one commit

Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>

.gemini/settings.json

@@ -1,9 +1,9 @@
 {
   "experimental": {
-    "plan": true,
     "extensionReloading": true,
     "modelSteering": true,
-    "memoryManager": true
+    "memoryManager": false,
+    "topicUpdateNarration": true
   },
   "general": {
     "devtools": true

.github/actions/publish-release/action.yml

@@ -175,7 +175,9 @@ runs:
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
+        fi
 
     - name: '🔗 Install latest core package'
       working-directory: '${{ inputs.working-directory }}'
@@ -193,7 +195,7 @@ runs:
         INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
 
     - name: '📦 Prepare bundled CLI for npm release'
-      if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/' && inputs.npm-tag != 'latest'"
+      if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/'"
       working-directory: '${{ inputs.working-directory }}'
       shell: 'bash'
       run: |
@@ -248,7 +250,9 @@ runs:
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
+          if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
+          fi
 
     - name: '🔬 Verify NPM release by version'
       uses: './.github/actions/verify-release'
@@ -287,8 +291,25 @@ runs:
         INPUTS_PREVIOUS_TAG: '${{ inputs.previous-tag }}'
       shell: 'bash'
       run: |
+        rm -f gemini-cli-bundle.zip
+        (cd bundle && chmod +x gemini.js && zip -r ../gemini-cli-bundle.zip .)
+
+        echo "Testing the generated bundle archive..."
+        rm -rf test-bundle
+        mkdir -p test-bundle
+        unzip -q gemini-cli-bundle.zip -d test-bundle
+
+        # Verify it runs and outputs a version
+        BUNDLE_VERSION=$(node test-bundle/gemini.js --version | xargs)
+        echo "Bundle version output: ${BUNDLE_VERSION}"
+        if [[ -z "${BUNDLE_VERSION}" ]]; then
+          echo "Error: Bundle failed to execute or return version."
+          exit 1
+        fi
+        rm -rf test-bundle
+
         gh release create "${INPUTS_RELEASE_TAG}" \
-          bundle/gemini.js \
+          gemini-cli-bundle.zip \
           --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
           --title "Release ${INPUTS_RELEASE_TAG}" \
           --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \

.github/actions/run-tests/action.yml

@@ -18,6 +18,13 @@ runs:
       env:
         JSON_INPUTS: '${{ toJSON(inputs) }}'
       run: 'echo "$JSON_INPUTS"'
+    - name: 'Install system dependencies'
+      if: "runner.os == 'Linux'"
+      run: |
+        sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq bubblewrap
+        # Ubuntu 24.04+ requires this to allow bwrap to function in CI
+        sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
+      shell: 'bash'
     - name: 'Run Tests'
       env:
         GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'

.github/workflows/eval-guidance.yml

@@ -1,69 +0,0 @@
-name: 'Evals: PR Guidance'
-
-on:
-  pull_request:
-    paths:
-      - 'packages/core/src/**/*.ts'
-      - '!**/*.test.ts'
-      - '!**/*.test.tsx'
-
-permissions:
-  pull-requests: 'write'
-  contents: 'read'
-
-jobs:
-  provide-guidance:
-    name: 'Model Steering Guidance'
-    runs-on: 'ubuntu-latest'
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    steps:
-      - name: 'Checkout'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: 'Set up Node.js'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
-        with:
-          node-version-file: '.nvmrc'
-          cache: 'npm'
-
-      - name: 'Detect Steering Changes'
-        id: 'detect'
-        run: |
-          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
-          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
-
-      - name: 'Analyze PR Content'
-        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
-        id: 'analysis'
-        env:
-          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-        run: |
-          # Check for behavioral eval changes
-          EVAL_CHANGES=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep "^evals/" || true)
-          if [ -z "$EVAL_CHANGES" ]; then
-            echo "MISSING_EVALS=true" >> "$GITHUB_OUTPUT"
-          fi
-
-          # Check if user is a maintainer (has write/admin access)
-          USER_PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/${{ github.actor }}/permission --jq '.permission')
-          if [[ "$USER_PERMISSION" == "admin" || "$USER_PERMISSION" == "write" ]]; then
-            echo "IS_MAINTAINER=true" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: 'Post Guidance Comment'
-        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
-        uses: 'thollander/actions-comment-pull-request@65f9e5c9a1f2cd378bd74b2e057c9736982a8e74' # ratchet:thollander/actions-comment-pull-request@v3
-        with:
-          comment-tag: 'eval-guidance-bot'
-          message: |
-            ### 🧠 Model Steering Guidance
-
-            This PR modifies files that affect the model's behavior (prompts, tools, or instructions).
-
-            ${{ steps.analysis.outputs.MISSING_EVALS == 'true' && '- ⚠️ **Consider adding Evals:** No behavioral evaluations (`evals/*.eval.ts`) were added or updated in this PR. Consider adding a test case to verify the new behavior and prevent regressions.' || '' }}
-            ${{ steps.analysis.outputs.IS_MAINTAINER == 'true' && '- 🚀 **Maintainer Reminder:** Please ensure that these changes do not regress results on benchmark evals before merging.' || '' }}
-
-            ---
-            *This is an automated guidance message triggered by steering logic signatures.*

.github/workflows/eval-pr.yml

@@ -0,0 +1,137 @@
+name: 'Evals: PR Evaluation & Regression'
+
+on:
+  pull_request:
+    types: ['opened', 'synchronize', 'reopened', 'ready_for_review']
+    paths:
+      - 'packages/core/src/prompts/**'
+      - 'packages/core/src/tools/**'
+      - 'packages/core/src/agents/**'
+      - 'evals/**'
+      - '!**/*.test.ts'
+      - '!**/*.test.tsx'
+  workflow_dispatch:
+
+# Prevents multiple runs for the same PR simultaneously (saves tokens)
+concurrency:
+  group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
+  cancel-in-progress: true
+
+permissions:
+  pull-requests: 'write'
+  contents: 'read'
+  actions: 'read'
+
+jobs:
+  pr-evaluation:
+    name: 'Evaluate Steering & Regressions'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name != 'pull_request' || (github.event.pull_request.draft == false && github.event.pull_request.head.repo.full_name == github.repository))"
+    # External contributors' PRs will wait for approval in this environment
+    environment: |-
+      ${{ (github.event.pull_request.head.repo.full_name == github.repository) && 'internal' || 'external-evals' }}
+    env:
+      # CENTRALIZED MODEL LIST
+      MODEL_LIST: 'gemini-3-flash-preview'
+
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
+        with:
+          fetch-depth: 0
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Detect Steering Changes'
+        id: 'detect'
+        run: |
+          SHOULD_RUN=$(node scripts/changed_prompt.js)
+          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
+          echo "SHOULD_RUN=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
+          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
+
+      - name: 'Analyze PR Content (Guidance)'
+        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
+        id: 'analysis'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          # Check for behavioral eval changes
+          EVAL_CHANGES=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep "^evals/" || true)
+          if [ -z "$EVAL_CHANGES" ]; then
+            echo "MISSING_EVALS=true" >> "$GITHUB_OUTPUT"
+          fi
+
+          # Check if user is a maintainer
+          USER_PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/${{ github.actor }}/permission --jq '.permission')
+          if [[ "$USER_PERMISSION" == "admin" || "$USER_PERMISSION" == "write" ]]; then
+            echo "IS_MAINTAINER=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: 'Execute Regression Check'
+        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          MODEL_LIST: '${{ env.MODEL_LIST }}'
+        run: |
+          # Run the regression check loop. The script saves the report to a file.
+          node scripts/run_eval_regression.js
+
+          # Use the generated report file if it exists
+          if [[ -f eval_regression_report.md ]]; then
+            echo "REPORT_FILE=eval_regression_report.md" >> "$GITHUB_ENV"
+          fi
+
+      - name: 'Post or Update PR Comment'
+        if: "always() && steps.detect.outputs.STEERING_DETECTED == 'true'"
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          # 1. Build the full comment body
+          {
+            if [[ -f eval_regression_report.md ]]; then
+              cat eval_regression_report.md
+              echo ""
+            fi
+            echo "### 🧠 Model Steering Guidance"
+            echo ""
+            echo "This PR modifies files that affect the model's behavior (prompts, tools, or instructions)."
+            echo ""
+
+            if [[ "${{ steps.analysis.outputs.MISSING_EVALS }}" == "true" ]]; then
+              echo "- ⚠️ **Consider adding Evals:** No behavioral evaluations (\`evals/*.eval.ts\`) were added or updated in this PR. Consider [adding a test case](https://github.com/google-gemini/gemini-cli/blob/main/evals/README.md#creating-an-evaluation) to verify the new behavior and prevent regressions."
+            fi
+
+            if [[ "${{ steps.analysis.outputs.IS_MAINTAINER }}" == "true" ]]; then
+              echo "- 🚀 **Maintainer Reminder:** Please ensure that these changes do not regress results on benchmark evals before merging."
+            fi
+
+            echo ""
+            echo "---"
+            echo "*This is an automated guidance message triggered by steering logic signatures.*"
+            echo "<!-- eval-pr-report -->"
+          } > full_comment.md
+
+          # 2. Find if a comment with our unique tag already exists
+          # We extract the numeric ID from the URL to ensure compatibility with the REST API
+          COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-pr-report -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
+
+          # 3. Update or Create the comment
+          if [ -n "$COMMENT_ID" ]; then
+            echo "Updating existing comment $COMMENT_ID via API..."
+            gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body=@full_comment.md
+          else
+            echo "Creating new PR comment..."
+            gh pr comment ${{ github.event.pull_request.number }} --body-file full_comment.md
+          fi

CONTRIBUTING.md

@@ -346,9 +346,11 @@ npm run lint
 
 - Please adhere to the coding style, patterns, and conventions used throughout
   the existing codebase.
-- Consult [GEMINI.md](../GEMINI.md) (typically found in the project root) for
-  specific instructions related to AI-assisted development, including
-  conventions for React, comments, and Git usage.
+- Consult
+  [GEMINI.md](https://github.com/google-gemini/gemini-cli/blob/main/GEMINI.md)
+  (typically found in the project root) for specific instructions related to
+  AI-assisted development, including conventions for React, comments, and Git
+  usage.
 - **Imports:** Pay special attention to import paths. The project uses ESLint to
   enforce restrictions on relative imports between packages.
 
@@ -505,8 +507,9 @@ code.
 
 ### Documentation structure
 
-Our documentation is organized using [sidebar.json](/docs/sidebar.json) as the
-table of contents. When adding new documentation:
+Our documentation is organized using
+[sidebar.json](https://github.com/google-gemini/gemini-cli/blob/main/docs/sidebar.json)
+as the table of contents. When adding new documentation:
 
 1. Create your markdown file **in the appropriate directory** under `/docs`.
 2. Add an entry to `sidebar.json` in the relevant section.

README.md

@@ -30,7 +30,7 @@ Learn all about Gemini CLI in our [documentation](https://geminicli.com/docs/).
 ## 📦 Installation
 
 See
-[Gemini CLI installation, execution, and releases](./docs/get-started/installation.md)
+[Gemini CLI installation, execution, and releases](https://www.geminicli.com/docs/get-started/installation)
 for recommended system specifications and a detailed installation guide.
 
 ### Quick Install
@@ -71,9 +71,9 @@ conda activate gemini_env
 npm install -g @google/gemini-cli
 ```
 
-## Release Cadence and Tags
+## Release Channels
 
-See [Releases](./docs/releases.md) for more details.
+See [Releases](https://www.geminicli.com/docs/changelogs) for more details.
 
 ### Preview
 
@@ -209,7 +209,7 @@ gemini
 ```
 
 For Google Workspace accounts and other authentication methods, see the
-[authentication guide](./docs/get-started/authentication.md).
+[authentication guide](https://www.geminicli.com/docs/get-started/authentication).
 
 ## 🚀 Getting Started
 
@@ -278,59 +278,64 @@ gemini
 
 ### Getting Started
 
-- [**Quickstart Guide**](./docs/get-started/index.md) - Get up and running
-  quickly.
-- [**Authentication Setup**](./docs/get-started/authentication.md) - Detailed
-  auth configuration.
-- [**Configuration Guide**](./docs/reference/configuration.md) - Settings and
-  customization.
-- [**Keyboard Shortcuts**](./docs/reference/keyboard-shortcuts.md) -
+- [**Quickstart Guide**](https://www.geminicli.com/docs/get-started) - Get up
+  and running quickly.
+- [**Authentication Setup**](https://www.geminicli.com/docs/get-started/authentication) -
+  Detailed auth configuration.
+- [**Configuration Guide**](https://www.geminicli.com/docs/reference/configuration) -
+  Settings and customization.
+- [**Keyboard Shortcuts**](https://www.geminicli.com/docs/reference/keyboard-shortcuts) -
   Productivity tips.
 
 ### Core Features
 
-- [**Commands Reference**](./docs/reference/commands.md) - All slash commands
-  (`/help`, `/chat`, etc).
-- [**Custom Commands**](./docs/cli/custom-commands.md) - Create your own
-  reusable commands.
-- [**Context Files (GEMINI.md)**](./docs/cli/gemini-md.md) - Provide persistent
-  context to Gemini CLI.
-- [**Checkpointing**](./docs/cli/checkpointing.md) - Save and resume
-  conversations.
-- [**Token Caching**](./docs/cli/token-caching.md) - Optimize token usage.
+- [**Commands Reference**](https://www.geminicli.com/docs/reference/commands) -
+  All slash commands (`/help`, `/chat`, etc).
+- [**Custom Commands**](https://www.geminicli.com/docs/cli/custom-commands) -
+  Create your own reusable commands.
+- [**Context Files (GEMINI.md)**](https://www.geminicli.com/docs/cli/gemini-md) -
+  Provide persistent context to Gemini CLI.
+- [**Checkpointing**](https://www.geminicli.com/docs/cli/checkpointing) - Save
+  and resume conversations.
+- [**Token Caching**](https://www.geminicli.com/docs/cli/token-caching) -
+  Optimize token usage.
 
 ### Tools & Extensions
 
-- [**Built-in Tools Overview**](./docs/reference/tools.md)
-  - [File System Operations](./docs/tools/file-system.md)
-  - [Shell Commands](./docs/tools/shell.md)
-  - [Web Fetch & Search](./docs/tools/web-fetch.md)
-- [**MCP Server Integration**](./docs/tools/mcp-server.md) - Extend with custom
-  tools.
-- [**Custom Extensions**](./docs/extensions/index.md) - Build and share your own
-  commands.
+- [**Built-in Tools Overview**](https://www.geminicli.com/docs/reference/tools)
+  - [File System Operations](https://www.geminicli.com/docs/tools/file-system)
+  - [Shell Commands](https://www.geminicli.com/docs/tools/shell)
+  - [Web Fetch & Search](https://www.geminicli.com/docs/tools/web-fetch)
+- [**MCP Server Integration**](https://www.geminicli.com/docs/tools/mcp-server) -
+  Extend with custom tools.
+- [**Custom Extensions**](https://geminicli.com/docs/extensions/writing-extensions) -
+  Build and share your own commands.
 
 ### Advanced Topics
 
-- [**Headless Mode (Scripting)**](./docs/cli/headless.md) - Use Gemini CLI in
-  automated workflows.
-- [**IDE Integration**](./docs/ide-integration/index.md) - VS Code companion.
-- [**Sandboxing & Security**](./docs/cli/sandbox.md) - Safe execution
-  environments.
-- [**Trusted Folders**](./docs/cli/trusted-folders.md) - Control execution
-  policies by folder.
-- [**Enterprise Guide**](./docs/cli/enterprise.md) - Deploy and manage in a
-  corporate environment.
-- [**Telemetry & Monitoring**](./docs/cli/telemetry.md) - Usage tracking.
-- [**Tools reference**](./docs/reference/tools.md) - Built-in tools overview.
-- [**Local development**](./docs/local-development.md) - Local development
-  tooling.
+- [**Headless Mode (Scripting)**](https://www.geminicli.com/docs/cli/headless) -
+  Use Gemini CLI in automated workflows.
+- [**IDE Integration**](https://www.geminicli.com/docs/ide-integration) - VS
+  Code companion.
+- [**Sandboxing & Security**](https://www.geminicli.com/docs/cli/sandbox) - Safe
+  execution environments.
+- [**Trusted Folders**](https://www.geminicli.com/docs/cli/trusted-folders) -
+  Control execution policies by folder.
+- [**Enterprise Guide**](https://www.geminicli.com/docs/cli/enterprise) - Deploy
+  and manage in a corporate environment.
+- [**Telemetry & Monitoring**](https://www.geminicli.com/docs/cli/telemetry) -
+  Usage tracking.
+- [**Tools reference**](https://www.geminicli.com/docs/reference/tools) -
+  Built-in tools overview.
+- [**Local development**](https://www.geminicli.com/docs/local-development) -
+  Local development tooling.
 
 ### Troubleshooting & Support
 
-- [**Troubleshooting Guide**](./docs/resources/troubleshooting.md) - Common
-  issues and solutions.
-- [**FAQ**](./docs/resources/faq.md) - Frequently asked questions.
+- [**Troubleshooting Guide**](https://www.geminicli.com/docs/resources/troubleshooting) -
+  Common issues and solutions.
+- [**FAQ**](https://www.geminicli.com/docs/resources/faq) - Frequently asked
+  questions.
 - Use `/bug` command to report issues directly from the CLI.
 
 ### Using MCP Servers
@@ -344,8 +349,9 @@ custom tools:
 > @database Run a query to find inactive users
 ```
 
-See the [MCP Server Integration guide](./docs/tools/mcp-server.md) for setup
-instructions.
+See the
+[MCP Server Integration guide](https://www.geminicli.com/docs/tools/mcp-server)
+for setup instructions.
 
 ## 🤝 Contributing
 
@@ -366,7 +372,8 @@ for planned features and priorities.
 ## 📖 Resources
 
 - **[Official Roadmap](./ROADMAP.md)** - See what's coming next.
-- **[Changelog](./docs/changelogs/index.md)** - See recent notable updates.
+- **[Changelog](https://www.geminicli.com/docs/changelogs)** - See recent
+  notable updates.
 - **[NPM Package](https://www.npmjs.com/package/@google/gemini-cli)** - Package
   registry.
 - **[GitHub Issues](https://github.com/google-gemini/gemini-cli/issues)** -
@@ -376,13 +383,14 @@ for planned features and priorities.
 
 ### Uninstall
 
-See the [Uninstall Guide](./docs/resources/uninstall.md) for removal
-instructions.
+See the [Uninstall Guide](https://www.geminicli.com/docs/resources/uninstall)
+for removal instructions.
 
 ## 📄 Legal
 
 - **License**: [Apache License 2.0](LICENSE)
-- **Terms of Service**: [Terms & Privacy](./docs/resources/tos-privacy.md)
+- **Terms of Service**:
+  [Terms & Privacy](https://www.geminicli.com/docs/resources/tos-privacy)
 - **Security**: [Security Policy](SECURITY.md)
 
 ---

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.35.2
+# Latest stable release: v0.35.3
 
-Released: March 26, 2026
+Released: March 28, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -29,6 +29,9 @@ npm install -g @google/gemini-cli
 
 ## What's Changed
 
+- fix(patch): cherry-pick 765fb67 to release/v0.35.2-pr-24055 [CONFLICTS] by
+  @gemini-cli-robot in
+  [#24063](https://github.com/google-gemini/gemini-cli/pull/24063)
 - fix(core): allow disabling environment variable redaction by @galz10 in
   [#23927](https://github.com/google-gemini/gemini-cli/pull/23927)
 - fix(a2a-server): A2A server should execute ask policies in interactive mode by
@@ -385,4 +388,4 @@ npm install -g @google/gemini-cli
   [#23585](https://github.com/google-gemini/gemini-cli/pull/23585)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.34.0...v0.35.2
+https://github.com/google-gemini/gemini-cli/compare/v0.34.0...v0.35.3

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: v0.36.0-preview.5
+# Preview release: v0.36.0-preview.8
 
-Released: March 27, 2026
+Released: April 01, 2026
 
 Our preview release includes the latest, new, and experimental features. This
 release may not be as stable as our [latest weekly release](latest.md).
@@ -31,6 +31,10 @@ npm install -g @google/gemini-cli@preview
 
 ## What's Changed
 
+- fix(patch): cherry-pick 765fb67 to release/v0.36.0-preview.5-pr-24055 to patch
+  version v0.36.0-preview.5 and create version 0.36.0-preview.6 by
+  @gemini-cli-robot in
+  [#24061](https://github.com/google-gemini/gemini-cli/pull/24061)
 - fix(a2a-server): A2A server should execute ask policies in interactive mode by
   @kschaab in [#23831](https://github.com/google-gemini/gemini-cli/pull/23831)
 - docs(core): document agent_card_json string literal options for remote agents
@@ -386,4 +390,4 @@ npm install -g @google/gemini-cli@preview
   [#23666](https://github.com/google-gemini/gemini-cli/pull/23666)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.35.0-preview.5...v0.36.0-preview.5
+https://github.com/google-gemini/gemini-cli/compare/v0.35.0-preview.5...v0.36.0-preview.8

docs/cli/cli-reference.md

@@ -52,7 +52,7 @@ These commands are available within the interactive REPL.
 | `--prompt-interactive`           | `-i`  | string  | -         | Execute prompt and continue in interactive mode                                                                                                                        |
 | `--worktree`                     | `-w`  | string  | -         | Start Gemini in a new git worktree. If no name is provided, one is generated automatically. Requires `experimental.worktrees: true` in settings.                       |
 | `--sandbox`                      | `-s`  | boolean | `false`   | Run in a sandboxed environment for safer execution                                                                                                                     |
-| `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`                                                                                              |
+| `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`, `plan`                                                                                      |
 | `--yolo`                         | `-y`  | boolean | `false`   | **Deprecated.** Auto-approve all actions. Use `--approval-mode=yolo` instead.                                                                                          |
 | `--experimental-acp`             | -     | boolean | -         | Start in ACP (Agent Code Pilot) mode. **Experimental feature.**                                                                                                        |
 | `--experimental-zed-integration` | -     | boolean | -         | Run in Zed editor integration mode. **Experimental feature.**                                                                                                          |

docs/cli/plan-mode.md

@@ -56,19 +56,21 @@ Gemini CLI takes action.
 
 1.  **Provide a goal:** Start by describing what you want to achieve. Gemini CLI
     will then enter Plan Mode (if it's not already) to research the task.
-2.  **Review research and provide input:** As Gemini CLI analyzes your codebase,
-    it may ask you questions or present different implementation options using
-    [`ask_user`](../tools/ask-user.md). Provide your preferences to help guide
-    the design.
-3.  **Review the plan:** Once Gemini CLI has a proposed strategy, it creates a
-    detailed implementation plan as a Markdown file in your plans directory.
+2.  **Discuss and agree on strategy:** As Gemini CLI analyzes your codebase, it
+    will discuss its findings and proposed strategy with you to ensure
+    alignment. It may ask you questions or present different implementation
+    options using [`ask_user`](../tools/ask-user.md). **Gemini CLI will stop and
+    wait for your confirmation** before drafting the formal plan. You should
+    reach an informal agreement on the approach before proceeding.
+3.  **Review the plan:** Once you've agreed on the strategy, Gemini CLI creates
+    a detailed implementation plan as a Markdown file in your plans directory.
     - **View:** You can open and read this file to understand the proposed
       changes.
     - **Edit:** Press `Ctrl+X` to open the plan directly in your configured
       external editor.
 
 4.  **Approve or iterate:** Gemini CLI will present the finalized plan for your
-    approval.
+    formal approval.
     - **Approve:** If you're satisfied with the plan, approve it to start the
       implementation immediately: **Yes, automatically accept edits** or **Yes,
       manually accept edits**.
@@ -121,6 +123,7 @@ These are the only allowed tools:
   [`glob`](../tools/file-system.md#4-glob-findfiles)
 - **Search:** [`grep_search`](../tools/file-system.md#5-grep_search-searchtext),
   [`google_web_search`](../tools/web-search.md),
+  [`web_fetch`](../tools/web-fetch.md) (requires explicit confirmation),
   [`get_internal_docs`](../tools/internal-docs.md)
 - **Research Subagents:**
   [`codebase_investigator`](../core/subagents.md#codebase-investigator),

docs/cli/settings.md

@@ -30,6 +30,7 @@ they appear in the UI.
 | Default Approval Mode   | `general.defaultApprovalMode`      | The default approval mode for tool execution. 'default' prompts for approval, 'auto_edit' auto-approves edit tools, and 'plan' is read-only mode. YOLO mode (auto-approve all actions) can only be enabled via command line (--yolo or --approval-mode=yolo). | `"default"` |
 | Enable Auto Update      | `general.enableAutoUpdate`         | Enable automatic updates.                                                                                                                                                                                                                                     | `true`      |
 | Enable Notifications    | `general.enableNotifications`      | Enable run-event notifications for action-required prompts and session completion.                                                                                                                                                                            | `false`     |
+| Enable Plan Mode        | `general.plan.enabled`             | Enable Plan Mode for read-only safety during planning.                                                                                                                                                                                                        | `true`      |
 | Plan Directory          | `general.plan.directory`           | The directory where planning artifacts are stored. If not specified, defaults to the system temporary directory. A custom directory requires a policy to allow write access in Plan Mode.                                                                     | `undefined` |
 | Plan Model Routing      | `general.plan.modelRouting`        | Automatically switch between Pro and Flash models based on Plan Mode status. Uses Pro for the planning phase and Flash for the implementation phase.                                                                                                          | `true`      |
 | Retry Fetch Errors      | `general.retryFetchErrors`         | Retry on "exception TypeError: fetch failed sending request" errors.                                                                                                                                                                                          | `true`      |
@@ -46,38 +47,39 @@ they appear in the UI.
 
 ### UI
 
-| UI Label                             | Setting                                | Description                                                                                                                                                       | Default  |
-| ------------------------------------ | -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- |
-| Auto Theme Switching                 | `ui.autoThemeSwitching`                | Automatically switch between default light and dark themes based on terminal background color.                                                                    | `true`   |
-| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval` | Interval in seconds to poll the terminal background color.                                                                                                        | `60`     |
-| Hide Window Title                    | `ui.hideWindowTitle`                   | Hide the window title bar                                                                                                                                         | `false`  |
-| Inline Thinking                      | `ui.inlineThinkingMode`                | Display model thinking inline: off or full.                                                                                                                       | `"off"`  |
-| Show Thoughts in Title               | `ui.showStatusInTitle`                 | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false`  |
-| Dynamic Window Title                 | `ui.dynamicWindowTitle`                | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`   |
-| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`   |
-| Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                          | `true`   |
-| Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                       | `false`  |
-| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                         | `false`  |
-| Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`   |
-| Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                       | `false`  |
-| Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false`  |
-| Hide CWD                             | `ui.footer.hideCWD`                    | Hide the current working directory in the footer.                                                                                                                 | `false`  |
-| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`          | Hide the sandbox status indicator in the footer.                                                                                                                  | `false`  |
-| Hide Model Info                      | `ui.footer.hideModelInfo`              | Hide the model name and context usage in the footer.                                                                                                              | `false`  |
-| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`      | Hides the context window usage percentage.                                                                                                                        | `true`   |
-| Hide Footer                          | `ui.hideFooter`                        | Hide the footer from the UI                                                                                                                                       | `false`  |
-| Show Memory Usage                    | `ui.showMemoryUsage`                   | Display memory usage information in the UI                                                                                                                        | `false`  |
-| Show Line Numbers                    | `ui.showLineNumbers`                   | Show line numbers in the chat.                                                                                                                                    | `true`   |
-| Show Citations                       | `ui.showCitations`                     | Show citations for generated text in the chat.                                                                                                                    | `false`  |
-| Show Model Info In Chat              | `ui.showModelInfoInChat`               | Show the model name in the chat for each model turn.                                                                                                              | `false`  |
-| Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                        | `true`   |
-| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false`  |
-| Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                       | `true`   |
-| Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`   |
-| Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`   |
-| Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, both, or nothing.                                                                                  | `"tips"` |
-| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                       | `"low"`  |
-| Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                   | `false`  |
+| UI Label                             | Setting                                | Description                                                                                                                                                       | Default |
+| ------------------------------------ | -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Auto Theme Switching                 | `ui.autoThemeSwitching`                | Automatically switch between default light and dark themes based on terminal background color.                                                                    | `true`  |
+| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval` | Interval in seconds to poll the terminal background color.                                                                                                        | `60`    |
+| Hide Window Title                    | `ui.hideWindowTitle`                   | Hide the window title bar                                                                                                                                         | `false` |
+| Inline Thinking                      | `ui.inlineThinkingMode`                | Display model thinking inline: off or full.                                                                                                                       | `"off"` |
+| Show Thoughts in Title               | `ui.showStatusInTitle`                 | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false` |
+| Dynamic Window Title                 | `ui.dynamicWindowTitle`                | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`  |
+| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`  |
+| Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                          | `true`  |
+| Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                       | `false` |
+| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                         | `false` |
+| Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`  |
+| Compact Tool Output                  | `ui.compactToolOutput`                 | Display tool outputs (like directory listings and file reads) in a compact, structured format.                                                                    | `false` |
+| Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                       | `false` |
+| Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false` |
+| Hide CWD                             | `ui.footer.hideCWD`                    | Hide the current working directory in the footer.                                                                                                                 | `false` |
+| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`          | Hide the sandbox status indicator in the footer.                                                                                                                  | `false` |
+| Hide Model Info                      | `ui.footer.hideModelInfo`              | Hide the model name and context usage in the footer.                                                                                                              | `false` |
+| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`      | Hides the context window usage percentage.                                                                                                                        | `true`  |
+| Hide Footer                          | `ui.hideFooter`                        | Hide the footer from the UI                                                                                                                                       | `false` |
+| Show Memory Usage                    | `ui.showMemoryUsage`                   | Display memory usage information in the UI                                                                                                                        | `false` |
+| Show Line Numbers                    | `ui.showLineNumbers`                   | Show line numbers in the chat.                                                                                                                                    | `true`  |
+| Show Citations                       | `ui.showCitations`                     | Show citations for generated text in the chat.                                                                                                                    | `false` |
+| Show Model Info In Chat              | `ui.showModelInfoInChat`               | Show the model name in the chat for each model turn.                                                                                                              | `false` |
+| Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                        | `true`  |
+| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false` |
+| Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                       | `true`  |
+| Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`  |
+| Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`  |
+| Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, all, or off.                                                                                       | `"off"` |
+| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                       | `"low"` |
+| Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                   | `false` |
 
 ### IDE
 
@@ -151,25 +153,22 @@ they appear in the UI.
 
 | UI Label                          | Setting                        | Description                                   | Default |
 | --------------------------------- | ------------------------------ | --------------------------------------------- | ------- |
-| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits | `false` |
+| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits | `true`  |
 
 ### Experimental
 
-| UI Label                           | Setting                                        | Description                                                                                                                                               | Default |
-| ---------------------------------- | ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
-| Enable Tool Output Masking         | `experimental.toolOutputMasking.enabled`       | Enables tool output masking to save tokens.                                                                                                               | `true`  |
-| Enable Git Worktrees               | `experimental.worktrees`                       | Enable automated Git worktree management for parallel work.                                                                                               | `false` |
-| Use OSC 52 Paste                   | `experimental.useOSC52Paste`                   | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
-| Use OSC 52 Copy                    | `experimental.useOSC52Copy`                    | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
-| Plan                               | `experimental.plan`                            | Enable Plan Mode.                                                                                                                                         | `true`  |
-| Model Steering                     | `experimental.modelSteering`                   | Enable model steering (user hints) to guide the model during tool execution.                                                                              | `false` |
-| Direct Web Fetch                   | `experimental.directWebFetch`                  | Enable web fetch behavior that bypasses LLM summarization.                                                                                                | `false` |
-| Memory Manager Agent               | `experimental.memoryManager`                   | Replace the built-in save_memory tool with a memory manager subagent that supports adding, removing, de-duplicating, and organizing memories.             | `false` |
-| Agent History Truncation           | `experimental.agentHistoryTruncation`          | Enable truncation window logic for the Agent History Provider.                                                                                            | `false` |
-| Agent History Truncation Threshold | `experimental.agentHistoryTruncationThreshold` | The maximum number of messages before history is truncated.                                                                                               | `30`    |
-| Agent History Retained Messages    | `experimental.agentHistoryRetainedMessages`    | The number of recent messages to retain after truncation.                                                                                                 | `15`    |
-| Agent History Summarization        | `experimental.agentHistorySummarization`       | Enable summarization of truncated content via a small model for the Agent History Provider.                                                               | `false` |
-| Topic & Update Narration           | `experimental.topicUpdateNarration`            | Enable the experimental Topic & Update communication model for reduced chattiness and structured progress reporting.                                      | `false` |
+| UI Label                                             | Setting                             | Description                                                                                                                                               | Default |
+| ---------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Enable Git Worktrees                                 | `experimental.worktrees`            | Enable automated Git worktree management for parallel work.                                                                                               | `false` |
+| Use OSC 52 Paste                                     | `experimental.useOSC52Paste`        | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
+| Use OSC 52 Copy                                      | `experimental.useOSC52Copy`         | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
+| Model Steering                                       | `experimental.modelSteering`        | Enable model steering (user hints) to guide the model during tool execution.                                                                              | `false` |
+| Direct Web Fetch                                     | `experimental.directWebFetch`       | Enable web fetch behavior that bypasses LLM summarization.                                                                                                | `false` |
+| Memory Manager Agent                                 | `experimental.memoryManager`        | Replace the built-in save_memory tool with a memory manager subagent that supports adding, removing, de-duplicating, and organizing memories.             | `false` |
+| Use the power user profile for massive contexts.     | `experimental.powerUserProfile`     | Enables continuous minimal GC near the max tokens limit instead of a blocked backbuffer.                                                                  | `false` |
+| Use the generalist profile to manage agent contexts. | `experimental.generalistProfile`    | Suitable for general coding and software development tasks.                                                                                               | `false` |
+| Enable Context Management                            | `experimental.contextManagement`    | Enable logic for context management.                                                                                                                      | `false` |
+| Topic & Update Narration                             | `experimental.topicUpdateNarration` | Enable the experimental Topic & Update communication model for reduced chattiness and structured progress reporting.                                      | `false` |
 
 ### Skills
 

docs/cli/themes.md

@@ -19,6 +19,7 @@ using the `/theme` command within Gemini CLI:
   - `Holiday`
   - `Shades Of Purple`
   - `Solarized Dark`
+  - `Tokyo Night`
 - **Light themes:**
   - `ANSI Light`
   - `Ayu Light`
@@ -252,6 +253,10 @@ identify their source, for example: `shades-of-green (green-extension)`.
 
 <img src="/docs/assets/theme-solarized-dark.png" alt="Solarized Dark theme" width="600">
 
+### Tokyo Night
+
+<img src="/docs/assets/theme-tokyonight-dark.png" alt="Tokyo Night theme" width="600">
+
 ## Light themes
 
 ### ANSI Light

docs/core/index.md

@@ -7,8 +7,8 @@ requests sent from `packages/cli`. For a general overview of Gemini CLI, see the
 
 ## Navigating this section
 
-- **[Sub-agents (experimental)](./subagents.md):** Learn how to create and use
-  specialized sub-agents for complex tasks.
+- **[Sub-agents](./subagents.md):** Learn how to create and use specialized
+  sub-agents for complex tasks.
 - **[Core tools reference](../reference/tools.md):** Information on how tools
   are defined, registered, and used by the core.
 - **[Memory Import Processor](../reference/memport.md):** Documentation for the

docs/core/subagents.md

@@ -1,20 +1,16 @@
-# Subagents (experimental)
+# Subagents
 
 Subagents are specialized agents that operate within your main Gemini CLI
 session. They are designed to handle specific, complex tasks—like deep codebase
 analysis, documentation lookup, or domain-specific reasoning—without cluttering
 the main agent's context or toolset.
 
-<!-- prettier-ignore -->
-> [!NOTE]
-> Subagents are currently an experimental feature.
-> 
-To use custom subagents, you must ensure they are enabled in your
-`settings.json` (enabled by default):
+Subagents are enabled by default. To disable them, set `enableAgents` to `false`
+in your `settings.json`:
 
 ```json
 {
-  "experimental": { "enableAgents": true }
+  "experimental": { "enableAgents": false }
 }
 ```
 
@@ -124,10 +120,12 @@ Gemini CLI comes with the following built-in subagents:
 
 The browser agent requires:
 
-- **Chrome** version 144 or later (any recent stable release will work).
-- **Node.js** with `npx` available (used to launch the
-  [`chrome-devtools-mcp`](https://www.npmjs.com/package/chrome-devtools-mcp)
-  server).
+- **Chrome** version 144 or later (any recent stable release works).
+
+The underlying
+[`chrome-devtools-mcp`](https://www.npmjs.com/package/chrome-devtools-mcp)
+server is bundled with Gemini CLI and launched automatically — no separate
+installation is needed.
 
 #### Enabling the browser agent
 
@@ -173,26 +171,58 @@ The available modes are:
 | `isolated`   | Launches Chrome with a temporary profile that is deleted after each session. Use this for clean-state automation.                                                                           |
 | `existing`   | Attaches to an already-running Chrome instance. You must enable remote debugging first by navigating to `chrome://inspect/#remote-debugging` in Chrome. No new browser process is launched. |
 
+#### First-run consent
+
+The first time the browser agent is invoked, Gemini CLI displays a consent
+dialog. You must accept before the browser session starts. This dialog only
+appears once.
+
 #### Configuration reference
 
 All browser-specific settings go under `agents.browser` in your `settings.json`.
+For full details, see the
+[`agents.browser` configuration reference](../reference/configuration.md#agents).
 
-| Setting       | Type      | Default        | Description                                                                                     |
-| :------------ | :-------- | :------------- | :---------------------------------------------------------------------------------------------- |
-| `sessionMode` | `string`  | `"persistent"` | How Chrome is managed: `"persistent"`, `"isolated"`, or `"existing"`.                           |
-| `headless`    | `boolean` | `false`        | Run Chrome in headless mode (no visible window).                                                |
-| `profilePath` | `string`  | —              | Custom path to a browser profile directory.                                                     |
-| `visualModel` | `string`  | —              | Model override for the visual agent (for example, `"gemini-2.5-computer-use-preview-10-2025"`). |
+| Setting                   | Type       | Default        | Description                                                                     |
+| :------------------------ | :--------- | :------------- | :------------------------------------------------------------------------------ |
+| `sessionMode`             | `string`   | `"persistent"` | How Chrome is managed: `"persistent"`, `"isolated"`, or `"existing"`.           |
+| `headless`                | `boolean`  | `false`        | Run Chrome in headless mode (no visible window).                                |
+| `profilePath`             | `string`   | —              | Custom path to a browser profile directory.                                     |
+| `visualModel`             | `string`   | —              | Model override for the visual agent.                                            |
+| `allowedDomains`          | `string[]` | —              | Restrict navigation to specific domains (for example, `["github.com"]`).        |
+| `disableUserInput`        | `boolean`  | `true`         | Disable user input on the browser window during automation (non-headless only). |
+| `maxActionsPerTask`       | `number`   | `100`          | Maximum tool calls per task. The agent is terminated when the limit is reached. |
+| `confirmSensitiveActions` | `boolean`  | `false`        | Require manual confirmation for `upload_file` and `evaluate_script`.            |
+| `blockFileUploads`        | `boolean`  | `false`        | Hard-block all file upload requests from the agent.                             |
+
+#### Automation overlay and input blocking
+
+In non-headless mode, the browser agent injects a visual overlay into the
+browser window to indicate that automation is in progress. By default, user
+input (keyboard and mouse) is also blocked to prevent accidental interference.
+You can disable this by setting `disableUserInput` to `false`.
 
 #### Security
 
-The browser agent enforces the following security restrictions:
+The browser agent enforces several layers of security:
 
-- **Blocked URL patterns:** `file://`, `javascript:`, `data:text/html`,
-  `chrome://extensions`, and `chrome://settings/passwords` are always blocked.
-- **Sensitive action confirmation:** Actions like form filling, file uploads,
-  and form submissions require user confirmation through the standard policy
-  engine.
+- **Domain restrictions:** When `allowedDomains` is set, the agent can only
+  navigate to the listed domains (and their subdomains when using `*.` prefix).
+  Attempting to visit a disallowed domain throws a fatal error that immediately
+  terminates the agent. The agent also attempts to detect and block the use of
+  allowed domains as proxies (e.g., via query parameters or fragments) to access
+  restricted content.
+- **Blocked URL patterns:** The underlying MCP server blocks dangerous URL
+  schemes including `file://`, `javascript:`, `data:text/html`,
+  `chrome://extensions`, and `chrome://settings/passwords`.
+- **Sensitive action confirmation:** Form filling (`fill`, `fill_form`) always
+  requires user confirmation through the policy engine, regardless of approval
+  mode. When `confirmSensitiveActions` is `true`, `upload_file` and
+  `evaluate_script` also require confirmation.
+- **File upload blocking:** Set `blockFileUploads` to `true` to hard-block all
+  file upload requests, preventing the agent from uploading any files.
+- **Action rate limiting:** The `maxActionsPerTask` setting (default: 100)
+  limits the total number of tool calls per task to prevent runaway execution.
 
 #### Visual agent
 
@@ -226,19 +256,65 @@ the `click_at` tool for precise, coordinate-based interactions.
 > The visual agent requires API key or Vertex AI authentication. It is
 > not available when using "Sign in with Google".
 
+#### Sandbox support
+
+The browser agent adjusts its behavior automatically when running inside a
+sandbox.
+
+##### macOS seatbelt (`sandbox-exec`)
+
+When the CLI runs under the macOS seatbelt sandbox, `persistent` and `isolated`
+session modes are forced to `isolated` with `headless` enabled. This avoids
+permission errors caused by seatbelt file-system restrictions on persistent
+browser profiles. If `sessionMode` is set to `existing`, no override is applied.
+
+##### Container sandboxes (Docker / Podman)
+
+Chrome is not available inside the container, so the browser agent is
+**disabled** unless `sessionMode` is set to `"existing"`. When enabled with
+`existing` mode, the agent automatically connects to Chrome on the host via the
+resolved IP of `host.docker.internal:9222` instead of using local pipe
+discovery. Port `9222` is currently hardcoded and cannot be customized.
+
+To use the browser agent in a Docker sandbox:
+
+1. Start Chrome on the host with remote debugging enabled:
+
+   ```bash
+   # Option A: Launch Chrome from the command line
+   google-chrome --remote-debugging-port=9222
+
+   # Option B: Enable in Chrome settings
+   # Navigate to chrome://inspect/#remote-debugging and enable
+   ```
+
+2. Configure `sessionMode` and allowed domains in your project's
+   `.gemini/settings.json`:
+
+   ```json
+   {
+     "agents": {
+       "overrides": {
+         "browser_agent": { "enabled": true }
+       },
+       "browser": {
+         "sessionMode": "existing",
+         "allowedDomains": ["example.com"]
+       }
+     }
+   }
+   ```
+
+3. Launch the CLI with port forwarding:
+
+   ```bash
+   GEMINI_SANDBOX=docker SANDBOX_PORTS=9222 gemini
+   ```
+
 ## Creating custom subagents
 
 You can create your own subagents to automate specific workflows or enforce
-specific personas. To use custom subagents, you must enable them in your
-`settings.json`:
-
-```json
-{
-  "experimental": {
-    "enableAgents": true
-  }
-}
-```
+specific personas.
 
 ### Agent definition files
 
@@ -290,6 +366,7 @@ it yourself; just report it.
 | `description`  | string | Yes      | Short description of what the agent does. This is visible to the main agent to help it decide when to call this subagent.                                                                                     |
 | `kind`         | string | No       | `local` (default) or `remote`.                                                                                                                                                                                |
 | `tools`        | array  | No       | List of tool names this agent can use. Supports wildcards: `*` (all tools), `mcp_*` (all MCP tools), `mcp_server_*` (all tools from a server). **If omitted, it inherits all tools from the parent session.** |
+| `mcpServers`   | object | No       | Configuration for inline Model Context Protocol (MCP) servers isolated to this specific agent.                                                                                                                |
 | `model`        | string | No       | Specific model to use (e.g., `gemini-3-preview`). Defaults to `inherit` (uses the main session model).                                                                                                        |
 | `temperature`  | number | No       | Model temperature (0.0 - 2.0). Defaults to `1`.                                                                                                                                                               |
 | `max_turns`    | number | No       | Maximum number of conversation turns allowed for this agent before it must return. Defaults to `30`.                                                                                                          |
@@ -317,6 +394,78 @@ Each subagent runs in its own isolated context loop. This means:
   subagents **cannot** call other subagents. If a subagent is granted the `*`
   tool wildcard, it will still be unable to see or invoke other agents.
 
+## Subagent tool isolation
+
+Subagent tool isolation moves Gemini CLI away from a single global tool
+registry. By providing isolated execution environments, you can ensure that
+subagents only interact with the parts of the system they are designed for. This
+prevents unintended side effects, improves reliability by avoiding state
+contamination, and enables fine-grained permission control.
+
+With this feature, you can:
+
+- **Specify tool access:** Define exactly which tools an agent can access using
+  a `tools` list in the agent definition.
+- **Define inline MCP servers:** Configure Model Context Protocol (MCP) servers
+  (which provide a standardized way to connect AI models to external tools and
+  data sources) directly in the subagent's markdown frontmatter, isolating them
+  to that specific agent.
+- **Maintain state isolation:** Ensure that subagents only interact with their
+  own set of tools and servers, preventing side effects and state contamination.
+- **Apply subagent-specific policies:** Enforce granular rules in your
+  [Policy Engine](../reference/policy-engine.md) TOML configuration based on the
+  executing subagent's name.
+
+### Configuring isolated tools and servers
+
+You can configure tool isolation for a subagent by updating its markdown
+frontmatter. This allows you to explicitly state which tools the subagent can
+use, rather than relying on the global registry.
+
+Add an `mcpServers` object to define inline MCP servers that are unique to the
+agent.
+
+**Example:**
+
+```yaml
+---
+name: my-isolated-agent
+tools:
+  - grep_search
+  - read_file
+mcpServers:
+  my-custom-server:
+    command: 'node'
+    args: ['path/to/server.js']
+---
+```
+
+### Subagent-specific policies
+
+You can enforce fine-grained control over subagents using the
+[Policy Engine's](../reference/policy-engine.md) TOML configuration. This allows
+you to grant or restrict permissions specifically for an agent, without
+affecting the rest of your CLI session.
+
+To restrict a policy rule to a specific subagent, add the `subagent` property to
+the `[[rules]]` block in your `policy.toml` file.
+
+**Example:**
+
+```toml
+[[rules]]
+name = "Allow pr-creator to push code"
+subagent = "pr-creator"
+description = "Permit pr-creator to push branches automatically."
+action = "allow"
+toolName = "run_shell_command"
+commandPrefix = "git push"
+```
+
+In this configuration, the policy rule only triggers if the executing subagent's
+name matches `pr-creator`. Rules without the `subagent` property apply
+universally to all agents.
+
 ## Managing subagents
 
 You can manage subagents interactively using the `/agents` command or
@@ -406,15 +555,11 @@ If you need to further tune your subagent, you can do so by selecting the model
 to optimize for with `/model` and then asking the model why it does not think
 that your subagent was called with a specific prompt and the given description.
 
-## Remote subagents (Agent2Agent) (experimental)
+## Remote subagents (Agent2Agent)
 
 Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent
 (A2A) protocol.
 
-<!-- prettier-ignore -->
-> [!NOTE]
-> Remote subagents are currently an experimental feature.
-
 See the [Remote Subagents documentation](remote-agents) for detailed
 configuration, authentication, and usage instructions.
 

docs/reference/commands.md

@@ -17,8 +17,6 @@ Slash commands provide meta-level control over the CLI itself.
 ### `/agents`
 
 - **Description:** Manage local and remote subagents.
-- **Note:** This command is experimental and requires
-  `experimental.enableAgents: true` in your `settings.json`.
 - **Sub-commands:**
   - **`list`**:
     - **Description:** Lists all discovered agents, including built-in, local,
@@ -305,7 +303,7 @@ Slash commands provide meta-level control over the CLI itself.
 - **Description:** Switch to Plan Mode (read-only) and view the current plan if
   one has been generated.
   - **Note:** This feature is enabled by default. It can be disabled via the
-    `experimental.plan` setting in your configuration.
+    `general.plan.enabled` setting in your configuration.
 - **Sub-commands:**
   - **`copy`**:
     - **Description:** Copy the currently approved plan to your clipboard.

docs/reference/configuration.md

@@ -62,11 +62,13 @@ locations for these files:
 
 **Note on environment variables in settings:** String values within your
 `settings.json` and `gemini-extension.json` files can reference environment
-variables using either `$VAR_NAME` or `${VAR_NAME}` syntax. These variables will
-be automatically resolved when the settings are loaded. For example, if you have
-an environment variable `MY_API_TOKEN`, you could use it in `settings.json` like
-this: `"apiKey": "$MY_API_TOKEN"`. Additionally, each extension can have its own
-`.env` file in its directory, which will be loaded automatically.
+variables using `$VAR_NAME`, `${VAR_NAME}`, or `${VAR_NAME:-DEFAULT_VALUE}`
+syntax. These variables will be automatically resolved when the settings are
+loaded. For example, if you have an environment variable `MY_API_TOKEN`, you
+could use it in `settings.json` like this: `"apiKey": "$MY_API_TOKEN"`. If you
+want to provide a fallback value, use `${MY_API_TOKEN:-default-token}`.
+Additionally, each extension can have its own `.env` file in its directory,
+which will be loaded automatically.
 
 **Note for Enterprise Users:** For guidance on deploying and managing Gemini CLI
 in a corporate environment, please see the
@@ -141,6 +143,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
+- **`general.plan.enabled`** (boolean):
+  - **Description:** Enable Plan Mode for read-only safety during planning.
+  - **Default:** `true`
+  - **Requires restart:** Yes
+
 - **`general.plan.directory`** (string):
   - **Description:** The directory where planning artifacts are stored. If not
     specified, defaults to the system temporary directory. A custom directory
@@ -257,6 +264,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Description:** Show the "? for shortcuts" hint above the input.
   - **Default:** `true`
 
+- **`ui.compactToolOutput`** (boolean):
+  - **Description:** Display tool outputs (like directory listings and file
+    reads) in a compact, structured format.
+  - **Default:** `false`
+
 - **`ui.hideBanner`** (boolean):
   - **Description:** Hide the application banner
   - **Default:** `false`
@@ -344,8 +356,8 @@ their corresponding top-level category object in your `settings.json` file.
 
 - **`ui.loadingPhrases`** (enum):
   - **Description:** What to show while the model is working: tips, witty
-    comments, both, or nothing.
-  - **Default:** `"tips"`
+    comments, all, or off.
+  - **Default:** `"off"`
   - **Values:** `"tips"`, `"witty"`, `"all"`, `"off"`
 
 - **`ui.errorVerbosity`** (enum):
@@ -1232,7 +1244,8 @@ their corresponding top-level category object in your `settings.json` file.
   - **Requires restart:** Yes
 
 - **`agents.browser.visualModel`** (string):
-  - **Description:** Model override for the visual agent.
+  - **Description:** Model for the visual agent's analyze_screenshot tool. When
+    set, enables the tool.
   - **Default:** `undefined`
   - **Requires restart:** Yes
 
@@ -1555,7 +1568,7 @@ their corresponding top-level category object in your `settings.json` file.
 
 - **`advanced.autoConfigureMemory`** (boolean):
   - **Description:** Automatically configure Node.js memory limits
-  - **Default:** `false`
+  - **Default:** `true`
   - **Requires restart:** Yes
 
 - **`advanced.dnsResolutionOrder`** (string):
@@ -1577,26 +1590,9 @@ their corresponding top-level category object in your `settings.json` file.
 
 #### `experimental`
 
-- **`experimental.toolOutputMasking.enabled`** (boolean):
-  - **Description:** Enables tool output masking to save tokens.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
-- **`experimental.toolOutputMasking.toolProtectionThreshold`** (number):
-  - **Description:** Minimum number of tokens to protect from masking (most
-    recent tool outputs).
-  - **Default:** `50000`
-  - **Requires restart:** Yes
-
-- **`experimental.toolOutputMasking.minPrunableTokensThreshold`** (number):
-  - **Description:** Minimum prunable tokens required to trigger a masking pass.
-  - **Default:** `30000`
-  - **Requires restart:** Yes
-
-- **`experimental.toolOutputMasking.protectLatestTurn`** (boolean):
-  - **Description:** Ensures the absolute latest turn is never masked,
-    regardless of token count.
-  - **Default:** `true`
+- **`experimental.adk.agentSessionNoninteractiveEnabled`** (boolean):
+  - **Description:** Enable non-interactive agent sessions.
+  - **Default:** `false`
   - **Requires restart:** Yes
 
 - **`experimental.enableAgents`** (boolean):
@@ -1637,7 +1633,7 @@ their corresponding top-level category object in your `settings.json` file.
 
 - **`experimental.jitContext`** (boolean):
   - **Description:** Enable Just-In-Time (JIT) context loading.
-  - **Default:** `true`
+  - **Default:** `false`
   - **Requires restart:** Yes
 
 - **`experimental.useOSC52Paste`** (boolean):
@@ -1652,11 +1648,6 @@ their corresponding top-level category object in your `settings.json` file.
     configured to allow it).
   - **Default:** `false`
 
-- **`experimental.plan`** (boolean):
-  - **Description:** Enable Plan Mode.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 - **`experimental.taskTracker`** (boolean):
   - **Description:** Enable task tracker tools.
   - **Default:** `false`
@@ -1702,25 +1693,19 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
-- **`experimental.agentHistoryTruncation`** (boolean):
-  - **Description:** Enable truncation window logic for the Agent History
-    Provider.
+- **`experimental.powerUserProfile`** (boolean):
+  - **Description:** Enables continuous minimal GC near the max tokens limit
+    instead of a blocked backbuffer.
   - **Default:** `false`
   - **Requires restart:** Yes
 
-- **`experimental.agentHistoryTruncationThreshold`** (number):
-  - **Description:** The maximum number of messages before history is truncated.
-  - **Default:** `30`
+- **`experimental.generalistProfile`** (boolean):
+  - **Description:** Suitable for general coding and software development tasks.
+  - **Default:** `false`
   - **Requires restart:** Yes
 
-- **`experimental.agentHistoryRetainedMessages`** (number):
-  - **Description:** The number of recent messages to retain after truncation.
-  - **Default:** `15`
-  - **Requires restart:** Yes
-
-- **`experimental.agentHistorySummarization`** (boolean):
-  - **Description:** Enable summarization of truncated content via a small model
-    for the Agent History Provider.
+- **`experimental.contextManagement`** (boolean):
+  - **Description:** Enable logic for context management.
   - **Default:** `false`
   - **Requires restart:** Yes
 
@@ -1815,6 +1800,69 @@ their corresponding top-level category object in your `settings.json` file.
     prioritize available tools dynamically.
   - **Default:** `[]`
 
+#### `contextManagement`
+
+- **`contextManagement.historyWindow.maxTokens`** (number):
+  - **Description:** The number of tokens to allow before triggering
+    compression.
+  - **Default:** `150000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.historyWindow.retainedTokens`** (number):
+  - **Description:** The number of tokens to always retain.
+  - **Default:** `40000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.messageLimits.normalMaxTokens`** (number):
+  - **Description:** The target number of tokens to budget for a normal
+    conversation turn.
+  - **Default:** `2500`
+  - **Requires restart:** Yes
+
+- **`contextManagement.messageLimits.retainedMaxTokens`** (number):
+  - **Description:** The maximum number of tokens a single conversation turn can
+    consume before truncation.
+  - **Default:** `12000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.messageLimits.normalizationHeadRatio`** (number):
+  - **Description:** The ratio of tokens to retain from the beginning of a
+    truncated message (0.0 to 1.0).
+  - **Default:** `0.25`
+  - **Requires restart:** Yes
+
+- **`contextManagement.tools.distillation.maxOutputTokens`** (number):
+  - **Description:** Maximum tokens to show to the model when truncating large
+    tool outputs.
+  - **Default:** `10000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.tools.distillation.summarizationThresholdTokens`**
+  (number):
+  - **Description:** Threshold above which truncated tool outputs will be
+    summarized by an LLM.
+  - **Default:** `20000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.tools.outputMasking.protectionThresholdTokens`**
+  (number):
+  - **Description:** Minimum number of tokens to protect from masking (most
+    recent tool outputs).
+  - **Default:** `50000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.tools.outputMasking.minPrunableThresholdTokens`**
+  (number):
+  - **Description:** Minimum prunable tokens required to trigger a masking pass.
+  - **Default:** `30000`
+  - **Requires restart:** Yes
+
+- **`contextManagement.tools.outputMasking.protectLatestTurn`** (boolean):
+  - **Description:** Ensures the absolute latest turn is never masked,
+    regardless of token count.
+  - **Default:** `true`
+  - **Requires restart:** Yes
+
 #### `admin`
 
 - **`admin.secureModeEnabled`** (boolean):

docs/reference/keyboard-shortcuts.md

@@ -127,6 +127,13 @@ available combinations.
 | `background.unfocusList`    | Move focus from background shell list to Gemini.                   | `Tab`       |
 | `background.unfocusWarning` | Show warning when trying to move focus away from background shell. | `Tab`       |
 
+#### Extension Controls
+
+| Command            | Action                                      | Keys |
+| ------------------ | ------------------------------------------- | ---- |
+| `extension.update` | Update the current extension if available.  | `I`  |
+| `extension.link`   | Link the current extension to a local path. | `L`  |
+
 <!-- KEYBINDINGS-AUTOGEN:END -->
 
 ## Customizing Keybindings

docs/reference/policy-engine.md

@@ -29,13 +29,12 @@ To create your first policy:
     ```toml
     [[rule]]
     toolName = "run_shell_command"
-    commandPrefix = "git status"
-    decision = "allow"
+    commandPrefix = "rm -rf"
+    decision = "deny"
     priority = 100
     ```
 3.  **Run a command** that triggers the policy (e.g., ask Gemini CLI to
-    `git status`). The tool will now execute automatically without prompting for
-    confirmation.
+    `rm -rf /`). The tool will now be blocked automatically.
 
 ## Core concepts
 
@@ -143,25 +142,26 @@ engine transforms this into a final priority using the following formula:
 
 This system guarantees that:
 
-- Admin policies always override User, Workspace, and Default policies.
+- Admin policies always override User, Workspace, and Default policies (defined
+  in policy TOML files).
 - User policies override Workspace and Default policies.
 - Workspace policies override Default policies.
 - You can still order rules within a single tier with fine-grained control.
 
 For example:
 
-- A `priority: 50` rule in a Default policy file becomes `1.050`.
-- A `priority: 10` rule in a Workspace policy policy file becomes `2.010`.
-- A `priority: 100` rule in a User policy file becomes `3.100`.
-- A `priority: 20` rule in an Admin policy file becomes `4.020`.
+- A `priority: 50` rule in a Default policy TOML becomes `1.050`.
+- A `priority: 10` rule in a Workspace policy TOML becomes `2.010`.
+- A `priority: 100` rule in a User policy TOML becomes `3.100`.
+- A `priority: 20` rule in an Admin policy TOML becomes `4.020`.
 
 ### Approval modes
 
 Approval modes allow the policy engine to apply different sets of rules based on
-the CLI's operational mode. A rule can be associated with one or more modes
-(e.g., `yolo`, `autoEdit`, `plan`). The rule will only be active if the CLI is
-running in one of its specified modes. If a rule has no modes specified, it is
-always active.
+the CLI's operational mode. A rule in a TOML policy file can be associated with
+one or more modes (e.g., `yolo`, `autoEdit`, `plan`). The rule will only be
+active if the CLI is running in one of its specified modes. If a rule has no
+modes specified, it is always active.
 
 - `default`: The standard interactive mode where most write tools require
   confirmation.
@@ -179,8 +179,8 @@ outcome.
 
 A rule matches a tool call if all of its conditions are met:
 
-1.  **Tool name**: The `toolName` in the rule must match the name of the tool
-    being called.
+1.  **Tool name**: The `toolName` in the TOML rule must match the name of the
+    tool being called.
     - **Wildcards**: You can use wildcards like `*`, `mcp_server_*`, or
       `mcp_*_toolName` to match multiple tools. See [Tool Name](#tool-name) for
       details.
@@ -264,7 +264,7 @@ toolName = "run_shell_command"
 
 # (Optional) The name of a subagent. If provided, the rule only applies to tool
 # calls made by this specific subagent.
-subagent = "generalist"
+subagent = "codebase_investigator"
 
 # (Optional) The name of an MCP server. Can be combined with toolName
 # to form a composite FQN internally like "mcp_mcpName_toolName".
@@ -419,20 +419,6 @@ decision = "ask_user"
 priority = 10
 ```
 
-**4. Targeting a tool name across all servers**
-
-Use `mcpName = "*"` with a specific `toolName` to target that operation
-regardless of which server provides it.
-
-```toml
-# Allow the `search` tool across all connected MCP servers
-[[rule]]
-mcpName = "*"
-toolName = "search"
-decision = "allow"
-priority = 50
-```
-
 ## Default policies
 
 The Gemini CLI ships with a set of default policies to provide a safe

docs/reference/tools.md

@@ -115,10 +115,10 @@ each tool.
 
 ### Web
 
-| Tool                                          | Kind     | Description                                                                                                                                                                                                 |
-| :-------------------------------------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [`google_web_search`](../tools/web-search.md) | `Search` | Performs a Google Search to find up-to-date information.                                                                                                                                                    |
-| [`web_fetch`](../tools/web-fetch.md)          | `Fetch`  | Retrieves and processes content from specific URLs. **Warning:** This tool can access local and private network addresses (e.g., localhost), which may pose a security risk if used with untrusted prompts. |
+| Tool                                          | Kind     | Description                                                                                                                                                                                                                                                              |
+| :-------------------------------------------- | :------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [`google_web_search`](../tools/web-search.md) | `Search` | Performs a Google Search to find up-to-date information.                                                                                                                                                                                                                 |
+| [`web_fetch`](../tools/web-fetch.md)          | `Fetch`  | Retrieves and processes content from specific URLs. **Warning:** This tool can access local and private network addresses (e.g., localhost), which may pose a security risk if used with untrusted prompts. In Plan Mode, this tool requires explicit user confirmation. |
 
 ## Under the hood
 

docs/sidebar.json

@@ -138,12 +138,10 @@
           { "label": "Plan mode", "slug": "docs/cli/plan-mode" },
           {
             "label": "Subagents",
-            "badge": "🔬",
             "slug": "docs/core/subagents"
           },
           {
             "label": "Remote subagents",
-            "badge": "🔬",
             "slug": "docs/core/remote-agents"
           },
           { "label": "Rewind", "slug": "docs/cli/rewind" },

docs/tools/planning.md

@@ -32,7 +32,9 @@ and planning.
 ## 2. `exit_plan_mode` (ExitPlanMode)
 
 `exit_plan_mode` signals that the planning phase is complete. It presents the
-finalized plan to the user and requests approval to start the implementation.
+finalized plan to the user and requests formal approval to start the
+implementation. The agent MUST reach an informal agreement with the user in the
+chat regarding the proposed strategy BEFORE calling this tool.
 
 - **Tool name:** `exit_plan_mode`
 - **Display name:** Exit Plan Mode
@@ -44,7 +46,7 @@ finalized plan to the user and requests approval to start the implementation.
 - **Behavior:**
   - Validates that the `plan_path` is within the allowed directory and that the
     file exists and has content.
-  - Presents the plan to the user for review.
+  - Presents the plan to the user for formal review.
   - If the user approves the plan:
     - Switches the CLI's approval mode to the user's chosen approval mode (
       `DEFAULT` or `AUTO_EDIT`).
@@ -56,5 +58,5 @@ finalized plan to the user and requests approval to start the implementation.
   - On approval: A message indicating the plan was approved and the new approval
     mode.
   - On rejection: A message containing the user's feedback.
-- **Confirmation:** Yes. Shows the finalized plan and asks for user approval to
-  proceed with implementation.
+- **Confirmation:** Yes. Shows the finalized plan and asks for user formal
+  approval to proceed with implementation.

docs/tools/web-fetch.md

@@ -17,6 +17,9 @@ specific operations like summarization or extraction.
 ## Technical behavior
 
 - **Confirmation:** Triggers a confirmation dialog showing the converted URLs.
+- **Plan Mode:** In [Plan Mode](../cli/plan-mode.md), `web_fetch` is available
+  but always requires explicit user confirmation (`ask_user`) due to security
+  implications of accessing external or private network addresses.
 - **Processing:** Uses the Gemini API's `urlContext` for retrieval.
 - **Fallback:** If API access fails, the tool attempts to fetch raw content
   directly from your local machine.

esbuild.config.js

@@ -13,7 +13,7 @@ import { wasmLoader } from 'esbuild-plugin-wasm';
 let esbuild;
 try {
   esbuild = (await import('esbuild')).default;
-} catch (_error) {
+} catch {
   console.error('esbuild not available - cannot build bundle');
   process.exit(1);
 }

eslint.config.js

@@ -41,6 +41,11 @@ const commonRestrictedSyntaxRules = [
     message:
       'Do not use typeof to check object properties. Define a TypeScript interface and a type guard function instead.',
   },
+  {
+    selector: 'CatchClause > Identifier[name=/^_/]',
+    message:
+      'Do not use underscored identifiers in catch blocks. If the error is unused, use "catch {}". If it is used, remove the underscore.',
+  },
 ];
 
 export default tseslint.config(
@@ -129,7 +134,7 @@ export default tseslint.config(
         {
           argsIgnorePattern: '^_',
           varsIgnorePattern: '^_',
-          caughtErrorsIgnorePattern: '^_',
+          caughtErrors: 'all',
         },
       ],
       // Prevent async errors from bypassing catch handlers
@@ -336,7 +341,7 @@ export default tseslint.config(
         {
           argsIgnorePattern: '^_',
           varsIgnorePattern: '^_',
-          caughtErrorsIgnorePattern: '^_',
+          caughtErrors: 'all',
         },
       ],
     },
@@ -360,7 +365,7 @@ export default tseslint.config(
         {
           argsIgnorePattern: '^_',
           varsIgnorePattern: '^_',
-          caughtErrorsIgnorePattern: '^_',
+          caughtErrors: 'all',
         },
       ],
     },
@@ -422,7 +427,7 @@ export default tseslint.config(
         {
           argsIgnorePattern: '^_',
           varsIgnorePattern: '^_',
-          caughtErrorsIgnorePattern: '^_',
+          caughtErrors: 'all',
         },
       ],
     },

evals/README.md

@@ -212,6 +212,56 @@ The nightly workflow executes the full evaluation suite multiple times
 (currently 3 attempts) to account for non-determinism. These results are
 aggregated into a **Nightly Summary** attached to the workflow run.
 
+## Regression Check Scripts
+
+The project includes several scripts to automate high-signal regression checking
+in Pull Requests. These can also be run locally for debugging.
+
+- **`scripts/get_trustworthy_evals.js`**: Analyzes nightly history to identify
+  stable tests (80%+ aggregate pass rate).
+- **`scripts/run_regression_check.js`**: Runs a specific set of tests using the
+  "Best-of-4" logic and "Dynamic Baseline Verification".
+- **`scripts/run_eval_regression.js`**: The main orchestrator that loops through
+  models and generates the final PR report.
+
+### Running Regression Checks Locally
+
+You can simulate the PR regression check locally to verify your changes before
+pushing:
+
+```bash
+# Run the full regression loop for a specific model
+MODEL_LIST=gemini-3-flash-preview node scripts/run_eval_regression.js
+```
+
+To debug a specific failing test with the same logic used in CI:
+
+```bash
+# 1. Get the Vitest pattern for trustworthy tests
+OUTPUT=$(node scripts/get_trustworthy_evals.js "gemini-3-flash-preview")
+
+# 2. Run the regression logic for those tests
+node scripts/run_regression_check.js "gemini-3-flash-preview" "$OUTPUT"
+```
+
+### The Regression Quality Bar
+
+Because LLMs are non-deterministic, the PR regression check uses a high-signal
+probabilistic approach rather than a 100% pass requirement:
+
+1.  **Trustworthiness (60/80 Filter):** Only tests with a proven track record
+    are run. A test must score at least **60% (2/3)** every single night and
+    maintain an **80% aggregate** pass rate over the last 6 days.
+2.  **The 50% Pass Rule:** In a PR, a test is considered a **Pass** if the model
+    correctly performs the behavior at least half the time (**2 successes** out
+    of up to 4 attempts).
+3.  **Dynamic Baseline Verification:** If a test fails in a PR (e.g., 0/3), the
+    system automatically checks the `main` branch. If it fails there too, it is
+    marked as **Pre-existing** and cleared for the PR, ensuring you are only
+    blocked by regressions caused by your specific changes.
+
+## Fixing Evaluations
+
 #### How to interpret the report:
 
 - **Pass Rate (%)**: Each cell represents the percentage of successful runs for

evals/background_processes.eval.ts

@@ -0,0 +1,77 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+import fs from 'node:fs';
+import path from 'node:path';
+
+describe('Background Process Monitoring', () => {
+  evalTest('USUALLY_PASSES', {
+    name: 'should naturally use read output tool to find token',
+    prompt:
+      "Run the script using 'bash generate_token.sh'. It will emit a token after a short delay and continue running. Find the token and tell me what it is.",
+    files: {
+      'generate_token.sh': `#!/bin/bash
+sleep 2
+echo "TOKEN=xyz123"
+sleep 100
+`,
+    },
+    setup: async (rig) => {
+      // Create .gemini directory to avoid file system error in test rig
+      if (rig.homeDir) {
+        const geminiDir = path.join(rig.homeDir, '.gemini');
+        fs.mkdirSync(geminiDir, { recursive: true });
+      }
+    },
+    assert: async (rig, result) => {
+      const toolCalls = rig.readToolLogs();
+
+      // Check if read_background_output was called
+      const hasReadCall = toolCalls.some(
+        (call) => call.toolRequest.name === 'read_background_output',
+      );
+
+      expect(
+        hasReadCall,
+        'Expected agent to call read_background_output to find the token',
+      ).toBe(true);
+
+      // Verify that the agent found the correct token
+      expect(
+        result.includes('xyz123'),
+        `Expected agent to find the token xyz123. Agent output: ${result}`,
+      ).toBe(true);
+    },
+  });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'should naturally use list tool to verify multiple processes',
+    prompt:
+      "Start three background processes that run 'sleep 100', 'sleep 200', and 'sleep 300' respectively. Verify that all three are currently running.",
+    setup: async (rig) => {
+      // Create .gemini directory to avoid file system error in test rig
+      if (rig.homeDir) {
+        const geminiDir = path.join(rig.homeDir, '.gemini');
+        fs.mkdirSync(geminiDir, { recursive: true });
+      }
+    },
+    assert: async (rig, result) => {
+      const toolCalls = rig.readToolLogs();
+
+      // Check if list_background_processes was called
+      const hasListCall = toolCalls.some(
+        (call) => call.toolRequest.name === 'list_background_processes',
+      );
+
+      expect(
+        hasListCall,
+        'Expected agent to call list_background_processes',
+      ).toBe(true);
+    },
+  });
+});

evals/plan_mode.eval.ts

@@ -15,7 +15,9 @@ import {
 describe('plan_mode', () => {
   const TEST_PREFIX = 'Plan Mode: ';
   const settings = {
-    experimental: { plan: true },
+    general: {
+      plan: { enabled: true },
+    },
   };
 
   const getWriteTargets = (logs: any[]) =>
@@ -172,7 +174,8 @@ describe('plan_mode', () => {
     params: {
       settings,
     },
-    prompt: 'Create a plan for a new login feature.',
+    prompt:
+      'I agree with the strategy to use a JWT-based login. Create a plan for a new login feature.',
     assert: async (rig, result) => {
       await rig.waitForTelemetryReady();
       const toolLogs = rig.readToolLogs();
@@ -209,7 +212,7 @@ describe('plan_mode', () => {
         'import { sum } from "./mathUtils";\nconsole.log(sum(1, 2));',
     },
     prompt:
-      'I want to refactor our math utilities. Move the `sum` function from `src/mathUtils.ts` to a new file `src/basicMath.ts` and update `src/main.ts` to use the new file. Please create a detailed implementation plan first, then execute it.',
+      'I want to refactor our math utilities. I agree with the strategy to move the `sum` function from `src/mathUtils.ts` to a new file `src/basicMath.ts` and update `src/main.ts`. Please create a detailed implementation plan first, then execute it.',
     assert: async (rig, result) => {
       const enterPlanCalled = await rig.waitForToolCall('enter_plan_mode');
       expect(
@@ -281,4 +284,80 @@ describe('plan_mode', () => {
       assertModelHasOutput(result);
     },
   });
+
+  evalTest('ALWAYS_PASSES', {
+    name: 'should transition from plan mode to normal execution and create a plan file from scratch',
+    params: {
+      settings,
+    },
+    prompt:
+      'Enter plan mode and plan to create a new module called foo. The plan should be saved as foo-plan.md. Then, exit plan mode.',
+    assert: async (rig, result) => {
+      const enterPlanCalled = await rig.waitForToolCall('enter_plan_mode');
+      expect(
+        enterPlanCalled,
+        'Expected enter_plan_mode tool to be called',
+      ).toBe(true);
+
+      const exitPlanCalled = await rig.waitForToolCall('exit_plan_mode');
+      expect(exitPlanCalled, 'Expected exit_plan_mode tool to be called').toBe(
+        true,
+      );
+
+      await rig.waitForTelemetryReady();
+      const toolLogs = rig.readToolLogs();
+
+      // Check if the plan file was written successfully
+      const planWrite = toolLogs.find(
+        (log) =>
+          log.toolRequest.name === 'write_file' &&
+          log.toolRequest.args.includes('foo-plan.md'),
+      );
+
+      expect(
+        planWrite,
+        'Expected write_file to be called for foo-plan.md',
+      ).toBeDefined();
+
+      expect(
+        planWrite?.toolRequest.success,
+        `Expected write_file to succeed, but got error: ${planWrite?.toolRequest.error}`,
+      ).toBe(true);
+
+      assertModelHasOutput(result);
+    },
+  });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'should not exit plan mode or draft before informal agreement',
+    approvalMode: ApprovalMode.PLAN,
+    params: {
+      settings,
+    },
+    prompt: 'I need to build a new login feature. Please plan it.',
+    assert: async (rig, result) => {
+      await rig.waitForTelemetryReady();
+      const toolLogs = rig.readToolLogs();
+
+      const exitPlanCall = toolLogs.find(
+        (log) => log.toolRequest.name === 'exit_plan_mode',
+      );
+      expect(
+        exitPlanCall,
+        'Should NOT call exit_plan_mode before informal agreement',
+      ).toBeUndefined();
+
+      const planWrite = toolLogs.find(
+        (log) =>
+          log.toolRequest.name === 'write_file' &&
+          log.toolRequest.args.includes('/plans/'),
+      );
+      expect(
+        planWrite,
+        'Should NOT draft the plan file before informal agreement',
+      ).toBeUndefined();
+
+      assertModelHasOutput(result);
+    },
+  });
 });

evals/tracker.eval.ts

@@ -113,4 +113,21 @@ describe('tracker_mode', () => {
       assertModelHasOutput(result);
     },
   });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'should correctly identify the task tracker storage location from the system prompt',
+    params: {
+      settings: { experimental: { taskTracker: true } },
+    },
+    prompt:
+      'Where is my task tracker storage located? Please provide the absolute path in your response.',
+    assert: async (rig, result) => {
+      // The rig sets GEMINI_CLI_HOME to rig.homeDir
+      const homeDir = rig.homeDir!;
+      // The response should contain the dynamic path which includes the home directory
+      // and follows the .gemini/tmp/.../tracker structure.
+      expect(result).toContain(homeDir);
+      expect(result).toMatch(/\.gemini\/tmp\/.*\/tracker/);
+    },
+  });
 });

evals/update_topic.eval.ts

@@ -0,0 +1,116 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('update_topic_behavior', () => {
+  // Constants for tool names and params for robustness
+  const UPDATE_TOPIC_TOOL_NAME = 'update_topic';
+
+  /**
+   * Verifies the desired behavior of the update_topic tool. update_topic is used by the
+   * agent to share periodic, concise updates about what the agent is working on, independent
+   * of the regular model output and/or thoughts. This tool is expected to be called at least
+   * at the start and end of the session, and typically at least once in the middle, but no
+   * more than 1/4 turns.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'update_topic should be used at start, end and middle for complex tasks',
+    prompt: `Create a simple users REST API using Express. 
+1. Initialize a new npm project and install express.
+2. Create src/app.ts as the main entry point.
+3. Create src/routes/userRoutes.ts for user routes.
+4. Create src/controllers/userController.ts for user logic.
+5. Implement GET /users, POST /users, and GET /users/:id using an in-memory array.
+6. Add a 'start' script to package.json.
+7. Finally, run a quick grep to verify the routes are in src/app.ts.`,
+    files: {
+      'package.json': JSON.stringify(
+        {
+          name: 'users-api',
+          version: '1.0.0',
+          private: true,
+        },
+        null,
+        2,
+      ),
+      '.gemini/settings.json': JSON.stringify({
+        experimental: {
+          topicUpdateNarration: true,
+        },
+      }),
+    },
+    assert: async (rig, result) => {
+      const toolLogs = rig.readToolLogs();
+      const topicCalls = toolLogs.filter(
+        (l) => l.toolRequest.name === UPDATE_TOPIC_TOOL_NAME,
+      );
+
+      // 1. Assert that update_topic is called at least 3 times (start, middle, end)
+      expect(
+        topicCalls.length,
+        `Expected at least 3 update_topic calls, but found ${topicCalls.length}`,
+      ).toBeGreaterThanOrEqual(3);
+
+      // 2. Assert update_topic is called at the very beginning (first tool call)
+      expect(
+        toolLogs[0].toolRequest.name,
+        'First tool call should be update_topic',
+      ).toBe(UPDATE_TOPIC_TOOL_NAME);
+
+      // 3. Assert update_topic is called near the end
+      const lastTopicCallIndex = toolLogs
+        .map((l) => l.toolRequest.name)
+        .lastIndexOf(UPDATE_TOPIC_TOOL_NAME);
+      expect(
+        lastTopicCallIndex,
+        'Expected update_topic to be used near the end of the task',
+      ).toBeGreaterThanOrEqual(toolLogs.length * 0.7);
+
+      // 4. Assert there is at least one update_topic call in the middle (between start and end phases)
+      const middleTopicCalls = topicCalls.slice(1, -1);
+
+      expect(
+        middleTopicCalls.length,
+        'Expected at least one update_topic call in the middle of the task',
+      ).toBeGreaterThanOrEqual(1);
+
+      // 5. Turn Ratio Assertion: update_topic should be <= 1/2 of total turns.
+      // We only enforce this for tasks that take more than 5 turns, as shorter tasks
+      // naturally have a higher ratio when following the "start, middle, end" rule.
+      const uniquePromptIds = new Set(
+        toolLogs
+          .map((l) => l.toolRequest.prompt_id)
+          .filter((id) => id !== undefined),
+      );
+      const totalTurns = uniquePromptIds.size;
+
+      if (totalTurns > 5) {
+        const topicTurns = new Set(
+          topicCalls
+            .map((l) => l.toolRequest.prompt_id)
+            .filter((id) => id !== undefined),
+        );
+        const topicTurnCount = topicTurns.size;
+
+        const ratio = topicTurnCount / totalTurns;
+
+        expect(
+          ratio,
+          `update_topic was used in ${topicTurnCount} out of ${totalTurns} turns (${(ratio * 100).toFixed(1)}%). Expected <= 50%.`,
+        ).toBeLessThanOrEqual(0.5);
+
+        // Ideal ratio is closer to 1/5 (20%). We log high usage as a warning.
+        if (ratio > 0.25) {
+          console.warn(
+            `[Efficiency Warning] update_topic usage is high: ${(ratio * 100).toFixed(1)}% (Goal: ~20%)`,
+          );
+        }
+      }
+    },
+  });
+});

integration-tests/api-resilience.responses

@@ -1 +1 @@
-{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Part 1. "}],"role":"model"},"index":0}]},{"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":10,"totalTokenCount":110}},{"candidates":[{"content":{"parts":[{"text":"Part 2."}],"role":"model"},"index":0}],"finishReason":"STOP"}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Part 1. "}],"role":"model"},"index":0}]},{"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":10,"totalTokenCount":110}},{"candidates":[{"content":{"parts":[{"text":"Part 2."}],"role":"model"},"index":0,"finishReason":"STOP"}]}]}

integration-tests/browser-agent-localhost.dynamic.responses

@@ -0,0 +1,6 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll check the dynamic content page on the localhost server."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to http://127.0.0.1:18923/dynamic.html, wait for the dynamic content to load, then capture the accessibility tree and report what content appeared"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/dynamic.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"wait_for","args":{"selector":"#dynamic-content","state":"visible","timeout":5000}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":25,"totalTokenCount":175}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":180,"candidatesTokenCount":15,"totalTokenCount":195}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Dynamic content loaded successfully. Found heading 'Content Loaded', message 'This content was loaded dynamically via JavaScript.', and a list with items: Item Alpha, Item Beta, Item Gamma."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The dynamic content page loaded successfully:\n\n- **Heading**: Content Loaded\n- **Message**: This content was loaded dynamically via JavaScript\n- **Items**: Item Alpha, Item Beta, Item Gamma\n\nThe JavaScript-rendered content appeared after the initial page load, replacing the 'Loading...' indicator."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":60,"totalTokenCount":260}}]}

integration-tests/browser-agent-localhost.form.responses

@@ -0,0 +1,9 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll fill out the contact form on the localhost server."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to http://127.0.0.1:18923/form.html, fill in the name field with 'Test User', the email field with 'test@example.com', the message field with 'Hello World', and submit the form"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/form.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#name","value":"Test User"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":25,"totalTokenCount":175}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#email","value":"test@example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":180,"candidatesTokenCount":25,"totalTokenCount":205}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#message","value":"Hello World"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":210,"candidatesTokenCount":25,"totalTokenCount":235}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"selector":"#submit-btn"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":240,"candidatesTokenCount":20,"totalTokenCount":260}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":270,"candidatesTokenCount":15,"totalTokenCount":285}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully filled and submitted the contact form. Navigated to form-result.html which shows 'Form Submitted Successfully'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":40,"totalTokenCount":340}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've successfully filled out and submitted the contact form:\n\n- **Name**: Test User\n- **Email**: test@example.com\n- **Message**: Hello World\n\nAfter submission, the page navigated to the result page showing 'Form Submitted Successfully'."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":60,"totalTokenCount":360}}]}

integration-tests/browser-agent-localhost.multistep.responses

@@ -0,0 +1,9 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll go through the multi-step flow on the localhost server."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to http://127.0.0.1:18923/multi-step/step1.html, fill in 'testuser' as the username, click Next, then on step 2 select 'Option B' and click Finish. Report the final result page content."}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/multi-step/step1.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#username","value":"testuser"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":25,"totalTokenCount":175}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"selector":"#next-btn"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":180,"candidatesTokenCount":20,"totalTokenCount":200}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":210,"candidatesTokenCount":15,"totalTokenCount":225}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"selector":"#finish-btn"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":240,"candidatesTokenCount":20,"totalTokenCount":260}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":270,"candidatesTokenCount":15,"totalTokenCount":285}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Completed all steps. Step 1: entered username 'testuser'. Step 2: selected default option. Final result page shows 'Multi-Step Complete' with '✓ Complete' status badge."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":40,"totalTokenCount":340}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've completed the multi-step flow:\n\n1. **Step 1**: Entered 'testuser' as username and clicked Next\n2. **Step 2**: Confirmed selection and clicked Finish\n3. **Result**: Final page shows 'Multi-Step Complete' with a '✓ Complete' status badge\n\nAll steps were successfully navigated."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":60,"totalTokenCount":360}}]}

integration-tests/browser-agent-localhost.navigate.responses

@@ -0,0 +1,5 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll navigate to the localhost page and read its content using the browser agent."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to http://127.0.0.1:18923/index.html and tell me the page title and list all links on the page"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/index.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is 'Test Fixture - Home'. Found 3 links: Contact Form (/form.html), Multi-Step Flow (/multi-step/step1.html), Dynamic Content (/dynamic.html)."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The localhost test fixture page has:\n\n**Title**: Test Fixture - Home\n\n**Links**:\n1. Contact Form (form.html)\n2. Multi-Step Flow (multi-step/step1.html)\n3. Dynamic Content (dynamic.html)\n\nThe page also has a heading 'Test Fixture Home Page' and footer content."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":60,"totalTokenCount":260}}]}

integration-tests/browser-agent-localhost.screenshot.responses

@@ -0,0 +1,5 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll take a screenshot of the localhost test page."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to http://127.0.0.1:18923/index.html and take a screenshot of the page"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":35,"totalTokenCount":135}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/index.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_screenshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":15,"totalTokenCount":165}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Screenshot captured of the localhost test fixture home page showing the heading, navigation links, and footer.","data":{"screenshotTaken":true}}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've captured a screenshot of the localhost test fixture page. The screenshot shows the 'Test Fixture Home Page' heading with navigation links to the Contact Form, Multi-Step Flow, and Dynamic Content pages, along with the footer section."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":50,"totalTokenCount":250}}]}

integration-tests/browser-agent-localhost.test.ts

@@ -0,0 +1,161 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig, assertModelHasOutput } from './test-helper.js';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+describe('browser-agent-localhost', () => {
+  let rig: TestRig;
+
+  const browserSettings = {
+    agents: {
+      overrides: {
+        browser_agent: {
+          enabled: true,
+        },
+      },
+      browser: {
+        headless: true,
+        sessionMode: 'isolated' as const,
+      },
+    },
+  };
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => {
+    await rig.cleanup();
+  });
+
+  it('should navigate to localhost fixture and read page content', async () => {
+    rig.setup('localhost-navigate', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent-localhost.navigate.responses',
+      ),
+      settings: browserSettings,
+    });
+
+    const result = await rig.run({
+      args: 'Navigate to http://127.0.0.1:18923/index.html and tell me the page title and list all links.',
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserAgentCall = toolLogs.find(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(
+      browserAgentCall,
+      'Expected browser_agent to be called',
+    ).toBeDefined();
+  });
+
+  it('should fill out and submit a form on localhost', async () => {
+    rig.setup('localhost-form', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent-localhost.form.responses',
+      ),
+      settings: browserSettings,
+    });
+
+    const result = await rig.run({
+      args: "Navigate to http://127.0.0.1:18923/form.html, fill in name='Test User', email='test@example.com', message='Hello World', and submit the form.",
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserAgentCall = toolLogs.find(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(
+      browserAgentCall,
+      'Expected browser_agent to be called',
+    ).toBeDefined();
+  });
+
+  it('should navigate through a multi-step flow', async () => {
+    rig.setup('localhost-multistep', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent-localhost.multistep.responses',
+      ),
+      settings: browserSettings,
+    });
+
+    const result = await rig.run({
+      args: "Go to http://127.0.0.1:18923/multi-step/step1.html, fill in 'testuser' as username, click Next, then click Finish on step 2. Report the result.",
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserAgentCall = toolLogs.find(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(
+      browserAgentCall,
+      'Expected browser_agent to be called',
+    ).toBeDefined();
+  });
+
+  it('should handle dynamically loaded content', async () => {
+    rig.setup('localhost-dynamic', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent-localhost.dynamic.responses',
+      ),
+      settings: browserSettings,
+    });
+
+    const result = await rig.run({
+      args: 'Navigate to http://127.0.0.1:18923/dynamic.html, wait for content to load, and tell me what items appear.',
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserAgentCall = toolLogs.find(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(
+      browserAgentCall,
+      'Expected browser_agent to be called',
+    ).toBeDefined();
+  });
+
+  it('should take a screenshot of localhost page', async () => {
+    rig.setup('localhost-screenshot', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent-localhost.screenshot.responses',
+      ),
+      settings: browserSettings,
+    });
+
+    const result = await rig.run({
+      args: 'Navigate to http://127.0.0.1:18923/index.html and take a screenshot.',
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserCalls = toolLogs.filter(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(browserCalls.length).toBeGreaterThan(0);
+  });
+});

integration-tests/browser-agent.cleanup.responses

@@ -1,4 +1,5 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll open https://example.com and check the page title for you."},{"functionCall":{"name":"browser_agent","args":{"task":"Open https://example.com and get the page title"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":35,"totalTokenCount":135}}]}
-{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I have opened the page and the title is 'Example Domain'."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
-{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The task is complete. The page title is 'Example Domain'."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":20,"totalTokenCount":320}}]}
-{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Done."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":400,"candidatesTokenCount":5,"totalTokenCount":405}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"The page title is 'Example Domain'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I have opened the page and the title is 'Example Domain'. The browser session has been cleaned up successfully."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}

integration-tests/browser-agent.interaction.responses

@@ -1,2 +1,5 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll navigate to https://example.com and analyze the links on the page."},{"functionCall":{"name":"browser_agent","args":{"task":"Go to https://example.com and find all links on the page, then describe them"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Found one link on https://example.com: 'More information...' linking to the IANA website for details about reserved domains."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"After analyzing https://example.com, I found the following links:\n\n1. **\"More information...\"** - This is the main link on the page that points to the IANA (Internet Assigned Numbers Authority) website for more details about reserved domains.\n\nThe page is quite minimal with just this single informational link, which is typical for example domains used in documentation."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":70,"totalTokenCount":270}}]}

integration-tests/browser-agent.navigate-snapshot.responses

@@ -1,2 +1,5 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll help you open https://example.com and analyze the page. Let me use the browser agent to navigate and capture the page information."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to https://example.com and capture the accessibility tree to get the page title and main content"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":30,"totalTokenCount":130}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to https://example.com. The page title is 'Example Domain' and the main content states: 'This domain is for use in illustrative examples in documents.'"}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Based on the browser analysis of https://example.com:\n\n**Page Title**: Example Domain\n\n**Main Content**: The page contains a simple heading \"Example Domain\" and explanatory text stating \"This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.\"\n\nThe page has a clean, minimal layout typical of placeholder domains used for documentation and examples."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":80,"totalTokenCount":280}}]}

integration-tests/browser-agent.screenshot.responses

@@ -1,2 +1,5 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll navigate to https://example.com and take a screenshot for you."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to https://example.com and take a screenshot of the page"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_screenshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to https://example.com and captured a screenshot. The page shows the Example Domain header with explanatory text."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've successfully navigated to https://example.com and captured a screenshot. The page shows the familiar \"Example Domain\" header with explanatory text below it. The screenshot captures the clean, minimal layout of this demonstration website."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":50,"totalTokenCount":250}}]}

integration-tests/browser-agent.sequential.responses

@@ -1,2 +1,6 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll help you navigate to https://example.com and perform both operations - capturing the accessibility tree and taking a screenshot."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to https://example.com, take a snapshot of the accessibility tree, then take a screenshot"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":45,"totalTokenCount":145}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_screenshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":20,"totalTokenCount":220}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to https://example.com, captured accessibility tree snapshot and took a screenshot. Page title is 'Example Domain'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":250,"candidatesTokenCount":40,"totalTokenCount":290}}]}
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've successfully completed both operations on https://example.com:\n\n**Accessibility Tree Snapshot**: The page has a clear structure with the main heading \"Example Domain\" and descriptive text about the domain's purpose for documentation examples.\n\n**Screenshot**: Captured a visual representation of the page showing the clean, minimal layout with the heading and explanatory text.\n\nBoth the accessibility data and visual screenshot confirm this is the standard example domain page used for documentation purposes."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":80,"totalTokenCount":280}}]}

integration-tests/browser-agent.test.ts

@@ -77,7 +77,12 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
       ),
       settings: {
         agents: {
-          browser_agent: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
             headless: true,
             sessionMode: 'isolated',
           },
@@ -106,7 +111,12 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
       fakeResponsesPath: join(__dirname, 'browser-agent.screenshot.responses'),
       settings: {
         agents: {
-          browser_agent: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
             headless: true,
             sessionMode: 'isolated',
           },
@@ -132,7 +142,12 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
       fakeResponsesPath: join(__dirname, 'browser-agent.interaction.responses'),
       settings: {
         agents: {
-          browser_agent: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
             headless: true,
             sessionMode: 'isolated',
           },
@@ -161,7 +176,12 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
       fakeResponsesPath: join(__dirname, 'browser-agent.cleanup.responses'),
       settings: {
         agents: {
-          browser_agent: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
             headless: true,
             sessionMode: 'isolated',
           },
@@ -182,7 +202,12 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
       fakeResponsesPath: join(__dirname, 'browser-agent.sequential.responses'),
       settings: {
         agents: {
-          browser_agent: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
             headless: true,
             sessionMode: 'isolated',
           },
@@ -212,7 +237,12 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
       ),
       settings: {
         agents: {
-          browser_agent: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
             headless: true,
             sessionMode: 'isolated',
           },

integration-tests/browser-policy.test.ts

@@ -10,8 +10,13 @@ import { dirname, join } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { execSync } from 'node:child_process';
 import { existsSync, writeFileSync, readFileSync, mkdirSync } from 'node:fs';
+import { env } from 'node:process';
 import stripAnsi from 'strip-ansi';
 
+// Browser agent Chrome DevTools MCP connection is flaky in Docker sandbox.
+// See: https://github.com/google-gemini/gemini-cli/issues/24382
+const isDockerSandbox = env['GEMINI_SANDBOX'] === 'docker';
+
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = dirname(__filename);
 
@@ -59,122 +64,146 @@ describe.skipIf(!chromeAvailable)('browser-policy', () => {
     await rig.cleanup();
   });
 
-  it('should skip confirmation when "Allow all server tools for this session" is chosen', async () => {
-    rig.setup('browser-policy-skip-confirmation', {
-      fakeResponsesPath: join(__dirname, 'browser-policy.responses'),
-      settings: {
-        agents: {
-          overrides: {
-            browser_agent: {
-              enabled: true,
+  it.skipIf(isDockerSandbox)(
+    'should skip confirmation when "Allow all server tools for this session" is chosen',
+    async () => {
+      rig.setup('browser-policy-skip-confirmation', {
+        fakeResponsesPath: join(__dirname, 'browser-policy.responses'),
+        settings: {
+          agents: {
+            overrides: {
+              browser_agent: {
+                enabled: true,
+              },
+            },
+            browser: {
+              headless: true,
+              sessionMode: 'isolated',
+              allowedDomains: ['example.com'],
             },
           },
-          browser: {
-            headless: true,
-            sessionMode: 'isolated',
-            allowedDomains: ['example.com'],
-          },
         },
-      },
-    });
+      });
 
-    // Manually trust the folder to avoid the dialog and enable option 3
-    const geminiDir = join(rig.homeDir!, '.gemini');
-    mkdirSync(geminiDir, { recursive: true });
+      // Manually trust the folder to avoid the dialog and enable option 3
+      const geminiDir = join(rig.homeDir!, '.gemini');
+      mkdirSync(geminiDir, { recursive: true });
 
-    // Write to trustedFolders.json
-    const trustedFoldersPath = join(geminiDir, 'trustedFolders.json');
-    const trustedFolders = {
-      [rig.testDir!]: 'TRUST_FOLDER',
-    };
-    writeFileSync(trustedFoldersPath, JSON.stringify(trustedFolders, null, 2));
+      // Write to trustedFolders.json
+      const trustedFoldersPath = join(geminiDir, 'trustedFolders.json');
+      const trustedFolders = {
+        [rig.testDir!]: 'TRUST_FOLDER',
+      };
+      writeFileSync(
+        trustedFoldersPath,
+        JSON.stringify(trustedFolders, null, 2),
+      );
 
-    // Force confirmation for browser agent.
-    // NOTE: We don't force confirm browser tools here because "Allow all server tools"
-    // adds a rule with ALWAYS_ALLOW_PRIORITY (3.9x) which would be overshadowed by
-    // a rule in the user tier (4.x) like the one from this TOML.
-    // By removing the explicit mcp rule, the first MCP tool will still prompt
-    // due to default approvalMode = 'default', and then "Allow all" will correctly
-    // bypass subsequent tools.
-    const policyFile = join(rig.testDir!, 'force-confirm.toml');
-    writeFileSync(
-      policyFile,
-      `
+      // Force confirmation for browser agent.
+      // NOTE: We don't force confirm browser tools here because "Allow all server tools"
+      // adds a rule with ALWAYS_ALLOW_PRIORITY (3.9x) which would be overshadowed by
+      // a rule in the user tier (4.x) like the one from this TOML.
+      // By removing the explicit mcp rule, the first MCP tool will still prompt
+      // due to default approvalMode = 'default', and then "Allow all" will correctly
+      // bypass subsequent tools.
+      const policyFile = join(rig.testDir!, 'force-confirm.toml');
+      writeFileSync(
+        policyFile,
+        `
 [[rule]]
 name = "Force confirm browser_agent"
 toolName = "browser_agent"
 decision = "ask_user"
 priority = 200
 `,
-    );
+      );
 
-    // Update settings.json in both project and home directories to point to the policy file
-    for (const baseDir of [rig.testDir!, rig.homeDir!]) {
-      const settingsPath = join(baseDir, '.gemini', 'settings.json');
-      if (existsSync(settingsPath)) {
-        const settings = JSON.parse(readFileSync(settingsPath, 'utf-8'));
-        settings.policyPaths = [policyFile];
-        // Ensure folder trust is enabled
-        settings.security = settings.security || {};
-        settings.security.folderTrust = settings.security.folderTrust || {};
-        settings.security.folderTrust.enabled = true;
-        writeFileSync(settingsPath, JSON.stringify(settings, null, 2));
+      // Update settings.json in both project and home directories to point to the policy file
+      for (const baseDir of [rig.testDir!, rig.homeDir!]) {
+        const settingsPath = join(baseDir, '.gemini', 'settings.json');
+        if (existsSync(settingsPath)) {
+          const settings = JSON.parse(readFileSync(settingsPath, 'utf-8'));
+          settings.policyPaths = [policyFile];
+          // Ensure folder trust is enabled
+          settings.security = settings.security || {};
+          settings.security.folderTrust = settings.security.folderTrust || {};
+          settings.security.folderTrust.enabled = true;
+          writeFileSync(settingsPath, JSON.stringify(settings, null, 2));
+        }
       }
-    }
 
-    const run = await rig.runInteractive({
-      approvalMode: 'default',
-      env: {
-        GEMINI_CLI_INTEGRATION_TEST: 'true',
-      },
-    });
+      const run = await rig.runInteractive({
+        approvalMode: 'default',
+        env: {
+          GEMINI_CLI_INTEGRATION_TEST: 'true',
+        },
+      });
 
-    await run.sendKeys(
-      'Open https://example.com and check if there is a heading\r',
-    );
-    await run.sendKeys('\r');
+      await run.sendKeys(
+        'Open https://example.com and check if there is a heading\r',
+      );
+      await run.sendKeys('\r');
 
-    // Handle confirmations.
-    // 1. Initial browser_agent delegation (likely only 3 options, so use option 1: Allow once)
-    await poll(
-      () => stripAnsi(run.output).toLowerCase().includes('action required'),
-      60000,
-      1000,
-    );
-    await run.sendKeys('1\r');
-    await new Promise((r) => setTimeout(r, 2000));
+      // Handle confirmations.
+      // 1. Initial browser_agent delegation (likely only 3 options, so use option 1: Allow once)
+      await poll(
+        () => stripAnsi(run.output).toLowerCase().includes('action required'),
+        60000,
+        1000,
+      );
+      await run.sendKeys('1\r');
+      await new Promise((r) => setTimeout(r, 2000));
 
-    // Handle privacy notice
-    await poll(
-      () => stripAnsi(run.output).toLowerCase().includes('privacy notice'),
-      5000,
-      100,
-    );
-    await run.sendKeys('1\r');
-    await new Promise((r) => setTimeout(r, 5000));
+      // Handle privacy notice
+      await poll(
+        () => stripAnsi(run.output).toLowerCase().includes('privacy notice'),
+        5000,
+        100,
+      );
+      await run.sendKeys('1\r');
+      await new Promise((r) => setTimeout(r, 5000));
 
-    // new_page (MCP tool, should have 4 options, use option 3: Allow all server tools)
-    await poll(
-      () => {
-        const stripped = stripAnsi(run.output).toLowerCase();
-        return (
-          stripped.includes('new_page') &&
-          stripped.includes('allow all server tools for this session')
-        );
-      },
-      60000,
-      1000,
-    );
+      // new_page (MCP tool, should have 4 options, use option 3: Allow all server tools)
+      await poll(
+        () => {
+          const stripped = stripAnsi(run.output).toLowerCase();
+          return (
+            stripped.includes('new_page') &&
+            stripped.includes('allow all server tools for this session')
+          );
+        },
+        60000,
+        1000,
+      );
 
-    // Select "Allow all server tools for this session" (option 3)
-    await run.sendKeys('3\r');
-    await new Promise((r) => setTimeout(r, 30000));
+      // Select "Allow all server tools for this session" (option 3)
+      await run.sendKeys('3\r');
 
-    const output = stripAnsi(run.output).toLowerCase();
+      // Wait for the browser agent to finish (success or failure)
+      await poll(
+        () => {
+          const stripped = stripAnsi(run.output).toLowerCase();
+          return (
+            stripped.includes('completed successfully') ||
+            stripped.includes('agent error')
+          );
+        },
+        120000,
+        1000,
+      );
 
-    expect(output).toContain('browser_agent');
-    expect(output).toContain('completed successfully');
-  });
+      const output = stripAnsi(run.output).toLowerCase();
+
+      expect(output).toContain('browser_agent');
+      // The test validates that "Allow all server tools" skips subsequent
+      // tool confirmations — the browser agent may still fail due to
+      // Chrome/MCP issues in CI, which is acceptable for this policy test.
+      expect(
+        output.includes('completed successfully') ||
+          output.includes('agent error'),
+      ).toBe(true);
+    },
+  );
 
   it('should show the visible warning when browser agent starts in existing session mode', async () => {
     rig.setup('browser-session-warning', {

integration-tests/file-system.test.ts

@@ -121,6 +121,7 @@ describe('file-system', () => {
 
     const result = await rig.run({
       args: `write "hello" to "${fileName}" and then stop. Do not perform any other actions.`,
+      timeout: 600000, // 10 min — real LLM can be slow in Docker sandbox
     });
 
     const foundToolCall = await rig.waitForToolCall('write_file');

integration-tests/globalSetup.ts

@@ -9,16 +9,80 @@ if (process.env['NO_COLOR'] !== undefined) {
   delete process.env['NO_COLOR'];
 }
 
-import { mkdir, readdir, rm } from 'node:fs/promises';
-import { join, dirname } from 'node:path';
+import { mkdir, readdir, rm, readFile } from 'node:fs/promises';
+import { join, dirname, extname } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { canUseRipgrep } from '../packages/core/src/tools/ripGrep.js';
 import { disableMouseTracking } from '@google/gemini-cli-core';
+import { createServer, type Server } from 'node:http';
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const rootDir = join(__dirname, '..');
 const integrationTestsDir = join(rootDir, '.integration-tests');
 let runDir = ''; // Make runDir accessible in teardown
+let fixtureServer: Server | undefined;
+
+const FIXTURE_PORT = 18923;
+const FIXTURE_DIR = join(__dirname, 'test-fixtures');
+
+const MIME_TYPES: Record<string, string> = {
+  '.html': 'text/html',
+  '.css': 'text/css',
+  '.js': 'application/javascript',
+  '.json': 'application/json',
+  '.png': 'image/png',
+  '.jpg': 'image/jpeg',
+  '.svg': 'image/svg+xml',
+};
+
+async function startFixtureServer(): Promise<number> {
+  return new Promise((resolve, reject) => {
+    const server = createServer(async (req, res) => {
+      const urlPath = req.url?.split('?')[0] || '/';
+      const relativePath = urlPath === '/' ? 'index.html' : urlPath;
+      const filePath = join(FIXTURE_DIR, relativePath);
+
+      if (!filePath.startsWith(FIXTURE_DIR)) {
+        res.writeHead(403, { 'Content-Type': 'text/html' });
+        res.end('<h1>403 Forbidden</h1>');
+        return;
+      }
+
+      try {
+        const content = await readFile(filePath);
+        const ext = extname(filePath);
+        res.writeHead(200, {
+          'Content-Type': MIME_TYPES[ext] || 'application/octet-stream',
+        });
+        res.end(content);
+      } catch {
+        res.writeHead(404, { 'Content-Type': 'text/html' });
+        res.end('<h1>404 Not Found</h1>');
+      }
+    });
+
+    server.on('error', (err: NodeJS.ErrnoException) => {
+      if (err.code === 'EADDRINUSE') {
+        console.warn(
+          `Port ${FIXTURE_PORT} in use, trying ${FIXTURE_PORT + 1}...`,
+        );
+        server.listen(FIXTURE_PORT + 1, '127.0.0.1');
+      } else {
+        reject(err);
+      }
+    });
+
+    server.on('listening', () => {
+      const addr = server.address();
+      const port = typeof addr === 'object' && addr ? addr.port : FIXTURE_PORT;
+      fixtureServer = server;
+      console.log(`Test fixture server listening on http://127.0.0.1:${port}`);
+      resolve(port);
+    });
+
+    server.listen(FIXTURE_PORT, '127.0.0.1');
+  });
+}
 
 export async function setup() {
   runDir = join(integrationTestsDir, `${Date.now()}`);
@@ -40,6 +104,10 @@ export async function setup() {
     throw new Error('Failed to download ripgrep binary');
   }
 
+  // Start the test fixture server
+  const port = await startFixtureServer();
+  process.env['TEST_FIXTURE_PORT'] = String(port);
+
   // Clean up old test runs, but keep the latest few for debugging
   try {
     const testRuns = await readdir(integrationTestsDir);
@@ -73,6 +141,14 @@ export async function setup() {
 }
 
 export async function teardown() {
+  // Stop the fixture server
+  if (fixtureServer) {
+    await new Promise<void>((resolve) => {
+      fixtureServer!.close(() => resolve());
+    });
+    fixtureServer = undefined;
+  }
+
   // Disable mouse tracking
   if (process.stdout.isTTY) {
     disableMouseTracking();

integration-tests/plan-mode.test.ts

@@ -23,7 +23,9 @@ describe('Plan Mode', () => {
       'should allow read-only tools but deny write tools in plan mode',
       {
         settings: {
-          experimental: { plan: true },
+          general: {
+            plan: { enabled: true },
+          },
           tools: {
             core: [
               'run_shell_command',
@@ -67,15 +69,12 @@ describe('Plan Mode', () => {
 
     await rig.setup(testName, {
       settings: {
-        experimental: { plan: true },
         tools: {
           core: ['write_file', 'read_file', 'list_directory'],
         },
         general: {
+          plan: { enabled: true, directory: plansDir },
           defaultApprovalMode: 'plan',
-          plan: {
-            directory: plansDir,
-          },
         },
       },
     });
@@ -120,22 +119,19 @@ describe('Plan Mode', () => {
 
     await rig.setup(testName, {
       settings: {
-        experimental: { plan: true },
         tools: {
           core: ['write_file', 'read_file', 'list_directory'],
         },
         general: {
+          plan: { enabled: true, directory: plansDir },
           defaultApprovalMode: 'plan',
-          plan: {
-            directory: plansDir,
-          },
         },
       },
     });
 
     await rig.run({
       approvalMode: 'plan',
-      args: 'Create a file called hello.txt in the current directory.',
+      args: 'Attempt to create a file named "hello.txt" in the current directory. Do not create a plan file, try to write hello.txt directly.',
     });
 
     const toolLogs = rig.readToolLogs();
@@ -156,7 +152,9 @@ describe('Plan Mode', () => {
   it('should be able to enter plan mode from default mode', async () => {
     await rig.setup('should be able to enter plan mode from default mode', {
       settings: {
-        experimental: { plan: true },
+        general: {
+          plan: { enabled: true },
+        },
         tools: {
           core: ['enter_plan_mode'],
           allowed: ['enter_plan_mode'],
@@ -184,15 +182,12 @@ describe('Plan Mode', () => {
 
     await rig.setup(testName, {
       settings: {
-        experimental: { plan: true },
         tools: {
           core: ['write_file', 'read_file', 'list_directory'],
         },
         general: {
+          plan: { enabled: true, directory: plansDir },
           defaultApprovalMode: 'plan',
-          plan: {
-            directory: plansDir,
-          },
         },
       },
     });

integration-tests/shell-background.responses

@@ -0,0 +1,5 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will run the command in the background for you."},{"functionCall":{"name":"run_shell_command","args":{"command":"sleep 10 && echo hello-from-background","is_background":true}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The background process has been started. Now I will list the background processes to verify."},{"functionCall":{"name":"list_background_processes","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I see the background process 'sleep 10 && echo hello-from-background' is running. Would you like me to read its output?"}],"role":"model"},"finishReason":"STOP","index":0}]}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will read the output for you."},{"functionCall":{"name":"read_background_output","args":{"pid":12345}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The output of the background process is:\nhello-from-background"}],"role":"model"},"finishReason":"STOP","index":0}]}]}

integration-tests/shell-background.test.ts

@@ -0,0 +1,105 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+describe('shell-background-tools', () => {
+  let rig: TestRig;
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => await rig.cleanup());
+
+  it('should run a command in the background, list it, and read its output', async () => {
+    // We use a fake responses file to make the test deterministic and run in CI.
+    rig.setup('shell-background-workflow', {
+      fakeResponsesPath: join(__dirname, 'shell-background.responses'),
+      settings: {
+        tools: {
+          core: [
+            'run_shell_command',
+            'list_background_processes',
+            'read_background_output',
+          ],
+        },
+        hooksConfig: {
+          enabled: true,
+        },
+        hooks: {
+          BeforeTool: [
+            {
+              matcher: 'run_shell_command',
+              hooks: [
+                {
+                  type: 'command',
+                  // This hook intercepts run_shell_command.
+                  // If is_background is true, it returns a mock result with PID 12345.
+                  // It also creates the mock log file that read_background_output expects.
+                  command: `node -e "
+                    const fs = require('fs');
+                    const path = require('path');
+                    const input = JSON.parse(fs.readFileSync(0, 'utf-8'));
+                    const args = JSON.parse(input.tool_call.args);
+                    
+                    if (args.is_background) {
+                      const logDir = path.join(process.env.GEMINI_CLI_HOME, 'background-processes');
+                      if (!fs.existsSync(logDir)) fs.mkdirSync(logDir, { recursive: true });
+                      fs.writeFileSync(path.join(logDir, 'background-12345.log'), 'hello-from-background\\n');
+                      
+                      console.log(JSON.stringify({
+                        decision: 'replace',
+                        hookSpecificOutput: {
+                          result: {
+                            llmContent: 'Command moved to background (PID: 12345). Output hidden. Press Ctrl+B to view.',
+                            data: { pid: 12345, command: args.command }
+                          }
+                        }
+                      }));
+                    } else {
+                      console.log(JSON.stringify({ decision: 'allow' }));
+                    }
+                  "`,
+                },
+              ],
+            },
+          ],
+        },
+      },
+    });
+
+    const run = await rig.runInteractive({ approvalMode: 'yolo' });
+
+    // 1. Start a background process
+    // We use a command that stays alive for a bit to ensure it shows up in lists
+    await run.type(
+      "Run 'sleep 10 && echo hello-from-background' in the background.",
+    );
+    await run.type('\r');
+
+    // Wait for the model's canned response acknowledging the start
+    await run.expectText('background', 30000);
+
+    // 2. List background processes
+    await run.type('List my background processes.');
+    await run.type('\r');
+    // Wait for the model's canned response showing the list
+    await run.expectText('hello-from-background', 30000);
+
+    // 3. Read the output
+    await run.type('Read the output of that process.');
+    await run.type('\r');
+    // Wait for the model's canned response showing the output
+    await run.expectText('hello-from-background', 30000);
+  }, 60000);
+});

integration-tests/test-fixtures/dynamic.html

@@ -0,0 +1,29 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Dynamic Content</title>
+  </head>
+  <body>
+    <h1 id="dynamic-heading">Dynamic Content Page</h1>
+    <div id="loading-indicator">Loading...</div>
+    <div id="dynamic-content" style="display: none">
+      <h2 id="loaded-heading">Content Loaded</h2>
+      <p id="loaded-message">
+        This content was loaded dynamically via JavaScript.
+      </p>
+      <ul id="item-list">
+        <li>Item Alpha</li>
+        <li>Item Beta</li>
+        <li>Item Gamma</li>
+      </ul>
+    </div>
+    <script>
+      // Simulate async content loading
+      setTimeout(function () {
+        document.getElementById('loading-indicator').style.display = 'none';
+        document.getElementById('dynamic-content').style.display = 'block';
+      }, 500);
+    </script>
+  </body>
+</html>

integration-tests/test-fixtures/form-result.html

@@ -0,0 +1,15 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Form Result</title>
+  </head>
+  <body>
+    <h1 id="result-heading">Form Submitted Successfully</h1>
+    <p id="result-message">Thank you for your submission.</p>
+    <div id="submitted-data">
+      <p>Your form data has been received.</p>
+    </div>
+    <a href="/index.html" id="home-link">Back to Home</a>
+  </body>
+</html>

integration-tests/test-fixtures/form.html

@@ -0,0 +1,37 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Contact Form</title>
+  </head>
+  <body>
+    <h1 id="form-heading">Contact Form</h1>
+    <form id="contact-form" action="/form-result.html" method="GET">
+      <div>
+        <label for="name">Name:</label>
+        <input type="text" id="name" name="name" required />
+      </div>
+      <div>
+        <label for="email">Email:</label>
+        <input type="email" id="email" name="email" required />
+      </div>
+      <div>
+        <label for="message">Message:</label>
+        <textarea id="message" name="message" rows="4"></textarea>
+      </div>
+      <div>
+        <label for="category">Category:</label>
+        <select id="category" name="category">
+          <option value="general">General</option>
+          <option value="support">Support</option>
+          <option value="feedback">Feedback</option>
+        </select>
+      </div>
+      <div>
+        <input type="checkbox" id="subscribe" name="subscribe" value="yes" />
+        <label for="subscribe">Subscribe to newsletter</label>
+      </div>
+      <button type="submit" id="submit-btn">Submit</button>
+    </form>
+  </body>
+</html>

integration-tests/test-fixtures/index.html

@@ -0,0 +1,27 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Home</title>
+  </head>
+  <body>
+    <h1 id="main-heading">Test Fixture Home Page</h1>
+    <p id="description">
+      This is a test fixture page for browser agent integration tests.
+    </p>
+    <nav>
+      <ul>
+        <li><a href="/form.html" id="form-link">Contact Form</a></li>
+        <li>
+          <a href="/multi-step/step1.html" id="multistep-link"
+            >Multi-Step Flow</a
+          >
+        </li>
+        <li><a href="/dynamic.html" id="dynamic-link">Dynamic Content</a></li>
+      </ul>
+    </nav>
+    <footer id="footer">
+      <p>Footer content for testing.</p>
+    </footer>
+  </body>
+</html>

integration-tests/test-fixtures/multi-step/result.html

@@ -0,0 +1,15 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Result</title>
+  </head>
+  <body>
+    <h1 id="result-heading">Multi-Step Complete</h1>
+    <p id="result-message">You have completed all steps successfully.</p>
+    <div id="completion-status">
+      <span id="status-badge">✓ Complete</span>
+    </div>
+    <a href="/index.html" id="home-link">Back to Home</a>
+  </body>
+</html>

integration-tests/test-fixtures/multi-step/step1.html

@@ -0,0 +1,16 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Step 1</title>
+  </head>
+  <body>
+    <h1 id="step-heading">Step 1: Enter Your Details</h1>
+    <p id="step-description">Please provide your name to continue.</p>
+    <form id="step1-form" action="/multi-step/step2.html" method="GET">
+      <label for="username">Username:</label>
+      <input type="text" id="username" name="username" required />
+      <button type="submit" id="next-btn">Next Step</button>
+    </form>
+  </body>
+</html>

integration-tests/test-fixtures/multi-step/step2.html

@@ -0,0 +1,22 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <title>Test Fixture - Step 2</title>
+  </head>
+  <body>
+    <h1 id="step-heading">Step 2: Confirm Your Selection</h1>
+    <p id="step-description">Choose your preference below.</p>
+    <form id="step2-form" action="/multi-step/result.html" method="GET">
+      <div>
+        <label for="preference">Preference:</label>
+        <select id="preference" name="preference">
+          <option value="option-a">Option A</option>
+          <option value="option-b">Option B</option>
+          <option value="option-c">Option C</option>
+        </select>
+      </div>
+      <button type="submit" id="finish-btn">Finish</button>
+    </form>
+  </body>
+</html>

package-lock.json

@@ -11,7 +11,7 @@
         "packages/*"
       ],
       "dependencies": {
-        "ink": "npm:@jrichman/ink@6.5.0",
+        "ink": "npm:@jrichman/ink@6.6.7",
         "latest-version": "^9.0.0",
         "node-fetch-native": "^1.6.7",
         "proper-lockfile": "^4.1.2",
@@ -92,46 +92,6 @@
         "zod": "^3.25.0 || ^4.0.0"
       }
     },
-    "node_modules/@alcalzone/ansi-tokenize": {
-      "version": "0.2.2",
-      "resolved": "https://registry.npmjs.org/@alcalzone/ansi-tokenize/-/ansi-tokenize-0.2.2.tgz",
-      "integrity": "sha512-mkOh+Wwawzuf5wa30bvc4nA+Qb6DIrGWgBhRR/Pw4T9nsgYait8izvXkNyU78D6Wcu3Z+KUdwCmLCxlWjEotYA==",
-      "license": "MIT",
-      "dependencies": {
-        "ansi-styles": "^6.2.1",
-        "is-fullwidth-code-point": "^5.0.0"
-      },
-      "engines": {
-        "node": ">=18"
-      }
-    },
-    "node_modules/@alcalzone/ansi-tokenize/node_modules/ansi-styles": {
-      "version": "6.2.3",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.3.tgz",
-      "integrity": "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==",
-      "license": "MIT",
-      "engines": {
-        "node": ">=12"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/ansi-styles?sponsor=1"
-      }
-    },
-    "node_modules/@alcalzone/ansi-tokenize/node_modules/is-fullwidth-code-point": {
-      "version": "5.1.0",
-      "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-5.1.0.tgz",
-      "integrity": "sha512-5XHYaSyiqADb4RnZ1Bdad6cPp8Toise4TzEjcOYDHZkTCbKgiUl7WTUCpNWHuxmDt91wnsZBc9xinNzopv3JMQ==",
-      "license": "MIT",
-      "dependencies": {
-        "get-east-asian-width": "^1.3.1"
-      },
-      "engines": {
-        "node": ">=18"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
     "node_modules/@ampproject/remapping": {
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/@ampproject/remapping/-/remapping-2.3.0.tgz",
@@ -10089,14 +10049,13 @@
     },
     "node_modules/ink": {
       "name": "@jrichman/ink",
-      "version": "6.5.0",
-      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.5.0.tgz",
-      "integrity": "sha512-S4g/ng7fPZmFwclO82iWkOce8vDLy/FIDgHIfkCWGOehqHe6dexHsmq3kNQD21okh198pA5SAQTCqNQJb/svRQ==",
+      "version": "6.6.7",
+      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.7.tgz",
+      "integrity": "sha512-bDzQLpLzK/dn9Ur/Ku88ZZR9totVcMGrGYAgPHidsAAbe9NKztU1fggj/iu0wRp5g1kBeALb3cfagFGdDxAU1w==",
       "license": "MIT",
       "dependencies": {
-        "@alcalzone/ansi-tokenize": "^0.2.1",
         "ansi-escapes": "^7.0.0",
-        "ansi-styles": "^6.2.1",
+        "ansi-styles": "^6.2.3",
         "auto-bind": "^5.0.1",
         "chalk": "^5.6.0",
         "cli-boxes": "^3.0.0",
@@ -10105,6 +10064,7 @@
         "code-excerpt": "^4.0.0",
         "es-toolkit": "^1.39.10",
         "indent-string": "^5.0.0",
+        "is-fullwidth-code-point": "^5.0.0",
         "is-in-ci": "^2.0.0",
         "mnemonist": "^0.40.3",
         "patch-console": "^2.0.0",
@@ -10174,9 +10134,9 @@
       }
     },
     "node_modules/ink/node_modules/ansi-styles": {
-      "version": "6.2.1",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.1.tgz",
-      "integrity": "sha512-bN798gFfQX+viw3R7yrGWRqnrN2oRkEkUjjl4JNn4E8GxxbjtG3FbrEIIY3l8/hrwUwIeCZvi4QuOTP4MErVug==",
+      "version": "6.2.3",
+      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.3.tgz",
+      "integrity": "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==",
       "license": "MIT",
       "engines": {
         "node": ">=12"
@@ -10197,6 +10157,21 @@
         "url": "https://github.com/chalk/chalk?sponsor=1"
       }
     },
+    "node_modules/ink/node_modules/is-fullwidth-code-point": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-5.1.0.tgz",
+      "integrity": "sha512-5XHYaSyiqADb4RnZ1Bdad6cPp8Toise4TzEjcOYDHZkTCbKgiUl7WTUCpNWHuxmDt91wnsZBc9xinNzopv3JMQ==",
+      "license": "MIT",
+      "dependencies": {
+        "get-east-asian-width": "^1.3.1"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
     "node_modules/ink/node_modules/is-in-ci": {
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/is-in-ci/-/is-in-ci-2.0.0.tgz",
@@ -17551,7 +17526,7 @@
         "fzf": "^0.5.2",
         "glob": "^12.0.0",
         "highlight.js": "^11.11.1",
-        "ink": "npm:@jrichman/ink@6.5.0",
+        "ink": "npm:@jrichman/ink@6.6.7",
         "ink-gradient": "^3.0.0",
         "ink-spinner": "^5.0.0",
         "latest-version": "^9.0.0",

package.json

@@ -38,7 +38,7 @@
     "build:packages": "npm run build --workspaces",
     "build:sandbox": "node scripts/build_sandbox.js",
     "build:binary": "node scripts/build_binary.js",
-    "bundle": "npm run generate && npm run build --workspace=@google/gemini-cli-devtools && node esbuild.config.js && node scripts/copy_bundle_assets.js",
+    "bundle": "npm run generate && npm run build --workspace=@google/gemini-cli-devtools && npm run bundle:browser-mcp -w @google/gemini-cli-core && node esbuild.config.js && node scripts/copy_bundle_assets.js",
     "test": "npm run test --workspaces --if-present && npm run test:sea-launch",
     "test:ci": "npm run test:ci --workspaces --if-present && npm run test:scripts && npm run test:sea-launch",
     "test:scripts": "vitest run --config ./scripts/tests/vitest.config.ts",
@@ -68,7 +68,7 @@
     "pre-commit": "node scripts/pre-commit.js"
   },
   "overrides": {
-    "ink": "npm:@jrichman/ink@6.5.0",
+    "ink": "npm:@jrichman/ink@6.6.7",
     "wrap-ansi": "9.0.2",
     "cliui": {
       "wrap-ansi": "7.0.0"
@@ -136,7 +136,7 @@
     "yargs": "^17.7.2"
   },
   "dependencies": {
-    "ink": "npm:@jrichman/ink@6.5.0",
+    "ink": "npm:@jrichman/ink@6.6.7",
     "latest-version": "^9.0.0",
     "node-fetch-native": "^1.6.7",
     "proper-lockfile": "^4.1.2",

packages/a2a-server/src/commands/restore.ts

@@ -98,7 +98,7 @@ export class RestoreCommand implements Command {
         name: this.name,
         data: restoreResult,
       };
-    } catch (_error) {
+    } catch {
       return {
         name: this.name,
         data: {
@@ -142,7 +142,7 @@ export class ListCheckpointsCommand implements Command {
           content: JSON.stringify(checkpointInfoList),
         },
       };
-    } catch (_error) {
+    } catch {
       return {
         name: this.name,
         data: {

packages/a2a-server/src/utils/testing_utils.ts

@@ -109,12 +109,8 @@ export function createMockConfig(
         enableEnvironmentVariableRedaction: false,
       },
     }),
-    isExperimentalAgentHistoryTruncationEnabled: vi.fn().mockReturnValue(false),
-    getExperimentalAgentHistoryTruncationThreshold: vi.fn().mockReturnValue(50),
-    getExperimentalAgentHistoryRetainedMessages: vi.fn().mockReturnValue(30),
-    isExperimentalAgentHistorySummarizationEnabled: vi
-      .fn()
-      .mockReturnValue(false),
+    isContextManagementEnabled: vi.fn().mockReturnValue(false),
+    getContextManagementConfig: vi.fn().mockReturnValue({ enabled: false }),
     ...overrides,
   } as unknown as Config;
 

packages/cli/package.json

@@ -49,7 +49,7 @@
     "fzf": "^0.5.2",
     "glob": "^12.0.0",
     "highlight.js": "^11.11.1",
-    "ink": "npm:@jrichman/ink@6.5.0",
+    "ink": "npm:@jrichman/ink@6.6.7",
     "ink-gradient": "^3.0.0",
     "ink-spinner": "^5.0.0",
     "latest-version": "^9.0.0",

packages/cli/src/acp/acpClient.test.ts

@@ -27,6 +27,7 @@ import {
   type MessageBus,
   LlmRole,
   type GitService,
+  type ModelRouterService,
   processSingleFileContent,
   InvalidStreamError,
 } from '@google/gemini-cli-core';
@@ -102,17 +103,7 @@ vi.mock(
       ...actual,
       updatePolicy: vi.fn(),
       createPolicyUpdater: vi.fn(),
-      ReadManyFilesTool: vi.fn().mockImplementation(() => ({
-        name: 'read_many_files',
-        kind: 'read',
-        build: vi.fn().mockReturnValue({
-          getDescription: () => 'Read files',
-          toolLocations: () => [],
-          execute: vi.fn().mockResolvedValue({
-            llmContent: ['--- file.txt ---\n\nFile content\n\n'],
-          }),
-        }),
-      })),
+      ReadManyFilesTool: vi.fn(),
       logToolCall: vi.fn(),
       LlmRole: {
         MAIN: 'main',
@@ -421,6 +412,26 @@ describe('GeminiAgent', () => {
     );
   });
 
+  it('should include gemini-3.1-flash-lite when useGemini31FlashLite is true', async () => {
+    mockConfig.getHasAccessToPreviewModel = vi.fn().mockReturnValue(true);
+    mockConfig.getGemini31LaunchedSync = vi.fn().mockReturnValue(true);
+    mockConfig.getGemini31FlashLiteLaunchedSync = vi.fn().mockReturnValue(true);
+
+    const response = await agent.newSession({
+      cwd: '/tmp',
+      mcpServers: [],
+    });
+
+    expect(response.models?.availableModels).toEqual(
+      expect.arrayContaining([
+        expect.objectContaining({
+          modelId: 'gemini-3.1-flash-lite-preview',
+          name: 'gemini-3.1-flash-lite-preview',
+        }),
+      ]),
+    );
+  });
+
   it('should return modes with plan mode when plan is enabled', async () => {
     mockConfig.getContentGeneratorConfig = vi.fn().mockReturnValue({
       apiKey: 'test-key',
@@ -646,6 +657,7 @@ describe('Session', () => {
       sendMessageStream: vi.fn(),
       addHistory: vi.fn(),
       recordCompletedToolCalls: vi.fn(),
+      getHistory: vi.fn().mockReturnValue([]),
     } as unknown as Mocked<GeminiChat>;
     mockTool = {
       kind: 'read',
@@ -667,6 +679,9 @@ describe('Session', () => {
     mockConfig = {
       getModel: vi.fn().mockReturnValue('gemini-pro'),
       getActiveModel: vi.fn().mockReturnValue('gemini-pro'),
+      getModelRouterService: vi.fn().mockReturnValue({
+        route: vi.fn().mockResolvedValue({ model: 'resolved-model' }),
+      }),
       getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
       getMcpServers: vi.fn(),
       getFileService: vi.fn().mockReturnValue({
@@ -713,10 +728,22 @@ describe('Session', () => {
       },
       errors: [],
     } as unknown as LoadedSettings);
+
+    (ReadManyFilesTool as unknown as Mock).mockImplementation(() => ({
+      name: 'read_many_files',
+      kind: 'read',
+      build: vi.fn().mockReturnValue({
+        getDescription: () => 'Read files',
+        toolLocations: () => [],
+        execute: vi.fn().mockResolvedValue({
+          llmContent: ['--- file.txt ---\n\nFile content\n\n'],
+        }),
+      }),
+    }));
   });
 
   afterEach(() => {
-    vi.clearAllMocks();
+    vi.restoreAllMocks();
   });
 
   it('should send available commands', async () => {
@@ -786,6 +813,42 @@ describe('Session', () => {
     expect(result).toMatchObject({ stopReason: 'end_turn' });
   });
 
+  it('should use model router to determine model', async () => {
+    const mockRouter = {
+      route: vi.fn().mockResolvedValue({ model: 'routed-model' }),
+    } as unknown as ModelRouterService;
+    mockConfig.getModelRouterService.mockReturnValue(mockRouter);
+
+    const stream = createMockStream([
+      {
+        type: StreamEventType.CHUNK,
+        value: {
+          candidates: [{ content: { parts: [{ text: 'Hello' }] } }],
+        },
+      },
+    ]);
+    mockChat.sendMessageStream.mockResolvedValue(stream);
+
+    await session.prompt({
+      sessionId: 'session-1',
+      prompt: [{ type: 'text', text: 'Hi' }],
+    });
+
+    expect(mockRouter.route).toHaveBeenCalledWith(
+      expect.objectContaining({
+        requestedModel: 'gemini-pro',
+        request: [{ text: 'Hi' }],
+      }),
+    );
+    expect(mockChat.sendMessageStream).toHaveBeenCalledWith(
+      expect.objectContaining({ model: 'routed-model' }),
+      expect.any(Array),
+      expect.any(String),
+      expect.any(Object),
+      expect.any(String),
+    );
+  });
+
   it('should handle prompt with empty response (InvalidStreamError)', async () => {
     mockChat.sendMessageStream.mockRejectedValue(
       new InvalidStreamError('Empty response', 'NO_RESPONSE_TEXT'),
@@ -812,6 +875,32 @@ describe('Session', () => {
     expect(result).toMatchObject({ stopReason: 'end_turn' });
   });
 
+  it('should handle prompt with no finish reason (InvalidStreamError)', async () => {
+    mockChat.sendMessageStream.mockRejectedValue(
+      new InvalidStreamError('No finish reason', 'NO_FINISH_REASON'),
+    );
+
+    const result = await session.prompt({
+      sessionId: 'session-1',
+      prompt: [{ type: 'text', text: 'Hi' }],
+    });
+
+    expect(mockChat.sendMessageStream).toHaveBeenCalled();
+    expect(result).toMatchObject({ stopReason: 'end_turn' });
+  });
+
+  it('should handle prompt with no finish reason (NO_FINISH_REASON anomaly)', async () => {
+    mockChat.sendMessageStream.mockRejectedValue({ type: 'NO_FINISH_REASON' });
+
+    const result = await session.prompt({
+      sessionId: 'session-1',
+      prompt: [{ type: 'text', text: 'Hi' }],
+    });
+
+    expect(mockChat.sendMessageStream).toHaveBeenCalled();
+    expect(result).toMatchObject({ stopReason: 'end_turn' });
+  });
+
   it('should handle /memory command', async () => {
     const handleCommandSpy = vi
       .spyOn(

packages/cli/src/acp/acpClient.ts

@@ -28,7 +28,7 @@ import {
   debugLogger,
   ReadManyFilesTool,
   REFERENCE_CONTENT_START,
-  resolveModel,
+  type RoutingContext,
   createWorkingStdio,
   startupProfiler,
   Kind,
@@ -42,6 +42,7 @@ import {
   DEFAULT_GEMINI_FLASH_LITE_MODEL,
   PREVIEW_GEMINI_MODEL,
   PREVIEW_GEMINI_3_1_MODEL,
+  PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
   PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
   PREVIEW_GEMINI_FLASH_MODEL,
   DEFAULT_GEMINI_MODEL_AUTO,
@@ -758,10 +759,15 @@ export class Session {
       const functionCalls: FunctionCall[] = [];
 
       try {
-        const model = resolveModel(
-          this.context.config.getModel(),
-          (await this.context.config.getGemini31Launched?.()) ?? false,
-        );
+        const routingContext: RoutingContext = {
+          history: chat.getHistory(/*curated=*/ true),
+          request: nextMessage?.parts ?? [],
+          signal: pendingSend.signal,
+          requestedModel: this.context.config.getModel(),
+        };
+
+        const router = this.context.config.getModelRouterService();
+        const { model } = await router.route(routingContext);
         const responseStream = await chat.sendMessageStream(
           { model },
           nextMessage?.parts ?? [],
@@ -857,7 +863,10 @@ export class Session {
           (error &&
             typeof error === 'object' &&
             'type' in error &&
-            error.type === 'NO_RESPONSE_TEXT')
+            (error.type === 'NO_RESPONSE_TEXT' ||
+              error.type === 'NO_FINISH_REASON' ||
+              error.type === 'MALFORMED_FUNCTION_CALL' ||
+              error.type === 'UNEXPECTED_TOOL_CALL'))
         ) {
           // The stream ended with an empty response or malformed tool call.
           // Treat this as a graceful end to the model's turn rather than a crash.
@@ -2009,10 +2018,31 @@ function buildAvailableModels(
   const preferredModel = config.getModel() || DEFAULT_GEMINI_MODEL_AUTO;
   const shouldShowPreviewModels = config.getHasAccessToPreviewModel();
   const useGemini31 = config.getGemini31LaunchedSync?.() ?? false;
+  const useGemini31FlashLite =
+    config.getGemini31FlashLiteLaunchedSync?.() ?? false;
   const selectedAuthType = settings.merged.security.auth.selectedType;
   const useCustomToolModel =
     useGemini31 && selectedAuthType === AuthType.USE_GEMINI;
 
+  // --- DYNAMIC PATH ---
+  if (
+    config.getExperimentalDynamicModelConfiguration?.() === true &&
+    config.getModelConfigService
+  ) {
+    const options = config.getModelConfigService().getAvailableModelOptions({
+      useGemini3_1: useGemini31,
+      useGemini3_1FlashLite: useGemini31FlashLite,
+      useCustomTools: useCustomToolModel,
+      hasAccessToPreview: shouldShowPreviewModels,
+    });
+
+    return {
+      availableModels: options,
+      currentModelId: preferredModel,
+    };
+  }
+
+  // --- LEGACY PATH ---
   const mainOptions = [
     {
       value: DEFAULT_GEMINI_MODEL_AUTO,
@@ -2056,7 +2086,7 @@ function buildAvailableModels(
       ? PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL
       : previewProModel;
 
-    manualOptions.unshift(
+    const previewOptions = [
       {
         value: previewProValue,
         title: getDisplayString(previewProModel),
@@ -2065,7 +2095,16 @@ function buildAvailableModels(
         value: PREVIEW_GEMINI_FLASH_MODEL,
         title: getDisplayString(PREVIEW_GEMINI_FLASH_MODEL),
       },
-    );
+    ];
+
+    if (useGemini31FlashLite) {
+      previewOptions.push({
+        value: PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
+        title: getDisplayString(PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL),
+      });
+    }
+
+    manualOptions.unshift(...previewOptions);
   }
 
   const scaleOptions = (

packages/cli/src/acp/commands/extensions.ts

@@ -284,7 +284,7 @@ export class LinkExtensionCommand implements Command {
 
     try {
       await stat(sourceFilepath);
-    } catch (_error) {
+    } catch {
       return { name: this.name, data: `Invalid source: ${sourceFilepath}` };
     }
 

packages/cli/src/acp/commands/restore.ts

@@ -130,7 +130,7 @@ export class ListCheckpointsCommand implements Command {
       const checkpointDir = config.storage.getProjectTempCheckpointsDir();
       try {
         await fs.mkdir(checkpointDir, { recursive: true });
-      } catch (_e) {
+      } catch {
         // Ignore
       }
 
@@ -169,7 +169,7 @@ export class ListCheckpointsCommand implements Command {
         name: this.name,
         data: `Available Checkpoints:\n${formatted}`,
       };
-    } catch (_error) {
+    } catch {
       return {
         name: this.name,
         data: 'An unexpected error occurred while listing checkpoints.',

packages/cli/src/commands/extensions/new.ts

@@ -25,7 +25,7 @@ async function pathExists(path: string) {
   try {
     await access(path);
     return true;
-  } catch (_e) {
+  } catch {
     return false;
   }
 }

packages/cli/src/commands/mcp.test.ts

@@ -32,7 +32,7 @@ describe('mcp command', () => {
 
     try {
       await parser.parse('mcp');
-    } catch (_error) {
+    } catch {
       // yargs might throw an error when demandCommand is not met
     }
 

packages/cli/src/commands/mcp/list.ts

@@ -121,7 +121,7 @@ async function testMCPConnection(
   try {
     // Use the same transport creation logic as core
     transport = await createTransport(serverName, config, false, mcpContext);
-  } catch (_error) {
+  } catch {
     await client.close();
     return MCPServerStatus.DISCONNECTED;
   }
@@ -135,7 +135,7 @@ async function testMCPConnection(
 
     await client.close();
     return MCPServerStatus.CONNECTED;
-  } catch (_error) {
+  } catch {
     await transport.close();
     return MCPServerStatus.DISCONNECTED;
   }

packages/cli/src/config/config.test.ts

@@ -21,6 +21,8 @@ import {
   type MCPServerConfig,
   type GeminiCLIExtension,
   Storage,
+  GENERALIST_PROFILE,
+  type ContextManagementConfig,
 } from '@google/gemini-cli-core';
 import { loadCliConfig, parseArguments, type CliArgs } from './config.js';
 import {
@@ -1364,8 +1366,8 @@ describe('Approval mode tool exclusion logic', () => {
       'test',
     ];
     const settings = createTestMergedSettings({
-      experimental: {
-        plan: true,
+      general: {
+        plan: { enabled: true },
       },
     });
     const argv = await parseArguments(createTestMergedSettings());
@@ -1479,9 +1481,7 @@ describe('Approval mode tool exclusion logic', () => {
     const settings = createTestMergedSettings({
       general: {
         defaultApprovalMode: 'plan',
-      },
-      experimental: {
-        plan: false,
+        plan: { enabled: false },
       },
     });
     const argv = await parseArguments(settings);
@@ -1489,14 +1489,12 @@ describe('Approval mode tool exclusion logic', () => {
     expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
   });
 
-  it('should allow plan approval mode if experimental plan is enabled', async () => {
+  it('should allow plan approval mode if plan is enabled', async () => {
     process.argv = ['node', 'script.js'];
     const settings = createTestMergedSettings({
       general: {
         defaultApprovalMode: 'plan',
-      },
-      experimental: {
-        plan: true,
+        plan: { enabled: true },
       },
     });
     const argv = await parseArguments(settings);
@@ -2178,6 +2176,84 @@ describe('loadCliConfig directWebFetch', () => {
   });
 });
 
+describe('loadCliConfig context management', () => {
+  beforeEach(() => {
+    vi.resetAllMocks();
+    vi.mocked(os.homedir).mockReturnValue('/mock/home/user');
+    vi.stubEnv('GEMINI_API_KEY', 'test-api-key');
+    vi.spyOn(ExtensionManager.prototype, 'getExtensions').mockReturnValue([]);
+  });
+
+  afterEach(() => {
+    vi.unstubAllEnvs();
+    vi.restoreAllMocks();
+  });
+
+  it('should be false by default when generalistProfile / context management is not set in settings', async () => {
+    process.argv = ['node', 'script.js'];
+    const argv = await parseArguments(createTestMergedSettings());
+    const settings = createTestMergedSettings();
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getContextManagementConfig()).haveOwnProperty(
+      'enabled',
+      false,
+    );
+    expect(config.isContextManagementEnabled()).toBe(false);
+  });
+
+  it('should be true when generalistProfile is set to true in settings', async () => {
+    process.argv = ['node', 'script.js'];
+    const argv = await parseArguments(createTestMergedSettings());
+    const settings = createTestMergedSettings({
+      experimental: {
+        generalistProfile: true,
+      },
+    });
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getContextManagementConfig()).toStrictEqual(
+      GENERALIST_PROFILE,
+    );
+    expect(config.isContextManagementEnabled()).toBe(true);
+  });
+
+  it('should be true when contextManagement is set to true in settings', async () => {
+    process.argv = ['node', 'script.js'];
+    const argv = await parseArguments(createTestMergedSettings());
+    const contextManagementConfig: Partial<ContextManagementConfig> = {
+      budget: {
+        maxPressureStrategy: 'truncate',
+        maxTokens: 100_000,
+        retainedTokens: 50_000,
+        protectedEpisodes: 1,
+        protectSystemEpisode: true,
+      },
+      strategies: {
+        historySquashing: { maxTokensPerNode: 12000 },
+        toolMasking: { stringLengthThresholdTokens: 10000 },
+        semanticCompression: {
+          nodeThresholdTokens: 5000,
+          compressionModel: 'chat-compression-2.5-flash-lite',
+        },
+      },
+    };
+    const settings = createTestMergedSettings({
+      experimental: {
+        contextManagement: true,
+      },
+      // The type of numbers is being inferred strangely, and so we have to cast
+      // to `any` here.
+      // eslint-disable-next-line @typescript-eslint/no-explicit-any
+      contextManagement: contextManagementConfig as any,
+    });
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getContextManagementConfig()).toStrictEqual({
+      enabled: true,
+      ...contextManagementConfig,
+    });
+    expect(config.isContextManagementEnabled()).toBe(true);
+  });
+});
+
 describe('screenReader configuration', () => {
   beforeEach(() => {
     vi.resetAllMocks();
@@ -2742,12 +2818,12 @@ describe('loadCliConfig approval mode', () => {
     expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.YOLO);
   });
 
-  it('should set Plan approval mode when --approval-mode=plan is used and experimental.plan is enabled', async () => {
+  it('should set Plan approval mode when --approval-mode=plan is used and plan is enabled', async () => {
     process.argv = ['node', 'script.js', '--approval-mode', 'plan'];
     const argv = await parseArguments(createTestMergedSettings());
     const settings = createTestMergedSettings({
-      experimental: {
-        plan: true,
+      general: {
+        plan: { enabled: true },
       },
     });
     const config = await loadCliConfig(settings, 'test-session', argv);
@@ -2767,12 +2843,12 @@ describe('loadCliConfig approval mode', () => {
     expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.DEFAULT);
   });
 
-  it('should throw error when --approval-mode=plan is used but experimental.plan is disabled', async () => {
+  it('should throw error when --approval-mode=plan is used but plan is disabled', async () => {
     process.argv = ['node', 'script.js', '--approval-mode', 'plan'];
     const argv = await parseArguments(createTestMergedSettings());
     const settings = createTestMergedSettings({
-      experimental: {
-        plan: false,
+      general: {
+        plan: { enabled: false },
       },
     });
 
@@ -2893,22 +2969,26 @@ describe('loadCliConfig approval mode', () => {
       expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.YOLO);
     });
 
-    it('should respect plan mode from settings when experimental.plan is enabled', async () => {
+    it('should respect plan mode from settings when plan is enabled', async () => {
       process.argv = ['node', 'script.js'];
       const settings = createTestMergedSettings({
-        general: { defaultApprovalMode: 'plan' },
-        experimental: { plan: true },
+        general: {
+          defaultApprovalMode: 'plan',
+          plan: { enabled: true },
+        },
       });
       const argv = await parseArguments(settings);
       const config = await loadCliConfig(settings, 'test-session', argv);
       expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.PLAN);
     });
 
-    it('should throw error if plan mode is in settings but experimental.plan is disabled', async () => {
+    it('should fall back to default if plan mode is in settings but disabled', async () => {
       process.argv = ['node', 'script.js'];
       const settings = createTestMergedSettings({
-        general: { defaultApprovalMode: 'plan' },
-        experimental: { plan: false },
+        general: {
+          defaultApprovalMode: 'plan',
+          plan: { enabled: false },
+        },
       });
       const argv = await parseArguments(settings);
       const config = await loadCliConfig(settings, 'test-session', argv);
@@ -3696,7 +3776,9 @@ describe('loadCliConfig mcpEnabled', () => {
     it('should use plan directory from active extension when user has not specified one', async () => {
       process.argv = ['node', 'script.js'];
       const settings = createTestMergedSettings({
-        experimental: { plan: true },
+        general: {
+          plan: { enabled: true },
+        },
       });
       const argv = await parseArguments(settings);
 
@@ -3715,9 +3797,11 @@ describe('loadCliConfig mcpEnabled', () => {
     it('should NOT use plan directory from active extension when user has specified one', async () => {
       process.argv = ['node', 'script.js'];
       const settings = createTestMergedSettings({
-        experimental: { plan: true },
         general: {
-          plan: { directory: 'user-plans-dir' },
+          plan: {
+            enabled: true,
+            directory: 'user-plans-dir',
+          },
         },
       });
       const argv = await parseArguments(settings);
@@ -3738,7 +3822,9 @@ describe('loadCliConfig mcpEnabled', () => {
     it('should NOT use plan directory from inactive extension', async () => {
       process.argv = ['node', 'script.js'];
       const settings = createTestMergedSettings({
-        experimental: { plan: true },
+        general: {
+          plan: { enabled: true },
+        },
       });
       const argv = await parseArguments(settings);
 
@@ -3759,7 +3845,9 @@ describe('loadCliConfig mcpEnabled', () => {
     it('should use default path if neither user nor extension settings provide a plan directory', async () => {
       process.argv = ['node', 'script.js'];
       const settings = createTestMergedSettings({
-        experimental: { plan: true },
+        general: {
+          plan: { enabled: true },
+        },
       });
       const argv = await parseArguments(settings);
 

packages/cli/src/config/config.ts

@@ -46,6 +46,9 @@ import {
   type HookEventName,
   type OutputFormat,
   detectIdeFromEnv,
+  GENERALIST_PROFILE,
+  POWER_USER_PROFILE,
+  STRESS_TEST_PROFILE,
 } from '@google/gemini-cli-core';
 import {
   type Settings,
@@ -669,9 +672,9 @@ export async function loadCliConfig(
         approvalMode = ApprovalMode.AUTO_EDIT;
         break;
       case 'plan':
-        if (!(settings.experimental?.plan ?? false)) {
+        if (!(settings.general?.plan?.enabled ?? true)) {
           debugLogger.warn(
-            'Approval mode "plan" is only available when experimental.plan is enabled. Falling back to "default".',
+            'Approval mode "plan" is disabled in your settings. Falling back to "default".',
           );
           approvalMode = ApprovalMode.DEFAULT;
         } else {
@@ -883,6 +886,21 @@ export async function loadCliConfig(
     }
   }
 
+  const useGeneralistProfile =
+    settings.experimental?.generalistProfile ?? false;
+  const useStressTestProfile = settings.experimental?.stressTestProfile ?? false;
+  const usePowerUserProfile = settings.experimental?.powerUserProfile ?? false;
+  const useContextManagement =
+    settings.experimental?.contextManagement ?? false;
+  const contextManagement = {
+    ...(useGeneralistProfile ? GENERALIST_PROFILE : {}),
+    ...(usePowerUserProfile ? POWER_USER_PROFILE : {}),
+    ...(useStressTestProfile ? STRESS_TEST_PROFILE : {}),
+    ...(useContextManagement ? settings?.contextManagement : {}),
+    enabled:
+      useContextManagement || useGeneralistProfile || usePowerUserProfile || useStressTestProfile,
+  };
+
   return new Config({
     acpMode: isAcpMode,
     clientName,
@@ -966,7 +984,7 @@ export async function loadCliConfig(
     extensionRegistryURI,
     enableExtensionReloading: settings.experimental?.extensionReloading,
     enableAgents: settings.experimental?.enableAgents,
-    plan: settings.experimental?.plan,
+    plan: settings.general?.plan?.enabled ?? true,
     tracker: settings.experimental?.taskTracker,
     directWebFetch: settings.experimental?.directWebFetch,
     planSettings: settings.general?.plan?.directory
@@ -977,17 +995,9 @@ export async function loadCliConfig(
     disabledSkills: settings.skills?.disabled,
     experimentalJitContext: settings.experimental?.jitContext,
     experimentalMemoryManager: settings.experimental?.memoryManager,
-    experimentalAgentHistoryTruncation:
-      settings.experimental?.agentHistoryTruncation,
-    experimentalAgentHistoryTruncationThreshold:
-      settings.experimental?.agentHistoryTruncationThreshold,
-    experimentalAgentHistoryRetainedMessages:
-      settings.experimental?.agentHistoryRetainedMessages,
-    experimentalAgentHistorySummarization:
-      settings.experimental?.agentHistorySummarization,
+    contextManagement,
     modelSteering: settings.experimental?.modelSteering,
     topicUpdateNarration: settings.experimental?.topicUpdateNarration,
-    toolOutputMasking: settings.experimental?.toolOutputMasking,
     noBrowser: !!process.env['NO_BROWSER'],
     summarizeToolOutput: settings.model?.summarizeToolOutput,
     ideMode,
@@ -1014,6 +1024,7 @@ export async function loadCliConfig(
       format: (argv.outputFormat ?? settings.output?.format) as OutputFormat,
     },
     gemmaModelRouter: settings.experimental?.gemmaModelRouter,
+    adk: settings.experimental?.adk,
     fakeResponses: argv.fakeResponses,
     recordResponses: argv.recordResponses,
     retryFetchErrors: settings.general?.retryFetchErrors,
@@ -1068,7 +1079,7 @@ async function resolveWorktreeSettings(
     if (isGeminiWorktree(toplevel, projectRoot)) {
       worktreePath = toplevel;
     }
-  } catch (_e) {
+  } catch {
     return undefined;
   }
 

packages/cli/src/config/extension-manager-permissions.test.ts

@@ -33,7 +33,7 @@ describe('copyExtension permissions', () => {
             makeWritableSync(path.join(p, child)),
           );
         }
-      } catch (_e) {
+      } catch {
         // Ignore errors during cleanup
       }
     };

packages/cli/src/config/extension-manager.test.ts

@@ -101,7 +101,7 @@ describe('ExtensionManager', () => {
     themeManager.clearExtensionThemes();
     try {
       fs.rmSync(tempHomeDir, { recursive: true, force: true });
-    } catch (_e) {
+    } catch {
       // Ignore
     }
   });

packages/cli/src/config/extension.ts

@@ -63,7 +63,7 @@ export function loadInstallMetadata(
     // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
     const metadata = JSON.parse(configContent) as ExtensionInstallMetadata;
     return metadata;
-  } catch (_e) {
+  } catch {
     return undefined;
   }
 }

packages/cli/src/config/extensions/github.ts

@@ -151,7 +151,7 @@ export async function fetchReleaseFromGithub(
       return await fetchJson(
         `https://api.github.com/repos/${owner}/${repo}/releases/latest`,
       );
-    } catch (_) {
+    } catch {
       // This can fail if there is no release marked latest. In that case
       // we want to just try the pre-release logic below.
     }

packages/cli/src/config/footerItems.test.ts

@@ -5,87 +5,153 @@
  */
 
 import { describe, it, expect } from 'vitest';
-import { deriveItemsFromLegacySettings } from './footerItems.js';
+import {
+  deriveItemsFromLegacySettings,
+  resolveFooterState,
+} from './footerItems.js';
 import { createMockSettings } from '../test-utils/settings.js';
 
-describe('deriveItemsFromLegacySettings', () => {
-  it('returns defaults when no legacy settings are customized', () => {
-    const settings = createMockSettings({
-      ui: { footer: { hideContextPercentage: true } },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).toEqual([
-      'workspace',
-      'git-branch',
-      'sandbox',
-      'model-name',
-      'quota',
-    ]);
-  });
+describe('footerItems', () => {
+  describe('deriveItemsFromLegacySettings', () => {
+    it('returns defaults when no legacy settings are customized', () => {
+      const settings = createMockSettings({
+        ui: { footer: { hideContextPercentage: true } },
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).toEqual([
+        'workspace',
+        'git-branch',
+        'sandbox',
+        'model-name',
+        'quota',
+      ]);
+    });
 
-  it('removes workspace when hideCWD is true', () => {
-    const settings = createMockSettings({
-      ui: { footer: { hideCWD: true, hideContextPercentage: true } },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).not.toContain('workspace');
-  });
+    it('removes workspace when hideCWD is true', () => {
+      const settings = createMockSettings({
+        ui: { footer: { hideCWD: true, hideContextPercentage: true } },
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).not.toContain('workspace');
+    });
 
-  it('removes sandbox when hideSandboxStatus is true', () => {
-    const settings = createMockSettings({
-      ui: { footer: { hideSandboxStatus: true, hideContextPercentage: true } },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).not.toContain('sandbox');
-  });
-
-  it('removes model-name, context-used, and quota when hideModelInfo is true', () => {
-    const settings = createMockSettings({
-      ui: { footer: { hideModelInfo: true, hideContextPercentage: true } },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).not.toContain('model-name');
-    expect(items).not.toContain('context-used');
-    expect(items).not.toContain('quota');
-  });
-
-  it('includes context-used when hideContextPercentage is false', () => {
-    const settings = createMockSettings({
-      ui: { footer: { hideContextPercentage: false } },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).toContain('context-used');
-    // Should be after model-name
-    const modelIdx = items.indexOf('model-name');
-    const contextIdx = items.indexOf('context-used');
-    expect(contextIdx).toBe(modelIdx + 1);
-  });
-
-  it('includes memory-usage when showMemoryUsage is true', () => {
-    const settings = createMockSettings({
-      ui: { showMemoryUsage: true, footer: { hideContextPercentage: true } },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).toContain('memory-usage');
-  });
-
-  it('handles combination of settings', () => {
-    const settings = createMockSettings({
-      ui: {
-        showMemoryUsage: true,
-        footer: {
-          hideCWD: true,
-          hideModelInfo: true,
-          hideContextPercentage: false,
+    it('removes sandbox when hideSandboxStatus is true', () => {
+      const settings = createMockSettings({
+        ui: {
+          footer: { hideSandboxStatus: true, hideContextPercentage: true },
         },
-      },
-    }).merged;
-    const items = deriveItemsFromLegacySettings(settings);
-    expect(items).toEqual([
-      'git-branch',
-      'sandbox',
-      'context-used',
-      'memory-usage',
-    ]);
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).not.toContain('sandbox');
+    });
+
+    it('removes model-name, context-used, and quota when hideModelInfo is true', () => {
+      const settings = createMockSettings({
+        ui: { footer: { hideModelInfo: true, hideContextPercentage: true } },
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).not.toContain('model-name');
+      expect(items).not.toContain('context-used');
+      expect(items).not.toContain('quota');
+    });
+
+    it('includes context-used when hideContextPercentage is false', () => {
+      const settings = createMockSettings({
+        ui: { footer: { hideContextPercentage: false } },
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).toContain('context-used');
+      // Should be after model-name
+      const modelIdx = items.indexOf('model-name');
+      const contextIdx = items.indexOf('context-used');
+      expect(contextIdx).toBe(modelIdx + 1);
+    });
+
+    it('includes memory-usage when showMemoryUsage is true', () => {
+      const settings = createMockSettings({
+        ui: { showMemoryUsage: true, footer: { hideContextPercentage: true } },
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).toContain('memory-usage');
+    });
+
+    it('handles combination of settings', () => {
+      const settings = createMockSettings({
+        ui: {
+          showMemoryUsage: true,
+          footer: {
+            hideCWD: true,
+            hideModelInfo: true,
+            hideContextPercentage: false,
+          },
+        },
+      }).merged;
+      const items = deriveItemsFromLegacySettings(settings);
+      expect(items).toEqual([
+        'git-branch',
+        'sandbox',
+        'context-used',
+        'memory-usage',
+      ]);
+    });
+  });
+
+  describe('resolveFooterState', () => {
+    it('filters out auth item when showUserIdentity is false', () => {
+      const settings = createMockSettings({
+        ui: {
+          showUserIdentity: false,
+          footer: {
+            items: ['workspace', 'auth', 'model-name'],
+          },
+        },
+      }).merged;
+
+      const state = resolveFooterState(settings);
+      expect(state.orderedIds).not.toContain('auth');
+      expect(state.selectedIds.has('auth')).toBe(false);
+      // It should also not be in the 'others' part of orderedIds
+      expect(state.orderedIds).toEqual([
+        'workspace',
+        'model-name',
+        'git-branch',
+        'sandbox',
+        'context-used',
+        'quota',
+        'memory-usage',
+        'session-id',
+        'code-changes',
+        'token-count',
+      ]);
+    });
+
+    it('includes auth item when showUserIdentity is true', () => {
+      const settings = createMockSettings({
+        ui: {
+          showUserIdentity: true,
+          footer: {
+            items: ['workspace', 'auth', 'model-name'],
+          },
+        },
+      }).merged;
+
+      const state = resolveFooterState(settings);
+      expect(state.orderedIds).toContain('auth');
+      expect(state.selectedIds.has('auth')).toBe(true);
+    });
+
+    it('includes auth item by default when showUserIdentity is undefined (defaults to true)', () => {
+      const settings = createMockSettings({
+        ui: {
+          footer: {
+            items: ['workspace', 'auth', 'model-name'],
+          },
+        },
+      }).merged;
+
+      const state = resolveFooterState(settings);
+      expect(state.orderedIds).toContain('auth');
+      expect(state.selectedIds.has('auth')).toBe(true);
+    });
   });
 });

packages/cli/src/config/footerItems.ts

@@ -47,6 +47,11 @@ export const ALL_ITEMS = [
     header: 'session',
     description: 'Unique identifier for the current session',
   },
+  {
+    id: 'auth',
+    header: '/auth',
+    description: 'Current authentication info',
+  },
   {
     id: 'code-changes',
     header: 'diff',
@@ -70,6 +75,7 @@ export const DEFAULT_ORDER = [
   'quota',
   'memory-usage',
   'session-id',
+  'auth',
   'code-changes',
   'token-count',
 ];
@@ -121,10 +127,19 @@ export function resolveFooterState(settings: MergedSettings): {
   orderedIds: string[];
   selectedIds: Set<string>;
 } {
+  const showUserIdentity = settings.ui?.showUserIdentity !== false;
+  const filteredValidIds = showUserIdentity
+    ? VALID_IDS
+    : new Set([...VALID_IDS].filter((id) => id !== 'auth'));
+
   const source = (
     settings.ui?.footer?.items ?? deriveItemsFromLegacySettings(settings)
-  ).filter((id: string) => VALID_IDS.has(id));
-  const others = DEFAULT_ORDER.filter((id) => !source.includes(id));
+  ).filter((id: string) => filteredValidIds.has(id));
+
+  const others = DEFAULT_ORDER.filter(
+    (id) => !source.includes(id) && filteredValidIds.has(id),
+  );
+
   return {
     orderedIds: [...source, ...others],
     selectedIds: new Set(source),

packages/cli/src/config/settings.ts

@@ -612,7 +612,7 @@ export function loadEnvironment(
           }
         }
       }
-    } catch (_e) {
+    } catch {
       // Errors are ignored to match the behavior of `dotenv.config({ quiet: true })`.
     }
   }
@@ -1124,15 +1124,15 @@ function migrateExperimentalSettings(
     };
     let modified = false;
 
-    const migrateExperimental = (
+    const migrateExperimental = <T = Record<string, unknown>>(
       oldKey: string,
-      migrateFn: (oldValue: Record<string, unknown>) => void,
+      migrateFn: (oldValue: T) => void,
     ) => {
       const old = experimentalSettings[oldKey];
-      if (old) {
+      if (old !== undefined) {
         foundDeprecated?.push(`experimental.${oldKey}`);
         // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-        migrateFn(old as Record<string, unknown>);
+        migrateFn(old as T);
         modified = true;
       }
     };
@@ -1197,6 +1197,24 @@ function migrateExperimentalSettings(
       agentsOverrides['cli_help'] = override;
     });
 
+    // Migrate experimental.plan -> general.plan.enabled
+    migrateExperimental<boolean>('plan', (planValue) => {
+      const generalSettings =
+        (settings.general as Record<string, unknown> | undefined) || {};
+      const newGeneral = { ...generalSettings };
+      const planSettings =
+        // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+        (newGeneral['plan'] as Record<string, unknown> | undefined) || {};
+      const newPlan = { ...planSettings };
+
+      if (newPlan['enabled'] === undefined) {
+        newPlan['enabled'] = planValue;
+        newGeneral['plan'] = newPlan;
+        loadedSettings.setValue(scope, 'general', newGeneral);
+        modified = true;
+      }
+    });
+
     if (modified) {
       agentsSettings['overrides'] = agentsOverrides;
       loadedSettings.setValue(scope, 'agents', agentsSettings);
@@ -1205,6 +1223,7 @@ function migrateExperimentalSettings(
         const newExperimental = { ...experimentalSettings };
         delete newExperimental['codebaseInvestigatorSettings'];
         delete newExperimental['cliHelpAgentSettings'];
+        delete newExperimental['plan'];
         loadedSettings.setValue(scope, 'experimental', newExperimental);
       }
       return true;

packages/cli/src/config/settingsSchema.test.ts

@@ -87,7 +87,7 @@ describe('SettingsSchema', () => {
       const definition = getSettingsSchema().ui?.properties?.loadingPhrases;
       expect(definition).toBeDefined();
       expect(definition?.type).toBe('enum');
-      expect(definition?.default).toBe('tips');
+      expect(definition?.default).toBe('off');
       expect(definition?.options?.map((o) => o.value)).toEqual([
         'tips',
         'witty',
@@ -418,14 +418,17 @@ describe('SettingsSchema', () => {
     });
 
     it('should have plan setting in schema', () => {
-      const setting = getSettingsSchema().experimental.properties.plan;
+      const setting =
+        getSettingsSchema().general.properties.plan.properties.enabled;
       expect(setting).toBeDefined();
       expect(setting.type).toBe('boolean');
-      expect(setting.category).toBe('Experimental');
+      expect(setting.category).toBe('General');
       expect(setting.default).toBe(true);
       expect(setting.requiresRestart).toBe(true);
       expect(setting.showInDialog).toBe(true);
-      expect(setting.description).toBe('Enable Plan Mode.');
+      expect(setting.description).toBe(
+        'Enable Plan Mode for read-only safety during planning.',
+      );
     });
 
     it('should have hooksConfig.notifications setting in schema', () => {
@@ -502,6 +505,31 @@ describe('SettingsSchema', () => {
         'The model to use for the classifier. Only tested on `gemma3-1b-gpu-custom`.',
       );
     });
+
+    it('should have adk setting in schema', () => {
+      const adk = getSettingsSchema().experimental.properties.adk;
+      expect(adk).toBeDefined();
+      expect(adk.type).toBe('object');
+      expect(adk.category).toBe('Experimental');
+      expect(adk.default).toEqual({});
+      expect(adk.requiresRestart).toBe(true);
+      expect(adk.showInDialog).toBe(false);
+      expect(adk.description).toBe(
+        'Settings for the Agent Development Kit (ADK).',
+      );
+
+      const agentSessionNoninteractiveEnabled =
+        adk.properties.agentSessionNoninteractiveEnabled;
+      expect(agentSessionNoninteractiveEnabled).toBeDefined();
+      expect(agentSessionNoninteractiveEnabled.type).toBe('boolean');
+      expect(agentSessionNoninteractiveEnabled.category).toBe('Experimental');
+      expect(agentSessionNoninteractiveEnabled.default).toBe(false);
+      expect(agentSessionNoninteractiveEnabled.requiresRestart).toBe(true);
+      expect(agentSessionNoninteractiveEnabled.showInDialog).toBe(false);
+      expect(agentSessionNoninteractiveEnabled.description).toBe(
+        'Enable non-interactive agent sessions.',
+      );
+    });
   });
 
   it('has JSON schema definitions for every referenced ref', () => {

packages/cli/src/config/settingsSchema.ts

@@ -293,6 +293,16 @@ const SETTINGS_SCHEMA = {
         description: 'Planning features configuration.',
         showInDialog: false,
         properties: {
+          enabled: {
+            type: 'boolean',
+            label: 'Enable Plan Mode',
+            category: 'General',
+            requiresRestart: true,
+            default: true,
+            description:
+              'Enable Plan Mode for read-only safety during planning.',
+            showInDialog: true,
+          },
           directory: {
             type: 'string',
             label: 'Plan Directory',
@@ -561,6 +571,16 @@ const SETTINGS_SCHEMA = {
         description: 'Show the "? for shortcuts" hint above the input.',
         showInDialog: true,
       },
+      compactToolOutput: {
+        type: 'boolean',
+        label: 'Compact Tool Output',
+        category: 'UI',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Display tool outputs (like directory listings and file reads) in a compact, structured format.',
+        showInDialog: true,
+      },
       hideBanner: {
         type: 'boolean',
         label: 'Hide Banner',
@@ -756,9 +776,9 @@ const SETTINGS_SCHEMA = {
         label: 'Loading Phrases',
         category: 'UI',
         requiresRestart: false,
-        default: 'tips',
+        default: 'off',
         description:
-          'What to show while the model is working: tips, witty comments, both, or nothing.',
+          'What to show while the model is working: tips, witty comments, all, or off.',
         showInDialog: true,
         options: [
           { value: 'tips', label: 'Tips' },
@@ -1182,7 +1202,8 @@ const SETTINGS_SCHEMA = {
             category: 'Advanced',
             requiresRestart: true,
             default: undefined as string | undefined,
-            description: 'Model override for the visual agent.',
+            description:
+              "Model for the visual agent's analyze_screenshot tool. When set, enables the tool.",
             showInDialog: false,
           },
           allowedDomains: {
@@ -1867,7 +1888,7 @@ const SETTINGS_SCHEMA = {
         label: 'Auto Configure Max Old Space Size',
         category: 'Advanced',
         requiresRestart: true,
-        default: false,
+        default: true,
         description: 'Automatically configure Node.js memory limits',
         showInDialog: true,
       },
@@ -1913,54 +1934,22 @@ const SETTINGS_SCHEMA = {
     description: 'Setting to enable experimental features',
     showInDialog: false,
     properties: {
-      toolOutputMasking: {
+      adk: {
         type: 'object',
-        label: 'Tool Output Masking',
+        label: 'ADK',
         category: 'Experimental',
         requiresRestart: true,
-        ignoreInDocs: false,
         default: {},
-        description:
-          'Advanced settings for tool output masking to manage context window efficiency.',
+        description: 'Settings for the Agent Development Kit (ADK).',
         showInDialog: false,
         properties: {
-          enabled: {
+          agentSessionNoninteractiveEnabled: {
             type: 'boolean',
-            label: 'Enable Tool Output Masking',
+            label: 'Agent Session Non-interactive Enabled',
             category: 'Experimental',
             requiresRestart: true,
-            default: true,
-            description: 'Enables tool output masking to save tokens.',
-            showInDialog: true,
-          },
-          toolProtectionThreshold: {
-            type: 'number',
-            label: 'Tool Protection Threshold',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: 50000,
-            description:
-              'Minimum number of tokens to protect from masking (most recent tool outputs).',
-            showInDialog: false,
-          },
-          minPrunableTokensThreshold: {
-            type: 'number',
-            label: 'Min Prunable Tokens Threshold',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: 30000,
-            description:
-              'Minimum prunable tokens required to trigger a masking pass.',
-            showInDialog: false,
-          },
-          protectLatestTurn: {
-            type: 'boolean',
-            label: 'Protect Latest Turn',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: true,
-            description:
-              'Ensures the absolute latest turn is never masked, regardless of token count.',
+            default: false,
+            description: 'Enable non-interactive agent sessions.',
             showInDialog: false,
           },
         },
@@ -2036,7 +2025,7 @@ const SETTINGS_SCHEMA = {
         label: 'JIT Context Loading',
         category: 'Experimental',
         requiresRestart: true,
-        default: true,
+        default: false,
         description: 'Enable Just-In-Time (JIT) context loading.',
         showInDialog: false,
       },
@@ -2060,15 +2049,6 @@ const SETTINGS_SCHEMA = {
           'Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).',
         showInDialog: true,
       },
-      plan: {
-        type: 'boolean',
-        label: 'Plan',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: true,
-        description: 'Enable Plan Mode.',
-        showInDialog: true,
-      },
       taskTracker: {
         type: 'boolean',
         label: 'Task Tracker',
@@ -2169,44 +2149,43 @@ const SETTINGS_SCHEMA = {
           'Replace the built-in save_memory tool with a memory manager subagent that supports adding, removing, de-duplicating, and organizing memories.',
         showInDialog: true,
       },
-      agentHistoryTruncation: {
+      powerUserProfile: {
         type: 'boolean',
-        label: 'Agent History Truncation',
+        label: 'Use the power user profile for massive contexts.',
         category: 'Experimental',
         requiresRestart: true,
         default: false,
         description:
-          'Enable truncation window logic for the Agent History Provider.',
+          'Enables continuous minimal GC near the max tokens limit instead of a blocked backbuffer.',
         showInDialog: true,
       },
-      agentHistoryTruncationThreshold: {
-        type: 'number',
-        label: 'Agent History Truncation Threshold',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: 30,
-        description:
-          'The maximum number of messages before history is truncated.',
-        showInDialog: true,
-      },
-      agentHistoryRetainedMessages: {
-        type: 'number',
-        label: 'Agent History Retained Messages',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: 15,
-        description:
-          'The number of recent messages to retain after truncation.',
-        showInDialog: true,
-      },
-      agentHistorySummarization: {
+      stressTestProfile: {
         type: 'boolean',
-        label: 'Agent History Summarization',
+        label: 'Stress Test Profile (Context GC)',
         category: 'Experimental',
         requiresRestart: true,
         default: false,
         description:
-          'Enable summarization of truncated content via a small model for the Agent History Provider.',
+          'Aggressively limits the token budget (6k retained, 12k max) to force rapid background snapshotting and foreground truncations for local E2E testing of the context system.',
+        showInDialog: true,
+      },
+      generalistProfile: {
+        type: 'boolean',
+        label: 'Use the generalist profile to manage agent contexts.',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: false,
+        description:
+          'Suitable for general coding and software development tasks.',
+        showInDialog: true,
+      },
+      contextManagement: {
+        type: 'boolean',
+        label: 'Enable Context Management',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: false,
+        description: 'Enable logic for context management.',
         showInDialog: true,
       },
       topicUpdateNarration: {
@@ -2485,6 +2464,171 @@ const SETTINGS_SCHEMA = {
     },
   },
 
+  contextManagement: {
+    type: 'object',
+    label: 'Context Management',
+    category: 'Experimental',
+    requiresRestart: true,
+    default: {},
+    description:
+      'Settings for agent history and tool distillation context management.',
+    showInDialog: false,
+    properties: {
+      historyWindow: {
+        type: 'object',
+        label: 'History Window Settings',
+        category: 'Context Management',
+        requiresRestart: true,
+        default: {},
+        showInDialog: false,
+        properties: {
+          maxTokens: {
+            type: 'number',
+            label: 'Max Tokens',
+            category: 'Context Management',
+            requiresRestart: true,
+            default: 150_000,
+            description:
+              'The number of tokens to allow before triggering compression.',
+            showInDialog: false,
+          },
+          retainedTokens: {
+            type: 'number',
+            label: 'Retained Tokens',
+            category: 'Context Management',
+            requiresRestart: true,
+            default: 40_000,
+            description: 'The number of tokens to always retain.',
+            showInDialog: false,
+          },
+        },
+      },
+      messageLimits: {
+        type: 'object',
+        label: 'Message Limits',
+        category: 'Context Management',
+        requiresRestart: true,
+        default: {},
+        showInDialog: false,
+        properties: {
+          normalMaxTokens: {
+            type: 'number',
+            label: 'Normal Maximum Tokens',
+            category: 'Context Management',
+            requiresRestart: true,
+            default: 2500,
+            description:
+              'The target number of tokens to budget for a normal conversation turn.',
+            showInDialog: false,
+          },
+          retainedMaxTokens: {
+            type: 'number',
+            label: 'Retained Maximum Tokens',
+            category: 'Context Management',
+            requiresRestart: true,
+            default: 12000,
+            description:
+              'The maximum number of tokens a single conversation turn can consume before truncation.',
+            showInDialog: false,
+          },
+          normalizationHeadRatio: {
+            type: 'number',
+            label: 'Normalization Head Ratio',
+            category: 'Context Management',
+            requiresRestart: true,
+            default: 0.25,
+            description:
+              'The ratio of tokens to retain from the beginning of a truncated message (0.0 to 1.0).',
+            showInDialog: false,
+          },
+        },
+      },
+      tools: {
+        type: 'object',
+        label: 'Context Management Tools',
+        category: 'Context Management',
+        requiresRestart: true,
+        default: {},
+        showInDialog: false,
+        properties: {
+          distillation: {
+            type: 'object',
+            label: 'Tool Distillation',
+            category: 'Context Management',
+            requiresRestart: true,
+            default: {},
+            showInDialog: false,
+            properties: {
+              maxOutputTokens: {
+                type: 'number',
+                label: 'Max Output Tokens',
+                category: 'Context Management',
+                requiresRestart: true,
+                default: 10_000,
+                description:
+                  'Maximum tokens to show to the model when truncating large tool outputs.',
+                showInDialog: false,
+              },
+              summarizationThresholdTokens: {
+                type: 'number',
+                label: 'Tool Summarization Threshold',
+                category: 'Context Management',
+                requiresRestart: true,
+                default: 20_000,
+                description:
+                  'Threshold above which truncated tool outputs will be summarized by an LLM.',
+                showInDialog: false,
+              },
+            },
+          },
+          outputMasking: {
+            type: 'object',
+            label: 'Tool Output Masking',
+            category: 'Context Management',
+            requiresRestart: true,
+            ignoreInDocs: false,
+            default: {},
+            description:
+              'Advanced settings for tool output masking to manage context window efficiency.',
+            showInDialog: false,
+            properties: {
+              protectionThresholdTokens: {
+                type: 'number',
+                label: 'Tool Protection Threshold (Tokens)',
+                category: 'Context Management',
+                requiresRestart: true,
+                default: 50_000,
+                description:
+                  'Minimum number of tokens to protect from masking (most recent tool outputs).',
+                showInDialog: false,
+              },
+              minPrunableThresholdTokens: {
+                type: 'number',
+                label: 'Min Prunable Tokens Threshold',
+                category: 'Context Management',
+                requiresRestart: true,
+                default: 30_000,
+                description:
+                  'Minimum prunable tokens required to trigger a masking pass.',
+                showInDialog: false,
+              },
+              protectLatestTurn: {
+                type: 'boolean',
+                label: 'Protect Latest Turn',
+                category: 'Context Management',
+                requiresRestart: true,
+                default: true,
+                description:
+                  'Ensures the absolute latest turn is never masked, regardless of token count.',
+                showInDialog: false,
+              },
+            },
+          },
+        },
+      },
+    },
+  },
+
   admin: {
     type: 'object',
     label: 'Admin',

packages/cli/src/interactiveCli.tsx

@@ -46,6 +46,7 @@ import { TerminalProvider } from './ui/contexts/TerminalContext.js';
 import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
 import { OverflowProvider } from './ui/contexts/OverflowContext.js';
 import { profiler } from './ui/components/DebugProfiler.js';
+import { initializeConsoleStore } from './ui/hooks/useConsoleMessages.js';
 
 const SLOW_RENDER_MS = 200;
 
@@ -57,6 +58,7 @@ export async function startInteractiveUI(
   resumedSessionData: ResumedSessionData | undefined,
   initializationResult: InitializationResult,
 ) {
+  initializeConsoleStore();
   // Never enter Ink alternate buffer mode when screen reader mode is enabled
   // as there is no benefit of alternate buffer mode when using a screen reader
   // and the Ink alternate buffer mode requires line wrapping harmful to

packages/cli/src/nonInteractiveCli.test.ts

@@ -1712,7 +1712,7 @@ describe('runNonInteractive', () => {
           input,
           prompt_id: promptId,
         });
-      } catch (_error) {
+      } catch {
         // Expected exit
       }
 

packages/cli/src/test-utils/mockCommandContext.ts

@@ -61,6 +61,7 @@ export const createMockCommandContext = (
       toggleCorgiMode: vi.fn(),
       toggleShortcutsHelp: vi.fn(),
       toggleVimEnabled: vi.fn(),
+      reloadCommands: vi.fn(),
       openAgentConfigDialog: vi.fn(),
       closeAgentConfigDialog: vi.fn(),
       extensionsUpdateState: new Map(),

packages/cli/src/test-utils/mockConfig.ts

@@ -38,6 +38,7 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
       fireSessionEndEvent: vi.fn().mockResolvedValue(undefined),
       fireSessionStartEvent: vi.fn().mockResolvedValue(undefined),
     })),
+    isMemoryManagerEnabled: vi.fn(() => false),
     getListExtensions: vi.fn(() => false),
     getExtensions: vi.fn(() => []),
     getListSessions: vi.fn(() => false),
@@ -194,6 +195,17 @@ export function createMockSettings(
     user: { settings: {} },
     workspace: { settings: {} },
     errors: [],
+    subscribe: vi.fn().mockReturnValue(() => {}),
+    getSnapshot: vi.fn().mockReturnValue({
+      system: { settings: {} },
+      systemDefaults: { settings: {} },
+      user: { settings: {} },
+      workspace: { settings: {} },
+      isTrusted: true,
+      errors: [],
+      merged,
+    }),
+    setValue: vi.fn(),
     ...overrides,
     merged,
   } as unknown as LoadedSettings;

packages/cli/src/test-utils/render.tsx

@@ -42,6 +42,7 @@ import {
   type OverflowState,
 } from '../ui/contexts/OverflowContext.js';
 
+import { makeFakeConfig } from '@google/gemini-cli-core';
 import { type Config } from '@google/gemini-cli-core';
 import { FakePersistentState } from './persistentStateFake.js';
 import { AppContext, type AppState } from '../ui/contexts/AppContext.js';
@@ -51,7 +52,6 @@ import { themeManager, DEFAULT_THEME } from '../ui/themes/theme-manager.js';
 import { DefaultLight } from '../ui/themes/builtin/light/default-light.js';
 import { pickDefaultThemeName } from '../ui/themes/theme.js';
 import { generateSvgForTerminal } from './svg.js';
-import { loadCliConfig, type CliArgs } from '../config/config.js';
 
 export const persistentStateMock = new FakePersistentState();
 
@@ -613,6 +613,7 @@ export const renderWithProviders = async (
     mouseEventsEnabled = false,
     config,
     uiActions,
+    toolActions,
     persistentState,
     appState = mockAppState,
   }: {
@@ -623,6 +624,11 @@ export const renderWithProviders = async (
     mouseEventsEnabled?: boolean;
     config?: Config;
     uiActions?: Partial<UIActions>;
+    toolActions?: Partial<{
+      isExpanded: (callId: string) => boolean;
+      toggleExpansion: (callId: string) => void;
+      toggleAllExpansion: (callIds: string[]) => void;
+    }>;
     persistentState?: {
       get?: typeof persistentStateMock.get;
       set?: typeof persistentStateMock.set;
@@ -660,12 +666,11 @@ export const renderWithProviders = async (
   const terminalWidth = width ?? baseState.terminalWidth;
 
   if (!config) {
-    config = await loadCliConfig(
-      settings.merged,
-      'random-session-id',
-      {} as unknown as CliArgs,
-      { cwd: '/' },
-    );
+    config = makeFakeConfig({
+      useAlternateBuffer: settings.merged.ui?.useAlternateBuffer,
+      showMemoryUsage: settings.merged.ui?.showMemoryUsage,
+      accessibility: settings.merged.ui?.accessibility,
+    });
   }
 
   const mainAreaWidth = providedUiState?.mainAreaWidth ?? terminalWidth;
@@ -710,6 +715,16 @@ export const renderWithProviders = async (
                         <ToolActionsProvider
                           config={config}
                           toolCalls={allToolCalls}
+                          isExpanded={
+                            toolActions?.isExpanded ??
+                            vi.fn().mockReturnValue(false)
+                          }
+                          toggleExpansion={
+                            toolActions?.toggleExpansion ?? vi.fn()
+                          }
+                          toggleAllExpansion={
+                            toolActions?.toggleAllExpansion ?? vi.fn()
+                          }
                         >
                           <AskUserActionsProvider
                             request={null}

packages/cli/src/ui/AppContainer.tsx

@@ -83,6 +83,7 @@ import {
   logBillingEvent,
   ApiKeyUpdatedEvent,
   type InjectionSource,
+  startMemoryService,
 } from '@google/gemini-cli-core';
 import { validateAuthMethod } from '../config/auth.js';
 import process from 'node:process';
@@ -168,6 +169,7 @@ import { useSuspend } from './hooks/useSuspend.js';
 import { useRunEventNotifications } from './hooks/useRunEventNotifications.js';
 import { isNotificationsEnabled } from '../utils/terminalNotifications.js';
 import {
+  getLastTurnToolCallIds,
   isToolExecuting,
   isToolAwaitingConfirmation,
   getAllToolCalls,
@@ -238,6 +240,39 @@ export const AppContainer = (props: AppContainerProps) => {
 
   const [adminSettingsChanged, setAdminSettingsChanged] = useState(false);
 
+  const [expandedTools, setExpandedTools] = useState<Set<string>>(new Set());
+
+  const toggleExpansion = useCallback((callId: string) => {
+    setExpandedTools((prev) => {
+      const next = new Set(prev);
+      if (next.has(callId)) {
+        next.delete(callId);
+      } else {
+        next.add(callId);
+      }
+      return next;
+    });
+  }, []);
+
+  const toggleAllExpansion = useCallback((callIds: string[]) => {
+    setExpandedTools((prev) => {
+      const next = new Set(prev);
+      const anyCollapsed = callIds.some((id) => !next.has(id));
+
+      if (anyCollapsed) {
+        callIds.forEach((id) => next.add(id));
+      } else {
+        callIds.forEach((id) => next.delete(id));
+      }
+      return next;
+    });
+  }, []);
+
+  const isExpanded = useCallback(
+    (callId: string) => expandedTools.has(callId),
+    [expandedTools],
+  );
+
   const [shellModeActive, setShellModeActive] = useState(false);
   const [modelSwitchedFromQuotaError, setModelSwitchedFromQuotaError] =
     useState<boolean>(false);
@@ -413,6 +448,13 @@ export const AppContainer = (props: AppContainerProps) => {
       setConfigInitialized(true);
       startupProfiler.flush(config);
 
+      // Fire-and-forget memory service (skill extraction from past sessions)
+      if (config.isMemoryManagerEnabled()) {
+        startMemoryService(config).catch((e) => {
+          debugLogger.error('Failed to start memory service:', e);
+        });
+      }
+
       const sessionStartSource = resumedSessionData
         ? SessionStartSource.Resume
         : SessionStartSource.Startup;
@@ -992,7 +1034,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       let fileCount: number;
 
       if (config.isJitContextEnabled()) {
-        await config.getContextManager()?.refresh();
+        await config.getMemoryContextManager()?.refresh();
+        config.updateSystemInstructionIfInitialized();
         flattenedMemory = flattenMemory(config.getUserMemory());
         fileCount = config.getGeminiMdFileCount();
       } else {
@@ -1137,11 +1180,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
     [pendingSlashCommandHistoryItems, pendingGeminiHistoryItems],
   );
 
-  const hasPendingToolConfirmation = useMemo(
-    () => isToolAwaitingConfirmation(pendingHistoryItems),
-    [pendingHistoryItems],
-  );
-
   toggleBackgroundTasksRef.current = toggleBackgroundTasks;
   isBackgroundTaskVisibleRef.current = isBackgroundTaskVisible;
   backgroundTasksRef.current = backgroundTasks;
@@ -1392,8 +1430,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     (streamingState === StreamingState.Idle ||
       streamingState === StreamingState.Responding ||
       streamingState === StreamingState.WaitingForConfirmation) &&
-    !proQuotaRequest &&
-    !copyModeEnabled;
+    !proQuotaRequest;
 
   const observerRef = useRef<ResizeObserver | null>(null);
   const [controlsHeight, setControlsHeight] = useState(0);
@@ -1727,13 +1764,25 @@ Logging in with Google... Restarting Gemini CLI to continue.
         return true;
       }
 
+      const toggleLastTurnTools = () => {
+        triggerExpandHint(true);
+
+        const targetToolCallIds = getLastTurnToolCallIds(
+          historyManager.history,
+          pendingHistoryItems,
+        );
+
+        if (targetToolCallIds.length > 0) {
+          toggleAllExpansion(targetToolCallIds);
+        }
+      };
+
       let enteringConstrainHeightMode = false;
       if (!constrainHeight) {
         enteringConstrainHeightMode = true;
         setConstrainHeight(true);
         if (keyMatchers[Command.SHOW_MORE_LINES](key)) {
-          // If the user manually collapses the view, show the hint and reset the x-second timer.
-          triggerExpandHint(true);
+          toggleLastTurnTools();
         }
         if (!isAlternateBuffer) {
           refreshStatic();
@@ -1781,11 +1830,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
         !enteringConstrainHeightMode
       ) {
         setConstrainHeight(false);
-        // If the user manually expands the view, show the hint and reset the x-second timer.
-        triggerExpandHint(true);
-        if (!isAlternateBuffer) {
-          refreshStatic();
-        }
+        toggleLastTurnTools();
+        refreshStatic();
         return true;
       } else if (
         (keyMatchers[Command.FOCUS_SHELL_INPUT](key) ||
@@ -1890,6 +1936,9 @@ Logging in with Google... Restarting Gemini CLI to continue.
       triggerExpandHint,
       keyMatchers,
       isHelpDismissKey,
+      historyManager.history,
+      pendingHistoryItems,
+      toggleAllExpansion,
     ],
   );
 
@@ -2033,6 +2082,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
     authState === AuthState.AwaitingApiKeyInput ||
     !!newAgents;
 
+  const hasPendingToolConfirmation = useMemo(
+    () => isToolAwaitingConfirmation(pendingHistoryItems),
+    [pendingHistoryItems],
+  );
+
   const hasConfirmUpdateExtensionRequests =
     confirmUpdateExtensionRequests.length > 0;
   const hasLoopDetectionConfirmationRequest =
@@ -2639,7 +2693,13 @@ Logging in with Google... Restarting Gemini CLI to continue.
               startupWarnings: props.startupWarnings || [],
             }}
           >
-            <ToolActionsProvider config={config} toolCalls={allToolCalls}>
+            <ToolActionsProvider
+              config={config}
+              toolCalls={allToolCalls}
+              isExpanded={isExpanded}
+              toggleExpansion={toggleExpansion}
+              toggleAllExpansion={toggleAllExpansion}
+            >
               <ShellFocusContext.Provider value={isFocused}>
                 <App key={`app-${forceRerenderKey}`} />
               </ShellFocusContext.Provider>

packages/cli/src/ui/__snapshots__/ToolConfirmationFullFrame-Full-Terminal-Tool-Confirmation-Snapshot-renders-tool-confirmation-box-in-the-frame-of-the-entire-terminal.snap.svg

@@ -4,16 +4,14 @@
   </style>
   <rect width="920" height="666" fill="#000000" />
   <g transform="translate(10, 10)">
-    <rect x="0" y="0" width="900" height="17" fill="#141414" />
-    <text x="0" y="2" fill="#000000" textLength="900" lengthAdjust="spacingAndGlyphs">▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀</text>
-    <rect x="0" y="17" width="9" height="17" fill="#141414" />
-    <rect x="9" y="17" width="18" height="17" fill="#141414" />
-    <text x="9" y="19" fill="#d7afff" textLength="18" lengthAdjust="spacingAndGlyphs">&gt; </text>
-    <rect x="27" y="17" width="324" height="17" fill="#141414" />
-    <text x="27" y="19" fill="#ffffff" textLength="324" lengthAdjust="spacingAndGlyphs">Can you edit InputPrompt.tsx for me?</text>
-    <rect x="351" y="17" width="549" height="17" fill="#141414" />
-    <rect x="0" y="34" width="900" height="17" fill="#141414" />
-    <text x="0" y="36" fill="#000000" textLength="900" lengthAdjust="spacingAndGlyphs">▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄</text>
+    <rect x="0" y="0" width="9" height="17" fill="#141414" />
+    <rect x="9" y="0" width="18" height="17" fill="#141414" />
+    <text x="9" y="2" fill="#d7afff" textLength="18" lengthAdjust="spacingAndGlyphs">&gt; </text>
+    <rect x="27" y="0" width="324" height="17" fill="#141414" />
+    <text x="27" y="2" fill="#ffffff" textLength="324" lengthAdjust="spacingAndGlyphs">Can you edit InputPrompt.tsx for me?</text>
+    <rect x="351" y="0" width="549" height="17" fill="#141414" />
+    <rect x="0" y="17" width="900" height="17" fill="#141414" />
+    <text x="0" y="19" fill="#000000" textLength="900" lengthAdjust="spacingAndGlyphs">▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄</text>
     <text x="0" y="53" fill="#ffffaf" textLength="891" lengthAdjust="spacingAndGlyphs">╭─────────────────────────────────────────────────────────────────────────────────────────────────╮</text>
     <text x="0" y="70" fill="#ffffaf" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
     <text x="18" y="70" fill="#ffffaf" textLength="135" lengthAdjust="spacingAndGlyphs" font-weight="bold">Action Required</text>
@@ -55,7 +53,7 @@
     <text x="198" y="189" fill="#0000ee" textLength="36" lengthAdjust="spacingAndGlyphs">true</text>
     <text x="234" y="189" fill="#00cd00" textLength="9" lengthAdjust="spacingAndGlyphs">;</text>
     <text x="882" y="189" fill="#ffffaf" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
-    <text x="891" y="189" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">█</text>
+    <text x="891" y="189" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">▄</text>
     <text x="0" y="206" fill="#ffffaf" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
     <text x="18" y="206" fill="#afafaf" textLength="18" lengthAdjust="spacingAndGlyphs">48</text>
     <text x="63" y="206" fill="#e5e5e5" textLength="54" lengthAdjust="spacingAndGlyphs">const </text>

packages/cli/src/ui/__snapshots__/ToolConfirmationFullFrame.test.tsx.snap

@@ -1,9 +1,9 @@
 // Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
 
 exports[`Full Terminal Tool Confirmation Snapshot > renders tool confirmation box in the frame of the entire terminal 1`] = `
-"▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
- > Can you edit InputPrompt.tsx for me?                                                             
+" > Can you edit InputPrompt.tsx for me?                                                             
 ▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
+
 ╭─────────────────────────────────────────────────────────────────────────────────────────────────╮
 │ Action Required                                                                                 │
 │                                                                                                 │
@@ -12,7 +12,7 @@ exports[`Full Terminal Tool Confirmation Snapshot > renders tool confirmation bo
 │ ... first 44 lines hidden (Ctrl+O to show) ...                                                  │
 │ 45   const line45 = true;                                                                       │
 │ 46   const line46 = true;                                                                       │
-│ 47   const line47 = true;                                                                       │█
+│ 47   const line47 = true;                                                                       │▄
 │ 48   const line48 = true;                                                                       │█
 │ 49   const line49 = true;                                                                       │█
 │ 50   const line50 = true;                                                                       │█

packages/cli/src/ui/commands/chatCommand.ts

@@ -65,7 +65,7 @@ const getSavedChatTags = async (
     );
 
     return chatDetails;
-  } catch (_err) {
+  } catch {
     return [];
   }
 };

packages/cli/src/ui/commands/directoryCommand.tsx

@@ -198,7 +198,7 @@ export const directoryCommand: SlashCommand = {
               alreadyAdded.push(trimmedPath);
               continue;
             }
-          } catch (_e) {
+          } catch {
             // Path might not exist or be inaccessible.
             // We'll let batchAddDirectories handle it later.
           }

packages/cli/src/ui/commands/extensionsCommand.ts

@@ -321,7 +321,7 @@ async function exploreAction(
     });
     try {
       await open(extensionsUrl);
-    } catch (_error) {
+    } catch {
       context.ui.addItem({
         type: MessageType.ERROR,
         text: `Failed to open browser. Check out the extensions gallery at ${extensionsUrl}`,

packages/cli/src/ui/commands/restoreCommand.ts

@@ -151,7 +151,7 @@ async function completion(
     const files = await fs.readdir(checkpointDir);
     const jsonFiles = files.filter((file) => file.endsWith('.json'));
     return getTruncatedCheckpointNames(jsonFiles);
-  } catch (_err) {
+  } catch {
     return [];
   }
 }

packages/cli/src/ui/commands/rewindCommand.test.tsx

@@ -106,7 +106,7 @@ describe('rewindCommand', () => {
           },
           config: {
             getSessionId: () => 'test-session-id',
-            getContextManager: () => ({ refresh: mockResetContext }),
+            getMemoryContextManager: () => ({ refresh: mockResetContext }),
             getProjectRoot: mockGetProjectRoot,
           },
         },

packages/cli/src/ui/commands/rewindCommand.tsx

@@ -61,7 +61,9 @@ async function rewindConversation(
     client.setHistory(clientHistory as Content[]);
 
     // Reset context manager as we are rewinding history
-    await context.services.agentContext?.config.getContextManager()?.refresh();
+    await context.services.agentContext?.config
+      .getMemoryContextManager()
+      ?.refresh();
 
     // Update UI History
     // We generate IDs based on index for the rewind history

packages/cli/src/ui/commands/setupGithubCommand.ts

@@ -76,7 +76,7 @@ export async function updateGitignore(gitRepoRoot: string): Promise<void> {
     let fileExists = true;
     try {
       existingContent = await fs.promises.readFile(gitignorePath, 'utf8');
-    } catch (_error) {
+    } catch {
       // File doesn't exist
       fileExists = false;
     }
@@ -168,8 +168,8 @@ async function downloadFiles({
 async function createDirectory(dirPath: string): Promise<void> {
   try {
     await fs.promises.mkdir(dirPath, { recursive: true });
-  } catch (_error) {
-    debugLogger.debug(`Failed to create ${dirPath} directory:`, _error);
+  } catch (error) {
+    debugLogger.debug(`Failed to create ${dirPath} directory:`, error);
     throw new Error(
       `Unable to create ${dirPath} directory. Do you have file permissions in the current directory?`,
     );
@@ -222,8 +222,8 @@ export const setupGithubCommand: SlashCommand = {
     let gitRepoRoot: string;
     try {
       gitRepoRoot = getGitRepoRoot();
-    } catch (_error) {
-      debugLogger.debug(`Failed to get git repo root:`, _error);
+    } catch (error) {
+      debugLogger.debug(`Failed to get git repo root:`, error);
       throw new Error(
         'Unable to determine the GitHub repository. /setup-github must be run from a git repository.',
       );

packages/cli/src/ui/commands/skillsCommand.test.ts

@@ -528,6 +528,7 @@ describe('skillsCommand', () => {
       await actionPromise;
 
       expect(reloadSkillsMock).toHaveBeenCalled();
+      expect(context.ui.reloadCommands).toHaveBeenCalled();
       expect(context.ui.setPendingItem).toHaveBeenCalledWith(null);
       expect(context.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({

packages/cli/src/ui/commands/skillsCommand.ts

@@ -285,6 +285,8 @@ async function reloadAction(
       context.ui.setPendingItem(null);
     }
 
+    context.ui.reloadCommands();
+
     const afterSkills = skillManager.getSkills();
     const afterNames = new Set(afterSkills.map((s) => s.name));
 

packages/cli/src/ui/components/AnsiOutput.test.tsx

@@ -156,4 +156,30 @@ describe('<AnsiOutputText />', () => {
     expect(lastFrame()).toBeDefined();
     unmount();
   });
+
+  describe('robustness', () => {
+    it('does NOT crash when data is undefined', async () => {
+      const { lastFrame, unmount } = await render(
+        <AnsiOutputText
+          data={undefined as unknown as AnsiOutput}
+          width={80}
+          disableTruncation={true}
+        />,
+      );
+      expect(lastFrame({ allowEmpty: true }).trim()).toBe('');
+      unmount();
+    });
+
+    it('does NOT crash when data is an object but not an array', async () => {
+      const { lastFrame, unmount } = await render(
+        <AnsiOutputText
+          data={{ summary: 'test' } as unknown as AnsiOutput}
+          width={80}
+          disableTruncation={true}
+        />,
+      );
+      expect(lastFrame({ allowEmpty: true }).trim()).toBe('');
+      unmount();
+    });
+  });
 });

packages/cli/src/ui/components/AnsiOutput.tsx

@@ -35,14 +35,16 @@ export const AnsiOutputText: React.FC<AnsiOutputProps> = ({
       ? Math.min(availableHeightLimit, maxLines)
       : (availableHeightLimit ?? maxLines ?? DEFAULT_HEIGHT);
 
-  const lastLines = disableTruncation
-    ? data
-    : numLinesRetained === 0
-      ? []
-      : data.slice(-numLinesRetained);
+  const lastLines = Array.isArray(data)
+    ? disableTruncation
+      ? data
+      : numLinesRetained === 0
+        ? []
+        : data.slice(-numLinesRetained)
+    : [];
   return (
     <Box flexDirection="column" width={width} flexShrink={0} overflow="hidden">
-      {lastLines.map((line: AnsiLine, lineIndex: number) => (
+      {(lastLines as AnsiLine[]).map((line: AnsiLine, lineIndex: number) => (
         <Box key={lineIndex} height={1} overflow="hidden">
           <AnsiLineText line={line} />
         </Box>

packages/cli/src/ui/components/Composer.tsx

@@ -172,9 +172,7 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
 
       {showUiDetails &&
         !settings.merged.ui.hideFooter &&
-        !isScreenReaderEnabled && (
-          <Footer copyModeEnabled={uiState.copyModeEnabled} />
-        )}
+        !isScreenReaderEnabled && <Footer />}
     </Box>
   );
 };