ -1,6 +1,8 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
+use codex_app_server_protocol::CancelLoginChatGptParams;
+use codex_app_server_protocol::CancelLoginChatGptResponse;
 use codex_app_server_protocol::GetAuthStatusParams;
 use codex_app_server_protocol::GetAuthStatusResponse;
 use codex_app_server_protocol::JSONRPCError;
@@ -12,6 +14,7 @@ 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;
 
@@ -84,6 +87,48 @@ async fn logout_chatgpt_removes_auth() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_and_cancel_chatgpt() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let 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??;
+    let login: LoginChatGptResponse = to_response(login_resp)?;
+
+    let cancel_id = mcp
+        .send_cancel_login_chat_gpt_request(CancelLoginChatGptParams {
+            login_id: login.login_id,
+        })
+        .await?;
+    let cancel_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(cancel_id)),
+    )
+    .await??;
+    let _ok: CancelLoginChatGptResponse = to_response(cancel_resp)?;
+
+    // Optionally observe the completion notification; do not fail if it races.
+    let maybe_note = timeout(
+        Duration::from_secs(2),
+        mcp.read_stream_until_notification_message("codex/event/login_chat_gpt_complete"),
+    )
+    .await;
+    if maybe_note.is_err() {
+        eprintln!("warning: did not observe login_chat_gpt_complete notification after cancel");
+    }
+    Ok(())
+}
+
 fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");
     let contents = format!(

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

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

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

@@ -4,7 +4,6 @@ use anyhow::Result;
 use anyhow::anyhow;
 use app_test_support::McpProcess;
 use app_test_support::to_response;
-use app_test_support::write_models_cache;
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::Model;
@@ -12,7 +11,7 @@ use codex_app_server_protocol::ModelListParams;
 use codex_app_server_protocol::ModelListResponse;
 use codex_app_server_protocol::ReasoningEffortOption;
 use codex_app_server_protocol::RequestId;
-use codex_protocol::openai_models::ReasoningEffort;
+use codex_protocol::config_types::ReasoningEffort;
 use pretty_assertions::assert_eq;
 use tempfile::TempDir;
 use tokio::time::timeout;
@@ -20,10 +19,9 @@ use tokio::time::timeout;
 const DEFAULT_TIMEOUT: Duration = Duration::from_secs(10);
 const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
 
-#[tokio::test]
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
     let codex_home = TempDir::new()?;
-    write_models_cache(codex_home.path())?;
     let mut mcp = McpProcess::new(codex_home.path()).await?;
 
     timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
@@ -48,13 +46,38 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
 
     let expected_models = vec![
         Model {
-            id: "gpt-5.2".to_string(),
-            model: "gpt-5.2".to_string(),
-            display_name: "gpt-5.2".to_string(),
-            description:
-                "Latest frontier model with improvements across knowledge, reasoning and coding"
-                    .to_string(),
+            id: "gpt-5-codex".to_string(),
+            model: "gpt-5-codex".to_string(),
+            display_name: "gpt-5-codex".to_string(),
+            description: "Optimized for codex.".to_string(),
             supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Fastest responses with limited reasoning".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: 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(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Minimal,
+                    description: "Fastest responses with little reasoning".to_string(),
+                },
                 ReasoningEffortOption {
                     reasoning_effort: ReasoningEffort::Low,
                     description: "Balances speed with some reasoning; useful for straightforward \
@@ -72,83 +95,6 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
                     description: "Maximizes reasoning depth for complex or ambiguous problems"
                         .to_string(),
                 },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::XHigh,
-                    description: "Extra high reasoning for complex problems".to_string(),
-                },
-            ],
-            default_reasoning_effort: ReasoningEffort::Medium,
-            is_default: true,
-        },
-        Model {
-            id: "gpt-5.1-codex-mini".to_string(),
-            model: "gpt-5.1-codex-mini".to_string(),
-            display_name: "gpt-5.1-codex-mini".to_string(),
-            description: "Optimized for codex. Cheaper, faster, but less capable.".to_string(),
-            supported_reasoning_efforts: vec![
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::Medium,
-                    description: "Dynamically adjusts reasoning based on the task".to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::High,
-                    description: "Maximizes reasoning depth for complex or ambiguous problems"
-                        .to_string(),
-                },
-            ],
-            default_reasoning_effort: ReasoningEffort::Medium,
-            is_default: false,
-        },
-        Model {
-            id: "gpt-5.1-codex-max".to_string(),
-            model: "gpt-5.1-codex-max".to_string(),
-            display_name: "gpt-5.1-codex-max".to_string(),
-            description: "Codex-optimized flagship for deep and fast reasoning.".to_string(),
-            supported_reasoning_efforts: vec![
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::Low,
-                    description: "Fast responses with lighter reasoning".to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::Medium,
-                    description: "Balances speed and reasoning depth for everyday tasks"
-                        .to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::High,
-                    description: "Greater reasoning depth for complex problems".to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::XHigh,
-                    description: "Extra high reasoning depth for complex problems".to_string(),
-                },
-            ],
-            default_reasoning_effort: ReasoningEffort::Medium,
-            is_default: false,
-        },
-        Model {
-            id: "gpt-5.2-codex".to_string(),
-            model: "gpt-5.2-codex".to_string(),
-            display_name: "gpt-5.2-codex".to_string(),
-            description: "Latest frontier agentic coding model.".to_string(),
-            supported_reasoning_efforts: vec![
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::Low,
-                    description: "Fast responses with lighter reasoning".to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::Medium,
-                    description: "Balances speed and reasoning depth for everyday tasks"
-                        .to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::High,
-                    description: "Greater reasoning depth for complex problems".to_string(),
-                },
-                ReasoningEffortOption {
-                    reasoning_effort: ReasoningEffort::XHigh,
-                    description: "Extra high reasoning depth for complex problems".to_string(),
-                },
             ],
             default_reasoning_effort: ReasoningEffort::Medium,
             is_default: false,
@@ -160,10 +106,9 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
     Ok(())
 }
 
-#[tokio::test]
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn list_models_pagination_works() -> Result<()> {
     let codex_home = TempDir::new()?;
-    write_models_cache(codex_home.path())?;
     let mut mcp = McpProcess::new(codex_home.path()).await?;
 
     timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
@@ -187,7 +132,7 @@ async fn list_models_pagination_works() -> Result<()> {
     } = to_response::<ModelListResponse>(first_response)?;
 
     assert_eq!(first_items.len(), 1);
-    assert_eq!(first_items[0].id, "gpt-5.2");
+    assert_eq!(first_items[0].id, "gpt-5-codex");
     let next_cursor = first_cursor.ok_or_else(|| anyhow!("cursor for second page"))?;
 
     let second_request = mcp
@@ -209,59 +154,14 @@ async fn list_models_pagination_works() -> Result<()> {
     } = to_response::<ModelListResponse>(second_response)?;
 
     assert_eq!(second_items.len(), 1);
-    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-codex-max");
-    let fourth_cursor = third_cursor.ok_or_else(|| anyhow!("cursor for fourth page"))?;
-
-    let fourth_request = mcp
-        .send_list_models_request(ModelListParams {
-            limit: Some(1),
-            cursor: Some(fourth_cursor.clone()),
-        })
-        .await?;
-
-    let fourth_response: JSONRPCResponse = timeout(
-        DEFAULT_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(fourth_request)),
-    )
-    .await??;
-
-    let ModelListResponse {
-        data: fourth_items,
-        next_cursor: fourth_cursor,
-    } = to_response::<ModelListResponse>(fourth_response)?;
-
-    assert_eq!(fourth_items.len(), 1);
-    assert_eq!(fourth_items[0].id, "gpt-5.2-codex");
-    assert!(fourth_cursor.is_none());
+    assert_eq!(second_items[0].id, "gpt-5");
+    assert!(second_cursor.is_none());
     Ok(())
 }
 
-#[tokio::test]
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn list_models_rejects_invalid_cursor() -> Result<()> {
     let codex_home = TempDir::new()?;
-    write_models_cache(codex_home.path())?;
     let mut mcp = McpProcess::new(codex_home.path()).await?;
 
     timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;

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

@@ -1,282 +0,0 @@
-use anyhow::Result;
-use app_test_support::McpProcess;
-use app_test_support::to_response;
-use codex_app_server_protocol::AddConversationListenerParams;
-use codex_app_server_protocol::InputItem;
-use codex_app_server_protocol::JSONRPCResponse;
-use codex_app_server_protocol::NewConversationParams;
-use codex_app_server_protocol::NewConversationResponse;
-use codex_app_server_protocol::RequestId;
-use codex_app_server_protocol::SendUserTurnParams;
-use codex_app_server_protocol::SendUserTurnResponse;
-use codex_core::protocol::AskForApproval;
-use codex_core::protocol::SandboxPolicy;
-use codex_protocol::config_types::ReasoningSummary;
-use codex_protocol::openai_models::ReasoningEffort;
-use core_test_support::responses;
-use core_test_support::skip_if_no_network;
-use pretty_assertions::assert_eq;
-use std::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 send_user_turn_accepts_output_schema_v1() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let server = responses::start_mock_server().await;
-    let body = responses::sse(vec![
-        responses::ev_response_created("resp-1"),
-        responses::ev_assistant_message("msg-1", "Done"),
-        responses::ev_completed("resp-1"),
-    ]);
-    let response_mock = responses::mount_sse_once(&server, body).await;
-
-    let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri())?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let new_conv_id = mcp
-        .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??;
-    let NewConversationResponse {
-        conversation_id, ..
-    } = to_response::<NewConversationResponse>(new_conv_resp)?;
-
-    let listener_id = mcp
-        .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(listener_id)),
-    )
-    .await??;
-
-    let output_schema = serde_json::json!({
-        "type": "object",
-        "properties": {
-            "answer": { "type": "string" }
-        },
-        "required": ["answer"],
-        "additionalProperties": false
-    });
-
-    let send_turn_id = mcp
-        .send_send_user_turn_request(SendUserTurnParams {
-            conversation_id,
-            items: vec![InputItem::Text {
-                text: "Hello".to_string(),
-            }],
-            cwd: codex_home.path().to_path_buf(),
-            approval_policy: AskForApproval::Never,
-            sandbox_policy: SandboxPolicy::new_read_only_policy(),
-            model: "mock-model".to_string(),
-            effort: Some(ReasoningEffort::Medium),
-            summary: ReasoningSummary::Auto,
-            output_schema: Some(output_schema.clone()),
-        })
-        .await?;
-    let _send_turn_resp: SendUserTurnResponse = to_response::<SendUserTurnResponse>(
-        timeout(
-            DEFAULT_READ_TIMEOUT,
-            mcp.read_stream_until_response_message(RequestId::Integer(send_turn_id)),
-        )
-        .await??,
-    )?;
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-
-    let request = response_mock.single_request();
-    let payload = request.body_json();
-    let text = payload.get("text").expect("request missing text field");
-    let format = text
-        .get("format")
-        .expect("request missing text.format field");
-    assert_eq!(
-        format,
-        &serde_json::json!({
-            "name": "codex_output_schema",
-            "type": "json_schema",
-            "strict": true,
-            "schema": output_schema,
-        })
-    );
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn send_user_turn_output_schema_is_per_turn_v1() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let server = responses::start_mock_server().await;
-    let body1 = responses::sse(vec![
-        responses::ev_response_created("resp-1"),
-        responses::ev_assistant_message("msg-1", "Done"),
-        responses::ev_completed("resp-1"),
-    ]);
-    let response_mock1 = responses::mount_sse_once(&server, body1).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 {
-            ..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::<NewConversationResponse>(new_conv_resp)?;
-
-    let listener_id = mcp
-        .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(listener_id)),
-    )
-    .await??;
-
-    let output_schema = serde_json::json!({
-        "type": "object",
-        "properties": {
-            "answer": { "type": "string" }
-        },
-        "required": ["answer"],
-        "additionalProperties": false
-    });
-
-    let send_turn_id = mcp
-        .send_send_user_turn_request(SendUserTurnParams {
-            conversation_id,
-            items: vec![InputItem::Text {
-                text: "Hello".to_string(),
-            }],
-            cwd: codex_home.path().to_path_buf(),
-            approval_policy: AskForApproval::Never,
-            sandbox_policy: SandboxPolicy::new_read_only_policy(),
-            model: "mock-model".to_string(),
-            effort: Some(ReasoningEffort::Medium),
-            summary: ReasoningSummary::Auto,
-            output_schema: Some(output_schema.clone()),
-        })
-        .await?;
-    let _send_turn_resp: SendUserTurnResponse = to_response::<SendUserTurnResponse>(
-        timeout(
-            DEFAULT_READ_TIMEOUT,
-            mcp.read_stream_until_response_message(RequestId::Integer(send_turn_id)),
-        )
-        .await??,
-    )?;
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-
-    let payload1 = response_mock1.single_request().body_json();
-    assert_eq!(
-        payload1.pointer("/text/format"),
-        Some(&serde_json::json!({
-            "name": "codex_output_schema",
-            "type": "json_schema",
-            "strict": true,
-            "schema": output_schema,
-        }))
-    );
-
-    let body2 = responses::sse(vec![
-        responses::ev_response_created("resp-2"),
-        responses::ev_assistant_message("msg-2", "Done"),
-        responses::ev_completed("resp-2"),
-    ]);
-    let response_mock2 = responses::mount_sse_once(&server, body2).await;
-
-    let send_turn_id_2 = mcp
-        .send_send_user_turn_request(SendUserTurnParams {
-            conversation_id,
-            items: vec![InputItem::Text {
-                text: "Hello again".to_string(),
-            }],
-            cwd: codex_home.path().to_path_buf(),
-            approval_policy: AskForApproval::Never,
-            sandbox_policy: SandboxPolicy::new_read_only_policy(),
-            model: "mock-model".to_string(),
-            effort: Some(ReasoningEffort::Medium),
-            summary: ReasoningSummary::Auto,
-            output_schema: None,
-        })
-        .await?;
-    let _send_turn_resp_2: SendUserTurnResponse = to_response::<SendUserTurnResponse>(
-        timeout(
-            DEFAULT_READ_TIMEOUT,
-            mcp.read_stream_until_response_message(RequestId::Integer(send_turn_id_2)),
-        )
-        .await??,
-    )?;
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-
-    let payload2 = response_mock2.single_request().body_json();
-    assert_eq!(payload2.pointer("/text/format"), None);
-
-    Ok(())
-}
-
-fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
-    let config_toml = codex_home.join("config.toml");
-    std::fs::write(
-        config_toml,
-        format!(
-            r#"
-model = "mock-model"
-approval_policy = "never"
-sandbox_mode = "read-only"
-
-model_provider = "mock_provider"
-
-[model_providers.mock_provider]
-name = "Mock provider for test"
-base_url = "{server_uri}/v1"
-wire_api = "responses"
-request_max_retries = 0
-stream_max_retries = 0
-"#
-        ),
-    )
-}

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

@@ -11,7 +11,6 @@ use codex_app_server_protocol::RateLimitSnapshot;
 use codex_app_server_protocol::RateLimitWindow;
 use codex_app_server_protocol::RequestId;
 use codex_core::auth::AuthCredentialsStoreMode;
-use codex_protocol::account::PlanType as AccountPlanType;
 use pretty_assertions::assert_eq;
 use serde_json::json;
 use std::path::Path;
@@ -27,7 +26,7 @@ use wiremock::matchers::path;
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
 
-#[tokio::test]
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn get_account_rate_limits_requires_auth() -> Result<()> {
     let codex_home = TempDir::new()?;
 
@@ -52,7 +51,7 @@ async fn get_account_rate_limits_requires_auth() -> Result<()> {
     Ok(())
 }
 
-#[tokio::test]
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
     let codex_home = TempDir::new()?;
 
@@ -79,7 +78,7 @@ async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
     Ok(())
 }
 
-#[tokio::test]
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
     let codex_home = TempDir::new()?;
     write_chatgpt_auth(
@@ -153,8 +152,6 @@ async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
                 window_duration_mins: Some(1440),
                 resets_at: Some(secondary_reset_timestamp),
             }),
-            credits: None,
-            plan_type: Some(AccountPlanType::Pro),
         },
     };
     assert_eq!(received, expected);

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

@@ -272,45 +272,40 @@ async fn read_raw_response_item(
     mcp: &mut McpProcess,
     conversation_id: ConversationId,
 ) -> ResponseItem {
-    loop {
-        let raw_notification: JSONRPCNotification = timeout(
-            DEFAULT_READ_TIMEOUT,
-            mcp.read_stream_until_notification_message("codex/event/raw_response_item"),
-        )
-        .await
-        .expect("codex/event/raw_response_item notification timeout")
-        .expect("codex/event/raw_response_item notification resp");
+    let 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 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");
+    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"
-        );
+    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 msg_value = params
+        .get("msg")
+        .cloned()
+        .expect("raw response item should include msg payload");
 
-        // Ghost snapshots are produced concurrently and may arrive before the model reply.
-        let event: RawResponseItemEvent =
-            serde_json::from_value(msg_value).expect("deserialize raw response item");
-        if !matches!(event.item, ResponseItem::GhostSnapshot { .. }) {
-            return event.item;
-        }
-    }
+    let event: RawResponseItemEvent =
+        serde_json::from_value(msg_value).expect("deserialize raw response item");
+    event.item
 }
 
 fn assert_instructions_message(item: &ResponseItem) {

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

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

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

@@ -25,13 +25,12 @@ async fn get_user_agent_returns_current_codex_user_agent() -> Result<()> {
     .await??;
 
     let os_info = os_info::get();
-    let originator = codex_core::default_client::originator().value.as_str();
-    let os_type = os_info.os_type();
-    let os_version = os_info.version();
-    let architecture = os_info.architecture().unwrap_or("unknown");
-    let terminal_ua = codex_core::terminal::user_agent();
     let user_agent = format!(
-        "{originator}/0.0.0 ({os_type} {os_version}; {architecture}) {terminal_ua} (codex-app-server-tests; 0.1.0)"
+        "codex_cli_rs/0.0.0 ({} {}; {}) {} (codex-app-server-tests; 0.1.0)",
+        os_info.os_type(),
+        os_info.version(),
+        os_info.architecture().unwrap_or("unknown"),
+        codex_core::terminal::user_agent()
     );
 
     let received: GetUserAgentResponse = to_response(response)?;

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

@@ -2,15 +2,11 @@ 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::GetAuthStatusParams;
+use codex_app_server_protocol::GetAuthStatusResponse;
 use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::LoginAccountResponse;
@@ -19,7 +15,6 @@ 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;
@@ -30,30 +25,22 @@ 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<()> {
+fn create_config_toml(
+    codex_home: &Path,
+    forced_method: Option<&str>,
+    forced_workspace_id: Option<&str>,
+) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");
-    let forced_line = if let Some(method) = params.forced_method {
+    let forced_line = if let Some(method) = forced_method {
         format!("forced_login_method = \"{method}\"\n")
     } else {
         String::new()
     };
-    let forced_workspace_line = if let Some(ws) = params.forced_workspace_id {
+    let forced_workspace_line = if let Some(ws) = 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"
@@ -70,7 +57,6 @@ 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)
@@ -79,7 +65,7 @@ stream_max_retries = 0
 #[tokio::test]
 async fn logout_account_removes_auth_and_notifies() -> Result<()> {
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
+    create_config_toml(codex_home.path(), None, None)?;
 
     login_with_api_key(
         codex_home.path(),
@@ -118,25 +104,27 @@ async fn logout_account_removes_auth_and_notifies() -> Result<()> {
         "auth.json should be deleted"
     );
 
-    let get_id = mcp
-        .send_get_account_request(GetAccountParams {
-            refresh_token: false,
+    let status_id = mcp
+        .send_get_auth_status_request(GetAuthStatusParams {
+            include_token: Some(true),
+            refresh_token: Some(false),
         })
         .await?;
-    let get_resp: JSONRPCResponse = timeout(
+    let status_resp: JSONRPCResponse = timeout(
         DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(get_id)),
+        mcp.read_stream_until_response_message(RequestId::Integer(status_id)),
     )
     .await??;
-    let account: GetAccountResponse = to_response(get_resp)?;
-    assert_eq!(account.account, None);
+    let status: GetAuthStatusResponse = to_response(status_resp)?;
+    assert_eq!(status.auth_method, None);
+    assert_eq!(status.auth_token, 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())?;
+    create_config_toml(codex_home.path(), None, None)?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -183,13 +171,7 @@ async fn login_account_api_key_succeeds_and_notifies() -> Result<()> {
 #[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()
-        },
-    )?;
+    create_config_toml(codex_home.path(), Some("chatgpt"), None)?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -213,13 +195,7 @@ async fn login_account_api_key_rejected_when_forced_chatgpt() -> Result<()> {
 #[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()
-        },
-    )?;
+    create_config_toml(codex_home.path(), Some("api"), None)?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -241,9 +217,9 @@ async fn login_account_chatgpt_rejected_when_forced_api() -> Result<()> {
 #[tokio::test]
 // Serialize tests that launch the login server since it binds to a fixed port.
 #[serial(login_port)]
-async fn login_account_chatgpt_start_can_be_cancelled() -> Result<()> {
+async fn login_account_chatgpt_start() -> Result<()> {
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
+    create_config_toml(codex_home.path(), None, None)?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -309,13 +285,7 @@ async fn login_account_chatgpt_start_can_be_cancelled() -> Result<()> {
 #[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()
-        },
-    )?;
+    create_config_toml(codex_home.path(), None, Some("ws-forced"))?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -337,156 +307,3 @@ async fn login_account_chatgpt_includes_forced_workspace_query_param() -> Result
     );
     Ok(())
 }
-
-#[tokio::test]
-async fn get_account_no_auth() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_config_toml(
-        codex_home.path(),
-        CreateConfigTomlParams {
-            requires_openai_auth: Some(true),
-            ..Default::default()
-        },
-    )?;
-
-    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let params = GetAccountParams {
-        refresh_token: false,
-    };
-    let request_id = mcp.send_get_account_request(params).await?;
-
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let account: GetAccountResponse = to_response(resp)?;
-
-    assert_eq!(account.account, None, "expected no account");
-    assert_eq!(account.requires_openai_auth, true);
-    Ok(())
-}
-
-#[tokio::test]
-async fn get_account_with_api_key() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_config_toml(
-        codex_home.path(),
-        CreateConfigTomlParams {
-            requires_openai_auth: Some(true),
-            ..Default::default()
-        },
-    )?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let req_id = mcp
-        .send_login_account_api_key_request("sk-test-key")
-        .await?;
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
-    )
-    .await??;
-    let _login_ok = to_response::<LoginAccountResponse>(resp)?;
-
-    let params = GetAccountParams {
-        refresh_token: false,
-    };
-    let request_id = mcp.send_get_account_request(params).await?;
-
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let received: GetAccountResponse = to_response(resp)?;
-
-    let expected = GetAccountResponse {
-        account: Some(Account::ApiKey {}),
-        requires_openai_auth: true,
-    };
-    assert_eq!(received, expected);
-    Ok(())
-}
-
-#[tokio::test]
-async fn get_account_when_auth_not_required() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_config_toml(
-        codex_home.path(),
-        CreateConfigTomlParams {
-            requires_openai_auth: Some(false),
-            ..Default::default()
-        },
-    )?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let params = GetAccountParams {
-        refresh_token: false,
-    };
-    let request_id = mcp.send_get_account_request(params).await?;
-
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let received: GetAccountResponse = to_response(resp)?;
-
-    let expected = GetAccountResponse {
-        account: None,
-        requires_openai_auth: false,
-    };
-    assert_eq!(received, expected);
-    Ok(())
-}
-
-#[tokio::test]
-async fn get_account_with_chatgpt() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_config_toml(
-        codex_home.path(),
-        CreateConfigTomlParams {
-            requires_openai_auth: Some(true),
-            ..Default::default()
-        },
-    )?;
-    write_chatgpt_auth(
-        codex_home.path(),
-        ChatGptAuthFixture::new("access-chatgpt")
-            .email("user@example.com")
-            .plan_type("pro"),
-        AuthCredentialsStoreMode::File,
-    )?;
-
-    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let params = GetAccountParams {
-        refresh_token: false,
-    };
-    let request_id = mcp.send_get_account_request(params).await?;
-
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let received: GetAccountResponse = to_response(resp)?;
-
-    let expected = GetAccountResponse {
-        account: Some(Account::Chatgpt {
-            email: "user@example.com".to_string(),
-            plan_type: AccountPlanType::Pro,
-        }),
-        requires_openai_auth: true,
-    };
-    assert_eq!(received, expected);
-    Ok(())
-}

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

@@ -1,476 +0,0 @@
-use anyhow::Result;
-use app_test_support::McpProcess;
-use app_test_support::test_path_buf_with_windows;
-use app_test_support::test_tmp_path_buf;
-use app_test_support::to_response;
-use codex_app_server_protocol::AskForApproval;
-use codex_app_server_protocol::ConfigBatchWriteParams;
-use codex_app_server_protocol::ConfigEdit;
-use codex_app_server_protocol::ConfigLayerSource;
-use codex_app_server_protocol::ConfigReadParams;
-use codex_app_server_protocol::ConfigReadResponse;
-use codex_app_server_protocol::ConfigValueWriteParams;
-use codex_app_server_protocol::ConfigWriteResponse;
-use codex_app_server_protocol::JSONRPCError;
-use codex_app_server_protocol::JSONRPCResponse;
-use codex_app_server_protocol::MergeStrategy;
-use codex_app_server_protocol::RequestId;
-use codex_app_server_protocol::SandboxMode;
-use codex_app_server_protocol::ToolsV2;
-use codex_app_server_protocol::WriteStatus;
-use codex_core::config_loader::SYSTEM_CONFIG_TOML_FILE_UNIX;
-use codex_utils_absolute_path::AbsolutePathBuf;
-use pretty_assertions::assert_eq;
-use serde_json::json;
-use tempfile::TempDir;
-use tokio::time::timeout;
-
-const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
-
-fn write_config(codex_home: &TempDir, contents: &str) -> Result<()> {
-    Ok(std::fs::write(
-        codex_home.path().join("config.toml"),
-        contents,
-    )?)
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn config_read_returns_effective_and_layers() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    write_config(
-        &codex_home,
-        r#"
-model = "gpt-user"
-sandbox_mode = "workspace-write"
-"#,
-    )?;
-    let codex_home_path = codex_home.path().canonicalize()?;
-    let user_file = AbsolutePathBuf::try_from(codex_home_path.join("config.toml"))?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let request_id = mcp
-        .send_config_read_request(ConfigReadParams {
-            include_layers: true,
-        })
-        .await?;
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let ConfigReadResponse {
-        config,
-        origins,
-        layers,
-    } = to_response(resp)?;
-
-    assert_eq!(config.model.as_deref(), Some("gpt-user"));
-    assert_eq!(
-        origins.get("model").expect("origin").name,
-        ConfigLayerSource::User {
-            file: user_file.clone(),
-        }
-    );
-    let layers = layers.expect("layers present");
-    assert_layers_user_then_optional_system(&layers, user_file)?;
-
-    Ok(())
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn config_read_includes_tools() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    write_config(
-        &codex_home,
-        r#"
-model = "gpt-user"
-
-[tools]
-web_search = true
-view_image = false
-"#,
-    )?;
-    let codex_home_path = codex_home.path().canonicalize()?;
-    let user_file = AbsolutePathBuf::try_from(codex_home_path.join("config.toml"))?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let request_id = mcp
-        .send_config_read_request(ConfigReadParams {
-            include_layers: true,
-        })
-        .await?;
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let ConfigReadResponse {
-        config,
-        origins,
-        layers,
-    } = to_response(resp)?;
-
-    let tools = config.tools.expect("tools present");
-    assert_eq!(
-        tools,
-        ToolsV2 {
-            web_search: Some(true),
-            view_image: Some(false),
-        }
-    );
-    assert_eq!(
-        origins.get("tools.web_search").expect("origin").name,
-        ConfigLayerSource::User {
-            file: user_file.clone(),
-        }
-    );
-    assert_eq!(
-        origins.get("tools.view_image").expect("origin").name,
-        ConfigLayerSource::User {
-            file: user_file.clone(),
-        }
-    );
-
-    let layers = layers.expect("layers present");
-    assert_layers_user_then_optional_system(&layers, user_file)?;
-
-    Ok(())
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn config_read_includes_system_layer_and_overrides() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    let user_dir = test_path_buf_with_windows("/user", Some(r"C:\Users\user"));
-    let system_dir = test_path_buf_with_windows("/system", Some(r"C:\System"));
-    write_config(
-        &codex_home,
-        &format!(
-            r#"
-model = "gpt-user"
-approval_policy = "on-request"
-sandbox_mode = "workspace-write"
-
-[sandbox_workspace_write]
-writable_roots = [{}]
-network_access = true
-"#,
-            serde_json::json!(user_dir)
-        ),
-    )?;
-    let codex_home_path = codex_home.path().canonicalize()?;
-    let user_file = AbsolutePathBuf::try_from(codex_home_path.join("config.toml"))?;
-
-    let managed_path = codex_home.path().join("managed_config.toml");
-    let managed_file = AbsolutePathBuf::try_from(managed_path.clone())?;
-    std::fs::write(
-        &managed_path,
-        format!(
-            r#"
-model = "gpt-system"
-approval_policy = "never"
-
-[sandbox_workspace_write]
-writable_roots = [{}]
-"#,
-            serde_json::json!(system_dir.clone())
-        ),
-    )?;
-
-    let managed_path_str = managed_path.display().to_string();
-
-    let mut mcp = McpProcess::new_with_env(
-        codex_home.path(),
-        &[("CODEX_MANAGED_CONFIG_PATH", Some(&managed_path_str))],
-    )
-    .await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let request_id = mcp
-        .send_config_read_request(ConfigReadParams {
-            include_layers: true,
-        })
-        .await?;
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    let ConfigReadResponse {
-        config,
-        origins,
-        layers,
-    } = to_response(resp)?;
-
-    assert_eq!(config.model.as_deref(), Some("gpt-system"));
-    assert_eq!(
-        origins.get("model").expect("origin").name,
-        ConfigLayerSource::LegacyManagedConfigTomlFromFile {
-            file: managed_file.clone(),
-        }
-    );
-
-    assert_eq!(config.approval_policy, Some(AskForApproval::Never));
-    assert_eq!(
-        origins.get("approval_policy").expect("origin").name,
-        ConfigLayerSource::LegacyManagedConfigTomlFromFile {
-            file: managed_file.clone(),
-        }
-    );
-
-    assert_eq!(config.sandbox_mode, Some(SandboxMode::WorkspaceWrite));
-    assert_eq!(
-        origins.get("sandbox_mode").expect("origin").name,
-        ConfigLayerSource::User {
-            file: user_file.clone(),
-        }
-    );
-
-    let sandbox = config
-        .sandbox_workspace_write
-        .as_ref()
-        .expect("sandbox workspace write");
-    assert_eq!(sandbox.writable_roots, vec![system_dir]);
-    assert_eq!(
-        origins
-            .get("sandbox_workspace_write.writable_roots.0")
-            .expect("origin")
-            .name,
-        ConfigLayerSource::LegacyManagedConfigTomlFromFile {
-            file: managed_file.clone(),
-        }
-    );
-
-    assert!(sandbox.network_access);
-    assert_eq!(
-        origins
-            .get("sandbox_workspace_write.network_access")
-            .expect("origin")
-            .name,
-        ConfigLayerSource::User {
-            file: user_file.clone(),
-        }
-    );
-
-    let layers = layers.expect("layers present");
-    assert_layers_managed_user_then_optional_system(&layers, managed_file, user_file)?;
-
-    Ok(())
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn config_value_write_replaces_value() -> Result<()> {
-    let temp_dir = TempDir::new()?;
-    let codex_home = temp_dir.path().canonicalize()?;
-    write_config(
-        &temp_dir,
-        r#"
-model = "gpt-old"
-"#,
-    )?;
-
-    let mut mcp = McpProcess::new(&codex_home).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let read_id = mcp
-        .send_config_read_request(ConfigReadParams {
-            include_layers: false,
-        })
-        .await?;
-    let read_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
-    )
-    .await??;
-    let read: ConfigReadResponse = to_response(read_resp)?;
-    let expected_version = read.origins.get("model").map(|m| m.version.clone());
-
-    let write_id = mcp
-        .send_config_value_write_request(ConfigValueWriteParams {
-            file_path: None,
-            key_path: "model".to_string(),
-            value: json!("gpt-new"),
-            merge_strategy: MergeStrategy::Replace,
-            expected_version,
-        })
-        .await?;
-    let write_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(write_id)),
-    )
-    .await??;
-    let write: ConfigWriteResponse = to_response(write_resp)?;
-    let expected_file_path = AbsolutePathBuf::resolve_path_against_base("config.toml", codex_home)?;
-
-    assert_eq!(write.status, WriteStatus::Ok);
-    assert_eq!(write.file_path, expected_file_path);
-    assert!(write.overridden_metadata.is_none());
-
-    let verify_id = mcp
-        .send_config_read_request(ConfigReadParams {
-            include_layers: false,
-        })
-        .await?;
-    let verify_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(verify_id)),
-    )
-    .await??;
-    let verify: ConfigReadResponse = to_response(verify_resp)?;
-    assert_eq!(verify.config.model.as_deref(), Some("gpt-new"));
-
-    Ok(())
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn config_value_write_rejects_version_conflict() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    write_config(
-        &codex_home,
-        r#"
-model = "gpt-old"
-"#,
-    )?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let write_id = mcp
-        .send_config_value_write_request(ConfigValueWriteParams {
-            file_path: Some(codex_home.path().join("config.toml").display().to_string()),
-            key_path: "model".to_string(),
-            value: json!("gpt-new"),
-            merge_strategy: MergeStrategy::Replace,
-            expected_version: Some("sha256:stale".to_string()),
-        })
-        .await?;
-
-    let err: JSONRPCError = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_error_message(RequestId::Integer(write_id)),
-    )
-    .await??;
-    let code = err
-        .error
-        .data
-        .as_ref()
-        .and_then(|d| d.get("config_write_error_code"))
-        .and_then(|v| v.as_str());
-    assert_eq!(code, Some("configVersionConflict"));
-
-    Ok(())
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn config_batch_write_applies_multiple_edits() -> Result<()> {
-    let tmp_dir = TempDir::new()?;
-    let codex_home = tmp_dir.path().canonicalize()?;
-    write_config(&tmp_dir, "")?;
-
-    let mut mcp = McpProcess::new(&codex_home).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let writable_root = test_tmp_path_buf();
-    let batch_id = mcp
-        .send_config_batch_write_request(ConfigBatchWriteParams {
-            file_path: Some(codex_home.join("config.toml").display().to_string()),
-            edits: vec![
-                ConfigEdit {
-                    key_path: "sandbox_mode".to_string(),
-                    value: json!("workspace-write"),
-                    merge_strategy: MergeStrategy::Replace,
-                },
-                ConfigEdit {
-                    key_path: "sandbox_workspace_write".to_string(),
-                    value: json!({
-                        "writable_roots": [writable_root.clone()],
-                        "network_access": false
-                    }),
-                    merge_strategy: MergeStrategy::Replace,
-                },
-            ],
-            expected_version: None,
-        })
-        .await?;
-    let batch_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(batch_id)),
-    )
-    .await??;
-    let batch_write: ConfigWriteResponse = to_response(batch_resp)?;
-    assert_eq!(batch_write.status, WriteStatus::Ok);
-    let expected_file_path = AbsolutePathBuf::resolve_path_against_base("config.toml", codex_home)?;
-    assert_eq!(batch_write.file_path, expected_file_path);
-
-    let read_id = mcp
-        .send_config_read_request(ConfigReadParams {
-            include_layers: false,
-        })
-        .await?;
-    let read_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
-    )
-    .await??;
-    let read: ConfigReadResponse = to_response(read_resp)?;
-    assert_eq!(read.config.sandbox_mode, Some(SandboxMode::WorkspaceWrite));
-    let sandbox = read
-        .config
-        .sandbox_workspace_write
-        .as_ref()
-        .expect("sandbox workspace write");
-    assert_eq!(sandbox.writable_roots, vec![writable_root]);
-    assert!(!sandbox.network_access);
-
-    Ok(())
-}
-
-fn assert_layers_user_then_optional_system(
-    layers: &[codex_app_server_protocol::ConfigLayer],
-    user_file: AbsolutePathBuf,
-) -> Result<()> {
-    if cfg!(unix) {
-        let system_file = AbsolutePathBuf::from_absolute_path(SYSTEM_CONFIG_TOML_FILE_UNIX)?;
-        assert_eq!(layers.len(), 2);
-        assert_eq!(layers[0].name, ConfigLayerSource::User { file: user_file });
-        assert_eq!(
-            layers[1].name,
-            ConfigLayerSource::System { file: system_file }
-        );
-    } else {
-        assert_eq!(layers.len(), 1);
-        assert_eq!(layers[0].name, ConfigLayerSource::User { file: user_file });
-    }
-    Ok(())
-}
-
-fn assert_layers_managed_user_then_optional_system(
-    layers: &[codex_app_server_protocol::ConfigLayer],
-    managed_file: AbsolutePathBuf,
-    user_file: AbsolutePathBuf,
-) -> Result<()> {
-    if cfg!(unix) {
-        let system_file = AbsolutePathBuf::from_absolute_path(SYSTEM_CONFIG_TOML_FILE_UNIX)?;
-        assert_eq!(layers.len(), 3);
-        assert_eq!(
-            layers[0].name,
-            ConfigLayerSource::LegacyManagedConfigTomlFromFile { file: managed_file }
-        );
-        assert_eq!(layers[1].name, ConfigLayerSource::User { file: user_file });
-        assert_eq!(
-            layers[2].name,
-            ConfigLayerSource::System { file: system_file }
-        );
-    } else {
-        assert_eq!(layers.len(), 2);
-        assert_eq!(
-            layers[0].name,
-            ConfigLayerSource::LegacyManagedConfigTomlFromFile { file: managed_file }
-        );
-        assert_eq!(layers[1].name, ConfigLayerSource::User { file: user_file });
-    }
-    Ok(())
-}

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

@@ -1,9 +1,4 @@
 mod account;
-mod config_rpc;
-mod model_list;
-mod output_schema;
-mod rate_limits;
-mod review;
 mod thread_archive;
 mod thread_list;
 mod thread_resume;

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

@@ -1,231 +0,0 @@
-use anyhow::Result;
-use app_test_support::McpProcess;
-use app_test_support::to_response;
-use codex_app_server_protocol::JSONRPCResponse;
-use codex_app_server_protocol::RequestId;
-use codex_app_server_protocol::ThreadStartParams;
-use codex_app_server_protocol::ThreadStartResponse;
-use codex_app_server_protocol::TurnStartParams;
-use codex_app_server_protocol::TurnStartResponse;
-use codex_app_server_protocol::UserInput as V2UserInput;
-use core_test_support::responses;
-use 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_accepts_output_schema_v2() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let server = responses::start_mock_server().await;
-    let body = responses::sse(vec![
-        responses::ev_response_created("resp-1"),
-        responses::ev_assistant_message("msg-1", "Done"),
-        responses::ev_completed("resp-1"),
-    ]);
-    let response_mock = responses::mount_sse_once(&server, body).await;
-
-    let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri())?;
-
-    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 {
-            ..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 output_schema = serde_json::json!({
-        "type": "object",
-        "properties": {
-            "answer": { "type": "string" }
-        },
-        "required": ["answer"],
-        "additionalProperties": false
-    });
-
-    let turn_req = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "Hello".to_string(),
-            }],
-            output_schema: Some(output_schema.clone()),
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
-    )
-    .await??;
-    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp)?;
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
-    )
-    .await??;
-
-    let request = response_mock.single_request();
-    let payload = request.body_json();
-    let text = payload.get("text").expect("request missing text field");
-    let format = text
-        .get("format")
-        .expect("request missing text.format field");
-    assert_eq!(
-        format,
-        &serde_json::json!({
-            "name": "codex_output_schema",
-            "type": "json_schema",
-            "strict": true,
-            "schema": output_schema,
-        })
-    );
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn turn_start_output_schema_is_per_turn_v2() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let server = responses::start_mock_server().await;
-    let body1 = responses::sse(vec![
-        responses::ev_response_created("resp-1"),
-        responses::ev_assistant_message("msg-1", "Done"),
-        responses::ev_completed("resp-1"),
-    ]);
-    let response_mock1 = responses::mount_sse_once(&server, body1).await;
-
-    let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri())?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let thread_req = mcp
-        .send_thread_start_request(ThreadStartParams {
-            ..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 output_schema = serde_json::json!({
-        "type": "object",
-        "properties": {
-            "answer": { "type": "string" }
-        },
-        "required": ["answer"],
-        "additionalProperties": false
-    });
-
-    let turn_req_1 = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "Hello".to_string(),
-            }],
-            output_schema: Some(output_schema.clone()),
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp_1: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_req_1)),
-    )
-    .await??;
-    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp_1)?;
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
-    )
-    .await??;
-
-    let payload1 = response_mock1.single_request().body_json();
-    assert_eq!(
-        payload1.pointer("/text/format"),
-        Some(&serde_json::json!({
-            "name": "codex_output_schema",
-            "type": "json_schema",
-            "strict": true,
-            "schema": output_schema,
-        }))
-    );
-
-    let body2 = responses::sse(vec![
-        responses::ev_response_created("resp-2"),
-        responses::ev_assistant_message("msg-2", "Done"),
-        responses::ev_completed("resp-2"),
-    ]);
-    let response_mock2 = responses::mount_sse_once(&server, body2).await;
-
-    let turn_req_2 = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "Hello again".to_string(),
-            }],
-            output_schema: None,
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp_2: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_req_2)),
-    )
-    .await??;
-    let _turn: TurnStartResponse = to_response::<TurnStartResponse>(turn_resp_2)?;
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
-    )
-    .await??;
-
-    let payload2 = response_mock2.single_request().body_json();
-    assert_eq!(payload2.pointer("/text/format"), None);
-
-    Ok(())
-}
-
-fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
-    let config_toml = codex_home.join("config.toml");
-    std::fs::write(
-        config_toml,
-        format!(
-            r#"
-model = "mock-model"
-approval_policy = "never"
-sandbox_mode = "read-only"
-
-model_provider = "mock_provider"
-
-[model_providers.mock_provider]
-name = "Mock provider for test"
-base_url = "{server_uri}/v1"
-wire_api = "responses"
-request_max_retries = 0
-stream_max_retries = 0
-"#
-        ),
-    )
-}

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

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

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

@@ -35,7 +35,7 @@ async fn thread_archive_moves_rollout_into_archived_directory() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(start_resp)?;
     assert!(!thread.id.is_empty());
 
     // Locate the rollout path recorded for this thread id.

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

@@ -2,100 +2,39 @@ use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_fake_rollout;
 use app_test_support::to_response;
-use codex_app_server_protocol::GitInfo as ApiGitInfo;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
-use codex_app_server_protocol::SessionSource;
+use codex_app_server_protocol::ThreadListParams;
 use codex_app_server_protocol::ThreadListResponse;
-use codex_protocol::protocol::GitInfo as CoreGitInfo;
-use std::path::Path;
-use std::path::PathBuf;
+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);
 
-async fn init_mcp(codex_home: &Path) -> Result<McpProcess> {
-    let mut mcp = McpProcess::new(codex_home).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-    Ok(mcp)
-}
-
-async fn list_threads(
-    mcp: &mut McpProcess,
-    cursor: Option<String>,
-    limit: Option<u32>,
-    providers: Option<Vec<String>>,
-) -> Result<ThreadListResponse> {
-    let request_id = mcp
-        .send_thread_list_request(codex_app_server_protocol::ThreadListParams {
-            cursor,
-            limit,
-            model_providers: providers,
-        })
-        .await?;
-    let resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
-    )
-    .await??;
-    to_response::<ThreadListResponse>(resp)
-}
-
-fn create_fake_rollouts<F, G>(
-    codex_home: &Path,
-    count: usize,
-    provider_for_index: F,
-    timestamp_for_index: G,
-    preview: &str,
-) -> Result<Vec<String>>
-where
-    F: Fn(usize) -> &'static str,
-    G: Fn(usize) -> (String, String),
-{
-    let mut ids = Vec::with_capacity(count);
-    for i in 0..count {
-        let (ts_file, ts_rfc) = timestamp_for_index(i);
-        ids.push(create_fake_rollout(
-            codex_home,
-            &ts_file,
-            &ts_rfc,
-            preview,
-            Some(provider_for_index(i)),
-            None,
-        )?);
-    }
-    Ok(ids)
-}
-
-fn timestamp_at(
-    year: i32,
-    month: u32,
-    day: u32,
-    hour: u32,
-    minute: u32,
-    second: u32,
-) -> (String, String) {
-    (
-        format!("{year:04}-{month:02}-{day:02}T{hour:02}-{minute:02}-{second:02}"),
-        format!("{year:04}-{month:02}-{day:02}T{hour:02}:{minute:02}:{second:02}Z"),
-    )
-}
-
 #[tokio::test]
 async fn thread_list_basic_empty() -> Result<()> {
     let codex_home = TempDir::new()?;
     create_minimal_config(codex_home.path())?;
 
-    let mut mcp = init_mcp(codex_home.path()).await?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
-    let ThreadListResponse { data, next_cursor } = list_threads(
-        &mut mcp,
-        None,
-        Some(10),
-        Some(vec!["mock_provider".to_string()]),
+    // 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?;
+    .await??;
+    let ThreadListResponse { data, next_cursor } = to_response::<ThreadListResponse>(list_resp)?;
     assert!(data.is_empty());
     assert_eq!(next_cursor, None);
 
@@ -126,7 +65,6 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         "2025-01-02T12:00:00Z",
         "Hello",
         Some("mock_provider"),
-        None,
     )?;
     let _b = create_fake_rollout(
         codex_home.path(),
@@ -134,7 +72,6 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         "2025-01-01T13:00:00Z",
         "Hello",
         Some("mock_provider"),
-        None,
     )?;
     let _c = create_fake_rollout(
         codex_home.path(),
@@ -142,55 +79,49 @@ async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
         "2025-01-01T12:00:00Z",
         "Hello",
         Some("mock_provider"),
-        None,
     )?;
 
-    let mut mcp = init_mcp(codex_home.path()).await?;
+    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,
-    } = list_threads(
-        &mut mcp,
-        None,
-        Some(2),
-        Some(vec!["mock_provider".to_string()]),
-    )
-    .await?;
+    } = 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);
-        assert_eq!(thread.cwd, PathBuf::from("/"));
-        assert_eq!(thread.cli_version, "0.0.0");
-        assert_eq!(thread.source, SessionSource::Cli);
-        assert_eq!(thread.git_info, None);
-    }
     let cursor1 = cursor1.expect("expected nextCursor on first page");
 
     // Page 2: with cursor → expect next_cursor None when no more results.
+    let 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,
-    } = list_threads(
-        &mut mcp,
-        Some(cursor1),
-        Some(2),
-        Some(vec!["mock_provider".to_string()]),
-    )
-    .await?;
+    } = 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!(thread.cwd, PathBuf::from("/"));
-        assert_eq!(thread.cli_version, "0.0.0");
-        assert_eq!(thread.source, SessionSource::Cli);
-        assert_eq!(thread.git_info, None);
-    }
     assert_eq!(cursor2, None, "expected nextCursor to be null on last page");
 
     Ok(())
@@ -208,224 +139,67 @@ async fn thread_list_respects_provider_filter() -> Result<()> {
         "2025-01-02T10:00:00Z",
         "X",
         Some("mock_provider"),
-        None,
     )?; // mock_provider
-    let _b = create_fake_rollout(
-        codex_home.path(),
-        "2025-01-02T11-00-00",
-        "2025-01-02T11:00:00Z",
-        "X",
-        Some("other_provider"),
-        None,
-    )?;
+    // one with a different provider
+    let uuid = Uuid::new_v4();
+    let dir = codex_home
+        .path()
+        .join("sessions")
+        .join("2025")
+        .join("01")
+        .join("02");
+    std::fs::create_dir_all(&dir)?;
+    let file_path = dir.join(format!("rollout-2025-01-02T11-00-00-{uuid}.jsonl"));
+    let lines = [
+        json!({
+            "timestamp": "2025-01-02T11:00:00Z",
+            "type": "session_meta",
+            "payload": {
+                "id": uuid,
+                "timestamp": "2025-01-02T11:00:00Z",
+                "cwd": "/",
+                "originator": "codex",
+                "cli_version": "0.0.0",
+                "instructions": null,
+                "source": "vscode",
+                "model_provider": "other_provider"
+            }
+        })
+        .to_string(),
+        json!({
+            "timestamp": "2025-01-02T11:00:00Z",
+            "type":"response_item",
+            "payload": {"type":"message","role":"user","content":[{"type":"input_text","text":"X"}]}
+        })
+        .to_string(),
+        json!({
+            "timestamp": "2025-01-02T11:00:00Z",
+            "type":"event_msg",
+            "payload": {"type":"user_message","message":"X","kind":"plain"}
+        })
+        .to_string(),
+    ];
+    std::fs::write(file_path, lines.join("\n") + "\n")?;
 
-    let mut mcp = init_mcp(codex_home.path()).await?;
+    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 ThreadListResponse { data, next_cursor } = list_threads(
-        &mut mcp,
-        None,
-        Some(10),
-        Some(vec!["other_provider".to_string()]),
+    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?;
+    .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);
-    assert_eq!(thread.cwd, PathBuf::from("/"));
-    assert_eq!(thread.cli_version, "0.0.0");
-    assert_eq!(thread.source, SessionSource::Cli);
-    assert_eq!(thread.git_info, None);
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_list_fetches_until_limit_or_exhausted() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_minimal_config(codex_home.path())?;
-
-    // Newest 16 conversations belong to a different provider; the older 8 are the
-    // only ones that match the filter. We request 8 so the server must keep
-    // paging past the first two pages to reach the desired count.
-    create_fake_rollouts(
-        codex_home.path(),
-        24,
-        |i| {
-            if i < 16 {
-                "skip_provider"
-            } else {
-                "target_provider"
-            }
-        },
-        |i| timestamp_at(2025, 3, 30 - i as u32, 12, 0, 0),
-        "Hello",
-    )?;
-
-    let mut mcp = init_mcp(codex_home.path()).await?;
-
-    // Request 8 threads for the target provider; the matches only start on the
-    // third page so we rely on pagination to reach the limit.
-    let ThreadListResponse { data, next_cursor } = list_threads(
-        &mut mcp,
-        None,
-        Some(8),
-        Some(vec!["target_provider".to_string()]),
-    )
-    .await?;
-    assert_eq!(
-        data.len(),
-        8,
-        "should keep paging until the requested count is filled"
-    );
-    assert!(
-        data.iter()
-            .all(|thread| thread.model_provider == "target_provider"),
-        "all returned threads must match the requested provider"
-    );
-    assert_eq!(
-        next_cursor, None,
-        "once the requested count is satisfied on the final page, nextCursor should be None"
-    );
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_list_enforces_max_limit() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_minimal_config(codex_home.path())?;
-
-    create_fake_rollouts(
-        codex_home.path(),
-        105,
-        |_| "mock_provider",
-        |i| {
-            let month = 5 + (i / 28);
-            let day = (i % 28) + 1;
-            timestamp_at(2025, month as u32, day as u32, 0, 0, 0)
-        },
-        "Hello",
-    )?;
-
-    let mut mcp = init_mcp(codex_home.path()).await?;
-
-    let ThreadListResponse { data, next_cursor } = list_threads(
-        &mut mcp,
-        None,
-        Some(200),
-        Some(vec!["mock_provider".to_string()]),
-    )
-    .await?;
-    assert_eq!(
-        data.len(),
-        100,
-        "limit should be clamped to the maximum page size"
-    );
-    assert!(
-        next_cursor.is_some(),
-        "when more than the maximum exist, nextCursor should continue pagination"
-    );
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_list_stops_when_not_enough_filtered_results_exist() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_minimal_config(codex_home.path())?;
-
-    // Only the last 7 conversations match the provider filter; we ask for 10 to
-    // ensure the server exhausts pagination without looping forever.
-    create_fake_rollouts(
-        codex_home.path(),
-        22,
-        |i| {
-            if i < 15 {
-                "skip_provider"
-            } else {
-                "target_provider"
-            }
-        },
-        |i| timestamp_at(2025, 4, 28 - i as u32, 8, 0, 0),
-        "Hello",
-    )?;
-
-    let mut mcp = init_mcp(codex_home.path()).await?;
-
-    // Request more threads than exist after filtering; expect all matches to be
-    // returned with nextCursor None.
-    let ThreadListResponse { data, next_cursor } = list_threads(
-        &mut mcp,
-        None,
-        Some(10),
-        Some(vec!["target_provider".to_string()]),
-    )
-    .await?;
-    assert_eq!(
-        data.len(),
-        7,
-        "all available filtered threads should be returned"
-    );
-    assert!(
-        data.iter()
-            .all(|thread| thread.model_provider == "target_provider"),
-        "results should still respect the provider filter"
-    );
-    assert_eq!(
-        next_cursor, None,
-        "when results are exhausted before reaching the limit, nextCursor should be None"
-    );
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_list_includes_git_info() -> Result<()> {
-    let codex_home = TempDir::new()?;
-    create_minimal_config(codex_home.path())?;
-
-    let git_info = CoreGitInfo {
-        commit_hash: Some("abc123".to_string()),
-        branch: Some("main".to_string()),
-        repository_url: Some("https://example.com/repo.git".to_string()),
-    };
-    let conversation_id = create_fake_rollout(
-        codex_home.path(),
-        "2025-02-01T09-00-00",
-        "2025-02-01T09:00:00Z",
-        "Git info preview",
-        Some("mock_provider"),
-        Some(git_info),
-    )?;
-
-    let mut mcp = init_mcp(codex_home.path()).await?;
-
-    let ThreadListResponse { data, .. } = list_threads(
-        &mut mcp,
-        None,
-        Some(10),
-        Some(vec!["mock_provider".to_string()]),
-    )
-    .await?;
-    let thread = data
-        .iter()
-        .find(|t| t.id == conversation_id)
-        .expect("expected thread for created rollout");
-
-    let expected_git = ApiGitInfo {
-        sha: Some("abc123".to_string()),
-        branch: Some("main".to_string()),
-        origin_url: Some("https://example.com/repo.git".to_string()),
-    };
-    assert_eq!(thread.git_info, Some(expected_git));
-    assert_eq!(thread.source, SessionSource::Cli);
-    assert_eq!(thread.cwd, PathBuf::from("/"));
-    assert_eq!(thread.cli_version, "0.0.0");
 
     Ok(())
 }

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

@@ -1,28 +1,20 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
-use app_test_support::create_fake_rollout;
 use app_test_support::create_mock_chat_completions_server;
 use app_test_support::to_response;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
-use codex_app_server_protocol::SessionSource;
-use codex_app_server_protocol::ThreadItem;
 use codex_app_server_protocol::ThreadResumeParams;
 use codex_app_server_protocol::ThreadResumeResponse;
 use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
-use codex_app_server_protocol::TurnStatus;
-use codex_app_server_protocol::UserInput;
-use codex_protocol::models::ContentItem;
-use codex_protocol::models::ResponseItem;
-use std::path::PathBuf;
 use tempfile::TempDir;
 use tokio::time::timeout;
 
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
 #[tokio::test]
-async fn thread_resume_returns_original_thread() -> Result<()> {
+async fn thread_resume_returns_existing_thread() -> Result<()> {
     let server = create_mock_chat_completions_server(vec![]).await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
@@ -33,7 +25,7 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
     // Start a thread.
     let start_id = mcp
         .send_thread_start_request(ThreadStartParams {
-            model: Some("gpt-5.1-codex-max".to_string()),
+            model: Some("gpt-5-codex".to_string()),
             ..Default::default()
         })
         .await?;
@@ -42,13 +34,12 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+    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(
@@ -56,177 +47,9 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
     )
     .await??;
-    let ThreadResumeResponse {
-        thread: resumed, ..
-    } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    assert_eq!(resumed, thread);
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_resume_returns_rollout_history() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
-    let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri())?;
-
-    let preview = "Saved user message";
-    let conversation_id = create_fake_rollout(
-        codex_home.path(),
-        "2025-01-05T12-00-00",
-        "2025-01-05T12:00:00Z",
-        preview,
-        Some("mock_provider"),
-        None,
-    )?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let resume_id = mcp
-        .send_thread_resume_request(ThreadResumeParams {
-            thread_id: conversation_id.clone(),
-            ..Default::default()
-        })
-        .await?;
-    let resume_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
-    )
-    .await??;
-    let ThreadResumeResponse { thread, .. } = to_response::<ThreadResumeResponse>(resume_resp)?;
-
-    assert_eq!(thread.id, conversation_id);
-    assert_eq!(thread.preview, preview);
-    assert_eq!(thread.model_provider, "mock_provider");
-    assert!(thread.path.is_absolute());
-    assert_eq!(thread.cwd, PathBuf::from("/"));
-    assert_eq!(thread.cli_version, "0.0.0");
-    assert_eq!(thread.source, SessionSource::Cli);
-    assert_eq!(thread.git_info, None);
-
-    assert_eq!(
-        thread.turns.len(),
-        1,
-        "expected rollouts to include one turn"
-    );
-    let turn = &thread.turns[0];
-    assert_eq!(turn.status, TurnStatus::Completed);
-    assert_eq!(turn.items.len(), 1, "expected user message item");
-    match &turn.items[0] {
-        ThreadItem::UserMessage { content, .. } => {
-            assert_eq!(
-                content,
-                &vec![UserInput::Text {
-                    text: preview.to_string()
-                }]
-            );
-        }
-        other => panic!("expected user message item, got {other:?}"),
-    }
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
-    let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri())?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let start_id = mcp
-        .send_thread_start_request(ThreadStartParams {
-            model: Some("gpt-5.1-codex-max".to_string()),
-            ..Default::default()
-        })
-        .await?;
-    let start_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
-    )
-    .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
-
-    let thread_path = thread.path.clone();
-    let resume_id = mcp
-        .send_thread_resume_request(ThreadResumeParams {
-            thread_id: "not-a-valid-thread-id".to_string(),
-            path: Some(thread_path),
-            ..Default::default()
-        })
-        .await?;
-
-    let resume_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
-    )
-    .await??;
-    let ThreadResumeResponse {
-        thread: resumed, ..
-    } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    assert_eq!(resumed, thread);
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn thread_resume_supports_history_and_overrides() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
-    let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path(), &server.uri())?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    // Start a thread.
-    let start_id = mcp
-        .send_thread_start_request(ThreadStartParams {
-            model: Some("gpt-5.1-codex-max".to_string()),
-            ..Default::default()
-        })
-        .await?;
-    let start_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
-    )
-    .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
-
-    let history_text = "Hello from history";
-    let history = vec![ResponseItem::Message {
-        id: None,
-        role: "user".to_string(),
-        content: vec![ContentItem::InputText {
-            text: history_text.to_string(),
-        }],
-    }];
-
-    // Resume with explicit history and override the model.
-    let resume_id = mcp
-        .send_thread_resume_request(ThreadResumeParams {
-            thread_id: thread.id,
-            history: Some(history),
-            model: Some("mock-model".to_string()),
-            model_provider: Some("mock_provider".to_string()),
-            ..Default::default()
-        })
-        .await?;
-    let resume_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
-    )
-    .await??;
-    let ThreadResumeResponse {
-        thread: resumed,
-        model_provider,
-        ..
-    } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    assert!(!resumed.id.is_empty());
-    assert_eq!(model_provider, "mock_provider");
-    assert_eq!(resumed.preview, history_text);
+    let ThreadResumeResponse { thread: resumed } =
+        to_response::<ThreadResumeResponse>(resume_resp)?;
+    assert_eq!(resumed.id, thread.id);
 
     Ok(())
 }

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

@@ -29,7 +29,7 @@ async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
     // Start a v2 thread with an explicit model override.
     let req_id = mcp
         .send_thread_start_request(ThreadStartParams {
-            model: Some("gpt-5.1".to_string()),
+            model: Some("gpt-5".to_string()),
             ..Default::default()
         })
         .await?;
@@ -40,21 +40,8 @@ async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
     )
     .await??;
-    let ThreadStartResponse {
-        thread,
-        model_provider,
-        ..
-    } = to_response::<ThreadStartResponse>(resp)?;
+    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!(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(
@@ -64,7 +51,7 @@ async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
     .await??;
     let started: ThreadStartedNotification =
         serde_json::from_value(notif.params.expect("params must be present"))?;
-    assert_eq!(started.thread, thread);
+    assert_eq!(started.thread.id, thread.id);
 
     Ok(())
 }

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

@@ -3,19 +3,16 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_mock_chat_completions_server;
-use app_test_support::create_shell_command_sse_response;
+use app_test_support::create_shell_sse_response;
 use app_test_support::to_response;
-use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
-use codex_app_server_protocol::TurnCompletedNotification;
 use codex_app_server_protocol::TurnInterruptParams;
 use codex_app_server_protocol::TurnInterruptResponse;
 use codex_app_server_protocol::TurnStartParams;
 use codex_app_server_protocol::TurnStartResponse;
-use codex_app_server_protocol::TurnStatus;
 use codex_app_server_protocol::UserInput as V2UserInput;
 use tempfile::TempDir;
 use tokio::time::timeout;
@@ -41,7 +38,7 @@ async fn turn_interrupt_aborts_running_turn() -> Result<()> {
     std::fs::create_dir(&working_directory)?;
 
     // Mock server: long-running shell command then (after abort) nothing else needed.
-    let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
+    let server = create_mock_chat_completions_server(vec![create_shell_sse_response(
         shell_command.clone(),
         Some(&working_directory),
         Some(10_000),
@@ -65,7 +62,7 @@ async fn turn_interrupt_aborts_running_turn() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(thread_resp)?;
 
     // Start a turn that triggers a long-running command.
     let turn_req = mcp
@@ -88,11 +85,10 @@ async fn turn_interrupt_aborts_running_turn() -> Result<()> {
     // Give the command a brief moment to start.
     tokio::time::sleep(std::time::Duration::from_secs(1)).await;
 
-    let thread_id = thread.id.clone();
     // Interrupt the in-progress turn by id (v2 API).
     let interrupt_id = mcp
         .send_turn_interrupt_request(TurnInterruptParams {
-            thread_id: thread_id.clone(),
+            thread_id: thread.id,
             turn_id: turn.id,
         })
         .await?;
@@ -103,19 +99,7 @@ async fn turn_interrupt_aborts_running_turn() -> Result<()> {
     .await??;
     let _resp: TurnInterruptResponse = to_response::<TurnInterruptResponse>(interrupt_resp)?;
 
-    let completed_notif: JSONRPCNotification = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
-    )
-    .await??;
-    let completed: TurnCompletedNotification = serde_json::from_value(
-        completed_notif
-            .params
-            .expect("turn/completed params must be present"),
-    )?;
-    assert_eq!(completed.thread_id, thread_id);
-    assert_eq!(completed.turn.status, TurnStatus::Interrupted);
-
+    // No fields to assert on; successful deserialization confirms proper response shape.
     Ok(())
 }
 

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

@@ -1,37 +1,25 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
-use app_test_support::create_apply_patch_sse_response;
-use app_test_support::create_exec_command_sse_response;
 use app_test_support::create_final_assistant_message_sse_response;
 use app_test_support::create_mock_chat_completions_server;
 use app_test_support::create_mock_chat_completions_server_unchecked;
-use app_test_support::create_shell_command_sse_response;
-use app_test_support::format_with_current_shell_display;
+use app_test_support::create_shell_sse_response;
 use app_test_support::to_response;
-use codex_app_server_protocol::ApprovalDecision;
-use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
-use codex_app_server_protocol::CommandExecutionStatus;
-use codex_app_server_protocol::FileChangeOutputDeltaNotification;
-use codex_app_server_protocol::FileChangeRequestApprovalResponse;
-use codex_app_server_protocol::ItemCompletedNotification;
-use codex_app_server_protocol::ItemStartedNotification;
 use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCResponse;
-use codex_app_server_protocol::PatchApplyStatus;
-use codex_app_server_protocol::PatchChangeKind;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::ServerRequest;
-use codex_app_server_protocol::ThreadItem;
 use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
-use codex_app_server_protocol::TurnCompletedNotification;
 use codex_app_server_protocol::TurnStartParams;
 use codex_app_server_protocol::TurnStartResponse;
 use codex_app_server_protocol::TurnStartedNotification;
-use codex_app_server_protocol::TurnStatus;
 use codex_app_server_protocol::UserInput as V2UserInput;
+use codex_core::protocol_config_types::ReasoningEffort;
 use codex_core::protocol_config_types::ReasoningSummary;
-use codex_protocol::openai_models::ReasoningEffort;
+use codex_protocol::parse_command::ParsedCommand;
+use codex_protocol::protocol::Event;
+use codex_protocol::protocol::EventMsg;
 use core_test_support::skip_if_no_network;
 use pretty_assertions::assert_eq;
 use std::path::Path;
@@ -69,7 +57,7 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
         mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(thread_resp)?;
 
     // Start a turn with only input and thread_id set (no overrides).
     let turn_req = mcp
@@ -97,7 +85,6 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
     .await??;
     let started: TurnStartedNotification =
         serde_json::from_value(notif.params.expect("params must be present"))?;
-    assert_eq!(started.thread_id, thread.id);
     assert_eq!(
         started.turn.status,
         codex_app_server_protocol::TurnStatus::InProgress
@@ -131,18 +118,13 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
     )
     .await??;
 
-    let completed_notif: JSONRPCNotification = timeout(
+    // 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("turn/completed"),
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
     .await??;
-    let completed: TurnCompletedNotification = serde_json::from_value(
-        completed_notif
-            .params
-            .expect("turn/completed params must be present"),
-    )?;
-    assert_eq!(completed.thread_id, thread.id);
-    assert_eq!(completed.turn.status, TurnStatus::Completed);
 
     Ok(())
 }
@@ -175,7 +157,7 @@ async fn turn_start_accepts_local_image_input() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
+    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.
@@ -209,7 +191,7 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
     // Mock server: first turn requests a shell call (elicitation), then completes.
     // Second turn same, but we'll set approval_policy=never to avoid elicitation.
     let responses = vec![
-        create_shell_command_sse_response(
+        create_shell_sse_response(
             vec![
                 "python3".to_string(),
                 "-c".to_string(),
@@ -220,7 +202,7 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
             "call1",
         )?,
         create_final_assistant_message_sse_response("done 1")?,
-        create_shell_command_sse_response(
+        create_shell_sse_response(
             vec![
                 "python3".to_string(),
                 "-c".to_string(),
@@ -251,9 +233,9 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(start_resp)?;
 
-    // turn/start — expect CommandExecutionRequestApproval request from server
+    // turn/start — expect ExecCommandApproval request from server
     let first_turn_id = mcp
         .send_turn_start_request(TurnStartParams {
             thread_id: thread.id.clone(),
@@ -276,10 +258,16 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
         mcp.read_stream_until_request_message(),
     )
     .await??;
-    let ServerRequest::CommandExecutionRequestApproval { request_id, params } = server_req else {
-        panic!("expected CommandExecutionRequestApproval request");
+    let ServerRequest::ExecCommandApproval { request_id, params } = server_req else {
+        panic!("expected ExecCommandApproval request");
     };
-    assert_eq!(params.item_id, "call1");
+    assert_eq!(params.call_id, "call1");
+    assert_eq!(
+        params.parsed_cmd,
+        vec![ParsedCommand::Unknown {
+            cmd: "python3 -c 'print(42)'".to_string()
+        }]
+    );
 
     // Approve and wait for task completion
     mcp.send_response(
@@ -292,11 +280,6 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
     .await??;
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
-    )
-    .await??;
 
     // Second turn with approval_policy=never should not elicit approval
     let second_turn_id = mcp
@@ -319,150 +302,7 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
     )
     .await??;
 
-    // Ensure we do NOT receive a CommandExecutionRequestApproval request before task completes
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
-    )
-    .await??;
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn turn_start_exec_approval_decline_v2() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let tmp = TempDir::new()?;
-    let codex_home = tmp.path().to_path_buf();
-    let workspace = tmp.path().join("workspace");
-    std::fs::create_dir(&workspace)?;
-
-    let responses = vec![
-        create_shell_command_sse_response(
-            vec![
-                "python3".to_string(),
-                "-c".to_string(),
-                "print(42)".to_string(),
-            ],
-            None,
-            Some(5000),
-            "call-decline",
-        )?,
-        create_final_assistant_message_sse_response("done")?,
-    ];
-    let server = create_mock_chat_completions_server(responses).await;
-    create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
-
-    let mut mcp = McpProcess::new(codex_home.as_path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let start_id = mcp
-        .send_thread_start_request(ThreadStartParams {
-            model: Some("mock-model".to_string()),
-            ..Default::default()
-        })
-        .await?;
-    let start_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
-    )
-    .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
-
-    let turn_id = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "run python".to_string(),
-            }],
-            cwd: Some(workspace.clone()),
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
-    )
-    .await??;
-    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
-
-    let started_command_execution = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let started_notif = mcp
-                .read_stream_until_notification_message("item/started")
-                .await?;
-            let started: ItemStartedNotification =
-                serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
-            if let ThreadItem::CommandExecution { .. } = started.item {
-                return Ok::<ThreadItem, anyhow::Error>(started.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::CommandExecution { id, status, .. } = started_command_execution else {
-        unreachable!("loop ensures we break on command execution items");
-    };
-    assert_eq!(id, "call-decline");
-    assert_eq!(status, CommandExecutionStatus::InProgress);
-
-    let server_req = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_request_message(),
-    )
-    .await??;
-    let ServerRequest::CommandExecutionRequestApproval { request_id, params } = server_req else {
-        panic!("expected CommandExecutionRequestApproval request")
-    };
-    assert_eq!(params.item_id, "call-decline");
-    assert_eq!(params.thread_id, thread.id);
-    assert_eq!(params.turn_id, turn.id);
-
-    mcp.send_response(
-        request_id,
-        serde_json::to_value(CommandExecutionRequestApprovalResponse {
-            decision: ApprovalDecision::Decline,
-        })?,
-    )
-    .await?;
-
-    let completed_command_execution = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let completed_notif = mcp
-                .read_stream_until_notification_message("item/completed")
-                .await?;
-            let completed: ItemCompletedNotification = serde_json::from_value(
-                completed_notif
-                    .params
-                    .clone()
-                    .expect("item/completed params"),
-            )?;
-            if let ThreadItem::CommandExecution { .. } = completed.item {
-                return Ok::<ThreadItem, anyhow::Error>(completed.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::CommandExecution {
-        id,
-        status,
-        exit_code,
-        aggregated_output,
-        ..
-    } = completed_command_execution
-    else {
-        unreachable!("loop ensures we break on command execution items");
-    };
-    assert_eq!(id, "call-decline");
-    assert_eq!(status, CommandExecutionStatus::Declined);
-    assert!(exit_code.is_none());
-    assert!(aggregated_output.is_none());
-
+    // Ensure we do NOT receive an ExecCommandApproval request before task completes
     timeout(
         DEFAULT_READ_TIMEOUT,
         mcp.read_stream_until_notification_message("codex/event/task_complete"),
@@ -474,6 +314,8 @@ async fn turn_start_exec_approval_decline_v2() -> Result<()> {
 
 #[tokio::test]
 async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
+    // When returning Result from a test, pass an Ok(()) to the skip macro
+    // so the early return type matches. The no-arg form returns unit.
     skip_if_no_network!(Ok(()));
 
     let tmp = TempDir::new()?;
@@ -487,15 +329,23 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
     std::fs::create_dir(&second_cwd)?;
 
     let responses = vec![
-        create_shell_command_sse_response(
-            vec!["echo".to_string(), "first".to_string(), "turn".to_string()],
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo first turn".to_string(),
+            ],
             None,
             Some(5000),
             "call-first",
         )?,
         create_final_assistant_message_sse_response("done first")?,
-        create_shell_command_sse_response(
-            vec!["echo".to_string(), "second".to_string(), "turn".to_string()],
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo second turn".to_string(),
+            ],
             None,
             Some(5000),
             "call-second",
@@ -520,7 +370,7 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
     )
     .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(start_resp)?;
 
     // first turn with workspace-write sandbox and first_cwd
     let first_turn = mcp
@@ -532,7 +382,7 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             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.try_into()?],
+                writable_roots: vec![first_cwd.clone()],
                 network_access: false,
                 exclude_tmpdir_env_var: false,
                 exclude_slash_tmp: false,
@@ -540,7 +390,6 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             model: Some("mock-model".to_string()),
             effort: Some(ReasoningEffort::Medium),
             summary: Some(ReasoningSummary::Auto),
-            output_schema: None,
         })
         .await?;
     timeout(
@@ -567,7 +416,6 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
             model: Some("mock-model".to_string()),
             effort: Some(ReasoningEffort::Medium),
             summary: Some(ReasoningSummary::Auto),
-            output_schema: None,
         })
         .await?;
     timeout(
@@ -576,482 +424,33 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
     )
     .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);
-            }
-        }
-    })
+    let exec_begin_notification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/exec_command_begin"),
+    )
     .await??;
-    let ThreadItem::CommandExecution {
-        cwd,
-        command,
-        status,
-        ..
-    } = command_exec_item
-    else {
-        unreachable!("loop ensures we break on command execution items");
+    let params = exec_begin_notification
+        .params
+        .clone()
+        .expect("exec_command_begin params");
+    let event: Event = serde_json::from_value(params).expect("deserialize exec begin event");
+    let exec_begin = match event.msg {
+        EventMsg::ExecCommandBegin(exec_begin) => exec_begin,
+        other => panic!("expected ExecCommandBegin event, got {other:?}"),
     };
-    assert_eq!(cwd, second_cwd);
-    let expected_command = format_with_current_shell_display("echo second turn");
-    assert_eq!(command, expected_command);
-    assert_eq!(status, CommandExecutionStatus::InProgress);
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn turn_start_file_change_approval_v2() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let tmp = TempDir::new()?;
-    let codex_home = tmp.path().join("codex_home");
-    std::fs::create_dir(&codex_home)?;
-    let workspace = tmp.path().join("workspace");
-    std::fs::create_dir(&workspace)?;
-
-    let patch = r#"*** Begin Patch
-*** Add File: README.md
-+new line
-*** End Patch
-"#;
-    let responses = vec![
-        create_apply_patch_sse_response(patch, "patch-call")?,
-        create_final_assistant_message_sse_response("patch applied")?,
-    ];
-    let server = create_mock_chat_completions_server(responses).await;
-    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
-
-    let mut mcp = McpProcess::new(&codex_home).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let start_req = mcp
-        .send_thread_start_request(ThreadStartParams {
-            model: Some("mock-model".to_string()),
-            cwd: Some(workspace.to_string_lossy().into_owned()),
-            ..Default::default()
-        })
-        .await?;
-    let start_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(start_req)),
-    )
-    .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
-
-    let turn_req = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "apply patch".into(),
-            }],
-            cwd: Some(workspace.clone()),
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
-    )
-    .await??;
-    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
-
-    let started_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let started_notif = mcp
-                .read_stream_until_notification_message("item/started")
-                .await?;
-            let started: ItemStartedNotification =
-                serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
-            if let ThreadItem::FileChange { .. } = started.item {
-                return Ok::<ThreadItem, anyhow::Error>(started.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::FileChange {
-        ref id,
-        status,
-        ref changes,
-    } = started_file_change
-    else {
-        unreachable!("loop ensures we break on file change items");
-    };
-    assert_eq!(id, "patch-call");
-    assert_eq!(status, PatchApplyStatus::InProgress);
-    let started_changes = changes.clone();
-
-    let server_req = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_request_message(),
-    )
-    .await??;
-    let ServerRequest::FileChangeRequestApproval { request_id, params } = server_req else {
-        panic!("expected FileChangeRequestApproval request")
-    };
-    assert_eq!(params.item_id, "patch-call");
-    assert_eq!(params.thread_id, thread.id);
-    assert_eq!(params.turn_id, turn.id);
-    let expected_readme_path = workspace.join("README.md");
-    let expected_readme_path = expected_readme_path.to_string_lossy().into_owned();
-    pretty_assertions::assert_eq!(
-        started_changes,
-        vec![codex_app_server_protocol::FileUpdateChange {
-            path: expected_readme_path.clone(),
-            kind: PatchChangeKind::Add,
-            diff: "new line\n".to_string(),
-        }]
-    );
-
-    mcp.send_response(
-        request_id,
-        serde_json::to_value(FileChangeRequestApprovalResponse {
-            decision: ApprovalDecision::Accept,
-        })?,
-    )
-    .await?;
-
-    let output_delta_notif = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("item/fileChange/outputDelta"),
-    )
-    .await??;
-    let output_delta: FileChangeOutputDeltaNotification = serde_json::from_value(
-        output_delta_notif
-            .params
-            .clone()
-            .expect("item/fileChange/outputDelta params"),
-    )?;
-    assert_eq!(output_delta.thread_id, thread.id);
-    assert_eq!(output_delta.turn_id, turn.id);
-    assert_eq!(output_delta.item_id, "patch-call");
-    assert!(
-        !output_delta.delta.is_empty(),
-        "expected delta to be non-empty, got: {}",
-        output_delta.delta
-    );
-
-    let completed_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let completed_notif = mcp
-                .read_stream_until_notification_message("item/completed")
-                .await?;
-            let completed: ItemCompletedNotification = serde_json::from_value(
-                completed_notif
-                    .params
-                    .clone()
-                    .expect("item/completed params"),
-            )?;
-            if let ThreadItem::FileChange { .. } = completed.item {
-                return Ok::<ThreadItem, anyhow::Error>(completed.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::FileChange { ref id, status, .. } = completed_file_change else {
-        unreachable!("loop ensures we break on file change items");
-    };
-    assert_eq!(id, "patch-call");
-    assert_eq!(status, PatchApplyStatus::Completed);
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-
-    let readme_contents = std::fs::read_to_string(expected_readme_path)?;
-    assert_eq!(readme_contents, "new line\n");
-
-    Ok(())
-}
-
-#[tokio::test]
-async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let tmp = TempDir::new()?;
-    let codex_home = tmp.path().join("codex_home");
-    std::fs::create_dir(&codex_home)?;
-    let workspace = tmp.path().join("workspace");
-    std::fs::create_dir(&workspace)?;
-
-    let patch = r#"*** Begin Patch
-*** Add File: README.md
-+new line
-*** End Patch
-"#;
-    let responses = vec![
-        create_apply_patch_sse_response(patch, "patch-call")?,
-        create_final_assistant_message_sse_response("patch declined")?,
-    ];
-    let server = create_mock_chat_completions_server(responses).await;
-    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
-
-    let mut mcp = McpProcess::new(&codex_home).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let start_req = mcp
-        .send_thread_start_request(ThreadStartParams {
-            model: Some("mock-model".to_string()),
-            cwd: Some(workspace.to_string_lossy().into_owned()),
-            ..Default::default()
-        })
-        .await?;
-    let start_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(start_req)),
-    )
-    .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
-
-    let turn_req = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "apply patch".into(),
-            }],
-            cwd: Some(workspace.clone()),
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
-    )
-    .await??;
-    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
-
-    let started_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let started_notif = mcp
-                .read_stream_until_notification_message("item/started")
-                .await?;
-            let started: ItemStartedNotification =
-                serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
-            if let ThreadItem::FileChange { .. } = started.item {
-                return Ok::<ThreadItem, anyhow::Error>(started.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::FileChange {
-        ref id,
-        status,
-        ref changes,
-    } = started_file_change
-    else {
-        unreachable!("loop ensures we break on file change items");
-    };
-    assert_eq!(id, "patch-call");
-    assert_eq!(status, PatchApplyStatus::InProgress);
-    let started_changes = changes.clone();
-
-    let server_req = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_request_message(),
-    )
-    .await??;
-    let ServerRequest::FileChangeRequestApproval { request_id, params } = server_req else {
-        panic!("expected FileChangeRequestApproval request")
-    };
-    assert_eq!(params.item_id, "patch-call");
-    assert_eq!(params.thread_id, thread.id);
-    assert_eq!(params.turn_id, turn.id);
-    let expected_readme_path = workspace.join("README.md");
-    let expected_readme_path_str = expected_readme_path.to_string_lossy().into_owned();
-    pretty_assertions::assert_eq!(
-        started_changes,
-        vec![codex_app_server_protocol::FileUpdateChange {
-            path: expected_readme_path_str.clone(),
-            kind: PatchChangeKind::Add,
-            diff: "new line\n".to_string(),
-        }]
-    );
-
-    mcp.send_response(
-        request_id,
-        serde_json::to_value(FileChangeRequestApprovalResponse {
-            decision: ApprovalDecision::Decline,
-        })?,
-    )
-    .await?;
-
-    let completed_file_change = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let completed_notif = mcp
-                .read_stream_until_notification_message("item/completed")
-                .await?;
-            let completed: ItemCompletedNotification = serde_json::from_value(
-                completed_notif
-                    .params
-                    .clone()
-                    .expect("item/completed params"),
-            )?;
-            if let ThreadItem::FileChange { .. } = completed.item {
-                return Ok::<ThreadItem, anyhow::Error>(completed.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::FileChange { ref id, status, .. } = completed_file_change else {
-        unreachable!("loop ensures we break on file change items");
-    };
-    assert_eq!(id, "patch-call");
-    assert_eq!(status, PatchApplyStatus::Declined);
-
-    timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("codex/event/task_complete"),
-    )
-    .await??;
-
-    assert!(
-        !expected_readme_path.exists(),
-        "declined patch should not be applied"
-    );
-
-    Ok(())
-}
-
-#[tokio::test]
-#[cfg_attr(windows, ignore = "process id reporting differs on Windows")]
-async fn command_execution_notifications_include_process_id() -> Result<()> {
-    skip_if_no_network!(Ok(()));
-
-    let responses = vec![
-        create_exec_command_sse_response("uexec-1")?,
-        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(), "never")?;
-    let config_toml = codex_home.path().join("config.toml");
-    let mut config_contents = std::fs::read_to_string(&config_toml)?;
-    config_contents.push_str(
-        r#"
-[features]
-unified_exec = true
-"#,
-    );
-    std::fs::write(&config_toml, config_contents)?;
-
-    let mut mcp = McpProcess::new(codex_home.path()).await?;
-    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
-
-    let start_id = mcp
-        .send_thread_start_request(ThreadStartParams {
-            model: Some("mock-model".to_string()),
-            ..Default::default()
-        })
-        .await?;
-    let start_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
-    )
-    .await??;
-    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
-
-    let turn_id = mcp
-        .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id.clone(),
-            input: vec![V2UserInput::Text {
-                text: "run a command".to_string(),
-            }],
-            ..Default::default()
-        })
-        .await?;
-    let turn_resp: JSONRPCResponse = timeout(
-        DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
-    )
-    .await??;
-    let TurnStartResponse { turn: _turn } = to_response::<TurnStartResponse>(turn_resp)?;
-
-    let started_command = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let notif = mcp
-                .read_stream_until_notification_message("item/started")
-                .await?;
-            let started: ItemStartedNotification = serde_json::from_value(
-                notif
-                    .params
-                    .clone()
-                    .expect("item/started should include params"),
-            )?;
-            if let ThreadItem::CommandExecution { .. } = started.item {
-                return Ok::<ThreadItem, anyhow::Error>(started.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::CommandExecution {
-        id,
-        process_id: started_process_id,
-        status,
-        ..
-    } = started_command
-    else {
-        unreachable!("loop ensures we break on command execution items");
-    };
-    assert_eq!(id, "uexec-1");
-    assert_eq!(status, CommandExecutionStatus::InProgress);
-    let started_process_id = started_process_id.expect("process id should be present");
-
-    let completed_command = timeout(DEFAULT_READ_TIMEOUT, async {
-        loop {
-            let notif = mcp
-                .read_stream_until_notification_message("item/completed")
-                .await?;
-            let completed: ItemCompletedNotification = serde_json::from_value(
-                notif
-                    .params
-                    .clone()
-                    .expect("item/completed should include params"),
-            )?;
-            if let ThreadItem::CommandExecution { .. } = completed.item {
-                return Ok::<ThreadItem, anyhow::Error>(completed.item);
-            }
-        }
-    })
-    .await??;
-    let ThreadItem::CommandExecution {
-        id: completed_id,
-        process_id: completed_process_id,
-        status: completed_status,
-        exit_code,
-        ..
-    } = completed_command
-    else {
-        unreachable!("loop ensures we break on command execution items");
-    };
-    assert_eq!(completed_id, "uexec-1");
-    assert_eq!(completed_status, CommandExecutionStatus::Completed);
-    assert_eq!(exit_code, Some(0));
+    assert_eq!(exec_begin.cwd, second_cwd);
     assert_eq!(
-        completed_process_id.as_deref(),
-        Some(started_process_id.as_str())
+        exec_begin.command,
+        vec![
+            "bash".to_string(),
+            "-lc".to_string(),
+            "echo second turn".to_string()
+        ]
     );
 
     timeout(
         DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_notification_message("turn/completed"),
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
     )
     .await??;
 

codex-rs/apply-patch/Cargo.toml

@@ -1,8 +1,7 @@
 [package]
+edition = "2024"
 name = "codex-apply-patch"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
+version = { workspace = true }
 
 [lib]
 name = "codex_apply_patch"
@@ -25,6 +24,5 @@ tree-sitter-bash = { workspace = true }
 [dev-dependencies]
 assert_cmd = { workspace = true }
 assert_matches = { workspace = true }
-codex-utils-cargo-bin = { workspace = true }
 pretty_assertions = { workspace = true }
 tempfile = { workspace = true }

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

@@ -1,813 +0,0 @@
-use std::collections::HashMap;
-use std::path::Path;
-use std::sync::LazyLock;
-
-use tree_sitter::Parser;
-use tree_sitter::Query;
-use tree_sitter::QueryCursor;
-use tree_sitter::StreamingIterator;
-use tree_sitter_bash::LANGUAGE as BASH;
-
-use crate::ApplyPatchAction;
-use crate::ApplyPatchArgs;
-use crate::ApplyPatchError;
-use crate::ApplyPatchFileChange;
-use crate::ApplyPatchFileUpdate;
-use crate::IoError;
-use crate::MaybeApplyPatchVerified;
-use crate::parser::Hunk;
-use crate::parser::ParseError;
-use crate::parser::parse_patch;
-use crate::unified_diff_from_chunks;
-use std::str::Utf8Error;
-use tree_sitter::LanguageError;
-
-const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-enum ApplyPatchShell {
-    Unix,
-    PowerShell,
-    Cmd,
-}
-
-#[derive(Debug, PartialEq)]
-pub enum MaybeApplyPatch {
-    Body(ApplyPatchArgs),
-    ShellParseError(ExtractHeredocError),
-    PatchParseError(ParseError),
-    NotApplyPatch,
-}
-
-#[derive(Debug, PartialEq)]
-pub enum ExtractHeredocError {
-    CommandDidNotStartWithApplyPatch,
-    FailedToLoadBashGrammar(LanguageError),
-    HeredocNotUtf8(Utf8Error),
-    FailedToParsePatchIntoAst,
-    FailedToFindHeredocBody,
-}
-
-fn classify_shell_name(shell: &str) -> Option<String> {
-    std::path::Path::new(shell)
-        .file_stem()
-        .and_then(|name| name.to_str())
-        .map(str::to_ascii_lowercase)
-}
-
-fn classify_shell(shell: &str, flag: &str) -> Option<ApplyPatchShell> {
-    classify_shell_name(shell).and_then(|name| match name.as_str() {
-        "bash" | "zsh" | "sh" if matches!(flag, "-lc" | "-c") => Some(ApplyPatchShell::Unix),
-        "pwsh" | "powershell" if flag.eq_ignore_ascii_case("-command") => {
-            Some(ApplyPatchShell::PowerShell)
-        }
-        "cmd" if flag.eq_ignore_ascii_case("/c") => Some(ApplyPatchShell::Cmd),
-        _ => None,
-    })
-}
-
-fn can_skip_flag(shell: &str, flag: &str) -> bool {
-    classify_shell_name(shell).is_some_and(|name| {
-        matches!(name.as_str(), "pwsh" | "powershell") && flag.eq_ignore_ascii_case("-noprofile")
-    })
-}
-
-fn parse_shell_script(argv: &[String]) -> Option<(ApplyPatchShell, &str)> {
-    match argv {
-        [shell, flag, script] => classify_shell(shell, flag).map(|shell_type| {
-            let script = script.as_str();
-            (shell_type, script)
-        }),
-        [shell, skip_flag, flag, script] if can_skip_flag(shell, skip_flag) => {
-            classify_shell(shell, flag).map(|shell_type| {
-                let script = script.as_str();
-                (shell_type, script)
-            })
-        }
-        _ => None,
-    }
-}
-
-fn extract_apply_patch_from_shell(
-    shell: ApplyPatchShell,
-    script: &str,
-) -> std::result::Result<(String, Option<String>), ExtractHeredocError> {
-    match shell {
-        ApplyPatchShell::Unix | ApplyPatchShell::PowerShell | ApplyPatchShell::Cmd => {
-            extract_apply_patch_from_bash(script)
-        }
-    }
-}
-
-// TODO: make private once we remove tests in lib.rs
-pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
-    match argv {
-        // Direct invocation: apply_patch <patch>
-        [cmd, body] if APPLY_PATCH_COMMANDS.contains(&cmd.as_str()) => match parse_patch(body) {
-            Ok(source) => MaybeApplyPatch::Body(source),
-            Err(e) => MaybeApplyPatch::PatchParseError(e),
-        },
-        // Shell heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
-        _ => match parse_shell_script(argv) {
-            Some((shell, script)) => match extract_apply_patch_from_shell(shell, script) {
-                Ok((body, workdir)) => match parse_patch(&body) {
-                    Ok(mut source) => {
-                        source.workdir = workdir;
-                        MaybeApplyPatch::Body(source)
-                    }
-                    Err(e) => MaybeApplyPatch::PatchParseError(e),
-                },
-                Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch) => {
-                    MaybeApplyPatch::NotApplyPatch
-                }
-                Err(e) => MaybeApplyPatch::ShellParseError(e),
-            },
-            None => MaybeApplyPatch::NotApplyPatch,
-        },
-    }
-}
-
-/// cwd must be an absolute path so that we can resolve relative paths in the
-/// patch.
-pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApplyPatchVerified {
-    // Detect a raw patch body passed directly as the command or as the body of a shell
-    // script. In these cases, report an explicit error rather than applying the patch.
-    if let [body] = argv
-        && parse_patch(body).is_ok()
-    {
-        return MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation);
-    }
-    if let Some((_, script)) = parse_shell_script(argv)
-        && parse_patch(script).is_ok()
-    {
-        return MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation);
-    }
-
-    match maybe_parse_apply_patch(argv) {
-        MaybeApplyPatch::Body(ApplyPatchArgs {
-            patch,
-            hunks,
-            workdir,
-        }) => {
-            let effective_cwd = workdir
-                .as_ref()
-                .map(|dir| {
-                    let path = Path::new(dir);
-                    if path.is_absolute() {
-                        path.to_path_buf()
-                    } else {
-                        cwd.join(path)
-                    }
-                })
-                .unwrap_or_else(|| cwd.to_path_buf());
-            let mut changes = HashMap::new();
-            for hunk in hunks {
-                let path = hunk.resolve_path(&effective_cwd);
-                match hunk {
-                    Hunk::AddFile { contents, .. } => {
-                        changes.insert(path, ApplyPatchFileChange::Add { content: contents });
-                    }
-                    Hunk::DeleteFile { .. } => {
-                        let content = match std::fs::read_to_string(&path) {
-                            Ok(content) => content,
-                            Err(e) => {
-                                return MaybeApplyPatchVerified::CorrectnessError(
-                                    ApplyPatchError::IoError(IoError {
-                                        context: format!("Failed to read {}", path.display()),
-                                        source: e,
-                                    }),
-                                );
-                            }
-                        };
-                        changes.insert(path, ApplyPatchFileChange::Delete { content });
-                    }
-                    Hunk::UpdateFile {
-                        move_path, chunks, ..
-                    } => {
-                        let ApplyPatchFileUpdate {
-                            unified_diff,
-                            content: contents,
-                        } = match unified_diff_from_chunks(&path, &chunks) {
-                            Ok(diff) => diff,
-                            Err(e) => {
-                                return MaybeApplyPatchVerified::CorrectnessError(e);
-                            }
-                        };
-                        changes.insert(
-                            path,
-                            ApplyPatchFileChange::Update {
-                                unified_diff,
-                                move_path: move_path.map(|p| effective_cwd.join(p)),
-                                new_content: contents,
-                            },
-                        );
-                    }
-                }
-            }
-            MaybeApplyPatchVerified::Body(ApplyPatchAction {
-                changes,
-                patch,
-                cwd: effective_cwd,
-            })
-        }
-        MaybeApplyPatch::ShellParseError(e) => MaybeApplyPatchVerified::ShellParseError(e),
-        MaybeApplyPatch::PatchParseError(e) => MaybeApplyPatchVerified::CorrectnessError(e.into()),
-        MaybeApplyPatch::NotApplyPatch => MaybeApplyPatchVerified::NotApplyPatch,
-    }
-}
-
-/// Extract the heredoc body (and optional `cd` workdir) from a `bash -lc` script
-/// that invokes the apply_patch tool using a heredoc.
-///
-/// Supported top‑level forms (must be the only top‑level statement):
-/// - `apply_patch <<'EOF'\n...\nEOF`
-/// - `cd <path> && apply_patch <<'EOF'\n...\nEOF`
-///
-/// Notes about matching:
-/// - Parsed with Tree‑sitter Bash and a strict query that uses anchors so the
-///   heredoc‑redirected statement is the only top‑level statement.
-/// - The connector between `cd` and `apply_patch` must be `&&` (not `|` or `||`).
-/// - Exactly one positional `word` argument is allowed for `cd` (no flags, no quoted
-///   strings, no second argument).
-/// - The apply command is validated in‑query via `#any-of?` to allow `apply_patch`
-///   or `applypatch`.
-/// - Preceding or trailing commands (e.g., `echo ...;` or `... && echo done`) do not match.
-///
-/// Returns `(heredoc_body, Some(path))` when the `cd` variant matches, or
-/// `(heredoc_body, None)` for the direct form. Errors are returned if the script
-/// cannot be parsed or does not match the allowed patterns.
-fn extract_apply_patch_from_bash(
-    src: &str,
-) -> std::result::Result<(String, Option<String>), ExtractHeredocError> {
-    // This function uses a Tree-sitter query to recognize one of two
-    // whole-script forms, each expressed as a single top-level statement:
-    //
-    // 1. apply_patch <<'EOF'\n...\nEOF
-    // 2. cd <path> && apply_patch <<'EOF'\n...\nEOF
-    //
-    // Key ideas when reading the query:
-    // - dots (`.`) between named nodes enforces adjacency among named children and
-    //   anchor to the start/end of the expression.
-    // - we match a single redirected_statement directly under program with leading
-    //   and trailing anchors (`.`). This ensures it is the only top-level statement
-    //   (so prefixes like `echo ...;` or suffixes like `... && echo done` do not match).
-    //
-    // Overall, we want to be conservative and only match the intended forms, as other
-    // forms are likely to be model errors, or incorrectly interpreted by later code.
-    //
-    // If you're editing this query, it's helpful to start by creating a debugging binary
-    // which will let you see the AST of an arbitrary bash script passed in, and optionally
-    // also run an arbitrary query against the AST. This is useful for understanding
-    // how tree-sitter parses the script and whether the query syntax is correct. Be sure
-    // to test both positive and negative cases.
-    static APPLY_PATCH_QUERY: LazyLock<Query> = LazyLock::new(|| {
-        let language = BASH.into();
-        #[expect(clippy::expect_used)]
-        Query::new(
-            &language,
-            r#"
-            (
-              program
-                . (redirected_statement
-                    body: (command
-                            name: (command_name (word) @apply_name) .)
-                    (#any-of? @apply_name "apply_patch" "applypatch")
-                    redirect: (heredoc_redirect
-                                . (heredoc_start)
-                                . (heredoc_body) @heredoc
-                                . (heredoc_end)
-                                .))
-                .)
-
-            (
-              program
-                . (redirected_statement
-                    body: (list
-                            . (command
-                                name: (command_name (word) @cd_name) .
-                                argument: [
-                                  (word) @cd_path
-                                  (string (string_content) @cd_path)
-                                  (raw_string) @cd_raw_string
-                                ] .)
-                            "&&"
-                            . (command
-                                name: (command_name (word) @apply_name))
-                            .)
-                    (#eq? @cd_name "cd")
-                    (#any-of? @apply_name "apply_patch" "applypatch")
-                    redirect: (heredoc_redirect
-                                . (heredoc_start)
-                                . (heredoc_body) @heredoc
-                                . (heredoc_end)
-                                .))
-                .)
-            "#,
-        )
-        .expect("valid bash query")
-    });
-
-    let lang = BASH.into();
-    let mut parser = Parser::new();
-    parser
-        .set_language(&lang)
-        .map_err(ExtractHeredocError::FailedToLoadBashGrammar)?;
-    let tree = parser
-        .parse(src, None)
-        .ok_or(ExtractHeredocError::FailedToParsePatchIntoAst)?;
-
-    let bytes = src.as_bytes();
-    let root = tree.root_node();
-
-    let mut cursor = QueryCursor::new();
-    let mut matches = cursor.matches(&APPLY_PATCH_QUERY, root, bytes);
-    while let Some(m) = matches.next() {
-        let mut heredoc_text: Option<String> = None;
-        let mut cd_path: Option<String> = None;
-
-        for capture in m.captures.iter() {
-            let name = APPLY_PATCH_QUERY.capture_names()[capture.index as usize];
-            match name {
-                "heredoc" => {
-                    let text = capture
-                        .node
-                        .utf8_text(bytes)
-                        .map_err(ExtractHeredocError::HeredocNotUtf8)?
-                        .trim_end_matches('\n')
-                        .to_string();
-                    heredoc_text = Some(text);
-                }
-                "cd_path" => {
-                    let text = capture
-                        .node
-                        .utf8_text(bytes)
-                        .map_err(ExtractHeredocError::HeredocNotUtf8)?
-                        .to_string();
-                    cd_path = Some(text);
-                }
-                "cd_raw_string" => {
-                    let raw = capture
-                        .node
-                        .utf8_text(bytes)
-                        .map_err(ExtractHeredocError::HeredocNotUtf8)?;
-                    let trimmed = raw
-                        .strip_prefix('\'')
-                        .and_then(|s| s.strip_suffix('\''))
-                        .unwrap_or(raw);
-                    cd_path = Some(trimmed.to_string());
-                }
-                _ => {}
-            }
-        }
-
-        if let Some(heredoc) = heredoc_text {
-            return Ok((heredoc, cd_path));
-        }
-    }
-
-    Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch)
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use assert_matches::assert_matches;
-    use pretty_assertions::assert_eq;
-    use std::fs;
-    use std::path::PathBuf;
-    use std::string::ToString;
-    use tempfile::tempdir;
-
-    /// Helper to construct a patch with the given body.
-    fn wrap_patch(body: &str) -> String {
-        format!("*** Begin Patch\n{body}\n*** End Patch")
-    }
-
-    fn strs_to_strings(strs: &[&str]) -> Vec<String> {
-        strs.iter().map(ToString::to_string).collect()
-    }
-
-    // Test helpers to reduce repetition when building bash -lc heredoc scripts
-    fn args_bash(script: &str) -> Vec<String> {
-        strs_to_strings(&["bash", "-lc", script])
-    }
-
-    fn args_powershell(script: &str) -> Vec<String> {
-        strs_to_strings(&["powershell.exe", "-Command", script])
-    }
-
-    fn args_powershell_no_profile(script: &str) -> Vec<String> {
-        strs_to_strings(&["powershell.exe", "-NoProfile", "-Command", script])
-    }
-
-    fn args_pwsh(script: &str) -> Vec<String> {
-        strs_to_strings(&["pwsh", "-NoProfile", "-Command", script])
-    }
-
-    fn args_cmd(script: &str) -> Vec<String> {
-        strs_to_strings(&["cmd.exe", "/c", script])
-    }
-
-    fn heredoc_script(prefix: &str) -> String {
-        format!(
-            "{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH"
-        )
-    }
-
-    fn heredoc_script_ps(prefix: &str, suffix: &str) -> String {
-        format!(
-            "{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH{suffix}"
-        )
-    }
-
-    fn expected_single_add() -> Vec<Hunk> {
-        vec![Hunk::AddFile {
-            path: PathBuf::from("foo"),
-            contents: "hi\n".to_string(),
-        }]
-    }
-
-    fn assert_match_args(args: Vec<String>, expected_workdir: Option<&str>) {
-        match maybe_parse_apply_patch(&args) {
-            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
-                assert_eq!(workdir.as_deref(), expected_workdir);
-                assert_eq!(hunks, expected_single_add());
-            }
-            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
-        }
-    }
-
-    fn assert_match(script: &str, expected_workdir: Option<&str>) {
-        let args = args_bash(script);
-        assert_match_args(args, expected_workdir);
-    }
-
-    fn assert_not_match(script: &str) {
-        let args = args_bash(script);
-        assert_matches!(
-            maybe_parse_apply_patch(&args),
-            MaybeApplyPatch::NotApplyPatch
-        );
-    }
-
-    #[test]
-    fn test_implicit_patch_single_arg_is_error() {
-        let patch = "*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch".to_string();
-        let args = vec![patch];
-        let dir = tempdir().unwrap();
-        assert_matches!(
-            maybe_parse_apply_patch_verified(&args, dir.path()),
-            MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation)
-        );
-    }
-
-    #[test]
-    fn test_implicit_patch_bash_script_is_error() {
-        let script = "*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch";
-        let args = args_bash(script);
-        let dir = tempdir().unwrap();
-        assert_matches!(
-            maybe_parse_apply_patch_verified(&args, dir.path()),
-            MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation)
-        );
-    }
-
-    #[test]
-    fn test_literal() {
-        let args = strs_to_strings(&[
-            "apply_patch",
-            r#"*** Begin Patch
-*** Add File: foo
-+hi
-*** End Patch
-"#,
-        ]);
-
-        match maybe_parse_apply_patch(&args) {
-            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, .. }) => {
-                assert_eq!(
-                    hunks,
-                    vec![Hunk::AddFile {
-                        path: PathBuf::from("foo"),
-                        contents: "hi\n".to_string()
-                    }]
-                );
-            }
-            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
-        }
-    }
-
-    #[test]
-    fn test_literal_applypatch() {
-        let args = strs_to_strings(&[
-            "applypatch",
-            r#"*** Begin Patch
-*** Add File: foo
-+hi
-*** End Patch
-"#,
-        ]);
-
-        match maybe_parse_apply_patch(&args) {
-            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, .. }) => {
-                assert_eq!(
-                    hunks,
-                    vec![Hunk::AddFile {
-                        path: PathBuf::from("foo"),
-                        contents: "hi\n".to_string()
-                    }]
-                );
-            }
-            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
-        }
-    }
-
-    #[test]
-    fn test_heredoc() {
-        assert_match(&heredoc_script(""), None);
-    }
-
-    #[test]
-    fn test_heredoc_non_login_shell() {
-        let script = heredoc_script("");
-        let args = strs_to_strings(&["bash", "-c", &script]);
-        assert_match_args(args, None);
-    }
-
-    #[test]
-    fn test_heredoc_applypatch() {
-        let args = strs_to_strings(&[
-            "bash",
-            "-lc",
-            r#"applypatch <<'PATCH'
-*** Begin Patch
-*** Add File: foo
-+hi
-*** End Patch
-PATCH"#,
-        ]);
-
-        match maybe_parse_apply_patch(&args) {
-            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
-                assert_eq!(workdir, None);
-                assert_eq!(
-                    hunks,
-                    vec![Hunk::AddFile {
-                        path: PathBuf::from("foo"),
-                        contents: "hi\n".to_string()
-                    }]
-                );
-            }
-            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
-        }
-    }
-
-    #[test]
-    fn test_powershell_heredoc() {
-        let script = heredoc_script("");
-        assert_match_args(args_powershell(&script), None);
-    }
-    #[test]
-    fn test_powershell_heredoc_no_profile() {
-        let script = heredoc_script("");
-        assert_match_args(args_powershell_no_profile(&script), None);
-    }
-    #[test]
-    fn test_pwsh_heredoc() {
-        let script = heredoc_script("");
-        assert_match_args(args_pwsh(&script), None);
-    }
-
-    #[test]
-    fn test_cmd_heredoc_with_cd() {
-        let script = heredoc_script("cd foo && ");
-        assert_match_args(args_cmd(&script), Some("foo"));
-    }
-
-    #[test]
-    fn test_heredoc_with_leading_cd() {
-        assert_match(&heredoc_script("cd foo && "), Some("foo"));
-    }
-
-    #[test]
-    fn test_cd_with_semicolon_is_ignored() {
-        assert_not_match(&heredoc_script("cd foo; "));
-    }
-
-    #[test]
-    fn test_cd_or_apply_patch_is_ignored() {
-        assert_not_match(&heredoc_script("cd bar || "));
-    }
-
-    #[test]
-    fn test_cd_pipe_apply_patch_is_ignored() {
-        assert_not_match(&heredoc_script("cd bar | "));
-    }
-
-    #[test]
-    fn test_cd_single_quoted_path_with_spaces() {
-        assert_match(&heredoc_script("cd 'foo bar' && "), Some("foo bar"));
-    }
-
-    #[test]
-    fn test_cd_double_quoted_path_with_spaces() {
-        assert_match(&heredoc_script("cd \"foo bar\" && "), Some("foo bar"));
-    }
-
-    #[test]
-    fn test_echo_and_apply_patch_is_ignored() {
-        assert_not_match(&heredoc_script("echo foo && "));
-    }
-
-    #[test]
-    fn test_apply_patch_with_arg_is_ignored() {
-        let script = "apply_patch foo <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH";
-        assert_not_match(script);
-    }
-
-    #[test]
-    fn test_double_cd_then_apply_patch_is_ignored() {
-        assert_not_match(&heredoc_script("cd foo && cd bar && "));
-    }
-
-    #[test]
-    fn test_cd_two_args_is_ignored() {
-        assert_not_match(&heredoc_script("cd foo bar && "));
-    }
-
-    #[test]
-    fn test_cd_then_apply_patch_then_extra_is_ignored() {
-        let script = heredoc_script_ps("cd bar && ", " && echo done");
-        assert_not_match(&script);
-    }
-
-    #[test]
-    fn test_echo_then_cd_and_apply_patch_is_ignored() {
-        // Ensure preceding commands before the `cd && apply_patch <<...` sequence do not match.
-        assert_not_match(&heredoc_script("echo foo; cd bar && "));
-    }
-
-    #[test]
-    fn test_unified_diff_last_line_replacement() {
-        // Replace the very last line of the file.
-        let dir = tempdir().unwrap();
-        let path = dir.path().join("last.txt");
-        fs::write(&path, "foo\nbar\nbaz\n").unwrap();
-
-        let patch = wrap_patch(&format!(
-            r#"*** Update File: {}
-@@
- foo
- bar
--baz
-+BAZ
-"#,
-            path.display()
-        ));
-
-        let patch = parse_patch(&patch).unwrap();
-        let chunks = match patch.hunks.as_slice() {
-            [Hunk::UpdateFile { chunks, .. }] => chunks,
-            _ => panic!("Expected a single UpdateFile hunk"),
-        };
-
-        let diff = unified_diff_from_chunks(&path, chunks).unwrap();
-        let expected_diff = r#"@@ -2,2 +2,2 @@
- bar
--baz
-+BAZ
-"#;
-        let expected = ApplyPatchFileUpdate {
-            unified_diff: expected_diff.to_string(),
-            content: "foo\nbar\nBAZ\n".to_string(),
-        };
-        assert_eq!(expected, diff);
-    }
-
-    #[test]
-    fn test_unified_diff_insert_at_eof() {
-        // Insert a new line at end‑of‑file.
-        let dir = tempdir().unwrap();
-        let path = dir.path().join("insert.txt");
-        fs::write(&path, "foo\nbar\nbaz\n").unwrap();
-
-        let patch = wrap_patch(&format!(
-            r#"*** Update File: {}
-@@
-+quux
-*** End of File
-"#,
-            path.display()
-        ));
-
-        let patch = parse_patch(&patch).unwrap();
-        let chunks = match patch.hunks.as_slice() {
-            [Hunk::UpdateFile { chunks, .. }] => chunks,
-            _ => panic!("Expected a single UpdateFile hunk"),
-        };
-
-        let diff = unified_diff_from_chunks(&path, chunks).unwrap();
-        let expected_diff = r#"@@ -3 +3,2 @@
- baz
-+quux
-"#;
-        let expected = ApplyPatchFileUpdate {
-            unified_diff: expected_diff.to_string(),
-            content: "foo\nbar\nbaz\nquux\n".to_string(),
-        };
-        assert_eq!(expected, diff);
-    }
-
-    #[test]
-    fn test_apply_patch_should_resolve_absolute_paths_in_cwd() {
-        let session_dir = tempdir().unwrap();
-        let relative_path = "source.txt";
-
-        // Note that we need this file to exist for the patch to be "verified"
-        // and parsed correctly.
-        let session_file_path = session_dir.path().join(relative_path);
-        fs::write(&session_file_path, "session directory content\n").unwrap();
-
-        let argv = vec![
-            "apply_patch".to_string(),
-            r#"*** Begin Patch
-*** Update File: source.txt
-@@
--session directory content
-+updated session directory content
-*** End Patch"#
-                .to_string(),
-        ];
-
-        let result = maybe_parse_apply_patch_verified(&argv, session_dir.path());
-
-        // Verify the patch contents - as otherwise we may have pulled contents
-        // from the wrong file (as we're using relative paths)
-        assert_eq!(
-            result,
-            MaybeApplyPatchVerified::Body(ApplyPatchAction {
-                changes: HashMap::from([(
-                    session_dir.path().join(relative_path),
-                    ApplyPatchFileChange::Update {
-                        unified_diff: r#"@@ -1 +1 @@
--session directory content
-+updated session directory content
-"#
-                        .to_string(),
-                        move_path: None,
-                        new_content: "updated session directory content\n".to_string(),
-                    },
-                )]),
-                patch: argv[1].clone(),
-                cwd: session_dir.path().to_path_buf(),
-            })
-        );
-    }
-
-    #[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:?}"),
-        }
-    }
-}

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

@@ -1,4 +1,3 @@
-mod invocation;
 mod parser;
 mod seek_sequence;
 mod standalone_executable;
@@ -6,6 +5,8 @@ mod standalone_executable;
 use std::collections::HashMap;
 use std::path::Path;
 use std::path::PathBuf;
+use std::str::Utf8Error;
+use std::sync::LazyLock;
 
 use anyhow::Context;
 use anyhow::Result;
@@ -16,15 +17,20 @@ use parser::UpdateFileChunk;
 pub use parser::parse_patch;
 use similar::TextDiff;
 use thiserror::Error;
+use tree_sitter::LanguageError;
+use tree_sitter::Parser;
+use tree_sitter::Query;
+use tree_sitter::QueryCursor;
+use tree_sitter::StreamingIterator;
+use tree_sitter_bash::LANGUAGE as BASH;
 
-pub use invocation::maybe_parse_apply_patch_verified;
 pub use standalone_executable::main;
 
-use crate::invocation::ExtractHeredocError;
-
 /// Detailed instructions for gpt-4.1 on how to use the `apply_patch` tool.
 pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_tool_instructions.md");
 
+const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
+
 #[derive(Debug, Error, PartialEq)]
 pub enum ApplyPatchError {
     #[error(transparent)]
@@ -73,6 +79,14 @@ impl PartialEq for IoError {
     }
 }
 
+#[derive(Debug, PartialEq)]
+pub enum MaybeApplyPatch {
+    Body(ApplyPatchArgs),
+    ShellParseError(ExtractHeredocError),
+    PatchParseError(ParseError),
+    NotApplyPatch,
+}
+
 /// Both the raw PATCH argument to `apply_patch` as well as the PATCH argument
 /// parsed into hunks.
 #[derive(Debug, PartialEq)]
@@ -82,6 +96,33 @@ pub struct ApplyPatchArgs {
     pub workdir: Option<String>,
 }
 
+pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
+    match argv {
+        // Direct invocation: apply_patch <patch>
+        [cmd, body] if APPLY_PATCH_COMMANDS.contains(&cmd.as_str()) => match parse_patch(body) {
+            Ok(source) => MaybeApplyPatch::Body(source),
+            Err(e) => MaybeApplyPatch::PatchParseError(e),
+        },
+        // Bash heredoc form: (optional `cd <path> &&`) apply_patch <<'EOF' ...
+        [bash, flag, script] if bash == "bash" && flag == "-lc" => {
+            match extract_apply_patch_from_bash(script) {
+                Ok((body, workdir)) => match parse_patch(&body) {
+                    Ok(mut source) => {
+                        source.workdir = workdir;
+                        MaybeApplyPatch::Body(source)
+                    }
+                    Err(e) => MaybeApplyPatch::PatchParseError(e),
+                },
+                Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch) => {
+                    MaybeApplyPatch::NotApplyPatch
+                }
+                Err(e) => MaybeApplyPatch::ShellParseError(e),
+            }
+        }
+        _ => MaybeApplyPatch::NotApplyPatch,
+    }
+}
+
 #[derive(Debug, PartialEq)]
 pub enum ApplyPatchFileChange {
     Add {
@@ -170,6 +211,263 @@ impl ApplyPatchAction {
     }
 }
 
+/// cwd must be an absolute path so that we can resolve relative paths in the
+/// patch.
+pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApplyPatchVerified {
+    // Detect a raw patch body passed directly as the command or as the body of a bash -lc
+    // script. In these cases, report an explicit error rather than applying the patch.
+    match argv {
+        [body] => {
+            if parse_patch(body).is_ok() {
+                return MaybeApplyPatchVerified::CorrectnessError(
+                    ApplyPatchError::ImplicitInvocation,
+                );
+            }
+        }
+        [bash, flag, script] if bash == "bash" && flag == "-lc" => {
+            if parse_patch(script).is_ok() {
+                return MaybeApplyPatchVerified::CorrectnessError(
+                    ApplyPatchError::ImplicitInvocation,
+                );
+            }
+        }
+        _ => {}
+    }
+
+    match maybe_parse_apply_patch(argv) {
+        MaybeApplyPatch::Body(ApplyPatchArgs {
+            patch,
+            hunks,
+            workdir,
+        }) => {
+            let effective_cwd = workdir
+                .as_ref()
+                .map(|dir| {
+                    let path = Path::new(dir);
+                    if path.is_absolute() {
+                        path.to_path_buf()
+                    } else {
+                        cwd.join(path)
+                    }
+                })
+                .unwrap_or_else(|| cwd.to_path_buf());
+            let mut changes = HashMap::new();
+            for hunk in hunks {
+                let path = hunk.resolve_path(&effective_cwd);
+                match hunk {
+                    Hunk::AddFile { contents, .. } => {
+                        changes.insert(path, ApplyPatchFileChange::Add { content: contents });
+                    }
+                    Hunk::DeleteFile { .. } => {
+                        let content = match std::fs::read_to_string(&path) {
+                            Ok(content) => content,
+                            Err(e) => {
+                                return MaybeApplyPatchVerified::CorrectnessError(
+                                    ApplyPatchError::IoError(IoError {
+                                        context: format!("Failed to read {}", path.display()),
+                                        source: e,
+                                    }),
+                                );
+                            }
+                        };
+                        changes.insert(path, ApplyPatchFileChange::Delete { content });
+                    }
+                    Hunk::UpdateFile {
+                        move_path, chunks, ..
+                    } => {
+                        let ApplyPatchFileUpdate {
+                            unified_diff,
+                            content: contents,
+                        } = match unified_diff_from_chunks(&path, &chunks) {
+                            Ok(diff) => diff,
+                            Err(e) => {
+                                return MaybeApplyPatchVerified::CorrectnessError(e);
+                            }
+                        };
+                        changes.insert(
+                            path,
+                            ApplyPatchFileChange::Update {
+                                unified_diff,
+                                move_path: move_path.map(|p| cwd.join(p)),
+                                new_content: contents,
+                            },
+                        );
+                    }
+                }
+            }
+            MaybeApplyPatchVerified::Body(ApplyPatchAction {
+                changes,
+                patch,
+                cwd: effective_cwd,
+            })
+        }
+        MaybeApplyPatch::ShellParseError(e) => MaybeApplyPatchVerified::ShellParseError(e),
+        MaybeApplyPatch::PatchParseError(e) => MaybeApplyPatchVerified::CorrectnessError(e.into()),
+        MaybeApplyPatch::NotApplyPatch => MaybeApplyPatchVerified::NotApplyPatch,
+    }
+}
+
+/// Extract the heredoc body (and optional `cd` workdir) from a `bash -lc` script
+/// that invokes the apply_patch tool using a heredoc.
+///
+/// Supported top‑level forms (must be the only top‑level statement):
+/// - `apply_patch <<'EOF'\n...\nEOF`
+/// - `cd <path> && apply_patch <<'EOF'\n...\nEOF`
+///
+/// Notes about matching:
+/// - Parsed with Tree‑sitter Bash and a strict query that uses anchors so the
+///   heredoc‑redirected statement is the only top‑level statement.
+/// - The connector between `cd` and `apply_patch` must be `&&` (not `|` or `||`).
+/// - Exactly one positional `word` argument is allowed for `cd` (no flags, no quoted
+///   strings, no second argument).
+/// - The apply command is validated in‑query via `#any-of?` to allow `apply_patch`
+///   or `applypatch`.
+/// - Preceding or trailing commands (e.g., `echo ...;` or `... && echo done`) do not match.
+///
+/// Returns `(heredoc_body, Some(path))` when the `cd` variant matches, or
+/// `(heredoc_body, None)` for the direct form. Errors are returned if the script
+/// cannot be parsed or does not match the allowed patterns.
+fn extract_apply_patch_from_bash(
+    src: &str,
+) -> std::result::Result<(String, Option<String>), ExtractHeredocError> {
+    // This function uses a Tree-sitter query to recognize one of two
+    // whole-script forms, each expressed as a single top-level statement:
+    //
+    // 1. apply_patch <<'EOF'\n...\nEOF
+    // 2. cd <path> && apply_patch <<'EOF'\n...\nEOF
+    //
+    // Key ideas when reading the query:
+    // - dots (`.`) between named nodes enforces adjacency among named children and
+    //   anchor to the start/end of the expression.
+    // - we match a single redirected_statement directly under program with leading
+    //   and trailing anchors (`.`). This ensures it is the only top-level statement
+    //   (so prefixes like `echo ...;` or suffixes like `... && echo done` do not match).
+    //
+    // Overall, we want to be conservative and only match the intended forms, as other
+    // forms are likely to be model errors, or incorrectly interpreted by later code.
+    //
+    // If you're editing this query, it's helpful to start by creating a debugging binary
+    // which will let you see the AST of an arbitrary bash script passed in, and optionally
+    // also run an arbitrary query against the AST. This is useful for understanding
+    // how tree-sitter parses the script and whether the query syntax is correct. Be sure
+    // to test both positive and negative cases.
+    static APPLY_PATCH_QUERY: LazyLock<Query> = LazyLock::new(|| {
+        let language = BASH.into();
+        #[expect(clippy::expect_used)]
+        Query::new(
+            &language,
+            r#"
+            (
+              program
+                . (redirected_statement
+                    body: (command
+                            name: (command_name (word) @apply_name) .)
+                    (#any-of? @apply_name "apply_patch" "applypatch")
+                    redirect: (heredoc_redirect
+                                . (heredoc_start)
+                                . (heredoc_body) @heredoc
+                                . (heredoc_end)
+                                .))
+                .)
+
+            (
+              program
+                . (redirected_statement
+                    body: (list
+                            . (command
+                                name: (command_name (word) @cd_name) .
+                                argument: [
+                                  (word) @cd_path
+                                  (string (string_content) @cd_path)
+                                  (raw_string) @cd_raw_string
+                                ] .)
+                            "&&"
+                            . (command
+                                name: (command_name (word) @apply_name))
+                            .)
+                    (#eq? @cd_name "cd")
+                    (#any-of? @apply_name "apply_patch" "applypatch")
+                    redirect: (heredoc_redirect
+                                . (heredoc_start)
+                                . (heredoc_body) @heredoc
+                                . (heredoc_end)
+                                .))
+                .)
+            "#,
+        )
+        .expect("valid bash query")
+    });
+
+    let lang = BASH.into();
+    let mut parser = Parser::new();
+    parser
+        .set_language(&lang)
+        .map_err(ExtractHeredocError::FailedToLoadBashGrammar)?;
+    let tree = parser
+        .parse(src, None)
+        .ok_or(ExtractHeredocError::FailedToParsePatchIntoAst)?;
+
+    let bytes = src.as_bytes();
+    let root = tree.root_node();
+
+    let mut cursor = QueryCursor::new();
+    let mut matches = cursor.matches(&APPLY_PATCH_QUERY, root, bytes);
+    while let Some(m) = matches.next() {
+        let mut heredoc_text: Option<String> = None;
+        let mut cd_path: Option<String> = None;
+
+        for capture in m.captures.iter() {
+            let name = APPLY_PATCH_QUERY.capture_names()[capture.index as usize];
+            match name {
+                "heredoc" => {
+                    let text = capture
+                        .node
+                        .utf8_text(bytes)
+                        .map_err(ExtractHeredocError::HeredocNotUtf8)?
+                        .trim_end_matches('\n')
+                        .to_string();
+                    heredoc_text = Some(text);
+                }
+                "cd_path" => {
+                    let text = capture
+                        .node
+                        .utf8_text(bytes)
+                        .map_err(ExtractHeredocError::HeredocNotUtf8)?
+                        .to_string();
+                    cd_path = Some(text);
+                }
+                "cd_raw_string" => {
+                    let raw = capture
+                        .node
+                        .utf8_text(bytes)
+                        .map_err(ExtractHeredocError::HeredocNotUtf8)?;
+                    let trimmed = raw
+                        .strip_prefix('\'')
+                        .and_then(|s| s.strip_suffix('\''))
+                        .unwrap_or(raw);
+                    cd_path = Some(trimmed.to_string());
+                }
+                _ => {}
+            }
+        }
+
+        if let Some(heredoc) = heredoc_text {
+            return Ok((heredoc, cd_path));
+        }
+    }
+
+    Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch)
+}
+
+#[derive(Debug, PartialEq)]
+pub enum ExtractHeredocError {
+    CommandDidNotStartWithApplyPatch,
+    FailedToLoadBashGrammar(LanguageError),
+    HeredocNotUtf8(Utf8Error),
+    FailedToParsePatchIntoAst,
+    FailedToFindHeredocBody,
+}
+
 /// Applies the patch and prints the result to stdout/stderr.
 pub fn apply_patch(
     patch: &str,
@@ -545,6 +843,7 @@ pub fn print_summary(
 #[cfg(test)]
 mod tests {
     use super::*;
+    use assert_matches::assert_matches;
     use pretty_assertions::assert_eq;
     use std::fs;
     use std::string::ToString;
@@ -555,6 +854,221 @@ mod tests {
         format!("*** Begin Patch\n{body}\n*** End Patch")
     }
 
+    fn strs_to_strings(strs: &[&str]) -> Vec<String> {
+        strs.iter().map(ToString::to_string).collect()
+    }
+
+    // Test helpers to reduce repetition when building bash -lc heredoc scripts
+    fn args_bash(script: &str) -> Vec<String> {
+        strs_to_strings(&["bash", "-lc", script])
+    }
+
+    fn heredoc_script(prefix: &str) -> String {
+        format!(
+            "{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH"
+        )
+    }
+
+    fn heredoc_script_ps(prefix: &str, suffix: &str) -> String {
+        format!(
+            "{prefix}apply_patch <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH{suffix}"
+        )
+    }
+
+    fn expected_single_add() -> Vec<Hunk> {
+        vec![Hunk::AddFile {
+            path: PathBuf::from("foo"),
+            contents: "hi\n".to_string(),
+        }]
+    }
+
+    fn assert_match(script: &str, expected_workdir: Option<&str>) {
+        let args = args_bash(script);
+        match maybe_parse_apply_patch(&args) {
+            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
+                assert_eq!(workdir.as_deref(), expected_workdir);
+                assert_eq!(hunks, expected_single_add());
+            }
+            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
+        }
+    }
+
+    fn assert_not_match(script: &str) {
+        let args = args_bash(script);
+        assert_matches!(
+            maybe_parse_apply_patch(&args),
+            MaybeApplyPatch::NotApplyPatch
+        );
+    }
+
+    #[test]
+    fn test_implicit_patch_single_arg_is_error() {
+        let patch = "*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch".to_string();
+        let args = vec![patch];
+        let dir = tempdir().unwrap();
+        assert_matches!(
+            maybe_parse_apply_patch_verified(&args, dir.path()),
+            MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation)
+        );
+    }
+
+    #[test]
+    fn test_implicit_patch_bash_script_is_error() {
+        let script = "*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch";
+        let args = args_bash(script);
+        let dir = tempdir().unwrap();
+        assert_matches!(
+            maybe_parse_apply_patch_verified(&args, dir.path()),
+            MaybeApplyPatchVerified::CorrectnessError(ApplyPatchError::ImplicitInvocation)
+        );
+    }
+
+    #[test]
+    fn test_literal() {
+        let args = strs_to_strings(&[
+            "apply_patch",
+            r#"*** Begin Patch
+*** Add File: foo
++hi
+*** End Patch
+"#,
+        ]);
+
+        match maybe_parse_apply_patch(&args) {
+            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, .. }) => {
+                assert_eq!(
+                    hunks,
+                    vec![Hunk::AddFile {
+                        path: PathBuf::from("foo"),
+                        contents: "hi\n".to_string()
+                    }]
+                );
+            }
+            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
+        }
+    }
+
+    #[test]
+    fn test_literal_applypatch() {
+        let args = strs_to_strings(&[
+            "applypatch",
+            r#"*** Begin Patch
+*** Add File: foo
++hi
+*** End Patch
+"#,
+        ]);
+
+        match maybe_parse_apply_patch(&args) {
+            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, .. }) => {
+                assert_eq!(
+                    hunks,
+                    vec![Hunk::AddFile {
+                        path: PathBuf::from("foo"),
+                        contents: "hi\n".to_string()
+                    }]
+                );
+            }
+            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
+        }
+    }
+
+    #[test]
+    fn test_heredoc() {
+        assert_match(&heredoc_script(""), None);
+    }
+
+    #[test]
+    fn test_heredoc_applypatch() {
+        let args = strs_to_strings(&[
+            "bash",
+            "-lc",
+            r#"applypatch <<'PATCH'
+*** Begin Patch
+*** Add File: foo
++hi
+*** End Patch
+PATCH"#,
+        ]);
+
+        match maybe_parse_apply_patch(&args) {
+            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, workdir, .. }) => {
+                assert_eq!(workdir, None);
+                assert_eq!(
+                    hunks,
+                    vec![Hunk::AddFile {
+                        path: PathBuf::from("foo"),
+                        contents: "hi\n".to_string()
+                    }]
+                );
+            }
+            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
+        }
+    }
+
+    #[test]
+    fn test_heredoc_with_leading_cd() {
+        assert_match(&heredoc_script("cd foo && "), Some("foo"));
+    }
+
+    #[test]
+    fn test_cd_with_semicolon_is_ignored() {
+        assert_not_match(&heredoc_script("cd foo; "));
+    }
+
+    #[test]
+    fn test_cd_or_apply_patch_is_ignored() {
+        assert_not_match(&heredoc_script("cd bar || "));
+    }
+
+    #[test]
+    fn test_cd_pipe_apply_patch_is_ignored() {
+        assert_not_match(&heredoc_script("cd bar | "));
+    }
+
+    #[test]
+    fn test_cd_single_quoted_path_with_spaces() {
+        assert_match(&heredoc_script("cd 'foo bar' && "), Some("foo bar"));
+    }
+
+    #[test]
+    fn test_cd_double_quoted_path_with_spaces() {
+        assert_match(&heredoc_script("cd \"foo bar\" && "), Some("foo bar"));
+    }
+
+    #[test]
+    fn test_echo_and_apply_patch_is_ignored() {
+        assert_not_match(&heredoc_script("echo foo && "));
+    }
+
+    #[test]
+    fn test_apply_patch_with_arg_is_ignored() {
+        let script = "apply_patch foo <<'PATCH'\n*** Begin Patch\n*** Add File: foo\n+hi\n*** End Patch\nPATCH";
+        assert_not_match(script);
+    }
+
+    #[test]
+    fn test_double_cd_then_apply_patch_is_ignored() {
+        assert_not_match(&heredoc_script("cd foo && cd bar && "));
+    }
+
+    #[test]
+    fn test_cd_two_args_is_ignored() {
+        assert_not_match(&heredoc_script("cd foo bar && "));
+    }
+
+    #[test]
+    fn test_cd_then_apply_patch_then_extra_is_ignored() {
+        let script = heredoc_script_ps("cd bar && ", " && echo done");
+        assert_not_match(&script);
+    }
+
+    #[test]
+    fn test_echo_then_cd_and_apply_patch_is_ignored() {
+        // Ensure preceding commands before the `cd && apply_patch <<...` sequence do not match.
+        assert_not_match(&heredoc_script("echo foo; cd bar && "));
+    }
+
     #[test]
     fn test_add_file_hunk_creates_file_with_contents() {
         let dir = tempdir().unwrap();
@@ -1043,6 +1557,52 @@ g
         );
     }
 
+    #[test]
+    fn test_apply_patch_should_resolve_absolute_paths_in_cwd() {
+        let session_dir = tempdir().unwrap();
+        let relative_path = "source.txt";
+
+        // Note that we need this file to exist for the patch to be "verified"
+        // and parsed correctly.
+        let session_file_path = session_dir.path().join(relative_path);
+        fs::write(&session_file_path, "session directory content\n").unwrap();
+
+        let argv = vec![
+            "apply_patch".to_string(),
+            r#"*** Begin Patch
+*** Update File: source.txt
+@@
+-session directory content
++updated session directory content
+*** End Patch"#
+                .to_string(),
+        ];
+
+        let result = maybe_parse_apply_patch_verified(&argv, session_dir.path());
+
+        // Verify the patch contents - as otherwise we may have pulled contents
+        // from the wrong file (as we're using relative paths)
+        assert_eq!(
+            result,
+            MaybeApplyPatchVerified::Body(ApplyPatchAction {
+                changes: HashMap::from([(
+                    session_dir.path().join(relative_path),
+                    ApplyPatchFileChange::Update {
+                        unified_diff: r#"@@ -1 +1 @@
+-session directory content
++updated session directory content
+"#
+                        .to_string(),
+                        move_path: None,
+                        new_content: "updated session directory content\n".to_string(),
+                    },
+                )]),
+                patch: argv[1].clone(),
+                cwd: session_dir.path().to_path_buf(),
+            })
+        );
+    }
+
     #[test]
     fn test_apply_patch_fails_on_write_error() {
         let dir = tempdir().unwrap();

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

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

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

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

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

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

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

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

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

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

codex-rs/apply-patch/tests/fixtures/scenarios/002_multiple_operations/input/delete.txt

@@ -1 +0,0 @@
-obsolete